APi test

* Non blocking improvements

* Test fix

* Background thread re-queue

* Nonblockimg improvements, run tasks in background, add warning about CPU cores

* Misc fixes

.dockerignore

@@ -29,3 +29,34 @@ venv/
 
 # Visual Studio
 .vscode/
+
+# Test and development files
+test-datastore/
+tests/
+*.md
+!README.md
+
+# Temporary and log files
+*.log
+*.tmp
+tmp/
+temp/
+
+# Training data and large files
+train-data/
+works-data/
+
+# Container files
+Dockerfile*
+docker-compose*.yml
+.dockerignore
+
+# Development certificates and keys
+*.pem
+*.key
+*.crt
+profile_output.prof
+
+# Large binary files that shouldn't be in container
+*.pdf
+chrome.json

.github/actions/extract-memory-report/action.yml

@@ -0,0 +1,51 @@
+name: 'Extract Memory Test Report'
+description: 'Extracts and displays memory test report from a container'
+inputs:
+  container-name:
+    description: 'Name of the container to extract logs from'
+    required: true
+  python-version:
+    description: 'Python version for artifact naming'
+    required: true
+  output-dir:
+    description: 'Directory to store output logs'
+    required: false
+    default: 'output-logs'
+
+runs:
+  using: "composite"
+  steps:
+    - name: Create output directory
+      shell: bash
+      run: |
+        mkdir -p ${{ inputs.output-dir }}
+
+    - name: Dump container log
+      shell: bash
+      run: |
+        echo "Disabled for now"
+#        return
+#        docker logs ${{ inputs.container-name }} > ${{ inputs.output-dir }}/${{ inputs.container-name }}-stdout-${{ inputs.python-version }}.txt 2>&1 || echo "Could not get stdout"
+#        docker logs ${{ inputs.container-name }} 2> ${{ inputs.output-dir }}/${{ inputs.container-name }}-stderr-${{ inputs.python-version }}.txt || echo "Could not get stderr"
+
+    - name: Extract and display memory test report
+      shell: bash
+      run: |
+        echo "Disabled for now"
+#        echo "Extracting test-memory.log from container..."
+#        docker cp ${{ inputs.container-name }}:/app/changedetectionio/test-memory.log ${{ inputs.output-dir }}/test-memory-${{ inputs.python-version }}.log || echo "test-memory.log not found in container"
+#
+#        echo "=== Top 10 Highest Peak Memory Tests ==="
+#        if [ -f ${{ inputs.output-dir }}/test-memory-${{ inputs.python-version }}.log ]; then
+#          grep "Peak memory:" ${{ inputs.output-dir }}/test-memory-${{ inputs.python-version }}.log | \
+#            sed 's/.*Peak memory: //' | \
+#            paste -d'|' - <(grep "Peak memory:" ${{ inputs.output-dir }}/test-memory-${{ inputs.python-version }}.log) | \
+#            sort -t'|' -k1 -nr | \
+#            cut -d'|' -f2 | \
+#            head -10
+#          echo ""
+#          echo "=== Full Memory Test Report ==="
+#          cat ${{ inputs.output-dir }}/test-memory-${{ inputs.python-version }}.log
+#        else
+#          echo "No memory log available"
+#        fi

.github/dependabot.yml

@@ -4,11 +4,11 @@ updates:
     directory: /
     schedule:
       interval: "weekly"
-    "caronc/apprise":
-      versioning-strategy: "increase"
-      schedule:
-        interval: "daily"
     groups:
       all:
         patterns:
         - "*"
+  - package-ecosystem: pip
+    directory: /
+    schedule:
+      interval: "weekly"

.github/nginx-reverse-proxy-test.conf

@@ -0,0 +1,33 @@
+server {
+    listen 80;
+    server_name localhost;
+
+    # Test basic reverse proxy to changedetection.io
+    location / {
+        proxy_pass http://changedet-app:5000;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+
+        # WebSocket support
+        proxy_http_version 1.1;
+        proxy_set_header Upgrade $http_upgrade;
+        proxy_set_header Connection "upgrade";
+    }
+
+    # Test subpath deployment with X-Forwarded-Prefix
+    location /changedet-sub/ {
+        proxy_pass http://changedet-app:5000/;
+        proxy_set_header X-Forwarded-Prefix /changedet-sub;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+
+        # WebSocket support
+        proxy_http_version 1.1;
+        proxy_set_header Upgrade $http_upgrade;
+        proxy_set_header Connection "upgrade";
+    }
+}

.github/test/Dockerfile-alpine

@@ -2,11 +2,13 @@
 # Test that we can still build on Alpine (musl modified libc https://musl.libc.org/)
 # Some packages wont install via pypi because they dont have a wheel available under this architecture.
 
-FROM ghcr.io/linuxserver/baseimage-alpine:3.21
+FROM ghcr.io/linuxserver/baseimage-alpine:3.22
 ENV PYTHONUNBUFFERED=1
 
 COPY requirements.txt /requirements.txt
 
+ARG TARGETPLATFORM
+
 RUN \
  apk add --update --no-cache --virtual=build-dependencies \
     build-base \
@@ -18,17 +20,31 @@ RUN \
     libxslt-dev \
     openssl-dev \
     python3-dev \
+    file \
     zip \
     zlib-dev && \
   apk add --update --no-cache \
     libjpeg \
     libxslt \
+    file \
     nodejs \
     poppler-utils \
-    python3 && \
+    python3 \
+    glib \
+    libsm \
+    libxext \
+    libxrender && \
+  case "$TARGETPLATFORM" in \
+    linux/arm/v7|linux/arm/v8) \
+      echo "INFO: Skipping py3-opencv on $TARGETPLATFORM (using pixelmatch fallback)" \
+      ;; \
+    *) \
+      apk add --update --no-cache py3-opencv || echo "WARN: py3-opencv install failed, using pixelmatch fallback" \
+      ;; \
+  esac && \
   echo "**** pip3 install test of changedetection.io ****" && \
   python3 -m venv /lsiopy  && \
   pip install -U pip wheel setuptools && \
-  pip install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.21/ -r /requirements.txt && \
+  pip install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.22/ -r /requirements.txt && \
   apk del --purge \
     build-dependencies

.github/workflows/codeql-analysis.yml

@@ -30,11 +30,11 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@v6
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@v4
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -45,7 +45,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v3
+      uses: github/codeql-action/autobuild@v4
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -59,4 +59,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@v4

.github/workflows/containers.yml

@@ -39,12 +39,20 @@ jobs:
     # Or if we are in a tagged release scenario.
     if: ${{ github.event.workflow_run.conclusion == 'success' }} || ${{ github.event.release.tag_name }} != ''
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - name: Set up Python 3.11
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: 3.11
 
+      - name: Cache pip packages
+        uses: actions/cache@v5
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
@@ -85,17 +93,28 @@ jobs:
           driver-opts: image=moby/buildkit:master
 
       # master branch -> :dev container tag
+      - name: Docker meta :dev
+        if: ${{ github.ref == 'refs/heads/master' && github.event_name != 'release' }}
+        uses: docker/metadata-action@v5
+        id: meta_dev
+        with:
+          images: |
+            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io
+            ghcr.io/${{ github.repository }}
+          tags: |
+            type=raw,value=dev
+
       - name: Build and push :dev
         id: docker_build
-        if: ${{ github.ref }} == "refs/heads/master"
+        if: ${{ github.ref == 'refs/heads/master' && github.event_name != 'release' }}
         uses: docker/build-push-action@v6
         with:
           context: ./
           file: ./Dockerfile
           push: true
-          tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
-          platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/v8
+          tags: ${{ steps.meta_dev.outputs.tags }}
+          labels: ${{ steps.meta_dev.outputs.labels }}
+          platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8
           cache-from: type=gha
           cache-to: type=gha,mode=max
 
@@ -103,6 +122,13 @@ jobs:
 #          provenance: false
 
       # A new tagged release is required, which builds :tag and :latest
+      - name: Debug release info
+        if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
+        run: |
+          echo "Release tag: ${{ github.event.release.tag_name }}"
+          echo "Github ref: ${{ github.ref }}"
+          echo "Github ref name: ${{ github.ref_name }}"
+          
       - name: Docker meta :tag
         if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
         uses: docker/metadata-action@v5
@@ -112,9 +138,10 @@ jobs:
                 ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io
                 ghcr.io/dgtlmoon/changedetection.io
             tags: |
-                type=semver,pattern={{version}}
-                type=semver,pattern={{major}}.{{minor}}
-                type=semver,pattern={{major}}
+                type=semver,pattern={{version}},value=${{ github.event.release.tag_name }}
+                type=semver,pattern={{major}}.{{minor}},value=${{ github.event.release.tag_name }}
+                type=semver,pattern={{major}},value=${{ github.event.release.tag_name }}
+                type=raw,value=latest
 
       - name: Build and push :tag
         id: docker_build_tag_release
@@ -125,7 +152,8 @@ jobs:
           file: ./Dockerfile
           push: true
           tags: ${{ steps.meta.outputs.tags }}
-          platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/v8
+          labels: ${{ steps.meta.outputs.labels }}
+          platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8
           cache-from: type=gha
           cache-to: type=gha,mode=max
 # Looks like this was disabled

.github/workflows/pypi-release.yml

@@ -7,9 +7,9 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v6
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v6
       with:
         python-version: "3.11"
     - name: Install pypa/build
@@ -21,39 +21,60 @@ jobs:
     - name: Build a binary wheel and a source tarball
       run: python3 -m build
     - name: Store the distribution packages
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v6
       with:
         name: python-package-distributions
         path: dist/
 
 
   test-pypi-package:
-    name: Test the built 📦 package works basically.
+    name: Test the built package works basically.
     runs-on: ubuntu-latest
     needs:
     - build
     steps:
     - name: Download all the dists
-      uses: actions/download-artifact@v4
+      uses: actions/download-artifact@v7
       with:
         name: python-package-distributions
         path: dist/
     - name: Set up Python 3.11
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v6
       with:
         python-version: '3.11'
+
     - name: Test that the basic pip built package runs without error
       run: |
         set -ex
         ls -alR 
         
-        # Find and install the first .whl file
-        find dist -type f -name "*.whl" -exec pip3 install {} \; -quit
+        # Install the first wheel found in dist/
+        WHEEL=$(find dist -type f -name "*.whl" -print -quit)
+        echo Installing $WHEEL
+        python3 -m pip install --upgrade pip
+        python3 -m pip install "$WHEEL"
         changedetection.io -d /tmp -p 10000 &
         
         sleep 3
         curl --retry-connrefused --retry 6 http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
         curl --retry-connrefused --retry 6 http://127.0.0.1:10000/ >/dev/null
+        
+        # --- API test ---
+        # This also means that the docs/api-spec.yml was shipped and could be read
+        test -f /tmp/changedetection.json
+        API_KEY=$(jq -r '.. | .api_access_token? // empty' /tmp/changedetection.json)
+        echo Test API KEY is $API_KEY
+        curl -X POST "http://127.0.0.1:10000/api/v1/watch" \
+          -H "x-api-key: ${API_KEY}" \
+          -H "Content-Type: application/json" \
+          --show-error --fail \
+          --retry 6 --retry-delay 1 --retry-connrefused \
+          -d '{
+            "url": "https://example.com",
+            "title": "Example Site Monitor",
+            "time_between_check": { "hours": 1 }
+          }'
+          
         killall changedetection.io
 
 
@@ -72,7 +93,7 @@ jobs:
 
     steps:
     - name: Download all the dists
-      uses: actions/download-artifact@v4
+      uses: actions/download-artifact@v7
       with:
         name: python-package-distributions
         path: dist/

.github/workflows/test-container-build.yml

@@ -23,15 +23,41 @@ on:
   # Changes to requirements.txt packages and Dockerfile may or may not always be compatible with arm etc, so worth testing
   # @todo: some kind of path filter for requirements.txt and Dockerfile
 jobs:
-  test-container-build:
+  builder:
+    name: Build ${{ matrix.platform }} (${{ matrix.dockerfile == './Dockerfile' && 'main' || 'alpine' }})
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          # Main Dockerfile platforms
+          - platform: linux/amd64
+            dockerfile: ./Dockerfile
+          - platform: linux/arm64
+            dockerfile: ./Dockerfile
+          - platform: linux/arm/v7
+            dockerfile: ./Dockerfile
+          - platform: linux/arm/v8
+            dockerfile: ./Dockerfile
+          # Alpine Dockerfile platforms (musl via alpine check)
+          - platform: linux/amd64
+            dockerfile: ./.github/test/Dockerfile-alpine
+          - platform: linux/arm64
+            dockerfile: ./.github/test/Dockerfile-alpine
     steps:
-        - uses: actions/checkout@v4
+        - uses: actions/checkout@v6
         - name: Set up Python 3.11
-          uses: actions/setup-python@v5
+          uses: actions/setup-python@v6
           with:
             python-version: 3.11
 
+        - name: Cache pip packages
+          uses: actions/cache@v5
+          with:
+            path: ~/.cache/pip
+            key: ${{ runner.os }}-pip-${{ hashFiles('requirements.txt') }}
+            restore-keys: |
+              ${{ runner.os }}-pip-
+
         # Just test that the build works, some libraries won't compile on ARM/rPi etc
         - name: Set up QEMU
           uses: docker/setup-qemu-action@v3
@@ -47,24 +73,14 @@ jobs:
             version: latest
             driver-opts: image=moby/buildkit:master
 
-        # https://github.com/dgtlmoon/changedetection.io/pull/1067
-        # Check we can still build under alpine/musl
-        - name: Test that the docker containers can build (musl via alpine check)
-          id: docker_build_musl
-          uses: docker/build-push-action@v6
-          with:
-            context: ./
-            file: ./.github/test/Dockerfile-alpine
-            platforms: linux/amd64,linux/arm64
-
-        - name: Test that the docker containers can build
+        - name: Test that the docker containers can build (${{ matrix.platform }} - ${{ matrix.dockerfile }})
           id: docker_build
           uses: docker/build-push-action@v6
           # https://github.com/docker/build-push-action#customizing
           with:
             context: ./
-            file: ./Dockerfile
-            platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/v8
-            cache-from: type=local,src=/tmp/.buildx-cache
-            cache-to: type=local,dest=/tmp/.buildx-cache
+            file: ${{ matrix.dockerfile }}
+            platforms: ${{ matrix.platform }}
+            cache-from: type=gha
+            cache-to: type=gha,mode=max
 

.github/workflows/test-only.yml

@@ -7,7 +7,7 @@ jobs:
   lint-code:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - name: Lint with Ruff
         run: |
           pip install ruff
@@ -15,8 +15,14 @@ jobs:
           ruff check . --select E9,F63,F7,F82
           # Complete check with errors treated as warnings
           ruff check . --exit-zero
+      - name: Validate OpenAPI spec
+        run: |
+          pip install openapi-spec-validator
+          python3 -c "from openapi_spec_validator import validate_spec; import yaml; validate_spec(yaml.safe_load(open('docs/api-spec.yaml')))"
 
   test-application-3-10:
+    # Only run on push to master (including PR merges)
+    if: github.event_name == 'push' && github.ref == 'refs/heads/master'
     needs: lint-code
     uses: ./.github/workflows/test-stack-reusable-workflow.yml
     with:
@@ -24,12 +30,15 @@ jobs:
 
 
   test-application-3-11:
+    # Always run
     needs: lint-code
     uses: ./.github/workflows/test-stack-reusable-workflow.yml
     with:
       python-version: '3.11'
 
   test-application-3-12:
+    # Only run on push to master (including PR merges)
+    if: github.event_name == 'push' && github.ref == 'refs/heads/master'
     needs: lint-code
     uses: ./.github/workflows/test-stack-reusable-workflow.yml
     with:
@@ -37,6 +46,8 @@ jobs:
       skip-pypuppeteer: true
 
   test-application-3-13:
+    # Only run on push to master (including PR merges)
+    if: github.event_name == 'push' && github.ref == 'refs/heads/master'
     needs: lint-code
     uses: ./.github/workflows/test-stack-reusable-workflow.yml
     with:

.github/workflows/test-stack-reusable-workflow.yml

@@ -15,138 +15,516 @@ on:
         default: false
 
 jobs:
-  test-application:
+  # Build the Docker image once and share it with all test jobs
+  build:
     runs-on: ubuntu-latest
     env:
       PYTHON_VERSION: ${{ inputs.python-version }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
 
-      # Mainly just for link/flake8
       - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 
+      - name: Cache pip packages
+        uses: actions/cache@v5
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-py${{ env.PYTHON_VERSION }}-${{ hashFiles('requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-py${{ env.PYTHON_VERSION }}-
+            ${{ runner.os }}-pip-
+
+      - name: Get current date for cache key
+        id: date
+        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
       - name: Build changedetection.io container for testing under Python ${{ env.PYTHON_VERSION }}
+        uses: docker/build-push-action@v6
+        with:
+          context: ./
+          file: ./Dockerfile
+          build-args: |
+            PYTHON_VERSION=${{ env.PYTHON_VERSION }}
+            LOGGER_LEVEL=TRACE
+          tags: test-changedetectionio
+          load: true
+          cache-from: type=gha,scope=build-${{ github.ref_name }}-py${{ env.PYTHON_VERSION }}-${{ hashFiles('requirements.txt', 'Dockerfile') }}-${{ steps.date.outputs.date }}
+          cache-to: type=gha,mode=max,scope=build-${{ github.ref_name }}-py${{ env.PYTHON_VERSION }}-${{ hashFiles('requirements.txt', 'Dockerfile') }}-${{ steps.date.outputs.date }}
+
+      - name: Verify build
         run: |
-          echo "---- Building for Python ${{ env.PYTHON_VERSION }} -----"
-          # Build a changedetection.io container and start testing inside
-          docker build --build-arg PYTHON_VERSION=${{ env.PYTHON_VERSION }} --build-arg LOGGER_LEVEL=TRACE -t test-changedetectionio .
-          # Debug info
-          docker run test-changedetectionio  bash -c 'pip list'         
+          echo "---- Built for Python ${{ env.PYTHON_VERSION }} -----"
+          docker run test-changedetectionio bash -c 'pip list'
 
       - name: We should be Python ${{ env.PYTHON_VERSION }} ...
-        run: |         
-          docker run test-changedetectionio  bash -c 'python3 --version'
-
-      - name: Spin up ancillary testable services
         run: |
-          
-          docker network create changedet-network
-          
-          # Selenium
-          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome:4
-          
-          # SocketPuppetBrowser + Extra for custom browser test
-          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser --hostname sockpuppetbrowser --rm -p 3000:3000 dgtlmoon/sockpuppetbrowser:latest                    
-          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser-custom-url --hostname sockpuppetbrowser-custom-url  -p 3001:3000 --rm dgtlmoon/sockpuppetbrowser:latest
+          docker run test-changedetectionio bash -c 'python3 --version'
 
-      - name: Spin up ancillary SMTP+Echo message test server
+      - name: Save Docker image
         run: |
-          # Debug SMTP server/echo message back server
-          docker run --network changedet-network -d -p 11025:11025 -p 11080:11080  --hostname mailserver test-changedetectionio  bash -c 'pip3 install aiosmtpd && python changedetectionio/tests/smtp/smtp-test-server.py'
-          docker ps
+          docker save test-changedetectionio -o /tmp/test-changedetectionio.tar
 
-      - name: Show docker container state and other debug info
+      - name: Upload Docker image artifact
+        uses: actions/upload-artifact@v6
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp/test-changedetectionio.tar
+          retention-days: 1
+
+  # Unit tests (lightweight, no ancillary services needed)
+  unit-tests:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 10
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Download Docker image artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp
+
+      - name: Load Docker image
         run: |
-          set -x
-          echo "Running processes in docker..."
-          docker ps
+          docker load -i /tmp/test-changedetectionio.tar
 
       - name: Run Unit Tests
         run: |
-          # Unit tests
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_watch_model'
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_jinja2_security'
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_semver'
+          docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
+          docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_watch_model'
+          docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_jinja2_security'
+          docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_semver'
+          docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_html_to_text'         
 
-      - name: Test built container with Pytest (generally as requests/plaintext fetching)
+  # Basic pytest tests with ancillary services
+  basic-tests:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 25
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Download Docker image artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp
+
+      - name: Load Docker image
         run: |
-          # All tests
-          echo "run test with pytest"
-          # The default pytest logger_level is TRACE
-          # To change logger_level for pytest(test/conftest.py),
-          # append the docker option. e.g. '-e LOGGER_LEVEL=DEBUG'
-          docker run --name test-cdio-basic-tests --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio && ./run_basic_tests.sh'
+          docker load -i /tmp/test-changedetectionio.tar
 
-# PLAYWRIGHT/NODE-> CDP
-      - name: Playwright and SocketPuppetBrowser - Specific tests in built container
+      - name: Test built container with Pytest
         run: |
-          # Playwright via Sockpuppetbrowser fetch
-          # tests/visualselector/test_fetch_data.py will do browser steps  
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
+          docker network inspect changedet-network >/dev/null 2>&1 || docker network create changedet-network
+          docker run --name test-cdio-basic-tests --network changedet-network test-changedetectionio bash -c 'cd changedetectionio && ./run_basic_tests.sh'
 
-
-      - name: Playwright and SocketPuppetBrowser - Headers and requests
-        run: |       
-          # Settings headers playwright tests - Call back in from Sockpuppetbrowser, check headers
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'find .; cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py; pwd;find .'
-
-      - name: Playwright and SocketPuppetBrowser - Restock detection
-        run: |                            
-          # restock detection via playwright - added name=changedet here so that playwright and sockpuppetbrowser can connect to it
-          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
-
-# STRAIGHT TO CDP
-      - name: Pyppeteer and SocketPuppetBrowser - Specific tests in built container
-        if: ${{ inputs.skip-pypuppeteer == false }}
+      - name: Test CLI options
         run: |
-          # Playwright via Sockpuppetbrowser fetch 
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
+          docker network inspect changedet-network >/dev/null 2>&1 || docker network create changedet-network
+          docker run --name test-cdio-cli-opts --network changedet-network test-changedetectionio bash -c 'changedetectionio/test_cli_opts.sh' &> cli-opts-output.txt
+          echo "=== CLI Options Test Output ==="
+          cat cli-opts-output.txt
 
-      - name: Pyppeteer and SocketPuppetBrowser - Headers and requests checks
-        if: ${{ inputs.skip-pypuppeteer == false }}
+      - name: CLI Memory Test
         run: |
-          # Settings headers playwright tests - Call back in from Sockpuppetbrowser, check headers
-          docker run --name "changedet" --hostname changedet --rm  -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
+          echo "=== Checking CLI batch mode memory usage ==="
+          # Extract RSS memory value from output
+          RSS_MB=$(grep -oP "Memory consumption before worker shutdown: RSS=\K[\d.]+" cli-opts-output.txt | head -1 || echo "0")
+          echo "RSS Memory: ${RSS_MB} MB"
 
-      - name: Pyppeteer and SocketPuppetBrowser - Restock detection
-        if: ${{ inputs.skip-pypuppeteer == false }}
-        run: |                            
-          # restock detection via playwright - added name=changedet here so that playwright and sockpuppetbrowser can connect to it
-          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet"  -e "FAST_PUPPETEER_CHROME_FETCHER=True"  -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
+          # Check if RSS is less than 100MB
+          if [ -n "$RSS_MB" ]; then
+            if (( $(echo "$RSS_MB < 100" | bc -l) )); then
+              echo "✓ Memory usage is acceptable: ${RSS_MB} MB < 100 MB"
+            else
+              echo "✗ Memory usage too high: ${RSS_MB} MB >= 100 MB"
+              exit 1
+            fi
+          else
+            echo "⚠ Could not extract memory usage, skipping check"
+          fi
+
+      - name: Extract memory report and logs
+        if: always()
+        uses: ./.github/actions/extract-memory-report
+        with:
+          container-name: test-cdio-basic-tests
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Store test artifacts
+        if: always()
+        uses: actions/upload-artifact@v6
+        with:
+          name: test-cdio-basic-tests-output-py${{ env.PYTHON_VERSION }}
+          path: output-logs
+
+      - name: Store CLI test output
+        if: always()
+        uses: actions/upload-artifact@v6
+        with:
+          name: test-cdio-cli-opts-output-py${{ env.PYTHON_VERSION }}
+          path: cli-opts-output.txt
+
+  # Playwright tests
+  playwright-tests:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 10
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Download Docker image artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp
+
+      - name: Load Docker image
+        run: |
+          docker load -i /tmp/test-changedetectionio.tar
+
+      - name: Spin up ancillary services
+        run: |
+          docker network create changedet-network
+          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser --hostname sockpuppetbrowser --rm -p 3000:3000 dgtlmoon/sockpuppetbrowser:latest
+          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser-custom-url --hostname sockpuppetbrowser-custom-url -p 3001:3000 --rm dgtlmoon/sockpuppetbrowser:latest
+
+      - name: Playwright - Specific tests in built container
+        run: |
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio bash -c 'cd changedetectionio;pytest -vv --capture=tee-sys --showlocals --tb=long --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio bash -c 'cd changedetectionio;pytest -vv --capture=tee-sys --showlocals --tb=long --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio bash -c 'cd changedetectionio;pytest -vv --capture=tee-sys --showlocals --tb=long --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio bash -c 'cd changedetectionio;pytest -vv --capture=tee-sys --showlocals --tb=long --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
+
+      - name: Playwright - Headers and requests
+        run: |
+          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000?dumpio=true" --network changedet-network test-changedetectionio bash -c 'find .; cd changedetectionio; pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_request.py; pwd;find .'
+
+      - name: Playwright - Restock detection
+        run: |
+          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
+
+  # Pyppeteer tests
+  pyppeteer-tests:
+    runs-on: ubuntu-latest
+    needs: build
+    if: ${{ inputs.skip-pypuppeteer == false }}
+    timeout-minutes: 10
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Download Docker image artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp
+
+      - name: Load Docker image
+        run: |
+          docker load -i /tmp/test-changedetectionio.tar
+
+      - name: Spin up ancillary services
+        run: |
+          docker network create changedet-network
+          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser --hostname sockpuppetbrowser --rm -p 3000:3000 dgtlmoon/sockpuppetbrowser:latest
+
+      - name: Pyppeteer - Specific tests in built container
+        run: |
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
+
+      - name: Pyppeteer - Headers and requests checks
+        run: |
+          docker run --name "changedet" --hostname changedet --rm -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000?dumpio=true" --network changedet-network test-changedetectionio bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_request.py'
+
+      - name: Pyppeteer - Restock detection
+        run: |
+          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
+
+  # Selenium tests
+  selenium-tests:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 10
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Download Docker image artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp
+
+      - name: Load Docker image
+        run: |
+          docker load -i /tmp/test-changedetectionio.tar
+
+      - name: Spin up ancillary services
+        run: |
+          docker network create changedet-network
+          docker run --network changedet-network -d --hostname selenium -p 4444:4444 --rm --shm-size="2g" selenium/standalone-chrome:4
+          sleep 3
+
+      - name: Specific tests for headers and requests checks with Selenium
+        run: |
+
+          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_request.py'
 
-# SELENIUM
       - name: Specific tests in built container for Selenium
         run: |
-          # Selenium fetch
-          docker run --rm -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py'
+          docker run --rm -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py'
 
-      - name: Specific tests in built container for headers and requests checks with Selenium
+
+  # SMTP tests
+  smtp-tests:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 10
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Download Docker image artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp
+
+      - name: Load Docker image
         run: |
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
+          docker load -i /tmp/test-changedetectionio.tar
+
+      - name: Spin up SMTP test server
+        run: |
+          docker network create changedet-network
+          docker run --network changedet-network -d -p 11025:11025 -p 11080:11080 --hostname mailserver test-changedetectionio bash -c 'pip3 install aiosmtpd && python changedetectionio/tests/smtp/smtp-test-server.py'
 
-# OTHER STUFF
       - name: Test SMTP notification mime types
         run: |
-          # SMTP content types - needs the 'Debug SMTP server/echo message back server' container from above
-          # "mailserver" hostname defined above
           docker run --rm --network changedet-network test-changedetectionio bash -c 'cd changedetectionio;pytest tests/smtp/test_notification_smtp.py'
 
-      # @todo Add a test via playwright/puppeteer
-      # squid with auth is tested in run_proxy_tests.sh -> tests/proxy_list/test_select_custom_proxy.py
-      - name: Test proxy squid style interaction
+  nginx-reverse-proxy:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 10
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Download Docker image artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp
+
+      - name: Load Docker image
+        run: |
+          docker load -i /tmp/test-changedetectionio.tar
+
+      - name: Spin up services
+        run: |
+          docker network create changedet-network
+
+          # Start changedetection.io container with X-Forwarded headers support
+          docker run --name changedet-app --hostname changedet-app --network changedet-network \
+            -e USE_X_SETTINGS=true \
+            -d test-changedetectionio
+          sleep 3
+
+      - name: Start nginx reverse proxy
+        run: |
+          # Start nginx with our test configuration
+          docker run --name nginx-proxy --network changedet-network -d -p 8080:80 --rm \
+            -v ${{ github.workspace }}/.github/nginx-reverse-proxy-test.conf:/etc/nginx/conf.d/default.conf:ro \
+            nginx:alpine
+          sleep 2
+
+      - name: Test reverse proxy - root path
+        run: |
+          echo "=== Testing nginx reverse proxy at root path ==="
+          curl --retry-connrefused --retry 6 -s http://localhost:8080/ > /tmp/nginx-test-root.html
+
+          # Check for changedetection.io UI elements
+          if grep -q "checkbox-uuid" /tmp/nginx-test-root.html; then
+            echo "✓ Found checkbox-uuid in response"
+          else
+            echo "ERROR: checkbox-uuid not found in response"
+            cat /tmp/nginx-test-root.html
+            exit 1
+          fi
+
+          # Check for watchlist content
+          if grep -q -i "watch" /tmp/nginx-test-root.html; then
+            echo "✓ Found watch/watchlist content in response"
+          else
+            echo "ERROR: watchlist content not found"
+            cat /tmp/nginx-test-root.html
+            exit 1
+          fi
+
+          echo "✓ Root path reverse proxy working correctly"
+
+      - name: Test reverse proxy - subpath with X-Forwarded-Prefix
+        run: |
+          echo "=== Testing nginx reverse proxy at subpath /changedet-sub/ ==="
+          curl --retry-connrefused --retry 6 -s http://localhost:8080/changedet-sub/ > /tmp/nginx-test-subpath.html
+
+          # Check for changedetection.io UI elements
+          if grep -q "checkbox-uuid" /tmp/nginx-test-subpath.html; then
+            echo "✓ Found checkbox-uuid in subpath response"
+          else
+            echo "ERROR: checkbox-uuid not found in subpath response"
+            cat /tmp/nginx-test-subpath.html
+            exit 1
+          fi
+
+          echo "✓ Subpath reverse proxy working correctly"
+
+      - name: Test API through reverse proxy subpath
+        run: |
+          echo "=== Testing API endpoints through nginx subpath /changedet-sub/ ==="
+
+          # Extract API key from the changedetection.io datastore
+          API_KEY=$(docker exec changedet-app cat /datastore/changedetection.json | grep -o '"api_access_token": *"[^"]*"' | cut -d'"' -f4)
+
+          if [ -z "$API_KEY" ]; then
+            echo "ERROR: Could not extract API key from datastore"
+            docker exec changedet-app cat /datastore/changedetection.json
+            exit 1
+          fi
+
+          echo "✓ Extracted API key: ${API_KEY:0:8}..."
+
+          # Create a watch via API through nginx proxy subpath
+          echo "Creating watch via POST to /changedet-sub/api/v1/watch"
+          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "http://localhost:8080/changedet-sub/api/v1/watch" \
+            -H "x-api-key: ${API_KEY}" \
+            -H "Content-Type: application/json" \
+            -d '{
+              "url": "https://example.com/test-nginx-proxy",
+              "tag": "nginx-test"
+            }')
+
+          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
+          BODY=$(echo "$RESPONSE" | head -n-1)
+
+          if [ "$HTTP_CODE" != "201" ]; then
+            echo "ERROR: Expected HTTP 201, got $HTTP_CODE"
+            echo "Response: $BODY"
+            exit 1
+          fi
+
+          echo "✓ Watch created successfully (HTTP 201)"
+
+          # Extract the watch UUID from response
+          WATCH_UUID=$(echo "$BODY" | grep -o '"uuid": *"[^"]*"' | cut -d'"' -f4)
+          echo "✓ Watch UUID: $WATCH_UUID"
+
+          # Update the watch via PUT through nginx proxy subpath
+          echo "Updating watch via PUT to /changedet-sub/api/v1/watch/${WATCH_UUID}"
+          RESPONSE=$(curl -s -w "\n%{http_code}" -X PUT "http://localhost:8080/changedet-sub/api/v1/watch/${WATCH_UUID}" \
+            -H "x-api-key: ${API_KEY}" \
+            -H "Content-Type: application/json" \
+            -d '{
+              "paused": true
+            }')
+
+          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
+          BODY=$(echo "$RESPONSE" | head -n-1)
+
+          if [ "$HTTP_CODE" != "200" ]; then
+            echo "ERROR: Expected HTTP 200, got $HTTP_CODE"
+            echo "Response: $BODY"
+            exit 1
+          fi
+
+          if echo "$BODY" | grep -q '"ok": *true'; then
+            echo "✓ Watch updated successfully (HTTP 200, ok: true)"
+          else
+            echo "ERROR: Response missing 'ok: true'"
+            echo "Response: $BODY"
+            exit 1
+          fi
+
+          # Verify the watch is paused via GET
+          echo "Verifying watch is paused via GET"
+          RESPONSE=$(curl -s "http://localhost:8080/changedet-sub/api/v1/watch/${WATCH_UUID}" \
+            -H "x-api-key: ${API_KEY}")
+
+          if echo "$RESPONSE" | grep -q '"paused": *true'; then
+            echo "✓ Watch is paused as expected"
+          else
+            echo "ERROR: Watch paused state not confirmed"
+            echo "Response: $RESPONSE"
+            exit 1
+          fi
+
+          echo "✓ API tests through nginx subpath completed successfully"
+
+      - name: Cleanup nginx test
+        if: always()
+        run: |
+          docker logs nginx-proxy || true
+          docker logs changedet-app || true
+          docker stop nginx-proxy changedet-app || true
+          docker rm nginx-proxy changedet-app || true
+
+
+
+  # Proxy tests
+  proxy-tests:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 10
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Download Docker image artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp
+
+      - name: Load Docker image
+        run: |
+          docker load -i /tmp/test-changedetectionio.tar
+
+      - name: Spin up services
+        run: |
+          docker network create changedet-network
+          docker run --network changedet-network -d --hostname selenium -p 4444:4444 --rm --shm-size="2g" selenium/standalone-chrome:4
+          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser --hostname sockpuppetbrowser --rm -p 3000:3000 dgtlmoon/sockpuppetbrowser:latest
+          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser-custom-url --hostname sockpuppetbrowser-custom-url -p 3001:3000 --rm dgtlmoon/sockpuppetbrowser:latest
+
+      - name: Test proxy Squid style interaction
         run: |
           cd changedetectionio
           ./run_proxy_tests.sh
+          docker ps
           cd ..
 
       - name: Test proxy SOCKS5 style interaction
@@ -155,87 +533,294 @@ jobs:
           ./run_socks_proxy_tests.sh
           cd ..
 
+  # Custom browser URL tests
+  custom-browser-tests:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 10
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Download Docker image artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp
+
+      - name: Load Docker image
+        run: |
+          docker load -i /tmp/test-changedetectionio.tar
+
+      - name: Spin up ancillary services
+        run: |
+          docker network create changedet-network
+          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser --hostname sockpuppetbrowser --rm -p 3000:3000 dgtlmoon/sockpuppetbrowser:latest
+          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser-custom-url --hostname sockpuppetbrowser-custom-url -p 3001:3000 --rm dgtlmoon/sockpuppetbrowser:latest
+
       - name: Test custom browser URL
         run: |
           cd changedetectionio
           ./run_custom_browser_url_tests.sh
-          cd ..
 
-      - name: Test changedetection.io container starts+runs basically without error
+  processor-plugin-tests:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 20
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Download Docker image artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp
+
+      - name: Load Docker image
         run: |
-          docker run --name test-changedetectionio -p 5556:5000  -d test-changedetectionio
+          docker load -i /tmp/test-changedetectionio.tar
+
+      - name: Basic processor plugin registration and checks
+        run: |
+          docker run  -e EXTRA_PACKAGES=changedetection.io-osint-processor test-changedetectionio bash -c 'cd changedetectionio;pytest -vvv -s  tests/plugins/test_processor.py::test_check_plugin_processor'
+
+  # Container startup tests
+  container-tests:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 10
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Download Docker image artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp
+
+      - name: Load Docker image
+        run: |
+          docker load -i /tmp/test-changedetectionio.tar
+
+      - name: Test container starts+runs basically without error
+        run: |
+          docker run --name test-changedetectionio -p 5556:5000 -d test-changedetectionio
           sleep 3
-          # Should return 0 (no error) when grep finds it
-          curl --retry-connrefused --retry 6  -s http://localhost:5556 |grep -q checkbox-uuid
-          
-          # and IPv6
-          curl --retry-connrefused --retry 6  -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
-
-          # Check whether TRACE log is enabled.
-          # Also, check whether TRACE came from STDOUT
+          curl --retry-connrefused --retry 6 -s http://localhost:5556 |grep -q checkbox-uuid
+          curl --retry-connrefused --retry 6 -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
           docker logs test-changedetectionio 2>/dev/null | grep 'TRACE log is enabled' || exit 1
-          # Check whether DEBUG is came from STDOUT
           docker logs test-changedetectionio 2>/dev/null | grep 'DEBUG' || exit 1
-
           docker kill test-changedetectionio
 
-      - name: Test changedetection.io SIGTERM and SIGINT signal shutdown
+      - name: Test HTTPS SSL mode
+        run: |
+          openssl req -x509 -newkey rsa:4096 -keyout privkey.pem -out cert.pem -days 365 -nodes -subj "/CN=localhost"
+          docker run --name test-changedetectionio-ssl --rm -e SSL_CERT_FILE=cert.pem -e SSL_PRIVKEY_FILE=privkey.pem -p 5000:5000 -v ./cert.pem:/app/cert.pem -v ./privkey.pem:/app/privkey.pem -d test-changedetectionio
+          sleep 3
+          curl --retry-connrefused --retry 6 -k https://localhost:5000 -v|grep -q checkbox-uuid
+          docker kill test-changedetectionio-ssl
+
+      - name: Test IPv6 Mode
+        run: |
+          docker run --name test-changedetectionio-ipv6 --rm -p 5000:5000 -e LISTEN_HOST=:: -d test-changedetectionio
+          sleep 3
+          curl --retry-connrefused --retry 6 http://[::1]:5000 -v|grep -q checkbox-uuid
+          docker kill test-changedetectionio-ipv6
+
+  # Signal tests
+  signal-tests:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 10
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Download Docker image artifact
+        uses: actions/download-artifact@v7
+        with:
+          name: test-changedetectionio-${{ env.PYTHON_VERSION }}
+          path: /tmp
+
+      - name: Load Docker image
+        run: |
+          docker load -i /tmp/test-changedetectionio.tar
+
+      - name: Test SIGTERM and SIGINT signal shutdown
         run: |
-          
           echo SIGINT Shutdown request test
           docker run --name sig-test -d test-changedetectionio
           sleep 3
           echo ">>> Sending SIGINT to sig-test container"
           docker kill --signal=SIGINT sig-test
           sleep 3
-          # invert the check (it should be not 0/not running)
           docker ps
-          # check signal catch(STDERR) log. Because of
-          # changedetectionio/__init__.py: logger.add(sys.stderr, level=logger_level)
           docker logs sig-test 2>&1 | grep 'Shutdown: Got Signal - SIGINT' || exit 1
           test -z "`docker ps|grep sig-test`"
-          if [ $? -ne 0 ]
-          then
+          if [ $? -ne 0 ]; then
             echo "Looks like container was running when it shouldnt be"
             docker ps
             exit 1
           fi
-          
-          # @todo - scan the container log to see the right "graceful shutdown" text exists 
           docker rm sig-test
-          
+
           echo SIGTERM Shutdown request test
           docker run --name sig-test -d test-changedetectionio
           sleep 3
           echo ">>> Sending SIGTERM to sig-test container"
           docker kill --signal=SIGTERM sig-test
           sleep 3
-          # invert the check (it should be not 0/not running)
           docker ps
-          # check signal catch(STDERR) log. Because of
-          # changedetectionio/__init__.py: logger.add(sys.stderr, level=logger_level)
           docker logs sig-test 2>&1 | grep 'Shutdown: Got Signal - SIGTERM' || exit 1
           test -z "`docker ps|grep sig-test`"
-          if [ $? -ne 0 ]
-          then
+          if [ $? -ne 0 ]; then
             echo "Looks like container was running when it shouldnt be"
             docker ps
             exit 1
           fi
-          
-          # @todo - scan the container log to see the right "graceful shutdown" text exists           
           docker rm sig-test
 
-      - name: Dump container log
-        if: always()
-        run: |
-          mkdir output-logs
-          docker logs test-cdio-basic-tests > output-logs/test-cdio-basic-tests-stdout-${{ env.PYTHON_VERSION }}.txt
-          docker logs test-cdio-basic-tests 2> output-logs/test-cdio-basic-tests-stderr-${{ env.PYTHON_VERSION }}.txt
-
-      - name: Store everything including test-datastore
-        if: always()
-        uses: actions/upload-artifact@v4
+  # Upgrade path test
+  upgrade-path-test:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 25
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v6
         with:
-          name: test-cdio-basic-tests-output-py${{ env.PYTHON_VERSION }}
-          path: .
+          fetch-depth: 0  # Fetch all history and tags for upgrade testing
+
+      - name: Set up Python ${{ env.PYTHON_VERSION }}
+        uses: actions/setup-python@v6
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Check upgrade works without error
+        run: |
+          echo "=== Testing upgrade path from 0.49.1 to ${{ github.ref_name }} (${{ github.sha }}) ==="
+
+          # Checkout old version and create datastore
+          git checkout 0.49.1
+          python3 -m venv .venv
+          source .venv/bin/activate
+          pip install -r requirements.txt
+          pip install 'pyOpenSSL>=23.2.0'
+
+          echo "=== Running version 0.49.1 to create datastore ==="
+          python3 ./changedetection.py -C -d /tmp/data &
+          APP_PID=$!
+
+          # Wait for app to be ready
+          echo "Waiting for 0.49.1 to be ready..."
+          sleep 6
+
+          # Extract API key from datastore (0.49.1 uses url-watches.json)
+          API_KEY=$(jq -r '.settings.application.api_access_token // empty' /tmp/data/url-watches.json)
+          echo "API Key: ${API_KEY:0:8}..."
+
+          # Create a watch with tag "github-group-test" via API
+          echo "Creating test watch with tag via API..."
+          curl -X POST "http://127.0.0.1:5000/api/v1/watch" \
+            -H "x-api-key: ${API_KEY}" \
+            -H "Content-Type: application/json" \
+            --show-error --fail \
+            --retry 6 --retry-delay 1 --retry-connrefused \
+            -d '{
+              "url": "https://example.com/upgrade-test",
+              "tag": "github-group-test"
+            }'
+
+          echo "✓ Created watch with tag 'github-group-test'"
+
+          # Create a specific test URL watch
+          echo "Creating test URL watch via API..."
+          curl -X POST "http://127.0.0.1:5000/api/v1/watch" \
+            -H "x-api-key: ${API_KEY}" \
+            -H "Content-Type: application/json" \
+            --show-error --fail \
+            -d '{
+              "url": "http://localhost/test.txt"
+            }'
+
+          echo "✓ Created watch for 'http://localhost/test.txt' in version 0.49.1"
+
+          # Stop the old version gracefully
+          kill $APP_PID
+          wait $APP_PID || true
+          echo "✓ Version 0.49.1 stopped"
+
+          # Upgrade to current version (use commit SHA since we're in detached HEAD)
+          echo "Upgrading to commit ${{ github.sha }}"
+          git checkout ${{ github.sha }}
+          pip install -r requirements.txt
+
+          echo "=== Running current version (commit ${{ github.sha }}) with old datastore (testing mode) ==="
+          TESTING_SHUTDOWN_AFTER_DATASTORE_LOAD=1 python3 ./changedetection.py -d /tmp/data > /tmp/upgrade-test.log 2>&1
+
+          echo "=== Upgrade test output ==="
+          cat /tmp/upgrade-test.log
+          echo "✓ Datastore upgraded successfully"
+
+          # Now start the current version normally to verify the tag survived
+          echo "=== Starting current version to verify tag exists after upgrade ==="
+          timeout 20 python3 ./changedetection.py -d /tmp/data > /tmp/ui-test.log 2>&1 &
+          APP_PID=$!
+
+          # Wait for app to be ready and fetch UI
+          echo "Waiting for current version to be ready..."
+          sleep 5
+          curl --retry 6 --retry-delay 1 --retry-connrefused --silent http://127.0.0.1:5000 > /tmp/ui-output.html
+
+          # Verify tag exists in UI
+          if grep -q "github-group-test" /tmp/ui-output.html; then
+            echo "✓ Tag 'github-group-test' found in UI after upgrade"
+          else
+            echo "ERROR: Tag 'github-group-test' not found in UI after upgrade"
+            echo "=== UI Output ==="
+            cat /tmp/ui-output.html
+            echo "=== App Log ==="
+            cat /tmp/ui-test.log
+            kill $APP_PID || true
+            exit 1
+          fi
+
+          # Verify test URL exists in UI
+          if grep -q "http://localhost/test.txt" /tmp/ui-output.html; then
+            echo "✓ Watch URL 'http://localhost/test.txt' found in UI after upgrade"
+          else
+            echo "ERROR: Watch URL 'http://localhost/test.txt' not found in UI after upgrade"
+            echo "=== UI Output ==="
+            cat /tmp/ui-output.html
+            echo "=== App Log ==="
+            cat /tmp/ui-test.log
+            kill $APP_PID || true
+            exit 1
+          fi
+
+          # Cleanup
+          kill $APP_PID || true
+          wait $APP_PID || true
+
+          echo ""
+          echo "✓✓✓ Upgrade test passed: 0.49.1 → ${{ github.ref_name }} ✓✓✓"
+          echo "    - Commit: ${{ github.sha }}"
+          echo "    - Datastore migrated successfully"
+          echo "    - Tag 'github-group-test' survived upgrade"
+          echo "    - Watch URL 'http://localhost/test.txt' survived upgrade"
+
+          echo "✓ Upgrade test passed: 0.49.1 → ${{ github.ref_name }}"
+
+      - name: Upload upgrade test logs
+        if: always()
+        uses: actions/upload-artifact@v6
+        with:
+          name: upgrade-test-logs-py${{ env.PYTHON_VERSION }}
+          path: /tmp/upgrade-test.log

.gitignore

@@ -21,6 +21,7 @@ venv/
 # IDEs
 .idea
 .vscode/settings.json
+*~
 
 # Datastore files
 datastore/
@@ -28,3 +29,4 @@ test-datastore/
 
 # Memory consumption log
 test-memory.log
+tests/logs/

Dockerfile

@@ -5,7 +5,6 @@ ARG PYTHON_VERSION=3.11
 FROM python:${PYTHON_VERSION}-slim-bookworm AS builder
 
 # See `cryptography` pin comment in requirements.txt
-ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     g++ \
@@ -16,6 +15,8 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     libssl-dev \
     libxslt-dev \
     make \
+    patch \
+    pkg-config \
     zlib1g-dev
 
 RUN mkdir /install
@@ -23,18 +24,66 @@ WORKDIR /install
 
 COPY requirements.txt /requirements.txt
 
-# --extra-index-url https://www.piwheels.org/simple  is for cryptography module to be prebuilt (or rustc etc needs to be installed)
-RUN pip install --extra-index-url https://www.piwheels.org/simple  --target=/dependencies -r /requirements.txt
+# Use cache mounts and multiple wheel sources for faster ARM builds
+ENV PIP_CACHE_DIR=/tmp/pip-cache
+# Help Rust find OpenSSL for cryptography package compilation on ARM
+ENV PKG_CONFIG_PATH="/usr/lib/pkgconfig:/usr/lib/arm-linux-gnueabihf/pkgconfig:/usr/lib/aarch64-linux-gnu/pkgconfig"
+ENV PKG_CONFIG_ALLOW_SYSTEM_CFLAGS=1
+ENV OPENSSL_DIR="/usr"
+ENV OPENSSL_LIB_DIR="/usr/lib/arm-linux-gnueabihf"
+ENV OPENSSL_INCLUDE_DIR="/usr/include/openssl"
+# Additional environment variables for cryptography Rust build
+ENV CRYPTOGRAPHY_DONT_BUILD_RUST=1
+
+RUN --mount=type=cache,id=pip,sharing=locked,target=/tmp/pip-cache \
+  pip install \
+  --prefer-binary \
+  --extra-index-url https://www.piwheels.org/simple \
+  --extra-index-url https://pypi.anaconda.org/ARM-software/simple \
+  --cache-dir=/tmp/pip-cache \
+  --target=/dependencies \
+  -r /requirements.txt
 
 # Playwright is an alternative to Selenium
 # Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
 # https://github.com/dgtlmoon/changedetection.io/pull/1067 also musl/alpine (not supported)
-RUN pip install --target=/dependencies playwright~=1.48.0 \
-    || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
+RUN --mount=type=cache,id=pip,sharing=locked,target=/tmp/pip-cache \
+  pip install \
+  --prefer-binary \
+  --cache-dir=/tmp/pip-cache \
+  --target=/dependencies \
+  playwright~=1.56.0 \
+  || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
+
+# OpenCV is optional for fast image comparison (pixelmatch is the fallback)
+# Skip on arm/v7 and arm/v8 where builds take weeks - excluded from requirements.txt
+ARG TARGETPLATFORM
+RUN --mount=type=cache,id=pip,sharing=locked,target=/tmp/pip-cache \
+  case "$TARGETPLATFORM" in \
+    linux/arm/v7|linux/arm/v8) \
+      echo "INFO: Skipping OpenCV on $TARGETPLATFORM (build takes too long), using pixelmatch fallback" \
+      ;; \
+    *) \
+      pip install \
+        --prefer-binary \
+        --extra-index-url https://www.piwheels.org/simple \
+        --cache-dir=/tmp/pip-cache \
+        --target=/dependencies \
+        opencv-python-headless>=4.8.0.76 \
+        || echo "WARN: OpenCV install failed, will use pixelmatch fallback" \
+      ;; \
+  esac
+
 
 # Final image stage
 FROM python:${PYTHON_VERSION}-slim-bookworm
 LABEL org.opencontainers.image.source="https://github.com/dgtlmoon/changedetection.io"
+LABEL org.opencontainers.image.url="https://changedetection.io"
+LABEL org.opencontainers.image.documentation="https://changedetection.io/tutorials"
+LABEL org.opencontainers.image.title="changedetection.io"
+LABEL org.opencontainers.image.description="Self-hosted web page change monitoring and notification service"
+LABEL org.opencontainers.image.licenses="Apache-2.0"
+LABEL org.opencontainers.image.vendor="changedetection.io"
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libxslt1.1 \
@@ -42,7 +91,14 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     locales \
     # For pdftohtml
     poppler-utils \
+    # favicon type detection and other uses
+    file \
     zlib1g \
+    # OpenCV dependencies for image processing
+    libglib2.0-0 \
+    libsm6 \
+    libxext6 \
+    libxrender-dev \
     && apt-get clean && rm -rf /var/lib/apt/lists/*
 
 
@@ -62,6 +118,14 @@ EXPOSE 5000
 
 # The actual flask app module
 COPY changedetectionio /app/changedetectionio
+
+# Compile translation files for i18n support
+RUN pybabel compile -d /app/changedetectionio/translations
+
+# Also for OpenAPI validation wrapper - needs the YML
+RUN [ ! -d "/app/docs" ] && mkdir /app/docs
+COPY docs/api-spec.yaml /app/docs/api-spec.yaml
+
 # Starting wrapper
 COPY changedetection.py /app/changedetection.py
 
@@ -70,7 +134,19 @@ COPY changedetection.py /app/changedetection.py
 ARG LOGGER_LEVEL=''
 ENV LOGGER_LEVEL="$LOGGER_LEVEL"
 
+# Default
+ENV LC_ALL=en_US.UTF-8
+
 WORKDIR /app
+
+# Copy and set up entrypoint script for installing extra packages
+COPY docker-entrypoint.sh /docker-entrypoint.sh
+RUN chmod +x /docker-entrypoint.sh
+
+# Set entrypoint to handle EXTRA_PACKAGES env var
+ENTRYPOINT ["/docker-entrypoint.sh"]
+
+# Default command (can be overridden in docker-compose.yml)
 CMD ["python", "./changedetection.py", "-d", "/datastore"]
 
 

LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright [yyyy] [name of copyright owner]
+   Copyright 2025 Web Technologies s.r.o.
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

MANIFEST.in

@@ -1,16 +1,23 @@
 recursive-include changedetectionio/api *
+include docs/api-spec.yaml
 recursive-include changedetectionio/blueprint *
-recursive-include changedetectionio/content_fetchers *
 recursive-include changedetectionio/conditions *
+recursive-include changedetectionio/content_fetchers *
+recursive-include changedetectionio/jinja2_custom *
 recursive-include changedetectionio/model *
 recursive-include changedetectionio/notification *
 recursive-include changedetectionio/processors *
+recursive-include changedetectionio/realtime *
 recursive-include changedetectionio/static *
+recursive-include changedetectionio/store *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/tests *
+recursive-include changedetectionio/translations *
+recursive-include changedetectionio/widgets *
 prune changedetectionio/static/package-lock.json
 prune changedetectionio/static/styles/node_modules
 prune changedetectionio/static/styles/package-lock.json
+include changedetectionio/favicon_utils.py
 include changedetection.py
 include requirements.txt
 include README-pip.md

README-pip.md

@@ -1,11 +1,21 @@
-## Web Site Change Detection, Monitoring and Notification.
+# Monitor website changes
 
-Live your data-life pro-actively, track website content changes and receive notifications via Discord, Email, Slack, Telegram and 70+ more
+Detect WebPage Changes Automatically — Monitor Web Page Changes in Real Time
+
+Monitor websites for updates — get notified via Discord, Email, Slack, Telegram, Webhook and many more.
+
+Detect web page content changes and get instant alerts.
+
+
+[Changedetection.io is the best tool to monitor web-pages for changes](https://changedetection.io) Track website content changes and receive notifications via Discord, Email, Slack, Telegram and 90+ more
+
+Ideal for monitoring price changes, content edits, conditional changes and more.
 
 [<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring, list of websites with changes"  title="Self-hosted web page change monitoring, list of websites with changes"  />](https://changedetection.io)
 
 
-[**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://changedetection.io) 
+[**Don't have time? Try our extremely affordable subscription use our proxies and support!**](https://changedetection.io)
+
 
 
 ### Target specific parts of the webpage using the Visual Selector tool.
@@ -21,7 +31,7 @@ Available when connected to a <a href="https://github.com/dgtlmoon/changedetecti
 
 ### Perform interactive browser steps
 
-Fill in text boxes, click buttons and more, setup your changedetection scenario. 
+Fill in text boxes, click buttons and more, setup your changedetection scenario.
 
 Using the **Browser Steps** configuration, add basic steps before performing change detection, such as logging into websites, adding a product to a cart, accept cookie logins, entering dates and refining searches.
 
@@ -44,7 +54,7 @@ Requires Playwright to be enabled.
 - Know when your favourite whiskey is on sale, or other special deals are announced before anyone else
 - COVID related news from government websites
 - University/organisation news from their website
-- Detect and monitor changes in JSON API responses 
+- Detect and monitor changes in JSON API responses
 - JSON API monitoring and alerting
 - Changes in legal and other documents
 - Trigger API calls via notifications when text appears on a website
@@ -76,7 +86,7 @@ _Need an actual Chrome runner with Javascript support? We support fetching via W
 
 We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) global proxy services, Bright Data will match any first deposit up to $100 using our signup link.
 
-[Oxylabs](https://oxylabs.go2cloud.org/SH2d) is also an excellent proxy provider and well worth using, they offer Residental, ISP, Rotating and many other proxy types to suit your project. 
+[Oxylabs](https://oxylabs.go2cloud.org/SH2d) is also an excellent proxy provider and well worth using, they offer Residential, ISP, Rotating and many other proxy types to suit your project.
 
 Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
 
@@ -96,4 +106,3 @@ $ changedetection.io -d /path/to/empty/data/dir -p 5000
 Then visit http://127.0.0.1:5000 , You should now be able to access the UI.
 
 See https://changedetection.io for more information.
-

README.md

@@ -1,11 +1,13 @@
-## Web Site Change Detection, Restock monitoring and notifications.
+# Detect Website Changes Automatically — Monitor Web Page Changes in Real Time
 
-**_Detect website content changes and perform meaningful actions - trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._**
+Monitor websites for updates — get notified via Discord, Email, Slack, Telegram, Webhook and many more.
 
-_Live your data-life pro-actively._ 
+**Detect web page content changes and get instant alerts.**  
+
+Ideal for monitoring price changes, content edits, conditional changes and more.
 
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web site page change monitoring"  title="Self-hosted web site page change monitoring"  />](https://changedetection.io?src=github)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Web site page change monitoring"  title="Web site page change monitoring"  />](https://changedetection.io?src=github)
 
 [![Release Version][release-shield]][release-link] [![Docker Pulls][docker-pulls]][docker-link] [![License][license-shield]](LICENSE.md)
 
@@ -13,6 +15,7 @@ _Live your data-life pro-actively._
 
 [**Get started with website page change monitoring straight away. Don't have time? Try our $8.99/month subscription, use our proxies and support!**](https://changedetection.io) , _half the price of other website change monitoring services!_
 
+
 - Chrome browser included.
 - Nothing to install, access via browser login after signup.
 - Super fast, no registration needed setup.
@@ -99,9 +102,7 @@ _Need an actual Chrome runner with Javascript support? We support fetching via W
 - Configurable [proxy per watch](https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration)
 - Send a screenshot with the notification when a change is detected in the web page
 
-We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) global proxy services, Bright Data will match any first deposit up to $100 using our signup link.
-
-[Oxylabs](https://oxylabs.go2cloud.org/SH2d) is also an excellent proxy provider and well worth using, they offer Residental, ISP, Rotating and many other proxy types to suit your project. 
+We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) global proxy services, Bright Data will match any first deposit up to $150 using our signup link.
 
 Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
 
@@ -182,6 +183,9 @@ docker compose pull && docker compose up -d
 
 See the wiki for more information https://github.com/dgtlmoon/changedetection.io/wiki
 
+## Different browser viewport sizes (mobile, desktop etc)
+
+If you are using the recommended `sockpuppetbrowser` (which is in the docker-compose.yml as a setting to be uncommented) you can easily set different viewport sizes for your web page change detection, [see more information here about setting up different viewport sizes](https://github.com/dgtlmoon/sockpuppetbrowser?tab=readme-ov-file#setting-viewport-size).
 
 ## Filters
 
@@ -279,7 +283,10 @@ Excel import is recommended - that way you can better organise tags/groups of we
 
 ## API Support
 
-Supports managing the website watch list [via our API](https://changedetection.io/docs/api_v1/index.html)
+Full REST API for programmatic management of watches, tags, notifications and more. 
+
+- **[Interactive API Documentation](https://changedetection.io/docs/api_v1/index.html)** - Complete API reference with live testing
+- **[OpenAPI Specification](docs/api-spec.yaml)** - Generate SDKs for any programming language
 
 ## Support us
 

babel.cfg

@@ -0,0 +1,5 @@
+[python: **.py]
+keywords = _:1,_l:1,gettext:1
+
+[jinja2: **/templates/**.html]
+encoding = utf-8

changedetectionio/PLUGIN_README.md

@@ -64,7 +64,7 @@ def count_words_in_history(watch):
             return 0
             
         latest_key = list(watch.history.keys())[-1]
-        latest_content = watch.get_history_snapshot(latest_key)
+        latest_content = watch.get_history_snapshot(timestamp=latest_key)
         return len(latest_content.split())
     except Exception as e:
         logger.error(f"Error counting words: {str(e)}")

changedetectionio/__init__.py

@@ -1,24 +1,77 @@
 #!/usr/bin/env python3
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
-
-__version__ = '0.49.15'
+# Semver means never use .01, or 00. Should be .1.
+__version__ = '0.53.2'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError
-import os
-os.environ['EVENTLET_NO_GREENDNS'] = 'yes'
-import eventlet
-import eventlet.wsgi
+
+from loguru import logger
 import getopt
+import logging
+import os
 import platform
 import signal
-import socket
+import threading
+import time
+
+# Eventlet completely removed - using threading mode for SocketIO
+# This provides better Python 3.12+ compatibility and eliminates eventlet/asyncio conflicts
+# Note: store and changedetection_app are imported inside main() to avoid
+# initialization before argument parsing (allows --help to work without loading everything)
+
+# ==============================================================================
+# Multiprocessing Configuration - CRITICAL for Thread Safety
+# ==============================================================================
+#
+# PROBLEM: Python 3.12+ warns about fork() with multi-threaded processes:
+#   "This process is multi-threaded, use of fork() may lead to deadlocks"
+#
+# WHY IT'S DANGEROUS:
+#   1. This Flask app has multiple threads (HTTP handlers, workers, SocketIO)
+#   2. fork() copies ONLY the calling thread to the child process
+#   3. BUT fork() also copies all locks/mutexes in their current state
+#   4. If another thread held a lock during fork() → child has locked lock with no owner
+#   5. Result: PERMANENT DEADLOCK if child tries to acquire that lock
+#
+# SOLUTION: Use 'spawn' instead of 'fork'
+#   - spawn starts a fresh Python interpreter (no inherited threads or locks)
+#   - Slower (~200ms vs ~1ms) but safe with multi-threaded parent
+#   - Consistent across all platforms (Windows already uses spawn by default)
+#
+# IMPLEMENTATION:
+#   1. Explicit contexts everywhere (primary protection):
+#      - playwright.py: ctx = multiprocessing.get_context('spawn')
+#      - puppeteer.py: ctx = multiprocessing.get_context('spawn')
+#      - isolated_opencv.py: ctx = multiprocessing.get_context('spawn')
+#      - isolated_libvips.py: ctx = multiprocessing.get_context('spawn')
+#
+#   2. Global default (defense-in-depth, below):
+#      - Safety net if future code forgets explicit context
+#      - Protects against third-party libraries using Process()
+#      - Costs nothing (explicit contexts always override it)
+#
+# WHY BOTH?
+#   - Explicit contexts: Clear, self-documenting, always works
+#   - Global default: Safety net for forgotten contexts or library code
+#   - If someone writes "Process()" instead of "ctx.Process()", still safe!
+#
+# See: https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
+# ==============================================================================
+
+import multiprocessing
 import sys
 
-from changedetectionio import store
-from changedetectionio.flask_app import changedetection_app
-from loguru import logger
+# Set spawn as global default (safety net - all our code uses explicit contexts anyway)
+# Skip in tests to avoid breaking pytest-flask's LiveServer fixture (uses unpicklable local functions)
+if 'pytest' not in sys.modules:
+    try:
+        if multiprocessing.get_start_method(allow_none=True) is None:
+            multiprocessing.set_start_method('spawn', force=False)
+            logger.debug("Set multiprocessing default to 'spawn' for thread safety (explicit contexts used everywhere)")
+    except RuntimeError:
+        logger.debug(f"Multiprocessing start method already set: {multiprocessing.get_start_method()}")
 
 # Only global so we can access it in the signal handler
 app = None
@@ -30,26 +83,121 @@ def get_version():
 # Parent wrapper or OS sends us a SIGTERM/SIGINT, do everything required for a clean shutdown
 def sigshutdown_handler(_signo, _stack_frame):
     name = signal.Signals(_signo).name
-    logger.critical(f'Shutdown: Got Signal - {name} ({_signo}), Saving DB to disk and calling shutdown')
-    datastore.sync_to_json()
-    logger.success('Sync JSON to disk complete.')
-    # This will throw a SystemExit exception, because eventlet.wsgi.server doesn't know how to deal with it.
-    # Solution: move to gevent or other server in the future (#2014)
-    datastore.stop_thread = True
+    logger.critical(f'Shutdown: Got Signal - {name} ({_signo}), Fast shutdown initiated')
+
+    # Set exit flag immediately to stop all loops
     app.config.exit.set()
+    datastore.stop_thread = True
+
+    # Log memory consumption before shutting down workers (cross-platform)
+    try:
+        import psutil
+        process = psutil.Process()
+        mem_info = process.memory_info()
+        rss_mb = mem_info.rss / 1024 / 1024
+        vms_mb = mem_info.vms / 1024 / 1024
+        logger.info(f"Memory consumption before worker shutdown: RSS={rss_mb:,.2f} MB, VMS={vms_mb:,.2f} MB")
+    except Exception as e:
+        logger.warning(f"Could not retrieve memory stats: {str(e)}")
+
+    # Shutdown workers and queues immediately
+    try:
+        from changedetectionio import worker_pool
+        worker_pool.shutdown_workers()
+    except Exception as e:
+        logger.error(f"Error shutting down workers: {str(e)}")
+    
+    # Close janus queues properly
+    try:
+        from changedetectionio.flask_app import update_q, notification_q
+        update_q.close()
+        notification_q.close()
+        logger.debug("Queues closed successfully")
+    except Exception as e:
+        logger.critical(f"CRITICAL: Failed to close queues: {e}")
+    
+    # Shutdown socketio server fast
+    from changedetectionio.flask_app import socketio_server
+    if socketio_server and hasattr(socketio_server, 'shutdown'):
+        try:
+            socketio_server.shutdown()
+        except Exception as e:
+            logger.error(f"Error shutting down Socket.IO server: {str(e)}")
+    
+    # With immediate persistence, all data is already saved
+    logger.success('All data already persisted (immediate commits enabled).')
+
     sys.exit()
 
+def print_help():
+    """Print help text for command line options"""
+    print('Usage: changedetection.py [options]')
+    print('')
+    print('Standard options:')
+    print('  -s                SSL enable')
+    print('  -h HOST           Listen host (default: 0.0.0.0)')
+    print('  -p PORT           Listen port (default: 5000)')
+    print('  -d PATH           Datastore path')
+    print('  -l LEVEL          Log level (TRACE, DEBUG, INFO, SUCCESS, WARNING, ERROR, CRITICAL)')
+    print('  -c                Cleanup unused snapshots')
+    print('  -C                Create datastore directory if it doesn\'t exist')
+    print('  -P true/false     Set all watches paused (true) or active (false)')
+    print('')
+    print('Add URLs on startup:')
+    print('  -u URL            Add URL to watch (can be used multiple times)')
+    print('  -u0 \'JSON\'        Set options for first -u URL (e.g. \'{"processor":"text_json_diff"}\')')
+    print('  -u1 \'JSON\'        Set options for second -u URL (0-indexed)')
+    print('  -u2 \'JSON\'        Set options for third -u URL, etc.')
+    print('                    Available options: processor, fetch_backend, headers, method, etc.')
+    print('                    See model/Watch.py for all available options')
+    print('')
+    print('Recheck on startup:')
+    print('  -r all            Queue all watches for recheck on startup')
+    print('  -r UUID,...       Queue specific watches (comma-separated UUIDs)')
+    print('  -r all N          Queue all watches, wait for completion, repeat N times')
+    print('  -r UUID,... N     Queue specific watches, wait for completion, repeat N times')
+    print('')
+    print('Batch mode:')
+    print('  -b                Run in batch mode (process queue then exit)')
+    print('                    Useful for CI/CD, cron jobs, or one-time checks')
+    print('                    NOTE: Batch mode checks if Flask is running and aborts if port is in use')
+    print('                    Use -p PORT to specify a different port if needed')
+    print('')
+
 def main():
     global datastore
     global app
 
+    # Early help/version check before any initialization
+    if '--help' in sys.argv or '-help' in sys.argv:
+        print_help()
+        sys.exit(0)
+
+    if '--version' in sys.argv or '-v' in sys.argv:
+        print(f'changedetection.io {__version__}')
+        sys.exit(0)
+
+    # Import heavy modules after help/version checks to keep startup fast for those flags
+    from changedetectionio import store
+    from changedetectionio.flask_app import changedetection_app
+
     datastore_path = None
-    do_cleanup = False
-    host = ''
-    ipv6_enabled = False
-    port = os.environ.get('PORT') or 5000
+    # Set a default logger level
+    logger_level = 'DEBUG'
+    include_default_watches = True
+    all_paused = None  # None means don't change, True/False to set
+
+    host = os.environ.get("LISTEN_HOST", "0.0.0.0").strip()
+    port = int(os.environ.get('PORT', 5000))
     ssl_mode = False
 
+    # Lists for multiple URLs and their options
+    urls_to_add = []
+    url_options = {}  # Key: index (0-based), Value: dict of options
+    recheck_watches = None  # None, 'all', or list of UUIDs
+    recheck_repeat_count = 1  # Number of times to repeat recheck cycle
+    batch_mode = False  # Run once then exit when queue is empty
+
     # On Windows, create and use a default path.
     if os.name == 'nt':
         datastore_path = os.path.expandvars(r'%APPDATA%\changedetection.io')
@@ -58,16 +206,72 @@ def main():
         # Must be absolute so that send_from_directory doesnt try to make it relative to backend/
         datastore_path = os.path.join(os.getcwd(), "../datastore")
 
+    # Pre-process arguments to extract -u, -u<N>, and -r options before getopt
+    # This allows unlimited -u0, -u1, -u2, ... options without predefining them
+    cleaned_argv = ['changedetection.py']  # Start with program name
+    i = 1
+    while i < len(sys.argv):
+        arg = sys.argv[i]
+
+        # Handle -u (add URL)
+        if arg == '-u' and i + 1 < len(sys.argv):
+            urls_to_add.append(sys.argv[i + 1])
+            i += 2
+            continue
+
+        # Handle -u<N> (set options for URL at index N)
+        if arg.startswith('-u') and len(arg) > 2 and arg[2:].isdigit():
+            idx = int(arg[2:])
+            if i + 1 < len(sys.argv):
+                try:
+                    import json
+                    url_options[idx] = json.loads(sys.argv[i + 1])
+                except json.JSONDecodeError as e:
+                    print(f'Error: Invalid JSON for {arg}: {sys.argv[i + 1]}')
+                    print(f'JSON decode error: {e}')
+                    sys.exit(2)
+                i += 2
+                continue
+
+        # Handle -r (recheck watches)
+        if arg == '-r' and i + 1 < len(sys.argv):
+            recheck_arg = sys.argv[i + 1]
+            if recheck_arg.lower() == 'all':
+                recheck_watches = 'all'
+            else:
+                # Parse comma-separated list of UUIDs
+                recheck_watches = [uuid.strip() for uuid in recheck_arg.split(',') if uuid.strip()]
+
+            # Check for optional repeat count as third argument
+            if i + 2 < len(sys.argv) and sys.argv[i + 2].isdigit():
+                recheck_repeat_count = int(sys.argv[i + 2])
+                if recheck_repeat_count < 1:
+                    print(f'Error: Repeat count must be at least 1, got {recheck_repeat_count}')
+                    sys.exit(2)
+                i += 3
+            else:
+                i += 2
+            continue
+
+        # Handle -b (batch mode - run once and exit)
+        if arg == '-b':
+            batch_mode = True
+            i += 1
+            continue
+
+        # Keep other arguments for getopt
+        cleaned_argv.append(arg)
+        i += 1
+
     try:
-        opts, args = getopt.getopt(sys.argv[1:], "6Ccsd:h:p:l:", "port")
-    except getopt.GetoptError:
-        print('backend.py -s SSL enable -h [host] -p [port] -d [datastore path] -l [debug level - TRACE, DEBUG(default), INFO, SUCCESS, WARNING, ERROR, CRITICAL]')
+        opts, args = getopt.getopt(cleaned_argv[1:], "6Csd:h:p:l:P:", "port")
+    except getopt.GetoptError as e:
+        print_help()
+        print(f'Error: {e}')
         sys.exit(2)
 
     create_datastore_dir = False
 
-    # Set a default logger level
-    logger_level = 'DEBUG'
     # Set a logger level via shell env variable
     # Used: Dockerfile for CICD
     # To set logger level for pytest, see the app function in tests/conftest.py
@@ -88,14 +292,6 @@ def main():
         if opt == '-d':
             datastore_path = arg
 
-        if opt == '-6':
-            logger.success("Enabling IPv6 listen support")
-            ipv6_enabled = True
-
-        # Cleanup (remove text files that arent in the index)
-        if opt == '-c':
-            do_cleanup = True
-
         # Create the datadir if it doesnt exist
         if opt == '-C':
             create_datastore_dir = True
@@ -103,6 +299,32 @@ def main():
         if opt == '-l':
             logger_level = int(arg) if arg.isdigit() else arg.upper()
 
+        if opt == '-P':
+            try:
+                all_paused = bool(strtobool(arg))
+            except ValueError:
+                print(f'Error: Invalid value for -P option: {arg}')
+                print('Expected: true, false, yes, no, 1, or 0')
+                sys.exit(2)
+
+    # If URLs are provided, don't include default watches
+    if urls_to_add:
+        include_default_watches = False
+
+
+    logger.success(f"changedetection.io version {get_version()} starting.")
+    # Launch using SocketIO run method for proper integration (if enabled)
+    ssl_cert_file = os.getenv("SSL_CERT_FILE", 'cert.pem')
+    ssl_privkey_file = os.getenv("SSL_PRIVKEY_FILE", 'privkey.pem')
+    if os.getenv("SSL_CERT_FILE") and os.getenv("SSL_PRIVKEY_FILE"):
+        ssl_mode = True
+
+    # SSL mode could have been set by -s too, therefor fallback to default values
+    if ssl_mode:
+        if not os.path.isfile(ssl_cert_file) or not os.path.isfile(ssl_privkey_file):
+            logger.critical(f"Cannot start SSL/HTTPS mode, Please be sure that {ssl_cert_file}' and '{ssl_privkey_file}' exist in in {os.getcwd()}")
+            os._exit(2)
+
     # Without this, a logger will be duplicated
     logger.remove()
     try:
@@ -119,12 +341,22 @@ def main():
               " WARNING, ERROR, CRITICAL")
         sys.exit(2)
 
+    # Disable verbose pyppeteer logging to prevent memory leaks from large CDP messages
+    # Set both parent and child loggers since pyppeteer hardcodes DEBUG level
+    logging.getLogger('pyppeteer.connection').setLevel(logging.WARNING)
+    logging.getLogger('pyppeteer.connection.Connection').setLevel(logging.WARNING)
+
     # isnt there some @thingy to attach to each route to tell it, that this route needs a datastore
-    app_config = {'datastore_path': datastore_path}
+    app_config = {
+        'datastore_path': datastore_path,
+        'batch_mode': batch_mode,
+        'recheck_watches': recheck_watches,
+        'recheck_repeat_count': recheck_repeat_count
+    }
 
     if not os.path.isdir(app_config['datastore_path']):
         if create_datastore_dir:
-            os.mkdir(app_config['datastore_path'])
+            os.makedirs(app_config['datastore_path'], exist_ok=True)
         else:
             logger.critical(
                 f"ERROR: Directory path for the datastore '{app_config['datastore_path']}'"
@@ -134,15 +366,229 @@ def main():
             sys.exit(2)
 
     try:
-        datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], version_tag=__version__)
+        datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], version_tag=__version__, include_default_watches=include_default_watches)
     except JSONDecodeError as e:
         # Dont' start if the JSON DB looks corrupt
         logger.critical(f"ERROR: JSON DB or Proxy List JSON at '{app_config['datastore_path']}' appears to be corrupt, aborting.")
         logger.critical(str(e))
-        return
+        sys.exit(1)
+
+    # Testing mode: Exit cleanly after datastore initialization (for CI/CD upgrade tests)
+    if os.environ.get('TESTING_SHUTDOWN_AFTER_DATASTORE_LOAD'):
+        logger.success(f"TESTING MODE: Datastore loaded successfully from {app_config['datastore_path']}")
+        logger.success(f"TESTING MODE: Schema version: {datastore.data['settings']['application'].get('schema_version', 'unknown')}")
+        logger.success(f"TESTING MODE: Loaded {len(datastore.data['watching'])} watches")
+        logger.success("TESTING MODE: Exiting cleanly (TESTING_SHUTDOWN_AFTER_DATASTORE_LOAD is set)")
+        sys.exit(0)
+
+    # Apply all_paused setting if specified via CLI
+    if all_paused is not None:
+        datastore.data['settings']['application']['all_paused'] = all_paused
+        logger.info(f"Setting all watches paused: {all_paused}")
+
+    # Inject datastore into plugins that need access to settings
+    from changedetectionio.pluggy_interface import inject_datastore_into_plugins
+    inject_datastore_into_plugins(datastore)
+
+    # Step 1: Add URLs with their options (if provided via -u flags)
+    added_watch_uuids = []
+    if urls_to_add:
+        logger.info(f"Adding {len(urls_to_add)} URL(s) from command line")
+        for idx, url in enumerate(urls_to_add):
+            extras = url_options.get(idx, {})
+            if extras:
+                logger.debug(f"Adding watch {idx}: {url} with options: {extras}")
+            else:
+                logger.debug(f"Adding watch {idx}: {url}")
+
+            new_uuid = datastore.add_watch(url=url, extras=extras)
+            if new_uuid:
+                added_watch_uuids.append(new_uuid)
+                logger.success(f"Added watch: {url} (UUID: {new_uuid})")
+            else:
+                logger.error(f"Failed to add watch: {url}")
 
     app = changedetection_app(app_config, datastore)
 
+    # Step 2: Queue newly added watches (if -u was provided in batch mode)
+    # This must happen AFTER app initialization so update_q is available
+    if batch_mode and added_watch_uuids:
+        from changedetectionio.flask_app import update_q
+        from changedetectionio import queuedWatchMetaData, worker_pool
+
+        logger.info(f"Batch mode: Queuing {len(added_watch_uuids)} newly added watches")
+        for watch_uuid in added_watch_uuids:
+            try:
+                worker_pool.queue_item_async_safe(
+                    update_q,
+                    queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid})
+                )
+                logger.debug(f"Queued newly added watch: {watch_uuid}")
+            except Exception as e:
+                logger.error(f"Failed to queue watch {watch_uuid}: {e}")
+
+    # Step 3: Queue watches for recheck (if -r was provided)
+    # This must happen AFTER app initialization so update_q is available
+    if recheck_watches is not None:
+        from changedetectionio.flask_app import update_q
+        from changedetectionio import queuedWatchMetaData, worker_pool
+
+        watches_to_queue = []
+        if recheck_watches == 'all':
+            # Queue all watches, excluding those already queued in batch mode
+            all_watches = list(datastore.data['watching'].keys())
+            if batch_mode and added_watch_uuids:
+                # Exclude newly added watches that were already queued in batch mode
+                watches_to_queue = [uuid for uuid in all_watches if uuid not in added_watch_uuids]
+                logger.info(f"Queuing {len(watches_to_queue)} existing watches for recheck ({len(added_watch_uuids)} newly added watches already queued)")
+            else:
+                watches_to_queue = all_watches
+                logger.info(f"Queuing all {len(watches_to_queue)} watches for recheck")
+        else:
+            # Queue specific UUIDs
+            watches_to_queue = recheck_watches
+            logger.info(f"Queuing {len(watches_to_queue)} specific watches for recheck")
+
+        queued_count = 0
+        for watch_uuid in watches_to_queue:
+            if watch_uuid in datastore.data['watching']:
+                try:
+                    worker_pool.queue_item_async_safe(
+                        update_q,
+                        queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid})
+                    )
+                    queued_count += 1
+                    logger.debug(f"Queued watch for recheck: {watch_uuid}")
+                except Exception as e:
+                    logger.error(f"Failed to queue watch {watch_uuid}: {e}")
+            else:
+                logger.warning(f"Watch UUID not found in datastore: {watch_uuid}")
+
+        logger.success(f"Successfully queued {queued_count} watches for recheck")
+
+    # Step 4: Setup batch mode monitor (if -b was provided)
+    if batch_mode:
+        from changedetectionio.flask_app import update_q
+
+        # Safety check: Ensure Flask app is not already running on this port
+        # Batch mode should never run alongside the web server
+        import socket
+        test_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+
+        try:
+            # Try to bind to the configured host:port (no SO_REUSEADDR - strict check)
+            test_socket.bind((host, port))
+            test_socket.close()
+            logger.debug(f"Batch mode: Port {port} is available (Flask app not running)")
+        except OSError as e:
+            test_socket.close()
+            # errno 98 = EADDRINUSE (Linux)
+            # errno 48 = EADDRINUSE (macOS)
+            # errno 10048 = WSAEADDRINUSE (Windows)
+            if e.errno in (48, 98, 10048) or "Address already in use" in str(e) or "already in use" in str(e).lower():
+                logger.critical(f"ERROR: Batch mode cannot run - port {port} is already in use")
+                logger.critical(f"The Flask web server appears to be running on {host}:{port}")
+                logger.critical(f"Batch mode is designed for standalone operation (CI/CD, cron jobs, etc.)")
+                logger.critical(f"Please either stop the Flask web server, or use a different port with -p PORT")
+                sys.exit(1)
+            else:
+                # Some other socket error - log but continue (might be network configuration issue)
+                logger.warning(f"Port availability check failed with unexpected error: {e}")
+                logger.warning(f"Continuing with batch mode anyway - be aware of potential conflicts")
+
+        def queue_watches_for_recheck(datastore, iteration):
+            """Helper function to queue watches for recheck"""
+            watches_to_queue = []
+            if recheck_watches == 'all':
+                all_watches = list(datastore.data['watching'].keys())
+                if batch_mode and added_watch_uuids and iteration == 1:
+                    # Only exclude newly added watches on first iteration
+                    watches_to_queue = [uuid for uuid in all_watches if uuid not in added_watch_uuids]
+                else:
+                    watches_to_queue = all_watches
+                logger.info(f"Batch mode (iteration {iteration}): Queuing all {len(watches_to_queue)} watches")
+            elif recheck_watches:
+                watches_to_queue = recheck_watches
+                logger.info(f"Batch mode (iteration {iteration}): Queuing {len(watches_to_queue)} specific watches")
+
+            queued_count = 0
+            for watch_uuid in watches_to_queue:
+                if watch_uuid in datastore.data['watching']:
+                    try:
+                        worker_pool.queue_item_async_safe(
+                            update_q,
+                            queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid})
+                        )
+                        queued_count += 1
+                    except Exception as e:
+                        logger.error(f"Failed to queue watch {watch_uuid}: {e}")
+                else:
+                    logger.warning(f"Watch UUID not found in datastore: {watch_uuid}")
+            logger.success(f"Batch mode (iteration {iteration}): Successfully queued {queued_count} watches")
+            return queued_count
+
+        def batch_mode_monitor():
+            """Monitor queue and workers, shutdown or repeat when work is complete"""
+            import time
+
+            # Track iterations if repeat mode is enabled
+            current_iteration = 1
+            total_iterations = recheck_repeat_count if recheck_watches and recheck_repeat_count > 1 else 1
+
+            if total_iterations > 1:
+                logger.info(f"Batch mode: Will repeat recheck {total_iterations} times")
+            else:
+                logger.info("Batch mode: Waiting for all queued items to complete...")
+
+            # Wait a bit for workers to start processing
+            time.sleep(3)
+
+            try:
+                while current_iteration <= total_iterations:
+                    logger.info(f"Batch mode: Waiting for iteration {current_iteration}/{total_iterations} to complete...")
+
+                    # Use the shared wait_for_all_checks function
+                    completed = worker_pool.wait_for_all_checks(update_q, timeout=300)
+
+                    if not completed:
+                        logger.warning(f"Batch mode: Iteration {current_iteration} timed out after 300 seconds")
+
+                    logger.success(f"Batch mode: Iteration {current_iteration}/{total_iterations} completed")
+
+                    # Check if we need to repeat
+                    if current_iteration < total_iterations:
+                        logger.info(f"Batch mode: Starting iteration {current_iteration + 1}...")
+                        current_iteration += 1
+
+                        # Re-queue watches for next iteration
+                        queue_watches_for_recheck(datastore, current_iteration)
+
+                        # Brief pause before continuing
+                        time.sleep(2)
+                    else:
+                        # All iterations complete
+                        logger.success(f"Batch mode: All {total_iterations} iterations completed, initiating shutdown")
+                        # Trigger shutdown
+                        import os, signal
+                        os.kill(os.getpid(), signal.SIGTERM)
+                        return
+
+            except Exception as e:
+                logger.error(f"Batch mode monitor error: {e}")
+                logger.error(f"Initiating emergency shutdown")
+                import os, signal
+                os.kill(os.getpid(), signal.SIGTERM)
+
+        # Start monitor in background thread
+        monitor_thread = threading.Thread(target=batch_mode_monitor, daemon=True, name="BatchModeMonitor")
+        monitor_thread.start()
+        logger.info("Batch mode enabled: Will exit after all queued items are processed")
+
+    # Get the SocketIO instance from the Flask app (created in flask_app.py)
+    from changedetectionio.flask_app import socketio_server
+    global socketio
+    socketio = socketio_server
+
     signal.signal(signal.SIGTERM, sigshutdown_handler)
     signal.signal(signal.SIGINT, sigshutdown_handler)
     
@@ -159,18 +605,17 @@ def main():
     else:
         logger.info("SIGUSR1 handler only registered on Linux, skipped.")
 
-    # Go into cleanup mode
-    if do_cleanup:
-        datastore.remove_unused_snapshots()
-
     app.config['datastore_path'] = datastore_path
 
 
     @app.context_processor
-    def inject_version():
-        return dict(right_sticky="v{}".format(datastore.data['version_tag']),
+    def inject_template_globals():
+        return dict(right_sticky="v"+__version__,
                     new_version_available=app.config['NEW_VERSION_AVAILABLE'],
-                    has_password=datastore.data['settings']['application']['password'] != False
+                    has_password=datastore.data['settings']['application']['password'] != False,
+                    socket_io_enabled=datastore.data['settings']['application'].get('ui', {}).get('socket_io_enabled', True),
+                    all_paused=datastore.data['settings']['application'].get('all_paused', False),
+                    all_muted=datastore.data['settings']['application'].get('all_muted', False)
                     )
 
     # Monitored websites will not receive a Referer header when a user clicks on an outgoing link.
@@ -192,17 +637,43 @@ def main():
     if os.getenv('USE_X_SETTINGS'):
         logger.info("USE_X_SETTINGS is ENABLED")
         from werkzeug.middleware.proxy_fix import ProxyFix
-        app.wsgi_app = ProxyFix(app.wsgi_app, x_prefix=1, x_host=1)
+        app.wsgi_app = ProxyFix(
+            app.wsgi_app,
+            x_for=1,      # X-Forwarded-For (client IP)
+            x_proto=1,    # X-Forwarded-Proto (http/https)
+            x_host=1,     # X-Forwarded-Host (original host)
+            x_port=1,     # X-Forwarded-Port (original port)
+            x_prefix=1    # X-Forwarded-Prefix (URL prefix)
+        )
 
-    s_type = socket.AF_INET6 if ipv6_enabled else socket.AF_INET
-
-    if ssl_mode:
-        # @todo finalise SSL config, but this should get you in the right direction if you need it.
-        eventlet.wsgi.server(eventlet.wrap_ssl(eventlet.listen((host, port), s_type),
-                                               certfile='cert.pem',
-                                               keyfile='privkey.pem',
-                                               server_side=True), app)
 
+    # In batch mode, skip starting the HTTP server - just keep workers running
+    if batch_mode:
+        logger.info("Batch mode: Skipping HTTP server startup, workers will process queue")
+        logger.info("Batch mode: Main thread will wait for shutdown signal")
+        # Keep main thread alive until batch monitor triggers shutdown
+        try:
+            while True:
+                time.sleep(1)
+        except KeyboardInterrupt:
+            logger.info("Batch mode: Keyboard interrupt received")
+            pass
     else:
-        eventlet.wsgi.server(eventlet.listen((host, int(port)), s_type), app)
-
+        # Normal mode: Start HTTP server
+        # SocketIO instance is already initialized in flask_app.py
+        if socketio_server:
+            if ssl_mode:
+                logger.success(f"SSL mode enabled, attempting to start with '{ssl_cert_file}' and '{ssl_privkey_file}' in {os.getcwd()}")
+                socketio.run(app, host=host, port=int(port), debug=False,
+                             ssl_context=(ssl_cert_file, ssl_privkey_file), allow_unsafe_werkzeug=True)
+            else:
+                socketio.run(app, host=host, port=int(port), debug=False, allow_unsafe_werkzeug=True)
+        else:
+            # Run Flask app without Socket.IO if disabled
+            logger.info("Starting Flask app without Socket.IO server")
+            if ssl_mode:
+                logger.success(f"SSL mode enabled, attempting to start with '{ssl_cert_file}' and '{ssl_privkey_file}' in {os.getcwd()}")
+                app.run(host=host, port=int(port), debug=False,
+                        ssl_context=(ssl_cert_file, ssl_privkey_file))
+            else:
+                app.run(host=host, port=int(port), debug=False)

changedetectionio/api/Import.py

@@ -1,9 +1,96 @@
-import os
 from changedetectionio.strtobool import strtobool
 from flask_restful import abort, Resource
 from flask import request
-import validators
-from . import auth
+from functools import wraps
+from . import auth, validate_openapi_request
+from ..validate_url import is_safe_valid_url
+import json
+
+# Number of URLs above which import switches to background processing
+IMPORT_SWITCH_TO_BACKGROUND_THRESHOLD = 20
+
+
+def default_content_type(content_type='text/plain'):
+    """Decorator to set a default Content-Type header if none is provided."""
+    def decorator(f):
+        @wraps(f)
+        def wrapper(*args, **kwargs):
+            if not request.content_type:
+                # Set default content type in the request environment
+                request.environ['CONTENT_TYPE'] = content_type
+            return f(*args, **kwargs)
+        return wrapper
+    return decorator
+
+
+def convert_query_param_to_type(value, schema_property):
+    """
+    Convert a query parameter string to the appropriate type based on schema definition.
+
+    Args:
+        value: String value from query parameter
+        schema_property: Schema property definition with 'type' or 'anyOf' field
+
+    Returns:
+        Converted value in the appropriate type
+
+    Supports both OpenAPI 3.1 formats:
+    - type: [string, 'null']  (array format)
+    - anyOf: [{type: string}, {type: null}]  (anyOf format)
+    """
+    prop_type = schema_property.get('type')
+
+    # Handle OpenAPI 3.1 type arrays: type: [string, 'null']
+    if isinstance(prop_type, list):
+        # Use the first non-null type from the array
+        for t in prop_type:
+            if t != 'null':
+                prop_type = t
+                break
+        else:
+            prop_type = None
+
+    # Handle anyOf schemas (older format)
+    elif 'anyOf' in schema_property:
+        # Use the first non-null type from anyOf
+        for option in schema_property['anyOf']:
+            if option.get('type') and option.get('type') != 'null':
+                prop_type = option.get('type')
+                break
+        else:
+            prop_type = None
+
+    # Handle array type (e.g., notification_urls)
+    if prop_type == 'array':
+        # Support both comma-separated and JSON array format
+        if value.startswith('['):
+            try:
+                return json.loads(value)
+            except json.JSONDecodeError:
+                return [v.strip() for v in value.split(',')]
+        return [v.strip() for v in value.split(',')]
+
+    # Handle object type (e.g., time_between_check, headers)
+    elif prop_type == 'object':
+        try:
+            return json.loads(value)
+        except json.JSONDecodeError:
+            raise ValueError(f"Invalid JSON object for field: {value}")
+
+    # Handle boolean type
+    elif prop_type == 'boolean':
+        return strtobool(value)
+
+    # Handle integer type
+    elif prop_type == 'integer':
+        return int(value)
+
+    # Handle number type (float)
+    elif prop_type == 'number':
+        return float(value)
+
+    # Default: return as string
+    return value
 
 
 class Import(Resource):
@@ -12,51 +99,131 @@ class Import(Resource):
         self.datastore = kwargs['datastore']
 
     @auth.check_token
+    @default_content_type('text/plain') #3547 #3542
+    @validate_openapi_request('importWatches')
     def post(self):
-        """
-        @api {post} /api/v1/import Import a list of watched URLs
-        @apiDescription Accepts a line-feed separated list of URLs to import, additionally with ?tag_uuids=(tag  id), ?tag=(name), ?proxy={key}, ?dedupe=true (default true) one URL per line.
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/import --data-binary @list-of-sites.txt -H"x-api-key:8a111a21bc2f8f1dd9b9353bbd46049a"
-        @apiName Import
-        @apiGroup Watch
-        @apiSuccess (200) {List} OK List of watch UUIDs added
-        @apiSuccess (500) {String} ERR Some other error
-        """
+        """Import a list of watched URLs with optional watch configuration."""
+        from . import get_watch_schema_properties
+        # Special parameters that are NOT watch configuration
+        special_params = {'tag', 'tag_uuids', 'dedupe', 'proxy'}
 
         extras = {}
 
+        # Handle special 'proxy' parameter
         if request.args.get('proxy'):
             plist = self.datastore.proxy_list
             if not request.args.get('proxy') in plist:
-                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
+                proxy_list_str = ', '.join(plist) if plist else 'none configured'
+                return f"Invalid proxy choice, currently supported proxies are '{proxy_list_str}'", 400
             else:
                 extras['proxy'] = request.args.get('proxy')
 
+        # Handle special 'dedupe' parameter
         dedupe = strtobool(request.args.get('dedupe', 'true'))
 
+        # Handle special 'tag' and 'tag_uuids' parameters
         tags = request.args.get('tag')
         tag_uuids = request.args.get('tag_uuids')
 
         if tag_uuids:
             tag_uuids = tag_uuids.split(',')
 
+        # Extract ALL other query parameters as watch configuration
+        # Get schema from OpenAPI spec (replaces old schema_create_watch)
+        schema_properties = get_watch_schema_properties()
+        for param_name, param_value in request.args.items():
+            # Skip special parameters
+            if param_name in special_params:
+                continue
+
+            # Skip if not in schema (unknown parameter)
+            if param_name not in schema_properties:
+                return f"Unknown watch configuration parameter: {param_name}", 400
+
+            # Convert to appropriate type based on schema
+            try:
+                converted_value = convert_query_param_to_type(param_value, schema_properties[param_name])
+                extras[param_name] = converted_value
+            except (ValueError, json.JSONDecodeError) as e:
+                return f"Invalid value for parameter '{param_name}': {str(e)}", 400
+
+        # Validate processor if provided
+        if 'processor' in extras:
+            from changedetectionio.processors import available_processors
+            available = [p[0] for p in available_processors()]
+            if extras['processor'] not in available:
+                return f"Invalid processor '{extras['processor']}'. Available processors: {', '.join(available)}", 400
+
+        # Validate fetch_backend if provided
+        if 'fetch_backend' in extras:
+            from changedetectionio.content_fetchers import available_fetchers
+            available = [f[0] for f in available_fetchers()]
+            # Also allow 'system' and extra_browser_* patterns
+            is_valid = (
+                extras['fetch_backend'] == 'system' or
+                extras['fetch_backend'] in available or
+                extras['fetch_backend'].startswith('extra_browser_')
+            )
+            if not is_valid:
+                return f"Invalid fetch_backend '{extras['fetch_backend']}'. Available: system, {', '.join(available)}", 400
+
+        # Validate notification_urls if provided
+        if 'notification_urls' in extras:
+            from wtforms import ValidationError
+            from changedetectionio.api.Notifications import validate_notification_urls
+            try:
+                validate_notification_urls(extras['notification_urls'])
+            except ValidationError as e:
+                return f"Invalid notification_urls: {str(e)}", 400
+
         urls = request.get_data().decode('utf8').splitlines()
-        added = []
-        allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
+        # Clean and validate URLs upfront
+        urls_to_import = []
         for url in urls:
             url = url.strip()
             if not len(url):
                 continue
 
-            # If hosts that only contain alphanumerics are allowed ("localhost" for example)
-            if not validators.url(url, simple_host=allow_simplehost):
+            # Validate URL
+            if not is_safe_valid_url(url):
                 return f"Invalid or unsupported URL - {url}", 400
 
+            # Check for duplicates if dedupe is enabled
             if dedupe and self.datastore.url_exists(url):
                 continue
 
-            new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags, tag_uuids=tag_uuids)
-            added.append(new_uuid)
+            urls_to_import.append(url)
 
-        return added
+        # For small imports, process synchronously for immediate feedback
+        if len(urls_to_import) < IMPORT_SWITCH_TO_BACKGROUND_THRESHOLD:
+            added = []
+            for url in urls_to_import:
+                new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags, tag_uuids=tag_uuids)
+                added.append(new_uuid)
+            return added, 200
+
+        # For large imports (>= 20), process in background thread
+        else:
+            import threading
+            from loguru import logger
+
+            def import_watches_background():
+                """Background thread to import watches - discarded after completion."""
+                try:
+                    added_count = 0
+                    for url in urls_to_import:
+                        try:
+                            self.datastore.add_watch(url=url, extras=extras, tag=tags, tag_uuids=tag_uuids)
+                            added_count += 1
+                        except Exception as e:
+                            logger.error(f"Error importing URL {url}: {e}")
+
+                    logger.info(f"Background import complete: {added_count} watches created")
+                except Exception as e:
+                    logger.error(f"Error in background import: {e}")
+
+            # Start background thread and return immediately
+            thread = threading.Thread(target=import_watches_background, daemon=True, name="ImportWatches-Background")
+            thread.start()
+
+            return {'status': f'Importing {len(urls_to_import)} URLs in background', 'count': len(urls_to_import)}, 202

changedetectionio/api/Notifications.py

@@ -1,10 +1,6 @@
-from flask_expects_json import expects_json
-from flask_restful import Resource
-from . import auth
-from flask_restful import abort, Resource
+from flask_restful import Resource, abort
 from flask import request
-from . import auth
-from . import schema_create_notification_urls, schema_delete_notification_urls
+from . import auth, validate_openapi_request
 
 class Notifications(Resource):
     def __init__(self, **kwargs):
@@ -12,19 +8,9 @@ class Notifications(Resource):
         self.datastore = kwargs['datastore']
 
     @auth.check_token
+    @validate_openapi_request('getNotifications')
     def get(self):
-        """
-        @api {get} /api/v1/notifications Return Notification URL List
-        @apiDescription Return the Notification URL List from the configuration
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/notifications -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            HTTP/1.0 200
-            {
-                'notification_urls': ["notification-urls-list"]
-            }
-        @apiName Get
-        @apiGroup Notifications
-        """
+        """Return Notification URL List."""
 
         notification_urls = self.datastore.data.get('settings', {}).get('application', {}).get('notification_urls', [])        
 
@@ -33,18 +19,9 @@ class Notifications(Resource):
                }, 200
     
     @auth.check_token
-    @expects_json(schema_create_notification_urls)
+    @validate_openapi_request('addNotifications')
     def post(self):
-        """
-        @api {post} /api/v1/notifications Create Notification URLs
-        @apiDescription Add one or more notification URLs from the configuration
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/notifications/batch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"notification_urls": ["url1", "url2"]}'
-        @apiName CreateBatch
-        @apiGroup Notifications
-        @apiSuccess (201) {Object[]} notification_urls List of added notification URLs
-        @apiError (400) {String} Invalid input
-        """
+        """Create Notification URLs."""
 
         json_data = request.get_json()
         notification_urls = json_data.get("notification_urls", [])
@@ -69,18 +46,9 @@ class Notifications(Resource):
         return {'notification_urls': added_urls}, 201
     
     @auth.check_token
-    @expects_json(schema_create_notification_urls)
+    @validate_openapi_request('replaceNotifications')
     def put(self):
-        """
-        @api {put} /api/v1/notifications Replace Notification URLs
-        @apiDescription Replace all notification URLs with the provided list (can be empty)
-        @apiExample {curl} Example usage:
-            curl -X PUT http://localhost:5000/api/v1/notifications -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"notification_urls": ["url1", "url2"]}'
-        @apiName Replace
-        @apiGroup Notifications
-        @apiSuccess (200) {Object[]} notification_urls List of current notification URLs
-        @apiError (400) {String} Invalid input
-        """
+        """Replace Notification URLs."""
         json_data = request.get_json()
         notification_urls = json_data.get("notification_urls", [])
 
@@ -95,24 +63,14 @@ class Notifications(Resource):
 
         clean_urls = [url.strip() for url in notification_urls if isinstance(url, str)]
         self.datastore.data['settings']['application']['notification_urls'] = clean_urls
-        self.datastore.needs_write = True
+        self.datastore.commit()
 
         return {'notification_urls': clean_urls}, 200
         
     @auth.check_token
-    @expects_json(schema_delete_notification_urls)
+    @validate_openapi_request('deleteNotifications')
     def delete(self):
-        """
-        @api {delete} /api/v1/notifications Delete Notification URLs
-        @apiDescription Deletes one or more notification URLs from the configuration
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/notifications -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"notification_urls": ["url1", "url2"]}'
-        @apiParam {String[]} notification_urls The notification URLs to delete.
-        @apiName Delete
-        @apiGroup Notifications
-        @apiSuccess (204) {String} OK Deleted
-        @apiError (400) {String} No matching notification URLs found.
-        """
+        """Delete Notification URLs."""
 
         json_data = request.get_json()
         urls_to_delete = json_data.get("notification_urls", [])
@@ -132,7 +90,7 @@ class Notifications(Resource):
             abort(400, message="No matching notification URLs found.")
 
         self.datastore.data['settings']['application']['notification_urls'] = notification_urls
-        self.datastore.needs_write = True
+        self.datastore.commit()
 
         return 'OK', 204
     

changedetectionio/api/Search.py

@@ -1,6 +1,6 @@
 from flask_restful import Resource, abort
 from flask import request
-from . import auth
+from . import auth, validate_openapi_request
 
 class Search(Resource):
     def __init__(self, **kwargs):
@@ -8,21 +8,9 @@ class Search(Resource):
         self.datastore = kwargs['datastore']
 
     @auth.check_token
+    @validate_openapi_request('searchWatches')
     def get(self):
-        """
-        @api {get} /api/v1/search Search for watches
-        @apiDescription Search watches by URL or title text
-        @apiExample {curl} Example usage:
-            curl "http://localhost:5000/api/v1/search?q=https://example.com/page1" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/search?q=https://example.com/page1?tag=Favourites" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/search?q=https://example.com?partial=true" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiName Search
-        @apiGroup Watch Management
-        @apiQuery {String} q Search query to match against watch URLs and titles
-        @apiQuery {String} [tag] Optional name of tag to limit results (name not UUID)
-        @apiQuery {String} [partial] Allow partial matching of URL query
-        @apiSuccess (200) {Object} JSON Object containing matched watches
-        """
+        """Search for watches by URL or title text."""
         query = request.args.get('q', '').strip()
         tag_limit = request.args.get('tag', '').strip()
         from changedetectionio.strtobool import strtobool

changedetectionio/api/SystemInfo.py

@@ -1,5 +1,5 @@
 from flask_restful import Resource
-from . import auth
+from . import auth, validate_openapi_request
 
 
 class SystemInfo(Resource):
@@ -9,23 +9,9 @@ class SystemInfo(Resource):
         self.update_q = kwargs['update_q']
 
     @auth.check_token
+    @validate_openapi_request('getSystemInfo')
     def get(self):
-        """
-        @api {get} /api/v1/systeminfo Return system info
-        @apiDescription Return some info about the current system state
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/systeminfo -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            HTTP/1.0 200
-            {
-                'queue_size': 10 ,
-                'overdue_watches': ["watch-uuid-list"],
-                'uptime': 38344.55,
-                'watch_count': 800,
-                'version': "0.40.1"
-            }
-        @apiName Get Info
-        @apiGroup System Information
-        """
+        """Return system info."""
         import time
         overdue_watches = []
 

changedetectionio/api/Tags.py

@@ -1,114 +1,190 @@
-from flask_expects_json import expects_json
+from changedetectionio import queuedWatchMetaData
+from changedetectionio import worker_pool
 from flask_restful import abort, Resource
+from loguru import logger
+
+import threading
 from flask import request
 from . import auth
 
-# Import schemas from __init__.py
-from . import schema_tag, schema_create_tag, schema_update_tag
+from . import validate_openapi_request
 
 
 class Tag(Resource):
     def __init__(self, **kwargs):
         # datastore is a black box dependency
         self.datastore = kwargs['datastore']
+        self.update_q = kwargs['update_q']
 
     # Get information about a single tag
     # curl http://localhost:5000/api/v1/tag/<string:uuid>
     @auth.check_token
+    @validate_openapi_request('getTag')
     def get(self, uuid):
-        """
-        @api {get} /api/v1/tag/:uuid Single tag - get data or toggle notification muting.
-        @apiDescription Retrieve tag information and set notification_muted status
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/tag/cc0cfffa-f449-477b-83ea-0caafd1dc091 -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/tag/cc0cfffa-f449-477b-83ea-0caafd1dc091?muted=muted" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiName Tag
-        @apiGroup Tag
-        @apiParam {uuid} uuid Tag unique ID.
-        @apiQuery {String} [muted] =`muted` or =`unmuted` , Sets the MUTE NOTIFICATIONS state
-        @apiSuccess (200) {String} OK When muted operation OR full JSON object of the tag
-        @apiSuccess (200) {JSON} TagJSON JSON Full JSON object of the tag
-        """
-        from copy import deepcopy
-        tag = deepcopy(self.datastore.data['settings']['application']['tags'].get(uuid))
+        """Get data for a single tag/group, toggle notification muting, or recheck all."""
+        tag = self.datastore.data['settings']['application']['tags'].get(uuid)
         if not tag:
             abort(404, message=f'No tag exists with the UUID of {uuid}')
 
+        if request.args.get('recheck'):
+            # Recheck all watches with this tag, including muted
+            # First collect watches to queue
+            watches_to_queue = []
+            for k in sorted(self.datastore.data['watching'].items(), key=lambda item: item[1].get('last_checked', 0)):
+                watch_uuid = k[0]
+                watch = k[1]
+                if not watch['paused'] and tag['uuid'] in watch['tags']:
+                    watches_to_queue.append(watch_uuid)
+
+            # If less than 20 watches, queue synchronously for immediate feedback
+            if len(watches_to_queue) < 20:
+                for watch_uuid in watches_to_queue:
+                    worker_pool.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
+                return {'status': f'OK, queued {len(watches_to_queue)} watches for rechecking'}, 200
+            else:
+                # 20+ watches - queue in background thread to avoid blocking API response
+                def queue_watches_background():
+                    """Background thread to queue watches - discarded after completion."""
+                    try:
+                        for watch_uuid in watches_to_queue:
+                            worker_pool.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
+                        logger.info(f"Background queueing complete for tag {tag['uuid']}: {len(watches_to_queue)} watches queued")
+                    except Exception as e:
+                        logger.error(f"Error in background queueing for tag {tag['uuid']}: {e}")
+
+                # Start background thread and return immediately
+                thread = threading.Thread(target=queue_watches_background, daemon=True, name=f"QueueTag-{tag['uuid'][:8]}")
+                thread.start()
+
+                return {'status': f'OK, queueing {len(watches_to_queue)} watches in background'}, 202
+
         if request.args.get('muted', '') == 'muted':
-            self.datastore.data['settings']['application']['tags'][uuid]['notification_muted'] = True
+            tag['notification_muted'] = True
+            tag.commit()
             return "OK", 200
         elif request.args.get('muted', '') == 'unmuted':
-            self.datastore.data['settings']['application']['tags'][uuid]['notification_muted'] = False
+            tag['notification_muted'] = False
+            tag.commit()
             return "OK", 200
 
-        return tag
+        # Filter out Watch-specific runtime fields that don't apply to Tags (yet)
+        # TODO: Future enhancement - aggregate these values from all Watches that have this tag:
+        #   - check_count: sum of all watches' check_count
+        #   - last_checked: most recent last_checked from all watches
+        #   - last_changed: most recent last_changed from all watches
+        #   - consecutive_filter_failures: count of watches with failures
+        #   - etc.
+        # These come from watch_base inheritance but currently have no meaningful value for Tags
+        watch_only_fields = {
+            'browser_steps_last_error_step', 'check_count', 'consecutive_filter_failures',
+            'content-type', 'fetch_time', 'last_changed', 'last_checked', 'last_error',
+            'last_notification_error', 'last_viewed', 'notification_alert_count',
+            'page_title', 'previous_md5', 'remote_server_reply'
+        }
+
+        # Create clean tag dict without Watch-specific fields
+        clean_tag = {k: v for k, v in tag.items() if k not in watch_only_fields}
+
+        return clean_tag
 
     @auth.check_token
+    @validate_openapi_request('deleteTag')
     def delete(self, uuid):
-        """
-        @api {delete} /api/v1/tag/:uuid Delete a tag and remove it from all watches
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/tag/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiParam {uuid} uuid Tag unique ID.
-        @apiName DeleteTag
-        @apiGroup Tag
-        @apiSuccess (200) {String} OK Was deleted
-        """
+        """Delete a tag/group and remove it from all watches."""
         if not self.datastore.data['settings']['application']['tags'].get(uuid):
             abort(400, message='No tag exists with the UUID of {}'.format(uuid))
 
         # Delete the tag, and any tag reference
         del self.datastore.data['settings']['application']['tags'][uuid]
-        
+
+        # Delete tag.json file if it exists
+        import os
+        tag_dir = os.path.join(self.datastore.datastore_path, uuid)
+        tag_json = os.path.join(tag_dir, "tag.json")
+        if os.path.exists(tag_json):
+            try:
+                os.unlink(tag_json)
+                logger.info(f"Deleted tag.json for tag {uuid}")
+            except Exception as e:
+                logger.error(f"Failed to delete tag.json for tag {uuid}: {e}")
+
         # Remove tag from all watches
         for watch_uuid, watch in self.datastore.data['watching'].items():
             if watch.get('tags') and uuid in watch['tags']:
                 watch['tags'].remove(uuid)
+                watch.commit()
 
         return 'OK', 204
 
     @auth.check_token
-    @expects_json(schema_update_tag)
+    @validate_openapi_request('updateTag')
     def put(self, uuid):
-        """
-        @api {put} /api/v1/tag/:uuid Update tag information
-        @apiExample {curl} Example usage:
-            Update (PUT)
-            curl http://localhost:5000/api/v1/tag/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X PUT -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"title": "New Tag Title"}'
-
-        @apiDescription Updates an existing tag using JSON
-        @apiParam {uuid} uuid Tag unique ID.
-        @apiName UpdateTag
-        @apiGroup Tag
-        @apiSuccess (200) {String} OK Was updated
-        @apiSuccess (500) {String} ERR Some other error
-        """
+        """Update tag information."""
         tag = self.datastore.data['settings']['application']['tags'].get(uuid)
         if not tag:
             abort(404, message='No tag exists with the UUID of {}'.format(uuid))
 
-        tag.update(request.json)
-        self.datastore.needs_write_urgent = True
+        # Make a mutable copy of request.json for modification
+        json_data = dict(request.json)
+
+        # Validate notification_urls if provided
+        if 'notification_urls' in json_data:
+            from wtforms import ValidationError
+            from changedetectionio.api.Notifications import validate_notification_urls
+            try:
+                notification_urls = json_data.get('notification_urls', [])
+                validate_notification_urls(notification_urls)
+            except ValidationError as e:
+                return str(e), 400
+
+        # Filter out readOnly fields (extracted from OpenAPI spec Tag schema)
+        # These are system-managed fields that should never be user-settable
+        from . import get_readonly_tag_fields
+        readonly_fields = get_readonly_tag_fields()
+
+        # Tag model inherits from watch_base but has no @property attributes of its own
+        # So we only need to filter readOnly fields
+        for field in readonly_fields:
+            json_data.pop(field, None)
+
+        # Validate remaining fields - reject truly unknown fields
+        # Get valid fields from Tag schema
+        from . import get_tag_schema_properties
+        valid_fields = set(get_tag_schema_properties().keys())
+
+        # Check for unknown fields
+        unknown_fields = set(json_data.keys()) - valid_fields
+        if unknown_fields:
+            return f"Unknown field(s): {', '.join(sorted(unknown_fields))}", 400
+
+        tag.update(json_data)
+        tag.commit()
+
+        # Clear checksums for all watches using this tag to force reprocessing
+        # Tag changes affect inherited configuration
+        cleared_count = self.datastore.clear_checksums_for_tag(uuid)
+        logger.info(f"Tag {uuid} updated via API, cleared {cleared_count} watch checksums")
 
         return "OK", 200
 
 
     @auth.check_token
-    # Only cares for {'title': 'xxxx'}
+    @validate_openapi_request('createTag')
     def post(self):
-        """
-        @api {post} /api/v1/watch Create a single tag
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"name": "Work related"}'
-        @apiName Create
-        @apiGroup Tag
-        @apiSuccess (200) {String} OK Was created
-        @apiSuccess (500) {String} ERR Some other error
-        """
+        """Create a single tag/group."""
 
         json_data = request.get_json()
         title = json_data.get("title",'').strip()
 
+        # Validate that only valid fields are provided
+        # Get valid fields from Tag schema
+        from . import get_tag_schema_properties
+        valid_fields = set(get_tag_schema_properties().keys())
+
+        # Check for unknown fields
+        unknown_fields = set(json_data.keys()) - valid_fields
+        if unknown_fields:
+            return f"Unknown field(s): {', '.join(sorted(unknown_fields))}", 400
 
         new_uuid = self.datastore.add_tag(title=title)
         if new_uuid:
@@ -122,28 +198,9 @@ class Tags(Resource):
         self.datastore = kwargs['datastore']
 
     @auth.check_token
+    @validate_openapi_request('listTags')
     def get(self):
-        """
-        @api {get} /api/v1/tags List tags
-        @apiDescription Return list of available tags
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/tags -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            {
-                "cc0cfffa-f449-477b-83ea-0caafd1dc091": {
-                    "title": "Tech News",
-                    "notification_muted": false,
-                    "date_created": 1677103794
-                },
-                "e6f5fd5c-dbfe-468b-b8f3-f9d6ff5ad69b": {
-                    "title": "Shopping",
-                    "notification_muted": true,
-                    "date_created": 1676662819
-                }
-            }
-        @apiName ListTags
-        @apiGroup Tag Management
-        @apiSuccess (200) {String} OK JSON dict
-        """
+        """List tags/groups."""
         result = {}
         for uuid, tag in self.datastore.data['settings']['application']['tags'].items():
             result[uuid] = {

changedetectionio/api/Watch.py

@@ -1,16 +1,53 @@
 import os
-from changedetectionio.strtobool import strtobool
+import threading
+
+from changedetectionio.validate_url import is_safe_valid_url
+from changedetectionio.favicon_utils import get_favicon_mime_type
 
-from flask_expects_json import expects_json
-from changedetectionio import queuedWatchMetaData
-from flask_restful import abort, Resource
-from flask import request, make_response
-import validators
 from . import auth
+from changedetectionio import queuedWatchMetaData, strtobool
+from changedetectionio import worker_pool
+from flask import request, make_response, send_from_directory
+from flask_restful import abort, Resource
+from loguru import logger
 import copy
 
-# Import schemas from __init__.py
-from . import schema, schema_create_watch, schema_update_watch
+from . import validate_openapi_request, get_readonly_watch_fields
+from ..notification import valid_notification_formats
+from ..notification.handler import newline_re
+
+
+def validate_time_between_check_required(json_data):
+    """
+    Validate that at least one time interval is specified when not using default settings.
+    Returns None if valid, or error message string if invalid.
+    Defaults to using global settings if time_between_check_use_default is not provided.
+    """
+    # Default to using global settings if not specified
+    use_default = json_data.get('time_between_check_use_default', True)
+
+    # If using default settings, no validation needed
+    if use_default:
+        return None
+
+    # If not using defaults, check if time_between_check exists and has at least one non-zero value
+    time_check = json_data.get('time_between_check')
+    if not time_check:
+        # No time_between_check provided and not using defaults - this is an error
+        return "At least one time interval (weeks, days, hours, minutes, or seconds) must be specified when not using global settings."
+
+    # time_between_check exists, check if it has at least one non-zero value
+    if any([
+        (time_check.get('weeks') or 0) > 0,
+        (time_check.get('days') or 0) > 0,
+        (time_check.get('hours') or 0) > 0,
+        (time_check.get('minutes') or 0) > 0,
+        (time_check.get('seconds') or 0) > 0
+    ]):
+        return None
+
+    # time_between_check exists but all values are 0 or empty - this is an error
+    return "At least one time interval (weeks, days, hours, minutes, or seconds) must be specified when not using global settings."
 
 
 class Watch(Resource):
@@ -24,63 +61,56 @@ class Watch(Resource):
     # @todo - version2 - ?muted and ?paused should be able to be called together, return the watch struct not "OK"
     # ?recheck=true
     @auth.check_token
+    @validate_openapi_request('getWatch')
     def get(self, uuid):
-        """
-        @api {get} /api/v1/watch/:uuid Single watch - get data, recheck, pause, mute.
-        @apiDescription Retrieve watch information and set muted/paused status
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?muted=unmuted"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?paused=unpaused"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiName Watch
-        @apiGroup Watch
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiQuery {Boolean} [recheck] Recheck this watch `recheck=1`
-        @apiQuery {String} [paused] =`paused` or =`unpaused` , Sets the PAUSED state
-        @apiQuery {String} [muted] =`muted` or =`unmuted` , Sets the MUTE NOTIFICATIONS state
-        @apiSuccess (200) {String} OK When paused/muted/recheck operation OR full JSON object of the watch
-        @apiSuccess (200) {JSON} WatchJSON JSON Full JSON object of the watch
-        """
-        from copy import deepcopy
-        watch = deepcopy(self.datastore.data['watching'].get(uuid))
-        if not watch:
+        """Get information about a single watch, recheck, pause, or mute."""
+        # Get watch reference first (for pause/mute operations)
+        watch_obj = self.datastore.data['watching'].get(uuid)
+        if not watch_obj:
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
 
+        # Create a dict copy for JSON response (with lock for thread safety)
+        # This is much faster than deepcopy and doesn't copy the datastore reference
+        # WARNING: dict() is a SHALLOW copy - nested dicts are shared with original!
+        # Only safe because we only ADD scalar properties (line 97-101), never modify nested dicts
+        # If you need to modify nested dicts, use: from copy import deepcopy; watch = deepcopy(dict(watch_obj))
+        with self.datastore.lock:
+            watch = dict(watch_obj)
+
         if request.args.get('recheck'):
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+            worker_pool.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             return "OK", 200
         if request.args.get('paused', '') == 'paused':
-            self.datastore.data['watching'].get(uuid).pause()
+            watch_obj.pause()
+            watch_obj.commit()
             return "OK", 200
         elif request.args.get('paused', '') == 'unpaused':
-            self.datastore.data['watching'].get(uuid).unpause()
+            watch_obj.unpause()
+            watch_obj.commit()
             return "OK", 200
         if request.args.get('muted', '') == 'muted':
-            self.datastore.data['watching'].get(uuid).mute()
+            watch_obj.mute()
+            watch_obj.commit()
             return "OK", 200
         elif request.args.get('muted', '') == 'unmuted':
-            self.datastore.data['watching'].get(uuid).unmute()
+            watch_obj.unmute()
+            watch_obj.commit()
             return "OK", 200
 
         # Return without history, get that via another API call
         # Properties are not returned as a JSON, so add the required props manually
-        watch['history_n'] = watch.history_n
+        watch['history_n'] = watch_obj.history_n
         # attr .last_changed will check for the last written text snapshot on change
-        watch['last_changed'] = watch.last_changed
-        watch['viewed'] = watch.viewed
+        watch['last_changed'] = watch_obj.last_changed
+        watch['viewed'] = watch_obj.viewed
+        watch['link'] = watch_obj.link,
+
         return watch
 
     @auth.check_token
+    @validate_openapi_request('deleteWatch')
     def delete(self, uuid):
-        """
-        @api {delete} /api/v1/watch/:uuid Delete a watch and related history
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiName Delete
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was deleted
-        """
+        """Delete a watch and related history."""
         if not self.datastore.data['watching'].get(uuid):
             abort(400, message='No watch exists with the UUID of {}'.format(uuid))
 
@@ -88,31 +118,95 @@ class Watch(Resource):
         return 'OK', 204
 
     @auth.check_token
-    @expects_json(schema_update_watch)
+    @validate_openapi_request('updateWatch')
     def put(self, uuid):
-        """
-        @api {put} /api/v1/watch/:uuid Update watch information
-        @apiExample {curl} Example usage:
-            Update (PUT)
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X PUT -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "new list"}'
-
-        @apiDescription Updates an existing watch using JSON, accepts the same structure as returned in <a href="#api-Watch-Watch">get single watch information</a>
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiName Update a watch
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was updated
-        @apiSuccess (500) {String} ERR Some other error
-        """
+        """Update watch information."""
         watch = self.datastore.data['watching'].get(uuid)
         if not watch:
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
 
         if request.json.get('proxy'):
             plist = self.datastore.proxy_list
-            if not request.json.get('proxy') in plist:
-                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
+            if not plist or request.json.get('proxy') not in plist:
+                proxy_list_str = ', '.join(plist) if plist else 'none configured'
+                return f"Invalid proxy choice, currently supported proxies are '{proxy_list_str}'", 400
 
-        watch.update(request.json)
+        # Validate time_between_check when not using defaults
+        validation_error = validate_time_between_check_required(request.json)
+        if validation_error:
+            return validation_error, 400
+
+        # Validate notification_urls if provided
+        if 'notification_urls' in request.json:
+            from wtforms import ValidationError
+            from changedetectionio.api.Notifications import validate_notification_urls
+            try:
+                notification_urls = request.json.get('notification_urls', [])
+                validate_notification_urls(notification_urls)
+            except ValidationError as e:
+                return str(e), 400
+
+        # XSS etc protection - validate URL if it's being updated
+        if 'url' in request.json:
+            new_url = request.json.get('url')
+
+            # URL must be a non-empty string
+            if new_url is None:
+                return "URL cannot be null", 400
+
+            if not isinstance(new_url, str):
+                return "URL must be a string", 400
+
+            if not new_url.strip():
+                return "URL cannot be empty or whitespace only", 400
+
+            if not is_safe_valid_url(new_url.strip()):
+                return "Invalid or unsupported URL format. URL must use http://, https://, or ftp:// protocol", 400
+
+        # Handle processor-config-* fields separately (save to JSON, not datastore)
+        from changedetectionio import processors
+
+        # Make a mutable copy of request.json for modification
+        json_data = dict(request.json)
+
+        # Extract and remove processor config fields from json_data
+        processor_config_data = processors.extract_processor_config_from_form_data(json_data)
+
+        # Filter out readOnly fields (extracted from OpenAPI spec Watch schema)
+        # These are system-managed fields that should never be user-settable
+        readonly_fields = get_readonly_watch_fields()
+
+        # Also filter out @property attributes (computed/derived values from the model)
+        # These are not stored and should be ignored in PUT requests
+        from changedetectionio.model.Watch import model as WatchModel
+        property_fields = WatchModel.get_property_names()
+
+        # Combine both sets of fields to ignore
+        fields_to_ignore = readonly_fields | property_fields
+
+        # Remove all ignored fields from update data
+        for field in fields_to_ignore:
+            json_data.pop(field, None)
+
+        # Validate remaining fields - reject truly unknown fields
+        # Get valid fields from WatchBase schema
+        from . import get_watch_schema_properties
+        valid_fields = set(get_watch_schema_properties().keys())
+
+        # Also allow last_viewed (explicitly defined in UpdateWatch schema)
+        valid_fields.add('last_viewed')
+
+        # Check for unknown fields
+        unknown_fields = set(json_data.keys()) - valid_fields
+        if unknown_fields:
+            return f"Unknown field(s): {', '.join(sorted(unknown_fields))}", 400
+
+        # Update watch with regular (non-processor-config) fields
+        watch.update(json_data)
+        watch.commit()
+
+        # Save processor config to JSON file
+        processors.save_processor_config(self.datastore, uuid, processor_config_data)
 
         return "OK", 200
 
@@ -125,22 +219,9 @@ class WatchHistory(Resource):
     # Get a list of available history for a watch by UUID
     # curl http://localhost:5000/api/v1/watch/<string:uuid>/history
     @auth.check_token
+    @validate_openapi_request('getWatchHistory')
     def get(self, uuid):
-        """
-        @api {get} /api/v1/watch/<string:uuid>/history Get a list of all historical snapshots available for a watch
-        @apiDescription Requires `uuid`, returns list
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
-            {
-                "1676649279": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/cb7e9be8258368262246910e6a2a4c30.txt",
-                "1677092785": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/e20db368d6fc633e34f559ff67bb4044.txt",
-                "1677103794": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/02efdd37dacdae96554a8cc85dc9c945.txt"
-            }
-        @apiName Get list of available stored snapshots for watch
-        @apiGroup Watch History
-        @apiSuccess (200) {String} OK
-        @apiSuccess (404) {String} ERR Not found
-        """
+        """Get a list of all historical snapshots available for a watch."""
         watch = self.datastore.data['watching'].get(uuid)
         if not watch:
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
@@ -153,18 +234,9 @@ class WatchSingleHistory(Resource):
         self.datastore = kwargs['datastore']
 
     @auth.check_token
+    @validate_openapi_request('getWatchSnapshot')
     def get(self, uuid, timestamp):
-        """
-        @api {get} /api/v1/watch/<string:uuid>/history/<int:timestamp> Get single snapshot from watch
-        @apiDescription Requires watch `uuid` and `timestamp`. `timestamp` of "`latest`" for latest available snapshot, or <a href="#api-Watch_History-Get_list_of_available_stored_snapshots_for_watch">use the list returned here</a>
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history/1677092977 -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
-        @apiName Get single snapshot content
-        @apiGroup Watch History
-        @apiParam {String} [html]       Optional Set to =1 to return the last HTML (only stores last 2 snapshots, use `latest` as timestamp)
-        @apiSuccess (200) {String} OK
-        @apiSuccess (404) {String} ERR Not found
-        """
+        """Get single snapshot from watch."""
         watch = self.datastore.data['watching'].get(uuid)
         if not watch:
             abort(404, message=f"No watch exists with the UUID of {uuid}")
@@ -175,6 +247,10 @@ class WatchSingleHistory(Resource):
         if timestamp == 'latest':
             timestamp = list(watch.history.keys())[-1]
 
+        # Validate that the timestamp exists in history
+        if timestamp not in watch.history:
+            abort(404, message=f"No history snapshot found for timestamp '{timestamp}'")
+
         if request.args.get('html'):
             content = watch.get_fetched_html(timestamp)
             if content:
@@ -184,12 +260,156 @@ class WatchSingleHistory(Resource):
                 response = make_response("No content found", 404)
                 response.mimetype = "text/plain"
         else:
-            content = watch.get_history_snapshot(timestamp)
+            content = watch.get_history_snapshot(timestamp=timestamp)
             response = make_response(content, 200)
             response.mimetype = "text/plain"
 
         return response
 
+class WatchHistoryDiff(Resource):
+    """
+    Generate diff between two historical snapshots.
+
+    Note: This API endpoint currently returns text-based diffs and works best
+    with the text_json_diff processor. Future processor types (like image_diff,
+    restock_diff) may want to implement their own specialized API endpoints
+    for returning processor-specific data (e.g., price charts, image comparisons).
+
+    The web UI diff page (/diff/<uuid>) is processor-aware and delegates rendering
+    to processors/{type}/difference.py::render() for processor-specific visualizations.
+    """
+    def __init__(self, **kwargs):
+        # datastore is a black box dependency
+        self.datastore = kwargs['datastore']
+
+    @auth.check_token
+    @validate_openapi_request('getWatchHistoryDiff')
+    def get(self, uuid, from_timestamp, to_timestamp):
+        """Generate diff between two historical snapshots."""
+        from changedetectionio import diff
+        from changedetectionio.notification.handler import apply_service_tweaks
+
+        watch = self.datastore.data['watching'].get(uuid)
+        if not watch:
+            abort(404, message=f"No watch exists with the UUID of {uuid}")
+
+        if not len(watch.history):
+            abort(404, message=f"Watch found but no history exists for the UUID {uuid}")
+
+        history_keys = list(watch.history.keys())
+
+        # Handle 'latest' keyword for to_timestamp
+        if to_timestamp == 'latest':
+            to_timestamp = history_keys[-1]
+
+        # Handle 'previous' keyword for from_timestamp (second-most-recent)
+        if from_timestamp == 'previous':
+            if len(history_keys) < 2:
+                abort(404, message=f"Not enough history entries. Need at least 2 snapshots for 'previous'")
+            from_timestamp = history_keys[-2]
+
+        # Validate timestamps exist
+        if from_timestamp not in watch.history:
+            abort(404, message=f"From timestamp {from_timestamp} not found in watch history")
+        if to_timestamp not in watch.history:
+            abort(404, message=f"To timestamp {to_timestamp} not found in watch history")
+
+        # Get the format parameter (default to 'text')
+        output_format = request.args.get('format', 'text').lower()
+
+        # Validate format
+        if output_format not in valid_notification_formats.keys():
+            abort(400, message=f"Invalid format. Must be one of: {', '.join(valid_notification_formats.keys())}")
+
+        # Get the word_diff parameter (default to False - line-level mode)
+        word_diff = strtobool(request.args.get('word_diff', 'false'))
+
+        # Get the no_markup parameter (default to False)
+        no_markup = strtobool(request.args.get('no_markup', 'false'))
+
+        # Retrieve snapshot contents
+        from_version_file_contents = watch.get_history_snapshot(from_timestamp)
+        to_version_file_contents = watch.get_history_snapshot(to_timestamp)
+
+        # Get diff preferences from query parameters (matching UI preferences in DIFF_PREFERENCES_CONFIG)
+        # Support both 'type' (UI parameter) and 'word_diff' (API parameter) for backward compatibility
+        diff_type = request.args.get('type', 'diffLines')
+        if diff_type == 'diffWords':
+            word_diff = True
+
+        # Get boolean diff preferences with defaults from DIFF_PREFERENCES_CONFIG
+        changes_only = strtobool(request.args.get('changesOnly', 'true'))
+        ignore_whitespace = strtobool(request.args.get('ignoreWhitespace', 'false'))
+        include_removed = strtobool(request.args.get('removed', 'true'))
+        include_added = strtobool(request.args.get('added', 'true'))
+        include_replaced = strtobool(request.args.get('replaced', 'true'))
+
+        # Generate the diff with all preferences
+        content = diff.render_diff(
+            previous_version_file_contents=from_version_file_contents,
+            newest_version_file_contents=to_version_file_contents,
+            ignore_junk=ignore_whitespace,
+            include_equal=changes_only,
+            include_removed=include_removed,
+            include_added=include_added,
+            include_replaced=include_replaced,
+            word_diff=word_diff,
+        )
+
+        # Skip formatting if no_markup is set
+        if no_markup:
+            mimetype = "text/plain"
+        else:
+            # Apply formatting based on the requested format
+            if output_format == 'htmlcolor':
+                from changedetectionio.notification.handler import apply_html_color_to_body
+                content = apply_html_color_to_body(n_body=content)
+                mimetype = "text/html"
+            else:
+                # Apply service tweaks for text/html formats
+                # Pass empty URL and title as they're not used for the placeholder replacement we need
+                _, content, _ = apply_service_tweaks(
+                    url='',
+                    n_body=content,
+                    n_title='',
+                    requested_output_format=output_format
+                )
+                mimetype = "text/html" if output_format == 'html' else "text/plain"
+
+            if 'html' in output_format:
+                content = newline_re.sub('<br>\r\n', content)
+
+        response = make_response(content, 200)
+        response.mimetype = mimetype
+        return response
+
+
+class WatchFavicon(Resource):
+    def __init__(self, **kwargs):
+        # datastore is a black box dependency
+        self.datastore = kwargs['datastore']
+
+    @auth.check_token
+    @validate_openapi_request('getWatchFavicon')
+    def get(self, uuid):
+        """Get favicon for a watch."""
+        watch = self.datastore.data['watching'].get(uuid)
+        if not watch:
+            abort(404, message=f"No watch exists with the UUID of {uuid}")
+
+        favicon_filename = watch.get_favicon_filename()
+        if favicon_filename:
+            # Use cached MIME type detection
+            filepath = os.path.join(watch.data_dir, favicon_filename)
+            mime = get_favicon_mime_type(filepath)
+
+            response = make_response(send_from_directory(watch.data_dir, favicon_filename))
+            response.headers['Content-type'] = mime
+            response.headers['Cache-Control'] = 'max-age=300, must-revalidate'  # Cache for 5 minutes, then revalidate
+            return response
+
+        abort(404, message=f'No Favicon available for {uuid}')
+
 
 class CreateWatch(Resource):
     def __init__(self, **kwargs):
@@ -198,34 +418,45 @@ class CreateWatch(Resource):
         self.update_q = kwargs['update_q']
 
     @auth.check_token
-    @expects_json(schema_create_watch)
+    @validate_openapi_request('createWatch')
     def post(self):
-        """
-        @api {post} /api/v1/watch Create a single watch
-        @apiDescription Requires atleast `url` set, can accept the same structure as <a href="#api-Watch-Watch">get single watch information</a> to create.
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "nice list"}'
-        @apiName Create
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was created
-        @apiSuccess (500) {String} ERR Some other error
-        """
+        """Create a single watch."""
 
         json_data = request.get_json()
         url = json_data['url'].strip()
 
-        # If hosts that only contain alphanumerics are allowed ("localhost" for example)
-        allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
-        if not validators.url(url, simple_host=allow_simplehost):
+        if not is_safe_valid_url(url):
             return "Invalid or unsupported URL", 400
 
         if json_data.get('proxy'):
             plist = self.datastore.proxy_list
-            if not json_data.get('proxy') in plist:
-                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
+            if not plist or json_data.get('proxy') not in plist:
+                proxy_list_str = ', '.join(plist) if plist else 'none configured'
+                return f"Invalid proxy choice, currently supported proxies are '{proxy_list_str}'", 400
+
+        # Validate time_between_check when not using defaults
+        validation_error = validate_time_between_check_required(json_data)
+        if validation_error:
+            return validation_error, 400
+
+        # Validate notification_urls if provided
+        if 'notification_urls' in json_data:
+            from wtforms import ValidationError
+            from changedetectionio.api.Notifications import validate_notification_urls
+            try:
+                notification_urls = json_data.get('notification_urls', [])
+                validate_notification_urls(notification_urls)
+            except ValidationError as e:
+                return str(e), 400
+
+        # Handle processor-config-* fields separately (save to JSON, not watch)
+        from changedetectionio import processors
 
         extras = copy.deepcopy(json_data)
 
+        # Extract and remove processor config fields from extras
+        processor_config_data = processors.extract_processor_config_from_form_data(extras)
+
         # Because we renamed 'tag' to 'tags' but don't want to change the API (can do this in v2 of the API)
         tags = None
         if extras.get('tag'):
@@ -235,42 +466,31 @@ class CreateWatch(Resource):
         del extras['url']
 
         new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags)
+
+        # Save processor config to separate JSON file
+        if new_uuid and processor_config_data:
+            processors.save_processor_config(self.datastore, new_uuid, processor_config_data)
         if new_uuid:
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
+# Dont queue because the scheduler will check that it hasnt been checked before anyway
+#            worker_pool.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
             return {'uuid': new_uuid}, 201
         else:
+            # Check if it was a limit issue
+            page_watch_limit = os.getenv('PAGE_WATCH_LIMIT')
+            if page_watch_limit:
+                try:
+                    page_watch_limit = int(page_watch_limit)
+                    current_watch_count = len(self.datastore.data['watching'])
+                    if current_watch_count >= page_watch_limit:
+                        return f"Watch limit reached ({current_watch_count}/{page_watch_limit} watches). Cannot add more watches.", 429
+                except ValueError:
+                    pass
             return "Invalid or unsupported URL", 400
 
     @auth.check_token
+    @validate_openapi_request('listWatches')
     def get(self):
-        """
-        @api {get} /api/v1/watch List watches
-        @apiDescription Return concise list of available watches and some very basic info
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            {
-                "6a4b7d5c-fee4-4616-9f43-4ac97046b595": {
-                    "last_changed": 1677103794,
-                    "last_checked": 1677103794,
-                    "last_error": false,
-                    "title": "",
-                    "url": "http://www.quotationspage.com/random.php"
-                },
-                "e6f5fd5c-dbfe-468b-b8f3-f9d6ff5ad69b": {
-                    "last_changed": 0,
-                    "last_checked": 1676662819,
-                    "last_error": false,
-                    "title": "QuickLook",
-                    "url": "https://github.com/QL-Win/QuickLook/tags"
-                }
-            }
-
-        @apiParam {String} [recheck_all]       Optional Set to =1 to force recheck of all watches
-        @apiParam {String} [tag]               Optional name of tag to limit results
-        @apiName ListWatches
-        @apiGroup Watch Management
-        @apiSuccess (200) {String} OK JSON dict
-        """
+        """List watches."""
         list = {}
 
         tag_limit = request.args.get('tag', '').lower()
@@ -284,14 +504,67 @@ class CreateWatch(Resource):
                 'last_changed': watch.last_changed,
                 'last_checked': watch['last_checked'],
                 'last_error': watch['last_error'],
+                'link': watch.link,
+                'page_title': watch['page_title'],
+                'tags': [*tags],  # Unpack dict keys to list (can't use list() since variable named 'list')
                 'title': watch['title'],
                 'url': watch['url'],
                 'viewed': watch.viewed
             }
 
         if request.args.get('recheck_all'):
-            for uuid in self.datastore.data['watching'].keys():
-                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-            return {'status': "OK"}, 200
+            # Collect all watches to queue
+            watches_to_queue = self.datastore.data['watching'].keys()
+
+            # If less than 20 watches, queue synchronously for immediate feedback
+            if len(watches_to_queue) < 20:
+                # Get already queued/running UUIDs once (efficient)
+                queued_uuids = set(self.update_q.get_queued_uuids())
+                running_uuids = set(worker_pool.get_running_uuids())
+
+                # Filter out watches that are already queued or running
+                watches_to_queue_filtered = [
+                    uuid for uuid in watches_to_queue
+                    if uuid not in queued_uuids and uuid not in running_uuids
+                ]
+
+                # Queue only the filtered watches
+                for uuid in watches_to_queue_filtered:
+                    worker_pool.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+
+                # Provide feedback about skipped watches
+                skipped_count = len(watches_to_queue) - len(watches_to_queue_filtered)
+                if skipped_count > 0:
+                    return {'status': f'OK, queued {len(watches_to_queue_filtered)} watches for rechecking ({skipped_count} already queued or running)'}, 200
+                else:
+                    return {'status': f'OK, queued {len(watches_to_queue_filtered)} watches for rechecking'}, 200
+            else:
+                # 20+ watches - queue in background thread to avoid blocking API response
+                # Capture queued/running state before background thread
+                queued_uuids = set(self.update_q.get_queued_uuids())
+                running_uuids = set(worker_pool.get_running_uuids())
+
+                def queue_all_watches_background():
+                    """Background thread to queue all watches - discarded after completion."""
+                    try:
+                        queued_count = 0
+                        skipped_count = 0
+                        for uuid in watches_to_queue:
+                            # Check if already queued or running (state captured at start)
+                            if uuid not in queued_uuids and uuid not in running_uuids:
+                                worker_pool.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                                queued_count += 1
+                            else:
+                                skipped_count += 1
+
+                        logger.info(f"Background queueing complete: {queued_count} watches queued, {skipped_count} skipped (already queued/running)")
+                    except Exception as e:
+                        logger.error(f"Error in background queueing all watches: {e}")
+
+                # Start background thread and return immediately
+                thread = threading.Thread(target=queue_all_watches_background, daemon=True, name="QueueAllWatches-Background")
+                thread.start()
+
+                return {'status': f'OK, queueing {len(watches_to_queue)} watches in background'}, 202
 
         return list, 200

changedetectionio/api/__init__.py

@@ -1,33 +1,140 @@
-import copy
-from . import api_schema
-from ..model import watch_base
+import functools
+from flask import request, abort
+from loguru import logger
 
-# Build a JSON Schema atleast partially based on our Watch model
-watch_base_config = watch_base()
-schema = api_schema.build_watch_json_schema(watch_base_config)
+@functools.cache
+def get_openapi_spec():
+    """Lazy load OpenAPI spec and dependencies only when validation is needed."""
+    import os
+    import yaml  # Lazy import - only loaded when API validation is actually used
+    from openapi_core import OpenAPI  # Lazy import - saves ~10.7 MB on startup
 
-schema_create_watch = copy.deepcopy(schema)
-schema_create_watch['required'] = ['url']
+    spec_path = os.path.join(os.path.dirname(__file__), '../../docs/api-spec.yaml')
+    if not os.path.exists(spec_path):
+        # Possibly for pip3 packages
+        spec_path = os.path.join(os.path.dirname(__file__), '../docs/api-spec.yaml')
 
-schema_update_watch = copy.deepcopy(schema)
-schema_update_watch['additionalProperties'] = False
+    with open(spec_path, 'r', encoding='utf-8') as f:
+        spec_dict = yaml.safe_load(f)
+    _openapi_spec = OpenAPI.from_dict(spec_dict)
+    return _openapi_spec
 
-# Tag schema is also based on watch_base since Tag inherits from it
-schema_tag = copy.deepcopy(schema)
-schema_create_tag = copy.deepcopy(schema_tag)
-schema_create_tag['required'] = ['title']
-schema_update_tag = copy.deepcopy(schema_tag)
-schema_update_tag['additionalProperties'] = False
+@functools.cache
+def get_openapi_schema_dict():
+    """
+    Get the raw OpenAPI spec dictionary for schema access.
 
-schema_notification_urls = copy.deepcopy(schema)
-schema_create_notification_urls = copy.deepcopy(schema_notification_urls)
-schema_create_notification_urls['required'] = ['notification_urls']
-schema_delete_notification_urls = copy.deepcopy(schema_notification_urls)
-schema_delete_notification_urls['required'] = ['notification_urls']
+    Used by Import endpoint to validate and convert query parameters.
+    Returns the YAML dict directly (not the OpenAPI object).
+    """
+    import os
+    import yaml
+
+    spec_path = os.path.join(os.path.dirname(__file__), '../../docs/api-spec.yaml')
+    if not os.path.exists(spec_path):
+        spec_path = os.path.join(os.path.dirname(__file__), '../docs/api-spec.yaml')
+
+    with open(spec_path, 'r', encoding='utf-8') as f:
+        return yaml.safe_load(f)
+
+@functools.cache
+def _resolve_schema_properties(schema_name):
+    """
+    Generic helper to resolve schema properties, including allOf inheritance.
+
+    Args:
+        schema_name: Name of the schema (e.g., 'WatchBase', 'Watch', 'Tag')
+
+    Returns:
+        dict: All properties including inherited ones from $ref schemas
+    """
+    spec_dict = get_openapi_schema_dict()
+    schema = spec_dict['components']['schemas'].get(schema_name, {})
+
+    properties = {}
+
+    # Handle allOf (schema inheritance)
+    if 'allOf' in schema:
+        for item in schema['allOf']:
+            # Resolve $ref to parent schema
+            if '$ref' in item:
+                ref_path = item['$ref'].split('/')[-1]
+                ref_schema = spec_dict['components']['schemas'].get(ref_path, {})
+                properties.update(ref_schema.get('properties', {}))
+            # Add schema-specific properties
+            if 'properties' in item:
+                properties.update(item['properties'])
+    else:
+        # Direct properties (no inheritance)
+        properties = schema.get('properties', {})
+
+    return properties
+
+
+@functools.cache
+def get_watch_schema_properties():
+    """
+    Extract watch schema properties from OpenAPI spec for Import endpoint.
+
+    Returns WatchBase properties (all writable Watch fields).
+    """
+    return _resolve_schema_properties('WatchBase')
+
+# Import readonly field utilities from shared module (avoids circular dependencies with model layer)
+from changedetectionio.model.schema_utils import get_readonly_watch_fields, get_readonly_tag_fields
+
+@functools.cache
+def get_tag_schema_properties():
+    """
+    Extract Tag schema properties from OpenAPI spec.
+
+    Returns WatchBase properties + Tag-specific properties (overrides_watch).
+    """
+    return _resolve_schema_properties('Tag')
+
+def validate_openapi_request(operation_id):
+    """Decorator to validate incoming requests against OpenAPI spec."""
+    def decorator(f):
+        @functools.wraps(f)
+        def wrapper(*args, **kwargs):
+            from werkzeug.exceptions import BadRequest
+            try:
+                # Skip OpenAPI validation for GET requests since they don't have request bodies
+                if request.method.upper() != 'GET':
+                    # Lazy import - only loaded when actually validating a request
+                    from openapi_core.contrib.flask import FlaskOpenAPIRequest
+
+                    spec = get_openapi_spec()
+                    openapi_request = FlaskOpenAPIRequest(request)
+                    result = spec.unmarshal_request(openapi_request)
+                    if result.errors:
+                        error_details = []
+                        for error in result.errors:
+                            # Extract detailed schema errors from __cause__
+                            if hasattr(error, '__cause__') and hasattr(error.__cause__, 'schema_errors'):
+                                for schema_error in error.__cause__.schema_errors:
+                                    field = '.'.join(str(p) for p in schema_error.path) if schema_error.path else 'body'
+                                    msg = schema_error.message if hasattr(schema_error, 'message') else str(schema_error)
+                                    error_details.append(f"{field}: {msg}")
+                            else:
+                                error_details.append(str(error))
+                            logger.error(f"API Call - Validation failed: {'; '.join(error_details)}")
+                        raise BadRequest(f"Validation failed: {'; '.join(error_details)}")
+            except BadRequest:
+                # Re-raise BadRequest exceptions (validation failures)
+                raise
+            except Exception as e:
+                # If OpenAPI spec loading fails, log but don't break existing functionality
+                logger.critical(f"OpenAPI validation warning for {operation_id}: {e}")
+                abort(500)
+            return f(*args, **kwargs)
+        return wrapper
+    return decorator
 
 # Import all API resources
-from .Watch import Watch, WatchHistory, WatchSingleHistory, CreateWatch
+from .Watch import Watch, WatchHistory, WatchSingleHistory, WatchHistoryDiff, CreateWatch, WatchFavicon
 from .Tags import Tags, Tag
 from .Import import Import
 from .SystemInfo import SystemInfo
 from .Notifications import Notifications
+

changedetectionio/api/api_schema.py

@@ -1,146 +0,0 @@
-# Responsible for building the storage dict into a set of rules ("JSON Schema") acceptable via the API
-# Probably other ways to solve this when the backend switches to some ORM
-from changedetectionio.notification import valid_notification_formats
-
-
-def build_time_between_check_json_schema():
-    # Setup time between check schema
-    schema_properties_time_between_check = {
-        "type": "object",
-        "additionalProperties": False,
-        "properties": {}
-    }
-    for p in ['weeks', 'days', 'hours', 'minutes', 'seconds']:
-        schema_properties_time_between_check['properties'][p] = {
-            "anyOf": [
-                {
-                    "type": "integer"
-                },
-                {
-                    "type": "null"
-                }
-            ]
-        }
-
-    return schema_properties_time_between_check
-
-def build_watch_json_schema(d):
-    # Base JSON schema
-    schema = {
-        'type': 'object',
-        'properties': {},
-    }
-
-    for k, v in d.items():
-        # @todo 'integer' is not covered here because its almost always for internal usage
-
-        if isinstance(v, type(None)):
-            schema['properties'][k] = {
-                "anyOf": [
-                    {"type": "null"},
-                ]
-            }
-        elif isinstance(v, list):
-            schema['properties'][k] = {
-                "anyOf": [
-                    {"type": "array",
-                     # Always is an array of strings, like text or regex or something
-                     "items": {
-                         "type": "string",
-                         "maxLength": 5000
-                     }
-                     },
-                ]
-            }
-        elif isinstance(v, bool):
-            schema['properties'][k] = {
-                "anyOf": [
-                    {"type": "boolean"},
-                ]
-            }
-        elif isinstance(v, str):
-            schema['properties'][k] = {
-                "anyOf": [
-                    {"type": "string",
-                     "maxLength": 5000},
-                ]
-            }
-
-    # Can also be a string (or None by default above)
-    for v in ['body',
-              'notification_body',
-              'notification_format',
-              'notification_title',
-              'proxy',
-              'tag',
-              'title',
-              'webdriver_js_execute_code'
-              ]:
-        schema['properties'][v]['anyOf'].append({'type': 'string', "maxLength": 5000})
-
-    # None or Boolean
-    schema['properties']['track_ldjson_price_data']['anyOf'].append({'type': 'boolean'})
-
-    schema['properties']['method'] = {"type": "string",
-                                      "enum": ["GET", "POST", "DELETE", "PUT"]
-                                      }
-
-    schema['properties']['fetch_backend']['anyOf'].append({"type": "string",
-                                                           "enum": ["html_requests", "html_webdriver"]
-                                                           })
-
-
-
-    # All headers must be key/value type dict
-    schema['properties']['headers'] = {
-        "type": "object",
-        "patternProperties": {
-            # Should always be a string:string type value
-            ".*": {"type": "string"},
-        }
-    }
-
-    schema['properties']['notification_format'] = {'type': 'string',
-                                                   'enum': list(valid_notification_formats.keys())
-                                                   }
-
-    # Stuff that shouldn't be available but is just state-storage
-    for v in ['previous_md5', 'last_error', 'has_ldjson_price_data', 'previous_md5_before_filters', 'uuid']:
-        del schema['properties'][v]
-
-    schema['properties']['webdriver_delay']['anyOf'].append({'type': 'integer'})
-
-    schema['properties']['time_between_check'] = build_time_between_check_json_schema()
-
-    schema['properties']['browser_steps'] = {
-        "anyOf": [
-            {
-                "type": "array",
-                "items": {
-                    "type": "object",
-                    "properties": {
-                        "operation": {
-                            "type": ["string", "null"],
-                            "maxLength": 5000  # Allows null and any string up to 5000 chars (including "")
-                        },
-                        "selector": {
-                            "type": ["string", "null"],
-                            "maxLength": 5000
-                        },
-                        "optional_value": {
-                            "type": ["string", "null"],
-                            "maxLength": 5000
-                        }
-                    },
-                    "required": ["operation", "selector", "optional_value"],
-                    "additionalProperties": False  # No extra keys allowed
-                }
-            },
-            {"type": "null"},  # Allows null for `browser_steps`
-            {"type": "array", "maxItems": 0}  # Allows empty array []
-        ]
-    }
-
-    # headers ?
-    return schema
-

changedetectionio/blueprint/backups/__init__.py

@@ -3,6 +3,7 @@ import glob
 import threading
 
 from flask import Blueprint, render_template, send_from_directory, flash, url_for, redirect, abort
+from flask_babel import gettext
 import os
 
 from changedetectionio.store import ChangeDetectionStore
@@ -26,15 +27,27 @@ def create_backup(datastore_path, watches: dict):
                          compression=zipfile.ZIP_DEFLATED,
                          compresslevel=8) as zipObj:
 
-        # Add the index
-        zipObj.write(os.path.join(datastore_path, "url-watches.json"), arcname="url-watches.json")
+        # Add the settings file (supports both formats)
+        # New format: changedetection.json
+        changedetection_json = os.path.join(datastore_path, "changedetection.json")
+        if os.path.isfile(changedetection_json):
+            zipObj.write(changedetection_json, arcname="changedetection.json")
+            logger.debug("Added changedetection.json to backup")
 
-        # Add the flask app secret
-        zipObj.write(os.path.join(datastore_path, "secret.txt"), arcname="secret.txt")
+        # Legacy format: url-watches.json (for backward compatibility)
+        url_watches_json = os.path.join(datastore_path, "url-watches.json")
+        if os.path.isfile(url_watches_json):
+            zipObj.write(url_watches_json, arcname="url-watches.json")
+            logger.debug("Added url-watches.json to backup")
+
+        # Add the flask app secret (if it exists)
+        secret_file = os.path.join(datastore_path, "secret.txt")
+        if os.path.isfile(secret_file):
+            zipObj.write(secret_file, arcname="secret.txt")
 
         # Add any data in the watch data directory.
         for uuid, w in watches.items():
-            for f in Path(w.watch_data_dir).glob('*'):
+            for f in Path(w.data_dir).glob('*'):
                 zipObj.write(f,
                              # Use the full path to access the file, but make the file 'relative' in the Zip.
                              arcname=os.path.join(f.parts[-2], f.parts[-1]),
@@ -82,19 +95,23 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @backups_blueprint.route("/request-backup", methods=['GET'])
     def request_backup():
         if any(thread.is_alive() for thread in backup_threads):
-            flash("A backup is already running, check back in a few minutes", "error")
+            flash(gettext("A backup is already running, check back in a few minutes"), "error")
             return redirect(url_for('backups.index'))
 
         if len(find_backups()) > int(os.getenv("MAX_NUMBER_BACKUPS", 100)):
-            flash("Maximum number of backups reached, please remove some", "error")
+            flash(gettext("Maximum number of backups reached, please remove some"), "error")
             return redirect(url_for('backups.index'))
 
-        # Be sure we're written fresh
-        datastore.sync_to_json()
-        zip_thread = threading.Thread(target=create_backup, args=(datastore.datastore_path, datastore.data.get("watching")))
+        # With immediate persistence, all data is already saved
+        zip_thread = threading.Thread(
+            target=create_backup,
+            args=(datastore.datastore_path, datastore.data.get("watching")),
+            daemon=True,
+            name="BackupCreator"
+        )
         zip_thread.start()
         backup_threads.append(zip_thread)
-        flash("Backup building in background, check back in a few minutes.")
+        flash(gettext("Backup building in background, check back in a few minutes."))
 
         return redirect(url_for('backups.index'))
 
@@ -157,7 +174,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         for backup in backups:
             os.unlink(backup)
 
-        flash("Backups were deleted.")
+        flash(gettext("Backups were deleted."))
 
         return redirect(url_for('backups.index'))
 

changedetectionio/blueprint/backups/templates/overview.html

@@ -3,31 +3,31 @@
     {% from '_helpers.html' import render_simple_field, render_field %}
     <div class="edit-form">
         <div class="box-wrap inner">
-            <h4>Backups</h4>
+            <h2>{{ _('Backups') }}</h2>
             {% if backup_running %}
                 <p>
-                    <strong>A backup is running!</strong>
+                    <span class="spinner"></span>&nbsp;<strong>{{ _('A backup is running!') }}</strong>
                 </p>
             {% endif %}
             <p>
-                Here you can download and request a new backup, when a backup is completed you will see it listed below.
+                {{ _('Here you can download and request a new backup, when a backup is completed you will see it listed below.') }}
             </p>
             <br>
                 {% if available_backups %}
                     <ul>
                     {% for backup in available_backups %}
-                        <li><a href="{{ url_for('backups.download_backup', filename=backup["filename"]) }}">{{ backup["filename"] }}</a> {{  backup["filesize"] }} Mb</li>
+                        <li><a href="{{ url_for('backups.download_backup', filename=backup["filename"]) }}">{{ backup["filename"] }}</a> {{  backup["filesize"] }} {{ _('Mb') }}</li>
                     {% endfor %}
                     </ul>
                 {% else %}
                     <p>
-                    <strong>No backups found.</strong>
+                    <strong>{{ _('No backups found.') }}</strong>
                     </p>
                 {% endif %}
 
-            <a class="pure-button pure-button-primary" href="{{ url_for('backups.request_backup') }}">Create backup</a>
+            <a class="pure-button pure-button-primary" href="{{ url_for('backups.request_backup') }}">{{ _('Create backup') }}</a>
             {% if available_backups %}
-                <a class="pure-button button-small button-error " href="{{ url_for('backups.remove_backups') }}">Remove backups</a>
+                <a class="pure-button button-small button-error " href="{{ url_for('backups.remove_backups') }}">{{ _('Remove backups') }}</a>
             {% endif %}
         </div>
     </div>

changedetectionio/blueprint/browser_steps/__init__.py

@@ -21,39 +21,180 @@ from changedetectionio.flask_app import login_optionally_required
 from loguru import logger
 
 browsersteps_sessions = {}
+browsersteps_watch_to_session = {}  # Maps watch_uuid -> browsersteps_session_id
 io_interface_context = None
 import json
 import hashlib
 from flask import Response
+import asyncio
+import threading
+import time
+
+# Dedicated event loop for ALL browser steps sessions
+_browser_steps_loop = None
+_browser_steps_thread = None
+_browser_steps_loop_lock = threading.Lock()
+
+def _start_browser_steps_loop():
+    """Start a dedicated event loop for browser steps in its own thread"""
+    global _browser_steps_loop
+
+    # Create and set the event loop for this thread
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+    _browser_steps_loop = loop
+
+    logger.debug("Browser steps event loop started")
+
+    try:
+        # Run the loop forever - handles all browsersteps sessions
+        loop.run_forever()
+    except Exception as e:
+        logger.error(f"Browser steps event loop error: {e}")
+    finally:
+        try:
+            # Cancel all remaining tasks
+            pending = asyncio.all_tasks(loop)
+            for task in pending:
+                task.cancel()
+
+            # Wait for tasks to finish cancellation
+            if pending:
+                loop.run_until_complete(asyncio.gather(*pending, return_exceptions=True))
+        except Exception as e:
+            logger.debug(f"Error during browser steps loop cleanup: {e}")
+        finally:
+            loop.close()
+            logger.debug("Browser steps event loop closed")
+
+def _ensure_browser_steps_loop():
+    """Ensure the browser steps event loop is running"""
+    global _browser_steps_loop, _browser_steps_thread
+
+    with _browser_steps_loop_lock:
+        if _browser_steps_thread is None or not _browser_steps_thread.is_alive():
+            logger.debug("Starting browser steps event loop thread")
+            _browser_steps_thread = threading.Thread(
+                target=_start_browser_steps_loop,
+                daemon=True,
+                name="BrowserStepsEventLoop"
+            )
+            _browser_steps_thread.start()
+
+            # Wait for the loop to be ready
+            timeout = 5.0
+            start_time = time.time()
+            while _browser_steps_loop is None:
+                if time.time() - start_time > timeout:
+                    raise RuntimeError("Browser steps event loop failed to start")
+                time.sleep(0.01)
+
+            logger.debug("Browser steps event loop thread started and ready")
+
+def run_async_in_browser_loop(coro):
+    """Run async coroutine using the dedicated browser steps event loop"""
+    _ensure_browser_steps_loop()
+
+    if _browser_steps_loop and not _browser_steps_loop.is_closed():
+        logger.debug("Browser steps using dedicated event loop")
+        future = asyncio.run_coroutine_threadsafe(coro, _browser_steps_loop)
+        return future.result()
+    else:
+        raise RuntimeError("Browser steps event loop is not available")
+
+def cleanup_expired_sessions():
+    """Remove expired browsersteps sessions and cleanup their resources"""
+    global browsersteps_sessions, browsersteps_watch_to_session
+
+    expired_session_ids = []
+
+    # Find expired sessions
+    for session_id, session_data in browsersteps_sessions.items():
+        browserstepper = session_data.get('browserstepper')
+        if browserstepper and browserstepper.has_expired:
+            expired_session_ids.append(session_id)
+
+    # Cleanup expired sessions
+    for session_id in expired_session_ids:
+        logger.debug(f"Cleaning up expired browsersteps session {session_id}")
+        session_data = browsersteps_sessions[session_id]
+
+        # Cleanup playwright resources asynchronously
+        browserstepper = session_data.get('browserstepper')
+        if browserstepper:
+            try:
+                run_async_in_browser_loop(browserstepper.cleanup())
+            except Exception as e:
+                logger.error(f"Error cleaning up session {session_id}: {e}")
+
+        # Remove from sessions dict
+        del browsersteps_sessions[session_id]
+
+        # Remove from watch mapping
+        for watch_uuid, mapped_session_id in list(browsersteps_watch_to_session.items()):
+            if mapped_session_id == session_id:
+                del browsersteps_watch_to_session[watch_uuid]
+                break
+
+    if expired_session_ids:
+        logger.info(f"Cleaned up {len(expired_session_ids)} expired browsersteps session(s)")
+
+def cleanup_session_for_watch(watch_uuid):
+    """Cleanup a specific browsersteps session for a watch UUID"""
+    global browsersteps_sessions, browsersteps_watch_to_session
+
+    session_id = browsersteps_watch_to_session.get(watch_uuid)
+    if not session_id:
+        logger.debug(f"No browsersteps session found for watch {watch_uuid}")
+        return
+
+    logger.debug(f"Cleaning up browsersteps session {session_id} for watch {watch_uuid}")
+
+    session_data = browsersteps_sessions.get(session_id)
+    if session_data:
+        browserstepper = session_data.get('browserstepper')
+        if browserstepper:
+            try:
+                run_async_in_browser_loop(browserstepper.cleanup())
+            except Exception as e:
+                logger.error(f"Error cleaning up session {session_id} for watch {watch_uuid}: {e}")
+
+        # Remove from sessions dict
+        del browsersteps_sessions[session_id]
+
+    # Remove from watch mapping
+    del browsersteps_watch_to_session[watch_uuid]
+
+    logger.debug(f"Cleaned up session for watch {watch_uuid}")
+
+    # Opportunistically cleanup any other expired sessions
+    cleanup_expired_sessions()
 
 def construct_blueprint(datastore: ChangeDetectionStore):
     browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
 
-    def start_browsersteps_session(watch_uuid):
-        from . import nonContext
-        from . import browser_steps
+    async def start_browsersteps_session(watch_uuid):
+        from changedetectionio.browser_steps import browser_steps
         import time
-        global io_interface_context
+        from playwright.async_api import async_playwright
 
         # We keep the playwright session open for many minutes
         keepalive_seconds = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
 
         browsersteps_start_session = {'start_time': time.time()}
 
-        # You can only have one of these running
-        # This should be very fine to leave running for the life of the application
-        # @idea - Make it global so the pool of watch fetchers can use it also
-        if not io_interface_context:
-            io_interface_context = nonContext.c_sync_playwright()
-            # Start the Playwright context, which is actually a nodejs sub-process and communicates over STDIN/STDOUT pipes
-            io_interface_context = io_interface_context.start()
+        # Create a new async playwright instance for browser steps
+        playwright_instance = async_playwright()
+        playwright_context = await playwright_instance.start()
 
         keepalive_ms = ((keepalive_seconds + 3) * 1000)
         base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '').strip('"')
         a = "?" if not '?' in base_url else '&'
         base_url += a + f"timeout={keepalive_ms}"
 
-        browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(base_url)
+        browser = await playwright_context.chromium.connect_over_cdp(base_url, timeout=keepalive_ms)
+        browsersteps_start_session['browser'] = browser
+        browsersteps_start_session['playwright_context'] = playwright_context
 
         proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
         proxy = None
@@ -75,15 +216,20 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 logger.debug(f"Browser Steps: UUID {watch_uuid} selected proxy {proxy_url}")
 
         # Tell Playwright to connect to Chrome and setup a new session via our stepper interface
-        browsersteps_start_session['browserstepper'] = browser_steps.browsersteps_live_ui(
-            playwright_browser=browsersteps_start_session['browser'],
+        browserstepper = browser_steps.browsersteps_live_ui(
+            playwright_browser=browser,
             proxy=proxy,
             start_url=datastore.data['watching'][watch_uuid].link,
             headers=datastore.data['watching'][watch_uuid].get('headers')
         )
+        
+        # Initialize the async connection
+        await browserstepper.connect(proxy=proxy)
+        
+        browsersteps_start_session['browserstepper'] = browserstepper
 
         # For test
-        #browsersteps_start_session['browserstepper'].action_goto_url(value="http://example.com?time="+str(time.time()))
+        #await browsersteps_start_session['browserstepper'].action_goto_url(value="http://example.com?time="+str(time.time()))
 
         return browsersteps_start_session
 
@@ -92,7 +238,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @browser_steps_blueprint.route("/browsersteps_start_session", methods=['GET'])
     def browsersteps_start_session():
         # A new session was requested, return sessionID
-
         import uuid
         browsersteps_session_id = str(uuid.uuid4())
         watch_uuid = request.args.get('uuid')
@@ -100,11 +245,21 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         if not watch_uuid:
             return make_response('No Watch UUID specified', 500)
 
+        # Cleanup any existing session for this watch
+        cleanup_session_for_watch(watch_uuid)
+
         logger.debug("Starting connection with playwright")
         logger.debug("browser_steps.py connecting")
 
         try:
-            browsersteps_sessions[browsersteps_session_id] = start_browsersteps_session(watch_uuid)
+            # Run the async function in the dedicated browser steps event loop
+            browsersteps_sessions[browsersteps_session_id] = run_async_in_browser_loop(
+                start_browsersteps_session(watch_uuid)
+            )
+
+            # Store the mapping of watch_uuid -> browsersteps_session_id
+            browsersteps_watch_to_session[watch_uuid] = browsersteps_session_id
+
         except Exception as e:
             if 'ECONNREFUSED' in str(e):
                 return make_response('Unable to start the Playwright Browser session, is sockpuppetbrowser running? Network configuration is OK?', 401)
@@ -129,8 +284,8 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         watch = datastore.data['watching'].get(uuid)
         filename = f"step_before-{step_n}.jpeg" if request.args.get('type', '') == 'before' else f"step_{step_n}.jpeg"
 
-        if step_n and watch and os.path.isfile(os.path.join(watch.watch_data_dir, filename)):
-            response = make_response(send_from_directory(directory=watch.watch_data_dir, path=filename))
+        if step_n and watch and os.path.isfile(os.path.join(watch.data_dir, filename)):
+            response = make_response(send_from_directory(directory=watch.data_dir, path=filename))
             response.headers['Content-type'] = 'image/jpeg'
             response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
             response.headers['Pragma'] = 'no-cache'
@@ -145,11 +300,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
     def browsersteps_ui_update():
         import base64
-        import playwright._impl._errors
-        from changedetectionio.blueprint.browser_steps import browser_steps
 
-        remaining =0
+        remaining = 0
         uuid = request.args.get('uuid')
+        goto_website_url_first_step = request.args.get('goto_website_url_first_step')
 
         browsersteps_session_id = request.args.get('browsersteps_session_id')
 
@@ -160,34 +314,41 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             return make_response('No session exists under that ID', 500)
 
         is_last_step = False
-        # Actions - step/apply/etc, do the thing and return state
-        if request.method == 'POST':
-            # @todo - should always be an existing session
+
+        # @todo - should always be an existing session
+        if goto_website_url_first_step:
+            logger.debug("Going to site (requested automatically before stepping)..")
+            step_operation = "Goto site"
+            step_selector = None
+            step_optional_value = None
+        else:
             step_operation = request.form.get('operation')
             step_selector = request.form.get('selector')
             step_optional_value = request.form.get('optional_value')
             is_last_step = strtobool(request.form.get('is_last_step'))
 
-            # @todo try.. accept.. nice errors not popups..
-            try:
+        try:
+            # Run the async call_action method in the dedicated browser steps event loop
+            run_async_in_browser_loop(
+                browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(
+                    action_name=step_operation,
+                    selector=step_selector,
+                    optional_value=step_optional_value
+                )
+            )
 
-                browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(action_name=step_operation,
-                                         selector=step_selector,
-                                         optional_value=step_optional_value)
-
-            except Exception as e:
-                logger.error(f"Exception when calling step operation {step_operation} {str(e)}")
-                # Try to find something of value to give back to the user
-                return make_response(str(e).splitlines()[0], 401)
-
-
-#        if not this_session.page:
-#            cleanup_playwright_session()
-#            return make_response('Browser session ran out of time :( Please reload this page.', 401)
+        except Exception as e:
+            logger.error(f"Exception when calling step operation {step_operation} {str(e)}")
+            # Try to find something of value to give back to the user
+            return make_response(str(e).splitlines()[0], 401)
 
         # Screenshots and other info only needed on requesting a step (POST)
         try:
-            (screenshot, xpath_data) = browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
+            # Run the async get_current_state method in the dedicated browser steps event loop
+            (screenshot, xpath_data) = run_async_in_browser_loop(
+                browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
+            )
+
             if is_last_step:
                 watch = datastore.data['watching'].get(uuid)
                 u = browsersteps_sessions[browsersteps_session_id]['browserstepper'].page.url
@@ -195,13 +356,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                     watch.save_screenshot(screenshot=screenshot)
                     watch.save_xpath_data(data=xpath_data)
 
-        except playwright._impl._api_types.Error as e:
-            return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
         except Exception as e:
-            return make_response("Error fetching screenshot and element data - " + str(e), 401)
+            return make_response(f"Error fetching screenshot and element data - {str(e)}", 401)
 
         # SEND THIS BACK TO THE BROWSER
-
         output = {
             "screenshot": f"data:image/jpeg;base64,{base64.b64encode(screenshot).decode('ascii')}",
             "xpath_data": xpath_data,

changedetectionio/blueprint/browser_steps/nonContext.py

@@ -1,17 +0,0 @@
-from playwright.sync_api import PlaywrightContextManager
-
-# So playwright wants to run as a context manager, but we do something horrible and hacky
-# we are holding the session open for as long as possible, then shutting it down, and opening a new one
-# So it means we don't get to use PlaywrightContextManager' __enter__ __exit__
-# To work around this, make goodbye() act the same as the __exit__()
-#
-# But actually I think this is because the context is opened correctly with __enter__() but we timeout the connection
-# then theres some lock condition where we cant destroy it without it hanging
-
-class c_PlaywrightContextManager(PlaywrightContextManager):
-
-    def goodbye(self) -> None:
-        self.__exit__()
-
-def c_sync_playwright() -> PlaywrightContextManager:
-    return c_PlaywrightContextManager()

changedetectionio/blueprint/check_proxies/__init__.py

@@ -33,7 +33,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def long_task(uuid, preferred_proxy):
         import time
         from changedetectionio.content_fetchers import exceptions as content_fetcher_exceptions
-        from changedetectionio.safe_jinja import render as jinja_render
+        from changedetectionio.jinja2_custom import render as jinja_render
 
         status = {'status': '', 'length': 0, 'text': ''}
 

changedetectionio/blueprint/imports/__init__.py

@@ -1,12 +1,8 @@
 from flask import Blueprint, request, redirect, url_for, flash, render_template
+from loguru import logger
+
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
-from changedetectionio.blueprint.imports.importer import (
-    import_url_list, 
-    import_distill_io_json, 
-    import_xlsx_wachete, 
-    import_xlsx_custom
-)
 
 def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
     import_blueprint = Blueprint('imports', __name__, template_folder="templates")
@@ -16,15 +12,27 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
     def import_page():
         remaining_urls = []
         from changedetectionio import forms
-
+#
         if request.method == 'POST':
+#            from changedetectionio import worker_pool
+
+            from changedetectionio.blueprint.imports.importer import (
+                import_url_list,
+                import_distill_io_json,
+                import_xlsx_wachete,
+                import_xlsx_custom
+            )
+
             # URL List import
             if request.values.get('urls') and len(request.values.get('urls').strip()):
                 # Import and push into the queue for immediate update check
+                from changedetectionio import processors
                 importer_handler = import_url_list()
-                importer_handler.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', 'text_json_diff'))
-                for uuid in importer_handler.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                importer_handler.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', processors.get_default_processor()))
+                logger.debug(f"Imported {len(importer_handler.new_uuids)} new UUIDs")
+                # Dont' add to queue because scheduler can see that they haven't been checked and will add them to the queue
+#                for uuid in importer_handler.new_uuids:
+#                    worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
                 if len(importer_handler.remaining_data) == 0:
                     return redirect(url_for('watchlist.index'))
@@ -36,8 +44,10 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                 # Import and push into the queue for immediate update check
                 d_importer = import_distill_io_json()
                 d_importer.run(data=request.values.get('distill-io'), flash=flash, datastore=datastore)
-                for uuid in d_importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                # Dont' add to queue because scheduler can see that they haven't been checked and will add them to the queue
+#                for uuid in importer_handler.new_uuids:
+#                    worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+
 
             # XLSX importer
             if request.files and request.files.get('xlsx_file'):
@@ -59,8 +69,10 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                     w_importer.import_profile = map
                     w_importer.run(data=file, flash=flash, datastore=datastore)
 
-                for uuid in w_importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                # Dont' add to queue because scheduler can see that they haven't been checked and will add them to the queue
+#                for uuid in importer_handler.new_uuids:
+#                    worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+
 
         # Could be some remaining, or we could be on GET
         form = forms.importForm(formdata=request.form if request.method == 'POST' else None)

changedetectionio/blueprint/imports/importer.py

@@ -2,6 +2,7 @@ from abc import abstractmethod
 import time
 from wtforms import ValidationError
 from loguru import logger
+from flask_babel import gettext
 
 from changedetectionio.forms import validate_url
 
@@ -41,7 +42,7 @@ class import_url_list(Importer):
         now = time.time()
 
         if (len(urls) > 5000):
-            flash("Importing 5,000 of the first URLs from your list, the rest can be imported again.")
+            flash(gettext("Importing 5,000 of the first URLs from your list, the rest can be imported again."))
 
         for url in urls:
             url = url.strip()
@@ -61,7 +62,7 @@ class import_url_list(Importer):
                 extras = None
                 if processor:
                     extras = {'processor': processor}
-                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False, extras=extras)
+                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, save_immediately=False, extras=extras)
 
                 if new_uuid:
                     # Straight into the queue.
@@ -74,7 +75,7 @@ class import_url_list(Importer):
                 self.remaining_data = []
             self.remaining_data.append(url)
 
-        flash("{} Imported from list in {:.2f}s, {} Skipped.".format(good, time.time() - now, len(self.remaining_data)))
+        flash(gettext("{} Imported from list in {:.2f}s, {} Skipped.").format(good, time.time() - now, len(self.remaining_data)))
 
 
 class import_distill_io_json(Importer):
@@ -94,11 +95,11 @@ class import_distill_io_json(Importer):
         try:
             data = json.loads(data.strip())
         except json.decoder.JSONDecodeError:
-            flash("Unable to read JSON file, was it broken?", 'error')
+            flash(gettext("Unable to read JSON file, was it broken?"), 'error')
             return
 
         if not data.get('data'):
-            flash("JSON structure looks invalid, was it broken?", 'error')
+            flash(gettext("JSON structure looks invalid, was it broken?"), 'error')
             return
 
         for d in data.get('data'):
@@ -128,14 +129,14 @@ class import_distill_io_json(Importer):
                 new_uuid = datastore.add_watch(url=d['uri'].strip(),
                                                tag=",".join(d.get('tags', [])),
                                                extras=extras,
-                                               write_to_disk_now=False)
+                                               save_immediately=False)
 
                 if new_uuid:
                     # Straight into the queue.
                     self.new_uuids.append(new_uuid)
                     good += 1
 
-        flash("{} Imported from Distill.io in {:.2f}s, {} Skipped.".format(len(self.new_uuids), time.time() - now, len(self.remaining_data)))
+        flash(gettext("{} Imported from Distill.io in {:.2f}s, {} Skipped.").format(len(self.new_uuids), time.time() - now, len(self.remaining_data)))
 
 
 class import_xlsx_wachete(Importer):
@@ -156,7 +157,7 @@ class import_xlsx_wachete(Importer):
             wb = load_workbook(data)
         except Exception as e:
             # @todo correct except
-            flash("Unable to read export XLSX file, something wrong with the file?", 'error')
+            flash(gettext("Unable to read export XLSX file, something wrong with the file?"), 'error')
             return
 
         row_id = 2
@@ -196,26 +197,25 @@ class import_xlsx_wachete(Importer):
                         validate_url(data.get('url'))
                     except ValidationError as e:
                         logger.error(f">> Import URL error {data.get('url')} {str(e)}")
-                        flash(f"Error processing row number {row_id}, URL value was incorrect, row was skipped.", 'error')
+                        flash(gettext("Error processing row number {}, URL value was incorrect, row was skipped.").format(row_id), 'error')
                         # Don't bother processing anything else on this row
                         continue
 
                     new_uuid = datastore.add_watch(url=data['url'].strip(),
                                                    extras=extras,
                                                    tag=data.get('folder'),
-                                                   write_to_disk_now=False)
+                                                   save_immediately=False)
                     if new_uuid:
                         # Straight into the queue.
                         self.new_uuids.append(new_uuid)
                         good += 1
             except Exception as e:
                 logger.error(e)
-                flash(f"Error processing row number {row_id}, check all cell data types are correct, row was skipped.", 'error')
+                flash(gettext("Error processing row number {}, check all cell data types are correct, row was skipped.").format(row_id), 'error')
             else:
                 row_id += 1
 
-        flash(
-            "{} imported from Wachete .xlsx in {:.2f}s".format(len(self.new_uuids), time.time() - now))
+        flash(gettext("{} imported from Wachete .xlsx in {:.2f}s").format(len(self.new_uuids), time.time() - now))
 
 
 class import_xlsx_custom(Importer):
@@ -236,7 +236,7 @@ class import_xlsx_custom(Importer):
             wb = load_workbook(data)
         except Exception as e:
             # @todo correct except
-            flash("Unable to read export XLSX file, something wrong with the file?", 'error')
+            flash(gettext("Unable to read export XLSX file, something wrong with the file?"), 'error')
             return
 
         # @todo cehck atleast 2 rows, same in other method
@@ -265,7 +265,7 @@ class import_xlsx_custom(Importer):
                             validate_url(url)
                         except ValidationError as e:
                             logger.error(f">> Import URL error {url} {str(e)}")
-                            flash(f"Error processing row number {row_i}, URL value was incorrect, row was skipped.", 'error')
+                            flash(gettext("Error processing row number {}, URL value was incorrect, row was skipped.").format(row_i), 'error')
                             # Don't bother processing anything else on this row
                             url = None
                             break
@@ -287,16 +287,15 @@ class import_xlsx_custom(Importer):
                     new_uuid = datastore.add_watch(url=url,
                                                    extras=extras,
                                                    tag=tags,
-                                                   write_to_disk_now=False)
+                                                   save_immediately=False)
                     if new_uuid:
                         # Straight into the queue.
                         self.new_uuids.append(new_uuid)
                         good += 1
         except Exception as e:
             logger.error(e)
-            flash(f"Error processing row number {row_i}, check all cell data types are correct, row was skipped.", 'error')
+            flash(gettext("Error processing row number {}, check all cell data types are correct, row was skipped.").format(row_i), 'error')
         else:
             row_i += 1
 
-        flash(
-            "{} imported from custom .xlsx in {:.2f}s".format(len(self.new_uuids), time.time() - now))
+        flash(gettext("{} imported from custom .xlsx in {:.2f}s").format(len(self.new_uuids), time.time() - now))

changedetectionio/blueprint/imports/templates/import.html

@@ -6,9 +6,9 @@
 
     <div class="tabs collapsable">
         <ul>
-            <li class="tab" id=""><a href="#url-list">URL List</a></li>
-            <li class="tab"><a href="#distill-io">Distill.io</a></li>
-            <li class="tab"><a href="#xlsx">.XLSX &amp; Wachete</a></li>
+            <li class="tab" id=""><a href="#url-list">{{ _('URL List') }}</a></li>
+            <li class="tab"><a href="#distill-io">{{ _('Distill.io') }}</a></li>
+            <li class="tab"><a href="#xlsx">{{ _('.XLSX & Wachete') }}</a></li>
         </ul>
     </div>
 
@@ -17,11 +17,10 @@
             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
             <div class="tab-pane-inner" id="url-list">
                 <div class="pure-control-group">
-                        Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma
-                        (,):
+                        {{ _('Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma (,):') }}
                         <br>
-                        <p><strong>Example:  </strong><code>https://example.com tag1, tag2, last tag</code></p>
-                        URLs which do not pass validation will stay in the textarea.
+                        <p><strong>{{ _('Example:') }}  </strong><code>https://example.com tag1, tag2, last tag</code></p>
+                        {{ _('URLs which do not pass validation will stay in the textarea.') }}
                 </div>
                 {{ render_field(form.processor, class="processor") }}
                 
@@ -42,12 +41,12 @@
 
 
                     <div class="pure-control-group">
-                        Copy and Paste your Distill.io watch 'export' file, this should be a JSON file.<br>
-                        This is <i>experimental</i>, supported fields are <code>name</code>, <code>uri</code>, <code>tags</code>, <code>config:selections</code>, the rest (including <code>schedule</code>) are ignored.
+                        {{ _('Copy and Paste your Distill.io watch \'export\' file, this should be a JSON file.') }}<br>
+                        {{ _('This is') }} <i>{{ _('experimental') }}</i>, {{ _('supported fields are') }} <code>name</code>, <code>uri</code>, <code>tags</code>, <code>config:selections</code>, {{ _('the rest (including') }} <code>schedule</code>) {{ _('are ignored.') }}
                         <br>
                         <p>
-                        How to export? <a href="https://distill.io/docs/web-monitor/how-export-and-import-monitors/">https://distill.io/docs/web-monitor/how-export-and-import-monitors/</a><br>
-                        Be sure to set your default fetcher to Chrome if required.<br>
+                        {{ _('How to export?') }} <a href="https://distill.io/docs/web-monitor/how-export-and-import-monitors/">https://distill.io/docs/web-monitor/how-export-and-import-monitors/</a><br>
+                        {{ _('Be sure to set your default fetcher to Chrome if required.') }}<br>
                         </p>
                     </div>
 
@@ -89,32 +88,32 @@
             </fieldset>
                 <div class="pure-control-group">
                 <span class="pure-form-message-inline">
-                    Table of custom column and data types mapping for the <strong>Custom mapping</strong> File mapping type.
+                    {{ _('Table of custom column and data types mapping for the') }} <strong>{{ _('Custom mapping') }}</strong> {{ _('File mapping type.') }}
                 </span>
                     <table style="border: 1px solid #aaa; padding: 0.5rem; border-radius: 4px;">
                         <tr>
-                            <td><strong>Column #</strong></td>
+                            <td><strong>{{ _('Column #') }}</strong></td>
                             {% for n in range(4) %}
                                 <td><input type="number" name="custom_xlsx[col_{{n}}]" style="width: 4rem;" min="1"></td>
                             {%  endfor %}
                         </tr>
                         <tr>
-                            <td><strong>Type</strong></td>
+                            <td><strong>{{ _('Type') }}</strong></td>
                             {% for n in range(4) %}
                                 <td><select name="custom_xlsx[col_type_{{n}}]">
-                                    <option value="" style="color: #aaa"> -- none --</option>
-                                    <option value="url">URL</option>
-                                    <option value="title">Title</option>
-                                    <option value="include_filters">CSS/xPath filter</option>
-                                    <option value="tag">Group / Tag name(s)</option>
-                                    <option value="interval_minutes">Recheck time (minutes)</option>
+                                    <option value="" style="color: #aaa"> -- {{ _('none') }} --</option>
+                                    <option value="url">{{ _('URL') }}</option>
+                                    <option value="title">{{ _('Title') }}</option>
+                                    <option value="include_filters">{{ _('CSS/xPath filter') }}</option>
+                                    <option value="tag">{{ _('Group / Tag name(s)') }}</option>
+                                    <option value="interval_minutes">{{ _('Recheck time (minutes)') }}</option>
                                 </select></td>
                             {%  endfor %}
                         </tr>
                     </table>
                 </div>
             </div>
-            <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">Import</button>
+            <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">{{ _('Import') }}</button>
         </form>
 
     </div>

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -4,6 +4,7 @@ from flask import Blueprint, flash, redirect, url_for
 from flask_login import login_required
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio import queuedWatchMetaData
+from changedetectionio import worker_pool
 from queue import PriorityQueue
 
 PRICE_DATA_TRACK_ACCEPT = 'accepted'
@@ -19,13 +20,15 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
         datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_ACCEPT
         datastore.data['watching'][uuid]['processor'] = 'restock_diff'
         datastore.data['watching'][uuid].clear_watch()
-        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+        datastore.data['watching'][uuid].commit()
+        worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
         return redirect(url_for("watchlist.index"))
 
     @login_required
     @price_data_follower_blueprint.route("/<string:uuid>/reject", methods=['GET'])
     def reject(uuid):
         datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_REJECT
+        datastore.data['watching'][uuid].commit()
         return redirect(url_for("watchlist.index"))
 
 

changedetectionio/blueprint/rss/__init__.py

@@ -1 +1,27 @@
-RSS_FORMAT_TYPES = [('plaintext', 'Plain text'), ('html', 'HTML Color')]
+from copy import deepcopy
+from loguru import logger
+
+from changedetectionio.model import USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH
+from changedetectionio.notification import valid_notification_formats
+
+RSS_CONTENT_FORMAT_DEFAULT = 'text'
+
+# Some stuff not related
+RSS_FORMAT_TYPES = deepcopy(valid_notification_formats)
+if RSS_FORMAT_TYPES.get('markdown'):
+    del RSS_FORMAT_TYPES['markdown']
+
+if RSS_FORMAT_TYPES.get(USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH):
+    del RSS_FORMAT_TYPES[USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH]
+
+if not RSS_FORMAT_TYPES.get(RSS_CONTENT_FORMAT_DEFAULT):
+    logger.critical(f"RSS_CONTENT_FORMAT_DEFAULT not in the acceptable list {RSS_CONTENT_FORMAT_DEFAULT}")
+
+RSS_TEMPLATE_TYPE_OPTIONS = {'system_default': 'System default', 'notification_body': 'Notification body'}
+
+# @note: We use <pre> because nearly all RSS readers render only HTML (Thunderbird for example cant do just plaintext)
+RSS_TEMPLATE_PLAINTEXT_DEFAULT = "<pre>{{watch_label}} had a change.\n\n{{diff}}\n</pre>"
+
+# @todo add some [edit]/[history]/[goto] etc links
+# @todo need {{watch_edit_link}} + delete + history link token
+RSS_TEMPLATE_HTML_DEFAULT = "<html><body>\n<h4><a href=\"{{watch_url}}\">{{watch_label}}</a></h4>\n<p>{{diff}}</p>\n</body></html>\n"

changedetectionio/blueprint/rss/_util.py

@@ -0,0 +1,156 @@
+"""
+Utility functions for RSS feed generation.
+"""
+
+from changedetectionio.notification.handler import process_notification
+from changedetectionio.notification_service import NotificationContextData, _check_cascading_vars
+from loguru import logger
+import datetime
+import pytz
+import re
+
+
+BAD_CHARS_REGEX = r'[\x00-\x08\x0B\x0C\x0E-\x1F]'
+
+
+def scan_invalid_chars_in_rss(content):
+    """
+    Scan for invalid characters in RSS content.
+    Returns True if invalid characters are found.
+    """
+    for match in re.finditer(BAD_CHARS_REGEX, content):
+        i = match.start()
+        bad_char = content[i]
+        hex_value = f"0x{ord(bad_char):02x}"
+        # Grab context
+        start = max(0, i - 20)
+        end = min(len(content), i + 21)
+        context = content[start:end].replace('\n', '\\n').replace('\r', '\\r')
+        logger.warning(f"Invalid char {hex_value} at pos {i}: ...{context}...")
+        # First match is enough
+        return True
+
+    return False
+
+
+def clean_entry_content(content):
+    """
+    Remove invalid characters from RSS content.
+    """
+    cleaned = re.sub(BAD_CHARS_REGEX, '', content)
+    return cleaned
+
+
+def generate_watch_guid(watch, timestamp):
+    """
+    Generate a unique GUID for a watch RSS entry.
+
+    Args:
+        watch: The watch object
+        timestamp: The timestamp of the specific change this entry represents
+    """
+    return f"{watch['uuid']}/{timestamp}"
+
+
+def validate_rss_token(datastore, request):
+    """
+    Validate the RSS access token from the request.
+
+    Returns:
+        tuple: (is_valid, error_response) where error_response is None if valid
+    """
+    app_rss_token = datastore.data['settings']['application'].get('rss_access_token')
+    rss_url_token = request.args.get('token')
+
+    if rss_url_token != app_rss_token:
+        return False, ("Access denied, bad token", 403)
+
+    return True, None
+
+
+def get_rss_template(datastore, watch, rss_content_format, default_html, default_plaintext):
+    """Get the appropriate template for RSS content."""
+    if datastore.data['settings']['application'].get('rss_template_type') == 'notification_body':
+        return _check_cascading_vars(datastore=datastore, var_name='notification_body', watch=watch)
+
+    override = datastore.data['settings']['application'].get('rss_template_override')
+    if override and override.strip():
+        return override
+    elif 'text' in rss_content_format:
+        return default_plaintext
+    else:
+        return default_html
+
+
+def get_watch_label(datastore, watch):
+    """Get the label for a watch based on settings."""
+    if datastore.data['settings']['application']['ui'].get('use_page_title_in_list') or watch.get('use_page_title_in_list'):
+        return watch.label
+    else:
+        return watch.get('url')
+
+
+def add_watch_categories(fe, watch, datastore):
+    """Add category tags to a feed entry based on watch tags."""
+    for tag_uuid in watch.get('tags', []):
+        tag = datastore.data['settings']['application'].get('tags', {}).get(tag_uuid)
+        if tag and tag.get('title'):
+            fe.category(term=tag.get('title'))
+
+
+def build_notification_context(watch, timestamp_from, timestamp_to, watch_label,
+                               n_body_template, rss_content_format):
+    """Build the notification context object."""
+    return NotificationContextData(initial_data={
+        'notification_urls': ['null://just-sending-a-null-test-for-the-render-in-RSS'],
+        'notification_body': n_body_template,
+        'timestamp_to': timestamp_to,
+        'timestamp_from': timestamp_from,
+        'watch_label': watch_label,
+        'notification_format': rss_content_format
+    })
+
+
+def render_notification(n_object, notification_service, watch, datastore,
+                       date_index_from=None, date_index_to=None):
+    """Process and render the notification content."""
+    kwargs = {'n_object': n_object, 'watch': watch}
+
+    if date_index_from is not None and date_index_to is not None:
+        kwargs['date_index_from'] = date_index_from
+        kwargs['date_index_to'] = date_index_to
+
+    n_object = notification_service.queue_notification_for_watch(**kwargs)
+    n_object['watch_mime_type'] = None
+
+    res = process_notification(n_object=n_object, datastore=datastore)
+    return res[0]
+
+
+def populate_feed_entry(fe, watch, content, guid, timestamp, link=None, title_suffix=None):
+    """Populate a feed entry with content and metadata."""
+    watch_label = watch.get('url')  # Already determined by caller
+
+    # Set link
+    if link:
+        fe.link(link=link)
+
+    # Set title
+    if title_suffix:
+        fe.title(title=f"{watch_label} - {title_suffix}")
+    else:
+        fe.title(title=watch_label)
+
+    # Clean and set content
+    if scan_invalid_chars_in_rss(content):
+        content = clean_entry_content(content)
+    fe.content(content=content, type='CDATA')
+
+    # Set GUID
+    fe.guid(guid, permalink=False)
+
+    # Set pubDate using the timestamp of this specific change
+    dt = datetime.datetime.fromtimestamp(int(timestamp))
+    dt = dt.replace(tzinfo=pytz.UTC)
+    fe.pubDate(dt)
+

changedetectionio/blueprint/rss/blueprint.py

@@ -1,147 +1,26 @@
 
-from changedetectionio.safe_jinja import render as jinja_render
 from changedetectionio.store import ChangeDetectionStore
-from feedgen.feed import FeedGenerator
-from flask import Blueprint, make_response, request, url_for, redirect
-from loguru import logger
-import datetime
-import pytz
-import re
-import time
+from flask import Blueprint
 
-
-BAD_CHARS_REGEX=r'[\x00-\x08\x0B\x0C\x0E-\x1F]'
-
-# Anything that is not text/UTF-8 should be stripped before it breaks feedgen (such as binary data etc)
-def scan_invalid_chars_in_rss(content):
-    for match in re.finditer(BAD_CHARS_REGEX, content):
-        i = match.start()
-        bad_char = content[i]
-        hex_value = f"0x{ord(bad_char):02x}"
-        # Grab context
-        start = max(0, i - 20)
-        end = min(len(content), i + 21)
-        context = content[start:end].replace('\n', '\\n').replace('\r', '\\r')
-        logger.warning(f"Invalid char {hex_value} at pos {i}: ...{context}...")
-        # First match is enough
-        return True
-
-    return False
-
-
-def clean_entry_content(content):
-    cleaned = re.sub(BAD_CHARS_REGEX, '', content)
-    return cleaned
+from . import tag as tag_routes
+from . import main_feed
+from . import single_watch
 
 def construct_blueprint(datastore: ChangeDetectionStore):
+    """
+    Construct and configure the RSS blueprint with all routes.
+
+    Args:
+        datastore: The ChangeDetectionStore instance
+
+    Returns:
+        The configured Flask blueprint
+    """
     rss_blueprint = Blueprint('rss', __name__)
 
-    # Some RSS reader situations ended up with rss/ (forward slash after RSS) due
-    # to some earlier blueprint rerouting work, it should goto feed.
-    @rss_blueprint.route("/", methods=['GET'])
-    def extraslash():
-        return redirect(url_for('rss.feed'))
-
-    # Import the login decorator if needed
-    # from changedetectionio.auth_decorator import login_optionally_required
-    @rss_blueprint.route("", methods=['GET'])
-    def feed():
-        now = time.time()
-        # Always requires token set
-        app_rss_token = datastore.data['settings']['application'].get('rss_access_token')
-        rss_url_token = request.args.get('token')
-        if rss_url_token != app_rss_token:
-            return "Access denied, bad token", 403
-
-        from changedetectionio import diff
-        limit_tag = request.args.get('tag', '').lower().strip()
-        # Be sure limit_tag is a uuid
-        for uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
-            if limit_tag == tag.get('title', '').lower().strip():
-                limit_tag = uuid
-
-        # Sort by last_changed and add the uuid which is usually the key..
-        sorted_watches = []
-
-        # @todo needs a .itemsWithTag() or something - then we can use that in Jinaj2 and throw this away
-        for uuid, watch in datastore.data['watching'].items():
-            # @todo tag notification_muted skip also (improve Watch model)
-            if datastore.data['settings']['application'].get('rss_hide_muted_watches') and watch.get('notification_muted'):
-                continue
-            if limit_tag and not limit_tag in watch['tags']:
-                continue
-            watch['uuid'] = uuid
-            sorted_watches.append(watch)
-
-        sorted_watches.sort(key=lambda x: x.last_changed, reverse=False)
-
-        fg = FeedGenerator()
-        fg.title('changedetection.io')
-        fg.description('Feed description')
-        fg.link(href='https://changedetection.io')
-
-        html_colour_enable = False
-        if datastore.data['settings']['application'].get('rss_content_format') == 'html':
-            html_colour_enable = True
-
-        for watch in sorted_watches:
-
-            dates = list(watch.history.keys())
-            # Re #521 - Don't bother processing this one if theres less than 2 snapshots, means we never had a change detected.
-            if len(dates) < 2:
-                continue
-
-            if not watch.viewed:
-                # Re #239 - GUID needs to be individual for each event
-                # @todo In the future make this a configurable link back (see work on BASE_URL https://github.com/dgtlmoon/changedetection.io/pull/228)
-                guid = "{}/{}".format(watch['uuid'], watch.last_changed)
-                fe = fg.add_entry()
-
-                # Include a link to the diff page, they will have to login here to see if password protection is enabled.
-                # Description is the page you watch, link takes you to the diff JS UI page
-                # Dict val base_url will get overriden with the env var if it is set.
-                ext_base_url = datastore.data['settings']['application'].get('active_base_url')
-                # @todo fix
-
-                # Because we are called via whatever web server, flask should figure out the right path (
-                diff_link = {'href': url_for('ui.ui_views.diff_history_page', uuid=watch['uuid'], _external=True)}
-
-                fe.link(link=diff_link)
-
-                # @todo watch should be a getter - watch.get('title') (internally if URL else..)
-
-                watch_title = watch.get('title') if watch.get('title') else watch.get('url')
-                fe.title(title=watch_title)
-                try:
-
-                    html_diff = diff.render_diff(previous_version_file_contents=watch.get_history_snapshot(dates[-2]),
-                                                 newest_version_file_contents=watch.get_history_snapshot(dates[-1]),
-                                                 include_equal=False,
-                                                 line_feed_sep="<br>",
-                                                 html_colour=html_colour_enable
-                                                 )
-                except FileNotFoundError as e:
-                    html_diff = f"History snapshot file for watch {watch.get('uuid')}@{watch.last_changed} - '{watch.get('title')} not found."
-
-                # @todo Make this configurable and also consider html-colored markup
-                # @todo User could decide if <link> goes to the diff page, or to the watch link
-                rss_template = "<html><body>\n<h4><a href=\"{{watch_url}}\">{{watch_title}}</a></h4>\n<p>{{html_diff}}</p>\n</body></html>\n"
-
-                content = jinja_render(template_str=rss_template, watch_title=watch_title, html_diff=html_diff, watch_url=watch.link)
-
-                # Out of range chars could also break feedgen
-                if scan_invalid_chars_in_rss(content):
-                    content = clean_entry_content(content)
-
-                fe.content(content=content, type='CDATA')
-                fe.guid(guid, permalink=False)
-                dt = datetime.datetime.fromtimestamp(int(watch.newest_history_key))
-                dt = dt.replace(tzinfo=pytz.UTC)
-                fe.pubDate(dt)
-
-        response = make_response(fg.rss_str())
-        response.headers.set('Content-Type', 'application/rss+xml;charset=utf-8')
-        logger.trace(f"RSS generated in {time.time() - now:.3f}s")
-        return response
+    # Register all route modules
+    main_feed.construct_main_feed_routes(rss_blueprint, datastore)
+    single_watch.construct_single_watch_routes(rss_blueprint, datastore)
+    tag_routes.construct_tag_routes(rss_blueprint, datastore)
 
     return rss_blueprint

changedetectionio/blueprint/rss/main_feed.py

@@ -0,0 +1,105 @@
+from flask import make_response, request, url_for, redirect
+
+
+
+def construct_main_feed_routes(rss_blueprint, datastore):
+    """
+    Construct the main RSS feed routes.
+
+    Args:
+        rss_blueprint: The Flask blueprint to add routes to
+        datastore: The ChangeDetectionStore instance
+    """
+
+    # Some RSS reader situations ended up with rss/ (forward slash after RSS) due
+    # to some earlier blueprint rerouting work, it should goto feed.
+    @rss_blueprint.route("/", methods=['GET'])
+    def extraslash():
+        return redirect(url_for('rss.feed'))
+
+    # Import the login decorator if needed
+    # from changedetectionio.auth_decorator import login_optionally_required
+    @rss_blueprint.route("", methods=['GET'])
+    def feed():
+        from feedgen.feed import FeedGenerator
+        from loguru import logger
+        import time
+
+        from . import RSS_TEMPLATE_HTML_DEFAULT, RSS_TEMPLATE_PLAINTEXT_DEFAULT
+        from ._util import (validate_rss_token, generate_watch_guid, get_rss_template,
+                           get_watch_label, build_notification_context, render_notification,
+                           populate_feed_entry, add_watch_categories)
+        from ...notification_service import NotificationService
+
+        now = time.time()
+
+        # Validate token
+        is_valid, error = validate_rss_token(datastore, request)
+        if not is_valid:
+            return error
+
+        rss_content_format = datastore.data['settings']['application'].get('rss_content_format')
+
+        limit_tag = request.args.get('tag', '').lower().strip()
+        # Be sure limit_tag is a uuid
+        for uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
+            if limit_tag == tag.get('title', '').lower().strip():
+                limit_tag = uuid
+
+        # Sort by last_changed and add the uuid which is usually the key..
+        sorted_watches = []
+
+        # @todo needs a .itemsWithTag() or something - then we can use that in Jinaj2 and throw this away
+        for uuid, watch in datastore.data['watching'].items():
+            # @todo tag notification_muted skip also (improve Watch model)
+            if datastore.data['settings']['application'].get('rss_hide_muted_watches') and watch.get('notification_muted'):
+                continue
+            if limit_tag and not limit_tag in watch['tags']:
+                continue
+            sorted_watches.append(watch)
+
+        sorted_watches.sort(key=lambda x: x.last_changed, reverse=False)
+
+        fg = FeedGenerator()
+        fg.title('changedetection.io')
+        fg.description('Feed description')
+        fg.link(href='https://changedetection.io')
+        notification_service = NotificationService(datastore=datastore, notification_q=False)
+
+        for watch in sorted_watches:
+
+            dates = list(watch.history.keys())
+            # Re #521 - Don't bother processing this one if theres less than 2 snapshots, means we never had a change detected.
+            if len(dates) < 2:
+                continue
+
+            if not watch.viewed:
+                # Re #239 - GUID needs to be individual for each event
+                # @todo In the future make this a configurable link back (see work on BASE_URL https://github.com/dgtlmoon/changedetection.io/pull/228)
+                watch_label = get_watch_label(datastore, watch)
+                timestamp_to = dates[-1]
+                timestamp_from = dates[-2]
+                guid = generate_watch_guid(watch, timestamp_to)
+                # Because we are called via whatever web server, flask should figure out the right path
+                diff_link = {'href': url_for('ui.ui_diff.diff_history_page', uuid=watch['uuid'], _external=True)}
+
+                # Get template and build notification context
+                n_body_template = get_rss_template(datastore, watch, rss_content_format,
+                                                   RSS_TEMPLATE_HTML_DEFAULT, RSS_TEMPLATE_PLAINTEXT_DEFAULT)
+
+                n_object = build_notification_context(watch, timestamp_from, timestamp_to,
+                                                     watch_label, n_body_template, rss_content_format)
+
+                # Render notification
+                res = render_notification(n_object, notification_service, watch, datastore)
+
+                # Create and populate feed entry
+                fe = fg.add_entry()
+                populate_feed_entry(fe, watch, res['body'], guid, timestamp_to, link=diff_link)
+                fe.title(title=watch_label)  # Override title to not include suffix
+                add_watch_categories(fe, watch, datastore)
+
+        response = make_response(fg.rss_str())
+        response.headers.set('Content-Type', 'application/rss+xml;charset=utf-8')
+        logger.trace(f"RSS generated in {time.time() - now:.3f}s")
+        return response

changedetectionio/blueprint/rss/single_watch.py

@@ -0,0 +1,114 @@
+
+
+def construct_single_watch_routes(rss_blueprint, datastore):
+    """
+    Construct RSS feed routes for single watches.
+
+    Args:
+        rss_blueprint: The Flask blueprint to add routes to
+        datastore: The ChangeDetectionStore instance
+    """
+
+    @rss_blueprint.route("/watch/<string:uuid>", methods=['GET'])
+    def rss_single_watch(uuid):
+        import time
+
+        from flask import make_response, request
+        from feedgen.feed import FeedGenerator
+        from loguru import logger
+
+        from . import RSS_TEMPLATE_HTML_DEFAULT, RSS_TEMPLATE_PLAINTEXT_DEFAULT
+        from ._util import (validate_rss_token, get_rss_template, get_watch_label,
+                           build_notification_context, render_notification,
+                           populate_feed_entry, add_watch_categories)
+        from ...notification_service import NotificationService
+
+        """
+        Display the most recent changes for a single watch as RSS feed.
+        Returns RSS XML with multiple entries showing diffs between consecutive snapshots.
+        The number of entries is controlled by the rss_diff_length setting.
+        """
+        now = time.time()
+
+        # Validate token
+        is_valid, error = validate_rss_token(datastore, request)
+        if not is_valid:
+            return error
+
+        rss_content_format = datastore.data['settings']['application'].get('rss_content_format')
+
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+        # Get the watch by UUID
+        watch = datastore.data['watching'].get(uuid)
+        if not watch:
+            return f"Watch with UUID {uuid} not found", 404
+
+        # Check if watch has at least 2 history snapshots
+        dates = list(watch.history.keys())
+        if len(dates) < 2:
+            return f"Watch {uuid} does not have enough history snapshots to show changes (need at least 2)", 400
+
+        # Get the number of diffs to include (default: 5)
+        rss_diff_length = datastore.data['settings']['application'].get('rss_diff_length', 5)
+
+        # Calculate how many diffs we can actually show (limited by available history)
+        # We need at least 2 snapshots to create 1 diff
+        max_possible_diffs = len(dates) - 1
+        num_diffs = min(rss_diff_length, max_possible_diffs) if rss_diff_length > 0 else max_possible_diffs
+
+        # Create RSS feed
+        fg = FeedGenerator()
+
+        # Set title: use "label (url)" if label differs from url, otherwise just url
+        watch_url = watch.get('url', '')
+        watch_label = get_watch_label(datastore, watch)
+
+        if watch_label != watch_url:
+            feed_title = f'changedetection.io - {watch_label} ({watch_url})'
+        else:
+            feed_title = f'changedetection.io - {watch_url}'
+
+        fg.title(feed_title)
+        fg.description('Changes')
+        fg.link(href='https://changedetection.io')
+
+        # Loop through history and create RSS entries for each diff
+        # Add entries in reverse order because feedgen reverses them
+        # This way, the newest change appears first in the final RSS
+
+        notification_service = NotificationService(datastore=datastore, notification_q=False)
+        for i in range(num_diffs - 1, -1, -1):
+            # Calculate indices for this diff (working backwards from newest)
+            # i=0: compare dates[-2] to dates[-1] (most recent change)
+            # i=1: compare dates[-3] to dates[-2] (previous change)
+            # etc.
+            date_index_to = -(i + 1)
+            date_index_from = -(i + 2)
+            timestamp_to = dates[date_index_to]
+            timestamp_from = dates[date_index_from]
+
+            # Get template and build notification context
+            n_body_template = get_rss_template(datastore, watch, rss_content_format,
+                                               RSS_TEMPLATE_HTML_DEFAULT, RSS_TEMPLATE_PLAINTEXT_DEFAULT)
+
+            n_object = build_notification_context(watch, timestamp_from, timestamp_to,
+                                                 watch_label, n_body_template, rss_content_format)
+
+            # Render notification with date indices
+            res = render_notification(n_object, notification_service, watch, datastore,
+                                     date_index_from, date_index_to)
+
+            # Create and populate feed entry
+            guid = f"{uuid}/{timestamp_to}"
+            fe = fg.add_entry()
+            title_suffix = f"Change @ {res['original_context']['change_datetime']}"
+            populate_feed_entry(fe, watch, res.get('body', ''), guid, timestamp_to,
+                              link={'href': watch.get('url')}, title_suffix=title_suffix)
+            add_watch_categories(fe, watch, datastore)
+
+        response = make_response(fg.rss_str())
+        response.headers.set('Content-Type', 'application/rss+xml;charset=utf-8')
+        logger.debug(f"RSS Single watch built in {time.time()-now:.2f}s")
+
+        return response

changedetectionio/blueprint/rss/tag.py

@@ -0,0 +1,95 @@
+def construct_tag_routes(rss_blueprint, datastore):
+    """
+    Construct RSS feed routes for tags.
+
+    Args:
+        rss_blueprint: The Flask blueprint to add routes to
+        datastore: The ChangeDetectionStore instance
+    """
+
+    @rss_blueprint.route("/tag/<string:tag_uuid>", methods=['GET'])
+    def rss_tag_feed(tag_uuid):
+
+        from flask import make_response, request, url_for
+        from feedgen.feed import FeedGenerator
+
+        from . import RSS_TEMPLATE_HTML_DEFAULT, RSS_TEMPLATE_PLAINTEXT_DEFAULT
+        from ._util import (validate_rss_token, generate_watch_guid, get_rss_template,
+                           get_watch_label, build_notification_context, render_notification,
+                           populate_feed_entry, add_watch_categories)
+        from ...notification_service import NotificationService
+
+        """
+        Display an RSS feed for all unviewed watches that belong to a specific tag.
+        Returns RSS XML with entries for each unviewed watch with sufficient history.
+        """
+        # Validate token
+        is_valid, error = validate_rss_token(datastore, request)
+        if not is_valid:
+            return error
+
+        rss_content_format = datastore.data['settings']['application'].get('rss_content_format')
+
+        # Verify tag exists
+        tag = datastore.data['settings']['application'].get('tags', {}).get(tag_uuid)
+        if not tag:
+            return f"Tag with UUID {tag_uuid} not found", 404
+
+        tag_title = tag.get('title', 'Unknown Tag')
+
+        # Create RSS feed
+        fg = FeedGenerator()
+        fg.title(f'changedetection.io - {tag_title}')
+        fg.description(f'Changes for watches tagged with {tag_title}')
+        fg.link(href='https://changedetection.io')
+        notification_service = NotificationService(datastore=datastore, notification_q=False)
+        # Find all watches with this tag
+        for uuid, watch in datastore.data['watching'].items():
+            #@todo  This is wrong, it needs to sort by most recently changed and then limit it  datastore.data['watching'].items().sorted(?)
+            # So get all watches in this tag then sort
+
+            # Skip if watch doesn't have this tag
+            if tag_uuid not in watch.get('tags', []):
+                continue
+
+            # Skip muted watches if configured
+            if datastore.data['settings']['application'].get('rss_hide_muted_watches') and watch.get('notification_muted'):
+                continue
+
+            # Check if watch has at least 2 history snapshots
+            dates = list(watch.history.keys())
+            if len(dates) < 2:
+                continue
+
+            # Only include unviewed watches
+            if not watch.viewed:
+                # Include a link to the diff page (use uuid from loop, don't modify watch dict)
+                diff_link = {'href': url_for('ui.ui_diff.diff_history_page', uuid=uuid, _external=True)}
+
+                # Get watch label
+                watch_label = get_watch_label(datastore, watch)
+
+                # Get template and build notification context
+                timestamp_to = dates[-1]
+                timestamp_from = dates[-2]
+
+                # Generate GUID for this entry
+                guid = generate_watch_guid(watch, timestamp_to)
+                n_body_template = get_rss_template(datastore, watch, rss_content_format,
+                                                   RSS_TEMPLATE_HTML_DEFAULT, RSS_TEMPLATE_PLAINTEXT_DEFAULT)
+
+                n_object = build_notification_context(watch, timestamp_from, timestamp_to,
+                                                     watch_label, n_body_template, rss_content_format)
+
+                # Render notification
+                res = render_notification(n_object, notification_service, watch, datastore)
+
+                # Create and populate feed entry
+                fe = fg.add_entry()
+                title_suffix = f"Change @ {res['original_context']['change_datetime']}"
+                populate_feed_entry(fe, watch, res['body'], guid, timestamp_to, link=diff_link, title_suffix=title_suffix)
+                add_watch_categories(fe, watch, datastore)
+
+        response = make_response(fg.rss_str())
+        response.headers.set('Content-Type', 'application/rss+xml;charset=utf-8')
+        return response

changedetectionio/blueprint/settings/__init__.py

@@ -1,10 +1,12 @@
 import os
 from copy import deepcopy
-from datetime import datetime
+from datetime import datetime, timedelta
 from zoneinfo import ZoneInfo, available_timezones
 import secrets
+import time
 import flask_login
 from flask import Blueprint, render_template, request, redirect, url_for, flash
+from flask_babel import gettext
 
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
@@ -17,6 +19,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @login_optionally_required
     def settings_page():
         from changedetectionio import forms
+        from changedetectionio.pluggy_interface import (
+            get_plugin_settings_tabs,
+            load_plugin_settings,
+            save_plugin_settings
+        )
+
 
         default = deepcopy(datastore.data['settings'])
         if datastore.proxy_list is not None:
@@ -54,7 +62,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 # SALTED_PASS means the password is "locked" to what we set in the Env var
                 if not os.getenv("SALTED_PASS", False):
                     datastore.remove_password()
-                    flash("Password protection removed.", 'notice')
+                    flash(gettext("Password protection removed."), 'notice')
                     flask_login.logout_user()
                     return redirect(url_for('settings.settings_page'))
 
@@ -67,26 +75,100 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                     del (app_update['password'])
 
                 datastore.data['settings']['application'].update(app_update)
+
+                # Handle dynamic worker count adjustment
+                old_worker_count = datastore.data['settings']['requests'].get('workers', 1)
+                new_worker_count = form.data['requests'].get('workers', 1)
+
                 datastore.data['settings']['requests'].update(form.data['requests'])
+                datastore.commit()
+
+                # Clear all checksums to force reprocessing with new settings
+                # Global settings can affect watch behavior (filters, rendering, etc.)
+                datastore.clear_all_last_checksums()
+
+                # Adjust worker count if it changed
+                if new_worker_count != old_worker_count:
+                    from changedetectionio import worker_pool
+                    from changedetectionio.flask_app import update_q, notification_q, app, datastore as ds
+
+                    # Check CPU core availability and warn if worker count is high
+                    cpu_count = os.cpu_count()
+                    if cpu_count and new_worker_count >= (cpu_count * 0.9):
+                        flash(gettext("Warning: Worker count ({}) is close to or exceeds available CPU cores ({})").format(
+                            new_worker_count, cpu_count), 'warning')
+
+                    result = worker_pool.adjust_async_worker_count(
+                        new_count=new_worker_count,
+                        update_q=update_q,
+                        notification_q=notification_q,
+                        app=app,
+                        datastore=ds
+                    )
+
+                    if result['status'] == 'success':
+                        flash(gettext("Worker count adjusted: {}").format(result['message']), 'notice')
+                    elif result['status'] == 'not_supported':
+                        flash(gettext("Dynamic worker adjustment not supported for sync workers"), 'warning')
+                    elif result['status'] == 'error':
+                        flash(gettext("Error adjusting workers: {}").format(result['message']), 'error')
 
                 if not os.getenv("SALTED_PASS", False) and len(form.application.form.password.encrypted_password):
                     datastore.data['settings']['application']['password'] = form.application.form.password.encrypted_password
-                    datastore.needs_write_urgent = True
-                    flash("Password protection enabled.", 'notice')
+                    datastore.commit()
+                    flash(gettext("Password protection enabled."), 'notice')
                     flask_login.logout_user()
                     return redirect(url_for('watchlist.index'))
 
-                datastore.needs_write_urgent = True
-                flash("Settings updated.")
+                # Also save plugin settings from the same form submission
+                plugin_tabs_list = get_plugin_settings_tabs()
+                for tab in plugin_tabs_list:
+                    plugin_id = tab['plugin_id']
+                    form_class = tab['form_class']
+
+                    # Instantiate plugin form with POST data
+                    plugin_form = form_class(formdata=request.form)
+
+                    # Save plugin settings (validation is optional for plugins)
+                    if plugin_form.data:
+                        save_plugin_settings(datastore.datastore_path, plugin_id, plugin_form.data)
+
+                flash(gettext("Settings updated."))
 
             else:
-                flash("An error occurred, please see below.", "error")
+                flash(gettext("An error occurred, please see below."), "error")
 
         # Convert to ISO 8601 format, all date/time relative events stored as UTC time
         utc_time = datetime.now(ZoneInfo("UTC")).isoformat()
 
+        # Get active plugins
+        from changedetectionio.pluggy_interface import get_active_plugins
+        import sys
+        active_plugins = get_active_plugins()
+        python_version = f"{sys.version_info.major}.{sys.version_info.minor}.{sys.version_info.micro}"
+
+        # Calculate uptime in seconds
+        uptime_seconds = time.time() - datastore.start_time
+
+        # Get plugin settings tabs and instantiate forms
+        plugin_tabs = get_plugin_settings_tabs()
+        plugin_forms = {}
+
+        for tab in plugin_tabs:
+            plugin_id = tab['plugin_id']
+            form_class = tab['form_class']
+
+            # Load existing settings
+            settings = load_plugin_settings(datastore.datastore_path, plugin_id)
+
+            # Instantiate the form with existing settings
+            plugin_forms[plugin_id] = form_class(data=settings)
+
         output = render_template("settings.html",
+                                active_plugins=active_plugins,
                                 api_key=datastore.data['settings']['application'].get('api_access_token'),
+                                python_version=python_version,
+                                uptime_seconds=uptime_seconds,
                                 available_timezones=sorted(available_timezones()),
                                 emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
                                 extra_notification_token_placeholder_info=datastore.get_unique_notification_token_placeholders_available(),
@@ -94,8 +176,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                                 hide_remove_pass=os.getenv("SALTED_PASS", False),
                                 min_system_recheck_seconds=int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3)),
                                 settings_application=datastore.data['settings']['application'],
-                                timezone_default_config=datastore.data['settings']['application'].get('timezone'),
+                                timezone_default_config=datastore.data['settings']['application'].get('scheduler_timezone_default'),
                                 utc_time=utc_time,
+                                plugin_tabs=plugin_tabs,
+                                plugin_forms=plugin_forms,
                                 )
 
         return output
@@ -105,8 +189,8 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def settings_reset_api_key():
         secret = secrets.token_hex(16)
         datastore.data['settings']['application']['api_access_token'] = secret
-        datastore.needs_write_urgent = True
-        flash("API Key was regenerated.")
+        datastore.commit()
+        flash(gettext("API Key was regenerated."))
         return redirect(url_for('settings.settings_page')+'#api')
         
     @settings_blueprint.route("/notification-logs", methods=['GET'])
@@ -117,4 +201,32 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                                logs=notification_debug_log if len(notification_debug_log) else ["Notification logs are empty - no notifications sent yet."])
         return output
 
+    @settings_blueprint.route("/toggle-all-paused", methods=['GET'])
+    @login_optionally_required
+    def toggle_all_paused():
+        current_state = datastore.data['settings']['application'].get('all_paused', False)
+        datastore.data['settings']['application']['all_paused'] = not current_state
+        datastore.commit()
+
+        if datastore.data['settings']['application']['all_paused']:
+            flash(gettext("Automatic scheduling paused - checks will not be queued."), 'notice')
+        else:
+            flash(gettext("Automatic scheduling resumed - checks will be queued normally."), 'notice')
+
+        return redirect(url_for('watchlist.index'))
+
+    @settings_blueprint.route("/toggle-all-muted", methods=['GET'])
+    @login_optionally_required
+    def toggle_all_muted():
+        current_state = datastore.data['settings']['application'].get('all_muted', False)
+        datastore.data['settings']['application']['all_muted'] = not current_state
+        datastore.commit()
+
+        if datastore.data['settings']['application']['all_muted']:
+            flash(gettext("All notifications muted."), 'notice')
+        else:
+            flash(gettext("All notifications unmuted."), 'notice')
+
+        return redirect(url_for('watchlist.index'))
+
     return settings_blueprint

changedetectionio/blueprint/settings/templates/notification-log.html

@@ -4,7 +4,7 @@
 <div class="edit-form">
      <div class="inner">
 
-         <h4 style="margin-top: 0px;">Notification debug log</h4>
+         <h4 style="margin-top: 0px;">{{ _('Notification debug log') }}</h4>
                 <div id="notification-error-log">
                 <ul style="font-size: 80%; margin:0px; padding: 0 0 0 7px">
                 {% for log in logs|reverse %}

changedetectionio/blueprint/settings/templates/settings.html

@@ -1,8 +1,8 @@
 {% extends 'base.html' %}
 
 {% block content %}
-{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_time_schedule_form %}
-{% from '_common_fields.html' import render_common_settings_form %}
+{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_time_schedule_form, render_ternary_field, render_fieldlist_with_inline_errors %}
+{% from '_common_fields.html' import render_common_settings_form, show_token_placeholders %}
 <script>
     const notification_base_url="{{url_for('ui.ui_notification.ajax_callback_send_notification_test', mode="global-settings")}}";
 {% if emailprefix %}
@@ -18,14 +18,22 @@
 <div class="edit-form">
     <div class="tabs collapsable">
         <ul>
-            <li class="tab" id=""><a href="#general">General</a></li>
-            <li class="tab"><a href="#notifications">Notifications</a></li>
-            <li class="tab"><a href="#fetching">Fetching</a></li>
-            <li class="tab"><a href="#filters">Global Filters</a></li>
-            <li class="tab"><a href="#ui-options">UI Options</a></li>
-            <li class="tab"><a href="#api">API</a></li>
-            <li class="tab"><a href="#timedate">Time &amp Date</a></li>
-            <li class="tab"><a href="#proxies">CAPTCHA &amp; Proxies</a></li>
+            <li class="tab" id=""><a href="#general">{{ _('General') }}</a></li>
+            <li class="tab"><a href="#notifications">{{ _('Notifications') }}</a></li>
+            <li class="tab"><a href="#fetching">{{ _('Fetching') }}</a></li>
+            <li class="tab"><a href="#filters">{{ _('Global Filters') }}</a></li>
+            <li class="tab"><a href="#ui-options">{{ _('UI Options') }}</a></li>
+            <li class="tab"><a href="#api">{{ _('API') }}</a></li>
+            <li class="tab"><a href="#rss">{{ _('RSS') }}</a></li>
+            <li class="tab"><a href="{{ url_for('backups.index') }}">{{ _('Backups') }}</a></li>
+            <li class="tab"><a href="#timedate">{{ _('Time & Date') }}</a></li>
+            <li class="tab"><a href="#proxies">{{ _('CAPTCHA & Proxies') }}</a></li>
+            {% if plugin_tabs %}
+                {% for tab in plugin_tabs %}
+            <li class="tab"><a href="#plugin-{{ tab.plugin_id }}">{{ tab.tab_label }}</a></li>
+                {% endfor %}
+            {% endif %}
+            <li class="tab"><a href="#info">{{ _('Info') }}</a></li>
         </ul>
     </div>
     <div class="box-wrap inner">
@@ -35,84 +43,73 @@
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.requests.form.time_between_check, class="time-check-widget") }}
-                        <span class="pure-form-message-inline">Default recheck time for all watches, current system minimum is <i>{{min_system_recheck_seconds}}</i> seconds (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Misc-system-settings#enviroment-variables">more info</a>).</span>
+
+                        <span class="pure-form-message-inline">{{ _('Default recheck time for all watches, current system minimum is') }} <i>{{min_system_recheck_seconds}}</i> {{ _('seconds') }} (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Misc-system-settings#enviroment-variables">{{ _('more info') }}</a>).</span>
                             <div id="time-between-check-schedule">
-                                <!-- Start Time and End Time -->
+                                <!-- Start Time and End Time {{ timezone_default_config }} -->
                                 <div id="limit-between-time">
-                                    {{ render_time_schedule_form(form.requests, available_timezones, timezone_default_config) }}
+                                   {{ render_time_schedule_form(form.requests, available_timezones, timezone_default_config) }}
                                 </div>
                         </div>
                     </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.requests.form.jitter_seconds, class="jitter_seconds") }}
-                        <span class="pure-form-message-inline">Example - 3 seconds random jitter could trigger up to 3 seconds earlier or up to 3 seconds later</span>
-                    </div>
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.filter_failure_notification_threshold_attempts, class="filter_failure_notification_threshold_attempts") }}
-                        <span class="pure-form-message-inline">After this many consecutive times that the CSS/xPath filter is missing, send a notification
+                        <span class="pure-form-message-inline">{{ _('After this many consecutive times that the CSS/xPath filter is missing, send a notification') }}
                             <br>
-                        Set to <strong>0</strong> to disable
+                        {{ _('Set to') }} <strong>0</strong> {{ _('to disable') }}
                         </span>
                     </div>
+                    <div class="pure-control-group">
+                        {{ render_field(form.application.form.history_snapshot_max_length, class="history_snapshot_max_length") }}
+                        <span class="pure-form-message-inline">{{ _('Limit collection of history snapshots for each watch to this number of history items.') }}
+                            <br>
+                        {{ _('Set to empty to disable / no limit') }}
+                        </span>
+                    </div>
+
                     <div class="pure-control-group">
                         {% if not hide_remove_pass %}
                             {% if current_user.is_authenticated %}
                                 {{ render_button(form.application.form.removepassword_button) }}
                             {% else %}
                             {{ render_field(form.application.form.password) }}
-                            <span class="pure-form-message-inline">Password protection for your changedetection.io application.</span>
+                            <span class="pure-form-message-inline">{{ _('Password protection for your changedetection.io application.') }}</span>
                             {% endif %}
                         {% else %}
-                            <span class="pure-form-message-inline">Password is locked.</span>
+                            <span class="pure-form-message-inline">{{ _('Password is locked.') }}</span>
                         {% endif %}
                     </div>
 
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.shared_diff_access, class="shared_diff_access") }}
-                        <span class="pure-form-message-inline">Allow access to view watch diff page when password is enabled (Good for sharing the diff page)
-                        </span>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.application.form.rss_hide_muted_watches) }}
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.application.form.pager_size) }}
-                        <span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.application.form.rss_content_format) }}
-                        <span class="pure-form-message-inline">Love RSS? Does your reader support HTML? Set it here</span>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.application.form.extract_title_as_title) }}
-                        <span class="pure-form-message-inline">Note: This will automatically apply to all existing watches.</span>
+                        <span class="pure-form-message-inline">{{ _('Allow access to the watch change history page when password is enabled (Good for sharing the diff page)') }}</span>
                     </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.empty_pages_are_a_change) }}
-                        <span class="pure-form-message-inline">When a request returns no content, or the HTML does not contain any text, is this considered a change?</span>
+                        <span class="pure-form-message-inline">{{ _('When a request returns no content, or the HTML does not contain any text, is this considered a change?') }}</span>
                     </div>
                 {% if form.requests.proxy %}
-                    <div class="pure-control-group inline-radio">
-                        {{ render_field(form.requests.form.proxy, class="fetch-backend-proxy") }}
-                        <span class="pure-form-message-inline">
-                        Choose a default proxy for all watches
-                        </span>
+                    <div>
+                    <br>
+                        <div class="inline-radio">
+                            {{ render_field(form.requests.form.proxy, class="fetch-backend-proxy") }}
+                            <span class="pure-form-message-inline">{{ _('Choose a default proxy for all watches') }}</span>
+                        </div>
                     </div>
                 {% endif %}
+
                 </fieldset>
             </div>
 
             <div class="tab-pane-inner" id="notifications">
                 <fieldset>
-                    <div class="field-group">
-                        {{ render_common_settings_form(form.application.form, emailprefix, settings_application, extra_notification_token_placeholder_info) }}
-                    </div>
+                    {{ render_common_settings_form(form.application.form, emailprefix, settings_application, extra_notification_token_placeholder_info) }}
                 </fieldset>
                 <div class="pure-control-group" id="notification-base-url">
                     {{ render_field(form.application.form.base_url, class="m-d") }}
                     <span class="pure-form-message-inline">
-                        Base URL used for the <code>{{ '{{ base_url }}' }}</code> token in notification links.<br>
-                        Default value is the system environment variable '<code>BASE_URL</code>' - <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">read more here</a>.
+                        {{ _('Base URL used for the') }} <code>{{ '{{ base_url }}' }}</code> {{ _('token in notification links.') }}<br>
+                        {{ _('Default value is the system environment variable') }} '<code>BASE_URL</code>' - <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">{{ _('read more here') }}</a>.
                     </span>
                 </div>
             </div>
@@ -121,30 +118,44 @@
                 <div class="pure-control-group inline-radio">
                     {{ render_field(form.application.form.fetch_backend, class="fetch-backend") }}
                     <span class="pure-form-message-inline">
-                        <p>Use the <strong>Basic</strong> method (default) where your watched sites don't need Javascript to render.</p>
-                        <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
+                        <p>{{ _('Use the') }} <strong>{{ _('Basic') }}</strong> {{ _('method (default) where your watched sites don\'t need Javascript to render.') }}</p>
+                        <p>{{ _('The') }} <strong>{{ _('Chrome/Javascript') }}</strong> {{ _('method requires a network connection to a running WebDriver+Chrome server, set by the ENV var') }} 'WEBDRIVER_URL'. </p>
                     </span>
                 </div>
                 <fieldset class="pure-group" id="webdriver-override-options" data-visible-for="application-fetch_backend=html_webdriver">
                     <div class="pure-form-message-inline">
-                        <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
+                        <strong>{{ _('If you\'re having trouble waiting for the page to be fully rendered (text missing etc), try increasing the \'wait\' time here.') }}</strong>
                         <br>
-                        This will wait <i>n</i> seconds before extracting the text.
+                        {{ _('This will wait') }} <i>n</i> {{ _('seconds before extracting the text.') }}
                     </div>
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.webdriver_delay) }}
                     </div>
                 </fieldset>
+                <div class="pure-control-group">
+                    {{ render_field(form.requests.form.workers) }}
+                    {% set worker_info = get_worker_status_info() %}
+                    <span class="pure-form-message-inline">{{ _('Number of concurrent workers to process watches. More workers = faster processing but higher memory usage.') }}<br>
+                    {{ _('Currently running:') }} <strong>{{ worker_info.count }}</strong> {{ _('operational') }} {{ worker_info.type }} {{ _('workers') }}{% if worker_info.active_workers > 0 %} ({{ worker_info.active_workers }} {{ _('actively processing') }}){% endif %}.</span>
+                </div>
+                <div class="pure-control-group">
+                    {{ render_field(form.requests.form.jitter_seconds, class="jitter_seconds") }}
+                    <span class="pure-form-message-inline">{{ _('Example - 3 seconds random jitter could trigger up to 3 seconds earlier or up to 3 seconds later') }}</span>
+                </div>
+                <div class="pure-control-group">
+                    {{ render_field(form.requests.form.timeout) }}
+                    <span class="pure-form-message-inline">{{ _('For regular plain requests (not chrome based), maximum number of seconds until timeout, 1-999.') }}</span><br>
+                </div>
                 <div class="pure-control-group inline-radio">
                     {{ render_field(form.requests.form.default_ua) }}
                     <span class="pure-form-message-inline">
-                        Applied to all requests.<br><br>
-                        Note: Simply changing the User-Agent often does not defeat anti-robot technologies, it's important to consider <a href="https://changedetection.io/tutorial/what-are-main-types-anti-robot-mechanisms">all of the ways that the browser is detected</a>.
+                        {{ _('Applied to all requests.') }}<br><br>
+                        {{ _('Note: Simply changing the User-Agent often does not defeat anti-robot technologies, it\'s important to consider') }} <a href="https://changedetection.io/tutorial/what-are-main-types-anti-robot-mechanisms">{{ _('all of the ways that the browser is detected') }}</a>.
                     </span>
                 </div>
                 <div class="pure-control-group">
                                         <br>
-                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
+                    {{ _('Tip:') }} <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">{{ _('Connect using Bright Data and Oxylabs Proxies, find out more here.') }}</a>
 
                 </div>
             </div>
@@ -153,15 +164,15 @@
 
                     <fieldset class="pure-group">
                     {{ render_checkbox_field(form.application.form.ignore_whitespace) }}
-                    <span class="pure-form-message-inline">Ignore whitespace, tabs and new-lines/line-feeds when considering if a change was detected.<br>
-                    <i>Note:</i> Changing this will change the status of your existing watches, possibly trigger alerts etc.
+                    <span class="pure-form-message-inline">{{ _('Ignore whitespace, tabs and new-lines/line-feeds when considering if a change was detected.') }}<br>
+                    <i>{{ _('Note:') }}</i> {{ _('Changing this will change the status of your existing watches, possibly trigger alerts etc.') }}
                     </span>
                     </fieldset>
                 <fieldset class="pure-group">
                     {{ render_checkbox_field(form.application.form.render_anchor_tag_content) }}
-                    <span class="pure-form-message-inline">Render anchor tag content, default disabled, when enabled renders links as <code>(link text)[https://somesite.com]</code>
+                    <span class="pure-form-message-inline">{{ _('Render anchor tag content, default disabled, when enabled renders links as') }} <code>(link text)[https://somesite.com]</code>
                         <br>
-                    <i>Note:</i> Changing this could affect the content of your existing watches, possibly trigger alerts etc.
+                    <i>{{ _('Note:') }}</i> {{ _('Changing this could affect the content of your existing watches, possibly trigger alerts etc.') }}
                     </span>
                     </fieldset>
                     <fieldset class="pure-group">
@@ -172,9 +183,9 @@ nav
 //*[contains(text(), 'Advertisement')]") }}
                       <span class="pure-form-message-inline">
                         <ul>
-                          <li> Remove HTML element(s) by CSS and XPath selectors before text conversion. </li>
-                          <li> Don't paste HTML here, use only CSS and XPath selectors </li>
-                          <li> Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML. </li>
+                          <li> {{ _('Remove HTML element(s) by CSS and XPath selectors before text conversion.') }} </li>
+                          <li> {{ _('Don\'t paste HTML here, use only CSS and XPath selectors') }} </li>
+                          <li> {{ _('Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML.') }} </li>
                         </ul>
                       </span>
                     </fieldset>
@@ -182,70 +193,120 @@ nav
                     {{ render_field(form.application.form.global_ignore_text, rows=5, placeholder="Some text to ignore in a line
 /some.regex\d{2}/ for case-INsensitive regex
                     ") }}
-                    <span class="pure-form-message-inline">Note: This is applied globally in addition to the per-watch rules.</span><br>
+                    <span class="pure-form-message-inline">{{ _('Note: This is applied globally in addition to the per-watch rules.') }}</span><br>
                     <span class="pure-form-message-inline">
                         <ul>
-                            <li>Matching text will be <strong>ignored</strong> in the text snapshot (you can still see it but it wont trigger a change)</li>
-                            <li>Note: This is applied globally in addition to the per-watch rules.</li>
-                            <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
-                            <li>Changing this will affect the comparison checksum which may trigger an alert</li>
+                            <li>{{ _('Matching text will be') }} <strong>{{ _('ignored') }}</strong> {{ _('in the text snapshot (you can still see it but it wont trigger a change)') }}</li>
+                            <li>{{ _('Note: This is applied globally in addition to the per-watch rules.') }}</li>
+                            <li>{{ _('Each line processed separately, any line matching will be ignored (removed before creating the checksum)') }}</li>
+                            <li>{{ _('Regular Expression support, wrap the entire line in forward slash') }} <code>/regex/</code></li>
+                            <li>{{ _('Changing this will affect the comparison checksum which may trigger an alert') }}</li>
                         </ul>
                      </span>
                     </fieldset>
+                    <fieldset class="pure-group">
+                        {{ render_checkbox_field(form.application.form.strip_ignored_lines) }}
+                        <span class="pure-form-message-inline">{{ _('Remove any text that appears in the "Ignore text" from the output (otherwise its just ignored for change-detection)') }}<br>
+                        <i>{{ _('Note:') }}</i> {{ _('Changing this will change the status of your existing watches, possibly trigger alerts etc.') }}
+                        </span>
+                    </fieldset>
            </div>
 
             <div class="tab-pane-inner" id="api">
-                <h4>API Access</h4>
-                <p>Drive your changedetection.io via API, More about <a href="https://github.com/dgtlmoon/changedetection.io/wiki/API-Reference">API access here</a></p>
+                <h4>{{ _('API Access') }}</h4>
+                <p>{{ _('Drive your changedetection.io via API, More about') }} <a href="https://changedetection.io/docs/api_v1/index.html">{{ _('API access and examples here') }}</a>.</p>
 
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.api_access_token_enabled) }}
-                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header - required for the Chrome Extension to work</div><br>
-                    <div class="pure-form-message-inline"><br>API Key <span id="api-key">{{api_key}}</span>
-                        <span style="display:none;" id="api-key-copy" >copy</span>
+                    <div class="pure-form-message-inline">{{ _('Restrict API access limit by using') }} <code>x-api-key</code> {{ _('header - required for the Chrome Extension to work') }}</div><br>
+                    <div class="pure-form-message-inline"><br>{{ _('API Key') }} <span id="api-key">{{api_key}}</span>
+                        <span style="display:none;" id="api-key-copy" >{{ _('copy') }}</span>
                     </div>
                 </div>
                 <div class="pure-control-group">
-                    <a href="{{url_for('settings.settings_reset_api_key')}}" class="pure-button button-small button-cancel">Regenerate API key</a>
+                    <a href="{{url_for('settings.settings_reset_api_key')}}" class="pure-button button-small button-cancel">{{ _('Regenerate API key') }}</a>
                 </div>
                 <div class="pure-control-group">
-                    <h4>Chrome Extension</h4>
-                    <p>Easily add any web-page to your changedetection.io installation from within Chrome.</p>
-                    <strong>Step 1</strong> Install the extension, <strong>Step 2</strong> Navigate to this page,
-                    <strong>Step 3</strong> Open the extension from the toolbar and click "<i>Sync API Access</i>"
+                    <h4>{{ _('Chrome Extension') }}</h4>
+                    <p>{{ _('Easily add any web-page to your changedetection.io installation from within Chrome.') }}</p>
+                    <strong>{{ _('Step 1') }}</strong> {{ _('Install the extension,') }} <strong>{{ _('Step 2') }}</strong> {{ _('Navigate to this page,') }}
+                    <strong>{{ _('Step 3') }}</strong> {{ _('Open the extension from the toolbar and click') }} "<i>{{ _('Sync API Access') }}</i>"
                     <p>
                         <a id="chrome-extension-link"
-                           title="Try our new Chrome Extension!"
+                           title="{{ _('Try our new Chrome Extension!') }}"
                            href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
-                            <img alt="Chrome store icon" src="{{ url_for('static_content', group='images', filename='google-chrome-icon.png') }}" alt="Chrome">
-                            Chrome Webstore
+                            <img alt="{{ _('Chrome store icon') }}" src="{{ url_for('static_content', group='images', filename='google-chrome-icon.png') }}" >
+                            {{ _('Chrome Webstore') }}
                         </a>
                     </p>
                 </div>
             </div>
-            <div class="tab-pane-inner" id="timedate">
+            <div class="tab-pane-inner" id="rss">
                 <div class="pure-control-group">
-                    Ensure the settings below are correct, they are used to manage the time schedule for checking your web page watches.
+                    {{ render_checkbox_field(form.application.form.rss_hide_muted_watches) }}
                 </div>
                 <div class="pure-control-group">
-                    <p><strong>UTC Time &amp Date from Server:</strong> <span id="utc-time" >{{ utc_time }}</span></p>
-                    <p><strong>Local Time &amp Date in Browser:</strong> <span class="local-time" data-utc="{{ utc_time }}"></span></p>
-                    <p>
-                       {{ render_field(form.application.form.timezone) }}
+                    {{ render_field(form.application.form.rss_diff_length) }}
+                    <span class="pure-form-message-inline">{{ _('Maximum number of history snapshots to include in the watch specific RSS feed.') }}</span>
+                </div>
+                <div class="pure-control-group">
+                    {{ render_checkbox_field(form.application.form.rss_reader_mode) }}
+                    <span class="pure-form-message-inline">{{ _('For watching other RSS feeds - When watching RSS/Atom feeds, convert them into clean text for better change detection.') }}</span>
+                </div>
+                <div class="pure-control-group grey-form-border">
+                    <div class="pure-control-group">
+                        {{ render_field(form.application.form.rss_content_format) }}
+                        <span class="pure-form-message-inline">{{ _('Does your reader support HTML? Set it here') }}</span>
+                    </div>
+                    <div class="pure-control-group">
+                        {{ render_field(form.application.form.rss_template_type) }}
+                        <span class="pure-form-message-inline">{{ _('\'System default\' for the same template for all items, or re-use your "Notification Body" as the template.') }}</span>
+                    </div>
+                    <div>
+                       {{ render_field(form.application.form.rss_template_override) }}
+                        {{ show_token_placeholders(extra_notification_token_placeholder_info=extra_notification_token_placeholder_info, suffix="-rss") }}
+                    </div>
+                </div>
+                <br>
+
+
+            </div>
+                <div class="tab-pane-inner" id="timedate">
+                <div class="pure-control-group">
+                    {{ _('Ensure the settings below are correct, they are used to manage the time schedule for checking your web page watches.') }}
+                </div>
+                <div class="pure-control-group">
+                    <p><strong>{{ _('UTC Time & Date from Server:') }}</strong> <span id="utc-time" >{{ utc_time }}</span></p>
+                    <p><strong>{{ _('Local Time & Date in Browser:') }}</strong> <span class="local-time" data-utc="{{ utc_time }}"></span></p>
+                    <div>
+                       {{ render_field(form.application.form.scheduler_timezone_default) }}
                         <datalist id="timezones" style="display: none;">
-                            {% for tz_name in available_timezones %}
-                                <option value="{{ tz_name }}">{{ tz_name }}</option>
-                            {% endfor %}
+                            {%- for timezone in available_timezones -%}<option value="{{ timezone }}">{{ timezone }}</option>{%- endfor -%}
                         </datalist>
-                    </p>
+                    </div>
                 </div>
             </div>
             <div class="tab-pane-inner" id="ui-options">
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.ui.form.open_diff_in_new_tab, class="open_diff_in_new_tab") }}
-                    <span class="pure-form-message-inline">Enable this setting to open the diff page in a new tab. If disabled, the diff page will open in the current tab.</span>
+                    <span class="pure-form-message-inline">{{ _('Enable this setting to open the diff page in a new tab. If disabled, the diff page will open in the current tab.') }}</span>
                 </div>
+                <div class="pure-control-group">
+                    {{ render_checkbox_field(form.application.form.ui.form.socket_io_enabled, class="socket_io_enabled") }}
+                    <span class="pure-form-message-inline">{{ _('Realtime UI Updates Enabled - (Restart required if this is changed)') }}</span>
+                </div>
+                <div class="pure-control-group">
+                    {{ render_checkbox_field(form.application.form.ui.form.favicons_enabled, class="") }}
+                    <span class="pure-form-message-inline">{{ _('Enable or Disable Favicons next to the watch list') }}</span>
+                </div>
+                <div class="pure-control-group">
+                    {{ render_checkbox_field(form.application.form.ui.use_page_title_in_list) }}
+                </div>
+                <div class="pure-control-group">
+                    {{ render_field(form.application.form.pager_size) }}
+                    <span class="pure-form-message-inline">{{ _('Number of items per page in the watch overview list, 0 to disable.') }}</span>
+                </div>
+
             </div>
             <div class="tab-pane-inner" id="proxies">
                 <div id="recommended-proxy">
@@ -291,26 +352,66 @@ nav
                     </div>
                 </div>
 
-               <p><strong>Tip</strong>: "Residential" and "Mobile" proxy type can be more successfull than "Data Center" for blocked websites.
+                <p><strong>{{ _('Tip') }}</strong>: {{ _('"Residential" and "Mobile" proxy type can be more successfull than "Data Center" for blocked websites.') }}</p>
 
                 <div class="pure-control-group" id="extra-proxies-setting">
-                {{ render_field(form.requests.form.extra_proxies) }}
-                <span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span><br>
-                <span class="pure-form-message-inline">SOCKS5 proxies with authentication are only supported with 'plain requests' fetcher, for other fetchers you should whitelist the IP access instead</span>
+                {{ render_fieldlist_with_inline_errors(form.requests.form.extra_proxies) }}
+                <span class="pure-form-message-inline">{{ _('"Name" will be used for selecting the proxy in the Watch Edit settings') }}</span><br>
+                <span class="pure-form-message-inline">{{ _('SOCKS5 proxies with authentication are only supported with \'plain requests\' fetcher, for other fetchers you should whitelist the IP access instead') }}</span>
                 </div>
                 <div class="pure-control-group" id="extra-browsers-setting">
                     <p>
                     <span class="pure-form-message-inline"><i>Extra Browsers</i> can be attached to further defeat CAPTCHA's on websites that are particularly hard to scrape.</span><br>
                     <span class="pure-form-message-inline">Simply paste the connection address into the box, <a href="https://changedetection.io/tutorial/using-bright-datas-scraping-browser-pass-captchas-and-other-protection-when-monitoring">More instructions and examples here</a> </span>
                     </p>
-                    {{ render_field(form.requests.form.extra_browsers) }}
+                    {{ render_fieldlist_with_inline_errors(form.requests.form.extra_browsers) }}
                 </div>
             </div>
+            {% if plugin_tabs %}
+                {% for tab in plugin_tabs %}
+            <div class="tab-pane-inner" id="plugin-{{ tab.plugin_id }}">
+                {% set plugin_form = plugin_forms[tab.plugin_id] %}
+                {% if tab.template_path %}
+                    {# Plugin provides custom template - include it directly (no separate form) #}
+                    {% include tab.template_path with context %}
+                {% else %}
+                    {# Default form rendering - fields only, no submit button #}
+                    <fieldset>
+                        {% for field in plugin_form %}
+                            {% if field.type != 'CSRFToken' and field.type != 'SubmitField' %}
+                        <div class="pure-control-group">
+                                {% if field.type == 'BooleanField' %}
+                            {{ render_checkbox_field(field) }}
+                                {% else %}
+                            {{ render_field(field) }}
+                                {% endif %}
+                        </div>
+                            {% endif %}
+                        {% endfor %}
+                    </fieldset>
+                {% endif %}
+            </div>
+                {% endfor %}
+            {% endif %}
+            <div class="tab-pane-inner" id="info">
+                <p><strong>{{ _('Uptime:') }}</strong> {{ uptime_seconds|format_duration }}</p>
+                <p><strong>{{ _('Python version:') }}</strong> {{ python_version }}</p>
+                <p><strong>{{ _('Plugins active:') }}</strong></p>
+                {% if active_plugins %}
+                <ul>
+                    {% for plugin in active_plugins %}
+                    <li><strong>{{ plugin.name }}</strong> - {{ plugin.description }}</li>
+                    {% endfor %}
+                </ul>
+                {% else %}
+                <p>{{ _('No plugins active') }}</p>
+                {% endif %}
+            </div>
             <div id="actions">
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}
-                    <a href="{{url_for('watchlist.index')}}" class="pure-button button-small button-cancel">Back</a>
-                    <a href="{{url_for('ui.clear_all_history')}}" class="pure-button button-small button-error">Clear Snapshot History</a>
+                    <a href="{{url_for('watchlist.index')}}" class="pure-button button-cancel">{{ _('Back') }}</a>
+                    <a href="{{url_for('ui.clear_all_history')}}" class="pure-button button-error">{{ _('Clear Snapshot History') }}</a>
                 </div>
             </div>
         </form>

changedetectionio/blueprint/tags/__init__.py

@@ -1,5 +1,7 @@
+import threading
 from flask import Blueprint, request, render_template, flash, url_for, redirect
-
+from flask_babel import gettext
+from loguru import logger
 
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.flask_app import login_optionally_required
@@ -21,9 +23,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         tag_count = Counter(tag for watch in datastore.data['watching'].values() if watch.get('tags') for tag in watch['tags'])
 
         output = render_template("groups-overview.html",
+                                 app_rss_token=datastore.data['settings']['application'].get('rss_access_token'),
                                  available_tags=sorted_tags,
                                  form=add_form,
-                                 tag_count=tag_count
+                                 tag_count=tag_count,
                                  )
 
         return output
@@ -42,11 +45,11 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         title = request.form.get('name').strip()
 
         if datastore.tag_exists_by_name(title):
-            flash(f'The tag "{title}" already exists', "error")
+            flash(gettext('The tag "{}" already exists').format(title), "error")
             return redirect(url_for('tags.tags_overview_page'))
 
         datastore.add_tag(title)
-        flash("Tag added")
+        flash(gettext("Tag added"))
 
 
         return redirect(url_for('tags.tags_overview_page'))
@@ -54,46 +57,107 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @tags_blueprint.route("/mute/<string:uuid>", methods=['GET'])
     @login_optionally_required
     def mute(uuid):
-        if datastore.data['settings']['application']['tags'].get(uuid):
-            datastore.data['settings']['application']['tags'][uuid]['notification_muted'] = not datastore.data['settings']['application']['tags'][uuid]['notification_muted']
+        tag = datastore.data['settings']['application']['tags'].get(uuid)
+        if tag:
+            tag['notification_muted'] = not tag['notification_muted']
+            tag.commit()
         return redirect(url_for('tags.tags_overview_page'))
 
     @tags_blueprint.route("/delete/<string:uuid>", methods=['GET'])
     @login_optionally_required
     def delete(uuid):
-        removed = 0
-        # Delete the tag, and any tag reference
+        # Delete the tag from settings immediately
         if datastore.data['settings']['application']['tags'].get(uuid):
             del datastore.data['settings']['application']['tags'][uuid]
 
-        for watch_uuid, watch in datastore.data['watching'].items():
-            if watch.get('tags') and uuid in watch['tags']:
-                removed += 1
-                watch['tags'].remove(uuid)
+        # Delete tag.json file if it exists
+        import os
+        tag_dir = os.path.join(datastore.datastore_path, uuid)
+        tag_json = os.path.join(tag_dir, "tag.json")
+        if os.path.exists(tag_json):
+            try:
+                os.unlink(tag_json)
+                logger.info(f"Deleted tag.json for tag {uuid}")
+            except Exception as e:
+                logger.error(f"Failed to delete tag.json for tag {uuid}: {e}")
 
-        flash(f"Tag deleted and removed from {removed} watches")
+        # Remove tag from all watches in background thread to avoid blocking
+        def remove_tag_background(tag_uuid):
+            """Background thread to remove tag from watches - discarded after completion."""
+            removed_count = 0
+            try:
+                for watch_uuid, watch in datastore.data['watching'].items():
+                    if watch.get('tags') and tag_uuid in watch['tags']:
+                        watch['tags'].remove(tag_uuid)
+                        watch.commit()
+                        removed_count += 1
+                logger.info(f"Background: Tag {tag_uuid} removed from {removed_count} watches")
+            except Exception as e:
+                logger.error(f"Error removing tag from watches: {e}")
+
+        # Start daemon thread
+        threading.Thread(target=remove_tag_background, args=(uuid,), daemon=True).start()
+
+        flash(gettext("Tag deleted, removing from watches in background"))
         return redirect(url_for('tags.tags_overview_page'))
 
     @tags_blueprint.route("/unlink/<string:uuid>", methods=['GET'])
     @login_optionally_required
     def unlink(uuid):
-        unlinked = 0
-        for watch_uuid, watch in datastore.data['watching'].items():
-            if watch.get('tags') and uuid in watch['tags']:
-                unlinked += 1
-                watch['tags'].remove(uuid)
+        # Unlink tag from all watches in background thread to avoid blocking
+        def unlink_tag_background(tag_uuid):
+            """Background thread to unlink tag from watches - discarded after completion."""
+            unlinked_count = 0
+            try:
+                for watch_uuid, watch in datastore.data['watching'].items():
+                    if watch.get('tags') and tag_uuid in watch['tags']:
+                        watch['tags'].remove(tag_uuid)
+                        watch.commit()
+                        unlinked_count += 1
+                logger.info(f"Background: Tag {tag_uuid} unlinked from {unlinked_count} watches")
+            except Exception as e:
+                logger.error(f"Error unlinking tag from watches: {e}")
 
-        flash(f"Tag unlinked removed from {unlinked} watches")
+        # Start daemon thread
+        threading.Thread(target=unlink_tag_background, args=(uuid,), daemon=True).start()
+
+        flash(gettext("Unlinking tag from watches in background"))
         return redirect(url_for('tags.tags_overview_page'))
 
     @tags_blueprint.route("/delete_all", methods=['GET'])
     @login_optionally_required
     def delete_all():
-        for watch_uuid, watch in datastore.data['watching'].items():
-            watch['tags'] = []
+        # Delete all tag.json files
+        import os
+        for tag_uuid in list(datastore.data['settings']['application']['tags'].keys()):
+            tag_dir = os.path.join(datastore.datastore_path, tag_uuid)
+            tag_json = os.path.join(tag_dir, "tag.json")
+            if os.path.exists(tag_json):
+                try:
+                    os.unlink(tag_json)
+                except Exception as e:
+                    logger.error(f"Failed to delete tag.json for tag {tag_uuid}: {e}")
+
+        # Clear all tags from settings immediately
         datastore.data['settings']['application']['tags'] = {}
 
-        flash(f"All tags deleted")
+        # Clear tags from all watches in background thread to avoid blocking
+        def clear_all_tags_background():
+            """Background thread to clear tags from all watches - discarded after completion."""
+            cleared_count = 0
+            try:
+                for watch_uuid, watch in datastore.data['watching'].items():
+                    watch['tags'] = []
+                    watch.commit()
+                    cleared_count += 1
+                logger.info(f"Background: Cleared tags from {cleared_count} watches")
+            except Exception as e:
+                logger.error(f"Error clearing tags from watches: {e}")
+
+        # Start daemon thread
+        threading.Thread(target=clear_all_tags_background, daemon=True).start()
+
+        flash(gettext("All tags deleted, clearing from watches in background"))
         return redirect(url_for('tags.tags_overview_page'))
 
     @tags_blueprint.route("/edit/<string:uuid>", methods=['GET'])
@@ -105,7 +169,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         default = datastore.data['settings']['application']['tags'].get(uuid)
         if not default:
-            flash("Tag not found", "error")
+            flash(gettext("Tag not found"), "error")
             return redirect(url_for('watchlist.index'))
 
         form = group_restock_settings_form(
@@ -149,9 +213,9 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             included_content = template.render(**template_args)
 
         output = render_template("edit-tag.html",
-                                 settings_application=datastore.data['settings']['application'],
-                                 extra_tab_content=form.extra_tab_content() if form.extra_tab_content() else None,
                                  extra_form_content=included_content,
+                                 extra_tab_content=form.extra_tab_content() if form.extra_tab_content() else None,
+                                 settings_application=datastore.data['settings']['application'],
                                  **template_args
                                  )
 
@@ -165,10 +229,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         if uuid == 'first':
             uuid = list(datastore.data['settings']['application']['tags'].keys()).pop()
 
-        default = datastore.data['settings']['application']['tags'].get(uuid)
+        tag = datastore.data['settings']['application']['tags'].get(uuid)
 
         form = group_restock_settings_form(formdata=request.form if request.method == 'POST' else None,
-                               data=default,
+                               data=tag,
                                extra_notification_tokens=datastore.get_unique_notification_tokens_available()
                                )
         # @todo subclass form so validation works
@@ -177,10 +241,16 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 #                flash(','.join(l), 'error')
 #           return redirect(url_for('tags.form_tag_edit_submit', uuid=uuid))
 
-        datastore.data['settings']['application']['tags'][uuid].update(form.data)
-        datastore.data['settings']['application']['tags'][uuid]['processor'] = 'restock_diff'
-        datastore.needs_write_urgent = True
-        flash("Updated")
+        tag.update(form.data)
+        tag['processor'] = 'restock_diff'
+        tag.commit()
+
+        # Clear checksums for all watches using this tag to force reprocessing
+        # Tag changes affect inherited configuration
+        cleared_count = datastore.clear_checksums_for_tag(uuid)
+        logger.info(f"Tag {uuid} updated, cleared {cleared_count} watch checksums")
+
+        flash(gettext("Updated"))
 
         return redirect(url_for('tags.tags_overview_page'))
 

changedetectionio/blueprint/tags/templates/edit-tag.html

@@ -1,6 +1,6 @@
 {% extends 'base.html' %}
 {% block content %}
-{% from '_helpers.html' import render_field, render_checkbox_field, render_button %}
+{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_ternary_field %}
 {% from '_common_fields.html' import render_common_settings_form %}
 <script>
     const notification_base_url="{{url_for('ui.ui_notification.ajax_callback_send_notification_test', mode="group-settings")}}";
@@ -24,12 +24,12 @@
 
     <div class="tabs collapsable">
         <ul>
-            <li class="tab" id=""><a href="#general">General</a></li>
-            <li class="tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
+            <li class="tab" id=""><a href="#general">{{ _('General') }}</a></li>
+            <li class="tab"><a href="#filters-and-triggers">{{ _('Filters & Triggers') }}</a></li>
             {% if extra_tab_content %}
             <li class="tab"><a href="#extras_tab">{{ extra_tab_content }}</a></li>
             {% endif %}
-            <li class="tab"><a href="#notifications">Notifications</a></li>
+            <li class="tab"><a href="#notifications">{{ _('Notifications') }}</a></li>
         </ul>
     </div>
 
@@ -47,10 +47,10 @@
             </div>
 
             <div class="tab-pane-inner" id="filters-and-triggers">
-                <p>These settings are <strong><i>added</i></strong> to any existing watch configurations.</p>
+                <p>{{ _('These settings are') }} <strong><i>{{ _('added') }}</i></strong> {{ _('to any existing watch configurations.') }}</p>
                 {% include "edit/include_subtract.html" %}
                 <div class="text-filtering border-fieldset">
-                    <h3>Text filtering</h3>
+                    <h3>{{ _('Text filtering') }}</h3>
                     {% include "edit/text-options.html" %}
                 </div>
             </div>
@@ -64,24 +64,24 @@
             <div class="tab-pane-inner" id="notifications">
                 <fieldset>
                     <div  class="pure-control-group inline-radio">
-                      {{ render_checkbox_field(form.notification_muted) }}
+                      {{ render_ternary_field(form.notification_muted, BooleanField=True) }}
                     </div>
                     {% if 1 %}
                     <div class="pure-control-group inline-radio">
                       {{ render_checkbox_field(form.notification_screenshot) }}
                         <span class="pure-form-message-inline">
-                            <strong>Use with caution!</strong> This will easily fill up your email storage quota or flood other storages.
+                            <strong>{{ _('Use with caution!') }}</strong> {{ _('This will easily fill up your email storage quota or flood other storages.') }}
                         </span>
                     </div>
                     {% endif %}
                     <div class="field-group" id="notification-field-group">
                         {% if has_default_notification_urls %}
                         <div class="inline-warning">
-                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!" >
-                            There are <a href="{{ url_for('settings.settings_page')}}#notifications">system-wide notification URLs enabled</a>, this form will override notification settings for this watch only &dash; an empty Notification URL list here will still send notifications.
+                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="{{ _('Look out!') }}" title="{{ _('Lookout!') }}" >
+                            {{ _('There are') }} <a href="{{ url_for('settings.settings_page')}}#notifications">{{ _('system-wide notification URLs enabled') }}</a>, {{ _('this form will override notification settings for this watch only') }} &dash; {{ _('an empty Notification URL list here will still send notifications.') }}
                         </div>
                         {% endif %}
-                        <a href="#notifications" id="notification-setting-reset-to-default" class="pure-button button-xsmall" style="right: 20px; top: 20px; position: absolute; background-color: #5f42dd; border-radius: 4px; font-size: 70%; color: #fff">Use system defaults</a>
+                        <a href="#notifications" id="notification-setting-reset-to-default" class="pure-button button-xsmall" style="right: 20px; top: 20px; position: absolute; background-color: #5f42dd; border-radius: 4px; font-size: 70%; color: #fff">{{ _('Use system defaults') }}</a>
 
                         {{ render_common_settings_form(form, emailprefix, settings_application, extra_notification_token_placeholder_info) }}
                     </div>

changedetectionio/blueprint/tags/templates/groups-overview.html

@@ -2,22 +2,23 @@
 {% block content %}
 {% from '_helpers.html' import render_simple_field, render_field %}
 <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
+<script src="{{url_for('static_content', group='js', filename='modal.js')}}"></script>
 
 <div class="box">
     <form class="pure-form" action="{{ url_for('tags.form_tag_add') }}" method="POST" id="new-watch-form">
         <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
         <fieldset>
-            <legend>Add a new organisational tag</legend>
+            <legend>{{ _('Add a new organisational tag') }}</legend>
             <div id="watch-add-wrapper-zone">
                 <div>
-                    {{ render_simple_field(form.name, placeholder="watch label / tag") }}
+                    {{ render_simple_field(form.name, placeholder=_("Watch group / tag")) }}
                 </div>
                 <div>
-                    {{ render_simple_field(form.save_button, title="Save" ) }}
+                    {{ render_simple_field(form.save_button, title=_("Save") ) }}
                 </div>
             </div>
             <br>
-            <div style="color: #fff;">Groups allows you to manage filters and notifications for multiple watches under a single organisational tag.</div>
+            <div style="color: #fff;">{{ _('Groups allows you to manage filters and notifications for multiple watches under a single organisational tag.') }}</div>
         </fieldset>
     </form>
     <!-- @todo maybe some overview matrix, 'tick' with which has notification, filter rules etc -->
@@ -27,8 +28,8 @@
             <thead>
             <tr>
                 <th></th>
-                <th># Watches</th>
-                <th>Tag / Label name</th>
+                <th>{{ _('# Watches') }}</th>
+                <th>{{ _('Tag / Label name') }}</th>
                 <th></th>
             </tr>
             </thead>
@@ -38,7 +39,7 @@
             --->
             {% if not available_tags|length %}
             <tr>
-                <td colspan="3">No website organisational tags/groups configured</td>
+                <td colspan="3">{{ _('No website organisational tags/groups configured') }}</td>
             </tr>
             {% endif %}
             {% for uuid, tag in available_tags  %}
@@ -49,9 +50,25 @@
                 <td>{{ "{:,}".format(tag_count[uuid]) if uuid in tag_count else 0 }}</td>
                 <td class="title-col inline"> <a href="{{url_for('watchlist.index', tag=uuid) }}">{{ tag.title }}</a></td>
                 <td>
-                    <a class="pure-button pure-button-primary" href="{{ url_for('tags.form_tag_edit', uuid=uuid) }}">Edit</a>&nbsp;
-                    <a class="pure-button pure-button-primary" href="{{ url_for('tags.delete', uuid=uuid) }}" title="Deletes and removes tag">Delete</a>
-                    <a class="pure-button pure-button-primary" href="{{ url_for('tags.unlink', uuid=uuid) }}" title="Keep the tag but unlink any watches">Unlink</a>
+                    <a class="pure-button pure-button-primary" href="{{ url_for('tags.form_tag_edit', uuid=uuid) }}">{{ _('Edit') }}</a>
+                    <a href="{{ url_for('ui.form_watch_checknow', tag=uuid) }}" class="pure-button pure-button-primary" >{{ _('Recheck') }}</a>
+                    <a class="pure-button button-error"
+                       href="{{ url_for('tags.delete', uuid=uuid) }}"
+                       data-requires-confirm
+                       data-confirm-type="danger"
+                       data-confirm-title="{{ _('Delete Group?') }}"
+                       data-confirm-message="{{ _('<p>Are you sure you want to delete group <strong>%(title)s</strong>?</p><p>This action cannot be undone.</p>', title=tag.title) }}"
+                       data-confirm-button="{{ _('Delete') }}"
+                       title="{{ _('Deletes and removes tag') }}">{{ _('Delete') }}</a>
+                    <a class="pure-button button-warning"
+                       href="{{ url_for('tags.unlink', uuid=uuid) }}"
+                       data-requires-confirm
+                       data-confirm-type="warning"
+                       data-confirm-title="{{ _('Unlink Group?') }}"
+                       data-confirm-message="{{ _('<p>Are you sure you want to unlink all watches from group <strong>%(title)s</strong>?</p><p>The tag will be kept but watches will be removed from it.</p>', title=tag.title) }}"
+                       data-confirm-button="{{ _('Unlink') }}"
+                       title="{{ _('Keep the tag but unlink any watches') }}">{{ _('Unlink') }}</a>
+                    <a href="{{ url_for('rss.rss_tag_feed', tag_uuid=uuid, token=app_rss_token)}}"><img alt="{{ _('RSS Feed for this watch') }}" style="padding-left: 1em;" src="{{url_for('static_content', group='images', filename='generic_feed-icon.svg')}}" height="15"></a>
                 </td>
             </tr>
             {% endfor %}

changedetectionio/blueprint/ui/__init__.py

@@ -1,14 +1,122 @@
 import time
-from flask import Blueprint, request, redirect, url_for, flash, render_template, session
+import threading
+from flask import Blueprint, request, redirect, url_for, flash, render_template, session, current_app
+from flask_babel import gettext
 from loguru import logger
-from functools import wraps
 
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.blueprint.ui.edit import construct_blueprint as construct_edit_blueprint
 from changedetectionio.blueprint.ui.notification import construct_blueprint as construct_notification_blueprint
 from changedetectionio.blueprint.ui.views import construct_blueprint as construct_views_blueprint
+from changedetectionio.blueprint.ui import diff, preview
 
-def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_update_threads, queuedWatchMetaData):
+def _handle_operations(op, uuids, datastore, worker_pool, update_q, queuedWatchMetaData, watch_check_update, extra_data=None, emit_flash=True):
+    from flask import request, flash
+
+    if op == 'delete':
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.delete(uuid)
+        if emit_flash:
+            flash(gettext("{} watches deleted").format(len(uuids)))
+
+    elif op == 'pause':
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.data['watching'][uuid]['paused'] = True
+                datastore.data['watching'][uuid].commit()
+        if emit_flash:
+            flash(gettext("{} watches paused").format(len(uuids)))
+
+    elif op == 'unpause':
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.data['watching'][uuid.strip()]['paused'] = False
+                datastore.data['watching'][uuid].commit()
+        if emit_flash:
+            flash(gettext("{} watches unpaused").format(len(uuids)))
+
+    elif (op == 'mark-viewed'):
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.set_last_viewed(uuid, int(time.time()))
+        if emit_flash:
+            flash(gettext("{} watches updated").format(len(uuids)))
+
+    elif (op == 'mute'):
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.data['watching'][uuid]['notification_muted'] = True
+                datastore.data['watching'][uuid].commit()
+        if emit_flash:
+            flash(gettext("{} watches muted").format(len(uuids)))
+
+    elif (op == 'unmute'):
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.data['watching'][uuid]['notification_muted'] = False
+                datastore.data['watching'][uuid].commit()
+        if emit_flash:
+            flash(gettext("{} watches un-muted").format(len(uuids)))
+
+    elif (op == 'recheck'):
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                # Recheck and require a full reprocessing
+                worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+        if emit_flash:
+            flash(gettext("{} watches queued for rechecking").format(len(uuids)))
+
+    elif (op == 'clear-errors'):
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.data['watching'][uuid]["last_error"] = False
+                datastore.data['watching'][uuid].commit()
+        if emit_flash:
+            flash(gettext("{} watches errors cleared").format(len(uuids)))
+
+    elif (op == 'clear-history'):
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.clear_watch_history(uuid)
+        if emit_flash:
+            flash(gettext("{} watches cleared/reset.").format(len(uuids)))
+
+    elif (op == 'notification-default'):
+        from changedetectionio.notification import (
+            USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH
+        )
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.data['watching'][uuid]['notification_title'] = None
+                datastore.data['watching'][uuid]['notification_body'] = None
+                datastore.data['watching'][uuid]['notification_urls'] = []
+                datastore.data['watching'][uuid]['notification_format'] = USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH
+                datastore.data['watching'][uuid].commit()
+        if emit_flash:
+            flash(gettext("{} watches set to use default notification settings").format(len(uuids)))
+
+    elif (op == 'assign-tag'):
+        op_extradata = extra_data
+        if op_extradata:
+            tag_uuid = datastore.add_tag(title=op_extradata)
+            if op_extradata and tag_uuid:
+                for uuid in uuids:
+                    if datastore.data['watching'].get(uuid):
+                        # Bug in old versions caused by bad edit page/tag handler
+                        if isinstance(datastore.data['watching'][uuid]['tags'], str):
+                            datastore.data['watching'][uuid]['tags'] = []
+
+                        datastore.data['watching'][uuid]['tags'].append(tag_uuid)
+                        datastore.data['watching'][uuid].commit()
+        if emit_flash:
+            flash(gettext("{} watches were tagged").format(len(uuids)))
+
+    if uuids:
+        for uuid in uuids:
+            watch_check_update.send(watch_uuid=uuid)
+
+def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool, queuedWatchMetaData, watch_check_update):
     ui_blueprint = Blueprint('ui', __name__, template_folder="templates")
     
     # Register the edit blueprint
@@ -20,9 +128,16 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
     ui_blueprint.register_blueprint(notification_blueprint)
     
     # Register the views blueprint
-    views_blueprint = construct_views_blueprint(datastore, update_q, queuedWatchMetaData)
+    views_blueprint = construct_views_blueprint(datastore, update_q, queuedWatchMetaData, watch_check_update)
     ui_blueprint.register_blueprint(views_blueprint)
-    
+
+    # Register diff and preview blueprints
+    diff_blueprint = diff.construct_blueprint(datastore)
+    ui_blueprint.register_blueprint(diff_blueprint)
+
+    preview_blueprint = preview.construct_blueprint(datastore)
+    ui_blueprint.register_blueprint(preview_blueprint)
+
     # Import the login decorator
     from changedetectionio.auth_decorator import login_optionally_required
 
@@ -32,10 +147,9 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
         try:
             datastore.clear_watch_history(uuid)
         except KeyError:
-            flash('Watch not found', 'error')
+            flash(gettext('Watch not found'), 'error')
         else:
-            flash("Cleared snapshot history for watch {}".format(uuid))
-
+            flash(gettext("Cleared snapshot history for watch {}").format(uuid))
         return redirect(url_for('watchlist.index'))
 
     @ui_blueprint.route("/clear_history", methods=['GET', 'POST'])
@@ -45,12 +159,26 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
             confirmtext = request.form.get('confirmtext')
 
             if confirmtext == 'clear':
-                for uuid in datastore.data['watching'].keys():
-                    datastore.clear_watch_history(uuid)
+                # Run in background thread to avoid blocking
+                def clear_history_background():
+                    # Capture UUIDs first to avoid race conditions
+                    watch_uuids = list(datastore.data['watching'].keys())
+                    logger.info(f"Background: Clearing history for {len(watch_uuids)} watches")
 
-                flash("Cleared snapshot history for all watches")
+                    for uuid in watch_uuids:
+                        try:
+                            datastore.clear_watch_history(uuid)
+                        except Exception as e:
+                            logger.error(f"Error clearing history for watch {uuid}: {e}")
+
+                    logger.info("Background: Completed clearing history")
+
+                # Start daemon thread
+                threading.Thread(target=clear_history_background, daemon=True).start()
+
+                flash(gettext("History clearing started in background"))
             else:
-                flash('Incorrect confirmation text.', 'error')
+                flash(gettext('Incorrect confirmation text.'), 'error')
 
             return redirect(url_for('watchlist.index'))
 
@@ -63,27 +191,49 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
     def mark_all_viewed():
         # Save the current newest history as the most recently viewed
         with_errors = request.args.get('with_errors') == "1"
-        for watch_uuid, watch in datastore.data['watching'].items():
-            if with_errors and not watch.get('last_error'):
-                continue
-            datastore.set_last_viewed(watch_uuid, int(time.time()))
+        tag_limit = request.args.get('tag')
+        now = int(time.time())
 
-        return redirect(url_for('watchlist.index'))
+        # Mark watches as viewed in background thread to avoid blocking
+        def mark_viewed_background():
+            """Background thread to mark watches as viewed - discarded after completion."""
+            marked_count = 0
+            try:
+                for watch_uuid, watch in datastore.data['watching'].items():
+                    if with_errors and not watch.get('last_error'):
+                        continue
+
+                    if tag_limit and (not watch.get('tags') or tag_limit not in watch['tags']):
+                        continue
+
+                    datastore.set_last_viewed(watch_uuid, now)
+                    marked_count += 1
+
+                logger.info(f"Background marking complete: {marked_count} watches marked as viewed")
+            except Exception as e:
+                logger.error(f"Error in background mark as viewed: {e}")
+
+        # Start background thread and return immediately
+        thread = threading.Thread(target=mark_viewed_background, daemon=True)
+        thread.start()
+
+        flash(gettext("Marking watches as viewed in background..."))
+        return redirect(url_for('watchlist.index', tag=tag_limit))
 
     @ui_blueprint.route("/delete", methods=['GET'])
     @login_optionally_required
     def form_delete():
         uuid = request.args.get('uuid')
-
-        if uuid != 'all' and not uuid in datastore.data['watching'].keys():
-            flash('The watch by UUID {} does not exist.'.format(uuid), 'error')
-            return redirect(url_for('watchlist.index'))
-
         # More for testing, possible to return the first/only
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
+
+        if uuid != 'all' and not uuid in datastore.data['watching'].keys():
+            flash(gettext('The watch by UUID {} does not exist.').format(uuid), 'error')
+            return redirect(url_for('watchlist.index'))
+
         datastore.delete(uuid)
-        flash('Deleted.')
+        flash(gettext('Deleted.'))
 
         return redirect(url_for('watchlist.index'))
 
@@ -91,16 +241,16 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
     @login_optionally_required
     def form_clone():
         uuid = request.args.get('uuid')
-        # More for testing, possible to return the first/only
+
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
 
         new_uuid = datastore.clone(uuid)
 
         if not datastore.data['watching'].get(uuid).get('paused'):
-            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
+            worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
 
-        flash('Cloned, you are editing the new watch.')
+        flash(gettext('Cloned, you are editing the new watch.'))
 
         return redirect(url_for("ui.ui_edit.edit_page", uuid=new_uuid))
 
@@ -112,141 +262,100 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
         uuid = request.args.get('uuid')
         with_errors = request.args.get('with_errors') == "1"
 
-        i = 0
-
-        running_uuids = []
-        for t in running_update_threads:
-            running_uuids.append(t.current_uuid)
-
         if uuid:
-            if uuid not in running_uuids:
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-                i += 1
-
+            # Single watch - check if already queued or running
+            if worker_pool.is_watch_running(uuid) or uuid in update_q.get_queued_uuids():
+                flash(gettext("Watch is already queued or being checked."))
+            else:
+                worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                flash(gettext("Queued 1 watch for rechecking."))
         else:
-            # Recheck all, including muted
-            # Get most overdue first
+            # Multiple watches - first count how many need to be queued
+            watches_to_queue = []
             for k in sorted(datastore.data['watching'].items(), key=lambda item: item[1].get('last_checked', 0)):
                 watch_uuid = k[0]
                 watch = k[1]
-                if not watch['paused']:
-                    if watch_uuid not in running_uuids:
-                        if with_errors and not watch.get('last_error'):
-                            continue
+                if not watch['paused'] and watch_uuid:
+                    if with_errors and not watch.get('last_error'):
+                        continue
+                    if tag != None and tag not in watch['tags']:
+                        continue
+                    watches_to_queue.append(watch_uuid)
 
-                        if tag != None and tag not in watch['tags']:
-                            continue
+            # If less than 20 watches, queue synchronously for immediate feedback
+            if len(watches_to_queue) < 20:
+                # Get already queued/running UUIDs once (efficient)
+                queued_uuids = set(update_q.get_queued_uuids())
+                running_uuids = set(worker_pool.get_running_uuids())
 
-                        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
-                        i += 1
+                # Filter out watches that are already queued or running
+                watches_to_queue_filtered = []
+                for watch_uuid in watches_to_queue:
+                    if watch_uuid not in queued_uuids and watch_uuid not in running_uuids:
+                        watches_to_queue_filtered.append(watch_uuid)
 
-        if i == 1:
-            flash("Queued 1 watch for rechecking.")
-        if i > 1:
-            flash(f"Queued {i} watches for rechecking.")
-        if i == 0:
-            flash("No watches available to recheck.")
+                # Queue only the filtered watches
+                for watch_uuid in watches_to_queue_filtered:
+                    worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
 
-        return redirect(url_for('watchlist.index'))
+                # Provide feedback about skipped watches
+                skipped_count = len(watches_to_queue) - len(watches_to_queue_filtered)
+                if skipped_count > 0:
+                    flash(gettext("Queued {} watches for rechecking ({} already queued or running).").format(
+                        len(watches_to_queue_filtered), skipped_count))
+                else:
+                    if len(watches_to_queue_filtered) == 1:
+                        flash(gettext("Queued 1 watch for rechecking."))
+                    else:
+                        flash(gettext("Queued {} watches for rechecking.").format(len(watches_to_queue_filtered)))
+            else:
+                # 20+ watches - queue in background thread to avoid blocking HTTP response
+                # Capture queued/running state before background thread
+                queued_uuids = set(update_q.get_queued_uuids())
+                running_uuids = set(worker_pool.get_running_uuids())
+
+                def queue_watches_background():
+                    """Background thread to queue watches - discarded after completion."""
+                    try:
+                        queued_count = 0
+                        skipped_count = 0
+                        for watch_uuid in watches_to_queue:
+                            # Check if already queued or running (state captured at start)
+                            if watch_uuid not in queued_uuids and watch_uuid not in running_uuids:
+                                worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
+                                queued_count += 1
+                            else:
+                                skipped_count += 1
+
+                        logger.info(f"Background queueing complete: {queued_count} watches queued, {skipped_count} skipped (already queued/running)")
+                    except Exception as e:
+                        logger.error(f"Error in background queueing: {e}")
+
+                # Start background thread and return immediately
+                thread = threading.Thread(target=queue_watches_background, daemon=True, name="QueueWatches-Background")
+                thread.start()
+
+                # Return immediately with approximate message
+                flash(gettext("Queueing watches for rechecking in background..."))
+
+        return redirect(url_for('watchlist.index', **({'tag': tag} if tag else {})))
 
     @ui_blueprint.route("/form/checkbox-operations", methods=['POST'])
     @login_optionally_required
     def form_watch_list_checkbox_operations():
         op = request.form['op']
-        uuids = request.form.getlist('uuids')
-
-        if (op == 'delete'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.delete(uuid.strip())
-            flash("{} watches deleted".format(len(uuids)))
-
-        elif (op == 'pause'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid.strip()]['paused'] = True
-            flash("{} watches paused".format(len(uuids)))
-
-        elif (op == 'unpause'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid.strip()]['paused'] = False
-            flash("{} watches unpaused".format(len(uuids)))
-
-        elif (op == 'mark-viewed'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.set_last_viewed(uuid, int(time.time()))
-            flash("{} watches updated".format(len(uuids)))
-
-        elif (op == 'mute'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid.strip()]['notification_muted'] = True
-            flash("{} watches muted".format(len(uuids)))
-
-        elif (op == 'unmute'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid.strip()]['notification_muted'] = False
-            flash("{} watches un-muted".format(len(uuids)))
-
-        elif (op == 'recheck'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    # Recheck and require a full reprocessing
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-            flash("{} watches queued for rechecking".format(len(uuids)))
-
-        elif (op == 'clear-errors'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid]["last_error"] = False
-            flash(f"{len(uuids)} watches errors cleared")
-
-        elif (op == 'clear-history'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.clear_watch_history(uuid)
-            flash("{} watches cleared/reset.".format(len(uuids)))
-
-        elif (op == 'notification-default'):
-            from changedetectionio.notification import (
-                default_notification_format_for_watch
-            )
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid.strip()]['notification_title'] = None
-                    datastore.data['watching'][uuid.strip()]['notification_body'] = None
-                    datastore.data['watching'][uuid.strip()]['notification_urls'] = []
-                    datastore.data['watching'][uuid.strip()]['notification_format'] = default_notification_format_for_watch
-            flash("{} watches set to use default notification settings".format(len(uuids)))
-
-        elif (op == 'assign-tag'):
-            op_extradata = request.form.get('op_extradata', '').strip()
-            if op_extradata:
-                tag_uuid = datastore.add_tag(title=op_extradata)
-                if op_extradata and tag_uuid:
-                    for uuid in uuids:
-                        uuid = uuid.strip()
-                        if datastore.data['watching'].get(uuid):
-                            # Bug in old versions caused by bad edit page/tag handler
-                            if isinstance(datastore.data['watching'][uuid]['tags'], str):
-                                datastore.data['watching'][uuid]['tags'] = []
-
-                            datastore.data['watching'][uuid]['tags'].append(tag_uuid)
-
-            flash(f"{len(uuids)} watches were tagged")
+        uuids = [u.strip() for u in request.form.getlist('uuids') if u]
+        extra_data = request.form.get('op_extradata', '').strip()
+        _handle_operations(
+            datastore=datastore,
+            extra_data=extra_data,
+            queuedWatchMetaData=queuedWatchMetaData,
+            uuids=uuids,
+            worker_pool=worker_pool,
+            update_q=update_q,
+            watch_check_update=watch_check_update,
+            op=op,
+        )
 
         return redirect(url_for('watchlist.index'))
 
@@ -260,9 +369,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
         import json
         from copy import deepcopy
 
-        # more for testing
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
 
         # copy it to memory as trim off what we dont need (history)
         watch = deepcopy(datastore.data['watching'].get(uuid))
@@ -298,8 +404,29 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
 
         except Exception as e:
             logger.error(f"Error sharing -{str(e)}")
-            flash(f"Could not share, something went wrong while communicating with the share server - {str(e)}", 'error')
+            flash(gettext("Could not share, something went wrong while communicating with the share server - {}").format(str(e)), 'error')
 
         return redirect(url_for('watchlist.index'))
 
+    @ui_blueprint.route("/language/auto-detect", methods=['GET'])
+    def delete_locale_language_session_var_if_it_exists():
+        """Clear the session locale preference to auto-detect from browser Accept-Language header"""
+        if 'locale' in session:
+            session.pop('locale', None)
+            # Refresh Flask-Babel to clear cached locale
+            from flask_babel import refresh
+            refresh()
+            flash(gettext("Language set to auto-detect from browser"))
+
+        # Check if there's a redirect parameter to return to the same page
+        redirect_url = request.args.get('redirect')
+
+        # If redirect is provided and safe, use it
+        from changedetectionio.is_safe_url import is_safe_url
+        if redirect_url and is_safe_url(redirect_url, current_app):
+            return redirect(redirect_url)
+
+        # Otherwise redirect to watchlist
+        return redirect(url_for('watchlist.index'))
+
     return ui_blueprint

changedetectionio/blueprint/ui/diff.py

@@ -0,0 +1,305 @@
+from flask import Blueprint, request, redirect, url_for, flash, render_template, make_response, send_from_directory
+from flask_babel import gettext
+
+import re
+import importlib
+from loguru import logger
+from markupsafe import Markup
+
+from changedetectionio.diff import (
+    REMOVED_STYLE, ADDED_STYLE, REMOVED_INNER_STYLE, ADDED_INNER_STYLE,
+    REMOVED_PLACEMARKER_OPEN, REMOVED_PLACEMARKER_CLOSED,
+    ADDED_PLACEMARKER_OPEN, ADDED_PLACEMARKER_CLOSED,
+    CHANGED_PLACEMARKER_OPEN, CHANGED_PLACEMARKER_CLOSED,
+    CHANGED_INTO_PLACEMARKER_OPEN, CHANGED_INTO_PLACEMARKER_CLOSED
+)
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio.auth_decorator import login_optionally_required
+
+
+def construct_blueprint(datastore: ChangeDetectionStore):
+    diff_blueprint = Blueprint('ui_diff', __name__, template_folder="../ui/templates")
+
+    @diff_blueprint.app_template_filter('diff_unescape_difference_spans')
+    def diff_unescape_difference_spans(content):
+        """Emulate Jinja2's auto-escape, then selectively unescape our diff spans."""
+        from markupsafe import escape
+
+        if not content:
+            return Markup('')
+
+        # Step 1: Escape everything like Jinja2 would (this makes it XSS-safe)
+        escaped_content = escape(str(content))
+
+        # Step 2: Unescape only our exact diff spans generated by apply_html_color_to_body()
+        # Pattern matches the exact structure:
+        # <span style="{STYLE}" role="{ROLE}" aria-label="{LABEL}" title="{TITLE}">
+
+        # Unescape outer span opening tags with full attributes (role, aria-label, title)
+        # Matches removed/added/changed/changed_into spans
+        result = re.sub(
+            rf'&lt;span style=&#34;({re.escape(REMOVED_STYLE)}|{re.escape(ADDED_STYLE)})&#34; '
+            rf'role=&#34;(deletion|insertion|note)&#34; '
+            rf'aria-label=&#34;([^&]+?)&#34; '
+            rf'title=&#34;([^&]+?)&#34;&gt;',
+            r'<span style="\1" role="\2" aria-label="\3" title="\4">',
+            str(escaped_content),
+            flags=re.IGNORECASE
+        )
+
+        # Unescape inner span opening tags (without additional attributes)
+        # This matches the darker background styles for changed parts within lines
+        result = re.sub(
+            rf'&lt;span style=&#34;({re.escape(REMOVED_INNER_STYLE)}|{re.escape(ADDED_INNER_STYLE)})&#34;&gt;',
+            r'<span style="\1">',
+            result,
+            flags=re.IGNORECASE
+        )
+
+        # Unescape closing tags (but only as many as we opened)
+        open_count = result.count('<span style=')
+        close_count = str(escaped_content).count('&lt;/span&gt;')
+
+        # Replace up to the number of spans we opened
+        for _ in range(min(open_count, close_count)):
+            result = result.replace('&lt;/span&gt;', '</span>', 1)
+
+        return Markup(result)
+
+    @diff_blueprint.route("/diff/<string:uuid>", methods=['GET'])
+    @login_optionally_required
+    def diff_history_page(uuid):
+        """
+        Render the history/diff page for a watch.
+
+        This route is processor-aware: it delegates rendering to the processor's
+        difference.py module, allowing different processor types to provide
+        custom visualizations:
+        - text_json_diff: Text/HTML diff with syntax highlighting
+        - restock_diff: Could show price charts and stock history
+        - image_diff: Could show image comparison slider/overlay
+
+        Each processor implements processors/{type}/difference.py::render()
+        If a processor doesn't have a difference module, falls back to text_json_diff.
+        """
+
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+
+        try:
+            watch = datastore.data['watching'][uuid]
+        except KeyError:
+            flash(gettext("No history found for the specified link, bad link?"), "error")
+            return redirect(url_for('watchlist.index'))
+
+        dates = list(watch.history.keys())
+        if not dates or len(dates) < 2:
+            flash(gettext("Not enough history (2 snapshots required) to show difference page for this watch."), "error")
+            return redirect(url_for('watchlist.index'))
+
+        # Get the processor type for this watch
+        processor_name = watch.get('processor', 'text_json_diff')
+
+        # Try to get the processor's difference module (works for both built-in and plugin processors)
+        from changedetectionio.processors import get_processor_submodule
+        processor_module = get_processor_submodule(processor_name, 'difference')
+
+        # Call the processor's render() function
+        if processor_module and hasattr(processor_module, 'render'):
+            return processor_module.render(
+                watch=watch,
+                datastore=datastore,
+                request=request,
+                url_for=url_for,
+                render_template=render_template,
+                flash=flash,
+                redirect=redirect
+            )
+
+        # Fallback: if processor doesn't have difference module, use text_json_diff as default
+        from changedetectionio.processors.text_json_diff.difference import render as default_render
+        return default_render(
+            watch=watch,
+            datastore=datastore,
+            request=request,
+            url_for=url_for,
+            render_template=render_template,
+            flash=flash,
+            redirect=redirect
+        )
+
+    @diff_blueprint.route("/diff/<string:uuid>/extract", methods=['GET'])
+    @login_optionally_required
+    def diff_history_page_extract_GET(uuid):
+        """
+        Render the data extraction form for a watch.
+
+        This route is processor-aware: it delegates to the processor's
+        extract.py module, allowing different processor types to provide
+        custom extraction interfaces.
+
+        Each processor implements processors/{type}/extract.py::render_form()
+        If a processor doesn't have an extract module, falls back to text_json_diff.
+        """
+
+
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+        try:
+            watch = datastore.data['watching'][uuid]
+        except KeyError:
+            flash(gettext("No history found for the specified link, bad link?"), "error")
+            return redirect(url_for('watchlist.index'))
+
+        # Get the processor type for this watch
+        processor_name = watch.get('processor', 'text_json_diff')
+
+        # Try to get the processor's extract module (works for both built-in and plugin processors)
+        from changedetectionio.processors import get_processor_submodule
+        processor_module = get_processor_submodule(processor_name, 'extract')
+
+        # Call the processor's render_form() function
+        if processor_module and hasattr(processor_module, 'render_form'):
+            return processor_module.render_form(
+                watch=watch,
+                datastore=datastore,
+                request=request,
+                url_for=url_for,
+                render_template=render_template,
+                flash=flash,
+                redirect=redirect
+            )
+
+        # Fallback: if processor doesn't have extract module, use base processors.extract as default
+        from changedetectionio.processors.extract import render_form as default_render_form
+        return default_render_form(
+            watch=watch,
+            datastore=datastore,
+            request=request,
+            url_for=url_for,
+            render_template=render_template,
+            flash=flash,
+            redirect=redirect
+        )
+
+    @diff_blueprint.route("/diff/<string:uuid>/extract", methods=['POST'])
+    @login_optionally_required
+    def diff_history_page_extract_POST(uuid):
+        """
+        Process the data extraction request.
+
+        This route is processor-aware: it delegates to the processor's
+        extract.py module, allowing different processor types to provide
+        custom extraction logic.
+
+        Each processor implements processors/{type}/extract.py::process_extraction()
+        If a processor doesn't have an extract module, falls back to text_json_diff.
+        """
+
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+
+        try:
+            watch = datastore.data['watching'][uuid]
+        except KeyError:
+            flash(gettext("No history found for the specified link, bad link?"), "error")
+            return redirect(url_for('watchlist.index'))
+
+        # Get the processor type for this watch
+        processor_name = watch.get('processor', 'text_json_diff')
+
+        # Try to get the processor's extract module (works for both built-in and plugin processors)
+        from changedetectionio.processors import get_processor_submodule
+        processor_module = get_processor_submodule(processor_name, 'extract')
+
+        # Call the processor's process_extraction() function
+        if processor_module and hasattr(processor_module, 'process_extraction'):
+            return processor_module.process_extraction(
+                watch=watch,
+                datastore=datastore,
+                request=request,
+                url_for=url_for,
+                make_response=make_response,
+                send_from_directory=send_from_directory,
+                flash=flash,
+                redirect=redirect
+            )
+
+        # Fallback: if processor doesn't have extract module, use base processors.extract as default
+        from changedetectionio.processors.extract import process_extraction as default_process_extraction
+        return default_process_extraction(
+            watch=watch,
+            datastore=datastore,
+            request=request,
+            url_for=url_for,
+            make_response=make_response,
+            send_from_directory=send_from_directory,
+            flash=flash,
+            redirect=redirect
+        )
+
+    @diff_blueprint.route("/diff/<string:uuid>/processor-asset/<string:asset_name>", methods=['GET'])
+    @login_optionally_required
+    def processor_asset(uuid, asset_name):
+        """
+        Serve processor-specific binary assets (images, files, etc.).
+
+        This route is processor-aware: it delegates to the processor's
+        difference.py module, allowing different processor types to serve
+        custom assets without embedding them as base64 in templates.
+
+        This solves memory issues with large binary data (e.g., screenshots)
+        by streaming them as separate HTTP responses instead of embedding
+        in the HTML template.
+
+        Each processor implements processors/{type}/difference.py::get_asset()
+        which returns (binary_data, content_type, cache_control_header).
+
+        Example URLs:
+        - /diff/{uuid}/processor-asset/before
+        - /diff/{uuid}/processor-asset/after
+        - /diff/{uuid}/processor-asset/rendered_diff
+        """
+
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+
+        try:
+            watch = datastore.data['watching'][uuid]
+        except KeyError:
+            flash(gettext("No history found for the specified link, bad link?"), "error")
+            return redirect(url_for('watchlist.index'))
+
+        # Get the processor type for this watch
+        processor_name = watch.get('processor', 'text_json_diff')
+
+        # Try to get the processor's difference module (works for both built-in and plugin processors)
+        from changedetectionio.processors import get_processor_submodule
+        processor_module = get_processor_submodule(processor_name, 'difference')
+
+        # Call the processor's get_asset() function
+        if processor_module and hasattr(processor_module, 'get_asset'):
+            result = processor_module.get_asset(
+                asset_name=asset_name,
+                watch=watch,
+                datastore=datastore,
+                request=request
+            )
+
+            if result is None:
+                from flask import abort
+                abort(404, description=f"Asset '{asset_name}' not found")
+
+            binary_data, content_type, cache_control = result
+
+            response = make_response(binary_data)
+            response.headers['Content-Type'] = content_type
+            if cache_control:
+                response.headers['Cache-Control'] = cache_control
+            return response
+        else:
+            logger.warning(f"Processor {processor_name} does not implement get_asset()")
+            from flask import abort
+            abort(404, description=f"Processor '{processor_name}' does not support assets")
+
+    return diff_blueprint

changedetectionio/blueprint/ui/edit.py

@@ -1,14 +1,15 @@
-import time
 from copy import deepcopy
 import os
 import importlib.resources
-from flask import Blueprint, request, redirect, url_for, flash, render_template, make_response, send_from_directory, abort
+from flask import Blueprint, request, redirect, url_for, flash, render_template, abort
+from flask_babel import gettext
 from loguru import logger
 from jinja2 import Environment, FileSystemLoader
 
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
 from changedetectionio.time_handler import is_within_schedule
+from changedetectionio import worker_pool
 
 def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
     edit_blueprint = Blueprint('ui_edit', __name__, template_folder="../ui/templates")
@@ -25,20 +26,19 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
     # https://wtforms.readthedocs.io/en/3.0.x/forms/#wtforms.form.Form.populate_obj ?
     def edit_page(uuid):
         from changedetectionio import forms
-        from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
+        from changedetectionio.browser_steps.browser_steps import browser_step_ui_config
         from changedetectionio import processors
         import importlib
 
-        # More for testing, possible to return the first/only
-        if not datastore.data['watching'].keys():
-            flash("No watches to edit", "error")
-            return redirect(url_for('watchlist.index'))
-
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
+        # More for testing, possible to return the first/only
+        if not datastore.data['watching'].keys():
+            flash(gettext("No watches to edit"), "error")
+            return redirect(url_for('watchlist.index'))
 
         if not uuid in datastore.data['watching']:
-            flash("No watch with the UUID %s found." % (uuid), "error")
+            flash(gettext("No watch with the UUID {} found.").format(uuid), "error")
             return redirect(url_for('watchlist.index'))
 
         switch_processor = request.args.get('switch_processor')
@@ -46,12 +46,18 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             for p in processors.available_processors():
                 if p[0] == switch_processor:
                     datastore.data['watching'][uuid]['processor'] = switch_processor
-                    flash(f"Switched to mode - {p[1]}.")
+                    flash(gettext("Switched to mode - {}.").format(p[1]))
                     datastore.clear_watch_history(uuid)
                     redirect(url_for('ui_edit.edit_page', uuid=uuid))
 
         # be sure we update with a copy instead of accidently editing the live object by reference
-        default = deepcopy(datastore.data['watching'][uuid])
+        default = None
+        while not default:
+            try:
+                default = deepcopy(datastore.data['watching'][uuid])
+            except RuntimeError as e:
+                # Dictionary changed
+                continue
 
         # Defaults for proxy choice
         if datastore.proxy_list is not None:  # When enabled
@@ -65,8 +71,13 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
         processor_name = datastore.data['watching'][uuid].get('processor', '')
         processor_classes = next((tpl for tpl in processors.find_processors() if tpl[1] == processor_name), None)
         if not processor_classes:
-            flash(f"Cannot load the edit form for processor/plugin '{processor_classes[1]}', plugin missing?", 'error')
-            return redirect(url_for('watchlist.index'))
+            flash(gettext("Could not load '{}' processor, processor plugin might be missing. Please select a different processor.").format(processor_name), 'error')
+            # Fall back to default processor so user can still edit and change processor
+            processor_classes = next((tpl for tpl in processors.find_processors() if tpl[1] == 'text_json_diff'), None)
+            if not processor_classes:
+                # If even text_json_diff is missing, something is very wrong
+                flash(gettext("Could not load '{}' processor, processor plugin might be missing.").format(processor_name), 'error')
+                return redirect(url_for('watchlist.index'))
 
         parent_module = processors.get_parent_module(processor_classes[0])
 
@@ -95,6 +106,26 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
         form.datastore = datastore
         form.watch = default
 
+        # Load processor-specific config from JSON file for GET requests
+        if request.method == 'GET' and processor_name:
+            try:
+                from changedetectionio.processors.base import difference_detection_processor
+                # Create a processor instance to access config methods
+                processor_instance = difference_detection_processor(datastore, uuid)
+                # Use processor name as filename so each processor keeps its own config
+                config_filename = f'{processor_name}.json'
+                processor_config = processor_instance.get_extra_watch_config(config_filename)
+
+                if processor_config:
+                    # Populate processor-config-* fields from JSON
+                    for config_key, config_value in processor_config.items():
+                        field_name = f'processor_config_{config_key}'
+                        if hasattr(form, field_name):
+                            getattr(form, field_name).data = config_value
+                            logger.debug(f"Loaded processor config from {config_filename}: {field_name} = {config_value}")
+            except Exception as e:
+                logger.warning(f"Failed to load processor config: {e}")
+
         for p in datastore.extra_browsers:
             form.fetch_backend.choices.append(p)
 
@@ -113,11 +144,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
         if request.method == 'POST' and form.validate():
 
-            # If they changed processor, it makes sense to reset it.
-            if datastore.data['watching'][uuid].get('processor') != form.data.get('processor'):
-                datastore.data['watching'][uuid].clear_watch()
-                flash("Reset watch history due to change of processor")
-
             extra_update_obj = {
                 'consecutive_filter_failures': 0,
                 'last_error' : False
@@ -128,7 +154,12 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
             extra_update_obj['time_between_check'] = form.time_between_check.data
 
-             # Ignore text
+            # Handle processor-config-* fields separately (save to JSON, not datastore)
+            # IMPORTANT: These must NOT be saved to url-watches.json, only to the processor-specific JSON file
+            processor_config_data = processors.extract_processor_config_from_form_data(form.data)
+            processors.save_processor_config(datastore, uuid, processor_config_data)
+
+            # Ignore text
             form_ignore_text = form.ignore_text.data
             datastore.data['watching'][uuid]['ignore_text'] = form_ignore_text
 
@@ -166,12 +197,19 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
             # Recast it if need be to right data Watch handler
             watch_class = processors.get_custom_watch_obj_for_processor(form.data.get('processor'))
-            datastore.data['watching'][uuid] = watch_class(datastore_path=datastore.datastore_path, default=datastore.data['watching'][uuid])
-            flash("Updated watch - unpaused!" if request.args.get('unpause_on_save') else "Updated watch.")
+            datastore.data['watching'][uuid] = watch_class(datastore_path=datastore.datastore_path, __datastore=datastore.data, default=datastore.data['watching'][uuid])
 
-            # Re #286 - We wait for syncing new data to disk in another thread every 60 seconds
-            # But in the case something is added we should save straight away
-            datastore.needs_write_urgent = True
+            # Save the watch immediately
+            datastore.data['watching'][uuid].commit()
+
+            flash(gettext("Updated watch - unpaused!") if request.args.get('unpause_on_save') else gettext("Updated watch."))
+
+            # Cleanup any browsersteps session for this watch
+            try:
+                from changedetectionio.blueprint.browser_steps import cleanup_session_for_watch
+                cleanup_session_for_watch(uuid)
+            except Exception as e:
+                logger.debug(f"Error cleaning up browsersteps session: {e}")
 
             # Do not queue on edit if its not within the time range
 
@@ -186,7 +224,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
             tz_name = time_schedule_limit.get('timezone')
             if not tz_name:
-                tz_name = datastore.data['settings']['application'].get('timezone', 'UTC')
+                tz_name = datastore.data['settings']['application'].get('scheduler_timezone_default', os.getenv('TZ', 'UTC').strip())
 
             if time_schedule_limit and time_schedule_limit.get('enabled'):
                 try:
@@ -201,17 +239,17 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             #############################
             if not datastore.data['watching'][uuid].get('paused') and is_in_schedule:
                 # Queue the watch for immediate recheck, with a higher priority
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
             # Diff page [edit] link should go back to diff page
             if request.args.get("next") and request.args.get("next") == 'diff':
-                return redirect(url_for('ui.ui_views.diff_history_page', uuid=uuid))
+                return redirect(url_for('ui.ui_diff.diff_history_page', uuid=uuid))
 
             return redirect(url_for('watchlist.index', tag=request.args.get("tag",'')))
 
         else:
             if request.method == 'POST' and not form.validate():
-                flash("An error occurred, please see below.", "error")
+                flash(gettext("An error occurred, please see below."), "error")
 
             # JQ is difficult to install on windows and must be manually added (outside requirements.txt)
             jq_support = True
@@ -222,25 +260,32 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
             watch = datastore.data['watching'].get(uuid)
 
-            # if system or watch is configured to need a chrome type browser
-            system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
-            watch_needs_selenium_or_playwright = False
-            if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
-                watch_needs_selenium_or_playwright = True
-
-
             from zoneinfo import available_timezones
 
-            # Only works reliably with Playwright
-
             # Import the global plugin system
-            from changedetectionio.pluggy_interface import collect_ui_edit_stats_extras
-            
+            from changedetectionio.pluggy_interface import collect_ui_edit_stats_extras, get_fetcher_capabilities
+
+            # Get fetcher capabilities instead of hardcoded logic
+            capabilities = get_fetcher_capabilities(watch, datastore)
+
+            # Add processor capabilities from module
+            capabilities['supports_visual_selector'] = getattr(parent_module, 'supports_visual_selector', False)
+            capabilities['supports_text_filters_and_triggers'] = getattr(parent_module, 'supports_text_filters_and_triggers', False)
+            capabilities['supports_text_filters_and_triggers_elements'] = getattr(parent_module, 'supports_text_filters_and_triggers_elements', False)
+            capabilities['supports_request_type'] = getattr(parent_module, 'supports_request_type', False)
+
+            app_rss_token = datastore.data['settings']['application'].get('rss_access_token'),
+
+            c = [f"processor-{watch.get('processor')}"]
+            if worker_pool.is_watch_running(uuid):
+                c.append('checking-now')
+
             template_args = {
                 'available_processors': processors.available_processors(),
                 'available_timezones': sorted(available_timezones()),
                 'browser_steps_config': browser_step_ui_config,
                 'emailprefix': os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
+                'extra_classes': ' '.join(c),
                 'extra_notification_token_placeholder_info': datastore.get_unique_notification_token_placeholders_available(),
                 'extra_processor_config': form.extra_tab_content(),
                 'extra_title': f" - Edit - {watch.label}",
@@ -250,16 +295,19 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                 'has_special_tag_options': _watch_has_tag_options_set(watch=watch),
                 'jq_support': jq_support,
                 'playwright_enabled': os.getenv('PLAYWRIGHT_DRIVER_URL', False),
+                'app_rss_token': app_rss_token,
+                'rss_uuid_feed' : {
+                    'label': watch.label,
+                    'url': url_for('rss.rss_single_watch', uuid=watch['uuid'], token=app_rss_token)
+                },
                 'settings_application': datastore.data['settings']['application'],
-                'system_has_playwright_configured': os.getenv('PLAYWRIGHT_DRIVER_URL'),
-                'system_has_webdriver_configured': os.getenv('WEBDRIVER_URL'),
                 'ui_edit_stats_extras': collect_ui_edit_stats_extras(watch),
                 'visual_selector_data_ready': datastore.visualselector_data_is_ready(watch_uuid=uuid),
-                'timezone_default_config': datastore.data['settings']['application'].get('timezone'),
+                'timezone_default_config': datastore.data['settings']['application'].get('scheduler_timezone_default'),
                 'using_global_webdriver_wait': not default['webdriver_delay'],
                 'uuid': uuid,
                 'watch': watch,
-                'watch_needs_selenium_or_playwright': watch_needs_selenium_or_playwright,
+                'capabilities': capabilities
             }
 
             included_content = None
@@ -286,10 +334,12 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
         from flask import send_file
         import brotli
 
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
         watch = datastore.data['watching'].get(uuid)
-        if watch and watch.history.keys() and os.path.isdir(watch.watch_data_dir):
+        if watch and watch.history.keys() and os.path.isdir(watch.data_dir):
             latest_filename = list(watch.history.keys())[-1]
-            html_fname = os.path.join(watch.watch_data_dir, f"{latest_filename}.html.br")
+            html_fname = os.path.join(watch.data_dir, f"{latest_filename}.html.br")
             with open(html_fname, 'rb') as f:
                 if html_fname.endswith('.br'):
                     # Read and decompress the Brotli file
@@ -304,12 +354,65 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
         # Return a 500 error
         abort(500)
 
+    @edit_blueprint.route("/edit/<string:uuid>/get-data-package", methods=['GET'])
+    @login_optionally_required
+    def watch_get_data_package(uuid):
+        """Download all data for a single watch as a zip file"""
+        from io import BytesIO
+        from flask import send_file
+        import zipfile
+        from pathlib import Path
+        import datetime
+
+        watch = datastore.data['watching'].get(uuid)
+        if not watch:
+            abort(404)
+
+        # Create zip in memory
+        memory_file = BytesIO()
+
+        with zipfile.ZipFile(memory_file, 'w',
+                           compression=zipfile.ZIP_DEFLATED,
+                           compresslevel=8) as zipObj:
+
+            # Add the watch's JSON file if it exists
+            watch_json_path = os.path.join(watch.data_dir, 'watch.json')
+            if os.path.isfile(watch_json_path):
+                zipObj.write(watch_json_path,
+                           arcname=os.path.join(uuid, 'watch.json'),
+                           compress_type=zipfile.ZIP_DEFLATED,
+                           compresslevel=8)
+
+            # Add all files in the watch data directory
+            if os.path.isdir(watch.data_dir):
+                for f in Path(watch.data_dir).glob('*'):
+                    if f.is_file() and f.name != 'watch.json':  # Skip watch.json since we already added it
+                        zipObj.write(f,
+                                   arcname=os.path.join(uuid, f.name),
+                                   compress_type=zipfile.ZIP_DEFLATED,
+                                   compresslevel=8)
+
+        # Seek to beginning of file
+        memory_file.seek(0)
+
+        # Generate filename with timestamp
+        timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
+        filename = f"watch-data-{uuid[:8]}-{timestamp}.zip"
+
+        return send_file(memory_file,
+                        as_attachment=True,
+                        download_name=filename,
+                        mimetype='application/zip')
+
     # Ajax callback
     @edit_blueprint.route("/edit/<string:uuid>/preview-rendered", methods=['POST'])
     @login_optionally_required
     def watch_get_preview_rendered(uuid):
         '''For when viewing the "preview" of the rendered text from inside of Edit'''
         from flask import jsonify
+
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
         from changedetectionio.processors.text_json_diff import prepare_filter_prevew
         result = prepare_filter_prevew(watch_uuid=uuid, form_data=request.form, datastore=datastore)
         return jsonify(result)
@@ -333,6 +436,9 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                     s = re.sub(r'[0-9]+', r'\\d+', s)
                     datastore.data["watching"][uuid]['ignore_text'].append('/' + s + '/')
 
-        return f"<a href={url_for('ui.ui_views.preview_page', uuid=uuid)}>Click to preview</a>"
+            # Save the updated ignore_text
+            datastore.data["watching"][uuid].commit()
+
+        return f"<a href={url_for('ui.ui_preview.preview_page', uuid=uuid)}>Click to preview</a>"
     
     return edit_blueprint

changedetectionio/blueprint/ui/notification.py

@@ -14,11 +14,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @notification_blueprint.route("/notification/send-test/", methods=['POST'])
     @login_optionally_required
     def ajax_callback_send_notification_test(watch_uuid=None):
-
+        from changedetectionio.notification_service import NotificationContextData, set_basic_notification_vars
         # Watch_uuid could be unset in the case it`s used in tag editor, global settings
         import apprise
         from changedetectionio.notification.handler import process_notification
         from changedetectionio.notification.apprise_plugin.assets import apprise_asset
+        from changedetectionio.jinja2_custom import render as jinja_render
 
         from changedetectionio.notification.apprise_plugin.custom_handlers import apprise_http_custom_handler
 
@@ -37,11 +38,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             return make_response("Error: You must have atleast one watch configured for 'test notification' to work", 400)
 
         watch = datastore.data['watching'].get(watch_uuid)
-
-        notification_urls = None
-
-        if request.form.get('notification_urls'):
-            notification_urls = request.form['notification_urls'].strip().splitlines()
+        notification_urls = request.form.get('notification_urls','').strip().splitlines()
 
         if not notification_urls:
             logger.debug("Test notification - Trying by group/tag in the edit form if available")
@@ -61,20 +58,26 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             return 'Error: No Notification URLs set/found'
 
         for n_url in notification_urls:
+            # We are ONLY validating the apprise:// part here, convert all tags to something so as not to break apprise URLs
+            generic_notification_context_data = NotificationContextData()
+            generic_notification_context_data.set_random_for_validation()
+            n_url = jinja_render(template_str=n_url, **generic_notification_context_data).strip()
             if len(n_url.strip()):
                 if not apobj.add(n_url):
                     return f'Error:  {n_url} is not a valid AppRise URL.'
 
         try:
             # use the same as when it is triggered, but then override it with the form test values
-            n_object = {
+            n_object = NotificationContextData({
                 'watch_url': request.form.get('window_url', "https://changedetection.io"),
                 'notification_urls': notification_urls
-            }
+            })
 
             # Only use if present, if not set in n_object it should use the default system value
             if 'notification_format' in request.form and request.form['notification_format'].strip():
                 n_object['notification_format'] = request.form.get('notification_format', '').strip()
+            else:
+                n_object['notification_format'] = datastore.data['settings']['application'].get('notification_format')
 
             if 'notification_title' in request.form and request.form['notification_title'].strip():
                 n_object['notification_title'] = request.form.get('notification_title', '').strip()
@@ -91,10 +94,31 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 n_object['notification_body'] = "Test body"
 
             n_object['as_async'] = False
-            n_object.update(watch.extra_notification_token_values())
+
+            #  Same like in notification service, should be refactored
+            dates = list(watch.history.keys())
+            trigger_text = ''
+            snapshot_contents = ''
+
+            # Could be called as a 'test notification' with only 1 snapshot available
+            prev_snapshot = "Example text: example test\nExample text: change detection is cool\nExample text: some more examples\n"
+            current_snapshot = "Example text: example test\nExample text: change detection is fantastic\nExample text: even more examples\nExample text: a lot more examples"
+
+            if len(dates) > 1:
+                prev_snapshot = watch.get_history_snapshot(timestamp=dates[-2])
+                current_snapshot = watch.get_history_snapshot(timestamp=dates[-1])
+
+            n_object.update(set_basic_notification_vars(current_snapshot=current_snapshot,
+                                                        prev_snapshot=prev_snapshot,
+                                                        watch=watch,
+                                                        triggered_text=trigger_text,
+                                                        timestamp_changed=dates[-1] if dates else None))
+
+
             sent_obj = process_notification(n_object, datastore)
 
         except Exception as e:
+            logger.error(e)
             e_str = str(e)
             # Remove this text which is not important and floods the container
             e_str = e_str.replace(

changedetectionio/blueprint/ui/preview.py

@@ -0,0 +1,189 @@
+from flask import Blueprint, request, url_for, flash, render_template, redirect
+from flask_babel import gettext
+import time
+from loguru import logger
+
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio.auth_decorator import login_optionally_required
+from changedetectionio import html_tools
+
+def construct_blueprint(datastore: ChangeDetectionStore):
+    preview_blueprint = Blueprint('ui_preview', __name__, template_folder="../ui/templates")
+
+    @preview_blueprint.route("/preview/<string:uuid>", methods=['GET'])
+    @login_optionally_required
+    def preview_page(uuid):
+        """
+        Render the preview page for a watch.
+
+        This route is processor-aware: it delegates rendering to the processor's
+        preview.py module, allowing different processor types to provide
+        custom visualizations:
+        - text_json_diff: Text preview with syntax highlighting
+        - image_ssim_diff: Image preview with proper rendering
+        - restock_diff: Could show latest price/stock data
+
+        Each processor implements processors/{type}/preview.py::render()
+        If a processor doesn't have a preview module, falls back to default text preview.
+        """
+
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+        try:
+            watch = datastore.data['watching'][uuid]
+        except KeyError:
+            flash(gettext("No history found for the specified link, bad link?"), "error")
+            return redirect(url_for('watchlist.index'))
+
+        # Get the processor type for this watch
+        processor_name = watch.get('processor', 'text_json_diff')
+
+        # Try to get the processor's preview module (works for both built-in and plugin processors)
+        from changedetectionio.processors import get_processor_submodule
+        processor_module = get_processor_submodule(processor_name, 'preview')
+
+        # Call the processor's render() function
+        if processor_module and hasattr(processor_module, 'render'):
+            return processor_module.render(
+                watch=watch,
+                datastore=datastore,
+                request=request,
+                url_for=url_for,
+                render_template=render_template,
+                flash=flash,
+                redirect=redirect
+            )
+
+        # Fallback: if processor doesn't have preview module, use default text preview
+        content = []
+        versions = []
+        timestamp = None
+
+        system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
+        extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
+
+        is_html_webdriver = False
+        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
+            is_html_webdriver = True
+
+        triggered_line_numbers = []
+        ignored_line_numbers = []
+        blocked_line_numbers = []
+
+        if datastore.data['watching'][uuid].history_n == 0 and (watch.get_error_text() or watch.get_error_snapshot()):
+            flash(gettext("Preview unavailable - No fetch/check completed or triggers not reached"), "error")
+        else:
+            # So prepare the latest preview or not
+            preferred_version = request.args.get('version')
+            versions = list(watch.history.keys())
+            timestamp = versions[-1]
+            if preferred_version and preferred_version in versions:
+                timestamp = preferred_version
+
+            try:
+                versions = list(watch.history.keys())
+                content = watch.get_history_snapshot(timestamp=timestamp)
+
+                triggered_line_numbers = html_tools.strip_ignore_text(content=content,
+                                                                      wordlist=watch.get('trigger_text'),
+                                                                      mode='line numbers'
+                                                                      )
+                ignored_line_numbers = html_tools.strip_ignore_text(content=content,
+                                                                      wordlist=watch.get('ignore_text'),
+                                                                      mode='line numbers'
+                                                                      )
+                blocked_line_numbers = html_tools.strip_ignore_text(content=content,
+                                                                      wordlist=watch.get("text_should_not_be_present"),
+                                                                      mode='line numbers'
+                                                                      )
+            except Exception as e:
+                content.append({'line': f"File doesnt exist or unable to read timestamp {timestamp}", 'classes': ''})
+
+        from changedetectionio.pluggy_interface import get_fetcher_capabilities
+        capabilities = get_fetcher_capabilities(watch, datastore)
+
+        output = render_template("preview.html",
+                                 capabilities=capabilities,
+                                 content=content,
+                                 current_diff_url=watch['url'],
+                                 current_version=timestamp,
+                                 extra_stylesheets=extra_stylesheets,
+                                 extra_title=f" - Diff - {watch.label} @ {timestamp}",
+                                 highlight_ignored_line_numbers=ignored_line_numbers,
+                                 highlight_triggered_line_numbers=triggered_line_numbers,
+                                 highlight_blocked_line_numbers=blocked_line_numbers,
+                                 history_n=watch.history_n,
+                                 is_html_webdriver=is_html_webdriver,
+                                 last_error=watch['last_error'],
+                                 last_error_screenshot=watch.get_error_snapshot(),
+                                 last_error_text=watch.get_error_text(),
+                                 screenshot=watch.get_screenshot(),
+                                 uuid=uuid,
+                                 versions=versions,
+                                 watch=watch,
+                                 )
+
+        return output
+
+    @preview_blueprint.route("/preview/<string:uuid>/processor-asset/<string:asset_name>", methods=['GET'])
+    @login_optionally_required
+    def processor_asset(uuid, asset_name):
+        """
+        Serve processor-specific binary assets for preview (images, files, etc.).
+
+        This route is processor-aware: it delegates to the processor's
+        preview.py module, allowing different processor types to serve
+        custom assets without embedding them as base64 in templates.
+
+        This solves memory issues with large binary data by streaming them
+        as separate HTTP responses instead of embedding in the HTML template.
+
+        Each processor implements processors/{type}/preview.py::get_asset()
+        which returns (binary_data, content_type, cache_control_header).
+
+        Example URLs:
+        - /preview/{uuid}/processor-asset/screenshot?version=123456789
+        """
+        from flask import make_response
+
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+        try:
+            watch = datastore.data['watching'][uuid]
+        except KeyError:
+            flash(gettext("No history found for the specified link, bad link?"), "error")
+            return redirect(url_for('watchlist.index'))
+
+        # Get the processor type for this watch
+        processor_name = watch.get('processor', 'text_json_diff')
+
+        # Try to get the processor's preview module (works for both built-in and plugin processors)
+        from changedetectionio.processors import get_processor_submodule
+        processor_module = get_processor_submodule(processor_name, 'preview')
+
+        # Call the processor's get_asset() function
+        if processor_module and hasattr(processor_module, 'get_asset'):
+            result = processor_module.get_asset(
+                asset_name=asset_name,
+                watch=watch,
+                datastore=datastore,
+                request=request
+            )
+
+            if result is None:
+                from flask import abort
+                abort(404, description=f"Asset '{asset_name}' not found")
+
+            binary_data, content_type, cache_control = result
+
+            response = make_response(binary_data)
+            response.headers['Content-Type'] = content_type
+            if cache_control:
+                response.headers['Cache-Control'] = cache_control
+            return response
+        else:
+            logger.warning(f"Processor {processor_name} does not implement get_asset()")
+            from flask import abort
+            abort(404, description=f"Processor '{processor_name}' does not support assets")
+
+    return preview_blueprint

changedetectionio/blueprint/ui/templates/clear_all_history.html

@@ -9,13 +9,12 @@
       <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
       <fieldset>
         <div class="pure-control-group">
-          This will remove version history (snapshots) for ALL watches, but keep
-          your list of URLs! <br />
-          You may like to use the <strong>BACKUP</strong> link first.<br />
+          {{ _('This will remove version history (snapshots) for ALL watches, but keep your list of URLs!') }} <br />
+          {{ _('You may like to use the') }} <strong>{{ _('BACKUP') }}</strong> {{ _('link first.') }}<br />
         </div>
         <br />
         <div class="pure-control-group">
-          <label for="confirmtext">Confirmation text</label>
+          <label for="confirmtext">{{ _('Confirmation text') }}</label>
           <input
             type="text"
             id="confirmtext"
@@ -25,20 +24,19 @@
             size="10"
           />
           <span class="pure-form-message-inline"
-            >Type in the word <strong>clear</strong> to confirm that you
-            understand.</span
+            >{{ _('Type in the word') }} <strong>{{ _('clear') }}</strong> {{ _('to confirm that you understand.') }}</span
           >
         </div>
         <br />
         <div class="pure-control-group">
           <button type="submit" class="pure-button pure-button-primary">
-            Clear History!
+            {{ _('Clear History!') }}
           </button>
         </div>
         <br />
         <div class="pure-control-group">
           <a href="{{url_for('watchlist.index')}}" class="pure-button button-cancel"
-            >Cancel</a
+            >{{ _('Cancel') }}</a
           >
         </div>
       </fieldset>

changedetectionio/blueprint/ui/templates/diff-offscreen-options.html

@@ -0,0 +1,12 @@
+<ul id="highlightSnippetActions">
+    <li>
+        <button class="pure-button pure-button-primary" onclick="diffToJpeg()" title="{{ _('Share diff as image') }}">{{ _('Share as Image') }}</button>
+    </li>
+    <li>
+        <a class="pure-button pure-button-primary" data-mode="exact" href="javascript:void(0);">{{ _('Ignore any lines matching') }}</a>
+    </li>
+    <li>
+        <a class="pure-button pure-button-primary" data-mode="digit-regex" href="javascript:void(0);" >{{ _('Ignore any lines matching excluding digits') }}</a>
+    </li>
+</ul>
+

changedetectionio/blueprint/ui/templates/diff.html

@@ -0,0 +1,166 @@
+{% extends 'base.html' %}
+{% from '_helpers.html' import render_field, render_checkbox_field, render_button %}
+{% block content %}
+<script>
+    const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
+    {% if last_error_screenshot %}
+    const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
+    {% endif %}
+
+    const highlight_submit_ignore_url="{{url_for('ui.ui_edit.highlight_submit_ignore_url', uuid=uuid)}}";
+    const watch_url= {{watch_a.link|tojson}};
+
+    // Initial scroll position: if set, scroll to this line number in #difference on page load
+    const initialScrollToLineNumber = {{ initial_scroll_line_number|default('null') }};
+</script>
+<script src="https://cdn.jsdelivr.net/npm/html2canvas@1.4.1/dist/html2canvas.min.js"></script>
+<script src="{{url_for('static_content', group='js', filename='plugins.js')}}"></script>
+<script src="https://cdn.jsdelivr.net/npm/piexifjs@1.0.6/piexif.min.js"></script>
+<script src="{{url_for('static_content', group='js', filename='snippet-to-image.js')}}"></script>
+<script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
+
+
+<div id="settings">
+    <form class="pure-form " action="{{ url_for("ui.ui_diff.diff_history_page", uuid=uuid) }}" method="GET" id="diff-form">
+        <fieldset class="diff-fieldset">
+            {% if versions|length >= 1 %}
+                <span style="white-space: nowrap;">
+                <label id="change-from" for="diff-from-version" class="from-to-label">{{ _('From') }}</label>
+                <select id="diff-from-version" name="from_version" class="needs-localtime">
+                    {%- for version in versions|reverse -%}
+                        <option value="{{ version }}" {% if version== from_version %} selected="" {% endif %}>
+                            {{ version }}{#{% if loop.index == 2 %} (Previous){% endif %}#}
+                        </option>
+                    {%- endfor -%}
+                </select>
+                </span>
+                <span style="white-space: nowrap;">
+                <label id="change-to" for="diff-to-version" class="from-to-label">{{ _('To') }}</label>
+                <select id="diff-to-version" name="to_version" class="needs-localtime">
+                    {%- for version in versions|reverse -%}
+                        <option value="{{ version }}" {% if version== to_version %} selected="" {% endif %}>
+                            {{ version }}{#{% if loop.first %} (Current){% endif %}#}
+                        </option>
+                    {%- endfor -%}
+                </select>
+                </span>
+                {#<button type="submit" class="pure-button pure-button-primary reset-margin">Go</button>#}
+            {% endif %}
+        </fieldset>
+        <fieldset id="diff-style">
+            <span>
+                <label for="diffWords" class="pure-checkbox">
+                <input type="radio" name="type" id="diffWords" value="diffWords" {% if diff_prefs.type == 'diffWords' %}checked=""{% endif %}> {{ _('Words') }}</label>
+            </span>
+            <span>
+                <label for="diffLines" class="pure-checkbox">
+                <input type="radio" name="type" id="diffLines" value="diffLines" {% if diff_prefs.type == 'diffLines' %}checked=""{% endif %}> {{ _('Lines') }}</label>
+            </span>
+            <span>
+                <label for="ignoreWhitespace" class="pure-checkbox" id="label-diff-ignorewhitespace">
+                <input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace" {% if diff_prefs.ignoreWhitespace %}checked=""{% endif %}> {{ _('Ignore Whitespace') }}</label>
+            </span>
+            <span>
+                <label for="changesOnly" class="pure-checkbox" id="label-diff-changes">
+                <input type="checkbox" id="changesOnly" name="changesOnly" {% if diff_prefs.changesOnly %}checked=""{% endif %}> {{ _('Same/non-changed') }}</label>
+            </span>
+            <span>
+                <label for="removed" class="pure-checkbox" id="label-diff-removed">
+                <input type="checkbox" id="removed" name="removed" {% if diff_prefs.removed %}checked=""{% endif %}> {{ _('Removed') }}</label>
+            </span>
+            <span>
+                <label for="added" class="pure-checkbox" id="label-diff-added">
+                <input type="checkbox" id="added" name="added" {% if diff_prefs.added %}checked=""{% endif %}> {{ _('Added') }}</label>
+            </span>
+            <span>
+                <label for="replaced" class="pure-checkbox" id="label-diff-replaced">
+                <input type="checkbox" id="replaced"  name="replaced" {% if diff_prefs.replaced %}checked=""{% endif %}> {{ _('Replaced') }}</label>
+            </span>
+        </fieldset>
+        {%- if versions|length >= 2 -%}
+            <div id="keyboard-nav">
+                <strong>{{ _('Keyboard:') }} </strong>
+                <a href="" class="pure-button pure-button-primary" id="btn-previous"> &larr; {{ _('Previous') }}</a>
+                &nbsp; <a class="pure-button pure-button-primary" id="btn-next" href=""> &rarr; {{ _('Next') }}</a>
+            </div>
+        {%- endif -%}
+    </form>
+</div>
+
+<div id="diff-jump" style="display:none;"><!-- disabled for now -->
+    <a id="jump-next-diff" title="{{ _('Jump to next difference') }}">{{ _('Jump') }}</a>
+</div>
+
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<div class="tabs">
+    <ul>
+        {% if last_error_text %}<li class="tab" id="error-text-tab"><a href="#error-text">{{ _('Error Text') }}</a></li> {% endif %}
+        {% if last_error_screenshot %}<li class="tab" id="error-screenshot-tab"><a href="#error-screenshot">{{ _('Error Screenshot') }}</a></li> {% endif %}
+        <li class="tab" id="text-tab"><a href="#text">{{ _('Text') }}</a></li>
+        <li class="tab" id="screenshot-tab"><a href="#screenshot">{{ _('Current screenshot') }}</a></li>
+        <li class="tab" id="extract-tab"><a href="{{ url_for('ui.ui_diff.diff_history_page_extract_GET', uuid=uuid)}}">{{ _('Extract Data') }}</a></li>
+    </ul>
+</div>
+
+<div id="diff-ui">
+    <div class="tab-pane-inner" id="error-text">
+        <div class="snapshot-age error">{{watch_a.error_text_ctime|format_seconds_ago}} {{ _('seconds ago.') }}</div>
+        <pre>
+            {{ last_error_text }}
+        </pre>
+    </div>
+
+    <div class="tab-pane-inner" id="error-screenshot">
+        <div class="snapshot-age error">{{watch_a.snapshot_error_screenshot_ctime|format_seconds_ago}} {{ _('seconds ago') }}</div>
+        <img id="error-screenshot-img"  style="max-width: 80%" alt="{{ _('Current error-ing screenshot from most recent request') }}" >
+    </div>
+
+    <div class="tab-pane-inner" id="text">
+    {%- if (content | default('')).split('\n') | length > 100 -%}
+        <div id="cell-diff-jump-visualiser"  style="user-select: none;">
+            {%- for cell in diff_cell_grid -%}
+            <div{% if cell.class %} class="{{ cell.class }}"{% endif %}></div>
+            {%- endfor -%}
+        </div>
+    {%- endif -%}
+        {%- if password_enabled_and_share_is_off -%}
+            <div class="tip">{{ _('Pro-tip: You can enable') }} <strong>{{ _('"share access when password is enabled"') }}</strong> {{ _('from settings.') }}
+            </div>
+        {%- endif -%}
+        <div id="text-diff-heading-area"  style="user-select: none;">
+            <div class="snapshot-age"><span>{{ from_version|format_timestamp_timeago }}</span>
+                {%- if note -%}<span class="note"><strong>{{ note }}</strong></span>{%- endif -%}
+                <a href="{{ url_for("ui.ui_preview.preview_page", uuid=uuid) }}">{{ _('Goto single snapshot') }}</a>
+            </div>
+        </div>
+        <pre id="difference" style="border-left: 2px solid #ddd;">{{ content| diff_unescape_difference_spans }}</pre>
+    <div id="diff-visualiser-area-after" style="user-select: none;">
+        <strong>{{ _('Tip:') }}</strong> {{ _('Highlight text to share or add to ignore lists.') }}
+    </div>
+    </div>
+
+    <div class="tab-pane-inner" id="screenshot">
+         <div class="tip">
+             {{ _('For now, Differences are performed on text, not graphically, only the latest screenshot is available.') }}
+         </div>
+         {% if is_html_webdriver %}
+           {% if screenshot %}
+            <div class="snapshot-age">{{watch_a.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
+            <img style="max-width: 80%" id="screenshot-img" alt="{{ _('Current screenshot from most recent request') }}" >
+           {% else %}
+              {{ _('No screenshot available just yet! Try rechecking the page.') }}
+           {% endif %}
+         {% else %}
+           <strong>{{ _('Screenshot requires Playwright/WebDriver enabled') }}</strong>
+         {% endif %}
+     </div>
+
+</div>
+
+<script>
+    const newest_version_timestamp = {{newest_version_timestamp}};
+</script>
+<script src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
+
+
+{% endblock %}

changedetectionio/blueprint/ui/templates/edit.html

@@ -1,12 +1,13 @@
 {% extends 'base.html' %}
 {% block content %}
-{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_time_schedule_form, playwright_warning, only_playwright_type_watches_warning, render_conditions_fieldlist_of_formfields_as_table %}
+{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_time_schedule_form, playwright_warning, only_playwright_type_watches_warning, highlight_trigger_ignored_explainer, render_conditions_fieldlist_of_formfields_as_table, render_ternary_field %}
 {% from '_common_fields.html' import render_common_settings_form %}
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='vis.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='scheduler.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='conditions.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='modal.js')}}"></script>
 
 
 <script>
@@ -43,20 +44,25 @@
 
     <div class="tabs collapsable">
         <ul>
-            <li class="tab"><a href="#general">General</a></li>
-            <li class="tab"><a href="#request">Request</a></li>
+            <li class="tab"><a href="#general">{{ _('General') }}</a></li>
+            {% if capabilities.supports_request_type %}
+            <li class="tab"><a href="#request">{{ _('Request') }}</a></li>
+            {% endif %}
             {% if extra_tab_content %}
             <li class="tab"><a href="#extras_tab">{{ extra_tab_content }}</a></li>
             {% endif %}
-            <li class="tab"><a id="browsersteps-tab" href="#browser-steps">Browser Steps</a></li>
-        <!-- should goto extra forms? -->
-            {% if watch['processor'] == 'text_json_diff' %}
-            <li class="tab"><a id="visualselector-tab" href="#visualselector">Visual Filter Selector</a></li>
-            <li class="tab" id="filters-and-triggers-tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
-            <li class="tab" id="conditions-tab"><a href="#conditions">Conditions</a></li>
+            {% if capabilities.supports_browser_steps %}
+            <li class="tab"><a id="browsersteps-tab" href="#browser-steps">{{ _('Browser Steps') }}</a></li>
             {% endif %}
-            <li class="tab"><a href="#notifications">Notifications</a></li>
-            <li class="tab"><a href="#stats">Stats</a></li>
+            {% if capabilities.supports_visual_selector %}
+            <li class="tab"><a id="visualselector-tab" href="#visualselector">{{ _('Visual Filter Selector') }}</a></li>
+            {% endif %}
+            {% if capabilities.supports_text_filters_and_triggers %}
+            <li class="tab" id="filters-and-triggers-tab"><a href="#filters-and-triggers">{{ _('Filters & Triggers') }}</a></li>
+            <li class="tab" id="conditions-tab"><a href="#conditions">{{ _('Conditions') }}</a></li>
+            {% endif %}
+            <li class="tab"><a href="#notifications">{{ _('Notifications') }}</a></li>
+            <li class="tab"><a href="#stats">{{ _('Stats') }}</a></li>
         </ul>
     </div>
 
@@ -69,18 +75,19 @@
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.url, placeholder="https://...", required=true, class="m-d") }}
-                        <div class="pure-form-message">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></div>
-                        <div class="pure-form-message">Variables are supported in the URL (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
+                        <div class="pure-form-message">{{ _('Some sites use JavaScript to create the content, for this you should') }} <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">{{ _('use the Chrome/WebDriver Fetcher') }}</a></div>
+                        <div class="pure-form-message">{{ _('Variables are supported in the URL') }} (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">{{ _('help and examples here') }}</a>).</div>
+                    </div>
+                    <div class="pure-control-group">
+                        {{ render_field(form.tags) }}
+                        <span class="pure-form-message-inline">{{ _('Organisational tag/group name used in the main listing page') }}</span>
                     </div>
                     <div class="pure-control-group inline-radio">
                         {{ render_field(form.processor) }}
                     </div>
                     <div class="pure-control-group">
-                        {{ render_field(form.title, class="m-d") }}
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.tags) }}
-                        <span class="pure-form-message-inline">Organisational tag/group name used in the main listing page</span>
+                        {{ render_field(form.title, class="m-d", placeholder=watch.label) }}
+                        <span class="pure-form-message-inline">{{ _('Automatically uses the page title if found, you can also use your own title/description here') }}</span>
                     </div>
                     <div class="pure-control-group time-between-check border-fieldset">
 
@@ -90,7 +97,7 @@
                             {{ render_field(form.time_between_check, class="time-check-widget") }}
 
                             <span class="pure-form-message-inline">
-                             The interval/amount of time between each check.
+                             {{ _('The interval/amount of time between each check.') }}
                             </span>
                         </div>
                         <div id="time-between-check-schedule">
@@ -101,33 +108,42 @@
                         </div>
 <br>
               </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.extract_title_as_title) }}
-                    </div>
+
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.filter_failure_notification_send) }}
                         <span class="pure-form-message-inline">
-                         Sends a notification when the filter can no longer be seen on the page, good for knowing when the page changed and your filter will not work anymore.
+                         {{ _('Sends a notification when the filter can no longer be seen on the page, good for knowing when the page changed and your filter will not work anymore.') }}
                         </span>
                     </div>
+                    <div class="pure-control-group">
+                        {{ render_field(form.history_snapshot_max_length, class="history_snapshot_max_length") }}
+                        <span class="pure-form-message-inline">{{ _('Limit collection of history snapshots for each watch to this number of history items.') }}
+                        <br>
+                        {{ _('Set to empty to use system settings default') }}
+                        </span>
+                    </div>
+                    <div class="pure-control-group">
+                        {{ render_ternary_field(form.use_page_title_in_list) }}
+                    </div>
                 </fieldset>
             </div>
 
+            {% if capabilities.supports_request_type %}
             <div class="tab-pane-inner" id="request">
                     <div class="pure-control-group inline-radio">
                         {{ render_field(form.fetch_backend, class="fetch-backend") }}
                         <span class="pure-form-message-inline">
-                            <p>Use the <strong>Basic</strong> method (default) where your watched site doesn't need Javascript to render.</p>
-                            <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
-                            Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
+                            <p>{{ _('Use the') }} <strong>{{ _('Basic') }}</strong> {{ _('method (default) where your watched site doesn\'t need Javascript to render.') }}</p>
+                            <p>{{ _('The') }} <strong>{{ _('Chrome/Javascript') }}</strong> {{ _('method requires a network connection to a running WebDriver+Chrome server, set by the ENV var \'WEBDRIVER_URL\'.') }} </p>
+                            {{ _('Tip:') }} <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">{{ _('Connect using Bright Data and Oxylabs Proxies, find out more here.') }}</a>
                         </span>
                     </div>
                 {% if form.proxy %}
                     <div class="pure-control-group inline-radio">
-                          <div>{{ form.proxy.label }} <a href="" id="check-all-proxies" class="pure-button button-secondary button-xsmall" >Check/Scan all</a></div>
+                          <div>{{ form.proxy.label }} <a href="" id="check-all-proxies" class="pure-button button-secondary button-xsmall" >{{ _('Check/Scan all') }}</a></div>
                           <div>{{ form.proxy(class="fetch-backend-proxy") }}</div>
                         <span class="pure-form-message-inline">
-                        Choose a proxy for this watch
+                        {{ _('Choose a proxy for this watch') }}
                         </span>
                     </div>
                 {% endif %}
@@ -137,31 +153,29 @@
                     <div class="pure-control-group">
                         {{ render_field(form.webdriver_delay) }}
                         <div class="pure-form-message-inline">
-                            <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
+                            <strong>{{ _('If you\'re having trouble waiting for the page to be fully rendered (text missing etc), try increasing the \'wait\' time here.') }}</strong>
                             <br>
-                            This will wait <i>n</i> seconds before extracting the text.
+                            {{ _('This will wait') }} <i>n</i> {{ _('seconds before extracting the text.') }}
                             {% if using_global_webdriver_wait %}
-                            <br><strong>Using the current global default settings</strong>
+                            <br><strong>{{ _('Using the current global default settings') }}</strong>
                             {% endif %}
                         </div>
                     </div>
                     <div class="pure-control-group">
-                        <a class="pure-button button-secondary button-xsmall show-advanced">Show advanced options</a>
+                        <a class="pure-button button-secondary button-xsmall show-advanced">{{ _('Show advanced options') }}</a>
                     </div>
                     <div class="advanced-options"  style="display: none;">
                         {{ render_field(form.webdriver_js_execute_code) }}
                         <div class="pure-form-message-inline">
-                            Run this code before performing change detection, handy for filling in fields and other
-                            actions <a
-                                href="https://github.com/dgtlmoon/changedetection.io/wiki/Run-JavaScript-before-change-detection">More
-                            help and examples here</a>
+                            {{ _('Run this code before performing change detection, handy for filling in fields and other actions') }} <a
+                                href="https://github.com/dgtlmoon/changedetection.io/wiki/Run-JavaScript-before-change-detection">{{ _('More help and examples here') }}</a>
                         </div>
                     </div>
                 </fieldset>
                 <!-- html requests always -->
                 <fieldset data-visible-for="fetch_backend=html_requests">
                     <div class="pure-control-group">
-                        <a class="pure-button button-secondary button-xsmall show-advanced">Show advanced options</a>
+                        <a class="pure-button button-secondary button-xsmall show-advanced">{{ _('Show advanced options') }}</a>
                     </div>
                     <div class="advanced-options"  style="display: none;">
                         <div class="pure-control-group" id="request-method">
@@ -176,7 +190,7 @@
    \"year\":{% now 'Europe/Berlin', '%Y' %}
 }") }}
                         </div>
-                        <div class="pure-form-message">Variables are supported in the request body (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
+                        <div class="pure-form-message">{{ _('Variables are supported in the request body') }} (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">{{ _('help and examples here') }}</a>).</div>
                     </div>
                 </fieldset>
             <!-- hmm -->
@@ -185,15 +199,15 @@
 Cookie: foobar
 User-Agent: wonderbra 1.0
 Math: {{ 1 + 1 }}") }}
-                        <div class="pure-form-message">Variables are supported in the request header values (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
+                        <div class="pure-form-message">{{ _('Variables are supported in the request header values') }} (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">{{ _('help and examples here') }}</a>).</div>
                         <div class="pure-form-message-inline">
                             {% if has_extra_headers_file %}
-                                <strong>Alert! Extra headers file found and will be added to this watch!</strong>
+                                <strong>{{ _('Alert! Extra headers file found and will be added to this watch!') }}</strong>
                             {% else %}
-                                Headers can be also read from a file in your data-directory <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Adding-headers-from-an-external-file">Read more here</a>
+                                {{ _('Headers can be also read from a file in your data-directory') }} <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Adding-headers-from-an-external-file">{{ _('Read more here') }}</a>
                             {% endif %}
                             <br>
-                            (Not supported by Selenium browser)
+                            ({{ _('Not supported by Selenium browser') }})
                         </div>
                     </div>
             <fieldset data-visible-for="fetch_backend=html_requests fetch_backend=html_webdriver" >
@@ -202,11 +216,11 @@ Math: {{ 1 + 1 }}") }}
                     </div>
             </fieldset>
             </div>
+            {% endif %}
 
             <div class="tab-pane-inner" id="browser-steps">
-            {% if watch_needs_selenium_or_playwright %}
-                {# Only works with playwright #}
-                {% if system_has_playwright_configured %}
+            {% if capabilities.supports_browser_steps %}
+               {% if true %}
                 <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
                 <fieldset>
                     <div class="pure-control-group">
@@ -218,19 +232,19 @@ Math: {{ 1 + 1 }}") }}
 
                         <!---  Do this later -->
                         <div class="checkbox" style="display: none;">
-                            <input type=checkbox id="include_text_elements" > <label for="include_text_elements">Turn on text finder</label>
+                            <input type=checkbox id="include_text_elements" > <label for="include_text_elements">{{ _('Turn on text finder') }}</label>
                         </div>
 
-                        <div id="loading-status-text" style="display: none;">Please wait, first browser step can take a little time to load..<div class="spinner"></div></div>
+                        <div id="loading-status-text" style="display: none;">{{ _('Please wait, first browser step can take a little time to load..') }}<div class="spinner"></div></div>
                         <div class="flex-wrapper" >
 
                             <div id="browser-steps-ui" class="noselect">
                                 <div class="noselect"  id="browsersteps-selector-wrapper" style="width: 100%">
                                     <span class="loader" >
                                         <span id="browsersteps-click-start">
-                                            <h2 >Click here to Start</h2>
+                                            <h2 >{{ _('Click here to Start') }}</h2>
                                             <svg style="height: 3.5rem;" version="1.1" viewBox="0 0 32 32"  xml:space="preserve" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g id="start"/><g id="play_x5F_alt"><path d="M16,0C7.164,0,0,7.164,0,16s7.164,16,16,16s16-7.164,16-16S24.836,0,16,0z M10,24V8l16.008,8L10,24z" style="fill: var(--color-grey-400);"/></g></svg><br>
-                                            Please allow 10-15 seconds for the browser to connect.<br>
+                                            {{ _('Please allow 10-15 seconds for the browser to connect.') }}<br>
                                         </span>
                                         <div class="spinner"  style="display: none;"></div>
                                     </span>
@@ -239,22 +253,20 @@ Math: {{ 1 + 1 }}") }}
                                 </div>
                             </div>
                             <div id="browser-steps-fieldlist" >
-                                <span id="browser-seconds-remaining">Loading</span> <span style="font-size: 80%;"> (<a target="newwindow" href="https://github.com/dgtlmoon/changedetection.io/pull/478/files#diff-1a79d924d1840c485238e66772391268a89c95b781d69091384cf1ea1ac146c9R4">?</a>) </span>
+                                <span id="browser-seconds-remaining">{{ _('Press "Play" to start.') }}</span> <span style="font-size: 80%;"> (<a target="newwindow" href="https://github.com/dgtlmoon/changedetection.io/pull/478/files#diff-1a79d924d1840c485238e66772391268a89c95b781d69091384cf1ea1ac146c9R4">?</a>) </span>
                                 {{ render_field(form.browser_steps) }}
                             </div>
                         </div>
                     </div>
                 </fieldset>
                 {% else %}
-                    {# it's configured to use selenium or chrome but system says its not configured #}
-                    {{ playwright_warning() }}
-                    {% if system_has_webdriver_configured %}
-                        <strong>Selenium/Webdriver cant be used here because it wont fetch screenshots reliably.</strong>
-                    {% endif %}
+                    <strong>{{ _('Visual Selector data is not ready, watch needs to be checked atleast once.') }}</strong>
                 {% endif %}
             {% else %}
-                {# "This functionality needs chrome.." #}
-                {{ only_playwright_type_watches_warning() }}
+                <p>
+                    <strong>{{ _('Sorry, this functionality only works with fetchers that support interactive Javascript (so far only Playwright based fetchers)') }}<br>
+                    {{ _('You need to') }} <a href="#request">{{ _('Set the fetch method') }}</a> {{ _('to one that supports interactive Javascript.') }}</strong>
+                </p>
             {% endif %}
             </div>
 
@@ -262,31 +274,30 @@ Math: {{ 1 + 1 }}") }}
             <div class="tab-pane-inner" id="notifications">
                 <fieldset>
                     <div  class="pure-control-group inline-radio">
-                      {{ render_checkbox_field(form.notification_muted) }}
+                      {{ render_ternary_field(form.notification_muted, BooleanField=true) }}
                     </div>
-                    {% if watch_needs_selenium_or_playwright %}
+                    {% if capabilities.supports_screenshots %}
                     <div class="pure-control-group inline-radio">
                       {{ render_checkbox_field(form.notification_screenshot) }}
                         <span class="pure-form-message-inline">
-                            <strong>Use with caution!</strong> This will easily fill up your email storage quota or flood other storages.
+                            <strong>{{ _('Use with caution!') }}</strong> {{ _('This will easily fill up your email storage quota or flood other storages.') }}
                         </span>
                     </div>
                     {% endif %}
                     <div class="field-group" id="notification-field-group">
                         {% if has_default_notification_urls %}
                         <div class="inline-warning">
-                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!" >
-                            There are <a href="{{ url_for('settings.settings_page')}}#notifications">system-wide notification URLs enabled</a>, this form will override notification settings for this watch only &dash; an empty Notification URL list here will still send notifications.
+                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="{{ _('Look out!') }}" title="{{ _('Lookout!') }}" >
+                            {{ _('There are') }} <a href="{{ url_for('settings.settings_page')}}#notifications">{{ _('system-wide notification URLs enabled') }}</a>, {{ _('this form will override notification settings for this watch only') }} &dash; {{ _('an empty Notification URL list here will still send notifications.') }}
                         </div>
                         {% endif %}
-                        <a href="#notifications" id="notification-setting-reset-to-default" class="pure-button button-xsmall" style="right: 20px; top: 20px; position: absolute; background-color: #5f42dd; border-radius: 4px; font-size: 70%; color: #fff">Use system defaults</a>
+                        <a href="#notifications" id="notification-setting-reset-to-default" class="pure-button button-xsmall" style="right: 20px; top: 20px; position: absolute; background-color: #5f42dd; border-radius: 4px; font-size: 70%; color: #fff">{{ _('Use system defaults') }}</a>
                         {{ render_common_settings_form(form, emailprefix, settings_application, extra_notification_token_placeholder_info) }}
                     </div>
                 </fieldset>
             </div>
 
-            {% if watch['processor'] == 'text_json_diff' %}
-
+            {% if capabilities.supports_text_filters_and_triggers %}
             <div class="tab-pane-inner" id="conditions">
                     <script>
                         const verify_condition_rule_url="{{url_for('conditions.verify_condition_single_rule', watch_uuid=uuid)}}";
@@ -296,74 +307,77 @@ Math: {{ 1 + 1 }}") }}
                     {{ render_conditions_fieldlist_of_formfields_as_table(form.conditions) }}
                     <div class="pure-form-message-inline">
 
-                        <p id="verify-state-text">Use the verify (✓) button to test if a condition passes against the current snapshot.</p>
-                       Read a quick tutorial about <a href="https://changedetection.io/tutorial/conditional-actions-web-page-changes">using conditional web page changes here</a>.<br>
+                        <p id="verify-state-text">{{ _('Use the verify (✓) button to test if a condition passes against the current snapshot.') }}</p>
+                       {{ _('Read a quick tutorial about') }} <a href="https://changedetection.io/tutorial/conditional-actions-web-page-changes">{{ _('using conditional web page changes here') }}</a>.<br>
                     </div>
                 </div>
             </div>
             <div class="tab-pane-inner" id="filters-and-triggers">
-                <span id="activate-text-preview" class="pure-button pure-button-primary button-xsmall">Activate preview</span>
+                <span id="activate-text-preview" class="pure-button pure-button-primary button-xsmall">{{ _('Activate preview') }}</span>
               <div>
               <div id="edit-text-filter">
-                    <div class="pure-control-group" id="pro-tips">
-                            <strong>Pro-tips:</strong><br>
+
+{% if capabilities.supports_text_filters_and_triggers_elements %}
+                        <div class="pure-control-group" id="pro-tips">
+                            <strong>{{ _('Pro-tips:') }}</strong><br>
                             <ul>
                                 <li>
-                                    Use the preview page to see your filters and triggers highlighted.
+                                    {{ _('Use the preview page to see your filters and triggers highlighted.') }}
                                 </li>
                                 <li>
-                                    Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a>
+                                    {{ _('Some sites use JavaScript to create the content, for this you should') }} <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">{{ _('use the Chrome/WebDriver Fetcher') }}</a>
                                 </li>
                             </ul>
                     </div>
-
 {% include "edit/include_subtract.html" %}
+{% endif %}
                 <div class="text-filtering border-fieldset">
                 <fieldset class="pure-group" id="text-filtering-type-options">
-                    <h3>Text filtering</h3>
-                        Limit trigger/ignore/block/extract to;<br>
+                    <h3>{{ _('Text filtering') }}</h3>
+                        {{ _('Limit trigger/ignore/block/extract to;') }}<br>
                         {{ render_checkbox_field(form.filter_text_added) }}
                         {{ render_checkbox_field(form.filter_text_replaced) }}
                         {{ render_checkbox_field(form.filter_text_removed) }}
-                    <span class="pure-form-message-inline">Note: Depending on the length and similarity of the text on each line, the algorithm may consider an <strong>addition</strong> instead of <strong>replacement</strong> for example.</span><br>
-                    <span class="pure-form-message-inline">&nbsp;So it's always better to select <strong>Added</strong>+<strong>Replaced</strong> when you're interested in new content.</span><br>
-                    <span class="pure-form-message-inline">&nbsp;When content is merely moved in a list, it will also trigger an <strong>addition</strong>, consider enabling <code><strong>Only trigger when unique lines appear</strong></code></span>
+                    <span class="pure-form-message-inline">{{ _('Note: Depending on the length and similarity of the text on each line, the algorithm may consider an') }} <strong>{{ _('addition') }}</strong> {{ _('instead of') }} <strong>{{ _('replacement') }}</strong> {{ _('for example.') }}</span><br>
+                    <span class="pure-form-message-inline">&nbsp;{{ _('So it\'s always better to select') }} <strong>{{ _('Added') }}</strong>+<strong>{{ _('Replaced') }}</strong> {{ _('when you\'re interested in new content.') }}</span><br>
+                    <span class="pure-form-message-inline">&nbsp;{{ _('When content is merely moved in a list, it will also trigger an') }} <strong>{{ _('addition') }}</strong>, {{ _('consider enabling') }} <code><strong>{{ _('Only trigger when unique lines appear') }}</strong></code></span>
                 </fieldset>
                 <fieldset class="pure-control-group">
                     {{ render_checkbox_field(form.check_unique_lines) }}
-                    <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
+                    <span class="pure-form-message-inline">{{ _('Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.') }}</span>
                 </fieldset>
                 <fieldset class="pure-control-group">
                     {{ render_checkbox_field(form.remove_duplicate_lines) }}
-                    <span class="pure-form-message-inline">Remove duplicate lines of text</span>
+                    <span class="pure-form-message-inline">{{ _('Remove duplicate lines of text') }}</span>
                 </fieldset>
                 <fieldset class="pure-control-group">
                     {{ render_checkbox_field(form.sort_text_alphabetically) }}
-                    <span class="pure-form-message-inline">Helps reduce changes detected caused by sites shuffling lines around, combine with <i>check unique lines</i> below.</span>
+                    <span class="pure-form-message-inline">{{ _('Helps reduce changes detected caused by sites shuffling lines around, combine with') }} <i>{{ _('check unique lines') }}</i> {{ _('below.') }}</span>
                 </fieldset>
                 <fieldset class="pure-control-group">
                     {{ render_checkbox_field(form.trim_text_whitespace) }}
-                    <span class="pure-form-message-inline">Remove any whitespace before and after each line of text</span>
+                    <span class="pure-form-message-inline">{{ _('Remove any whitespace before and after each line of text') }}</span>
                 </fieldset>
                 {% include "edit/text-options.html" %}
                 </div>
               </div>
               <div id="text-preview" style="display: none;" >
-                    <script>
-                        const preview_text_edit_filters_url="{{url_for('ui.ui_edit.watch_get_preview_rendered', uuid=uuid)}}";
-                    </script>
-                    <br>
-                    {#<div id="text-preview-controls"><span id="text-preview-refresh" class="pure-button button-xsmall">Refresh</span></div>#}
-                    <div class="minitabs-wrapper">
-                      <div class="minitabs-content">
-                          <div id="text-preview-inner" class="monospace-preview">
-                              <p>Loading...</p>
-                          </div>
-                          <div id="text-preview-before-inner" style="display: none;" class="monospace-preview">
-                              <p>Loading...</p>
-                          </div>
+                <script>
+                    const preview_text_edit_filters_url="{{url_for('ui.ui_edit.watch_get_preview_rendered', uuid=uuid)}}";
+                </script>
+                <br>
+                {#<div id="text-preview-controls"><span id="text-preview-refresh" class="pure-button button-xsmall">Refresh</span></div>#}
+                <div class="minitabs-wrapper">
+                  <div class="minitabs-content">
+                      <div id="text-preview-inner" class="monospace-preview">
+                          <p>{{ _('Loading...') }}</p>
                       </div>
-                    </div>
+                      <div id="text-preview-before-inner" style="display: none;" class="monospace-preview">
+                          <p>{{ _('Loading...') }}</p>
+                      </div>
+                  </div>
+                </div>
+                {{ highlight_trigger_ignored_explainer() }}
             </div>
           </div>
         </div>
@@ -375,41 +389,55 @@ Math: {{ 1 + 1 }}") }}
             {{ extra_form_content|safe }}
             </div>
         {% endif %}
-            {% if watch['processor'] == 'text_json_diff' %}
+            {% if capabilities.supports_visual_selector %}
             <div class="tab-pane-inner visual-selector-ui" id="visualselector">
                 <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
 
                 <fieldset>
                     <div class="pure-control-group">
-                        {% if watch_needs_selenium_or_playwright %}
-                            {% if system_has_playwright_configured %}
-                            <span class="pure-form-message-inline" id="visual-selector-heading">
-                                The Visual Selector tool lets you select the <i>text</i> elements that will be used for the change detection. It automatically fills-in the filters in the "CSS/JSONPath/JQ/XPath Filters" box of the <a href="#filters-and-triggers">Filters & Triggers</a> tab. Use <strong>Shift+Click</strong> to select multiple items.
-                            </span>
+                        {% if capabilities.supports_screenshots and capabilities.supports_xpath_element_data %}
+                            {% if visual_selector_data_ready %}
+                                <span class="pure-form-message-inline" id="visual-selector-heading">
+                                    {{ _('The Visual Selector tool lets you select the') }} <i>{{ _('text') }}</i> {{ _('elements that will be used for the change detection. It automatically fills-in the filters in the "CSS/JSONPath/JQ/XPath Filters" box of the') }} <a href="#filters-and-triggers">{{ _('Filters & Triggers') }}</a> {{ _('tab. Use') }} <strong>{{ _('Shift+Click') }}</strong> {{ _('to select multiple items.') }}
+                                </span>
 
-                            <div id="selector-header">
-                                <a id="clear-selector" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Clear selection</a>
-                                <!-- visual selector IMG will try to load, it will either replace this or on error replace it with some handy text -->
-                                <i class="fetching-update-notice" style="font-size: 80%;">One moment, fetching screenshot and element information..</i>
-                            </div>
-                            <div id="selector-wrapper" style="display: none">
-                                <!-- request the screenshot and get the element offset info ready -->
-                                <!-- use img src ready load to know everything is ready to map out -->
-                                <!-- @todo: maybe something interesting like a field to select 'elements that contain text... and their parents n' -->
-                                <img id="selector-background" >
-                                <canvas id="selector-canvas"></canvas>
-                            </div>
-                            <div id="selector-current-xpath" style="overflow-x: hidden"><strong>Currently:</strong>&nbsp;<span class="text">Loading...</span></div>
-                        {% else %}
-                            {# The watch needed chrome but system says that playwright is not ready #}
-                            {{ playwright_warning() }}
-                        {% endif %}
-                            {% if system_has_webdriver_configured %}
-                                <strong>Selenium/Webdriver cant be used here because it wont fetch screenshots reliably.</strong>
-                            {% endif %}
+                                {% if watch['processor'] == 'image_ssim_diff' %} {# @todo, integrate with image_ssim_diff selector better, use some extra form ? #}
+                                <div id="selection-mode-controls" style="margin: 10px 0; padding: 10px; background: var(--color-background-tab); border-radius: 5px;">
+                                    <label style="font-weight: 600; margin-right: 15px;">{{ _('Selection Mode:') }}</label>
+                                    <label style="margin-right: 15px;">
+                                        <input type="radio" name="selector-mode" value="element" style="margin-right: 5px;">
+                                        {{ _('Select by element') }}
+                                    </label>
+                                    <label>
+                                        <input type="radio" name="selector-mode" value="draw" checked style="margin-right: 5px;">
+                                        {{ _('Draw area') }}
+                                    </label>
+                                    {{ render_field(form.processor_config_bounding_box) }}
+                                    {{ render_field(form.processor_config_selection_mode) }}
+                                </div>
+                                {% endif %}
+
+                                <div id="selector-header">
+                                    <a id="clear-selector" class="pure-button button-secondary button-xsmall" style="font-size: 70%">{{ _('Clear selection') }}</a>
+                                    <!-- visual selector IMG will try to load, it will either replace this or on error replace it with some handy text -->
+                                    <i class="fetching-update-notice" style="font-size: 80%;">{{ _('One moment, fetching screenshot and element information..') }}</i>
+                                </div>
+                                <div id="selector-wrapper" style="display: none">
+                                    <!-- request the screenshot and get the element offset info ready -->
+                                    <!-- use img src ready load to know everything is ready to map out -->
+                                    <!-- @todo: maybe something interesting like a field to select 'elements that contain text... and their parents n' -->
+                                    <img id="selector-background" >
+                                    <canvas id="selector-canvas"></canvas>
+                                </div>
+                                <div id="selector-current-xpath" style="overflow-x: hidden"><strong>{{ _('Currently:') }}</strong>&nbsp;<span class="text">{{ _('Loading...') }}</span></div>
+                            {%  else %}
+                                <strong>{{ _('Visual Selector data is not ready, watch needs to be checked atleast once.') }}</strong>
+                            {%  endif %}
                     {% else %}
-                        {# "This functionality needs chrome.." #}
-                        {{ only_playwright_type_watches_warning() }}
+                        <p>
+                            <strong>{{ _('Sorry, this functionality only works with fetchers that support Javascript and screenshots (such as playwright etc).') }}<br>
+                            {{ _('You need to') }} <a href="#request">{{ _('Set the fetch method') }}</a> {{ _('to one that supports Javascript and screenshots.') }}</strong>
+                        </p>
                     {% endif %}
                     </div>
                 </fieldset>
@@ -425,27 +453,27 @@ Math: {{ 1 + 1 }}") }}
                     <table class="pure-table" id="stats-table">
                         <tbody>
                         <tr>
-                            <td>Check count</td>
+                            <td>{{ _('Check count') }}</td>
                             <td>{{ "{:,}".format( watch.check_count) }}</td>
                         </tr>
                         <tr>
-                            <td>Consecutive filter failures</td>
+                            <td>{{ _('Consecutive filter failures') }}</td>
                             <td>{{ "{:,}".format( watch.consecutive_filter_failures) }}</td>
                         </tr>
                         <tr>
-                            <td>History length</td>
+                            <td>{{ _('History length') }}</td>
                             <td>{{ "{:,}".format(watch.history|length) }}</td>
                         </tr>
                         <tr>
-                            <td>Last fetch duration</td>
+                            <td>{{ _('Last fetch duration') }}</td>
                             <td>{{ watch.fetch_time }}s</td>
                         </tr>
                         <tr>
-                            <td>Notification alert count</td>
+                            <td>{{ _('Notification alert count') }}</td>
                             <td>{{ watch.notification_alert_count }}</td>
                         </tr>
                         <tr>
-                            <td>Server type reply</td>
+                            <td>{{ _('Server type reply') }}</td>
                             <td>{{ watch.get('remote_server_reply') }}</td>
                         </tr>
                         </tbody>
@@ -459,7 +487,8 @@ Math: {{ 1 + 1 }}") }}
 
                     {% if watch.history_n %}
                         <p>
-                             <a href="{{url_for('ui.ui_edit.watch_get_latest_html', uuid=uuid)}}" class="pure-button button-small">Download latest HTML snapshot</a>
+                             <a href="{{url_for('ui.ui_edit.watch_get_latest_html', uuid=uuid)}}" class="pure-button button-small">{{ _('Download latest HTML snapshot') }}</a>
+                             <a href="{{url_for('ui.ui_edit.watch_get_data_package', uuid=uuid)}}" class="pure-button button-small">{{ _('Download watch data package') }}</a>
                         </p>
                     {% endif %}
 
@@ -469,11 +498,22 @@ Math: {{ 1 + 1 }}") }}
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}
                     <a href="{{url_for('ui.form_delete', uuid=uuid)}}"
-                       class="pure-button button-small button-error ">Delete</a>
+                       class="pure-button button-error"
+                       data-requires-confirm
+                       data-confirm-type="danger"
+                       data-confirm-title="{{ _('Delete Watch?') }}"
+                       data-confirm-message="<p>{{ _('Are you sure you want to delete the watch for:') }}</p><p><strong>{{ watch.get('url', 'this watch') }}</strong></p><p>{{ _('This action cannot be undone.') }}</p>"
+                       data-confirm-button="{{ _('Delete') }}">{{ _('Delete') }}</a>
                     {% if watch.history_n %}<a href="{{url_for('ui.clear_watch_history', uuid=uuid)}}"
-                       class="pure-button button-small button-error ">Clear History</a>{% endif %}
+                       class="pure-button button-error"
+                       data-requires-confirm
+                       data-confirm-type="warning"
+                       data-confirm-title="{{ _('Clear History?') }}"
+                       data-confirm-message="<p>{{ _('Are you sure you want to clear all history for:') }}</p><p><strong>{{ watch.get('url', 'this watch') }}</strong></p><p>{{ _('This will remove all snapshots and previous versions. This action cannot be undone.') }}</p>"
+                       data-confirm-button="{{ _('Clear History') }}">{{ _('Clear History') }}</a>{% endif %}
                     <a href="{{url_for('ui.form_clone', uuid=uuid)}}"
-                       class="pure-button button-small ">Clone &amp; Edit</a>
+                       class="pure-button">{{ _('Clone & Edit') }}</a>
+                 <a href="{{ url_for('rss.rss_single_watch', uuid=uuid, token=app_rss_token)}}"><img alt="{{ _('RSS Feed for this watch') }}" style="padding: .5em 1em;" src="{{url_for('static_content', group='images', filename='generic_feed-icon.svg')}}" height="15"></a>
                 </div>
             </div>
         </form>

changedetectionio/blueprint/ui/templates/preview.html

@@ -1,9 +1,11 @@
 {% extends 'base.html' %}
-
+{% from '_helpers.html' import highlight_trigger_ignored_explainer %}
 {% block content %}
     <script>
         const screenshot_url = "{{url_for('static_content', group='screenshot', filename=uuid)}}";
-        const triggered_line_numbers = {{ triggered_line_numbers|tojson }};
+        const triggered_line_numbers = {{ highlight_triggered_line_numbers|tojson }};
+        const ignored_line_numbers = {{ highlight_ignored_line_numbers|tojson }};
+        const blocked_line_numbers = {{ highlight_blocked_line_numbers|tojson }};
         {% if last_error_screenshot %}
             const error_screenshot_url = "{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
         {% endif %}
@@ -14,10 +16,10 @@
     <script src="{{ url_for('static_content', group='js', filename='preview.js') }}" defer></script>
     <script src="{{ url_for('static_content', group='js', filename='tabs.js') }}" defer></script>
     {% if versions|length >= 2 %}
-        <div id="settings" style="text-align: center;">
+        <div id="diff-form" style="text-align: center;">
             <form class="pure-form " action="" method="POST">
                 <fieldset>
-                    <label for="preview-version">Select timestamp</label> <select id="preview-version"
+                    <label for="preview-version">{{ _('Select timestamp') }}</label> <select id="preview-version"
                                                                                  name="from_version"
                                                                                  class="needs-localtime">
                     {% for version in versions|reverse %}
@@ -26,27 +28,27 @@
                         </option>
                     {% endfor %}
                 </select>
-                    <button type="submit" class="pure-button pure-button-primary">Go</button>
+                    <button type="submit" class="pure-button pure-button-primary">{{ _('Go') }}</button>
 
                 </fieldset>
             </form>
                 <br>
-                <strong>Keyboard: </strong><a href="" class="pure-button pure-button-primary" id="btn-previous">
-                &larr; Previous</a> &nbsp; <a class="pure-button pure-button-primary" id="btn-next" href="">
-                &rarr; Next</a>
+                <strong>{{ _('Keyboard:') }} </strong><a href="" class="pure-button pure-button-primary" id="btn-previous">
+                &larr; {{ _('Previous') }}</a> &nbsp; <a class="pure-button pure-button-primary" id="btn-next" href="">
+                &rarr; {{ _('Next') }}</a>
         </div>
     {% endif %}
 
     <div class="tabs">
         <ul>
             {% if last_error_text %}
-                <li class="tab" id="error-text-tab"><a href="#error-text">Error Text</a></li> {% endif %}
+                <li class="tab" id="error-text-tab"><a href="#error-text">{{ _('Error Text') }}</a></li> {% endif %}
             {% if last_error_screenshot %}
-                <li class="tab" id="error-screenshot-tab"><a href="#error-screenshot">Error Screenshot</a>
+                <li class="tab" id="error-screenshot-tab"><a href="#error-screenshot">{{ _('Error Screenshot') }}</a>
                 </li> {% endif %}
             {% if history_n > 0 %}
-                <li class="tab" id="text-tab"><a href="#text">Text</a></li>
-                <li class="tab" id="screenshot-tab"><a href="#screenshot">Screenshot</a></li>
+                <li class="tab" id="text-tab"><a href="#text">{{ _('Text') }}</a></li>
+                <li class="tab" id="screenshot-tab"><a href="#screenshot">{{ _('Current screenshot') }}</a></li>
             {% endif %}
         </ul>
     </div>
@@ -54,50 +56,39 @@
 
     <div id="diff-ui">
         <div class="tab-pane-inner" id="error-text">
-            <div class="snapshot-age error">{{ watch.error_text_ctime|format_seconds_ago }} seconds ago</div>
+            <div class="snapshot-age error">{{ watch.error_text_ctime|format_seconds_ago }} {{ _('seconds ago') }}</div>
             <pre>
             {{ last_error_text }}
         </pre>
         </div>
 
         <div class="tab-pane-inner" id="error-screenshot">
-            <div class="snapshot-age error">{{ watch.snapshot_error_screenshot_ctime|format_seconds_ago }} seconds ago
+            <div class="snapshot-age error">{{ watch.snapshot_error_screenshot_ctime|format_seconds_ago }} {{ _('seconds ago') }}
             </div>
             <img id="error-screenshot-img" style="max-width: 80%"
-                 alt="Current erroring screenshot from most recent request">
+                 alt="{{ _('Current erroring screenshot from most recent request') }}">
         </div>
 
         <div class="tab-pane-inner" id="text">
+            {{ highlight_trigger_ignored_explainer() }}
             <div class="snapshot-age">{{ current_version|format_timestamp_timeago }}</div>
-            <span class="tip"><strong>Pro-tip</strong>: Highlight text to add to ignore filters</span>
-
-            <table>
-                <tbody>
-                <tr>
-                    <td id="diff-col" class="highlightable-filter">
-                        <pre style="border-left: 2px solid #ddd;">
-{{ content }}
-                        </pre>
-                    </td>
-                </tr>
-                </tbody>
-            </table>
+            <pre id="difference" style="border-left: 2px solid #ddd;">{{ content| diff_unescape_difference_spans }}</pre>
         </div>
 
         <div class="tab-pane-inner" id="screenshot">
             <div class="tip">
-                For now, Differences are performed on text, not graphically, only the latest screenshot is available.
+                {{ _('For now, Differences are performed on text, not graphically, only the latest screenshot is available.') }}
             </div>
             <br>
-            {% if is_html_webdriver %}
+            {% if capabilities.supports_screenshots %}
                 {% if screenshot %}
                     <div class="snapshot-age">{{ watch.snapshot_screenshot_ctime|format_timestamp_timeago }}</div>
-                    <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request">
+                    <img style="max-width: 80%" id="screenshot-img" alt="{{ _('Current screenshot from most recent request') }}">
                 {% else %}
-                    No screenshot available just yet! Try rechecking the page.
+                    {{ _('No screenshot available just yet! Try rechecking the page.') }}
                 {% endif %}
             {% else %}
-                <strong>Screenshot requires Playwright/WebDriver enabled</strong>
+                <strong>{{ _('Screenshot requires a Content Fetcher ( Sockpuppetbrowser, selenium, etc ) that supports screenshots.') }}</strong>
             {% endif %}
         </div>
     </div>

changedetectionio/blueprint/ui/views.py

@@ -1,191 +1,12 @@
-from flask import Blueprint, request, redirect, url_for, flash, render_template, make_response, send_from_directory, abort
-from flask_login import current_user
-import os
-import time
-from copy import deepcopy
-
+from flask import Blueprint, request, redirect, url_for, flash
+from flask_babel import gettext
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
-from changedetectionio import html_tools
+from changedetectionio import worker_pool
 
-def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
+
+def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData, watch_check_update):
     views_blueprint = Blueprint('ui_views', __name__, template_folder="../ui/templates")
-    
-    @views_blueprint.route("/preview/<string:uuid>", methods=['GET'])
-    @login_optionally_required
-    def preview_page(uuid):
-        content = []
-        versions = []
-        timestamp = None
-
-        # More for testing, possible to return the first/only
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
-
-        try:
-            watch = datastore.data['watching'][uuid]
-        except KeyError:
-            flash("No history found for the specified link, bad link?", "error")
-            return redirect(url_for('watchlist.index'))
-
-        system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
-        extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
-
-        is_html_webdriver = False
-        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
-            is_html_webdriver = True
-        triggered_line_numbers = []
-        if datastore.data['watching'][uuid].history_n == 0 and (watch.get_error_text() or watch.get_error_snapshot()):
-            flash("Preview unavailable - No fetch/check completed or triggers not reached", "error")
-        else:
-            # So prepare the latest preview or not
-            preferred_version = request.args.get('version')
-            versions = list(watch.history.keys())
-            timestamp = versions[-1]
-            if preferred_version and preferred_version in versions:
-                timestamp = preferred_version
-
-            try:
-                versions = list(watch.history.keys())
-                content = watch.get_history_snapshot(timestamp)
-
-                triggered_line_numbers = html_tools.strip_ignore_text(content=content,
-                                                                      wordlist=watch['trigger_text'],
-                                                                      mode='line numbers'
-                                                                      )
-
-            except Exception as e:
-                content.append({'line': f"File doesnt exist or unable to read timestamp {timestamp}", 'classes': ''})
-
-        output = render_template("preview.html",
-                                 content=content,
-                                 current_version=timestamp,
-                                 history_n=watch.history_n,
-                                 extra_stylesheets=extra_stylesheets,
-                                 extra_title=f" - Diff - {watch.label} @ {timestamp}",
-                                 triggered_line_numbers=triggered_line_numbers,
-                                 current_diff_url=watch['url'],
-                                 screenshot=watch.get_screenshot(),
-                                 watch=watch,
-                                 uuid=uuid,
-                                 is_html_webdriver=is_html_webdriver,
-                                 last_error=watch['last_error'],
-                                 last_error_text=watch.get_error_text(),
-                                 last_error_screenshot=watch.get_error_snapshot(),
-                                 versions=versions
-                                )
-
-        return output
-
-    @views_blueprint.route("/diff/<string:uuid>", methods=['GET', 'POST'])
-    @login_optionally_required
-    def diff_history_page(uuid):
-        from changedetectionio import forms
-
-        # More for testing, possible to return the first/only
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
-
-        extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
-        try:
-            watch = datastore.data['watching'][uuid]
-        except KeyError:
-            flash("No history found for the specified link, bad link?", "error")
-            return redirect(url_for('watchlist.index'))
-
-        # For submission of requesting an extract
-        extract_form = forms.extractDataForm(request.form)
-        if request.method == 'POST':
-            if not extract_form.validate():
-                flash("An error occurred, please see below.", "error")
-
-            else:
-                extract_regex = request.form.get('extract_regex').strip()
-                output = watch.extract_regex_from_all_history(extract_regex)
-                if output:
-                    watch_dir = os.path.join(datastore.datastore_path, uuid)
-                    response = make_response(send_from_directory(directory=watch_dir, path=output, as_attachment=True))
-                    response.headers['Content-type'] = 'text/csv'
-                    response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
-                    response.headers['Pragma'] = 'no-cache'
-                    response.headers['Expires'] = 0
-                    return response
-
-                flash('Nothing matches that RegEx', 'error')
-                redirect(url_for('ui_views.diff_history_page', uuid=uuid)+'#extract')
-
-        history = watch.history
-        dates = list(history.keys())
-
-        if len(dates) < 2:
-            flash("Not enough saved change detection snapshots to produce a report.", "error")
-            return redirect(url_for('watchlist.index'))
-
-        # Save the current newest history as the most recently viewed
-        datastore.set_last_viewed(uuid, time.time())
-
-        # Read as binary and force decode as UTF-8
-        # Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
-        from_version = request.args.get('from_version')
-        from_version_index = -2  # second newest
-        if from_version and from_version in dates:
-            from_version_index = dates.index(from_version)
-        else:
-            from_version = dates[from_version_index]
-
-        try:
-            from_version_file_contents = watch.get_history_snapshot(dates[from_version_index])
-        except Exception as e:
-            from_version_file_contents = f"Unable to read to-version at index {dates[from_version_index]}.\n"
-
-        to_version = request.args.get('to_version')
-        to_version_index = -1
-        if to_version and to_version in dates:
-            to_version_index = dates.index(to_version)
-        else:
-            to_version = dates[to_version_index]
-
-        try:
-            to_version_file_contents = watch.get_history_snapshot(dates[to_version_index])
-        except Exception as e:
-            to_version_file_contents = "Unable to read to-version at index{}.\n".format(dates[to_version_index])
-
-        screenshot_url = watch.get_screenshot()
-
-        system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
-
-        is_html_webdriver = False
-        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
-            is_html_webdriver = True
-
-        password_enabled_and_share_is_off = False
-        if datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False):
-            password_enabled_and_share_is_off = not datastore.data['settings']['application'].get('shared_diff_access')
-
-        output = render_template("diff.html",
-                                 current_diff_url=watch['url'],
-                                 from_version=str(from_version),
-                                 to_version=str(to_version),
-                                 extra_stylesheets=extra_stylesheets,
-                                 extra_title=f" - Diff - {watch.label}",
-                                 extract_form=extract_form,
-                                 is_html_webdriver=is_html_webdriver,
-                                 last_error=watch['last_error'],
-                                 last_error_screenshot=watch.get_error_snapshot(),
-                                 last_error_text=watch.get_error_text(),
-                                 left_sticky=True,
-                                 newest=to_version_file_contents,
-                                 newest_version_timestamp=dates[-1],
-                                 password_enabled_and_share_is_off=password_enabled_and_share_is_off,
-                                 from_version_file_contents=from_version_file_contents,
-                                 to_version_file_contents=to_version_file_contents,
-                                 screenshot=screenshot_url,
-                                 uuid=uuid,
-                                 versions=dates, # All except current/last
-                                 watch_a=watch
-                                 )
-
-        return output
 
     @views_blueprint.route("/form/add/quickwatch", methods=['POST'])
     @login_optionally_required
@@ -200,21 +21,22 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
         url = request.form.get('url').strip()
         if datastore.url_exists(url):
-            flash(f'Warning, URL {url} already exists', "notice")
+            flash(gettext('Warning, URL {} already exists').format(url), "notice")
 
         add_paused = request.form.get('edit_and_watch_submit_button') != None
-        processor = request.form.get('processor', 'text_json_diff')
-        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tags').strip(), extras={'paused': add_paused, 'processor': processor})
+        from changedetectionio import processors
+        processor = request.form.get('processor', processors.get_default_processor())
+        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tags','').strip(), extras={'paused': add_paused, 'processor': processor})
 
         if new_uuid:
             if add_paused:
-                flash('Watch added in Paused state, saving will unpause.')
+                flash(gettext('Watch added in Paused state, saving will unpause.'))
                 return redirect(url_for('ui.ui_edit.edit_page', uuid=new_uuid, unpause_on_save=1, tag=request.args.get('tag')))
             else:
                 # Straight into the queue.
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
-                flash("Watch added.")
+                worker_pool.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
+                flash(gettext("Watch added."))
 
         return redirect(url_for('watchlist.index', tag=request.args.get('tag','')))
 
-    return views_blueprint
+    return views_blueprint

changedetectionio/blueprint/watchlist/__init__.py

@@ -2,10 +2,11 @@ import os
 import time
 
 from flask import Blueprint, request, make_response, render_template, redirect, url_for, flash, session
-from flask_login import current_user
 from flask_paginate import Pagination, get_page_parameter
+from flask_babel import gettext as _
 
 from changedetectionio import forms
+from changedetectionio import processors
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
 
@@ -38,18 +39,22 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             elif op == 'mute':
                 datastore.data['watching'][uuid].toggle_mute()
 
-            datastore.needs_write = True
+            datastore.data['watching'][uuid].commit()
             return redirect(url_for('watchlist.index', tag = active_tag_uuid))
 
         # Sort by last_changed and add the uuid which is usually the key..
         sorted_watches = []
         with_errors = request.args.get('with_errors') == "1"
+        unread_only = request.args.get('unread') == "1"
         errored_count = 0
         search_q = request.args.get('q').strip().lower() if request.args.get('q') else False
         for uuid, watch in datastore.data['watching'].items():
             if with_errors and not watch.get('last_error'):
                 continue
 
+            if unread_only and (watch.viewed or watch.last_changed == 0) :
+                continue
+
             if active_tag_uuid and not active_tag_uuid in watch['tags']:
                     continue
             if watch.get('last_error'):
@@ -69,34 +74,44 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
         pagination = Pagination(page=page,
                                 total=total_count,
-                                per_page=datastore.data['settings']['application'].get('pager_size', 50), css_framework="semantic")
+                                per_page=datastore.data['settings']['application'].get('pager_size', 50),
+                                css_framework="semantic",
+                                display_msg=_('displaying <b>{start} - {end}</b> {record_name} in total <b>{total}</b>'),
+                                record_name=_('records'))
 
         sorted_tags = sorted(datastore.data['settings']['application'].get('tags').items(), key=lambda x: x[1]['title'])
+
         output = render_template(
             "watch-overview.html",
-                                 active_tag=active_tag,
-                                 active_tag_uuid=active_tag_uuid,
-                                 app_rss_token=datastore.data['settings']['application'].get('rss_access_token'),
-                                 datastore=datastore,
-                                 errored_count=errored_count,
-                                 form=form,
-                                 guid=datastore.data['app_guid'],
-                                 has_proxies=datastore.proxy_list,
-                                 has_unviewed=datastore.has_unviewed,
-                                 hosted_sticky=os.getenv("SALTED_PASS", False) == False,
-                                 now_time_server=time.time(),
-                                 pagination=pagination,
-                                 queued_uuids=[q_uuid.item['uuid'] for q_uuid in update_q.queue],
-                                 search_q=request.args.get('q', '').strip(),
-                                 sort_attribute=request.args.get('sort') if request.args.get('sort') else request.cookies.get('sort'),
-                                 sort_order=request.args.get('order') if request.args.get('order') else request.cookies.get('order'),
-                                 system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),
-                                 tags=sorted_tags,
-                                 watches=sorted_watches
-                                 )
+            active_tag=active_tag,
+            active_tag_uuid=active_tag_uuid,
+            app_rss_token=datastore.data['settings']['application'].get('rss_access_token'),
+            datastore=datastore,
+            errored_count=errored_count,
+            extra_classes='has-queue' if not update_q.empty() else '',
+            form=form,
+            generate_tag_colors=processors.generate_processor_badge_colors,
+            guid=datastore.data['app_guid'],
+            has_proxies=datastore.proxy_list,
+            hosted_sticky=os.getenv("SALTED_PASS", False) == False,
+            now_time_server=round(time.time()),
+            pagination=pagination,
+            processor_badge_css=processors.get_processor_badge_css(),
+            processor_badge_texts=processors.get_processor_badge_texts(),
+            processor_descriptions=processors.get_processor_descriptions(),
+            queue_size=update_q.qsize(),
+            queued_uuids=update_q.get_queued_uuids(),
+            search_q=request.args.get('q', '').strip(),
+            sort_attribute=request.args.get('sort') if request.args.get('sort') else request.cookies.get('sort'),
+            sort_order=request.args.get('order') if request.args.get('order') else request.cookies.get('order'),
+            system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),
+            tags=sorted_tags,
+            unread_changes_count=datastore.unread_changes_count,
+            watches=sorted_watches
+        )
 
         if session.get('share-link'):
-            del(session['share-link'])
+            del (session['share-link'])
 
         resp = make_response(output)
 

changedetectionio/blueprint/watchlist/templates/watch-overview.html

@@ -1,10 +1,61 @@
-{% extends 'base.html' %}
-{% block content %}
-{% from '_helpers.html' import render_simple_field, render_field, render_nolabel_field, sort_by_title %}
+{%- extends 'base.html' -%}
+{%- block content -%}
+{%- set tips = [
+    _("Changedetection.io can monitor more than just web-pages! See our plugins!") ~ ' <a href="https://changedetection.io/plugins">' ~ _('More info') ~ '</a>',
+    _("You can also add 'shared' watches.") ~ ' <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">' ~ _('More info') ~ '</a>'
+] -%}
+{%- from '_helpers.html' import render_simple_field, render_field, render_nolabel_field, sort_by_title -%}
 <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
 <script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='modal.js')}}"></script>
 <script>let nowtimeserver={{ now_time_server }};</script>
+<script>let favicon_baseURL="{{ url_for('static_content', group='favicon', filename="PLACEHOLDER")}}";</script>
+<script>
+// Initialize Feather icons after the page loads
+document.addEventListener('DOMContentLoaded', function() {
+    feather.replace();
 
+    // Intersection Observer for lazy loading favicons
+    // Only load favicon images when they enter the viewport
+    if ('IntersectionObserver' in window) {
+        const faviconObserver = new IntersectionObserver((entries, observer) => {
+            entries.forEach(entry => {
+                if (entry.isIntersecting) {
+                    const img = entry.target;
+                    const src = img.getAttribute('data-src');
+
+                    if (src) {
+                        // Load the actual favicon
+                        img.src = src;
+                        img.removeAttribute('data-src');
+                    }
+
+                    // Stop observing this image
+                    observer.unobserve(img);
+                }
+            });
+        }, {
+            // Start loading slightly before the image enters viewport
+            rootMargin: '50px',
+            threshold: 0.01
+        });
+
+        // Observe all lazy favicon images
+        document.querySelectorAll('.lazy-favicon').forEach(img => {
+            faviconObserver.observe(img);
+        });
+    } else {
+        // Fallback for older browsers: load all favicons immediately
+        document.querySelectorAll('.lazy-favicon').forEach(img => {
+            const src = img.getAttribute('data-src');
+            if (src) {
+                img.src = src;
+                img.removeAttribute('data-src');
+            }
+        });
+    }
+});
+</script>
 <style>
 .checking-now .last-checked {
     background-image: linear-gradient(to bottom, transparent 0%, rgba(0,0,0,0.05) 40%, rgba(0,0,0,0.1) 100%);
@@ -12,236 +63,304 @@
     background-repeat: no-repeat;
     transition: background-size 0.9s ease
 }
+
+/* Auto-generated processor badge colors */
+{{ processor_badge_css|safe }}
+
+/* Auto-generated tag colors */
+{%- for uuid, tag in tags -%}
+{%- if tag and tag.title -%}
+{%- set class_name = tag.title|sanitize_tag_class -%}
+{%- set colors = generate_tag_colors(tag.title) -%}
+.button-tag.tag-{{ class_name }} {
+  background-color: {{ colors['light']['bg'] }};
+  color: {{ colors['light']['color'] }};
+}
+
+.watch-tag-list.tag-{{ class_name }} {
+  background-color: {{ colors['light']['bg'] }};
+  color: {{ colors['light']['color'] }};
+}
+
+html[data-darkmode="true"] .button-tag.tag-{{ class_name }} {
+  background-color: {{ colors['dark']['bg'] }};
+  color: {{ colors['dark']['color'] }};
+}
+
+html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
+  background-color: {{ colors['dark']['bg'] }};
+  color: {{ colors['dark']['color'] }};
+}
+{%- endif -%}
+{%- endfor -%}
 </style>
-<div class="box">
+<div class="box" id="form-quick-watch-add">
 
     <form class="pure-form" action="{{ url_for('ui.ui_views.form_quick_watch_add', tag=active_tag_uuid) }}" method="POST" id="new-watch-form">
         <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
         <fieldset>
-            <legend>Add a new change detection watch</legend>
+            <legend>{{ _('Add a new web page change detection watch') }}</legend>
             <div id="watch-add-wrapper-zone">
-
                     {{ render_nolabel_field(form.url, placeholder="https://...", required=true) }}
-                    {{ render_nolabel_field(form.tags, value=active_tag.title if active_tag_uuid else '', placeholder="watch label / tag") }}
-                    {{ render_nolabel_field(form.watch_submit_button, title="Watch this URL!" ) }}
-                    {{ render_nolabel_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
+                    {{ render_nolabel_field(form.watch_submit_button, title=_("Watch this URL!") ) }}
+                    {{ render_nolabel_field(form.edit_and_watch_submit_button, title=_("Edit first then Watch") ) }}
+            </div>
+            <div id="watch-group-tag">
+               {{ render_field(form.tags, value=active_tag.title if active_tag_uuid else '', placeholder=_("Watch group / tag"), class="transparent-field") }}
             </div>
             <div id="quick-watch-processor-type">
                 {{ render_simple_field(form.processor) }}
             </div>
 
         </fieldset>
-        <span style="color:#eee; font-size: 80%;"><img alt="Create a shareable link" style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" > Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></span>
+        <span style="color:#eee; font-size: 80%;">
+            <strong>Tip: </strong> {{ tips | random | safe }}
+        </span>
     </form>
-
+</div>
+<div class="box">
     <form class="pure-form" action="{{ url_for('ui.form_watch_list_checkbox_operations') }}" method="POST" id="watch-list-form">
     <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
     <input type="hidden" id="op_extradata" name="op_extradata" value="" >
     <div id="checkbox-operations">
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="pause">Pause</button>
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="unpause">UnPause</button>
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="mute">Mute</button>
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="unmute">UnMute</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="recheck">Recheck</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="assign-tag" id="checkbox-assign-tag">Tag</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="mark-viewed">Mark viewed</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default">Use default notification</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="clear-errors">Clear errors</button>
-        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="clear-history">Clear/reset history</button>
-        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="delete">Delete</button>
+        <button class="pure-button button-secondary button-xsmall"  name="op" value="pause"><i data-feather="pause" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('Pause') }}</button>
+        <button class="pure-button button-secondary button-xsmall"  name="op" value="unpause"><i data-feather="play" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('UnPause') }}</button>
+        <button class="pure-button button-secondary button-xsmall"  name="op" value="mute"><i data-feather="volume-x" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('Mute') }}</button>
+        <button class="pure-button button-secondary button-xsmall"  name="op" value="unmute"><i data-feather="volume-2" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('UnMute') }}</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="recheck"><i data-feather="refresh-cw" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('Recheck') }}</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="assign-tag" id="checkbox-assign-tag"><i data-feather="tag" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('Tag') }}</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="mark-viewed"><i data-feather="eye" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('Mark viewed') }}</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default"><i data-feather="bell" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('Use default notification') }}</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="clear-errors"><i data-feather="x-circle" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('Clear errors') }}</button>
+        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="clear-history"
+                       data-requires-confirm
+                       data-confirm-type="danger"
+                       data-confirm-title="{{ _('Clear Histories') }}"
+                       data-confirm-message="{{ _('<p>Are you sure you want to clear history for the selected items?</p><p>This action cannot be undone.</p>') }}"
+                       data-confirm-button="{{ _('OK') }}"><i data-feather="trash-2" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('Clear/reset history') }}</button>
+        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="delete"
+                       data-requires-confirm
+                       data-confirm-type="danger"
+                       data-confirm-title="{{ _('Delete Watches?') }}"
+                       data-confirm-message="{{ _('<p>Are you sure you want to delete the selected watches?</strong></p><p>This action cannot be undone.</p>') }}"
+                       data-confirm-button="{{ _('Delete') }}"><i data-feather="trash" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>{{ _('Delete') }}</button>
     </div>
-    {% if watches|length >= pagination.per_page %}
-        {{ pagination.info }}
-    {% endif %}
-    {% if search_q %}<div id="search-result-info">Searching "<strong><i>{{search_q}}</i></strong>"</div>{% endif %}
+
+    <div id="stats_row">
+        <div class="left">{%- if watches|length >= pagination.per_page -%}{{ pagination.info }}{%- endif -%}</div>
+        <div class="right" >{{ _('Queued size') }}: <span id="queue-size-int">{{ queue_size }}</span></div>
+    </div>
+
+
+
+    {%- if search_q -%}<div id="search-result-info">{{ _('Searching') }} "<strong><i>{{search_q}}</i></strong>"</div>{%- endif -%}
     <div>
-        <a href="{{url_for('watchlist.index')}}" class="pure-button button-tag {{'active' if not active_tag_uuid }}">All</a>
+        <a href="{{url_for('watchlist.index')}}" class="pure-button button-tag {{'active' if not active_tag_uuid }}">{{ _('All') }}</a>
 
     <!-- tag list -->
-    {% for uuid, tag in tags %}
-        {% if tag != "" %}
-            <a href="{{url_for('watchlist.index', tag=uuid) }}" class="pure-button button-tag {{'active' if active_tag_uuid == uuid }}">{{ tag.title }}</a>
-        {% endif %}
-    {% endfor %}
+    {%- for uuid, tag in tags -%}
+        {%- if tag != "" -%}
+            <a href="{{url_for('watchlist.index', tag=uuid) }}" class="pure-button button-tag tag-{{ tag.title|sanitize_tag_class }} {{'active' if active_tag_uuid == uuid }}">{{ tag.title }}</a>
+        {%- endif -%}
+    {%- endfor -%}
     </div>
 
-    {% set sort_order = sort_order or 'asc' %}
-    {% set sort_attribute = sort_attribute or 'last_changed'  %}
-    {% set pagination_page = request.args.get('page', 0) %}
-    {% set cols_required = 6 %}
-    {% set any_has_restock_price_processor = datastore.any_watches_have_processor_by_name("restock_diff") %}
-    {% if any_has_restock_price_processor %}
-        {% set cols_required = cols_required + 1 %}
-    {% endif %}
-
-    <div id="watch-table-wrapper">
-
-        <table class="pure-table pure-table-striped watch-table">
+    {%- set sort_order = sort_order or 'asc' -%}
+    {%- set sort_attribute = sort_attribute or 'last_changed'  -%}
+    {%- set pagination_page = request.args.get('page', 0) -%}
+    {%- set cols_required = 6 -%}
+    {%- set any_has_restock_price_processor = datastore.any_watches_have_processor_by_name("restock_diff") -%}
+    {%- if any_has_restock_price_processor -%}
+        {%- set cols_required = cols_required + 1 -%}
+    {%- endif -%}
+    {%- set ui_settings = datastore.data['settings']['application']['ui'] -%}
+    {%- set wrapper_classes = [
+        'has-unread-changes' if unread_changes_count else '',
+        'has-error' if errored_count else '',
+    ] -%}
+    <div id="watch-table-wrapper" class="{{ wrapper_classes | reject('equalto', '') | join(' ') }}">
+        {%- set table_classes = [
+            'favicon-enabled' if 'favicons_enabled' not in ui_settings or ui_settings['favicons_enabled'] else 'favicon-not-enabled',
+        ] -%}
+        <table class="pure-table pure-table-striped watch-table {{ table_classes | reject('equalto', '') | join(' ') }}">
             <thead>
             <tr>
-                {% set link_order = "desc" if sort_order  == 'asc' else "asc" %}
-                {% set arrow_span = "" %}
+                {%- set link_order = "desc" if sort_order  == 'asc' else "asc" -%}
+                {%- set arrow_span = "" -%}
                 <th><input style="vertical-align: middle" type="checkbox" id="check-all" > <a class="{{ 'active '+link_order if sort_attribute == 'date_created' else 'inactive' }}"  href="{{url_for('watchlist.index', sort='date_created', order=link_order, tag=active_tag_uuid)}}"># <span class='arrow {{link_order}}'></span></a></th>
-                <th class="empty-cell"></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('watchlist.index', sort='label', order=link_order, tag=active_tag_uuid)}}">Website <span class='arrow {{link_order}}'></span></a></th>
-             {% if any_has_restock_price_processor %}
-                <th>Restock &amp; Price</th>
-             {% endif %}
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('watchlist.index', sort='last_checked', order=link_order, tag=active_tag_uuid)}}"><span class="hide-on-mobile">Last</span> Checked <span class='arrow {{link_order}}'></span></a></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('watchlist.index', sort='last_changed', order=link_order, tag=active_tag_uuid)}}"><span class="hide-on-mobile">Last</span> Changed <span class='arrow {{link_order}}'></span></a></th>
+                <th>
+                    <a class="{{ 'active '+link_order if sort_attribute == 'paused' else 'inactive' }}" href="{{url_for('watchlist.index', sort='paused', order=link_order, tag=active_tag_uuid)}}"><i data-feather="pause" style="vertical-align: bottom; width: 14px; height: 14px;  margin-right: 4px;"></i><span class='arrow {{link_order}}'></span></a>
+                    &nbsp;
+                    <a class="{{ 'active '+link_order if sort_attribute == 'notification_muted' else 'inactive' }}" href="{{url_for('watchlist.index', sort='notification_muted', order=link_order, tag=active_tag_uuid)}}"><i data-feather="volume-2" style="vertical-align: bottom; width: 14px; height: 14px;  margin-right: 4px;"></i><span class='arrow {{link_order}}'></span></a>
+                </th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('watchlist.index', sort='label', order=link_order, tag=active_tag_uuid)}}">{{ _('Website') }} <span class='arrow {{link_order}}'></span></a></th>
+             {%- if any_has_restock_price_processor -%}
+                <th>{{ _('Restock & Price') }}</th>
+             {%- endif -%}
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('watchlist.index', sort='last_checked', order=link_order, tag=active_tag_uuid)}}"><span class="hide-on-mobile">{{ _('Last') }}</span> {{ _('Checked') }} <span class='arrow {{link_order}}'></span></a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('watchlist.index', sort='last_changed', order=link_order, tag=active_tag_uuid)}}"><span class="hide-on-mobile">{{ _('Last') }}</span> {{ _('Changed') }} <span class='arrow {{link_order}}'></span></a></th>
                 <th class="empty-cell"></th>
             </tr>
             </thead>
             <tbody>
-            {% if not watches|length %}
+            {%- if not watches|length -%}
             <tr>
-                <td colspan="{{ cols_required }}" style="text-wrap: wrap;">No website watches configured, please add a URL in the box above, or <a href="{{ url_for('imports.import_page')}}" >import a list</a>.</td>
+                <td colspan="{{ cols_required }}" style="text-wrap: wrap;">{{ _('No web page change detection watches configured, please add a URL in the box above, or') }} <a href="{{ url_for('imports.import_page')}}" >{{ _('import a list') }}</a>.</td>
             </tr>
-            {% endif %}
-            {% for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))|pagination_slice(skip=pagination.skip) %}
+            {%- endif -%}
 
-                {% set is_unviewed = watch.newest_history_key| int > watch.last_viewed and watch.history_n>=2 %}
-                {% set checking_now = is_checking_now(watch) %}
-            <tr id="{{ watch.uuid }}"
-                class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }} processor-{{ watch['processor'] }}
-                {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
-                {% if watch.last_notification_error is defined and watch.last_notification_error != False %}error{% endif %}
-                {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
-                {% if is_unviewed %}unviewed{% endif %}
-                {% if watch.has_restock_info %} has-restock-info {% if watch['restock']['in_stock'] %}in-stock{% else %}not-in-stock{% endif %} {% else %}no-restock-info{% endif %}
-                {% if watch.uuid in queued_uuids %}queued{% endif %}
-                {% if checking_now %}checking-now{% endif %}
-                ">
-                <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span>{{ loop.index+pagination.skip }}</span></td>
+            {%- for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))|pagination_slice(skip=pagination.skip) -%}
+                {%- set checking_now = is_checking_now(watch) -%}
+                {%- set history_n = watch.history_n -%}
+                {%- set favicon = watch.get_favicon_filename() -%}
+                {%- set system_use_url_watchlist = datastore.data['settings']['application']['ui'].get('use_page_title_in_list')  -%}
+                {#  Class settings mirrored in changedetectionio/static/js/realtime.js for the frontend #}
+                {%- set row_classes = [
+                    loop.cycle('pure-table-odd', 'pure-table-even'),
+                    'processor-' ~ watch['processor'],
+                    'has-error' if watch.compile_error_texts()|length > 2 else '',
+                    'paused' if watch.paused is defined and watch.paused != False else '',
+                    'unviewed' if watch.has_unviewed else '',
+                    'has-restock-info' if watch.has_restock_info else 'no-restock-info',
+                    'has-favicon' if favicon else '',
+                    'in-stock' if watch.has_restock_info and watch['restock']['in_stock'] else '',
+                    'not-in-stock' if watch.has_restock_info and not watch['restock']['in_stock'] else '',
+                    'queued' if watch.uuid in queued_uuids else '',
+                    'checking-now' if checking_now else '',
+                    'notification_muted' if watch.notification_muted else '',
+                    'single-history' if history_n == 1 else '',
+                    'multiple-history' if history_n >= 2 else '',
+                    'use-html-title' if system_use_url_watchlist else 'no-html-title',
+                ] -%}
+            <tr id="{{ watch.uuid }}" data-watch-uuid="{{ watch.uuid }}" class="{{ row_classes | reject('equalto', '') | join(' ') }}">
+                <td class="inline checkbox-uuid" ><div><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span class="counter-i">{{ loop.index+pagination.skip }}</span></div></td>
                 <td class="inline watch-controls">
-                    {% if not watch.paused %}
-                    <a class="state-off" href="{{url_for('watchlist.index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause" ></a>
-                    {% else %}
-                    <a class="state-on" href="{{url_for('watchlist.index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause" ></a>
-                    {% endif %}
-                    {% set mute_label = 'UnMute notification' if watch.notification_muted else 'Mute notification' %}
-                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('watchlist.index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="{{ mute_label }}" title="{{ mute_label }}" class="icon icon-mute" ></a>
-                </td>
-                <td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
-                    <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
-                    <a class="link-spread" href="{{url_for('ui.form_share_put_watch', uuid=watch.uuid)}}"><img src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" ></a>
-
-                    {% if watch.get_fetch_backend == "html_webdriver"
-                         or (  watch.get_fetch_backend == "system" and system_default_fetcher == 'html_webdriver'  )
-                         or "extra_browser_" in watch.get_fetch_backend
-                    %}
-                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='google-chrome-icon.png')}}" alt="Using a Chrome browser" title="Using a Chrome browser" >
-                    {% endif %}
-
-                    {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" >{% endif %}
-                    {% if watch.has_browser_steps %}<img class="status-icon status-browsersteps" src="{{url_for('static_content', group='images', filename='steps.svg')}}" title="Browser Steps is enabled" >{% endif %}
-                    {% if watch.last_error is defined and watch.last_error != False %}
-                    <div class="fetch-error">{{ watch.last_error }}
-
-                        {% if '403' in watch.last_error %}
-                            {% if has_proxies %}
-                                <a href="{{ url_for('settings.settings_page', uuid=watch.uuid) }}#proxies">Try other proxies/location</a>&nbsp;
-                            {% endif %}
-                            <a href="{{ url_for('settings.settings_page', uuid=watch.uuid) }}#proxies">Try adding external proxies/locations</a>
-                        
-                        {% endif %}
-                        {% if 'empty result or contain only an image' in watch.last_error %}
-                            <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Detecting-changes-in-images">more help here</a>.
-                        {% endif %}
+                    <div>
+                    <a class="ajax-op state-off pause-toggle" data-op="pause" href="{{url_for('watchlist.index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause" ></a>
+                    <a class="ajax-op state-on pause-toggle"  data-op="pause" style="display: none" href="{{url_for('watchlist.index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause" ></a>
+                    <a class="ajax-op state-off mute-toggle" data-op="mute" href="{{url_for('watchlist.index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notification" title="Mute notification" class="icon icon-mute" ></a>
+                    <a class="ajax-op state-on mute-toggle" data-op="mute"  style="display: none" href="{{url_for('watchlist.index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="UnMute notification" title="UnMute notification" class="icon icon-mute" ></a>
                     </div>
-                    {% endif %}
-                    {% if watch.last_notification_error is defined and watch.last_notification_error != False %}
-                    <div class="fetch-error notification-error"><a href="{{url_for('settings.notification_logs')}}">{{ watch.last_notification_error }}</a></div>
-                    {% endif %}
-
-                    {% if watch['processor'] == 'text_json_diff'  %}
-                        {% if watch['has_ldjson_price_data'] and not watch['track_ldjson_price_data']  %}
-                        <div class="ldjson-price-track-offer">Switch to Restock & Price watch mode? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
-                        {% endif %}
-                    {% endif %}
-                    {% if watch['processor'] == 'restock_diff' %}
-                        <span class="tracking-ldjson-price-data" title="Automatically following embedded price information"><img src="{{url_for('static_content', group='images', filename='price-tag-icon.svg')}}"  class="status-icon price-follow-tag-icon" > Price</span>
-                    {% endif %}
-                    {% for watch_tag_uuid, watch_tag in datastore.get_all_tags_for_watch(watch['uuid']).items() %}
-                      <span class="watch-tag-list">{{ watch_tag.title }}</span>
-                    {% endfor %}
                 </td>
-            <!-- @todo make it so any watch handler obj can expose this --->
-{% if any_has_restock_price_processor %}
-                <td class="restock-and-price">
-                    {% if watch['processor'] == 'restock_diff'  %}
-                        {% if watch.has_restock_info %}
-                            <span class="restock-label {{'in-stock' if watch['restock']['in_stock'] else 'not-in-stock' }}" title="Detecting restock and price">
-                                <!-- maybe some object watch['processor'][restock_diff] or.. -->
-                                 {% if watch['restock']['in_stock'] %} In stock {% else %} Not in stock {% endif %}
+
+                <td class="title-col inline">
+                    <div class="flex-wrapper">
+                    {% if 'favicons_enabled' not in ui_settings or ui_settings['favicons_enabled'] %}
+                        <div>
+                            {# Intersection Observer lazy loading: store real URL in data-src, load only when visible in viewport #}
+                            <img alt="Favicon thumbnail"
+                                 class="favicon lazy-favicon"
+                                 loading="lazy"
+                                 decoding="async"
+                                 fetchpriority="low"
+                                 {% if favicon %}
+                                 data-src="{{url_for('static_content', group='favicon', filename=watch.uuid)}}"
+                                 {% endif %}
+                                 src='data:image/svg+xml;utf8,%3Csvg xmlns="http://www.w3.org/2000/svg" width="7.087" height="7.087" viewBox="0 0 7.087 7.087"%3E%3Ccircle cx="3.543" cy="3.543" r="3.279" stroke="%23e1e1e1" stroke-width="0.45" fill="none" opacity="0.74"/%3E%3C/svg%3E'>
+                        </div>
+                    {%  endif %}
+                        <div>
+                            {%- if watch['processor'] and watch['processor'] in processor_badge_texts -%}
+                                <span class="processor-badge processor-badge-{{ watch['processor'] }}" title="{{ processor_descriptions.get(watch['processor'], watch['processor']) }}">{{ processor_badge_texts[watch['processor']] }}</span>
+                            {%- endif -%}
+                            <span class="watch-title">
+                                {% if system_use_url_watchlist or watch.get('use_page_title_in_list') %}
+                                    {{ watch.label }}
+                                {% else %}
+                                    {{ watch.get('title') or watch.link }}
+                                {% endif %}
+                               <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}">&nbsp;</a>
                             </span>
-                        {% endif %}
+                            <div class="error-text" style="display:none;">{{ watch.compile_error_texts(has_proxies=datastore.proxy_list)|safe }}</div>
+                            {%- if watch['processor'] == 'text_json_diff'  -%}
+                                {%- if watch['has_ldjson_price_data'] and not watch['track_ldjson_price_data']  -%}
+                                <div class="ldjson-price-track-offer">Switch to Restock & Price watch mode? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
+                                {%- endif -%}
+                            {%- endif -%}
 
-                        {% if watch.get('restock') and watch['restock']['price'] != None %}
-                            {% if watch['restock']['price'] != None %}
-                                <span class="restock-label price" title="Price">
-                                {{ watch['restock']['price']|format_number_locale }} {{ watch['restock']['currency'] }}
+                            {%- for watch_tag_uuid, watch_tag in datastore.get_all_tags_for_watch(watch['uuid']).items() -%}
+                              <a href="{{url_for('watchlist.index', tag=watch_tag_uuid) }}" class="watch-tag-list tag-{{ watch_tag.title|sanitize_tag_class }}">{{ watch_tag.title }}</a>
+                            {%- endfor -%}
+                        </div>
+                    <div class="status-icons">
+                            <a class="link-spread" href="{{url_for('ui.form_share_put_watch', uuid=watch.uuid)}}"><img src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" ></a>
+                            {%- set effective_fetcher = watch.get_fetch_backend if watch.get_fetch_backend != "system" else system_default_fetcher -%}
+                            {%- if effective_fetcher and ("html_webdriver" in effective_fetcher or "html_" in effective_fetcher or "extra_browser_" in effective_fetcher) -%}
+                                {{ effective_fetcher|fetcher_status_icons }}
+                            {%- endif -%}
+                            {%- if watch.is_pdf  -%}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" alt="Converting PDF to text" >{%- endif -%}
+                            {%- if watch.has_browser_steps -%}<img class="status-icon status-browsersteps" src="{{url_for('static_content', group='images', filename='steps.svg')}}" alt="Browser Steps is enabled" >{%- endif -%}
+
+                    </div>
+                    </div>
+                </td>
+{%- if any_has_restock_price_processor -%}
+                <td class="restock-and-price">
+                    {%- if watch['processor'] == 'restock_diff'  -%}
+                        {%- if watch.has_restock_info -%}
+                            <span class="restock-label {{'in-stock' if watch['restock']['in_stock'] else 'not-in-stock' }}" title="{{ _('Detecting restock and price') }}">
+                                <!-- maybe some object watch['processor'][restock_diff] or.. -->
+                                 {%- if watch['restock']['in_stock']-%}  {{ _('In stock') }} {%- else-%}  {{ _('Not in stock') }} {%- endif -%}
+                            </span>
+                        {%- endif -%}
+
+                        {%- if watch.get('restock') and watch['restock'].get('price') -%}
+                                {%- if watch['restock']['price'] is number -%}
+                                <span class="restock-label price" title="{{ _('Price') }}">
+                                {{ watch['restock']['price']|format_number_locale if watch['restock'].get('price') else '' }} {{ watch['restock'].get('currency','') }}
                                 </span>
-                            {% endif %}
-                        {% elif not watch.has_restock_info %}
-                            <span class="restock-label error">No information</span>
-                        {% endif %}
-                    {% endif %}
+                                {%- else -%} <!-- watch['restock']['price']' is not a number, cant output it -->
+                                {%- endif -%}
+                        {%- elif not watch.has_restock_info -%}
+                            <span class="restock-label error">{{ _('No information') }}</span>
+                        {%- endif -%}
+                    {%- endif -%}
                 </td>
-{% endif %}
+{%- endif -%}
             {#last_checked becomes fetch-start-time#}
-                <td class="last-checked" data-timestamp="{{ watch.last_checked }}" {% if checking_now %} data-fetchduration={{ watch.fetch_time }} data-eta_complete="{{ watch.last_checked+watch.fetch_time }}" {% endif %} >
-                    {% if checking_now %}
-                        <span class="spinner"></span><span> Checking now</span>
-                    {% else %}
-                        {{watch|format_last_checked_time|safe}}</td>
-                    {% endif %}
-
-                <td class="last-changed" data-timestamp="{{ watch.last_changed }}">{% if watch.history_n >=2 and watch.last_changed >0 %}
-                    {{watch.last_changed|format_timestamp_timeago}}
-                    {% else %}
-                    Not yet
-                    {% endif %}
+                <td class="last-checked" data-timestamp="{{ watch.last_checked }}" data-fetchduration={{ watch.fetch_time }} data-eta_complete="{{ watch.last_checked+watch.fetch_time }}" >
+                    <div class="spinner-wrapper" style="display:none;" >
+                        <span class="spinner"></span><span class="status-text">&nbsp;{{ _('Checking now') }}</span>
+                    </div>
+                    <span class="innertext">{{watch|format_last_checked_time|safe}}</span>
                 </td>
-                <td>
-                    <a {% if watch.uuid in queued_uuids %}disabled="true"{% endif %} href="{{ url_for('ui.form_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}"
-                       class="recheck pure-button pure-button-primary">{% if watch.uuid in queued_uuids %}Queued{% else %}Recheck{% endif %}</a>
-                    <a href="{{ url_for('ui.ui_edit.edit_page', uuid=watch.uuid, tag=active_tag_uuid)}}#general" class="pure-button pure-button-primary">Edit</a>
-                    {% if watch.history_n >= 2 %}
-
-                        {% set open_diff_in_new_tab = datastore.data['settings']['application']['ui'].get('open_diff_in_new_tab') %}
-                        {% set target_attr = ' target="' ~ watch.uuid ~ '"' if open_diff_in_new_tab else '' %}
-
-                        {%  if is_unviewed %}
-                           <a href="{{ url_for('ui.ui_views.diff_history_page', uuid=watch.uuid, from_version=watch.get_from_version_based_on_last_viewed) }}" {{target_attr}} class="pure-button pure-button-primary diff-link">History</a>
-                        {% else %}
-                           <a href="{{ url_for('ui.ui_views.diff_history_page', uuid=watch.uuid)}}" {{target_attr}} class="pure-button pure-button-primary diff-link">History</a>
-                        {% endif %}
-
-                    {% else %}
-                        {% if watch.history_n == 1 or (watch.history_n ==0 and watch.error_text_ctime )%}
-                            <a href="{{ url_for('ui.ui_views.preview_page', uuid=watch.uuid)}}" {{target_attr}} class="pure-button pure-button-primary">Preview</a>
-                        {% endif %}
-                    {% endif %}
+                <td class="last-changed" data-timestamp="{{ watch.last_changed }}">{%- if watch.history_n >=2 and watch.last_changed >0 -%}
+                    {{watch.last_changed|format_timestamp_timeago}}
+                    {%- else -%}
+                    {{ _('Not yet') }}
+                    {%- endif -%}
+                </td>
+                <td class="buttons">
+                    <div>
+                    {%- set target_attr = ' target="' ~ watch.uuid ~ '"' if datastore.data['settings']['application']['ui'].get('open_diff_in_new_tab') else '' -%}
+                    <a href="" class="already-in-queue-button recheck pure-button pure-button-primary" style="display: none;" disabled="disabled">{{ _('Queued') }}</a>
+                    <a href="{{ url_for('ui.form_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}" data-op='recheck' class="ajax-op recheck pure-button pure-button-primary">{{ _('Recheck') }}</a>
+                    <a href="{{ url_for('ui.ui_edit.edit_page', uuid=watch.uuid, tag=active_tag_uuid)}}#general" class="pure-button pure-button-primary">{{ _('Edit') }}</a>
+                    <a href="{{ url_for('ui.ui_diff.diff_history_page', uuid=watch.uuid)}}" {{target_attr}} class="pure-button pure-button-primary history-link" style="display: none;">{{ _('History') }}</a>
+                    <a href="{{ url_for('ui.ui_preview.preview_page', uuid=watch.uuid)}}" {{target_attr}} class="pure-button pure-button-primary preview-link" style="display: none;">{{ _('Preview') }}</a>
+                    </div>
                 </td>
             </tr>
-            {% endfor %}
+            {%- endfor -%}
             </tbody>
         </table>
         <ul id="post-list-buttons">
-            {% if errored_count %}
-            <li>
-                <a href="{{url_for('watchlist.index', with_errors=1, tag=request.args.get('tag')) }}" class="pure-button button-tag button-error ">With errors ({{ errored_count }})</a>
+            <li id="post-list-with-errors" style="display: none;" >
+                <a href="{{url_for('watchlist.index', with_errors=1, tag=request.args.get('tag')) }}" class="pure-button button-tag button-error">{{ _('With errors') }} ({{ errored_count }})</a>
             </li>
-            {% endif %}
-            {% if has_unviewed %}
-            <li>
-                <a href="{{url_for('ui.mark_all_viewed',with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Mark all viewed</a>
+            <li id="post-list-mark-views" style="display: none;" >
+                <a href="{{url_for('ui.mark_all_viewed',with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag " id="mark-all-viewed">{{ _('Mark all viewed') }}</a>
+            </li>
+        {%-  if active_tag_uuid -%}
+            <li id="post-list-mark-views-tag">
+                <a href="{{url_for('ui.mark_all_viewed', tag=active_tag_uuid) }}" class="pure-button button-tag " id="mark-all-viewed">{{ _("Mark all viewed in '%(title)s'", title=active_tag.title) }}</a>
+            </li>
+        {%-  endif -%}
+            <li id="post-list-unread" style="display: none;" >
+                <a href="{{url_for('watchlist.index', unread=1, tag=request.args.get('tag')) }}" class="pure-button button-tag">{{ _('Unread') }} (<span id="unread-tab-counter">{{ unread_changes_count }}</span>)</a>
             </li>
-            {% endif %}
             <li>
-               <a href="{{ url_for('ui.form_watch_checknow', tag=active_tag_uuid, with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Recheck
-                all {% if active_tag_uuid %} in "{{active_tag.title}}"{%endif%}</a>
+               <a href="{{ url_for('ui.form_watch_checknow', tag=active_tag_uuid, with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag" id="recheck-all">{{ _('Recheck all') }} {% if active_tag_uuid %}  {{ _("in '%(title)s'", title=active_tag.title) }}{%endif%}</a>
             </li>
             <li>
                 <a href="{{ url_for('rss.feed', tag=active_tag_uuid, token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='generic_feed-icon.svg')}}" height="15"></a>
@@ -251,4 +370,4 @@
     </div>
     </form>
 </div>
-{% endblock %}
+{%- endblock -%}

changedetectionio/browser_steps/browser_steps.py

@@ -1,15 +1,24 @@
 import os
 import time
 import re
-import sys
-import traceback
 from random import randint
 from loguru import logger
 
 from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT
 from changedetectionio.content_fetchers.base import manage_user_agent
-from changedetectionio.safe_jinja import render as jinja_render
+from changedetectionio.jinja2_custom import render as jinja_render
 
+def browser_steps_get_valid_steps(browser_steps: list):
+    if browser_steps is not None and len(browser_steps):
+        valid_steps = list(filter(
+            lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one'),browser_steps))
+
+        # Just incase they selected Goto site by accident with older JS
+        if valid_steps and valid_steps[0]['operation'] == 'Goto site':
+            del(valid_steps[0])
+
+        return valid_steps
+    return []
 
 
 # Two flags, tell the JS which of the "Selector" or "Value" field should be enabled in the front end
@@ -61,26 +70,9 @@ class steppable_browser_interface():
 
     def __init__(self, start_url):
         self.start_url = start_url
-        
-    def safe_page_operation(self, operation_fn, default_return=None):
-        """Safely execute a page operation with error handling"""
-        if self.page is None:
-            logger.warning("Attempted operation on None page object")
-            return default_return
-            
-        try:
-            return operation_fn()
-        except Exception as e:
-            logger.debug(f"Page operation failed: {str(e)}")
-            # Try to reclaim memory if possible
-            try:
-                self.page.request_gc()
-            except:
-                pass
-            return default_return
 
     # Convert and perform "Click Button" for example
-    def call_action(self, action_name, selector=None, optional_value=None):
+    async def call_action(self, action_name, selector=None, optional_value=None):
         if self.page is None:
             logger.warning("Cannot call action on None page object")
             return
@@ -109,110 +101,107 @@ class steppable_browser_interface():
         if optional_value and ('{%' in optional_value or '{{' in optional_value):
             optional_value = jinja_render(template_str=optional_value)
 
-        try:
-            action_handler(selector, optional_value)
-            # Safely wait for timeout
-            def wait_timeout():
-                self.page.wait_for_timeout(1.5 * 1000)
-            self.safe_page_operation(wait_timeout)
-            logger.debug(f"Call action done in {time.time()-now:.2f}s")
-        except Exception as e:
-            logger.error(f"Error executing action '{call_action_name}': {str(e)}")
-            # Request garbage collection to free up resources after error
+        # Trigger click and cautiously handle potential navigation
+        # This means the page redirects/reloads/changes JS etc etc
+        if call_action_name.startswith('click_'):
             try:
-                self.page.request_gc()
-            except:
-                pass
+                # Set up navigation expectation before the click (like sync version)
+                async with self.page.expect_event("framenavigated", timeout=3000) as navigation_info:
+                    await action_handler(selector, optional_value)
+                
+                # Check if navigation actually occurred
+                try:
+                    await navigation_info.value  # This waits for the navigation promise
+                    logger.debug(f"Navigation occurred on {call_action_name}.")
+                except Exception:
+                    logger.debug(f"No navigation occurred within timeout when calling {call_action_name}, that's OK, continuing.")
+                    
+            except Exception as e:
+                # If expect_event itself times out, that means no navigation occurred - that's OK
+                if "framenavigated" in str(e) and "exceeded" in str(e):
+                    logger.debug(f"No navigation occurred within timeout when calling {call_action_name}, that's OK, continuing.")
+                else:
+                    raise e
+        else:
+            # Some other action that probably a navigation is not expected
+            await action_handler(selector, optional_value)
 
-    def action_goto_url(self, selector=None, value=None):
+
+        # Safely wait for timeout
+        await self.page.wait_for_timeout(1.5 * 1000)
+        logger.debug(f"Call action done in {time.time()-now:.2f}s")
+
+    async def action_goto_url(self, selector=None, value=None):
         if not value:
             logger.warning("No URL provided for goto_url action")
             return None
             
         now = time.time()
-        
-        def goto_operation():
-            return self.page.goto(value, timeout=0, wait_until='load')
-            
-        response = self.safe_page_operation(goto_operation)
+        response = await self.page.goto(value, timeout=0, wait_until='load')
         logger.debug(f"Time to goto URL {time.time()-now:.2f}s")
         return response
 
     # Incase they request to go back to the start
-    def action_goto_site(self, selector=None, value=None):
-        return self.action_goto_url(value=self.start_url)
+    async def action_goto_site(self, selector=None, value=None):
+        return await self.action_goto_url(value=re.sub(r'^source:', '', self.start_url, flags=re.IGNORECASE))
 
-    def action_click_element_containing_text(self, selector=None, value=''):
+    async def action_click_element_containing_text(self, selector=None, value=''):
         logger.debug("Clicking element containing text")
         if not value or not len(value.strip()):
             return
             
-        def click_operation():
-            elem = self.page.get_by_text(value)
-            if elem.count():
-                elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
-                
-        self.safe_page_operation(click_operation)
+        elem = self.page.get_by_text(value)
+        if await elem.count():
+            await elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
 
-    def action_click_element_containing_text_if_exists(self, selector=None, value=''):
+
+    async def action_click_element_containing_text_if_exists(self, selector=None, value=''):
         logger.debug("Clicking element containing text if exists")
         if not value or not len(value.strip()):
             return
             
-        def click_if_exists_operation():
-            elem = self.page.get_by_text(value)
-            logger.debug(f"Clicking element containing text - {elem.count()} elements found")
-            if elem.count():
-                elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
+        elem = self.page.get_by_text(value)
+        count = await elem.count()
+        logger.debug(f"Clicking element containing text - {count} elements found")
+        if count:
+            await elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
                 
-        self.safe_page_operation(click_if_exists_operation)
 
-    def action_enter_text_in_field(self, selector, value):
+    async def action_enter_text_in_field(self, selector, value):
         if not selector or not len(selector.strip()):
             return
 
-        def fill_operation():
-            self.page.fill(selector, value, timeout=self.action_timeout)
-            
-        self.safe_page_operation(fill_operation)
+        await self.page.fill(selector, value, timeout=self.action_timeout)
 
-    def action_execute_js(self, selector, value):
+    async def action_execute_js(self, selector, value):
         if not value:
             return None
             
-        def evaluate_operation():
-            return self.page.evaluate(value)
-            
-        return self.safe_page_operation(evaluate_operation)
+        return await self.page.evaluate(value)
 
-    def action_click_element(self, selector, value):
+    async def action_click_element(self, selector, value):
         logger.debug("Clicking element")
         if not selector or not len(selector.strip()):
             return
 
-        def click_operation():
-            self.page.click(selector=selector, timeout=self.action_timeout + 20 * 1000, delay=randint(200, 500))
-            
-        self.safe_page_operation(click_operation)
+        await self.page.click(selector=selector, timeout=self.action_timeout + 20 * 1000, delay=randint(200, 500))
 
-    def action_click_element_if_exists(self, selector, value):
+    async def action_click_element_if_exists(self, selector, value):
         import playwright._impl._errors as _api_types
         logger.debug("Clicking element if exists")
         if not selector or not len(selector.strip()):
             return
             
-        def click_if_exists_operation():
-            try:
-                self.page.click(selector, timeout=self.action_timeout, delay=randint(200, 500))
-            except _api_types.TimeoutError:
-                return
-            except _api_types.Error:
-                # Element was there, but page redrew and now its long long gone
-                return
+        try:
+            await self.page.click(selector, timeout=self.action_timeout, delay=randint(200, 500))
+        except _api_types.TimeoutError:
+            return
+        except _api_types.Error:
+            # Element was there, but page redrew and now its long long gone
+            return
                 
-        self.safe_page_operation(click_if_exists_operation)
 
-    def action_click_x_y(self, selector, value):
+    async def action_click_x_y(self, selector, value):
         if not value or not re.match(r'^\s?\d+\s?,\s?\d+\s?$', value):
             logger.warning("'Click X,Y' step should be in the format of '100 , 90'")
             return
@@ -222,57 +211,42 @@ class steppable_browser_interface():
             x = int(float(x.strip()))
             y = int(float(y.strip()))
             
-            def click_xy_operation():
-                self.page.mouse.click(x=x, y=y, delay=randint(200, 500))
+            await self.page.mouse.click(x=x, y=y, delay=randint(200, 500))
                 
-            self.safe_page_operation(click_xy_operation)
         except Exception as e:
             logger.error(f"Error parsing x,y coordinates: {str(e)}")
 
-    def action__select_by_option_text(self, selector, value):
+    async def action__select_by_option_text(self, selector, value):
         if not selector or not len(selector.strip()):
             return
 
-        def select_operation():
-            self.page.select_option(selector, label=value, timeout=self.action_timeout)
+        await self.page.select_option(selector, label=value, timeout=self.action_timeout)
 
-        self.safe_page_operation(select_operation)
+    async def action_scroll_down(self, selector, value):
+        # Some sites this doesnt work on for some reason
+        await self.page.mouse.wheel(0, 600)
+        await self.page.wait_for_timeout(1000)
 
-    def action_scroll_down(self, selector, value):
-        def scroll_operation():
-            # Some sites this doesnt work on for some reason
-            self.page.mouse.wheel(0, 600)
-            self.page.wait_for_timeout(1000)
-            
-        self.safe_page_operation(scroll_operation)
-
-    def action_wait_for_seconds(self, selector, value):
+    async def action_wait_for_seconds(self, selector, value):
         try:
             seconds = float(value.strip()) if value else 1.0
-            
-            def wait_operation():
-                self.page.wait_for_timeout(seconds * 1000)
-                
-            self.safe_page_operation(wait_operation)
+            await self.page.wait_for_timeout(seconds * 1000)
         except (ValueError, TypeError) as e:
             logger.error(f"Invalid value for wait_for_seconds: {str(e)}")
 
-    def action_wait_for_text(self, selector, value):
+    async def action_wait_for_text(self, selector, value):
         if not value:
             return
             
         import json
         v = json.dumps(value)
-        
-        def wait_for_text_operation():
-            self.page.wait_for_function(
-                f'document.querySelector("body").innerText.includes({v});', 
-                timeout=30000
-            )
+        await self.page.wait_for_function(
+            f'document.querySelector("body").innerText.includes({v});',
+            timeout=30000
+        )
             
-        self.safe_page_operation(wait_for_text_operation)
 
-    def action_wait_for_text_in_element(self, selector, value):
+    async def action_wait_for_text_in_element(self, selector, value):
         if not selector or not value:
             return
             
@@ -280,82 +254,60 @@ class steppable_browser_interface():
         s = json.dumps(selector)
         v = json.dumps(value)
         
-        def wait_for_text_in_element_operation():
-            self.page.wait_for_function(
-                f'document.querySelector({s}).innerText.includes({v});', 
-                timeout=30000
-            )
-            
-        self.safe_page_operation(wait_for_text_in_element_operation)
+        await self.page.wait_for_function(
+            f'document.querySelector({s}).innerText.includes({v});',
+            timeout=30000
+        )
 
     # @todo - in the future make some popout interface to capture what needs to be set
     # https://playwright.dev/python/docs/api/class-keyboard
-    def action_press_enter(self, selector, value):
-        def press_operation():
-            self.page.keyboard.press("Enter", delay=randint(200, 500))
+    async def action_press_enter(self, selector, value):
+        await self.page.keyboard.press("Enter", delay=randint(200, 500))
             
-        self.safe_page_operation(press_operation)
 
-    def action_press_page_up(self, selector, value):
-        def press_operation():
-            self.page.keyboard.press("PageUp", delay=randint(200, 500))
-            
-        self.safe_page_operation(press_operation)
+    async def action_press_page_up(self, selector, value):
+        await self.page.keyboard.press("PageUp", delay=randint(200, 500))
 
-    def action_press_page_down(self, selector, value):
-        def press_operation():
-            self.page.keyboard.press("PageDown", delay=randint(200, 500))
-            
-        self.safe_page_operation(press_operation)
+    async def action_press_page_down(self, selector, value):
+        await self.page.keyboard.press("PageDown", delay=randint(200, 500))
 
-    def action_check_checkbox(self, selector, value):
+    async def action_check_checkbox(self, selector, value):
+        if not selector:
+            return
+
+        await self.page.locator(selector).check(timeout=self.action_timeout)
+
+    async def action_uncheck_checkbox(self, selector, value):
         if not selector:
             return
             
-        def check_operation():
-            self.page.locator(selector).check(timeout=self.action_timeout)
+        await self.page.locator(selector).uncheck(timeout=self.action_timeout)
             
-        self.safe_page_operation(check_operation)
 
-    def action_uncheck_checkbox(self, selector, value):
-        if not selector:
-            return
-            
-        def uncheck_operation():
-            self.page.locator(selector).uncheck(timeout=self.action_timeout)
-            
-        self.safe_page_operation(uncheck_operation)
-
-    def action_remove_elements(self, selector, value):
+    async def action_remove_elements(self, selector, value):
         """Removes all elements matching the given selector from the DOM."""
         if not selector:
             return
             
-        def remove_operation():
-            self.page.locator(selector).evaluate_all("els => els.forEach(el => el.remove())")
-            
-        self.safe_page_operation(remove_operation)
+        await self.page.locator(selector).evaluate_all("els => els.forEach(el => el.remove())")
 
-    def action_make_all_child_elements_visible(self, selector, value):
+    async def action_make_all_child_elements_visible(self, selector, value):
         """Recursively makes all child elements inside the given selector fully visible."""
         if not selector:
             return
             
-        def make_visible_operation():
-            self.page.locator(selector).locator("*").evaluate_all("""
-                els => els.forEach(el => {
-                    el.style.display = 'block';   // Forces it to be displayed
-                    el.style.visibility = 'visible';   // Ensures it's not hidden
-                    el.style.opacity = '1';   // Fully opaque
-                    el.style.position = 'relative';   // Avoids 'absolute' hiding
-                    el.style.height = 'auto';   // Expands collapsed elements
-                    el.style.width = 'auto';   // Ensures full visibility
-                    el.removeAttribute('hidden');   // Removes hidden attribute
-                    el.classList.remove('hidden', 'd-none');  // Removes common CSS hidden classes
-                })
-            """)
-            
-        self.safe_page_operation(make_visible_operation)
+        await self.page.locator(selector).locator("*").evaluate_all("""
+            els => els.forEach(el => {
+                el.style.display = 'block';   // Forces it to be displayed
+                el.style.visibility = 'visible';   // Ensures it's not hidden
+                el.style.opacity = '1';   // Fully opaque
+                el.style.position = 'relative';   // Avoids 'absolute' hiding
+                el.style.height = 'auto';   // Expands collapsed elements
+                el.style.width = 'auto';   // Ensures full visibility
+                el.removeAttribute('hidden');   // Removes hidden attribute
+                el.classList.remove('hidden', 'd-none');  // Removes common CSS hidden classes
+            })
+        """)
 
 # Responsible for maintaining a live 'context' with the chrome CDP
 # @todo - how long do contexts live for anyway?
@@ -389,21 +341,22 @@ class browsersteps_live_ui(steppable_browser_interface):
         self.playwright_browser = playwright_browser
         self.start_url = start_url
         self._is_cleaned_up = False
-        if self.context is None:
-            self.connect(proxy=proxy)
+        self.proxy = proxy
+        # Note: connect() is now async and must be called separately
 
     def __del__(self):
         # Ensure cleanup happens if object is garbage collected
-        self.cleanup()
+        # Note: cleanup is now async, so we can only mark as cleaned up here
+        self._is_cleaned_up = True
 
     # Connect and setup a new context
-    def connect(self, proxy=None):
+    async def connect(self, proxy=None):
         # Should only get called once - test that
         keep_open = 1000 * 60 * 5
         now = time.time()
 
         # @todo handle multiple contexts, bind a unique id from the browser on each req?
-        self.context = self.playwright_browser.new_context(
+        self.context = await self.playwright_browser.new_context(
             accept_downloads=False,  # Should never be needed
             bypass_csp=True,  # This is needed to enable JavaScript execution on GitHub and others
             extra_http_headers=self.headers,
@@ -414,7 +367,7 @@ class browsersteps_live_ui(steppable_browser_interface):
             user_agent=manage_user_agent(headers=self.headers),
         )
 
-        self.page = self.context.new_page()
+        self.page = await self.context.new_page()
 
         # self.page.set_default_navigation_timeout(keep_open)
         self.page.set_default_timeout(keep_open)
@@ -424,13 +377,15 @@ class browsersteps_live_ui(steppable_browser_interface):
         self.page.on("console", lambda msg: print(f"Browser steps console - {msg.type}: {msg.text} {msg.args}"))
 
         logger.debug(f"Time to browser setup {time.time()-now:.2f}s")
-        self.page.wait_for_timeout(1 * 1000)
+        await self.page.wait_for_timeout(1 * 1000)
 
     def mark_as_closed(self):
         logger.debug("Page closed, cleaning up..")
-        self.cleanup()
+        # Note: This is called from a sync context (event handler)
+        # so we'll just mark as cleaned up and let __del__ handle the rest
+        self._is_cleaned_up = True
 
-    def cleanup(self):
+    async def cleanup(self):
         """Properly clean up all resources to prevent memory leaks"""
         if self._is_cleaned_up:
             return
@@ -441,7 +396,7 @@ class browsersteps_live_ui(steppable_browser_interface):
         if hasattr(self, 'page') and self.page is not None:
             try:
                 # Force garbage collection before closing
-                self.page.request_gc()
+                await self.page.request_gc()
             except Exception as e:
                 logger.debug(f"Error during page garbage collection: {str(e)}")
                 
@@ -452,7 +407,7 @@ class browsersteps_live_ui(steppable_browser_interface):
                 logger.debug(f"Error removing event listeners: {str(e)}")
                 
             try:
-                self.page.close()
+                await self.page.close()
             except Exception as e:
                 logger.debug(f"Error closing page: {str(e)}")
             
@@ -461,7 +416,7 @@ class browsersteps_live_ui(steppable_browser_interface):
         # Clean up context
         if hasattr(self, 'context') and self.context is not None:
             try:
-                self.context.close()
+                await self.context.close()
             except Exception as e:
                 logger.debug(f"Error closing context: {str(e)}")
             
@@ -483,44 +438,47 @@ class browsersteps_live_ui(steppable_browser_interface):
             
         return False
 
-    def get_current_state(self):
+    async def get_current_state(self):
         """Return the screenshot and interactive elements mapping, generally always called after action_()"""
         import importlib.resources
         import json
         # because we for now only run browser steps in playwright mode (not puppeteer mode)
-        from changedetectionio.content_fetchers.playwright import capture_full_page
+        from changedetectionio.content_fetchers.playwright import capture_full_page_async
 
         # Safety check - don't proceed if resources are cleaned up
         if self._is_cleaned_up or self.page is None:
             logger.warning("Attempted to get current state after cleanup")
             return (None, None)
 
-        xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text()
+        xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text(encoding="utf-8")
 
         now = time.time()
-        self.page.wait_for_timeout(1 * 1000)
+        await self.page.wait_for_timeout(1 * 1000)
 
         screenshot = None
         xpath_data = None
         
         try:
             # Get screenshot first
-            screenshot = capture_full_page(page=self.page)
+            screenshot = await capture_full_page_async(page=self.page)
+            if not screenshot:
+                logger.error("No screenshot was retrieved :((")
+
             logger.debug(f"Time to get screenshot from browser {time.time() - now:.2f}s")
 
             # Then get interactive elements
             now = time.time()
-            self.page.evaluate("var include_filters=''")
-            self.page.request_gc()
+            await self.page.evaluate("var include_filters=''")
+            await self.page.request_gc()
 
             scan_elements = 'a,button,input,select,textarea,i,th,td,p,li,h1,h2,h3,h4,div,span'
 
             MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
-            xpath_data = json.loads(self.page.evaluate(xpath_element_js, {
+            xpath_data = json.loads(await self.page.evaluate(xpath_element_js, {
                 "visualselector_xpath_selectors": scan_elements,
                 "max_height": MAX_TOTAL_HEIGHT
             }))
-            self.page.request_gc()
+            await self.page.request_gc()
 
             # Sort elements by size
             xpath_data['size_pos'] = sorted(xpath_data['size_pos'], key=lambda k: k['width'] * k['height'], reverse=True)
@@ -528,15 +486,21 @@ class browsersteps_live_ui(steppable_browser_interface):
             
         except Exception as e:
             logger.error(f"Error getting current state: {str(e)}")
+            # If the page has navigated (common with logins) then the context is destroyed on navigation, continue
+            # I'm not sure that this is required anymore because we have the "expect navigation wrapper" at the top
+            if "Execution context was destroyed" in str(e):
+                logger.debug("Execution context was destroyed, most likely because of navigation, continuing...")
+            pass
+
             # Attempt recovery - force garbage collection
             try:
-                self.page.request_gc()
+                await self.page.request_gc()
             except:
                 pass
         
         # Request garbage collection one final time
         try:
-            self.page.request_gc()
+            await self.page.request_gc()
         except:
             pass
             

changedetectionio/conditions/__init__.py

@@ -1,5 +1,3 @@
-from flask import Blueprint
-
 from json_logic.builtins import BUILTINS
 
 from .exceptions import EmptyConditionRuleRowNotUsable
@@ -16,7 +14,6 @@ operator_choices = [
     ("==", "Equals"),
     ("!=", "Not Equals"),
     ("in", "Contains"),
-    ("!in", "Does Not Contain"),
 ]
 
 # Fields available in the rules

changedetectionio/conditions/default_plugin.py

@@ -21,17 +21,21 @@ def register_operators():
     def length_max(_, text, strlen):
         return len(text) <= int(strlen)
 
-    # ✅ Custom function for case-insensitive regex matching
+    # Custom function for case-insensitive regex matching
     def contains_regex(_, text, pattern):
         """Returns True if `text` contains `pattern` (case-insensitive regex match)."""
         return bool(re.search(pattern, str(text), re.IGNORECASE))
 
-    # ✅ Custom function for NOT matching case-insensitive regex
+    # Custom function for NOT matching case-insensitive regex
     def not_contains_regex(_, text, pattern):
         """Returns True if `text` does NOT contain `pattern` (case-insensitive regex match)."""
         return not bool(re.search(pattern, str(text), re.IGNORECASE))
 
+    def not_contains(_, text, pattern):
+        return not pattern in text
+
     return {
+        "!in": not_contains,
         "!contains_regex": not_contains_regex,
         "contains_regex": contains_regex,
         "ends_with": ends_with,
@@ -43,6 +47,7 @@ def register_operators():
 @hookimpl
 def register_operator_choices():
     return [
+        ("!in", "Does NOT Contain"),
         ("starts_with", "Text Starts With"),
         ("ends_with", "Text Ends With"),
         ("length_min", "Length minimum"),

changedetectionio/conditions/plugins/levenshtein_plugin.py

@@ -1,6 +1,12 @@
+"""
+Levenshtein distance and similarity plugin for text change detection.
+Provides metrics for measuring text similarity between snapshots.
+"""
 import pluggy
 from loguru import logger
 
+LEVENSHTEIN_MAX_LEN_FOR_EDIT_STATS=100000
+
 # Support both plugin systems
 conditions_hookimpl = pluggy.HookimplMarker("changedetectionio_conditions")
 global_hookimpl = pluggy.HookimplMarker("changedetectionio")
@@ -72,7 +78,17 @@ def ui_edit_stats_extras(watch):
     """Generate the HTML for Levenshtein stats - shared by both plugin systems"""
     if len(watch.history.keys()) < 2:
         return "<p>Not enough history to calculate Levenshtein metrics</p>"
-    
+
+
+    # Protection against the algorithm getting stuck on huge documents
+    k = list(watch.history.keys())
+    if any(
+            len(watch.get_history_snapshot(timestamp=k[idx])) > LEVENSHTEIN_MAX_LEN_FOR_EDIT_STATS
+            for idx in (-1, -2)
+            if len(k) >= abs(idx)
+    ):
+        return "<p>Snapshot too large for edit statistics, skipping.</p>"
+
     try:
         lev_data = levenshtein_ratio_recent_history(watch)
         if not lev_data or not isinstance(lev_data, dict):

changedetectionio/conditions/plugins/wordcount_plugin.py

@@ -1,3 +1,7 @@
+"""
+Word count plugin for content analysis.
+Provides word count metrics for snapshot content.
+"""
 import pluggy
 from loguru import logger
 
@@ -14,7 +18,7 @@ def count_words_in_history(watch, incoming_text=None):
         elif watch.history.keys():
             # When called from UI extras to count latest snapshot
             latest_key = list(watch.history.keys())[-1]
-            latest_content = watch.get_history_snapshot(latest_key)
+            latest_content = watch.get_history_snapshot(timestamp=latest_key)
             return len(latest_content.split())
         return 0
     except Exception as e:

changedetectionio/content_fetchers/__init__.py

@@ -7,6 +7,9 @@ import os
 # Visual Selector scraper - 'Button' is there because some sites have <button>OUT OF STOCK</button>.
 visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4,header,footer,section,article,aside,details,main,nav,section,summary,button'
 
+# Import hookimpl from centralized pluggy interface
+from changedetectionio.pluggy_interface import hookimpl
+
 SCREENSHOT_MAX_HEIGHT_DEFAULT = 20000
 SCREENSHOT_DEFAULT_QUALITY = 40
 
@@ -18,7 +21,9 @@ SCREENSHOT_MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_
 # The size at which we will switch to stitching method, when below this (and
 # MAX_TOTAL_HEIGHT which can be set by a user) we will use the default
 # screenshot method.
-SCREENSHOT_SIZE_STITCH_THRESHOLD = 8000
+# Increased from 8000 to 10000 for better performance (fewer chunks = faster)
+# Most modern GPUs support 16384x16384 textures, so 1280x10000 is safe
+SCREENSHOT_SIZE_STITCH_THRESHOLD = int(os.getenv("SCREENSHOT_CHUNK_HEIGHT", 10000))
 
 # available_fetchers() will scan this implementation looking for anything starting with html_
 # this information is used in the form selections
@@ -28,23 +33,61 @@ from changedetectionio.content_fetchers.requests import fetcher as html_requests
 import importlib.resources
 XPATH_ELEMENT_JS = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text(encoding='utf-8')
 INSTOCK_DATA_JS = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text(encoding='utf-8')
+FAVICON_FETCHER_JS = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('favicon-fetcher.js').read_text(encoding='utf-8')
 
 
 def available_fetchers():
     # See the if statement at the bottom of this file for how we switch between playwright and webdriver
     import inspect
     p = []
+
+    # Get built-in fetchers (but skip plugin fetchers that were added via setattr)
     for name, obj in inspect.getmembers(sys.modules[__name__], inspect.isclass):
         if inspect.isclass(obj):
             # @todo html_ is maybe better as fetcher_ or something
             # In this case, make sure to edit the default one in store.py and fetch_site_status.py
             if name.startswith('html_'):
-                t = tuple([name, obj.fetcher_description])
-                p.append(t)
+                # Skip plugin fetchers that were already registered
+                if name not in _plugin_fetchers:
+                    t = tuple([name, obj.fetcher_description])
+                    p.append(t)
+
+    # Get plugin fetchers from cache (already loaded at module init)
+    for name, fetcher_class in _plugin_fetchers.items():
+        if hasattr(fetcher_class, 'fetcher_description'):
+            t = tuple([name, fetcher_class.fetcher_description])
+            p.append(t)
+        else:
+            logger.warning(f"Plugin fetcher '{name}' does not have fetcher_description attribute")
 
     return p
 
 
+def get_plugin_fetchers():
+    """Load and return all plugin fetchers from the centralized plugin manager."""
+    from changedetectionio.pluggy_interface import plugin_manager
+
+    fetchers = {}
+    try:
+        # Call the register_content_fetcher hook from all registered plugins
+        results = plugin_manager.hook.register_content_fetcher()
+        for result in results:
+            if result:
+                name, fetcher_class = result
+                fetchers[name] = fetcher_class
+                # Register in current module so hasattr() checks work
+                setattr(sys.modules[__name__], name, fetcher_class)
+                logger.info(f"Registered plugin fetcher: {name} - {getattr(fetcher_class, 'fetcher_description', 'No description')}")
+    except Exception as e:
+        logger.error(f"Error loading plugin fetchers: {e}")
+
+    return fetchers
+
+
+# Initialize plugins at module load time
+_plugin_fetchers = get_plugin_fetchers()
+
+
 # Decide which is the 'real' HTML webdriver, this is more a system wide config
 # rather than site-specific.
 use_playwright_as_chrome_fetcher = os.getenv('PLAYWRIGHT_DRIVER_URL', False)
@@ -61,3 +104,8 @@ else:
     logger.debug("Falling back to selenium as fetcher")
     from .webdriver_selenium import fetcher as html_webdriver
 
+
+# Register built-in fetchers as plugins after all imports are complete
+from changedetectionio.pluggy_interface import register_builtin_fetchers
+register_builtin_fetchers()
+

changedetectionio/content_fetchers/base.py

@@ -38,7 +38,6 @@ def manage_user_agent(headers, current_ua=''):
 
     return None
 
-
 class Fetcher():
     browser_connection_is_custom = None
     browser_connection_url = None
@@ -48,8 +47,10 @@ class Fetcher():
     error = None
     fetcher_description = "No description"
     headers = {}
+    favicon_blob = None
     instock_data = None
     instock_data_js = ""
+    screenshot_format = None
     status_code = None
     webdriver_js_execute_code = None
     xpath_data = None
@@ -63,26 +64,79 @@ class Fetcher():
     # Time ONTOP of the system defined env minimum time
     render_extract_delay = 0
 
+    # Fetcher capability flags - subclasses should override these
+    # These indicate what features the fetcher supports
+    supports_browser_steps = False      # Can execute browser automation steps
+    supports_screenshots = False        # Can capture page screenshots
+    supports_xpath_element_data = False # Can extract xpath element positions/data for visual selector
+
+    # Screenshot element locking - prevents layout shifts during screenshot capture
+    # Only needed for visual comparison (image_ssim_diff processor)
+    # Locks element dimensions in the first viewport to prevent headers/ads from resizing
+    lock_viewport_elements = False      # Default: disabled for performance
+
+    def __init__(self, **kwargs):
+        if kwargs and 'screenshot_format' in kwargs:
+            self.screenshot_format = kwargs.get('screenshot_format')
+
+        # Allow lock_viewport_elements to be set via kwargs
+        if kwargs and 'lock_viewport_elements' in kwargs:
+            self.lock_viewport_elements = kwargs.get('lock_viewport_elements')
+
+
+    @classmethod
+    def get_status_icon_data(cls):
+        """Return data for status icon to display in the watch overview.
+
+        This method can be overridden by subclasses to provide custom status icons.
+
+        Returns:
+            dict or None: Dictionary with icon data:
+                {
+                    'filename': 'icon-name.svg',  # Icon filename
+                    'alt': 'Alt text',            # Alt attribute
+                    'title': 'Tooltip text',      # Title attribute
+                    'style': 'height: 1em;'       # Optional inline CSS
+                }
+                Or None if no icon
+        """
+        return None
+
+    def clear_content(self):
+        """
+        Explicitly clear all content from memory to free up heap space.
+        Call this after content has been saved to disk.
+        """
+        self.content = None
+        if hasattr(self, 'raw_content'):
+            self.raw_content = None
+        self.screenshot = None
+        self.xpath_data = None
+        # Keep headers and status_code as they're small
+
     @abstractmethod
     def get_error(self):
         return self.error
 
     @abstractmethod
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False,
-            empty_pages_are_a_change=False):
+    async def run(self,
+                  fetch_favicon=True,
+                  current_include_filters=None,
+                  empty_pages_are_a_change=False,
+                  ignore_status_codes=False,
+                  is_binary=False,
+                  request_body=None,
+                  request_headers=None,
+                  request_method=None,
+                  timeout=None,
+                  url=None,
+                  watch_uuid=None,
+                  ):
         # Should set self.error, self.status_code and self.content
         pass
 
     @abstractmethod
-    def quit(self, watch=None):
+    async def quit(self, watch=None):
         return
 
     @abstractmethod
@@ -108,36 +162,22 @@ class Fetcher():
         """
         return {k.lower(): v for k, v in self.headers.items()}
 
-    def browser_steps_get_valid_steps(self):
-        if self.browser_steps is not None and len(self.browser_steps):
-            valid_steps = list(filter(
-                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one'),
-                self.browser_steps))
-
-            # Just incase they selected Goto site by accident with older JS
-            if valid_steps and valid_steps[0]['operation'] == 'Goto site':
-                del(valid_steps[0])
-
-            return valid_steps
-
-        return None
-
-    def iterate_browser_steps(self, start_url=None):
-        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+    async def iterate_browser_steps(self, start_url=None):
+        from changedetectionio.browser_steps.browser_steps import steppable_browser_interface, browser_steps_get_valid_steps
         from playwright._impl._errors import TimeoutError, Error
-        from changedetectionio.safe_jinja import render as jinja_render
+        from changedetectionio.jinja2_custom import render as jinja_render
         step_n = 0
 
-        if self.browser_steps is not None and len(self.browser_steps):
+        if self.browser_steps:
             interface = steppable_browser_interface(start_url=start_url)
             interface.page = self.page
-            valid_steps = self.browser_steps_get_valid_steps()
+            valid_steps = browser_steps_get_valid_steps(self.browser_steps)
 
             for step in valid_steps:
                 step_n += 1
                 logger.debug(f">> Iterating check - browser Step n {step_n} - {step['operation']}...")
-                self.screenshot_step("before-" + str(step_n))
-                self.save_step_html("before-" + str(step_n))
+                await self.screenshot_step("before-" + str(step_n))
+                await self.save_step_html("before-" + str(step_n))
 
                 try:
                     optional_value = step['optional_value']
@@ -148,11 +188,11 @@ class Fetcher():
                     if '{%' in step['selector'] or '{{' in step['selector']:
                         selector = jinja_render(template_str=step['selector'])
 
-                    getattr(interface, "call_action")(action_name=step['operation'],
+                    await getattr(interface, "call_action")(action_name=step['operation'],
                                                       selector=selector,
                                                       optional_value=optional_value)
-                    self.screenshot_step(step_n)
-                    self.save_step_html(step_n)
+                    await self.screenshot_step(step_n)
+                    await self.save_step_html(step_n)
                 except (Error, TimeoutError) as e:
                     logger.debug(str(e))
                     # Stop processing here

changedetectionio/content_fetchers/playwright.py

@@ -1,3 +1,5 @@
+import asyncio
+import gc
 import json
 import os
 from urllib.parse import urlparse
@@ -5,75 +7,146 @@ from urllib.parse import urlparse
 from loguru import logger
 
 from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT, visualselector_xpath_selectors, \
-    SCREENSHOT_SIZE_STITCH_THRESHOLD, SCREENSHOT_MAX_TOTAL_HEIGHT, XPATH_ELEMENT_JS, INSTOCK_DATA_JS
+    SCREENSHOT_SIZE_STITCH_THRESHOLD, SCREENSHOT_MAX_TOTAL_HEIGHT, XPATH_ELEMENT_JS, INSTOCK_DATA_JS, FAVICON_FETCHER_JS
 from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
-from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, ScreenshotUnavailable
+from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, ScreenshotUnavailable, \
+    BrowserStepsStepException
 
-def capture_full_page(page):
+
+async def capture_full_page_async(page, screenshot_format='JPEG', watch_uuid=None, lock_viewport_elements=False):
     import os
     import time
-    from multiprocessing import Process, Pipe
 
     start = time.time()
+    watch_info = f"[{watch_uuid}] " if watch_uuid else ""
 
-    page_height = page.evaluate("document.documentElement.scrollHeight")
-    page_width = page.evaluate("document.documentElement.scrollWidth")
+    setup_start = time.time()
+    page_height = await page.evaluate("document.documentElement.scrollHeight")
+    page_width = await page.evaluate("document.documentElement.scrollWidth")
     original_viewport = page.viewport_size
+    dimensions_time = time.time() - setup_start
 
-    logger.debug(f"Playwright viewport size {page.viewport_size} page height {page_height} page width {page_width}")
+    logger.debug(f"{watch_info}Playwright viewport size {page.viewport_size} page height {page_height} page width {page_width} (got dimensions in {dimensions_time:.2f}s)")
 
     # Use an approach similar to puppeteer: set a larger viewport and take screenshots in chunks
     step_size = SCREENSHOT_SIZE_STITCH_THRESHOLD # Size that won't cause GPU to overflow
     screenshot_chunks = []
     y = 0
+    elements_locked = False
+
+    # Only lock viewport elements if explicitly enabled (for image_ssim_diff processor)
+    # This prevents headers/ads from resizing when viewport changes
+    if lock_viewport_elements and page_height > page.viewport_size['height']:
+        lock_start = time.time()
+        lock_elements_js_path = os.path.join(os.path.dirname(__file__), 'res', 'lock-elements-sizing.js')
+        with open(lock_elements_js_path, 'r') as f:
+            lock_elements_js = f.read()
+        await page.evaluate(lock_elements_js)
+        elements_locked = True
+        lock_time = time.time() - lock_start
+        logger.debug(f"{watch_info}Viewport element locking enabled (took {lock_time:.2f}s)")
 
     if page_height > page.viewport_size['height']:
         if page_height < step_size:
             step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
-        logger.debug(f"Setting bigger viewport to step through large page width W{page.viewport_size['width']}xH{step_size} because page_height > viewport_size")
+        viewport_start = time.time()
+        logger.debug(f"{watch_info}Setting bigger viewport to step through large page width W{page.viewport_size['width']}xH{step_size} because page_height > viewport_size")
         # Set viewport to a larger size to capture more content at once
-        page.set_viewport_size({'width': page.viewport_size['width'], 'height': step_size})
+        await page.set_viewport_size({'width': page.viewport_size['width'], 'height': step_size})
+        viewport_time = time.time() - viewport_start
+        logger.debug(f"{watch_info}Viewport changed to {page.viewport_size['width']}x{step_size} (took {viewport_time:.2f}s)")
 
     # Capture screenshots in chunks up to the max total height
+    capture_start = time.time()
+    chunk_times = []
+    # Use PNG for better quality (no compression artifacts), JPEG for smaller size
+    screenshot_type = screenshot_format.lower() if screenshot_format else 'jpeg'
+    # PNG should use quality 100, JPEG uses configurable quality
+    screenshot_quality = 100 if screenshot_type == 'png' else int(os.getenv("SCREENSHOT_QUALITY", 72))
+
     while y < min(page_height, SCREENSHOT_MAX_TOTAL_HEIGHT):
-        page.request_gc()
-        page.evaluate(f"window.scrollTo(0, {y})")
-        page.request_gc()
-        screenshot_chunks.append(page.screenshot(
-            type="jpeg",
-            full_page=False,
-            quality=int(os.getenv("SCREENSHOT_QUALITY", 72))
-        ))
+        # Only scroll if not at the top (y > 0)
+        if y > 0:
+            await page.evaluate(f"window.scrollTo(0, {y})")
+
+        # Request GC only before screenshot (not 3x per chunk)
+        await page.request_gc()
+
+        screenshot_kwargs = {
+            'type': screenshot_type,
+            'full_page': False
+        }
+        # Only pass quality parameter for jpeg (PNG doesn't support it in Playwright)
+        if screenshot_type == 'jpeg':
+            screenshot_kwargs['quality'] = screenshot_quality
+
+        chunk_start = time.time()
+        screenshot_chunks.append(await page.screenshot(**screenshot_kwargs))
+        chunk_time = time.time() - chunk_start
+        chunk_times.append(chunk_time)
+        logger.debug(f"{watch_info}Chunk {len(screenshot_chunks)} captured in {chunk_time:.2f}s")
         y += step_size
-        page.request_gc()
 
     # Restore original viewport size
-    page.set_viewport_size({'width': original_viewport['width'], 'height': original_viewport['height']})
+    await page.set_viewport_size({'width': original_viewport['width'], 'height': original_viewport['height']})
+
+    # Unlock element dimensions if they were locked
+    if elements_locked:
+        unlock_elements_js_path = os.path.join(os.path.dirname(__file__), 'res', 'unlock-elements-sizing.js')
+        with open(unlock_elements_js_path, 'r') as f:
+            unlock_elements_js = f.read()
+        await page.evaluate(unlock_elements_js)
+        logger.debug(f"{watch_info}Element dimensions unlocked after screenshot capture")
+
+    capture_time = time.time() - capture_start
+    total_capture_time = sum(chunk_times)
+    logger.debug(f"{watch_info}All {len(screenshot_chunks)} chunks captured in {capture_time:.2f}s (total chunk time: {total_capture_time:.2f}s)")
 
     # If we have multiple chunks, stitch them together
     if len(screenshot_chunks) > 1:
-        from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker
-        logger.debug(f"Screenshot stitching {len(screenshot_chunks)} chunks together")
-        parent_conn, child_conn = Pipe()
-        p = Process(target=stitch_images_worker, args=(child_conn, screenshot_chunks, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
+        stitch_start = time.time()
+        logger.debug(f"{watch_info}Starting stitching of {len(screenshot_chunks)} chunks")
+
+        # Always use spawn subprocess for ANY stitching (2+ chunks)
+        # PIL allocates at C level and Python GC never releases it - subprocess exit forces OS to reclaim
+        # Trade-off: 35MB resource_tracker vs 500MB+ PIL leak in main process
+        from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker_raw_bytes
+        import multiprocessing
+        import struct
+
+        ctx = multiprocessing.get_context('spawn')
+        parent_conn, child_conn = ctx.Pipe()
+        p = ctx.Process(target=stitch_images_worker_raw_bytes, args=(child_conn, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
         p.start()
+
+        # Send via raw bytes (no pickle)
+        parent_conn.send_bytes(struct.pack('I', len(screenshot_chunks)))
+        for chunk in screenshot_chunks:
+            parent_conn.send_bytes(chunk)
+
         screenshot = parent_conn.recv_bytes()
         p.join()
+
+        parent_conn.close()
+        child_conn.close()
+        del p, parent_conn, child_conn
+
+        stitch_time = time.time() - stitch_start
+        total_time = time.time() - start
+        setup_time = total_time - capture_time - stitch_time
         logger.debug(
-            f"Screenshot (chunked/stitched) - Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
-        # Explicit cleanup
-        del screenshot_chunks
-        del p
-        del parent_conn, child_conn
-        screenshot_chunks = None
+            f"{watch_info}Screenshot complete - Page height: {page_height}px, Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT}px | "
+            f"Setup: {setup_time:.2f}s, Capture: {capture_time:.2f}s, Stitching: {stitch_time:.2f}s, Total: {total_time:.2f}s")
         return screenshot
 
+    total_time = time.time() - start
+    setup_time = total_time - capture_time
     logger.debug(
-        f"Screenshot Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
+        f"{watch_info}Screenshot complete - Page height: {page_height}px, Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT}px | "
+        f"Setup: {setup_time:.2f}s, Single chunk: {capture_time:.2f}s, Total: {total_time:.2f}s")
 
     return screenshot_chunks[0]
 
-
 class fetcher(Fetcher):
     fetcher_description = "Playwright {}/Javascript".format(
         os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
@@ -90,8 +163,22 @@ class fetcher(Fetcher):
 
     proxy = None
 
-    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
-        super().__init__()
+    # Capability flags
+    supports_browser_steps = True
+    supports_screenshots = True
+    supports_xpath_element_data = True
+
+    @classmethod
+    def get_status_icon_data(cls):
+        """Return Chrome browser icon data for Playwright fetcher."""
+        return {
+            'filename': 'google-chrome-icon.png',
+            'alt': 'Using a Chrome browser',
+            'title': 'Using a Chrome browser'
+        }
+
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None, **kwargs):
+        super().__init__(**kwargs)
 
         self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
 
@@ -124,56 +211,75 @@ class fetcher(Fetcher):
                 self.proxy['username'] = parsed.username
                 self.proxy['password'] = parsed.password
 
-    def screenshot_step(self, step_n=''):
+    async def screenshot_step(self, step_n=''):
         super().screenshot_step(step_n=step_n)
-        screenshot = capture_full_page(page=self.page)
+        watch_uuid = getattr(self, 'watch_uuid', None)
+        screenshot = await capture_full_page_async(page=self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
 
+        # Request GC immediately after screenshot to free memory
+        # Screenshots can be large and browser steps take many of them
+        await self.page.request_gc()
 
         if self.browser_steps_screenshot_path is not None:
             destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.jpeg'.format(step_n))
             logger.debug(f"Saving step screenshot to {destination}")
             with open(destination, 'wb') as f:
                 f.write(screenshot)
+            # Clear local reference to allow screenshot bytes to be collected
+            del screenshot
+            gc.collect()
 
-    def save_step_html(self, step_n):
+    async def save_step_html(self, step_n):
         super().save_step_html(step_n=step_n)
-        content = self.page.content()
+        content = await self.page.content()
+
+        # Request GC after getting page content
+        await self.page.request_gc()
+
         destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.html'.format(step_n))
         logger.debug(f"Saving step HTML to {destination}")
-        with open(destination, 'w') as f:
+        with open(destination, 'w', encoding='utf-8') as f:
             f.write(content)
+        # Clear local reference
+        del content
+        gc.collect()
 
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False,
-            empty_pages_are_a_change=False):
+    async def run(self,
+                  fetch_favicon=True,
+                  current_include_filters=None,
+                  empty_pages_are_a_change=False,
+                  ignore_status_codes=False,
+                  is_binary=False,
+                  request_body=None,
+                  request_headers=None,
+                  request_method=None,
+                  screenshot_format=None,
+                  timeout=None,
+                  url=None,
+                  watch_uuid=None,
+                  ):
 
-        from playwright.sync_api import sync_playwright
+        from playwright.async_api import async_playwright
         import playwright._impl._errors
         import time
         self.delete_browser_steps_screenshots()
+        self.watch_uuid = watch_uuid  # Store for use in screenshot_step
         response = None
 
-        with sync_playwright() as p:
+        async with async_playwright() as p:
             browser_type = getattr(p, self.browser_type)
 
             # Seemed to cause a connection Exception even tho I can see it connect
             # self.browser = browser_type.connect(self.command_executor, timeout=timeout*1000)
             # 60,000 connection timeout only
-            browser = browser_type.connect_over_cdp(self.browser_connection_url, timeout=60000)
+            browser = await browser_type.connect_over_cdp(self.browser_connection_url, timeout=60000)
 
             # SOCKS5 with authentication is not supported (yet)
             # https://github.com/microsoft/playwright/issues/10567
 
             # Set user agent to prevent Cloudflare from blocking the browser
             # Use the default one configured in the App.py model that's passed from fetch_site_status.py
-            context = browser.new_context(
+            context = await browser.new_context(
                 accept_downloads=False,  # Should never be needed
                 bypass_csp=True,  # This is needed to enable JavaScript execution on GitHub and others
                 extra_http_headers=request_headers,
@@ -183,41 +289,47 @@ class fetcher(Fetcher):
                 user_agent=manage_user_agent(headers=request_headers),
             )
 
-            self.page = context.new_page()
+            self.page = await context.new_page()
 
             # Listen for all console events and handle errors
-            self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
+            self.page.on("console", lambda msg: logger.debug(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
 
             # Re-use as much code from browser steps as possible so its the same
-            from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+            from changedetectionio.browser_steps.browser_steps import steppable_browser_interface
             browsersteps_interface = steppable_browser_interface(start_url=url)
             browsersteps_interface.page = self.page
 
-            response = browsersteps_interface.action_goto_url(value=url)
-            self.headers = response.all_headers()
+            response = await browsersteps_interface.action_goto_url(value=url)
 
             if response is None:
-                context.close()
-                browser.close()
+                await context.close()
+                await browser.close()
                 logger.debug("Content Fetcher > Response object from the browser communication was none")
                 raise EmptyReply(url=url, status_code=None)
 
+            # In async_playwright, all_headers() returns a coroutine
+            try:
+                self.headers = await response.all_headers()
+            except TypeError:
+                # Fallback for sync version
+                self.headers = response.all_headers()
+
             try:
                 if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
-                    browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
+                    await browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
             except playwright._impl._errors.TimeoutError as e:
-                context.close()
-                browser.close()
+                await context.close()
+                await browser.close()
                 # This can be ok, we will try to grab what we could retrieve
                 pass
             except Exception as e:
                 logger.debug(f"Content Fetcher > Other exception when executing custom JS code {str(e)}")
-                context.close()
-                browser.close()
+                await context.close()
+                await browser.close()
                 raise PageUnloadable(url=url, status_code=None, message=str(e))
 
             extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-            self.page.wait_for_timeout(extra_wait * 1000)
+            await self.page.wait_for_timeout(extra_wait * 1000)
 
             try:
                 self.status_code = response.status
@@ -225,94 +337,135 @@ class fetcher(Fetcher):
                 # https://github.com/dgtlmoon/changedetection.io/discussions/2122#discussioncomment-8241962
                 logger.critical(f"Response from the browser/Playwright did not have a status_code! Response follows.")
                 logger.critical(response)
-                context.close()
-                browser.close()
+                await context.close()
+                await browser.close()
                 raise PageUnloadable(url=url, status_code=None, message=str(e))
 
+            if fetch_favicon:
+                try:
+                    self.favicon_blob = await self.page.evaluate(FAVICON_FETCHER_JS)
+                    await self.page.request_gc()
+                except Exception as e:
+                    logger.error(f"Error fetching FavIcon info {str(e)}, continuing.")
+
             if self.status_code != 200 and not ignore_status_codes:
-                screenshot = capture_full_page(self.page)
+                screenshot = await capture_full_page_async(self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
+                # Finally block will handle cleanup
                 raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
 
-            if not empty_pages_are_a_change and len(self.page.content().strip()) == 0:
+            if not empty_pages_are_a_change and len((await self.page.content()).strip()) == 0:
                 logger.debug("Content Fetcher > Content was empty, empty_pages_are_a_change = False")
-                context.close()
-                browser.close()
+                await context.close()
+                await browser.close()
                 raise EmptyReply(url=url, status_code=response.status)
 
-            # Run Browser Steps here
-            if self.browser_steps_get_valid_steps():
-                self.iterate_browser_steps(start_url=url)
-
-            self.page.wait_for_timeout(extra_wait * 1000)
-
-            now = time.time()
-            # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
-            if current_include_filters is not None:
-                self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
-            else:
-                self.page.evaluate("var include_filters=''")
-            self.page.request_gc()
-
-            # request_gc before and after evaluate to free up memory
-            # @todo browsersteps etc
-            MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
-            self.xpath_data = self.page.evaluate(XPATH_ELEMENT_JS, {
-                "visualselector_xpath_selectors": visualselector_xpath_selectors,
-                "max_height": MAX_TOTAL_HEIGHT
-            })
-            self.page.request_gc()
-
-            self.instock_data = self.page.evaluate(INSTOCK_DATA_JS)
-            self.page.request_gc()
-
-            self.content = self.page.content()
-            self.page.request_gc()
-            logger.debug(f"Scrape xPath element data in browser done in {time.time() - now:.2f}s")
-
-            # Bug 3 in Playwright screenshot handling
-            # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
-            # JPEG is better here because the screenshots can be very very large
-
-            # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
-            # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
-            # acceptable screenshot quality here
+            # Wrap remaining operations in try/finally to ensure cleanup
             try:
+                # Run Browser Steps here
+                if self.browser_steps:
+                    try:
+                        await self.iterate_browser_steps(start_url=url)
+                    except BrowserStepsStepException:
+                        # Finally block will handle cleanup
+                        raise
+
+                    await self.page.wait_for_timeout(extra_wait * 1000)
+
+                now = time.time()
+                # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
+                if current_include_filters is not None:
+                    await self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
+                else:
+                    await self.page.evaluate("var include_filters=''")
+                await self.page.request_gc()
+
+                # request_gc before and after evaluate to free up memory
+                # @todo browsersteps etc
+                MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
+                self.xpath_data = await self.page.evaluate(XPATH_ELEMENT_JS, {
+                    "visualselector_xpath_selectors": visualselector_xpath_selectors,
+                    "max_height": MAX_TOTAL_HEIGHT
+                })
+                await self.page.request_gc()
+
+                self.instock_data = await self.page.evaluate(INSTOCK_DATA_JS)
+                await self.page.request_gc()
+
+                self.content = await self.page.content()
+                await self.page.request_gc()
+                logger.debug(f"Scrape xPath element data in browser done in {time.time() - now:.2f}s")
+
+
+                # Bug 3 in Playwright screenshot handling
+                # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
+                # JPEG is better here because the screenshots can be very very large
+
+                # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
+                # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
+                # acceptable screenshot quality here
                 # The actual screenshot - this always base64 and needs decoding! horrible! huge CPU usage
-                self.screenshot = capture_full_page(page=self.page)
+                self.screenshot = await capture_full_page_async(page=self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
 
-            except Exception as e:
-                # It's likely the screenshot was too long/big and something crashed
+                # Force aggressive memory cleanup - screenshots are large and base64 decode creates temporary buffers
+                await self.page.request_gc()
+                gc.collect()
+
+            except ScreenshotUnavailable:
+                # Re-raise screenshot unavailable exceptions
                 raise ScreenshotUnavailable(url=url, status_code=self.status_code)
+
             finally:
-                # Request garbage collection one more time before closing
+                # Clean up resources properly with timeouts to prevent hanging
                 try:
-                    self.page.request_gc()
-                except:
-                    pass
-                
-                # Clean up resources properly
-                try:
-                    self.page.request_gc()
-                except:
-                    pass
+                    if hasattr(self, 'page') and self.page:
+                        await self.page.request_gc()
+                        await asyncio.wait_for(self.page.close(), timeout=5.0)
+                        logger.debug(f"Successfully closed page for {url}")
+                except asyncio.TimeoutError:
+                    logger.warning(f"Timed out closing page for {url} (5s)")
+                except Exception as e:
+                    logger.warning(f"Error closing page for {url}: {e}")
+                finally:
+                    self.page = None
 
                 try:
-                    self.page.close()
-                except:
-                    pass
-                self.page = None
+                    if context:
+                        await asyncio.wait_for(context.close(), timeout=5.0)
+                        logger.debug(f"Successfully closed context for {url}")
+                except asyncio.TimeoutError:
+                    logger.warning(f"Timed out closing context for {url} (5s)")
+                except Exception as e:
+                    logger.warning(f"Error closing context for {url}: {e}")
+                finally:
+                    context = None
 
                 try:
-                    context.close()
-                except:
-                    pass
-                context = None
+                    if browser:
+                        await asyncio.wait_for(browser.close(), timeout=5.0)
+                        logger.debug(f"Successfully closed browser connection for {url}")
+                except asyncio.TimeoutError:
+                    logger.warning(f"Timed out closing browser connection for {url} (5s)")
+                except Exception as e:
+                    logger.warning(f"Error closing browser for {url}: {e}")
+                finally:
+                    browser = None
 
-                try:
-                    browser.close()
-                except:
-                    pass
-                browser = None
+                # Force Python GC to release Playwright resources immediately
+                # Playwright objects can have circular references that delay cleanup
+                gc.collect()
+
+
+# Plugin registration for built-in fetcher
+class PlaywrightFetcherPlugin:
+    """Plugin class that registers the Playwright fetcher as a built-in plugin."""
+
+    def register_content_fetcher(self):
+        """Register the Playwright fetcher"""
+        return ('html_webdriver', fetcher)
+
+
+# Create module-level instance for plugin registration
+playwright_plugin = PlaywrightFetcherPlugin()
 
 
 

changedetectionio/content_fetchers/puppeteer.py

@@ -1,4 +1,5 @@
 import asyncio
+import gc
 import json
 import os
 import websockets.exceptions
@@ -8,7 +9,7 @@ from loguru import logger
 
 from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT, visualselector_xpath_selectors, \
     SCREENSHOT_SIZE_STITCH_THRESHOLD, SCREENSHOT_DEFAULT_QUALITY, XPATH_ELEMENT_JS, INSTOCK_DATA_JS, \
-    SCREENSHOT_MAX_TOTAL_HEIGHT
+    SCREENSHOT_MAX_TOTAL_HEIGHT, FAVICON_FETCHER_JS
 from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
 from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, BrowserFetchTimedOut, \
     BrowserConnectError
@@ -20,18 +21,20 @@ from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200
 # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
 # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
 # acceptable screenshot quality here
-async def capture_full_page(page):
+async def capture_full_page(page, screenshot_format='JPEG', watch_uuid=None, lock_viewport_elements=False):
     import os
     import time
-    from multiprocessing import Process, Pipe
 
     start = time.time()
+    watch_info = f"[{watch_uuid}] " if watch_uuid else ""
 
+    setup_start = time.time()
     page_height = await page.evaluate("document.documentElement.scrollHeight")
     page_width = await page.evaluate("document.documentElement.scrollWidth")
     original_viewport = page.viewport
+    dimensions_time = time.time() - setup_start
 
-    logger.debug(f"Puppeteer viewport size {page.viewport} page height {page_height} page width {page_width}")
+    logger.debug(f"{watch_info}Puppeteer viewport size {page.viewport} page height {page_height} page width {page_width} (got dimensions in {dimensions_time:.2f}s)")
 
     # Bug 3 in Playwright screenshot handling
     # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
@@ -41,40 +44,124 @@ async def capture_full_page(page):
     # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
     # acceptable screenshot quality here
 
+    # Use PNG for better quality (no compression artifacts), JPEG for smaller size
+    screenshot_type = screenshot_format.lower() if screenshot_format else 'jpeg'
+    # PNG should use quality 100, JPEG uses configurable quality
+    screenshot_quality = 100 if screenshot_type == 'png' else int(os.getenv("SCREENSHOT_QUALITY", 72))
 
     step_size = SCREENSHOT_SIZE_STITCH_THRESHOLD # Something that will not cause the GPU to overflow when taking the screenshot
     screenshot_chunks = []
     y = 0
+    elements_locked = False
+
+    # Only lock viewport elements if explicitly enabled (for image_ssim_diff processor)
+    # This prevents headers/ads from resizing when viewport changes
+    if lock_viewport_elements and page_height > page.viewport['height']:
+        lock_start = time.time()
+        lock_elements_js_path = os.path.join(os.path.dirname(__file__), 'res', 'lock-elements-sizing.js')
+        file_read_start = time.time()
+        with open(lock_elements_js_path, 'r') as f:
+            lock_elements_js = f.read()
+        file_read_time = time.time() - file_read_start
+
+        evaluate_start = time.time()
+        await page.evaluate(lock_elements_js)
+        evaluate_time = time.time() - evaluate_start
+
+        elements_locked = True
+        lock_time = time.time() - lock_start
+        logger.debug(f"{watch_info}Viewport element locking enabled - File read: {file_read_time:.3f}s, Browser evaluate: {evaluate_time:.2f}s, Total: {lock_time:.2f}s")
+
     if page_height > page.viewport['height']:
         if page_height < step_size:
             step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
+        viewport_start = time.time()
         await page.setViewport({'width': page.viewport['width'], 'height': step_size})
+        viewport_time = time.time() - viewport_start
+        logger.debug(f"{watch_info}Viewport changed to {page.viewport['width']}x{step_size} (took {viewport_time:.2f}s)")
 
+    capture_start = time.time()
+    chunk_times = []
     while y < min(page_height, SCREENSHOT_MAX_TOTAL_HEIGHT):
-        await page.evaluate(f"window.scrollTo(0, {y})")
-        screenshot_chunks.append(await page.screenshot(type_='jpeg',
-                                                       fullPage=False,
-                                                       quality=int(os.getenv("SCREENSHOT_QUALITY", 72))))
+        # better than scrollTo incase they override it in the page
+        await page.evaluate(
+            """(y) => {
+                document.documentElement.scrollTop = y;
+                document.body.scrollTop = y;
+            }""",
+            y
+        )
+
+        screenshot_kwargs = {
+            'type_': screenshot_type,
+            'fullPage': False
+        }
+        # PNG doesn't support quality parameter in Puppeteer
+        if screenshot_type == 'jpeg':
+            screenshot_kwargs['quality'] = screenshot_quality
+
+        chunk_start = time.time()
+        screenshot_chunks.append(await page.screenshot(**screenshot_kwargs))
+        chunk_time = time.time() - chunk_start
+        chunk_times.append(chunk_time)
+        logger.debug(f"{watch_info}Chunk {len(screenshot_chunks)} captured in {chunk_time:.2f}s")
         y += step_size
 
     await page.setViewport({'width': original_viewport['width'], 'height': original_viewport['height']})
 
+    # Unlock element dimensions if they were locked
+    if elements_locked:
+        unlock_elements_js_path = os.path.join(os.path.dirname(__file__), 'res', 'unlock-elements-sizing.js')
+        with open(unlock_elements_js_path, 'r') as f:
+            unlock_elements_js = f.read()
+        await page.evaluate(unlock_elements_js)
+        logger.debug(f"{watch_info}Element dimensions unlocked after screenshot capture")
+
+    capture_time = time.time() - capture_start
+    total_capture_time = sum(chunk_times)
+    logger.debug(f"{watch_info}All {len(screenshot_chunks)} chunks captured in {capture_time:.2f}s (total chunk time: {total_capture_time:.2f}s)")
+
     if len(screenshot_chunks) > 1:
-        from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker
-        logger.debug(f"Screenshot stitching {len(screenshot_chunks)} chunks together")
-        parent_conn, child_conn = Pipe()
-        p = Process(target=stitch_images_worker, args=(child_conn, screenshot_chunks, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
+        stitch_start = time.time()
+        logger.debug(f"{watch_info}Starting stitching of {len(screenshot_chunks)} chunks")
+
+        # Always use spawn subprocess for ANY stitching (2+ chunks)
+        # PIL allocates at C level and Python GC never releases it - subprocess exit forces OS to reclaim
+        # Trade-off: 35MB resource_tracker vs 500MB+ PIL leak in main process
+        from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker_raw_bytes
+        import multiprocessing
+        import struct
+
+        ctx = multiprocessing.get_context('spawn')
+        parent_conn, child_conn = ctx.Pipe()
+        p = ctx.Process(target=stitch_images_worker_raw_bytes, args=(child_conn, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
         p.start()
+
+        # Send via raw bytes (no pickle)
+        parent_conn.send_bytes(struct.pack('I', len(screenshot_chunks)))
+        for chunk in screenshot_chunks:
+            parent_conn.send_bytes(chunk)
+
         screenshot = parent_conn.recv_bytes()
         p.join()
-        logger.debug(
-            f"Screenshot (chunked/stitched) - Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
 
-        screenshot_chunks = None
+        parent_conn.close()
+        child_conn.close()
+        del p, parent_conn, child_conn
+
+        stitch_time = time.time() - stitch_start
+        total_time = time.time() - start
+        setup_time = total_time - capture_time - stitch_time
+        logger.debug(
+            f"{watch_info}Screenshot complete - Page height: {page_height}px, Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT}px | "
+            f"Setup: {setup_time:.2f}s, Capture: {capture_time:.2f}s, Stitching: {stitch_time:.2f}s, Total: {total_time:.2f}s")
         return screenshot
 
+    total_time = time.time() - start
+    setup_time = total_time - capture_time
     logger.debug(
-        f"Screenshot Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
+        f"{watch_info}Screenshot complete - Page height: {page_height}px, Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT}px | "
+        f"Setup: {setup_time:.2f}s, Single chunk: {capture_time:.2f}s, Total: {total_time:.2f}s")
     return screenshot_chunks[0]
 
 
@@ -85,13 +172,27 @@ class fetcher(Fetcher):
     if os.getenv("PLAYWRIGHT_DRIVER_URL"):
         fetcher_description += " via '{}'".format(os.getenv("PLAYWRIGHT_DRIVER_URL"))
 
+    browser = None
     browser_type = ''
     command_executor = ''
-
     proxy = None
 
-    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
-        super().__init__()
+    # Capability flags
+    supports_browser_steps = True
+    supports_screenshots = True
+    supports_xpath_element_data = True
+
+    @classmethod
+    def get_status_icon_data(cls):
+        """Return Chrome browser icon data for Puppeteer fetcher."""
+        return {
+            'filename': 'google-chrome-icon.png',
+            'alt': 'Using a Chrome browser',
+            'title': 'Using a Chrome browser'
+        }
+
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None, **kwargs):
+        super().__init__(**kwargs)
 
         if custom_browser_connection_url:
             self.browser_connection_is_custom = True
@@ -120,36 +221,59 @@ class fetcher(Fetcher):
                 proxy_url += f"{parsed.hostname}{port}{parsed.path}{q}"
                 self.browser_connection_url += f"{r}--proxy-server={proxy_url}"
 
-    # def screenshot_step(self, step_n=''):
-    #     screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=85)
-    #
-    #     if self.browser_steps_screenshot_path is not None:
-    #         destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.jpeg'.format(step_n))
-    #         logger.debug(f"Saving step screenshot to {destination}")
-    #         with open(destination, 'wb') as f:
-    #             f.write(screenshot)
-    #
-    # def save_step_html(self, step_n):
-    #     content = self.page.content()
-    #     destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.html'.format(step_n))
-    #     logger.debug(f"Saving step HTML to {destination}")
-    #     with open(destination, 'w') as f:
-    #         f.write(content)
+    async def quit(self, watch=None):
+        watch_uuid = watch.get('uuid') if watch else 'unknown'
+
+        # Close page
+        try:
+            if hasattr(self, 'page') and self.page:
+                await asyncio.wait_for(self.page.close(), timeout=5.0)
+                logger.debug(f"[{watch_uuid}] Page closed successfully")
+        except asyncio.TimeoutError:
+            logger.warning(f"[{watch_uuid}] Timed out closing page (5s)")
+        except Exception as e:
+            logger.warning(f"[{watch_uuid}] Error closing page: {e}")
+        finally:
+            self.page = None
+
+        # Close browser connection
+        try:
+            if hasattr(self, 'browser') and self.browser:
+                await asyncio.wait_for(self.browser.close(), timeout=5.0)
+                logger.debug(f"[{watch_uuid}] Browser closed successfully")
+        except asyncio.TimeoutError:
+            logger.warning(f"[{watch_uuid}] Timed out closing browser (5s)")
+        except Exception as e:
+            logger.warning(f"[{watch_uuid}] Error closing browser: {e}")
+        finally:
+            self.browser = None
+
+        logger.info(f"[{watch_uuid}] Cleanup puppeteer complete")
+
+        # Force garbage collection to release resources
+        gc.collect()
 
     async def fetch_page(self,
-                         url,
-                         timeout,
-                         request_headers,
-                         request_body,
-                         request_method,
-                         ignore_status_codes,
                          current_include_filters,
+                         empty_pages_are_a_change,
+                         fetch_favicon,
+                         ignore_status_codes,
                          is_binary,
-                         empty_pages_are_a_change
+                         request_body,
+                         request_headers,
+                         request_method,
+                         screenshot_format,
+                         timeout,
+                         url,
+                         watch_uuid
                          ):
         import re
         self.delete_browser_steps_screenshots()
-        extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+
+        n = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 12)) + self.render_extract_delay
+        extra_wait = min(n, 15)
+
+        logger.debug(f"Extra wait set to {extra_wait}s, requested was {n}s.")
 
         from pyppeteer import Pyppeteer
         pyppeteer_instance = Pyppeteer()
@@ -157,20 +281,34 @@ class fetcher(Fetcher):
         # Connect directly using the specified browser_ws_endpoint
         # @todo timeout
         try:
-            browser = await pyppeteer_instance.connect(browserWSEndpoint=self.browser_connection_url,
-                                                       ignoreHTTPSErrors=True
-                                                       )
+            logger.debug(f"[{watch_uuid}] Connecting to browser at {self.browser_connection_url}")
+            self.browser = await pyppeteer_instance.connect(browserWSEndpoint=self.browser_connection_url,
+                                                            ignoreHTTPSErrors=True
+                                                            )
+            logger.debug(f"[{watch_uuid}] Browser connected successfully")
         except websockets.exceptions.InvalidStatusCode as e:
             raise BrowserConnectError(msg=f"Error while trying to connect the browser, Code {e.status_code} (check your access, whitelist IP, password etc)")
         except websockets.exceptions.InvalidURI:
             raise BrowserConnectError(msg=f"Error connecting to the browser, check your browser connection address (should be ws:// or wss://")
         except Exception as e:
-            raise BrowserConnectError(msg=f"Error connecting to the browser {str(e)}")
+            raise BrowserConnectError(msg=f"Error connecting to the browser - Exception '{str(e)}'")
 
-        # Better is to launch chrome with the URL as arg
-        # non-headless - newPage() will launch an extra tab/window, .browser should already contain 1 page/tab
-        # headless - ask a new page
-        self.page = (pages := await browser.pages) and len(pages) or await browser.newPage()
+        # more reliable is to just request a new page
+        try:
+            logger.debug(f"[{watch_uuid}] Creating new page")
+            self.page = await self.browser.newPage()
+            logger.debug(f"[{watch_uuid}] Page created successfully")
+        except Exception as e:
+            logger.error(f"[{watch_uuid}] Failed to create new page: {e}")
+            # Browser is connected but page creation failed - must cleanup browser
+            try:
+                await asyncio.wait_for(self.browser.close(), timeout=3.0)
+            except Exception as cleanup_error:
+                logger.error(f"[{watch_uuid}] Failed to cleanup browser after page creation failure: {cleanup_error}")
+            raise
+        
+        # Add console handler to capture console.log from favicon fetcher
+        #self.page.on('console', lambda msg: logger.debug(f"Browser console [{msg.type}]: {msg.text}"))
 
         if '--window-size' in self.browser_connection_url:
             # Be sure the viewport is always the window-size, this is often not the same thing
@@ -182,7 +320,6 @@ class fetcher(Fetcher):
                     "height": int(match.group(2))
                 })
                 logger.debug(f"Puppeteer viewport size {self.page.viewport}")
-
         try:
             from pyppeteerstealth import inject_evasions_into_page
         except ImportError:
@@ -227,13 +364,59 @@ class fetcher(Fetcher):
         #            browsersteps_interface = steppable_browser_interface()
         #            browsersteps_interface.page = self.page
 
-        response = await self.page.goto(url, waitUntil="load")
+        # Enable Network domain to detect when first bytes arrive
+        await self.page._client.send('Network.enable')
 
-        if response is None:
-            await self.page.close()
-            await browser.close()
-            logger.warning("Content Fetcher > Response object was none (as in, the response from the browser was empty, not just the content)")
-            raise EmptyReply(url=url, status_code=None)
+        # Now set up the frame navigation handlers
+        async def handle_frame_navigation(event=None):
+            # Wait n seconds after the frameStartedLoading, not from any frameStartedLoading/frameStartedNavigating
+            logger.debug(f"Frame navigated: {event}")
+            w = extra_wait - 2 if extra_wait > 4 else 2
+            logger.debug(f"Waiting {w} seconds before calling Page.stopLoading...")
+            await asyncio.sleep(w)
+
+            # Check if page still exists (might have been closed due to error during sleep)
+            if not self.page or not hasattr(self.page, '_client'):
+                logger.debug("Page already closed, skipping stopLoading")
+                return
+
+            logger.debug("Issuing stopLoading command...")
+            await self.page._client.send('Page.stopLoading')
+            logger.debug("stopLoading command sent!")
+
+        async def setup_frame_handlers_on_first_response(event):
+            # Only trigger for the main document response
+            if event.get('type') == 'Document':
+                logger.debug("First response received, setting up frame handlers for forced page stop load.")
+                self.page._client.on('Page.frameStartedNavigating', lambda e: asyncio.create_task(handle_frame_navigation(e)))
+                self.page._client.on('Page.frameStartedLoading', lambda e: asyncio.create_task(handle_frame_navigation(e)))
+                self.page._client.on('Page.frameStoppedLoading', lambda e: logger.debug(f"Frame stopped loading: {e}"))
+                logger.debug("First response received, setting up frame handlers for forced page stop load DONE SETUP")
+                # De-register this listener - we only need it once
+                self.page._client.remove_listener('Network.responseReceived', setup_frame_handlers_on_first_response)
+
+        # Listen for first response to trigger frame handler setup
+        self.page._client.on('Network.responseReceived', setup_frame_handlers_on_first_response)
+
+        response = None
+        attempt=0
+        while not response:
+            logger.debug(f"Attempting page fetch {url} attempt {attempt}")
+            asyncio.create_task(handle_frame_navigation())
+            response = await self.page.goto(url, timeout=0)
+            await asyncio.sleep(1 + extra_wait)
+            # Check if page still exists before sending command
+            if self.page and hasattr(self.page, '_client'):
+                await self.page._client.send('Page.stopLoading')
+
+            if response:
+                break
+            if not response:
+                logger.warning("Page did not fetch! trying again!")
+            if response is None and attempt>=2:
+                logger.warning(f"Content Fetcher > Response object was none (as in, the response from the browser was empty, not just the content) exiting attempt {attempt}")
+                raise EmptyReply(url=url, status_code=None)
+            attempt+=1
 
         self.headers = response.headers
 
@@ -243,8 +426,6 @@ class fetcher(Fetcher):
         except Exception as e:
             logger.warning("Got exception when running evaluate on custom JS code")
             logger.error(str(e))
-            await self.page.close()
-            await browser.close()
             # This can be ok, we will try to grab what we could retrieve
             raise PageUnloadable(url=url, status_code=None, message=str(e))
 
@@ -254,12 +435,16 @@ class fetcher(Fetcher):
             # https://github.com/dgtlmoon/changedetection.io/discussions/2122#discussioncomment-8241962
             logger.critical(f"Response from the browser/Playwright did not have a status_code! Response follows.")
             logger.critical(response)
-            await self.page.close()
-            await browser.close()
             raise PageUnloadable(url=url, status_code=None, message=str(e))
 
+        if fetch_favicon:
+            try:
+                self.favicon_blob = await self.page.evaluate(FAVICON_FETCHER_JS)
+            except Exception as e:
+                logger.error(f"Error fetching FavIcon info {str(e)}, continuing.")
+
         if self.status_code != 200 and not ignore_status_codes:
-            screenshot = await capture_full_page(page=self.page)
+            screenshot = await capture_full_page(page=self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
 
             raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
 
@@ -267,16 +452,13 @@ class fetcher(Fetcher):
 
         if not empty_pages_are_a_change and len(content.strip()) == 0:
             logger.error("Content Fetcher > Content was empty (empty_pages_are_a_change is False), closing browsers")
-            await self.page.close()
-            await browser.close()
             raise EmptyReply(url=url, status_code=response.status)
 
         # Run Browser Steps here
         # @todo not yet supported, we switch to playwright in this case
-        #            if self.browser_steps_get_valid_steps():
+        #            if self.browser_steps:
         #                self.iterate_browser_steps()
 
-        await asyncio.sleep(1 + extra_wait)
 
         # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
         # Setup the xPath/VisualSelector scraper
@@ -287,6 +469,16 @@ class fetcher(Fetcher):
             await self.page.evaluate(f"var include_filters=''")
 
         MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
+
+        self.content = await self.page.content
+
+        # Now take screenshot (scrolling may trigger layout changes, but measurements are already captured)
+        logger.debug(f"Screenshot format {self.screenshot_format}")
+        self.screenshot = await capture_full_page(page=self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
+
+        # Force garbage collection - pyppeteer base64 decode creates temporary buffers
+        import gc
+        gc.collect()
         self.xpath_data = await self.page.evaluate(XPATH_ELEMENT_JS, {
             "visualselector_xpath_selectors": visualselector_xpath_selectors,
             "max_height": MAX_TOTAL_HEIGHT
@@ -294,41 +486,62 @@ class fetcher(Fetcher):
         if not self.xpath_data:
             raise Exception(f"Content Fetcher > xPath scraper failed. Please report this URL so we can fix it :)")
 
+
         self.instock_data = await self.page.evaluate(INSTOCK_DATA_JS)
 
-        self.content = await self.page.content
-
-        self.screenshot = await capture_full_page(page=self.page)
-
         # It's good to log here in the case that the browser crashes on shutting down but we still get the data we need
-        logger.success(f"Fetching '{url}' complete, closing page")
-        await self.page.close()
-        logger.success(f"Fetching '{url}' complete, closing browser")
-        await browser.close()
         logger.success(f"Fetching '{url}' complete, exiting puppeteer fetch.")
 
     async def main(self, **kwargs):
         await self.fetch_page(**kwargs)
 
-    def run(self, url, timeout, request_headers, request_body, request_method, ignore_status_codes=False,
-            current_include_filters=None, is_binary=False, empty_pages_are_a_change=False):
+    async def run(self,
+                  fetch_favicon=True,
+                  current_include_filters=None,
+                  empty_pages_are_a_change=False,
+                  ignore_status_codes=False,
+                  is_binary=False,
+                  request_body=None,
+                  request_headers=None,
+                  request_method=None,
+                  screenshot_format=None,
+                  timeout=None,
+                  url=None,
+                  watch_uuid=None,
+                  ):
 
         #@todo make update_worker async which could run any of these content_fetchers within memory and time constraints
-        max_time = os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180)
+        max_time = int(os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180))
 
-        # This will work in 3.10 but not >= 3.11 because 3.11 wants tasks only
+        # Now we run this properly in async context since we're called from async worker
         try:
-            asyncio.run(asyncio.wait_for(self.main(
-                url=url,
-                timeout=timeout,
-                request_headers=request_headers,
-                request_body=request_body,
-                request_method=request_method,
-                ignore_status_codes=ignore_status_codes,
+            await asyncio.wait_for(self.main(
                 current_include_filters=current_include_filters,
+                empty_pages_are_a_change=empty_pages_are_a_change,
+                fetch_favicon=fetch_favicon,
+                ignore_status_codes=ignore_status_codes,
                 is_binary=is_binary,
-                empty_pages_are_a_change=empty_pages_are_a_change
-            ), timeout=max_time))
+                request_body=request_body,
+                request_headers=request_headers,
+                request_method=request_method,
+                screenshot_format=None,
+                timeout=timeout,
+                url=url,
+                watch_uuid=watch_uuid,
+            ), timeout=max_time
+            )
         except asyncio.TimeoutError:
-            raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))
+            raise (BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))
 
+
+# Plugin registration for built-in fetcher
+class PuppeteerFetcherPlugin:
+    """Plugin class that registers the Puppeteer fetcher as a built-in plugin."""
+
+    def register_content_fetcher(self):
+        """Register the Puppeteer fetcher"""
+        return ('html_webdriver', fetcher)
+
+
+# Create module-level instance for plugin registration
+puppeteer_plugin = PuppeteerFetcherPlugin()

changedetectionio/content_fetchers/requests.py

@@ -1,6 +1,9 @@
 from loguru import logger
 import hashlib
 import os
+import re
+import asyncio
+
 from changedetectionio import strtobool
 from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
 from changedetectionio.content_fetchers.base import Fetcher
@@ -10,12 +13,12 @@ from changedetectionio.content_fetchers.base import Fetcher
 class fetcher(Fetcher):
     fetcher_description = "Basic fast Plaintext/HTTP Client"
 
-    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
-        super().__init__()
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None, **kwargs):
+        super().__init__(**kwargs)
         self.proxy_override = proxy_override
         # browser_connection_url is none because its always 'launched locally'
 
-    def run(self,
+    def _run_sync(self,
             url,
             timeout,
             request_headers,
@@ -24,18 +27,21 @@ class fetcher(Fetcher):
             ignore_status_codes=False,
             current_include_filters=None,
             is_binary=False,
-            empty_pages_are_a_change=False):
+            empty_pages_are_a_change=False,
+            watch_uuid=None,
+            ):
+        """Synchronous version of run - the original requests implementation"""
 
         import chardet
         import requests
+        from requests.exceptions import ProxyError, ConnectionError, RequestException
 
-        if self.browser_steps_get_valid_steps():
+        if self.browser_steps:
             raise BrowserStepsInUnsupportedFetcher(url=url)
 
         proxies = {}
 
         # Allows override the proxy on a per-request basis
-
         # https://requests.readthedocs.io/en/latest/user/advanced/#socks
         # Should also work with `socks5://user:pass@host:port` type syntax.
 
@@ -49,17 +55,43 @@ class fetcher(Fetcher):
 
         session = requests.Session()
 
+        # Configure retry adapter for low-level network errors only
+        # Retries connection timeouts, read timeouts, connection resets - not HTTP status codes
+        # Especially helpful in parallel test execution when servers are slow/overloaded
+        # Configurable via REQUESTS_RETRY_MAX_COUNT (default: 3 attempts)
+        from requests.adapters import HTTPAdapter
+        from urllib3.util.retry import Retry
+
+        max_retries = int(os.getenv("REQUESTS_RETRY_MAX_COUNT", "6"))
+        retry_strategy = Retry(
+            total=max_retries,
+            connect=max_retries,  # Retry connection timeouts
+            read=max_retries,     # Retry read timeouts
+            status=0,             # Don't retry on HTTP status codes
+            backoff_factor=0.5,   # Wait 0.3s, 0.6s, 1.2s between retries
+            allowed_methods=["HEAD", "GET", "OPTIONS", "POST"],
+            raise_on_status=False
+        )
+        adapter = HTTPAdapter(max_retries=retry_strategy)
+        session.mount("http://", adapter)
+        session.mount("https://", adapter)
+
         if strtobool(os.getenv('ALLOW_FILE_URI', 'false')) and url.startswith('file://'):
             from requests_file import FileAdapter
             session.mount('file://', FileAdapter())
-
-        r = session.request(method=request_method,
-                            data=request_body.encode('utf-8') if type(request_body) is str else request_body,
-                            url=url,
-                            headers=request_headers,
-                            timeout=timeout,
-                            proxies=proxies,
-                            verify=False)
+        try:
+            r = session.request(method=request_method,
+                                data=request_body.encode('utf-8') if type(request_body) is str else request_body,
+                                url=url,
+                                headers=request_headers,
+                                timeout=timeout,
+                                proxies=proxies,
+                                verify=False)
+        except Exception as e:
+            msg = str(e)
+            if proxies and 'SOCKSHTTPSConnectionPool' in msg:
+                msg = f"Proxy connection failed? {msg}"
+            raise Exception(msg) from e
 
         # If the response did not tell us what encoding format to expect, Then use chardet to override what `requests` thinks.
         # For example - some sites don't tell us it's utf-8, but return utf-8 content
@@ -68,9 +100,22 @@ class fetcher(Fetcher):
         if not is_binary:
             # Don't run this for PDF (and requests identified as binary) takes a _long_ time
             if not r.headers.get('content-type') or not 'charset=' in r.headers.get('content-type'):
-                encoding = chardet.detect(r.content)['encoding']
-                if encoding:
-                    r.encoding = encoding
+                # For XML/RSS feeds, check the XML declaration for encoding attribute
+                # This is more reliable than chardet which can misdetect UTF-8 as MacRoman
+                content_type = r.headers.get('content-type', '').lower()
+                if 'xml' in content_type or 'rss' in content_type:
+                    # Look for <?xml version="1.0" encoding="UTF-8"?>
+                    xml_encoding_match = re.search(rb'<\?xml[^>]+encoding=["\']([^"\']+)["\']', r.content[:200])
+                    if xml_encoding_match:
+                        r.encoding = xml_encoding_match.group(1).decode('ascii')
+                    else:
+                        # Default to UTF-8 for XML if no encoding found
+                        r.encoding = 'utf-8'
+                else:
+                    # For other content types, use chardet
+                    encoding = chardet.detect(r.content)['encoding']
+                    if encoding:
+                        r.encoding = encoding
 
         self.headers = r.headers
 
@@ -94,11 +139,51 @@ class fetcher(Fetcher):
         else:
             self.content = r.text
 
-
         self.raw_content = r.content
 
-    def quit(self, watch=None):
+        # If the content is an image, set it as screenshot for SSIM/visual comparison
+        content_type = r.headers.get('content-type', '').lower()
+        if 'image/' in content_type:
+            self.screenshot = r.content
+            logger.debug(f"Image content detected ({content_type}), set as screenshot for comparison")
 
+    async def run(self,
+                  fetch_favicon=True,
+                  current_include_filters=None,
+                  empty_pages_are_a_change=False,
+                  ignore_status_codes=False,
+                  is_binary=False,
+                  request_body=None,
+                  request_headers=None,
+                  request_method=None,
+                  screenshot_format=None,
+                  timeout=None,
+                  url=None,
+                  watch_uuid=None,
+                  ):
+        """Async wrapper that runs the synchronous requests code in a thread pool"""
+
+        loop = asyncio.get_event_loop()
+
+        # Run the synchronous _run_sync in a thread pool to avoid blocking the event loop
+        # Retry logic is handled by requests' HTTPAdapter (see _run_sync for configuration)
+        await loop.run_in_executor(
+            None,  # Use default ThreadPoolExecutor
+            lambda: self._run_sync(
+                url=url,
+                timeout=timeout,
+                request_headers=request_headers,
+                request_body=request_body,
+                request_method=request_method,
+                ignore_status_codes=ignore_status_codes,
+                current_include_filters=current_include_filters,
+                is_binary=is_binary,
+                empty_pages_are_a_change=empty_pages_are_a_change,
+                watch_uuid=watch_uuid,
+            )
+        )
+
+    async def quit(self, watch=None):
         # In case they switched to `requests` fetcher from something else
         # Then the screenshot could be old, in any case, it's not used here.
         # REMOVE_REQUESTS_OLD_SCREENSHOTS - Mainly used for testing
@@ -110,3 +195,15 @@ class fetcher(Fetcher):
                 except Exception as e:
                     logger.warning(f"Failed to unlink screenshot: {screenshot} - {e}")
 
+
+# Plugin registration for built-in fetcher
+class RequestsFetcherPlugin:
+    """Plugin class that registers the requests fetcher as a built-in plugin."""
+
+    def register_content_fetcher(self):
+        """Register the requests fetcher"""
+        return ('html_requests', fetcher)
+
+
+# Create module-level instance for plugin registration
+requests_plugin = RequestsFetcherPlugin()

changedetectionio/content_fetchers/res/favicon-fetcher.js

@@ -0,0 +1,101 @@
+(async () => {
+  // Define the function inside the IIFE for console testing
+  window.getFaviconAsBlob = async function() {
+    const links = Array.from(document.querySelectorAll(
+      'link[rel~="apple-touch-icon"], link[rel~="icon"]'
+    ));
+
+    const icons = links.map(link => {
+      const sizesStr = link.getAttribute('sizes');
+      let size = 0;
+      if (sizesStr) {
+        const [w] = sizesStr.split('x').map(Number);
+        if (!isNaN(w)) size = w;
+      } else {
+        size = 16;
+      }
+      return {
+        size,
+        rel: link.getAttribute('rel'),
+        href: link.href,
+        hasSizes: !!sizesStr
+      };
+    });
+
+    // If no icons found, add fallback favicon.ico
+    if (icons.length === 0) {
+      icons.push({
+        size: 16,
+        rel: 'icon',
+        href: '/favicon.ico',
+        hasSizes: false
+      });
+    }
+
+    // sort preference: highest resolution first, then apple-touch-icon, then regular icons
+    icons.sort((a, b) => {
+      // First priority: actual size (highest first)
+      if (a.size !== b.size) {
+        return b.size - a.size;
+      }
+      
+      // Second priority: apple-touch-icon over regular icon
+      const isAppleA = /apple-touch-icon/.test(a.rel);
+      const isAppleB = /apple-touch-icon/.test(b.rel);
+      if (isAppleA && !isAppleB) return -1;
+      if (!isAppleA && isAppleB) return 1;
+      
+      // Third priority: icons with no size attribute (fallback icons) last
+      const hasNoSizeA = !a.hasSizes;
+      const hasNoSizeB = !b.hasSizes;
+      if (hasNoSizeA && !hasNoSizeB) return 1;
+      if (!hasNoSizeA && hasNoSizeB) return -1;
+      
+      return 0;
+    });
+
+    const timeoutMs = 2000;
+
+    for (const icon of icons) {
+      try {
+        const controller = new AbortController();
+        const timeout = setTimeout(() => controller.abort(), timeoutMs);
+
+        const resp = await fetch(icon.href, {
+          signal: controller.signal,
+          redirect: 'follow'
+        });
+
+        clearTimeout(timeout);
+
+        if (!resp.ok) {
+          continue;
+        }
+
+        const blob = await resp.blob();
+
+        // Convert blob to base64
+        const reader = new FileReader();
+        return await new Promise(resolve => {
+          reader.onloadend = () => {
+            resolve({
+              url: icon.href,
+              base64: reader.result.split(",")[1]
+            });
+          };
+          reader.readAsDataURL(blob);
+        });
+
+      } catch (e) {
+        continue;
+      }
+    }
+
+    // nothing found
+    return null;
+  };
+
+  // Auto-execute and return result for page.evaluate()
+  return await window.getFaviconAsBlob();
+})();
+

changedetectionio/content_fetchers/res/lock-elements-sizing.js

@@ -0,0 +1,107 @@
+/**
+ * Lock Element Dimensions for Screenshot Capture (First Viewport Only)
+ *
+ * THE PROBLEM:
+ * When taking full-page screenshots of tall pages, Chrome/Puppeteer/Playwright need to:
+ * 1. Temporarily change the viewport height to a large value (e.g., 800px → 3809px)
+ * 2. Take screenshots in chunks while scrolling
+ * 3. Stitch the chunks together
+ *
+ * However, changing the viewport height triggers CSS media queries like:
+ *   @media (min-height: 860px) { .ad { height: 250px; } }
+ *
+ * This causes elements (especially ads/headers) to resize during screenshot capture.
+ *
+ * THE SOLUTION:
+ * Lock element dimensions in the FIRST VIEWPORT ONLY with !important inline styles.
+ * This prevents headers, navigation, and top ads from resizing when viewport changes.
+ * We only lock the visible portion because:
+ * - Most layout shifts happen in headers/navbars/top ads
+ * - Locking only visible elements is 100x+ faster (100-200 elements vs 10,000+)
+ * - Below-fold content shifts don't affect visual comparison accuracy
+ *
+ * WHAT THIS SCRIPT DOES:
+ * 1. Gets current viewport height
+ * 2. Finds elements within first viewport (top of page to bottom of screen)
+ * 3. Locks their dimensions with !important inline styles
+ * 4. Disables ResizeObserver API (for JS-based resizing)
+ *
+ * USAGE:
+ * Execute this script BEFORE calling capture_full_page() / screenshot functions.
+ * Only enabled for image_ssim_diff processor (visual comparison).
+ * Default: OFF for performance.
+ *
+ * PERFORMANCE:
+ * - Only processes 100-300 elements (first viewport) vs 10,000+ (entire page)
+ * - Typically completes in 10-50ms
+ * - 100x+ faster than locking entire page
+ *
+ * @see https://github.com/dgtlmoon/changedetection.io/issues/XXXX
+ */
+
+(() => {
+    // Store original styles in a global WeakMap for later restoration
+    window.__elementSizingRestore = new WeakMap();
+
+    const start = performance.now();
+
+    // Get current viewport height (visible portion of page)
+    const viewportHeight = window.innerHeight;
+
+    // Get all elements and filter to FIRST VIEWPORT ONLY
+    // This dramatically reduces elements to process (100-300 vs 10,000+)
+    const allElements = Array.from(document.querySelectorAll('*'));
+
+    // BATCH READ PHASE: Get bounding rects and filter to viewport
+    const measurements = allElements.map(el => {
+        const rect = el.getBoundingClientRect();
+        const computed = window.getComputedStyle(el);
+
+        // Only lock elements in the first viewport (visible on initial page load)
+        // rect.top < viewportHeight means element starts within visible area
+        const inViewport = rect.top < viewportHeight && rect.top >= 0;
+        const hasSize = rect.height > 0 && rect.width > 0;
+
+        return inViewport && hasSize ? { el, computed, rect } : null;
+    }).filter(Boolean);  // Remove null entries
+
+    const elapsed = performance.now() - start;
+    console.log(`Locked first viewport elements: ${measurements.length} of ${allElements.length} total elements (viewport height: ${viewportHeight}px, took ${elapsed.toFixed(0)}ms)`);
+
+    // BATCH WRITE PHASE: Apply all inline styles without triggering layout
+    // No interleaved reads means browser can optimize style application
+    measurements.forEach(({el, computed, rect}) => {
+        // Save original inline style values BEFORE locking
+        const properties = ['height', 'min-height', 'max-height', 'width', 'min-width', 'max-width'];
+        const originalStyles = {};
+        properties.forEach(prop => {
+            originalStyles[prop] = {
+                value: el.style.getPropertyValue(prop),
+                priority: el.style.getPropertyPriority(prop)
+            };
+        });
+        window.__elementSizingRestore.set(el, originalStyles);
+
+        // Lock dimensions with !important to override media queries
+        if (rect.height > 0) {
+            el.style.setProperty('height', computed.height, 'important');
+            el.style.setProperty('min-height', computed.height, 'important');
+            el.style.setProperty('max-height', computed.height, 'important');
+        }
+        if (rect.width > 0) {
+            el.style.setProperty('width', computed.width, 'important');
+            el.style.setProperty('min-width', computed.width, 'important');
+            el.style.setProperty('max-width', computed.width, 'important');
+        }
+    });
+
+    // Also disable ResizeObserver for JS-based resizing
+    window.ResizeObserver = class {
+        constructor() {}
+        observe() {}
+        unobserve() {}
+        disconnect() {}
+    };
+
+    console.log(`✓ Element dimensions locked (${measurements.length} elements) to prevent media query changes during screenshot`);
+})();

changedetectionio/content_fetchers/res/stock-not-in-stock.js

@@ -17,7 +17,9 @@ async () => {
             'back in stock soon',
             'back-order or out of stock',
             'backordered',
+            'backorder',
             'benachrichtigt mich', // notify me
+            'binnenkort leverbaar', // coming soon
             'brak na stanie',
             'brak w magazynie',
             'coming soon',
@@ -38,12 +40,14 @@ async () => {
             'mail me when available',
             'message if back in stock',
             'mevcut değil',
+            'more on order',
             'nachricht bei',
             'nicht auf lager',
             'nicht lagernd',
             'nicht lieferbar',
             'nicht verfügbar',
             'nicht vorrätig',
+            'nicht mehr lieferbar',
             'nicht zur verfügung',
             'nie znaleziono produktów',
             'niet beschikbaar',
@@ -85,6 +89,7 @@ async () => {
             'tidak tersedia',
             'tijdelijk uitverkocht',
             'tiket tidak tersedia',
+            'to subscribe to back in stock',
             'tükendi',
             'unavailable nearby',
             'unavailable tickets',
@@ -119,8 +124,7 @@ async () => {
             return text.toLowerCase().trim();
         }
 
-        const negateOutOfStockRegex = new RegExp('^([0-9] in stock|add to cart|in stock)', 'ig');
-
+        const negateOutOfStockRegex = new RegExp('^([0-9] in stock|add to cart|in stock|arrives approximately)', 'ig');
         // The out-of-stock or in-stock-text is generally always above-the-fold
         // and often below-the-fold is a list of related products that may or may not contain trigger text
         // so it's good to filter to just the 'above the fold' elements

changedetectionio/content_fetchers/res/unlock-elements-sizing.js

@@ -0,0 +1,52 @@
+/**
+ * Unlock Element Dimensions After Screenshot Capture
+ *
+ * This script removes the inline !important styles that were applied by lock-elements-sizing.js
+ * and restores elements to their original state using the WeakMap created during locking.
+ *
+ * USAGE:
+ * Execute this script AFTER completing screenshot capture and restoring the viewport.
+ * This allows the page to return to its normal responsive behavior.
+ *
+ * WHAT THIS SCRIPT DOES:
+ * 1. Iterates through every element that was locked
+ * 2. Reads original style values from the global WeakMap
+ * 3. Restores original inline styles (or removes them if they weren't set originally)
+ * 4. Cleans up the WeakMap
+ *
+ * @see lock-elements-sizing.js for the locking mechanism
+ */
+
+(() => {
+    // Check if the restore map exists
+    if (!window.__elementSizingRestore) {
+        console.log('⚠ Element sizing restore map not found - elements may not have been locked');
+        return;
+    }
+
+    // Restore all locked dimension styles to their original state
+    document.querySelectorAll('*').forEach(el => {
+        const originalStyles = window.__elementSizingRestore.get(el);
+
+        if (originalStyles) {
+            const properties = ['height', 'min-height', 'max-height', 'width', 'min-width', 'max-width'];
+
+            properties.forEach(prop => {
+                const original = originalStyles[prop];
+
+                if (original.value) {
+                    // Restore original value with original priority
+                    el.style.setProperty(prop, original.value, original.priority || '');
+                } else {
+                    // Was not set originally, so remove it
+                    el.style.removeProperty(prop);
+                }
+            });
+        }
+    });
+
+    // Clean up the global WeakMap
+    delete window.__elementSizingRestore;
+
+    console.log('✓ Element dimensions unlocked - page restored to original state');
+})();

changedetectionio/content_fetchers/screenshot_handler.py

@@ -8,16 +8,42 @@ from loguru import logger
 
 from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT, SCREENSHOT_DEFAULT_QUALITY
 
+def stitch_images_worker_raw_bytes(pipe_conn, original_page_height, capture_height):
+    """
+    Stitch image chunks together in a separate process.
 
-def stitch_images_worker(pipe_conn, chunks_bytes, original_page_height, capture_height):
+    Uses spawn multiprocessing to isolate PIL's C-level memory allocation.
+    When the subprocess exits, the OS reclaims ALL memory including C-level allocations
+    that Python's GC cannot release. This prevents the ~50MB per stitch from accumulating
+    in the main process.
+
+    Trade-off: Adds 35MB resource_tracker subprocess, but prevents 500MB+ memory leak
+    in main process (much better at scale: 35GB vs 500GB for 1000 instances).
+
+    Args:
+        pipe_conn: Pipe connection to receive data and send result
+        original_page_height: Original page height in pixels
+        capture_height: Maximum capture height
+    """
     import os
     import io
+    import struct
     from PIL import Image, ImageDraw, ImageFont
 
     try:
+        # Receive chunk count as 4-byte integer (no pickle!)
+        count_bytes = pipe_conn.recv_bytes()
+        chunk_count = struct.unpack('I', count_bytes)[0]
+
+        # Receive each chunk as raw bytes (no pickle!)
+        chunks_bytes = []
+        for _ in range(chunk_count):
+            chunks_bytes.append(pipe_conn.recv_bytes())
 
         # Load images from byte chunks
         images = [Image.open(io.BytesIO(b)) for b in chunks_bytes]
+        del chunks_bytes
+
         total_height = sum(im.height for im in images)
         max_width = max(im.width for im in images)
 
@@ -27,47 +53,42 @@ def stitch_images_worker(pipe_conn, chunks_bytes, original_page_height, capture_
         for im in images:
             stitched.paste(im, (0, y_offset))
             y_offset += im.height
+            im.close()
+        del images
 
-        # Draw caption on top (overlaid, not extending canvas)
-        draw = ImageDraw.Draw(stitched)
-
+        # Draw caption only if page was trimmed
         if original_page_height > capture_height:
+            draw = ImageDraw.Draw(stitched)
             caption_text = f"WARNING: Screenshot was {original_page_height}px but trimmed to {capture_height}px because it was too long"
             padding = 10
-            font_size = 35
-            font_color = (255, 0, 0)
-            background_color = (255, 255, 255)
-
-
-            # Try to load a proper font
             try:
-                font = ImageFont.truetype("arial.ttf", font_size)
+                font = ImageFont.truetype("arial.ttf", 35)
             except IOError:
                 font = ImageFont.load_default()
 
             bbox = draw.textbbox((0, 0), caption_text, font=font)
             text_width = bbox[2] - bbox[0]
             text_height = bbox[3] - bbox[1]
-
-            # Draw white rectangle background behind text
-            rect_top = 0
-            rect_bottom = text_height + 2 * padding
-            draw.rectangle([(0, rect_top), (max_width, rect_bottom)], fill=background_color)
-
-            # Draw text centered horizontally, 10px padding from top of the rectangle
+            draw.rectangle([(0, 0), (max_width, text_height + 2 * padding)], fill=(255, 255, 255))
             text_x = (max_width - text_width) // 2
-            text_y = padding
-            draw.text((text_x, text_y), caption_text, font=font, fill=font_color)
+            draw.text((text_x, padding), caption_text, font=font, fill=(255, 0, 0))
 
-        # Encode and send image
+        # Encode and send
         output = io.BytesIO()
-        stitched.save(output, format="JPEG", quality=int(os.getenv("SCREENSHOT_QUALITY", SCREENSHOT_DEFAULT_QUALITY)))
-        pipe_conn.send_bytes(output.getvalue())
+        stitched.save(output, format="JPEG", quality=int(os.getenv("SCREENSHOT_QUALITY", SCREENSHOT_DEFAULT_QUALITY)), optimize=True)
+        result_bytes = output.getvalue()
 
         stitched.close()
+        del stitched
+        output.close()
+        del output
+
+        pipe_conn.send_bytes(result_bytes)
+        del result_bytes
+
     except Exception as e:
-        pipe_conn.send(f"error:{e}")
+        logger.error(f"Error in stitch_images_worker_raw_bytes: {e}")
+        error_msg = f"error:{e}".encode('utf-8')
+        pipe_conn.send_bytes(error_msg)
     finally:
         pipe_conn.close()
-
-

changedetectionio/content_fetchers/webdriver_selenium.py

@@ -4,22 +4,34 @@ import time
 from loguru import logger
 from changedetectionio.content_fetchers.base import Fetcher
 
+
 class fetcher(Fetcher):
     if os.getenv("WEBDRIVER_URL"):
-        fetcher_description = "WebDriver Chrome/Javascript via '{}'".format(os.getenv("WEBDRIVER_URL"))
+        fetcher_description = f"WebDriver Chrome/Javascript via \"{os.getenv('WEBDRIVER_URL', '')}\""
     else:
         fetcher_description = "WebDriver Chrome/Javascript"
 
-    # Configs for Proxy setup
-    # In the ENV vars, is prefixed with "webdriver_", so it is for example "webdriver_sslProxy"
-    selenium_proxy_settings_mappings = ['proxyType', 'ftpProxy', 'httpProxy', 'noProxy',
-                                        'proxyAutoconfigUrl', 'sslProxy', 'autodetect',
-                                        'socksProxy', 'socksVersion', 'socksUsername', 'socksPassword']
     proxy = None
+    proxy_url = None
 
-    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
-        super().__init__()
-        from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
+    # Capability flags
+    supports_browser_steps = False
+    supports_screenshots = True
+    supports_xpath_element_data = True
+
+    @classmethod
+    def get_status_icon_data(cls):
+        """Return Chrome browser icon data for WebDriver fetcher."""
+        return {
+            'filename': 'google-chrome-icon.png',
+            'alt': 'Using a Chrome browser',
+            'title': 'Using a Chrome browser'
+        }
+
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None, **kwargs):
+        super().__init__(**kwargs)
+        from urllib.parse import urlparse
+        from selenium.webdriver.common.proxy import Proxy
 
         # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
         if not custom_browser_connection_url:
@@ -28,107 +40,160 @@ class fetcher(Fetcher):
             self.browser_connection_is_custom = True
             self.browser_connection_url = custom_browser_connection_url
 
-        # If any proxy settings are enabled, then we should setup the proxy object
-        proxy_args = {}
-        for k in self.selenium_proxy_settings_mappings:
-            v = os.getenv('webdriver_' + k, False)
-            if v:
-                proxy_args[k] = v.strip('"')
+        ##### PROXY SETUP #####
 
-        # Map back standard HTTP_ and HTTPS_PROXY to webDriver httpProxy/sslProxy
-        if not proxy_args.get('webdriver_httpProxy') and self.system_http_proxy:
-            proxy_args['httpProxy'] = self.system_http_proxy
-        if not proxy_args.get('webdriver_sslProxy') and self.system_https_proxy:
-            proxy_args['httpsProxy'] = self.system_https_proxy
-
-        # Allows override the proxy on a per-request basis
-        if proxy_override is not None:
-            proxy_args['httpProxy'] = proxy_override
-
-        if proxy_args:
-            self.proxy = SeleniumProxy(raw=proxy_args)
-
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False,
-            empty_pages_are_a_change=False):
-
-        from selenium import webdriver
-        from selenium.webdriver.chrome.options import Options as ChromeOptions
-        from selenium.common.exceptions import WebDriverException
-        # request_body, request_method unused for now, until some magic in the future happens.
-
-        options = ChromeOptions()
-
-        # Load Chrome options from env
-        CHROME_OPTIONS = [
-            line.strip()
-            for line in os.getenv("CHROME_OPTIONS", "").strip().splitlines()
-            if line.strip()
+        proxy_sources = [
+            self.system_http_proxy,
+            self.system_https_proxy,
+            os.getenv('webdriver_proxySocks'),
+            os.getenv('webdriver_socksProxy'),
+            os.getenv('webdriver_proxyHttp'),
+            os.getenv('webdriver_httpProxy'),
+            os.getenv('webdriver_proxyHttps'),
+            os.getenv('webdriver_httpsProxy'),
+            os.getenv('webdriver_sslProxy'),
+            proxy_override,  # last one should override
         ]
+        # The built in selenium proxy handling is super unreliable!!! so we just grab which ever proxy setting we can find and throw it in --proxy-server=
+        for k in filter(None, proxy_sources):
+            if not k:
+                continue
+            self.proxy_url = k.strip()
 
-        for opt in CHROME_OPTIONS:
-            options.add_argument(opt)
+    async def run(self,
+                  fetch_favicon=True,
+                  current_include_filters=None,
+                  empty_pages_are_a_change=False,
+                  ignore_status_codes=False,
+                  is_binary=False,
+                  request_body=None,
+                  request_headers=None,
+                  request_method=None,
+                  screenshot_format=None,
+                  timeout=None,
+                  url=None,
+                  watch_uuid=None,
+                  ):
 
-        if self.proxy:
-            options.proxy = self.proxy
+        import asyncio
 
-        self.driver = webdriver.Remote(
-            command_executor=self.browser_connection_url,
-            options=options)
+        # Wrap the entire selenium operation in a thread executor
+        def _run_sync():
+            from selenium.webdriver.chrome.options import Options as ChromeOptions
+            # request_body, request_method unused for now, until some magic in the future happens.
 
-        try:
-            self.driver.get(url)
-        except WebDriverException as e:
-            # Be sure we close the session window
-            self.quit()
-            raise
+            options = ChromeOptions()
 
-        if not "--window-size" in os.getenv("CHROME_OPTIONS", ""):
-            self.driver.set_window_size(1280, 1024)
+            # Load Chrome options from env
+            CHROME_OPTIONS = [
+                line.strip()
+                for line in os.getenv("CHROME_OPTIONS", "").strip().splitlines()
+                if line.strip()
+            ]
 
-        self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+            for opt in CHROME_OPTIONS:
+                options.add_argument(opt)
 
-        if self.webdriver_js_execute_code is not None:
-            self.driver.execute_script(self.webdriver_js_execute_code)
-            # Selenium doesn't automatically wait for actions as good as Playwright, so wait again
-            self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+            # 1. proxy_config /Proxy(proxy_config) selenium object is REALLY unreliable
+            # 2. selenium-wire cant be used because the websocket version conflicts with pypeteer-ng
+            # 3. selenium only allows ONE runner at a time by default!
+            # 4. driver must use quit() or it will continue to block/hold the selenium process!!
 
+            if self.proxy_url:
+                options.add_argument(f'--proxy-server={self.proxy_url}')
 
-        # @todo - how to check this? is it possible?
-        self.status_code = 200
-        # @todo somehow we should try to get this working for WebDriver
-        # raise EmptyReply(url=url, status_code=r.status_code)
-
-        # @todo - dom wait loaded?
-        time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay)
-        self.content = self.driver.page_source
-        self.headers = {}
-
-        self.screenshot = self.driver.get_screenshot_as_png()
-
-    # Does the connection to the webdriver work? run a test connection.
-    def is_ready(self):
-        from selenium import webdriver
-        from selenium.webdriver.chrome.options import Options as ChromeOptions
-
-        self.driver = webdriver.Remote(
-            command_executor=self.command_executor,
-            options=ChromeOptions())
-
-        # driver.quit() seems to cause better exceptions
-        self.quit()
-        return True
-
-    def quit(self, watch=None):
-        if self.driver:
+            from selenium.webdriver.remote.remote_connection import RemoteConnection
+            from selenium.webdriver.remote.webdriver import WebDriver as RemoteWebDriver
+            driver = None
             try:
-                self.driver.quit()
+                # Create the RemoteConnection and set timeout (e.g., 30 seconds)
+                remote_connection = RemoteConnection(
+                    self.browser_connection_url,
+                )
+                remote_connection.set_timeout(30)  # seconds
+
+                # Now create the driver with the RemoteConnection
+                driver = RemoteWebDriver(
+                    command_executor=remote_connection,
+                    options=options
+                )
+
+                driver.set_page_load_timeout(int(os.getenv("WEBDRIVER_PAGELOAD_TIMEOUT", 45)))
             except Exception as e:
-                logger.debug(f"Content Fetcher > Exception in chrome shutdown/quit {str(e)}")
+                if driver:
+                    driver.quit()
+                raise e
+
+            try:
+                driver.get(url)
+
+                if not "--window-size" in os.getenv("CHROME_OPTIONS", ""):
+                    driver.set_window_size(1280, 1024)
+
+                driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+
+                if self.webdriver_js_execute_code is not None:
+                    driver.execute_script(self.webdriver_js_execute_code)
+                    # Selenium doesn't automatically wait for actions as good as Playwright, so wait again
+                    driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+
+                # @todo - how to check this? is it possible?
+                self.status_code = 200
+                # @todo somehow we should try to get this working for WebDriver
+                # raise EmptyReply(url=url, status_code=r.status_code)
+
+                # @todo - dom wait loaded?
+                import time
+                time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay)
+                self.content = driver.page_source
+                self.headers = {}
+
+                # Selenium always captures as PNG, convert to JPEG if needed
+                screenshot_png = driver.get_screenshot_as_png()
+
+                # Convert to JPEG if requested (for smaller file size)
+                if self.screenshot_format and self.screenshot_format.upper() == 'JPEG':
+                    from PIL import Image
+                    import io
+                    img = Image.open(io.BytesIO(screenshot_png))
+                    # Convert to RGB if needed (JPEG doesn't support transparency)
+                    # Always convert non-RGB modes to RGB to ensure JPEG compatibility
+                    if img.mode in ('RGBA', 'LA', 'P', 'PA'):
+                        # Handle transparency by compositing onto white background
+                        if img.mode == 'P':
+                            img = img.convert('RGBA')
+                        background = Image.new('RGB', img.size, (255, 255, 255))
+                        if img.mode in ('RGBA', 'LA', 'PA'):
+                            background.paste(img, mask=img.split()[-1])  # Use alpha channel as mask
+                        img = background
+                    elif img.mode != 'RGB':
+                        # For other modes, direct conversion
+                        img = img.convert('RGB')
+                    jpeg_buffer = io.BytesIO()
+                    img.save(jpeg_buffer, format='JPEG', quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
+                    self.screenshot = jpeg_buffer.getvalue()
+                    img.close()
+                else:
+                    self.screenshot = screenshot_png
+            except Exception as e:
+                driver.quit()
+                raise e
+
+            driver.quit()
+
+        # Run the selenium operations in a thread pool to avoid blocking the event loop
+        loop = asyncio.get_event_loop()
+        await loop.run_in_executor(None, _run_sync)
+
+
+# Plugin registration for built-in fetcher
+class WebDriverSeleniumFetcherPlugin:
+    """Plugin class that registers the WebDriver Selenium fetcher as a built-in plugin."""
+
+    def register_content_fetcher(self):
+        """Register the WebDriver Selenium fetcher"""
+        return ('html_webdriver', fetcher)
+
+
+# Create module-level instance for plugin registration
+webdriver_selenium_plugin = WebDriverSeleniumFetcherPlugin()

changedetectionio/custom_queue.py

@@ -0,0 +1,537 @@
+import queue
+import asyncio
+from blinker import signal
+from loguru import logger
+
+
+class NotificationQueue(queue.Queue):
+    """
+    Extended Queue that sends a 'notification_event' signal when notifications are added.
+    
+    This class extends the standard Queue and adds a signal emission after a notification
+    is put into the queue. The signal includes the watch UUID if available.
+    """
+    
+    def __init__(self, maxsize=0):
+        super().__init__(maxsize)
+        try:
+            self.notification_event_signal = signal('notification_event')
+        except Exception as e:
+            logger.critical(f"Exception creating notification_event signal: {e}")
+
+    def put(self, item, block=True, timeout=None):
+        # Call the parent's put method first
+        super().put(item, block, timeout)
+        
+        # After putting the notification in the queue, emit signal with watch UUID
+        try:
+            if self.notification_event_signal and isinstance(item, dict):
+                watch_uuid = item.get('uuid')
+                if watch_uuid:
+                    # Send the notification_event signal with the watch UUID
+                    self.notification_event_signal.send(watch_uuid=watch_uuid)
+                    logger.trace(f"NotificationQueue: Emitted notification_event signal for watch UUID {watch_uuid}")
+                else:
+                    # Send signal without UUID for system notifications
+                    self.notification_event_signal.send()
+                    logger.trace("NotificationQueue: Emitted notification_event signal for system notification")
+        except Exception as e:
+            logger.error(f"Exception emitting notification_event signal: {e}")
+
+class SignalPriorityQueue(queue.PriorityQueue):
+    """
+    Extended PriorityQueue that sends a signal when items with a UUID are added.
+    
+    This class extends the standard PriorityQueue and adds a signal emission
+    after an item is put into the queue. If the item contains a UUID, the signal
+    is sent with that UUID as a parameter.
+    """
+    
+    def __init__(self, maxsize=0):
+        super().__init__(maxsize)
+        try:
+            self.queue_length_signal = signal('queue_length')
+        except Exception as e:
+            logger.critical(f"Exception: {e}")
+
+    def put(self, item, block=True, timeout=None):
+        # Call the parent's put method first
+        super().put(item, block, timeout)
+
+        # After putting the item in the queue, check if it has a UUID and emit signal
+        if hasattr(item, 'item') and isinstance(item.item, dict) and 'uuid' in item.item:
+            uuid = item.item['uuid']
+            # Get the signal and send it if it exists
+            watch_check_update = signal('watch_check_update')
+            if watch_check_update:
+                # NOTE: This would block other workers from .put/.get while this signal sends
+                # Signal handlers may iterate the queue/datastore while holding locks
+                watch_check_update.send(watch_uuid=uuid)
+        
+        # Send queue_length signal with current queue size
+        try:
+
+            if self.queue_length_signal:
+                self.queue_length_signal.send(length=self.qsize())
+        except Exception as e:
+            logger.critical(f"Exception: {e}")
+
+    def get(self, block=True, timeout=None):
+        # Call the parent's get method first
+        item = super().get(block, timeout)
+        
+        # Send queue_length signal with current queue size
+        try:
+            if self.queue_length_signal:
+                self.queue_length_signal.send(length=self.qsize())
+        except Exception as e:
+            logger.critical(f"Exception: {e}")
+        return item
+    
+    def get_uuid_position(self, target_uuid):
+        """
+        Find the position of a watch UUID in the priority queue.
+        Optimized for large queues - O(n) complexity instead of O(n log n).
+        
+        Args:
+            target_uuid: The UUID to search for
+            
+        Returns:
+            dict: Contains position info or None if not found
+                - position: 0-based position in queue (0 = next to be processed)
+                - total_items: total number of items in queue
+                - priority: the priority value of the found item
+        """
+        with self.mutex:
+            queue_list = list(self.queue)
+            total_items = len(queue_list)
+            
+            if total_items == 0:
+                return {
+                    'position': None,
+                    'total_items': 0,
+                    'priority': None,
+                    'found': False
+                }
+            
+            # Find the target item and its priority first - O(n)
+            target_item = None
+            target_priority = None
+            
+            for item in queue_list:
+                if (hasattr(item, 'item') and 
+                    isinstance(item.item, dict) and 
+                    item.item.get('uuid') == target_uuid):
+                    target_item = item
+                    target_priority = item.priority
+                    break
+            
+            if target_item is None:
+                return {
+                    'position': None,
+                    'total_items': total_items,
+                    'priority': None,
+                    'found': False
+                }
+            
+            # Count how many items have higher priority (lower numbers) - O(n)
+            position = 0
+            for item in queue_list:
+                # Items with lower priority numbers are processed first
+                if item.priority < target_priority:
+                    position += 1
+                elif item.priority == target_priority and item != target_item:
+                    # For same priority, count items that come before this one
+                    # (Note: this is approximate since heap order isn't guaranteed for equal priorities)
+                    position += 1
+            
+            return {
+                'position': position,
+                'total_items': total_items,
+                'priority': target_priority,
+                'found': True
+            }
+    
+    def get_all_queued_uuids(self, limit=None, offset=0):
+        """
+        Get UUIDs currently in the queue with their positions.
+        For large queues, use limit/offset for pagination.
+        
+        Args:
+            limit: Maximum number of items to return (None = all)
+            offset: Number of items to skip (for pagination)
+        
+        Returns:
+            dict: Contains items and metadata
+                - items: List of dicts with uuid, position, and priority
+                - total_items: Total number of items in queue
+                - returned_items: Number of items returned
+                - has_more: Whether there are more items after this page
+        """
+        with self.mutex:
+            queue_list = list(self.queue)
+            total_items = len(queue_list)
+            
+            if total_items == 0:
+                return {
+                    'items': [],
+                    'total_items': 0,
+                    'returned_items': 0,
+                    'has_more': False
+                }
+            
+            # For very large queues, warn about performance
+            if total_items > 1000 and limit is None:
+                logger.warning(f"Getting all {total_items} queued items without limit - this may be slow")
+            
+            # Sort only if we need exact positions (expensive for large queues)
+            if limit is not None and limit <= 100:
+                # For small requests, we can afford to sort
+                queue_items = sorted(queue_list)
+                end_idx = min(offset + limit, len(queue_items)) if limit else len(queue_items)
+                items_to_process = queue_items[offset:end_idx]
+                
+                result = []
+                for position, item in enumerate(items_to_process, start=offset):
+                    if (hasattr(item, 'item') and 
+                        isinstance(item.item, dict) and 
+                        'uuid' in item.item):
+                        
+                        result.append({
+                            'uuid': item.item['uuid'],
+                            'position': position,
+                            'priority': item.priority
+                        })
+                
+                return {
+                    'items': result,
+                    'total_items': total_items,
+                    'returned_items': len(result),
+                    'has_more': (offset + len(result)) < total_items
+                }
+            else:
+                # For large requests, return items with approximate positions
+                # This is much faster O(n) instead of O(n log n)
+                result = []
+                processed = 0
+                skipped = 0
+                
+                for item in queue_list:
+                    if (hasattr(item, 'item') and 
+                        isinstance(item.item, dict) and 
+                        'uuid' in item.item):
+                        
+                        if skipped < offset:
+                            skipped += 1
+                            continue
+                        
+                        if limit and processed >= limit:
+                            break
+                        
+                        # Approximate position based on priority comparison
+                        approx_position = sum(1 for other in queue_list if other.priority < item.priority)
+                        
+                        result.append({
+                            'uuid': item.item['uuid'],
+                            'position': approx_position,  # Approximate
+                            'priority': item.priority
+                        })
+                        processed += 1
+                
+                return {
+                    'items': result,
+                    'total_items': total_items,
+                    'returned_items': len(result),
+                    'has_more': (offset + len(result)) < total_items,
+                    'note': 'Positions are approximate for performance with large queues'
+                }
+    
+    def get_queue_summary(self):
+        """
+        Get a quick summary of queue state without expensive operations.
+        O(n) complexity - fast even for large queues.
+        
+        Returns:
+            dict: Queue summary statistics
+        """
+        with self.mutex:
+            queue_list = list(self.queue)
+            total_items = len(queue_list)
+            
+            if total_items == 0:
+                return {
+                    'total_items': 0,
+                    'priority_breakdown': {},
+                    'immediate_items': 0,
+                    'clone_items': 0,
+                    'scheduled_items': 0
+                }
+            
+            # Count items by priority type - O(n)
+            immediate_items = 0  # priority 1
+            clone_items = 0      # priority 5  
+            scheduled_items = 0  # priority > 100 (timestamps)
+            priority_counts = {}
+            
+            for item in queue_list:
+                priority = item.priority
+                priority_counts[priority] = priority_counts.get(priority, 0) + 1
+                
+                if priority == 1:
+                    immediate_items += 1
+                elif priority == 5:
+                    clone_items += 1
+                elif priority > 100:
+                    scheduled_items += 1
+            
+            return {
+                'total_items': total_items,
+                'priority_breakdown': priority_counts,
+                'immediate_items': immediate_items,
+                'clone_items': clone_items,
+                'scheduled_items': scheduled_items,
+                'min_priority': min(priority_counts.keys()) if priority_counts else None,
+                'max_priority': max(priority_counts.keys()) if priority_counts else None
+            }
+
+
+class AsyncSignalPriorityQueue(asyncio.PriorityQueue):
+    """
+    Async version of SignalPriorityQueue that sends signals when items are added/removed.
+    
+    This class extends asyncio.PriorityQueue and maintains the same signal behavior
+    as the synchronous version for real-time UI updates.
+    """
+    
+    def __init__(self, maxsize=0):
+        super().__init__(maxsize)
+        try:
+            self.queue_length_signal = signal('queue_length')
+        except Exception as e:
+            logger.critical(f"Exception: {e}")
+
+    async def put(self, item):
+        # Call the parent's put method first
+        await super().put(item)
+
+        # After putting the item in the queue, check if it has a UUID and emit signal
+        if hasattr(item, 'item') and isinstance(item.item, dict) and 'uuid' in item.item:
+            uuid = item.item['uuid']
+            # Get the signal and send it if it exists
+            watch_check_update = signal('watch_check_update')
+            if watch_check_update:
+                # NOTE: This would block other workers from .put/.get while this signal sends
+                # Signal handlers may iterate the queue/datastore while holding locks
+                watch_check_update.send(watch_uuid=uuid)
+        
+        # Send queue_length signal with current queue size
+        try:
+            if self.queue_length_signal:
+                self.queue_length_signal.send(length=self.qsize())
+        except Exception as e:
+            logger.critical(f"Exception: {e}")
+
+    async def get(self):
+        # Call the parent's get method first
+        item = await super().get()
+        
+        # Send queue_length signal with current queue size
+        try:
+            if self.queue_length_signal:
+                self.queue_length_signal.send(length=self.qsize())
+        except Exception as e:
+            logger.critical(f"Exception: {e}")
+        return item
+    
+    @property
+    def queue(self):
+        """
+        Provide compatibility with sync PriorityQueue.queue access
+        Returns the internal queue for template access
+        """
+        return self._queue if hasattr(self, '_queue') else []
+    
+    def get_uuid_position(self, target_uuid):
+        """
+        Find the position of a watch UUID in the async priority queue.
+        Optimized for large queues - O(n) complexity instead of O(n log n).
+        
+        Args:
+            target_uuid: The UUID to search for
+            
+        Returns:
+            dict: Contains position info or None if not found
+                - position: 0-based position in queue (0 = next to be processed)
+                - total_items: total number of items in queue
+                - priority: the priority value of the found item
+        """
+        queue_list = list(self._queue)
+        total_items = len(queue_list)
+        
+        if total_items == 0:
+            return {
+                'position': None,
+                'total_items': 0,
+                'priority': None,
+                'found': False
+            }
+        
+        # Find the target item and its priority first - O(n)
+        target_item = None
+        target_priority = None
+        
+        for item in queue_list:
+            if (hasattr(item, 'item') and 
+                isinstance(item.item, dict) and 
+                item.item.get('uuid') == target_uuid):
+                target_item = item
+                target_priority = item.priority
+                break
+        
+        if target_item is None:
+            return {
+                'position': None,
+                'total_items': total_items,
+                'priority': None,
+                'found': False
+            }
+        
+        # Count how many items have higher priority (lower numbers) - O(n)
+        position = 0
+        for item in queue_list:
+            if item.priority < target_priority:
+                position += 1
+            elif item.priority == target_priority and item != target_item:
+                position += 1
+        
+        return {
+            'position': position,
+            'total_items': total_items,
+            'priority': target_priority,
+            'found': True
+        }
+    
+    def get_all_queued_uuids(self, limit=None, offset=0):
+        """
+        Get UUIDs currently in the async queue with their positions.
+        For large queues, use limit/offset for pagination.
+        
+        Args:
+            limit: Maximum number of items to return (None = all)
+            offset: Number of items to skip (for pagination)
+        
+        Returns:
+            dict: Contains items and metadata (same structure as sync version)
+        """
+        queue_list = list(self._queue)
+        total_items = len(queue_list)
+        
+        if total_items == 0:
+            return {
+                'items': [],
+                'total_items': 0,
+                'returned_items': 0,
+                'has_more': False
+            }
+        
+        # Same logic as sync version but without mutex
+        if limit is not None and limit <= 100:
+            queue_items = sorted(queue_list)
+            end_idx = min(offset + limit, len(queue_items)) if limit else len(queue_items)
+            items_to_process = queue_items[offset:end_idx]
+            
+            result = []
+            for position, item in enumerate(items_to_process, start=offset):
+                if (hasattr(item, 'item') and 
+                    isinstance(item.item, dict) and 
+                    'uuid' in item.item):
+                    
+                    result.append({
+                        'uuid': item.item['uuid'],
+                        'position': position,
+                        'priority': item.priority
+                    })
+            
+            return {
+                'items': result,
+                'total_items': total_items,
+                'returned_items': len(result),
+                'has_more': (offset + len(result)) < total_items
+            }
+        else:
+            # Fast approximate positions for large queues
+            result = []
+            processed = 0
+            skipped = 0
+            
+            for item in queue_list:
+                if (hasattr(item, 'item') and 
+                    isinstance(item.item, dict) and 
+                    'uuid' in item.item):
+                    
+                    if skipped < offset:
+                        skipped += 1
+                        continue
+                    
+                    if limit and processed >= limit:
+                        break
+                    
+                    approx_position = sum(1 for other in queue_list if other.priority < item.priority)
+                    
+                    result.append({
+                        'uuid': item.item['uuid'],
+                        'position': approx_position,
+                        'priority': item.priority
+                    })
+                    processed += 1
+            
+            return {
+                'items': result,
+                'total_items': total_items,
+                'returned_items': len(result),
+                'has_more': (offset + len(result)) < total_items,
+                'note': 'Positions are approximate for performance with large queues'
+            }
+    
+    def get_queue_summary(self):
+        """
+        Get a quick summary of async queue state.
+        O(n) complexity - fast even for large queues.
+        """
+        queue_list = list(self._queue)
+        total_items = len(queue_list)
+        
+        if total_items == 0:
+            return {
+                'total_items': 0,
+                'priority_breakdown': {},
+                'immediate_items': 0,
+                'clone_items': 0,
+                'scheduled_items': 0
+            }
+        
+        immediate_items = 0
+        clone_items = 0
+        scheduled_items = 0
+        priority_counts = {}
+        
+        for item in queue_list:
+            priority = item.priority
+            priority_counts[priority] = priority_counts.get(priority, 0) + 1
+            
+            if priority == 1:
+                immediate_items += 1
+            elif priority == 5:
+                clone_items += 1
+            elif priority > 100:
+                scheduled_items += 1
+        
+        return {
+            'total_items': total_items,
+            'priority_breakdown': priority_counts,
+            'immediate_items': immediate_items,
+            'clone_items': clone_items,
+            'scheduled_items': scheduled_items,
+            'min_priority': min(priority_counts.keys()) if priority_counts else None,
+            'max_priority': max(priority_counts.keys()) if priority_counts else None
+        }

changedetectionio/diff.py

@@ -1,113 +0,0 @@
-import difflib
-from typing import List, Iterator, Union
-
-REMOVED_STYLE = "background-color: #fadad7; color: #b30000;"
-ADDED_STYLE = "background-color: #eaf2c2; color: #406619;"
-
-def same_slicer(lst: List[str], start: int, end: int) -> List[str]:
-    """Return a slice of the list, or a single element if start == end."""
-    return lst[start:end] if start != end else [lst[start]]
-
-def customSequenceMatcher(
-    before: List[str],
-    after: List[str],
-    include_equal: bool = False,
-    include_removed: bool = True,
-    include_added: bool = True,
-    include_replaced: bool = True,
-    include_change_type_prefix: bool = True,
-    html_colour: bool = False
-) -> Iterator[List[str]]:
-    """
-    Compare two sequences and yield differences based on specified parameters.
-
-    Args:
-        before (List[str]): Original sequence
-        after (List[str]): Modified sequence
-        include_equal (bool): Include unchanged parts
-        include_removed (bool): Include removed parts
-        include_added (bool): Include added parts
-        include_replaced (bool): Include replaced parts
-        include_change_type_prefix (bool): Add prefixes to indicate change types
-        html_colour (bool): Use HTML background colors for differences
-
-    Yields:
-        List[str]: Differences between sequences
-    """
-    cruncher = difflib.SequenceMatcher(isjunk=lambda x: x in " \t", a=before, b=after)
-
-
-
-    for tag, alo, ahi, blo, bhi in cruncher.get_opcodes():
-        if include_equal and tag == 'equal':
-            yield before[alo:ahi]
-        elif include_removed and tag == 'delete':
-            if html_colour:
-                yield [f'<span style="{REMOVED_STYLE}">{line}</span>' for line in same_slicer(before, alo, ahi)]
-            else:
-                yield [f"(removed) {line}" for line in same_slicer(before, alo, ahi)] if include_change_type_prefix else same_slicer(before, alo, ahi)
-        elif include_replaced and tag == 'replace':
-            if html_colour:
-                yield [f'<span style="{REMOVED_STYLE}">{line}</span>' for line in same_slicer(before, alo, ahi)] + \
-                      [f'<span style="{ADDED_STYLE}">{line}</span>' for line in same_slicer(after, blo, bhi)]
-            else:
-                yield [f"(changed) {line}" for line in same_slicer(before, alo, ahi)] + \
-                      [f"(into) {line}" for line in same_slicer(after, blo, bhi)] if include_change_type_prefix else same_slicer(before, alo, ahi) + same_slicer(after, blo, bhi)
-        elif include_added and tag == 'insert':
-            if html_colour:
-                yield [f'<span style="{ADDED_STYLE}">{line}</span>' for line in same_slicer(after, blo, bhi)]
-            else:
-                yield [f"(added) {line}" for line in same_slicer(after, blo, bhi)] if include_change_type_prefix else same_slicer(after, blo, bhi)
-
-def render_diff(
-    previous_version_file_contents: str,
-    newest_version_file_contents: str,
-    include_equal: bool = False,
-    include_removed: bool = True,
-    include_added: bool = True,
-    include_replaced: bool = True,
-    line_feed_sep: str = "\n",
-    include_change_type_prefix: bool = True,
-    patch_format: bool = False,
-    html_colour: bool = False
-) -> str:
-    """
-    Render the difference between two file contents.
-
-    Args:
-        previous_version_file_contents (str): Original file contents
-        newest_version_file_contents (str): Modified file contents
-        include_equal (bool): Include unchanged parts
-        include_removed (bool): Include removed parts
-        include_added (bool): Include added parts
-        include_replaced (bool): Include replaced parts
-        line_feed_sep (str): Separator for lines in output
-        include_change_type_prefix (bool): Add prefixes to indicate change types
-        patch_format (bool): Use patch format for output
-        html_colour (bool): Use HTML background colors for differences
-
-    Returns:
-        str: Rendered difference
-    """
-    newest_lines = [line.rstrip() for line in newest_version_file_contents.splitlines()]
-    previous_lines = [line.rstrip() for line in previous_version_file_contents.splitlines()] if previous_version_file_contents else []
-
-    if patch_format:
-        patch = difflib.unified_diff(previous_lines, newest_lines)
-        return line_feed_sep.join(patch)
-
-    rendered_diff = customSequenceMatcher(
-        before=previous_lines,
-        after=newest_lines,
-        include_equal=include_equal,
-        include_removed=include_removed,
-        include_added=include_added,
-        include_replaced=include_replaced,
-        include_change_type_prefix=include_change_type_prefix,
-        html_colour=html_colour
-    )
-
-    def flatten(lst: List[Union[str, List[str]]]) -> str:
-        return line_feed_sep.join(flatten(x) if isinstance(x, list) else x for x in lst)
-
-    return flatten(rendered_diff)

changedetectionio/diff/__init__.py

@@ -0,0 +1,479 @@
+"""
+Diff rendering module for change detection.
+
+This module provides functions for rendering differences between text content,
+with support for various output formats and tokenization strategies.
+"""
+
+import difflib
+from typing import List, Iterator, Union
+from loguru import logger
+import diff_match_patch as dmp_module
+import re
+import time
+
+from .tokenizers import TOKENIZERS, tokenize_words_and_html
+
+# Remember! gmail, outlook etc dont support <style> must be inline.
+# Gmail: strips <ins> and <del> tags entirely.
+# This is for the WHOLE line background style
+REMOVED_STYLE = "background-color: #fadad7; color: #b30000;"
+ADDED_STYLE = "background-color: #eaf2c2; color: #406619;"
+HTML_REMOVED_STYLE = REMOVED_STYLE  # Export alias for handler.py
+HTML_ADDED_STYLE = ADDED_STYLE      # Export alias for handler.py
+
+# Darker backgrounds for nested highlighting (changed parts within lines)
+REMOVED_INNER_STYLE = "background-color: #ff867a; color: #111;"
+ADDED_INNER_STYLE = "background-color: #b2e841; color: #444;"
+HTML_CHANGED_STYLE = REMOVED_STYLE
+HTML_CHANGED_INTO_STYLE = ADDED_STYLE
+
+# Placemarker constants - these get replaced by apply_service_tweaks() in handler.py
+# Something that cant get escaped to HTML by accident
+REMOVED_PLACEMARKER_OPEN = '@removed_PLACEMARKER_OPEN'
+REMOVED_PLACEMARKER_CLOSED = '@removed_PLACEMARKER_CLOSED'
+
+ADDED_PLACEMARKER_OPEN = '@added_PLACEMARKER_OPEN'
+ADDED_PLACEMARKER_CLOSED = '@added_PLACEMARKER_CLOSED'
+
+CHANGED_PLACEMARKER_OPEN = '@changed_PLACEMARKER_OPEN'
+CHANGED_PLACEMARKER_CLOSED = '@changed_PLACEMARKER_CLOSED'
+
+CHANGED_INTO_PLACEMARKER_OPEN = '@changed_into_PLACEMARKER_OPEN'
+CHANGED_INTO_PLACEMARKER_CLOSED = '@changed_into_PLACEMARKER_CLOSED'
+
+# Compiled regex patterns for performance
+WHITESPACE_NORMALIZE_RE = re.compile(r'\s+')
+
+
+def render_inline_word_diff(before_line: str, after_line: str, ignore_junk: bool = False, markdown_style: str = None, tokenizer: str = 'words_and_html') -> tuple[str, bool]:
+    """
+    Render word-level differences between two lines inline using diff-match-patch library.
+
+    Args:
+        before_line: Original line text
+        after_line: Modified line text
+        ignore_junk: Ignore whitespace-only changes
+        markdown_style: Unused (kept for backwards compatibility)
+        tokenizer: Name of tokenizer to use from TOKENIZERS registry (default: 'words_and_html')
+
+    Returns:
+        tuple[str, bool]: (diff output with inline word-level highlighting, has_changes flag)
+    """
+    # Normalize whitespace if ignore_junk is enabled
+    if ignore_junk:
+        # Normalize whitespace: replace multiple spaces/tabs with single space
+        before_normalized = WHITESPACE_NORMALIZE_RE.sub(' ', before_line)
+        after_normalized = WHITESPACE_NORMALIZE_RE.sub(' ', after_line)
+    else:
+        before_normalized = before_line
+        after_normalized = after_line
+
+    # Use diff-match-patch with word-level tokenization
+    # Strategy: Use linesToChars to treat words as atomic units
+    dmp = dmp_module.diff_match_patch()
+
+    # Get the tokenizer function from the registry
+    tokenizer_func = TOKENIZERS.get(tokenizer, tokenize_words_and_html)
+
+    # Tokenize both lines using the selected tokenizer
+    before_tokens = tokenizer_func(before_normalized)
+    after_tokens = tokenizer_func(after_normalized or ' ')
+
+    # Create mappings for linesToChars (using it for word-mode)
+    # Join tokens with newline so each "line" is a token
+    before_text = '\n'.join(before_tokens)
+    after_text = '\n'.join(after_tokens)
+
+    # Use linesToChars for word-mode diffing
+    lines_result = dmp.diff_linesToChars(before_text, after_text)
+    line_before, line_after, line_array = lines_result
+
+    # Perform diff on the encoded strings
+    diffs = dmp.diff_main(line_before, line_after, False)
+
+    # Convert back to original text
+    dmp.diff_charsToLines(diffs, line_array)
+
+    # Remove the newlines we added for tokenization
+    diffs = [(op, text.replace('\n', '')) for op, text in diffs]
+
+    # DON'T apply semantic cleanup here - it would break token boundaries
+    # (e.g., "63" -> "66" would become "6" + "3" vs "6" + "6")
+    # We want to preserve the tokenizer's word boundaries
+
+    # Check if there are any changes
+    has_changes = any(op != 0 for op, _ in diffs)
+
+    if ignore_junk and not has_changes:
+        return after_line, False
+
+    # Check if the whole line is replaced (no unchanged content)
+    whole_line_replaced = not any(op == 0 and text.strip() for op, text in diffs)
+
+    # Build the output using placemarkers
+    # When whole line is replaced, wrap entire removed content once and entire added content once
+    if whole_line_replaced:
+        removed_tokens = []
+        added_tokens = []
+
+        for op, text in diffs:
+            if op == 0:  # Equal (e.g., whitespace tokens in common positions)
+                # Include in both removed and added to preserve spacing
+                removed_tokens.append(text)
+                added_tokens.append(text)
+            elif op == -1:  # Deletion
+                removed_tokens.append(text)
+            elif op == 1:  # Insertion
+                added_tokens.append(text)
+
+        # Join all tokens and wrap the entire string once for removed, once for added
+        result_parts = []
+
+        if removed_tokens:
+            removed_full = ''.join(removed_tokens).rstrip()
+            trailing_removed = ''.join(removed_tokens)[len(removed_full):] if len(''.join(removed_tokens)) > len(removed_full) else ''
+            result_parts.append(f'{CHANGED_PLACEMARKER_OPEN}{removed_full}{CHANGED_PLACEMARKER_CLOSED}{trailing_removed}')
+
+        if added_tokens:
+            if result_parts:  # Add newline between removed and added
+                result_parts.append('\n')
+            added_full = ''.join(added_tokens).rstrip()
+            trailing_added = ''.join(added_tokens)[len(added_full):] if len(''.join(added_tokens)) > len(added_full) else ''
+            result_parts.append(f'{CHANGED_INTO_PLACEMARKER_OPEN}{added_full}{CHANGED_INTO_PLACEMARKER_CLOSED}{trailing_added}')
+
+        return ''.join(result_parts), has_changes
+    else:
+        # Inline changes within the line
+        result_parts = []
+        for op, text in diffs:
+            if op == 0:  # Equal
+                result_parts.append(text)
+            elif op == 1:  # Insertion
+                # Don't wrap empty content (e.g., whitespace-only tokens after rstrip)
+                content = text.rstrip()
+                trailing = text[len(content):] if len(text) > len(content) else ''
+                if content:
+                    result_parts.append(f'{ADDED_PLACEMARKER_OPEN}{content}{ADDED_PLACEMARKER_CLOSED}{trailing}')
+                else:
+                    result_parts.append(trailing)
+            elif op == -1:  # Deletion
+                # Don't wrap empty content (e.g., whitespace-only tokens after rstrip)
+                content = text.rstrip()
+                trailing = text[len(content):] if len(text) > len(content) else ''
+                if content:
+                    result_parts.append(f'{REMOVED_PLACEMARKER_OPEN}{content}{REMOVED_PLACEMARKER_CLOSED}{trailing}')
+                else:
+                    result_parts.append(trailing)
+
+        return ''.join(result_parts), has_changes
+
+
+def render_nested_line_diff(before_line: str, after_line: str, ignore_junk: bool = False, tokenizer: str = 'words_and_html') -> tuple[str, str, bool]:
+    """
+    Render line-level differences with nested highlighting for changed parts.
+
+    Returns two separate lines:
+    - Before line: light red background with dark red on removed parts
+    - After line: light green background with dark green on added parts
+
+    Args:
+        before_line: Original line text
+        after_line: Modified line text
+        ignore_junk: Ignore whitespace-only changes
+        tokenizer: Name of tokenizer to use from TOKENIZERS registry
+
+    Returns:
+        tuple[str, str, bool]: (before_with_highlights, after_with_highlights, has_changes)
+    """
+    # Normalize whitespace if ignore_junk is enabled
+    if ignore_junk:
+        before_normalized = WHITESPACE_NORMALIZE_RE.sub(' ', before_line)
+        after_normalized = WHITESPACE_NORMALIZE_RE.sub(' ', after_line)
+    else:
+        before_normalized = before_line
+        after_normalized = after_line
+
+    # Use diff-match-patch with word-level tokenization
+    dmp = dmp_module.diff_match_patch()
+
+    # Get the tokenizer function from the registry
+    tokenizer_func = TOKENIZERS.get(tokenizer, tokenize_words_and_html)
+
+    # Tokenize both lines
+    before_tokens = tokenizer_func(before_normalized)
+    after_tokens = tokenizer_func(after_normalized or ' ')
+
+    # Create mappings for linesToChars
+    before_text = '\n'.join(before_tokens)
+    after_text = '\n'.join(after_tokens)
+
+    # Use linesToChars for word-mode diffing
+    lines_result = dmp.diff_linesToChars(before_text, after_text)
+    line_before, line_after, line_array = lines_result
+
+    # Perform diff on the encoded strings
+    diffs = dmp.diff_main(line_before, line_after, False)
+
+    # Convert back to original text
+    dmp.diff_charsToLines(diffs, line_array)
+
+    # Remove the newlines we added for tokenization
+    diffs = [(op, text.replace('\n', '')) for op, text in diffs]
+
+    # DON'T apply semantic cleanup here - it would break token boundaries
+    # (e.g., "63" -> "66" would become "6" + "3" vs "6" + "6")
+    # We want to preserve the tokenizer's word boundaries
+
+    # Check if there are any changes
+    has_changes = any(op != 0 for op, _ in diffs)
+
+    if ignore_junk and not has_changes:
+        return before_line, after_line, False
+
+    # Build the before line (with nested highlighting for removed parts)
+    before_parts = []
+    for op, text in diffs:
+        if op == 0:  # Equal
+            before_parts.append(text)
+        elif op == -1:  # Deletion (in before)
+            before_parts.append(f'<span style="{REMOVED_INNER_STYLE}">{text}</span>')
+        # Skip insertions (op == 1) for the before line
+
+    before_content = ''.join(before_parts)
+
+    # Build the after line (with nested highlighting for added parts)
+    after_parts = []
+    for op, text in diffs:
+        if op == 0:  # Equal
+            after_parts.append(text)
+        elif op == 1:  # Insertion (in after)
+            after_parts.append(f'<span style="{ADDED_INNER_STYLE}">{text}</span>')
+        # Skip deletions (op == -1) for the after line
+
+    after_content = ''.join(after_parts)
+
+    # Wrap content with placemarkers (inner HTML highlighting is preserved)
+    before_html = f'{CHANGED_PLACEMARKER_OPEN}{before_content}{CHANGED_PLACEMARKER_CLOSED}'
+    after_html = f'{CHANGED_INTO_PLACEMARKER_OPEN}{after_content}{CHANGED_INTO_PLACEMARKER_CLOSED}'
+
+    return before_html, after_html, has_changes
+
+
+def same_slicer(lst: List[str], start: int, end: int) -> List[str]:
+    """Return a slice of the list, or a single element if start == end."""
+    return lst[start:end] if start != end else [lst[start]]
+
+def customSequenceMatcher(
+    before: List[str],
+    after: List[str],
+    include_equal: bool = False,
+    include_removed: bool = True,
+    include_added: bool = True,
+    include_replaced: bool = True,
+    include_change_type_prefix: bool = True,
+    word_diff: bool = False,
+    context_lines: int = 0,
+    case_insensitive: bool = False,
+    ignore_junk: bool = False,
+    tokenizer: str = 'words_and_html'
+) -> Iterator[List[str]]:
+    """
+    Compare two sequences and yield differences based on specified parameters.
+
+    Args:
+        before (List[str]): Original sequence
+        after (List[str]): Modified sequence
+        include_equal (bool): Include unchanged parts
+        include_removed (bool): Include removed parts
+        include_added (bool): Include added parts
+        include_replaced (bool): Include replaced parts
+        include_change_type_prefix (bool): Add prefixes to indicate change types
+        word_diff (bool): Use word-level diffing for replaced lines (controls inline rendering)
+        context_lines (int): Number of unchanged lines to show around changes (like grep -C)
+        case_insensitive (bool): Perform case-insensitive comparison
+        ignore_junk (bool): Ignore whitespace-only changes
+        tokenizer (str): Name of tokenizer to use from TOKENIZERS registry (default: 'words_and_html')
+
+    Yields:
+        List[str]: Differences between sequences
+    """
+    # Prepare sequences for comparison (lowercase if case-insensitive, normalize whitespace if ignore_junk)
+    def prepare_line(line):
+        if case_insensitive:
+            line = line.lower()
+        if ignore_junk:
+            # Normalize whitespace: replace multiple spaces/tabs with single space
+            line = WHITESPACE_NORMALIZE_RE.sub(' ', line)
+        return line
+
+    compare_before = [prepare_line(line) for line in before]
+    compare_after = [prepare_line(line) for line in after]
+
+    cruncher = difflib.SequenceMatcher(isjunk=lambda x: x in " \t", a=compare_before, b=compare_after)
+
+    # When context_lines is set and include_equal is False, we need to track which equal lines to include
+    if context_lines > 0 and not include_equal:
+        opcodes = list(cruncher.get_opcodes())
+        # Mark equal ranges that should be included based on context
+        included_equal_ranges = set()
+
+        for i, (tag, alo, ahi, blo, bhi) in enumerate(opcodes):
+            if tag != 'equal':
+                # Include context lines before this change
+                for j in range(max(0, i - 1), i):
+                    if opcodes[j][0] == 'equal':
+                        prev_alo, prev_ahi = opcodes[j][1], opcodes[j][2]
+                        # Include last N lines of the previous equal block
+                        context_start = max(prev_alo, prev_ahi - context_lines)
+                        for line_num in range(context_start, prev_ahi):
+                            included_equal_ranges.add(line_num)
+
+                # Include context lines after this change
+                for j in range(i + 1, min(len(opcodes), i + 2)):
+                    if opcodes[j][0] == 'equal':
+                        next_alo, next_ahi = opcodes[j][1], opcodes[j][2]
+                        # Include first N lines of the next equal block
+                        context_end = min(next_ahi, next_alo + context_lines)
+                        for line_num in range(next_alo, context_end):
+                            included_equal_ranges.add(line_num)
+
+    # Remember! gmail, outlook etc dont support <style> must be inline.
+    # Gmail: strips <ins> and <del> tags entirely.
+    for tag, alo, ahi, blo, bhi in cruncher.get_opcodes():
+        if tag == 'equal':
+            if include_equal:
+                yield before[alo:ahi]
+            elif context_lines > 0:
+                # Only include equal lines that are in the context range
+                context_lines_to_include = [before[i] for i in range(alo, ahi) if i in included_equal_ranges]
+                if context_lines_to_include:
+                    yield context_lines_to_include
+        elif include_removed and tag == 'delete':
+            if include_change_type_prefix:
+                yield [f'{REMOVED_PLACEMARKER_OPEN}{line}{REMOVED_PLACEMARKER_CLOSED}' for line in same_slicer(before, alo, ahi)]
+            else:
+                yield same_slicer(before, alo, ahi)
+        elif include_replaced and tag == 'replace':
+            before_lines = same_slicer(before, alo, ahi)
+            after_lines = same_slicer(after, blo, bhi)
+
+            # Use inline word-level diff for single line replacements when word_diff is enabled
+            if word_diff and len(before_lines) == 1 and len(after_lines) == 1:
+                inline_diff, has_changes = render_inline_word_diff(before_lines[0], after_lines[0], ignore_junk=ignore_junk, tokenizer=tokenizer)
+                # Check if there are any actual changes (not just whitespace when ignore_junk is enabled)
+                if ignore_junk and not has_changes:
+                    # No real changes, skip this line
+                    continue
+                yield [inline_diff]
+            else:
+                # Fall back to line-level diff for multi-line changes
+                if include_change_type_prefix:
+                    yield [f'{CHANGED_PLACEMARKER_OPEN}{line}{CHANGED_PLACEMARKER_CLOSED}' for line in before_lines] + \
+                          [f'{CHANGED_INTO_PLACEMARKER_OPEN}{line}{CHANGED_INTO_PLACEMARKER_CLOSED}' for line in after_lines]
+                else:
+                    yield before_lines + after_lines
+        elif include_added and tag == 'insert':
+            if include_change_type_prefix:
+                yield [f'{ADDED_PLACEMARKER_OPEN}{line}{ADDED_PLACEMARKER_CLOSED}' for line in same_slicer(after, blo, bhi)]
+            else:
+                yield same_slicer(after, blo, bhi)
+
+def render_diff(
+    previous_version_file_contents: str,
+    newest_version_file_contents: str,
+    include_equal: bool = False,
+    include_removed: bool = True,
+    include_added: bool = True,
+    include_replaced: bool = True,
+    include_change_type_prefix: bool = True,
+    patch_format: bool = False,
+    word_diff: bool = True,
+    context_lines: int = 0,
+    case_insensitive: bool = False,
+    ignore_junk: bool = False,
+    tokenizer: str = 'words_and_html'
+) -> str:
+    """
+    Render the difference between two file contents.
+
+    Args:
+        previous_version_file_contents (str): Original file contents
+        newest_version_file_contents (str): Modified file contents
+        include_equal (bool): Include unchanged parts
+        include_removed (bool): Include removed parts
+        include_added (bool): Include added parts
+        include_replaced (bool): Include replaced parts
+        include_change_type_prefix (bool): Add prefixes to indicate change types
+        patch_format (bool): Use patch format for output
+        word_diff (bool): Use word-level diffing for replaced lines (controls inline rendering)
+        context_lines (int): Number of unchanged lines to show around changes (like grep -C)
+        case_insensitive (bool): Perform case-insensitive comparison, By default the test_json_diff/process.py is case sensitive, so this follows same logic
+        ignore_junk (bool): Ignore whitespace-only changes
+        tokenizer (str): Name of tokenizer to use from TOKENIZERS registry (default: 'words_and_html')
+
+    Returns:
+        str: Rendered difference
+    """
+    newest_lines = [line.rstrip() for line in newest_version_file_contents.splitlines()]
+    previous_lines = [line.rstrip() for line in previous_version_file_contents.splitlines()] if previous_version_file_contents else []
+    now = time.time()
+    logger.debug(
+        f"diff options: "
+        f"include_equal={include_equal}, "
+        f"include_removed={include_removed}, "
+        f"include_added={include_added}, "
+        f"include_replaced={include_replaced}, "
+        f"include_change_type_prefix={include_change_type_prefix}, "
+        f"patch_format={patch_format}, "
+        f"word_diff={word_diff}, "
+        f"context_lines={context_lines}, "
+        f"case_insensitive={case_insensitive}, "
+        f"ignore_junk={ignore_junk}, "
+        f"tokenizer={tokenizer}"
+    )
+    if patch_format:
+        patch = difflib.unified_diff(previous_lines, newest_lines)
+        return "\n".join(patch)
+
+    rendered_diff = customSequenceMatcher(
+        before=previous_lines,
+        after=newest_lines,
+        include_equal=include_equal,
+        include_removed=include_removed,
+        include_added=include_added,
+        include_replaced=include_replaced,
+        include_change_type_prefix=include_change_type_prefix,
+        word_diff=word_diff,
+        context_lines=context_lines,
+        case_insensitive=case_insensitive,
+        ignore_junk=ignore_junk,
+        tokenizer=tokenizer
+    )
+
+    def flatten(lst: List[Union[str, List[str]]]) -> str:
+        result = []
+        for x in lst:
+            if isinstance(x, list):
+                result.extend(x)
+            else:
+                result.append(x)
+        return "\n".join(result)
+
+    logger.debug(f"Diff generated in {time.time() - now:.2f}s")
+
+    return flatten(rendered_diff)
+
+
+# Export main public API
+__all__ = [
+    'render_diff',
+    'customSequenceMatcher',
+    'render_inline_word_diff',
+    'render_nested_line_diff',
+    'TOKENIZERS',
+    'REMOVED_STYLE',
+    'ADDED_STYLE',
+    'REMOVED_INNER_STYLE',
+    'ADDED_INNER_STYLE',
+]

changedetectionio/diff/tokenizers/__init__.py

@@ -0,0 +1,23 @@
+"""
+Tokenizers for diff operations.
+
+This module provides various tokenization strategies for use with the diff system.
+New tokenizers can be easily added by:
+1. Creating a new module in this directory
+2. Importing and registering it in the TOKENIZERS dictionary below
+"""
+
+from .natural_text import tokenize_words
+from .words_and_html import tokenize_words_and_html
+
+# Tokenizer registry - maps tokenizer names to functions
+TOKENIZERS = {
+    'words': tokenize_words,
+    'words_and_html': tokenize_words_and_html,
+}
+
+__all__ = [
+    'tokenize_words',
+    'tokenize_words_and_html',
+    'TOKENIZERS',
+]

changedetectionio/diff/tokenizers/natural_text.py

@@ -0,0 +1,44 @@
+"""
+Simple word tokenizer using whitespace boundaries.
+
+This is a simpler tokenizer that treats all whitespace as token boundaries
+without special handling for HTML tags or other markup.
+"""
+
+from typing import List
+
+
+def tokenize_words(text: str) -> List[str]:
+    """
+    Split text into words using simple whitespace boundaries.
+
+    This is a simpler tokenizer that treats all whitespace as token boundaries
+    without special handling for HTML tags.
+
+    Args:
+        text: Input text to tokenize
+
+    Returns:
+        List of tokens (words and whitespace)
+
+    Examples:
+        >>> tokenize_words("Hello world")
+        ['Hello', ' ', 'world']
+        >>> tokenize_words("one  two")
+        ['one', ' ', ' ', 'two']
+    """
+    tokens = []
+    current = ''
+
+    for char in text:
+        if char.isspace():
+            if current:
+                tokens.append(current)
+                current = ''
+            tokens.append(char)
+        else:
+            current += char
+
+    if current:
+        tokens.append(current)
+    return tokens

changedetectionio/diff/tokenizers/words_and_html.py

@@ -0,0 +1,61 @@
+"""
+Tokenizer that preserves HTML tags as atomic units while splitting on whitespace.
+
+This tokenizer is specifically designed for HTML content where:
+- HTML tags should remain intact (e.g., '<p>', '<a href="...">')
+- Whitespace tokens are preserved for accurate diff reconstruction
+- Words are split on whitespace boundaries
+"""
+
+from typing import List
+
+
+def tokenize_words_and_html(text: str) -> List[str]:
+    """
+    Split text into words and boundaries (spaces, HTML tags).
+
+    This tokenizer preserves HTML tags as atomic units while splitting on whitespace.
+    Useful for content that contains HTML markup.
+
+    Args:
+        text: Input text to tokenize
+
+    Returns:
+        List of tokens (words, spaces, HTML tags)
+
+    Examples:
+        >>> tokenize_words_and_html("<p>Hello world</p>")
+        ['<p>', 'Hello', ' ', 'world', '</p>']
+        >>> tokenize_words_and_html("<a href='test.com'>link</a>")
+        ['<a href=\\'test.com\\'>', 'link', '</a>']
+    """
+    tokens = []
+    current = ''
+    in_tag = False
+
+    for char in text:
+        if char == '<':
+            # Start of HTML tag
+            if current:
+                tokens.append(current)
+                current = ''
+            current = '<'
+            in_tag = True
+        elif char == '>' and in_tag:
+            # End of HTML tag
+            current += '>'
+            tokens.append(current)
+            current = ''
+            in_tag = False
+        elif char.isspace() and not in_tag:
+            # Space outside of tag
+            if current:
+                tokens.append(current)
+                current = ''
+            tokens.append(char)
+        else:
+            current += char
+
+    if current:
+        tokens.append(current)
+    return tokens

changedetectionio/favicon_utils.py

@@ -0,0 +1,43 @@
+"""
+Favicon utilities for changedetection.io
+Handles favicon MIME type detection with caching
+"""
+
+from functools import lru_cache
+
+
+@lru_cache(maxsize=1000)
+def get_favicon_mime_type(filepath):
+    """
+    Detect MIME type of favicon by reading file content using puremagic.
+    Results are cached to avoid repeatedly reading the same files.
+
+    Args:
+        filepath: Full path to the favicon file
+
+    Returns:
+        MIME type string (e.g., 'image/png')
+    """
+    mime = None
+
+    try:
+        import puremagic
+        with open(filepath, 'rb') as f:
+            content_bytes = f.read(200)  # Read first 200 bytes
+
+        detections = puremagic.magic_string(content_bytes)
+        if detections:
+            mime = detections[0].mime_type
+    except Exception:
+        pass
+
+    # Fallback to mimetypes if puremagic fails
+    if not mime:
+        import mimetypes
+        mime, _ = mimetypes.guess_type(filepath)
+
+    # Final fallback based on extension
+    if not mime:
+        mime = 'image/x-icon' if filepath.endswith('.ico') else 'image/png'
+
+    return mime

changedetectionio/forms.py

@@ -2,15 +2,19 @@ import os
 import re
 from loguru import logger
 from wtforms.widgets.core import TimeInput
+from flask_babel import lazy_gettext as _l, gettext
 
-from changedetectionio.blueprint.rss import RSS_FORMAT_TYPES
+from changedetectionio.blueprint.rss import RSS_FORMAT_TYPES, RSS_TEMPLATE_TYPE_OPTIONS, RSS_TEMPLATE_HTML_DEFAULT
 from changedetectionio.conditions.form import ConditionFormRow
+from changedetectionio.notification_service import NotificationContextData
 from changedetectionio.strtobool import strtobool
+from changedetectionio import processors
 
 from wtforms import (
     BooleanField,
     Form,
     Field,
+    FloatField,
     IntegerField,
     RadioField,
     SelectField,
@@ -23,15 +27,15 @@ from wtforms import (
 )
 from flask_wtf.file import FileField, FileAllowed
 from wtforms.fields import FieldList
+from wtforms.utils import unset_value
 
 from wtforms.validators import ValidationError
 
-from validators.url import url as url_validator
-
+from changedetectionio.widgets import TernaryNoneBooleanField
 
 # default
 # each select <option data-enabled="enabled-0-0"
-from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
+from changedetectionio.browser_steps.browser_steps import browser_step_ui_config
 
 from changedetectionio import html_tools, content_fetchers
 
@@ -54,6 +58,8 @@ valid_method = {
 
 default_method = 'GET'
 allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
+REQUIRE_ATLEAST_ONE_TIME_PART_MESSAGE_DEFAULT=_l('At least one time interval (weeks, days, hours, minutes, or seconds) must be specified.')
+REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT=_l('At least one time interval (weeks, days, hours, minutes, or seconds) must be specified when not using global settings.')
 
 class StringListField(StringField):
     widget = widgets.TextArea()
@@ -153,7 +159,7 @@ class TimeStringField(Field):
             time_str = valuelist[0]
             # Simple validation for HH:MM format
             if not time_str or len(time_str.split(":")) != 2:
-                raise ValidationError("Invalid time format. Use HH:MM.")
+                raise ValidationError(_l("Invalid time format. Use HH:MM."))
             self.data = time_str
 
 
@@ -169,15 +175,15 @@ class validateTimeZoneName(object):
         from zoneinfo import available_timezones
         python_timezones = available_timezones()
         if field.data and field.data not in python_timezones:
-            raise ValidationError("Not a valid timezone name")
+            raise ValidationError(_l("Not a valid timezone name"))
 
 class ScheduleLimitDaySubForm(Form):
-    enabled = BooleanField("not set", default=True)
-    start_time = TimeStringField("Start At", default="00:00", validators=[validators.Optional()])
-    duration = FormField(TimeDurationForm, label="Run duration")
+    enabled = BooleanField(_l("not set"), default=True)
+    start_time = TimeStringField(_l("Start At"), default="00:00", validators=[validators.Optional()])
+    duration = FormField(TimeDurationForm, label=_l("Run duration"))
 
 class ScheduleLimitForm(Form):
-    enabled = BooleanField("Use time scheduler", default=False)
+    enabled = BooleanField(_l("Use time scheduler"), default=False)
     # Because the label for=""" doesnt line up/work with the actual checkbox
     monday = FormField(ScheduleLimitDaySubForm, label="")
     tuesday = FormField(ScheduleLimitDaySubForm, label="")
@@ -187,7 +193,7 @@ class ScheduleLimitForm(Form):
     saturday = FormField(ScheduleLimitDaySubForm, label="")
     sunday = FormField(ScheduleLimitDaySubForm, label="")
 
-    timezone = StringField("Optional timezone to run in",
+    timezone = StringField(_l("Optional timezone to run in"),
                                   render_kw={"list": "timezones"},
                                   validators=[validateTimeZoneName()]
                                   )
@@ -201,50 +207,206 @@ class ScheduleLimitForm(Form):
         **kwargs,
     ):
         super().__init__(formdata, obj, prefix, data, meta, **kwargs)
-        self.monday.form.enabled.label.text="Monday"
-        self.tuesday.form.enabled.label.text = "Tuesday"
-        self.wednesday.form.enabled.label.text = "Wednesday"
-        self.thursday.form.enabled.label.text = "Thursday"
-        self.friday.form.enabled.label.text = "Friday"
-        self.saturday.form.enabled.label.text = "Saturday"
-        self.sunday.form.enabled.label.text = "Sunday"
+        self.monday.form.enabled.label.text=_l("Monday")
+        self.tuesday.form.enabled.label.text = _l("Tuesday")
+        self.wednesday.form.enabled.label.text = _l("Wednesday")
+        self.thursday.form.enabled.label.text = _l("Thursday")
+        self.friday.form.enabled.label.text = _l("Friday")
+        self.saturday.form.enabled.label.text = _l("Saturday")
+        self.sunday.form.enabled.label.text = _l("Sunday")
+
+
+def validate_time_between_check_has_values(form):
+    """
+    Custom validation function for TimeBetweenCheckForm.
+    Returns True if at least one time interval field has a value > 0.
+    """
+    res = any([
+        form.weeks.data and int(form.weeks.data) > 0,
+        form.days.data and int(form.days.data) > 0,
+        form.hours.data and int(form.hours.data) > 0,
+        form.minutes.data and int(form.minutes.data) > 0,
+        form.seconds.data and int(form.seconds.data) > 0
+    ])
+
+    return res
+
+
+class RequiredTimeInterval(object):
+    """
+    WTForms validator that ensures at least one time interval field has a value > 0.
+    Use this with FormField(TimeBetweenCheckForm, validators=[RequiredTimeInterval()]).
+    """
+    def __init__(self, message=None):
+        self.message = message or _l('At least one time interval (weeks, days, hours, minutes, or seconds) must be specified.')
+
+    def __call__(self, form, field):
+        if not validate_time_between_check_has_values(field.form):
+            raise ValidationError(self.message)
 
 
 class TimeBetweenCheckForm(Form):
-    weeks = IntegerField('Weeks', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
-    days = IntegerField('Days', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
-    hours = IntegerField('Hours', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
-    minutes = IntegerField('Minutes', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
-    seconds = IntegerField('Seconds', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
+    weeks = IntegerField(_l('Weeks'), validators=[validators.Optional(), validators.NumberRange(min=0, message=_l("Should contain zero or more seconds"))])
+    days = IntegerField(_l('Days'), validators=[validators.Optional(), validators.NumberRange(min=0, message=_l("Should contain zero or more seconds"))])
+    hours = IntegerField(_l('Hours'), validators=[validators.Optional(), validators.NumberRange(min=0, message=_l("Should contain zero or more seconds"))])
+    minutes = IntegerField(_l('Minutes'), validators=[validators.Optional(), validators.NumberRange(min=0, message=_l("Should contain zero or more seconds"))])
+    seconds = IntegerField(_l('Seconds'), validators=[validators.Optional(), validators.NumberRange(min=0, message=_l("Should contain zero or more seconds"))])
     # @todo add total seconds minimum validatior = minimum_seconds_recheck_time
 
+    def __init__(self, formdata=None, obj=None, prefix="", data=None, meta=None, **kwargs):
+        super().__init__(formdata, obj, prefix, data, meta, **kwargs)
+        self.require_at_least_one = kwargs.get('require_at_least_one', False)
+        self.require_at_least_one_message = kwargs.get('require_at_least_one_message', REQUIRE_ATLEAST_ONE_TIME_PART_MESSAGE_DEFAULT)
+
+    def validate(self, **kwargs):
+        """Custom validation that can optionally require at least one time interval."""
+        # Run normal field validation first
+        if not super().validate(**kwargs):
+            return False
+
+        # Apply optional "at least one" validation
+        if self.require_at_least_one:
+            if not validate_time_between_check_has_values(self):
+                # Add error to the form's general errors (not field-specific)
+                if not hasattr(self, '_formdata_errors'):
+                    self._formdata_errors = []
+                self._formdata_errors.append(self.require_at_least_one_message)
+                return False
+
+        return True
+
+
+class EnhancedFormField(FormField):
+    """
+    An enhanced FormField that supports conditional validation with top-level error messages.
+    Adds a 'top_errors' property for validation errors at the FormField level.
+    """
+
+    def __init__(self, form_class, label=None, validators=None, separator="-",
+                 conditional_field=None, conditional_message=None, conditional_test_function=None, **kwargs):
+        """
+        Initialize EnhancedFormField with optional conditional validation.
+
+        :param conditional_field: Name of the field this FormField depends on (e.g. 'time_between_check_use_default')
+        :param conditional_message: Error message to show when validation fails
+        :param conditional_test_function: Custom function to test if FormField has valid values.
+                                        Should take self.form as parameter and return True if valid.
+        """
+        super().__init__(form_class, label, validators, separator, **kwargs)
+        self.top_errors = []
+        self.conditional_field = conditional_field
+        self.conditional_message = conditional_message or "At least one field must have a value when not using defaults."
+        self.conditional_test_function = conditional_test_function
+
+    def validate(self, form, extra_validators=()):
+        """
+        Custom validation that supports conditional logic and stores top-level errors.
+        """
+        self.top_errors = []
+
+        # First run the normal FormField validation
+        base_valid = super().validate(form, extra_validators)
+
+        # Apply conditional validation if configured
+        if self.conditional_field and hasattr(form, self.conditional_field):
+            conditional_field_obj = getattr(form, self.conditional_field)
+
+            # If the conditional field is False/unchecked, check if this FormField has any values
+            if not conditional_field_obj.data:
+                # Use custom test function if provided, otherwise use generic fallback
+                if self.conditional_test_function:
+                    has_any_value = self.conditional_test_function(self.form)
+                else:
+                    # Generic fallback - check if any field has truthy data
+                    has_any_value = any(field.data for field in self.form if hasattr(field, 'data') and field.data)
+
+                if not has_any_value:
+                    self.top_errors.append(self.conditional_message)
+                    base_valid = False
+
+        return base_valid
+
+
+class RequiredFormField(FormField):
+    """
+    A FormField that passes require_at_least_one=True to TimeBetweenCheckForm.
+    Use this when you want the sub-form to always require at least one value.
+    """
+
+    def __init__(self, form_class, label=None, validators=None, separator="-", **kwargs):
+        super().__init__(form_class, label, validators, separator, **kwargs)
+
+    def process(self, formdata, data=unset_value, extra_filters=None):
+        if extra_filters:
+            raise TypeError(
+                "FormField cannot take filters, as the encapsulated"
+                "data is not mutable."
+            )
+
+        if data is unset_value:
+            try:
+                data = self.default()
+            except TypeError:
+                data = self.default
+            self._obj = data
+
+        self.object_data = data
+
+        prefix = self.name + self.separator
+        # Pass require_at_least_one=True to the sub-form
+        if isinstance(data, dict):
+            self.form = self.form_class(formdata=formdata, prefix=prefix, require_at_least_one=True, **data)
+        else:
+            self.form = self.form_class(formdata=formdata, obj=data, prefix=prefix, require_at_least_one=True)
+
+    @property
+    def errors(self):
+        """Include sub-form validation errors"""
+        form_errors = self.form.errors
+        # Add any general form errors to a special 'form' key
+        if hasattr(self.form, '_formdata_errors') and self.form._formdata_errors:
+            form_errors = dict(form_errors)  # Make a copy
+            form_errors['form'] = self.form._formdata_errors
+        return form_errors
+
+
 # Separated by  key:value
 class StringDictKeyValue(StringField):
     widget = widgets.TextArea()
 
     def _value(self):
         if self.data:
-            output = u''
-            for k in self.data.keys():
-                output += "{}: {}\r\n".format(k, self.data[k])
-
+            output = ''
+            for k, v in self.data.items():
+                output += f"{k}: {v}\r\n"
             return output
         else:
-            return u''
+            return ''
 
-    # incoming
+    # incoming data processing + validation
     def process_formdata(self, valuelist):
+        self.data = {}
+        errors = []
         if valuelist:
-            self.data = {}
-            # Remove empty strings
-            cleaned = list(filter(None, valuelist[0].split("\n")))
-            for s in cleaned:
-                parts = s.strip().split(':', 1)
-                if len(parts) == 2:
-                    self.data.update({parts[0].strip(): parts[1].strip()})
+            # Remove empty strings (blank lines)
+            cleaned = [line.strip() for line in valuelist[0].split("\n") if line.strip()]
+            for idx, s in enumerate(cleaned, start=1):
+                if ':' not in s:
+                    errors.append(f"Line {idx} is missing a ':' separator.")
+                    continue
+                parts = s.split(':', 1)
+                key = parts[0].strip()
+                value = parts[1].strip()
 
-        else:
-            self.data = {}
+                if not key:
+                    errors.append(f"Line {idx} has an empty key.")
+                if not value:
+                    errors.append(f"Line {idx} has an empty value.")
+
+                self.data[key] = value
+
+        if errors:
+            raise ValidationError("Invalid input:\n" + "\n".join(errors))
 
 class ValidateContentFetcherIsReady(object):
     """
@@ -308,11 +470,16 @@ class ValidateAppRiseServers(object):
         import apprise
         from .notification.apprise_plugin.assets import apprise_asset
         from .notification.apprise_plugin.custom_handlers import apprise_http_custom_handler  # noqa: F401
+        from changedetectionio.jinja2_custom import render as jinja_render
 
         apobj = apprise.Apprise(asset=apprise_asset)
 
         for server_url in field.data:
-            url = server_url.strip()
+            generic_notification_context_data = NotificationContextData()
+            # Make sure something is atleast in all those regular token fields
+            generic_notification_context_data.set_random_for_validation()
+
+            url = jinja_render(template_str=server_url.strip(), **generic_notification_context_data).strip()
             if url.startswith("#"):
                 continue
 
@@ -325,10 +492,8 @@ class ValidateJinja2Template(object):
     Validates that a {token} is from a valid set
     """
     def __call__(self, form, field):
-        from changedetectionio import notification
-
+        from changedetectionio.jinja2_custom import create_jinja_env
         from jinja2 import BaseLoader, TemplateSyntaxError, UndefinedError
-        from jinja2.sandbox import ImmutableSandboxedEnvironment
         from jinja2.meta import find_undeclared_variables
         import jinja2.exceptions
 
@@ -336,9 +501,13 @@ class ValidateJinja2Template(object):
         joined_data = ' '.join(map(str, field.data)) if isinstance(field.data, list) else f"{field.data}"
 
         try:
-            jinja2_env = ImmutableSandboxedEnvironment(loader=BaseLoader)
-            jinja2_env.globals.update(notification.valid_tokens)
-            # Extra validation tokens provided on the form_class(... extra_tokens={}) setup
+            # Use the shared helper to create a properly configured environment
+            jinja2_env = create_jinja_env(loader=BaseLoader)
+
+            # Add notification tokens for validation
+            static_token_placeholders = NotificationContextData()
+            static_token_placeholders.set_random_for_validation()
+            jinja2_env.globals.update(static_token_placeholders)
             if hasattr(field, 'extra_notification_tokens'):
                 jinja2_env.globals.update(field.extra_notification_tokens)
 
@@ -350,6 +519,7 @@ class ValidateJinja2Template(object):
         except jinja2.exceptions.SecurityError as e:
             raise ValidationError(f"This is not a valid Jinja2 template: {e}") from e
 
+        # Check for undeclared variables
         ast = jinja2_env.parse(joined_data)
         undefined = ", ".join(find_undeclared_variables(ast))
         if undefined:
@@ -372,19 +542,23 @@ class validateURL(object):
 
 
 def validate_url(test_url):
-    # If hosts that only contain alphanumerics are allowed ("localhost" for example)
-    try:
-        url_validator(test_url, simple_host=allow_simplehost)
-    except validators.ValidationError:
-        #@todo check for xss
-        message = f"'{test_url}' is not a valid URL."
+    from changedetectionio.validate_url import is_safe_valid_url
+    if not is_safe_valid_url(test_url):
         # This should be wtforms.validators.
-        raise ValidationError(message)
+        raise ValidationError('Watch protocol is not permitted or invalid URL format')
+
+
+class ValidateSinglePythonRegexString(object):
+    def __init__(self, message=None):
+        self.message = message
+
+    def __call__(self, form, field):
+        try:
+            re.compile(field.data)
+        except re.error:
+            message = field.gettext('RegEx \'%s\' is not a valid regular expression.')
+            raise ValidationError(message % (field.data))
 
-    from .model.Watch import is_safe_url
-    if not is_safe_url(test_url):
-        # This should be wtforms.validators.
-        raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX or incorrect URL format')
 
 class ValidateListRegex(object):
     """
@@ -404,6 +578,7 @@ class ValidateListRegex(object):
                     message = field.gettext('RegEx \'%s\' is not a valid regular expression.')
                     raise ValidationError(message % (line))
 
+
 class ValidateCSSJSONXPATHInput(object):
     """
     Filter validation
@@ -503,15 +678,57 @@ class ValidateCSSJSONXPATHInput(object):
                 except:
                     raise ValidationError("A system-error occurred when validating your jq expression")
 
+class ValidateSimpleURL:
+    """Validate that the value can be parsed by urllib.parse.urlparse() and has a scheme/netloc."""
+    def __init__(self, message=None):
+        self.message = message or "Invalid URL."
+
+    def __call__(self, form, field):
+        data = (field.data or "").strip()
+        if not data:
+            return  # empty is OK — pair with validators.Optional()
+        from urllib.parse import urlparse
+
+        parsed = urlparse(data)
+        if not parsed.scheme or not parsed.netloc:
+            raise ValidationError(self.message)
+
+class ValidateStartsWithRegex(object):
+    def __init__(self, regex, *, flags=0, message=None, allow_empty=True, split_lines=True):
+        # compile with given flags (we’ll pass re.IGNORECASE below)
+        self.pattern = re.compile(regex, flags) if isinstance(regex, str) else regex
+        self.message = message
+        self.allow_empty = allow_empty
+        self.split_lines = split_lines
+
+    def __call__(self, form, field):
+        data = field.data
+        if not data:
+            return
+
+        # normalize into list of lines
+        if isinstance(data, str) and self.split_lines:
+            lines = data.splitlines()
+        elif isinstance(data, (list, tuple)):
+            lines = data
+        else:
+            lines = [data]
+
+        for line in lines:
+            stripped = line.strip()
+            if not stripped:
+                if self.allow_empty:
+                    continue
+                raise ValidationError(self.message or _l("Empty value not allowed."))
+            if not self.pattern.match(stripped):
+                raise ValidationError(self.message or _l("Invalid value."))
+
 class quickWatchForm(Form):
-    from . import processors
-
-    url = fields.URLField('URL', validators=[validateURL()])
-    tags = StringTagUUID('Group tag', [validators.Optional()])
-    watch_submit_button = SubmitField('Watch', render_kw={"class": "pure-button pure-button-primary"})
-    processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
-    edit_and_watch_submit_button = SubmitField('Edit > Watch', render_kw={"class": "pure-button pure-button-primary"})
-
+    url = fields.URLField(_l('URL'), validators=[validateURL()])
+    tags = StringTagUUID(_l('Group tag'), validators=[validators.Optional()])
+    watch_submit_button = SubmitField(_l('Watch'), render_kw={"class": "pure-button pure-button-primary"})
+    processor = RadioField(_l('Processor'), choices=lambda: processors.available_processors(), default=processors.get_default_processor)
+    edit_and_watch_submit_button = SubmitField(_l('Edit > Watch'), render_kw={"class": "pure-button pure-button-primary"})
 
 
 # Common to a single watch and the global settings
@@ -524,86 +741,99 @@ class commonSettingsForm(Form):
         self.notification_title.extra_notification_tokens = kwargs.get('extra_notification_tokens', {})
         self.notification_urls.extra_notification_tokens = kwargs.get('extra_notification_tokens', {})
 
-    extract_title_as_title = BooleanField('Extract <title> from document and use as watch title', default=False)
-    fetch_backend = RadioField(u'Fetch Method', choices=content_fetchers.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
-    notification_body = TextAreaField('Notification Body', default='{{ watch_url }} had a change.', validators=[validators.Optional(), ValidateJinja2Template()])
-    notification_format = SelectField('Notification format', choices=valid_notification_formats.keys())
-    notification_title = StringField('Notification Title', default='ChangeDetection.io Notification - {{ watch_url }}', validators=[validators.Optional(), ValidateJinja2Template()])
-    notification_urls = StringListField('Notification URL List', validators=[validators.Optional(), ValidateAppRiseServers(), ValidateJinja2Template()])
-    processor = RadioField( label=u"Processor - What do you want to achieve?", choices=processors.available_processors(), default="text_json_diff")
-    timezone = StringField("Timezone for watch schedule", render_kw={"list": "timezones"}, validators=[validateTimeZoneName()])
-    webdriver_delay = IntegerField('Wait seconds before extracting text', validators=[validators.Optional(), validators.NumberRange(min=1, message="Should contain one or more seconds")])
+    fetch_backend = RadioField(_l('Fetch Method'), choices=content_fetchers.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    notification_body = TextAreaField(_l('Notification Body'), default='{{ watch_url }} had a change.', validators=[validators.Optional(), ValidateJinja2Template()])
+    notification_format = SelectField(_l('Notification format'), choices=list(valid_notification_formats.items()))
+    notification_title = StringField(_l('Notification Title'), default='ChangeDetection.io Notification - {{ watch_url }}', validators=[validators.Optional(), ValidateJinja2Template()])
+    notification_urls = StringListField(_l('Notification URL List'), validators=[validators.Optional(), ValidateAppRiseServers(), ValidateJinja2Template()])
+    processor = RadioField( label=_l("Processor - What do you want to achieve?"), choices=lambda: processors.available_processors(), default=processors.get_default_processor)
+    scheduler_timezone_default = StringField(_l("Default timezone for watch check scheduler"), render_kw={"list": "timezones"}, validators=[validateTimeZoneName()])
+    webdriver_delay = IntegerField(_l('Wait seconds before extracting text'), validators=[validators.Optional(), validators.NumberRange(min=1, message=_l("Should contain one or more seconds"))])
+
+# Not true anymore but keep the validate_ hook for future use, we convert color tags
+#    def validate_notification_urls(self, field):
+#        """Validate that HTML Color format is not used with Telegram"""
+#        if self.notification_format.data == 'HTML Color' and field.data:
+#            for url in field.data:
+#                if url and ('tgram://' in url or 'discord://' in url or 'discord.com/api/webhooks' in url):
+#                    raise ValidationError('HTML Color format is not supported by Telegram and Discord. Please choose another Notification Format (Plain Text, HTML, or Markdown to HTML).')
 
 
 class importForm(Form):
-    from . import processors
-    processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
-    urls = TextAreaField('URLs')
-    xlsx_file = FileField('Upload .xlsx file', validators=[FileAllowed(['xlsx'], 'Must be .xlsx file!')])
-    file_mapping = SelectField('File mapping', [validators.DataRequired()], choices={('wachete', 'Wachete mapping'), ('custom','Custom mapping')})
+    processor = RadioField(_l('Processor'), choices=lambda: processors.available_processors(), default=processors.get_default_processor)
+    urls = TextAreaField(_l('URLs'))
+    xlsx_file = FileField(_l('Upload .xlsx file'), validators=[FileAllowed(['xlsx'], _l('Must be .xlsx file!'))])
+    file_mapping = SelectField(_l('File mapping'), [validators.DataRequired()], choices={('wachete', 'Wachete mapping'), ('custom','Custom mapping')})
 
 class SingleBrowserStep(Form):
 
-    operation = SelectField('Operation', [validators.Optional()], choices=browser_step_ui_config.keys())
+    operation = SelectField(_l('Operation'), [validators.Optional()], choices=browser_step_ui_config.keys())
 
     # maybe better to set some <script>var..
-    selector = StringField('Selector', [validators.Optional()], render_kw={"placeholder": "CSS or xPath selector"})
-    optional_value = StringField('value', [validators.Optional()], render_kw={"placeholder": "Value"})
+    selector = StringField(_l('Selector'), [validators.Optional()], render_kw={"placeholder": "CSS or xPath selector"})
+    optional_value = StringField(_l('value'), [validators.Optional()], render_kw={"placeholder": "Value"})
 #   @todo move to JS? ajax fetch new field?
-#    remove_button = SubmitField('-', render_kw={"type": "button", "class": "pure-button pure-button-primary", 'title': 'Remove'})
-#    add_button = SubmitField('+', render_kw={"type": "button", "class": "pure-button pure-button-primary", 'title': 'Add new step after'})
+#    remove_button = SubmitField(_l('-'), render_kw={"type": "button", "class": "pure-button pure-button-primary", 'title': 'Remove'})
+#    add_button = SubmitField(_l('+'), render_kw={"type": "button", "class": "pure-button pure-button-primary", 'title': 'Add new step after'})
 
 class processor_text_json_diff_form(commonSettingsForm):
 
-    url = fields.URLField('URL', validators=[validateURL()])
-    tags = StringTagUUID('Group tag', [validators.Optional()], default='')
+    url = fields.URLField('Web Page URL', validators=[validateURL()])
+    tags = StringTagUUID('Group Tag', [validators.Optional()], default='')
 
-    time_between_check = FormField(TimeBetweenCheckForm)
+    time_between_check = EnhancedFormField(
+        TimeBetweenCheckForm,
+        label=_l('Time Between Check'),
+        conditional_field='time_between_check_use_default',
+        conditional_message=REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT,
+        conditional_test_function=validate_time_between_check_has_values
+    )
 
     time_schedule_limit = FormField(ScheduleLimitForm)
 
-    time_between_check_use_default = BooleanField('Use global settings for time between check', default=False)
+    time_between_check_use_default = BooleanField(_l('Use global settings for time between check and scheduler.'), default=False)
 
-    include_filters = StringListField('CSS/JSONPath/JQ/XPath Filters', [ValidateCSSJSONXPATHInput()], default='')
+    include_filters = StringListField(_l('CSS/JSONPath/JQ/XPath Filters'), [ValidateCSSJSONXPATHInput()], default='')
 
-    subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_json=False)])
+    subtractive_selectors = StringListField(_l('Remove elements'), [ValidateCSSJSONXPATHInput(allow_json=False)])
 
-    extract_text = StringListField('Extract text', [ValidateListRegex()])
+    extract_text = StringListField(_l('Extract text'), [ValidateListRegex()])
 
-    title = StringField('Title', default='')
+    title = StringField(_l('Title'), default='')
 
-    ignore_text = StringListField('Ignore lines containing', [ValidateListRegex()])
+    ignore_text = StringListField(_l('Ignore lines containing'), [ValidateListRegex()])
     headers = StringDictKeyValue('Request headers')
-    body = TextAreaField('Request body', [validators.Optional()])
-    method = SelectField('Request method', choices=valid_method, default=default_method)
-    ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
-    check_unique_lines = BooleanField('Only trigger when unique lines appear in all history', default=False)
-    remove_duplicate_lines = BooleanField('Remove duplicate lines of text', default=False)
-    sort_text_alphabetically =  BooleanField('Sort text alphabetically', default=False)
-    trim_text_whitespace = BooleanField('Trim whitespace before and after text', default=False)
+    body = TextAreaField(_l('Request body'), [validators.Optional()])
+    method = SelectField(_l('Request method'), choices=valid_method, default=default_method)
+    ignore_status_codes = BooleanField(_l('Ignore status codes (process non-2xx status codes as normal)'), default=False)
+    check_unique_lines = BooleanField(_l('Only trigger when unique lines appear in all history'), default=False)
+    remove_duplicate_lines = BooleanField(_l('Remove duplicate lines of text'), default=False)
+    sort_text_alphabetically =  BooleanField(_l('Sort text alphabetically'), default=False)
+    strip_ignored_lines = TernaryNoneBooleanField(_l('Strip ignored lines'), default=None)
+    trim_text_whitespace = BooleanField(_l('Trim whitespace before and after text'), default=False)
 
-    filter_text_added = BooleanField('Added lines', default=True)
-    filter_text_replaced = BooleanField('Replaced/changed lines', default=True)
-    filter_text_removed = BooleanField('Removed lines', default=True)
+    filter_text_added = BooleanField(_l('Added lines'), default=True)
+    filter_text_replaced = BooleanField(_l('Replaced/changed lines'), default=True)
+    filter_text_removed = BooleanField(_l('Removed lines'), default=True)
 
-    trigger_text = StringListField('Keyword triggers - Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
-    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
-        browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
-    text_should_not_be_present = StringListField('Block change-detection while text matches', [validators.Optional(), ValidateListRegex()])
-    webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
+    trigger_text = StringListField(_l('Keyword triggers - Trigger/wait for text'), [validators.Optional(), ValidateListRegex()])
+    browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
+    text_should_not_be_present = StringListField(_l('Block change-detection while text matches'), [validators.Optional(), ValidateListRegex()])
+    webdriver_js_execute_code = TextAreaField(_l('Execute JavaScript before change detection'), render_kw={"rows": "5"}, validators=[validators.Optional()])
 
-    save_button = SubmitField('Save', render_kw={"class": "pure-button button-small pure-button-primary"})
+    save_button = SubmitField(_l('Save'), render_kw={"class": "pure-button pure-button-primary"})
 
-    proxy = RadioField('Proxy')
-    filter_failure_notification_send = BooleanField(
-        'Send a notification when the filter can no longer be found on the page', default=False)
+    proxy = RadioField(_l('Proxy'))
+    # filter_failure_notification_send @todo make ternary
+    filter_failure_notification_send = BooleanField(_l('Send a notification when the filter can no longer be found on the page'), default=False)
+    notification_muted = TernaryNoneBooleanField(_l('Notifications'), default=None, yes_text=_l("Muted"), no_text=_l("On"))
+    notification_screenshot = BooleanField(_l('Attach screenshot to notification (where possible)'), default=False)
 
-    notification_muted = BooleanField('Notifications Muted / Off', default=False)
-    notification_screenshot = BooleanField('Attach screenshot to notification (where possible)', default=False)
-
-    conditions_match_logic = RadioField(u'Match', choices=[('ALL', 'Match all of the following'),('ANY', 'Match any of the following')], default='ALL')
+    conditions_match_logic = RadioField(_l('Match'), choices=[('ALL', _l('Match all of the following')),('ANY', _l('Match any of the following'))], default='ALL')
     conditions = FieldList(FormField(ConditionFormRow), min_entries=1)  # Add rule logic here
+    use_page_title_in_list = TernaryNoneBooleanField(_l('Use page <title> in list'), default=None)
 
+    history_snapshot_max_length = IntegerField(_l('Number of history items per watch to keep'), render_kw={"style": "width: 5em;"}, validators=[validators.Optional(), validators.NumberRange(min=2)])
 
     def extra_tab_content(self):
         return None
@@ -615,12 +845,12 @@ class processor_text_json_diff_form(commonSettingsForm):
         if not super().validate():
             return False
 
-        from changedetectionio.safe_jinja import render as jinja_render
+        from changedetectionio.jinja2_custom import render as jinja_render
         result = True
 
         # Fail form validation when a body is set for a GET
         if self.method.data == 'GET' and self.body.data:
-            self.body.errors.append('Body must be empty when Request Method is set to GET')
+            self.body.errors.append(gettext('Body must be empty when Request Method is set to GET'))
             result = False
 
         # Attempt to validate jinja2 templates in the URL
@@ -629,11 +859,11 @@ class processor_text_json_diff_form(commonSettingsForm):
         except ModuleNotFoundError as e:
             # incase jinja2_time or others is missing
             logger.error(e)
-            self.url.errors.append(f'Invalid template syntax configuration: {e}')
+            self.url.errors.append(gettext('Invalid template syntax configuration: %(error)s') % {'error': e})
             result = False
         except Exception as e:
             logger.error(e)
-            self.url.errors.append(f'Invalid template syntax: {e}')
+            self.url.errors.append(gettext('Invalid template syntax: %(error)s') % {'error': e})
             result = False
 
         # Attempt to validate jinja2 templates in the body
@@ -643,11 +873,11 @@ class processor_text_json_diff_form(commonSettingsForm):
             except ModuleNotFoundError as e:
                 # incase jinja2_time or others is missing
                 logger.error(e)
-                self.body.errors.append(f'Invalid template syntax configuration: {e}')
+                self.body.errors.append(gettext('Invalid template syntax configuration: %(error)s') % {'error': e})
                 result = False
             except Exception as e:
                 logger.error(e)
-                self.body.errors.append(f'Invalid template syntax: {e}')
+                self.body.errors.append(gettext('Invalid template syntax: %(error)s') % {'error': e})
                 result = False
 
         # Attempt to validate jinja2 templates in the headers
@@ -658,11 +888,11 @@ class processor_text_json_diff_form(commonSettingsForm):
             except ModuleNotFoundError as e:
                 # incase jinja2_time or others is missing
                 logger.error(e)
-                self.headers.errors.append(f'Invalid template syntax configuration: {e}')
+                self.headers.errors.append(gettext('Invalid template syntax configuration: %(error)s') % {'error': e})
                 result = False
             except Exception as e:
                 logger.error(e)
-                self.headers.errors.append(f'Invalid template syntax in "{header}" header: {e}')
+                self.headers.errors.append(gettext('Invalid template syntax in \"%(header)s\" header: %(error)s') % {'header': header, 'error': e})
                 result = False
 
         return result
@@ -678,82 +908,132 @@ class processor_text_json_diff_form(commonSettingsForm):
     ):
         super().__init__(formdata, obj, prefix, data, meta, **kwargs)
         if kwargs and kwargs.get('default_system_settings'):
-            default_tz = kwargs.get('default_system_settings').get('application', {}).get('timezone')
+            default_tz = kwargs.get('default_system_settings').get('application', {}).get('scheduler_timezone_default')
             if default_tz:
                 self.time_schedule_limit.form.timezone.render_kw['placeholder'] = default_tz
 
 
 
 class SingleExtraProxy(Form):
-
     # maybe better to set some <script>var..
-    proxy_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
-    proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "socks5:// or regular proxy http://user:pass@...:3128", "size":50})
-    # @todo do the validation here instead
+    proxy_name = StringField(_l('Name'), [validators.Optional()], render_kw={"placeholder": "Name"})
+    proxy_url = StringField(_l('Proxy URL'), [
+        validators.Optional(),
+        ValidateStartsWithRegex(
+            regex=r'^(https?|socks5)://',  # ✅ main pattern
+            flags=re.IGNORECASE,  # ✅ makes it case-insensitive
+            message=_l('Proxy URLs must start with http://, https:// or socks5://'),
+        ),
+        ValidateSimpleURL()
+    ], render_kw={"placeholder": "socks5:// or regular proxy http://user:pass@...:3128", "size":50})
 
 class SingleExtraBrowser(Form):
-    browser_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
-    browser_connection_url = StringField('Browser connection URL', [validators.Optional()], render_kw={"placeholder": "wss://brightdata... wss://oxylabs etc", "size":50})
-    # @todo do the validation here instead
+    browser_name = StringField(_l('Name'), [validators.Optional()], render_kw={"placeholder": "Name"})
+    browser_connection_url = StringField(_l('Browser connection URL'), [
+        validators.Optional(),
+        ValidateStartsWithRegex(
+            regex=r'^(wss?|ws)://',
+            flags=re.IGNORECASE,
+            message=_l('Browser URLs must start with wss:// or ws://')
+        ),
+        ValidateSimpleURL()
+    ], render_kw={"placeholder": "wss://brightdata... wss://oxylabs etc", "size":50})
 
 class DefaultUAInputForm(Form):
-    html_requests = StringField('Plaintext requests', validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
+    html_requests = StringField(_l('Plaintext requests'), validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
     if os.getenv("PLAYWRIGHT_DRIVER_URL") or os.getenv("WEBDRIVER_URL"):
-        html_webdriver = StringField('Chrome requests', validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
+        html_webdriver = StringField(_l('Chrome requests'), validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
 
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
-    time_between_check = FormField(TimeBetweenCheckForm)
+    time_between_check = RequiredFormField(TimeBetweenCheckForm, label=_l('Time Between Check'))
     time_schedule_limit = FormField(ScheduleLimitForm)
-    proxy = RadioField('Proxy')
-    jitter_seconds = IntegerField('Random jitter seconds ± check',
+    proxy = RadioField(_l('Default proxy'))
+    jitter_seconds = IntegerField(_l('Random jitter seconds ± check'),
                                   render_kw={"style": "width: 5em;"},
-                                  validators=[validators.NumberRange(min=0, message="Should contain zero or more seconds")])
+                                  validators=[validators.NumberRange(min=0, message=_l("Should contain zero or more seconds"))])
+    
+    workers = IntegerField(_l('Number of fetch workers'),
+                          render_kw={"style": "width: 5em;"},
+                          validators=[validators.NumberRange(min=1, max=50,
+                                                             message=_l("Should be between 1 and 50"))])
+
+    timeout = IntegerField(_l('Requests timeout in seconds'),
+                           render_kw={"style": "width: 5em;"},
+                           validators=[validators.NumberRange(min=1, max=999,
+                                                              message=_l("Should be between 1 and 999"))])
+
     extra_proxies = FieldList(FormField(SingleExtraProxy), min_entries=5)
     extra_browsers = FieldList(FormField(SingleExtraBrowser), min_entries=5)
 
-    default_ua = FormField(DefaultUAInputForm, label="Default User-Agent overrides")
+    default_ua = FormField(DefaultUAInputForm, label=_l("Default User-Agent overrides"))
 
     def validate_extra_proxies(self, extra_validators=None):
         for e in self.data['extra_proxies']:
             if e.get('proxy_name') or e.get('proxy_url'):
                 if not e.get('proxy_name','').strip() or not e.get('proxy_url','').strip():
-                    self.extra_proxies.errors.append('Both a name, and a Proxy URL is required.')
+                    self.extra_proxies.errors.append(gettext('Both a name, and a Proxy URL is required.'))
                     return False
 
 class globalSettingsApplicationUIForm(Form):
-    open_diff_in_new_tab = BooleanField('Open diff page in a new tab', default=True, validators=[validators.Optional()])
+    open_diff_in_new_tab = BooleanField(_l("Open 'History' page in a new tab"), default=True, validators=[validators.Optional()])
+    socket_io_enabled = BooleanField(_l('Realtime UI Updates Enabled'), default=True, validators=[validators.Optional()])
+    favicons_enabled = BooleanField(_l('Favicons Enabled'), default=True, validators=[validators.Optional()])
+    use_page_title_in_list = BooleanField(_l('Use page <title> in watch overview list')) #BooleanField=True
 
 # datastore.data['settings']['application']..
 class globalSettingsApplicationForm(commonSettingsForm):
 
-    api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
-    base_url = StringField('Notification base URL override',
+    api_access_token_enabled = BooleanField(_l('API access token security check enabled'), default=True, validators=[validators.Optional()])
+    base_url = StringField(_l('Notification base URL override'),
                            validators=[validators.Optional()],
                            render_kw={"placeholder": os.getenv('BASE_URL', 'Not set')}
                            )
-    empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
-    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetchers.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
-    global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
-    global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_json=False)])
-    ignore_whitespace = BooleanField('Ignore whitespace')
-    password = SaltyPasswordField()
-    pager_size = IntegerField('Pager size',
+    empty_pages_are_a_change =  BooleanField(_l('Treat empty pages as a change?'), default=False)
+    fetch_backend = RadioField(_l('Fetch Method'), default="html_requests", choices=content_fetchers.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    global_ignore_text = StringListField(_l('Ignore Text'), [ValidateListRegex()])
+    global_subtractive_selectors = StringListField(_l('Remove elements'), [ValidateCSSJSONXPATHInput(allow_json=False)])
+    ignore_whitespace = BooleanField(_l('Ignore whitespace'))
+
+    # Screenshot comparison settings
+    min_change_percentage = FloatField(
+        'Screenshot: Minimum Change Percentage',
+        validators=[
+            validators.Optional(),
+            validators.NumberRange(min=0.0, max=100.0, message=_l('Must be between 0 and 100'))
+        ],
+        default=0.1,
+        render_kw={"placeholder": "0.1", "style": "width: 8em;"}
+    )
+
+    password = SaltyPasswordField(_l('Password'))
+    pager_size = IntegerField(_l('Pager size'),
                               render_kw={"style": "width: 5em;"},
                               validators=[validators.NumberRange(min=0,
-                                                                 message="Should be atleast zero (disabled)")])
+                                                                 message=_l("Should be atleast zero (disabled)"))])
 
-    rss_content_format = SelectField('RSS Content format', choices=RSS_FORMAT_TYPES)
+    rss_content_format = SelectField(_l('RSS Content format'), choices=list(RSS_FORMAT_TYPES.items()))
+    rss_template_type = SelectField(_l('RSS <description> body built from'), choices=list(RSS_TEMPLATE_TYPE_OPTIONS.items()))
+    rss_template_override = TextAreaField(_l('RSS "System default" template override'), render_kw={"rows": "5", "placeholder": RSS_TEMPLATE_HTML_DEFAULT}, validators=[validators.Optional(), ValidateJinja2Template()])
 
-    removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
-    render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
-    shared_diff_access = BooleanField('Allow access to view diff page when password is enabled', default=False, validators=[validators.Optional()])
-    rss_hide_muted_watches = BooleanField('Hide muted watches from RSS feed', default=True,
+    removepassword_button = SubmitField(_l('Remove password'), render_kw={"class": "pure-button pure-button-primary"})
+    render_anchor_tag_content = BooleanField(_l('Render anchor tag content'), default=False)
+    shared_diff_access = BooleanField(_l('Allow anonymous access to watch history page when password is enabled'), default=False, validators=[validators.Optional()])
+    strip_ignored_lines = BooleanField(_l('Strip ignored lines'))
+    rss_hide_muted_watches = BooleanField(_l('Hide muted watches from RSS feed'), default=True,
                                       validators=[validators.Optional()])
-    filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',
+
+    rss_reader_mode = BooleanField(_l('Enable RSS reader mode '), default=False, validators=[validators.Optional()])
+    rss_diff_length = IntegerField(label=_l('Number of changes to show in watch RSS feed'),
+                                   render_kw={"style": "width: 5em;"},
+                                   validators=[validators.NumberRange(min=0, message=_l("Should contain zero or more attempts"))])
+
+    filter_failure_notification_threshold_attempts = IntegerField(_l('Number of times the filter can be missing before sending a notification'),
                                                                   render_kw={"style": "width: 5em;"},
                                                                   validators=[validators.NumberRange(min=0,
-                                                                                                     message="Should contain zero or more attempts")])
+                                                                                                     message=_l("Should contain zero or more attempts"))])
+
+    history_snapshot_max_length = IntegerField(_l('Number of history items per watch to keep'), render_kw={"style": "width: 5em;"}, validators=[validators.Optional(), validators.NumberRange(min=2)])
     ui = FormField(globalSettingsApplicationUIForm)
 
 
@@ -769,9 +1049,9 @@ class globalSettingsForm(Form):
 
     requests = FormField(globalSettingsRequestForm)
     application = FormField(globalSettingsApplicationForm)
-    save_button = SubmitField('Save', render_kw={"class": "pure-button button-small pure-button-primary"})
+    save_button = SubmitField(_l('Save'), render_kw={"class": "pure-button pure-button-primary"})
 
 
 class extractDataForm(Form):
-    extract_regex = StringField('RegEx to extract', validators=[validators.Length(min=1, message="Needs a RegEx")])
-    extract_submit_button = SubmitField('Extract as CSV', render_kw={"class": "pure-button pure-button-primary"})
+    extract_regex = StringField(_l('RegEx to extract'), validators=[validators.DataRequired(), ValidateSinglePythonRegexString()])
+    extract_submit_button = SubmitField(_l('Extract as CSV'), render_kw={"class": "pure-button pure-button-primary"})

changedetectionio/html_tools.py

@@ -1,6 +1,8 @@
+from functools import lru_cache
+
 from loguru import logger
-from lxml import etree
 from typing import List
+import html
 import json
 import re
 
@@ -9,6 +11,10 @@ TEXT_FILTER_LIST_LINE_SUFFIX = "<br>"
 TRANSLATE_WHITESPACE_TABLE = str.maketrans('', '', '\r\n\t ')
 PERL_STYLE_REGEX = r'^/(.*?)/([a-z]*)?$'
 
+TITLE_RE = re.compile(r"<title[^>]*>(.*?)</title>", re.I | re.S)
+META_CS  = re.compile(r'<meta[^>]+charset=["\']?\s*([a-z0-9_\-:+.]+)', re.I)
+META_CT  = re.compile(r'<meta[^>]+http-equiv=["\']?content-type["\']?[^>]*content=["\'][^>]*charset=([a-z0-9_\-:+.]+)', re.I)
+
 # 'price' , 'lowPrice', 'highPrice' are usually under here
 # All of those may or may not appear on different websites - I didnt find a way todo case-insensitive searching here
 LD_JSON_PRODUCT_OFFER_SELECTORS = ["json:$..offers", "json:$..Offers"]
@@ -17,9 +23,9 @@ class JSONNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
 
-
 # Doesn't look like python supports forward slash auto enclosure in re.findall
 # So convert it to inline flag "(?i)foobar" type configuration
+@lru_cache(maxsize=100)
 def perl_style_slash_enclosed_regex_to_options(regex):
 
     res = re.search(PERL_STYLE_REGEX, regex, re.IGNORECASE)
@@ -52,13 +58,17 @@ def include_filters(include_filters, html_content, append_pretty_line_formatting
 
     return html_block
 
-def subtractive_css_selector(css_selector, html_content):
+def subtractive_css_selector(css_selector, content):
     from bs4 import BeautifulSoup
-    soup = BeautifulSoup(html_content, "html.parser")
+    soup = BeautifulSoup(content, "html.parser")
 
     # So that the elements dont shift their index, build a list of elements here which will be pointers to their place in the DOM
     elements_to_remove = soup.select(css_selector)
 
+    if not elements_to_remove:
+        # Better to return the original that rebuild with BeautifulSoup
+        return content
+
     # Then, remove them in a separate loop
     for item in elements_to_remove:
         item.decompose()
@@ -66,6 +76,7 @@ def subtractive_css_selector(css_selector, html_content):
     return str(soup)
 
 def subtractive_xpath_selector(selectors: List[str], html_content: str) -> str:
+    from lxml import etree
     # Parse the HTML content using lxml
     html_tree = etree.HTML(html_content)
 
@@ -77,6 +88,10 @@ def subtractive_xpath_selector(selectors: List[str], html_content: str) -> str:
         # Collect elements for each selector
         elements_to_remove.extend(html_tree.xpath(selector))
 
+    # If no elements were found, return the original HTML content
+    if not elements_to_remove:
+        return html_content
+
     # Then, remove them in a separate loop
     for element in elements_to_remove:
         if element.getparent() is not None:  # Ensure the element has a parent before removing
@@ -94,7 +109,7 @@ def element_removal(selectors: List[str], html_content):
     xpath_selectors = []
 
     for selector in selectors:
-        if selector.startswith(('xpath:', 'xpath1:', '//')):
+        if selector.strip().startswith(('xpath:', 'xpath1:', '//')):
             # Handle XPath selectors separately
             xpath_selector = selector.removeprefix('xpath:').removeprefix('xpath1:')
             xpath_selectors.append(xpath_selector)
@@ -157,75 +172,131 @@ def elementpath_tostring(obj):
     return str(obj)
 
 # Return str Utf-8 of matched rules
-def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_rss=False):
+def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_xml=False):
+    """
+
+    :param xpath_filter:
+    :param html_content:
+    :param append_pretty_line_formatting:
+    :param is_xml: set to true if is XML or is RSS (RSS is XML)
+    :return:
+    """
     from lxml import etree, html
     import elementpath
     # xpath 2.0-3.1
     from elementpath.xpath3 import XPath3Parser
 
     parser = etree.HTMLParser()
-    if is_rss:
-        # So that we can keep CDATA for cdata_in_document_to_text() to process
-        parser = etree.XMLParser(strip_cdata=False)
-
-    tree = html.fromstring(bytes(html_content, encoding='utf-8'), parser=parser)
-    html_block = ""
-
-    r = elementpath.select(tree, xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'}, parser=XPath3Parser)
-    #@note: //title/text() wont work where <title>CDATA..
-
-    if type(r) != list:
-        r = [r]
-
-    for element in r:
-        # When there's more than 1 match, then add the suffix to separate each line
-        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
-        # (This way each 'match' reliably has a new-line in the diff)
-        # Divs are converted to 4 whitespaces by inscriptis
-        if append_pretty_line_formatting and len(html_block) and (not hasattr( element, 'tag' ) or not element.tag in (['br', 'hr', 'div', 'p'])):
-            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
-
-        if type(element) == str:
-            html_block += element
-        elif issubclass(type(element), etree._Element) or issubclass(type(element), etree._ElementTree):
-            html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
+    tree = None
+    try:
+        if is_xml:
+            # So that we can keep CDATA for cdata_in_document_to_text() to process
+            parser = etree.XMLParser(strip_cdata=False)
+            # For XML/RSS content, use etree.fromstring to properly handle XML declarations
+            tree = etree.fromstring(html_content.encode('utf-8') if isinstance(html_content, str) else html_content, parser=parser)
         else:
-            html_block += elementpath_tostring(element)
+            tree = html.fromstring(html_content, parser=parser)
+        html_block = ""
 
-    return html_block
+        # Build namespace map for XPath queries
+        namespaces = {'re': 'http://exslt.org/regular-expressions'}
+
+        # Handle default namespace in documents (common in RSS/Atom feeds, but can occur in any XML)
+        # XPath spec: unprefixed element names have no namespace, not the default namespace
+        # Solution: Register the default namespace with empty string prefix in elementpath
+        # This is primarily for RSS/Atom feeds but works for any XML with default namespace
+        if hasattr(tree, 'nsmap') and tree.nsmap and None in tree.nsmap:
+            # Register the default namespace with empty string prefix for elementpath
+            # This allows //title to match elements in the default namespace
+            namespaces[''] = tree.nsmap[None]
+
+        r = elementpath.select(tree, xpath_filter.strip(), namespaces=namespaces, parser=XPath3Parser)
+        #@note: //title/text() now works with default namespaces (fixed by registering '' prefix)
+        #@note: //title/text() wont work where <title>CDATA.. (use cdata_in_document_to_text first)
+
+        if type(r) != list:
+            r = [r]
+
+        for element in r:
+            # When there's more than 1 match, then add the suffix to separate each line
+            # And where the matched result doesn't include something that will cause Inscriptis to add a newline
+            # (This way each 'match' reliably has a new-line in the diff)
+            # Divs are converted to 4 whitespaces by inscriptis
+            if append_pretty_line_formatting and len(html_block) and (not hasattr( element, 'tag' ) or not element.tag in (['br', 'hr', 'div', 'p'])):
+                html_block += TEXT_FILTER_LIST_LINE_SUFFIX
+
+            if type(element) == str:
+                html_block += element
+            elif issubclass(type(element), etree._Element) or issubclass(type(element), etree._ElementTree):
+                # Use 'xml' method for RSS/XML content, 'html' for HTML content
+                # parser will be XMLParser if we detected XML content
+                method = 'xml' if (is_xml or isinstance(parser, etree.XMLParser)) else 'html'
+                html_block += etree.tostring(element, pretty_print=True, method=method, encoding='unicode')
+            else:
+                html_block += elementpath_tostring(element)
+
+        return html_block
+    finally:
+        # Explicitly clear the tree to free memory
+        # lxml trees can hold significant memory, especially with large documents
+        if tree is not None:
+            tree.clear()
 
 # Return str Utf-8 of matched rules
 # 'xpath1:'
-def xpath1_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_rss=False):
+def xpath1_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_xml=False):
     from lxml import etree, html
 
     parser = None
-    if is_rss:
-        # So that we can keep CDATA for cdata_in_document_to_text() to process
-        parser = etree.XMLParser(strip_cdata=False)
-
-    tree = html.fromstring(bytes(html_content, encoding='utf-8'), parser=parser)
-    html_block = ""
-
-    r = tree.xpath(xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'})
-    #@note: //title/text() wont work where <title>CDATA..
-
-    for element in r:
-        # When there's more than 1 match, then add the suffix to separate each line
-        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
-        # (This way each 'match' reliably has a new-line in the diff)
-        # Divs are converted to 4 whitespaces by inscriptis
-        if append_pretty_line_formatting and len(html_block) and (not hasattr(element, 'tag') or not element.tag in (['br', 'hr', 'div', 'p'])):
-            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
-
-        # Some kind of text, UTF-8 or other
-        if isinstance(element, (str, bytes)):
-            html_block += element
+    tree = None
+    try:
+        if is_xml:
+            # So that we can keep CDATA for cdata_in_document_to_text() to process
+            parser = etree.XMLParser(strip_cdata=False)
+            # For XML/RSS content, use etree.fromstring to properly handle XML declarations
+            tree = etree.fromstring(html_content.encode('utf-8') if isinstance(html_content, str) else html_content, parser=parser)
         else:
-            # Return the HTML which will get parsed as text
-            html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
+            tree = html.fromstring(html_content, parser=parser)
+        html_block = ""
 
-    return html_block
+        # Build namespace map for XPath queries
+        namespaces = {'re': 'http://exslt.org/regular-expressions'}
+
+        # NOTE: lxml's native xpath() does NOT support empty string prefix for default namespace
+        # For documents with default namespace (RSS/Atom feeds), users must use:
+        #   - local-name(): //*[local-name()='title']/text()
+        #   - Or use xpath_filter (not xpath1_filter) which supports default namespaces
+        # XPath spec: unprefixed element names have no namespace, not the default namespace
+
+        r = tree.xpath(xpath_filter.strip(), namespaces=namespaces)
+        #@note: xpath1 (lxml) does NOT automatically handle default namespaces
+        #@note: Use //*[local-name()='element'] or switch to xpath_filter for default namespace support
+        #@note: //title/text() wont work where <title>CDATA.. (use cdata_in_document_to_text first)
+
+        for element in r:
+            # When there's more than 1 match, then add the suffix to separate each line
+            # And where the matched result doesn't include something that will cause Inscriptis to add a newline
+            # (This way each 'match' reliably has a new-line in the diff)
+            # Divs are converted to 4 whitespaces by inscriptis
+            if append_pretty_line_formatting and len(html_block) and (not hasattr(element, 'tag') or not element.tag in (['br', 'hr', 'div', 'p'])):
+                html_block += TEXT_FILTER_LIST_LINE_SUFFIX
+
+            # Some kind of text, UTF-8 or other
+            if isinstance(element, (str, bytes)):
+                html_block += element
+            else:
+                # Return the HTML/XML which will get parsed as text
+                # Use 'xml' method for RSS/XML content, 'html' for HTML content
+                # parser will be XMLParser if we detected XML content
+                method = 'xml' if (is_xml or isinstance(parser, etree.XMLParser)) else 'html'
+                html_block += etree.tostring(element, pretty_print=True, method=method, encoding='unicode')
+
+        return html_block
+    finally:
+        # Explicitly clear the tree to free memory
+        # lxml trees can hold significant memory, especially with large documents
+        if tree is not None:
+            tree.clear()
 
 # Extract/find element
 def extract_element(find='title', html_content=''):
@@ -289,70 +360,92 @@ def _get_stripped_text_from_json_match(match):
 
     return stripped_text_from_html
 
+def extract_json_blob_from_html(content, ensure_is_ldjson_info_type, json_filter):
+    from bs4 import BeautifulSoup
+    stripped_text_from_html = ''
+
+    # Foreach <script json></script> blob.. just return the first that matches json_filter
+    # As a last resort, try to parse the whole <body>
+    soup = BeautifulSoup(content, 'html.parser')
+
+    if ensure_is_ldjson_info_type:
+        bs_result = soup.find_all('script', {"type": "application/ld+json"})
+    else:
+        bs_result = soup.find_all('script')
+    bs_result += soup.find_all('body')
+
+    bs_jsons = []
+
+    for result in bs_result:
+        # result.text is how bs4 magically strips JSON from the body
+        content_start = result.text.lstrip("\ufeff").strip()[:100] if result.text else ''
+        # Skip empty tags, and things that dont even look like JSON
+        if not result.text or not (content_start[0] == '{' or content_start[0] == '['):
+            continue
+        try:
+            json_data = json.loads(result.text)
+            bs_jsons.append(json_data)
+        except json.JSONDecodeError:
+            # Skip objects which cannot be parsed
+            continue
+
+    if not bs_jsons:
+        raise JSONNotFound("No parsable JSON found in this document")
+
+    for json_data in bs_jsons:
+        stripped_text_from_html = _parse_json(json_data, json_filter)
+
+        if ensure_is_ldjson_info_type:
+            # Could sometimes be list, string or something else random
+            if isinstance(json_data, dict):
+                # If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
+                # (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
+                # @type could also be a list although non-standard ("@type": ["Product", "SubType"],)
+                # LD_JSON auto-extract also requires some content PLUS the ldjson to be present
+                # 1833 - could be either str or dict, should not be anything else
+
+                t = json_data.get('@type')
+                if t and stripped_text_from_html:
+
+                    if isinstance(t, str) and t.lower() == ensure_is_ldjson_info_type.lower():
+                        break
+                    # The non-standard part, some have a list
+                    elif isinstance(t, list):
+                        if ensure_is_ldjson_info_type.lower() in [x.lower().strip() for x in t]:
+                            break
+
+        elif stripped_text_from_html:
+            break
+
+    return stripped_text_from_html
+
 # content - json
 # json_filter - ie json:$..price
 # ensure_is_ldjson_info_type - str "product", optional, "@type == product" (I dont know how to do that as a json selector)
 def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None):
-    from bs4 import BeautifulSoup
 
     stripped_text_from_html = False
 # https://github.com/dgtlmoon/changedetection.io/pull/2041#issuecomment-1848397161w
     # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded within HTML tags
-    try:
-        # .lstrip("\ufeff") strings ByteOrderMark from UTF8 and still lets the UTF work
-        stripped_text_from_html = _parse_json(json.loads(content.lstrip("\ufeff") ), json_filter)
-    except json.JSONDecodeError as e:
-        logger.warning(str(e))
 
-        # Foreach <script json></script> blob.. just return the first that matches json_filter
-        # As a last resort, try to parse the whole <body>
-        soup = BeautifulSoup(content, 'html.parser')
+    # Looks like clean JSON, dont bother extracting from HTML
 
-        if ensure_is_ldjson_info_type:
-            bs_result = soup.findAll('script', {"type": "application/ld+json"})
-        else:
-            bs_result = soup.findAll('script')
-        bs_result += soup.findAll('body')
+    content_start = content.lstrip("\ufeff").strip()[:100]
 
-        bs_jsons = []
-        for result in bs_result:
-            # Skip empty tags, and things that dont even look like JSON
-            if not result.text or '{' not in result.text:
-                continue
-            try:
-                json_data = json.loads(result.text)
-                bs_jsons.append(json_data)
-            except json.JSONDecodeError:
-                # Skip objects which cannot be parsed
-                continue
-
-        if not bs_jsons:
-            raise JSONNotFound("No parsable JSON found in this document")
-        
-        for json_data in bs_jsons:
-            stripped_text_from_html = _parse_json(json_data, json_filter)
-
-            if ensure_is_ldjson_info_type:
-                # Could sometimes be list, string or something else random
-                if isinstance(json_data, dict):
-                    # If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
-                    # (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
-                    # @type could also be a list although non-standard ("@type": ["Product", "SubType"],)
-                    # LD_JSON auto-extract also requires some content PLUS the ldjson to be present
-                    # 1833 - could be either str or dict, should not be anything else
-
-                    t = json_data.get('@type')
-                    if t and stripped_text_from_html:
-
-                        if isinstance(t, str) and t.lower() == ensure_is_ldjson_info_type.lower():
-                            break
-                        # The non-standard part, some have a list
-                        elif isinstance(t, list):
-                            if ensure_is_ldjson_info_type.lower() in [x.lower().strip() for x in t]:
-                                break
-
-            elif stripped_text_from_html:
-                break
+    if content_start[0] == '{' or content_start[0] == '[':
+        try:
+            # .lstrip("\ufeff") strings ByteOrderMark from UTF8 and still lets the UTF work
+            stripped_text_from_html = _parse_json(json.loads(content.lstrip("\ufeff")), json_filter)
+        except json.JSONDecodeError as e:
+            logger.warning(f"Error processing JSON {content[:20]}...{str(e)})")
+    else:
+        # Probably something else, go fish inside for it
+        try:
+            stripped_text_from_html = extract_json_blob_from_html(content=content,
+                                                                  ensure_is_ldjson_info_type=ensure_is_ldjson_info_type,
+                                                                  json_filter=json_filter                                                                  )
+        except json.JSONDecodeError as e:
+            logger.warning(f"Error processing JSON while extracting JSON from HTML blob {content[:20]}...{str(e)})")
 
     if not stripped_text_from_html:
         # Re 265 - Just return an empty string when filter not found
@@ -371,7 +464,13 @@ def strip_ignore_text(content, wordlist, mode="content"):
     ignore_regex_multiline = []
     ignored_lines = []
 
+    if not content:
+        return ''
+
     for k in wordlist:
+        # Skip empty strings to avoid matching everything
+        if not k or not k.strip():
+            continue
         # Is it a regex?
         res = re.search(PERL_STYLE_REGEX, k, re.IGNORECASE)
         if res:
@@ -436,55 +535,39 @@ def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False
     return re.sub(pattern, repl, html_content)
 
 
-def html_to_text_sub_worker(conn, html_content: str, render_anchor_tag_content=False, is_rss=False):
+# NOTE!! ANYTHING LIBXML, HTML5LIB ETC WILL CAUSE SOME SMALL MEMORY LEAK IN THE LOCAL "LIB" IMPLEMENTATION OUTSIDE PYTHON
 
+
+def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=False, timeout=10) -> str:
+    """
+    Convert HTML content to plain text using inscriptis.
+
+    Thread-Safety: This function uses inscriptis.get_text() which internally calls
+    lxml.html.fromstring() with the default parser. Testing with 50 concurrent threads
+    confirms this approach is thread-safe and produces deterministic output.
+
+    Alternative Approach Rejected: An explicit HTMLParser instance (thread-local or fresh)
+    would also be thread-safe, but was found to break change detection logic in subtle ways
+    (test_check_basic_change_detection_functionality). The default parser provides correct
+    and reliable behavior.
+    """
     from inscriptis import get_text
     from inscriptis.model.config import ParserConfig
 
-    """Converts html string to a string with just the text. If ignoring
-    rendering anchor tag content is enable, anchor tag content are also
-    included in the text
-
-    :param html_content: string with html content
-    :param render_anchor_tag_content: boolean flag indicating whether to extract
-    hyperlinks (the anchor tag content) together with text. This refers to the
-    'href' inside 'a' tags.
-    Anchor tag content is rendered in the following manner:
-    '[ text ](anchor tag content)'
-    :return: extracted text from the HTML
-    """
-    #  if anchor tag content flag is set to True define a config for
-    #  extracting this content
     if render_anchor_tag_content:
         parser_config = ParserConfig(
             annotation_rules={"a": ["hyperlink"]},
             display_links=True
         )
-    # otherwise set config to None/default
     else:
         parser_config = None
 
-    # RSS Mode - Inscriptis will treat `title` as something else.
-    # Make it as a regular block display element (//item/title)
-    # This is a bit of a hack - the real way it to use XSLT to convert it to HTML #1874
     if is_rss:
         html_content = re.sub(r'<title([\s>])', r'<h1\1', html_content)
         html_content = re.sub(r'</title>', r'</h1>', html_content)
 
     text_content = get_text(html_content, config=parser_config)
-    conn.send(text_content)
-    conn.close()
-
-# NOTE!! ANYTHING LIBXML, HTML5LIB ETC WILL CAUSE SOME SMALL MEMORY LEAK IN THE LOCAL "LIB" IMPLEMENTATION OUTSIDE PYTHON
-def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=False):
-    from multiprocessing import Process, Pipe
-
-    parent_conn, child_conn = Pipe()
-    p = Process(target=html_to_text_sub_worker, args=(child_conn, html_content, render_anchor_tag_content, is_rss))
-    p.start()
-    text = parent_conn.recv()
-    p.join()
-    return text
+    return text_content
 
 # Does LD+JSON exist with a @type=='product' and a .price set anywhere?
 def has_ldjson_product_info(content):
@@ -538,3 +621,43 @@ def get_triggered_text(content, trigger_text):
         i += 1
 
     return triggered_text
+
+
+def extract_title(data: bytes | str, sniff_bytes: int = 2048, scan_chars: int = 8192) -> str | None:
+    try:
+        # Only decode/process the prefix we need for title extraction
+        match data:
+            case bytes() if data.startswith((b"\xff\xfe", b"\xfe\xff")):
+                prefix = data[:scan_chars * 2].decode("utf-16", errors="replace")
+            case bytes() if data.startswith((b"\xff\xfe\x00\x00", b"\x00\x00\xfe\xff")):
+                prefix = data[:scan_chars * 4].decode("utf-32", errors="replace")
+            case bytes():
+                try:
+                    prefix = data[:scan_chars].decode("utf-8")
+                except UnicodeDecodeError:
+                    try:
+                        head = data[:sniff_bytes].decode("ascii", errors="ignore")
+                        if m := (META_CS.search(head) or META_CT.search(head)):
+                            enc = m.group(1).lower()
+                        else:
+                            enc = "cp1252"
+                        prefix = data[:scan_chars * 2].decode(enc, errors="replace")
+                    except Exception as e:
+                        logger.error(f"Title extraction encoding detection failed: {e}")
+                        return None
+            case str():
+                prefix = data[:scan_chars] if len(data) > scan_chars else data
+            case _:
+                logger.error(f"Title extraction received unsupported data type: {type(data)}")
+                return None
+
+        # Search only in the prefix
+        if m := TITLE_RE.search(prefix):
+            title = html.unescape(" ".join(m.group(1).split())).strip()
+            # Some safe limit
+            return title[:2000]
+        return None
+        
+    except Exception as e:
+        logger.error(f"Title extraction failed: {e}")
+        return None

changedetectionio/is_safe_url.py

@@ -0,0 +1,113 @@
+"""
+URL redirect validation module for preventing open redirect vulnerabilities.
+
+This module provides functionality to safely validate redirect URLs, ensuring they:
+1. Point to internal routes only (no external redirects)
+2. Are properly normalized (preventing browser parsing differences)
+3. Match registered Flask routes (no fake/non-existent pages)
+4. Are fully logged for security monitoring
+
+References:
+- https://flask-login.readthedocs.io/ (safe redirect patterns)
+- https://blog.miguelgrinberg.com/post/the-flask-mega-tutorial-part-v-user-logins
+- https://www.pythonkitchen.com/how-prevent-open-redirect-vulnerab-flask/
+"""
+
+from urllib.parse import urlparse, urljoin
+from flask import request
+from loguru import logger
+
+
+def is_safe_url(target, app):
+    """
+    Validate that a redirect URL is safe to prevent open redirect vulnerabilities.
+
+    This follows Flask/Werkzeug best practices by ensuring the redirect URL:
+    1. Is a relative path starting with exactly one '/'
+    2. Does not start with '//' (double-slash attack)
+    3. Has no external protocol handlers
+    4. Points to a valid registered route in the application
+    5. Is properly normalized to prevent browser parsing differences
+
+    Args:
+        target: The URL to validate (e.g., '/settings', '/login#top')
+        app: The Flask application instance (needed for route validation)
+
+    Returns:
+        bool: True if the URL is safe for redirection, False otherwise
+
+    Examples:
+        >>> is_safe_url('/settings', app)
+        True
+        >>> is_safe_url('//evil.com', app)
+        False
+        >>> is_safe_url('/settings#general', app)
+        True
+        >>> is_safe_url('/fake-page', app)
+        False
+    """
+    if not target:
+        return False
+
+    # Normalize the URL to prevent browser parsing differences
+    # Strip whitespace and replace backslashes (which some browsers interpret as forward slashes)
+    target = target.strip()
+    target = target.replace('\\', '/')
+
+    # First, check if it starts with // or more (double-slash attack)
+    if target.startswith('//'):
+        logger.warning(f"Blocked redirect attempt with double-slash: {target}")
+        return False
+
+    # Parse the URL to check for scheme and netloc
+    parsed = urlparse(target)
+
+    # Block any URL with a scheme (http://, https://, javascript:, etc.)
+    if parsed.scheme:
+        logger.warning(f"Blocked redirect attempt with scheme: {target}")
+        return False
+
+    # Block any URL with a network location (netloc)
+    # This catches patterns like //evil.com, user@host, etc.
+    if parsed.netloc:
+        logger.warning(f"Blocked redirect attempt with netloc: {target}")
+        return False
+
+    # At this point, we have a relative URL with no scheme or netloc
+    # Use urljoin to resolve it and verify it points to the same host
+    ref_url = urlparse(request.host_url)
+    test_url = urlparse(urljoin(request.host_url, target))
+
+    # Check: ensure the resolved URL has the same netloc as current host
+    if not (test_url.scheme in ('http', 'https') and ref_url.netloc == test_url.netloc):
+        logger.warning(f"Blocked redirect attempt with mismatched netloc: {target}")
+        return False
+
+    # Additional validation: Check if the URL matches a registered route
+    # This prevents redirects to non-existent pages or unintended endpoints
+    try:
+        # Get the path without query string and fragment
+        # Fragments (like #general) are automatically stripped by urlparse
+        path = parsed.path
+
+        # Create a URL adapter bound to the server name
+        adapter = app.url_map.bind(ref_url.netloc)
+
+        # Try to match the path to a registered route
+        # This will raise NotFound if the route doesn't exist
+        endpoint, values = adapter.match(path, return_rule=False)
+
+        # Block redirects to static file endpoints - these are catch-all routes
+        # that would match arbitrary paths, potentially allowing unintended redirects
+        if endpoint in ('static_content', 'static', 'static_flags'):
+            logger.warning(f"Blocked redirect to static endpoint: {target}")
+            return False
+
+        # Successfully matched a valid route
+        logger.debug(f"Validated safe redirect to endpoint '{endpoint}': {target}")
+        return True
+
+    except Exception as e:
+        # Route doesn't exist or can't be matched
+        logger.warning(f"Blocked redirect to non-existent route: {target} (error: {e})")
+        return False

changedetectionio/jinja2_custom/__init__.py

@@ -0,0 +1,22 @@
+"""
+Jinja2 custom extensions and safe rendering utilities.
+"""
+from .extensions.TimeExtension import TimeExtension
+from .safe_jinja import (
+    render,
+    render_fully_escaped,
+    create_jinja_env,
+    JINJA2_MAX_RETURN_PAYLOAD_SIZE,
+    DEFAULT_JINJA2_EXTENSIONS,
+)
+from .plugins.regex import regex_replace
+
+__all__ = [
+    'TimeExtension',
+    'render',
+    'render_fully_escaped',
+    'create_jinja_env',
+    'JINJA2_MAX_RETURN_PAYLOAD_SIZE',
+    'DEFAULT_JINJA2_EXTENSIONS',
+    'regex_replace',
+]

changedetectionio/jinja2_custom/extensions/TimeExtension.py

@@ -0,0 +1,221 @@
+"""
+Jinja2 TimeExtension - Custom date/time handling for templates.
+
+This extension provides the {% now %} tag for Jinja2 templates, offering timezone-aware
+date/time formatting with support for time offsets.
+
+Why This Extension Exists:
+    The Arrow library has a now() function (arrow.now()), but Jinja2 templates cannot
+    directly call Python functions - they need extensions or filters to expose functionality.
+
+    This TimeExtension serves as a Jinja2-to-Arrow bridge that:
+
+    1. Makes Arrow accessible in templates - Jinja2 requires registering functions/tags
+       through extensions. You cannot use arrow.now() directly in a template.
+
+    2. Provides template-friendly syntax - Instead of complex Python code, you get clean tags:
+       {% now 'UTC' %}
+       {% now 'UTC' + 'hours=2' %}
+       {% now 'Europe/London', '%Y-%m-%d' %}
+
+    3. Adds convenience features on top of Arrow:
+       - Default timezone from environment variable (TZ) or config
+       - Default datetime format configuration
+       - Offset syntax parsing: 'hours=2,minutes=30' → shift(hours=2, minutes=30)
+       - Empty string timezone support to use configured defaults
+
+    4. Maintains security - Works within Jinja2's sandboxed environment so users
+       cannot access arbitrary Python code or objects.
+
+    Essentially, this is a Jinja2 wrapper around arrow.now() and arrow.shift() that
+    provides user-friendly template syntax while maintaining security.
+
+Basic Usage:
+    {% now 'UTC' %}
+    # Output: Wed, 09 Dec 2015 23:33:01
+
+Custom Format:
+    {% now 'UTC', '%Y-%m-%d %H:%M:%S' %}
+    # Output: 2015-12-09 23:33:01
+
+Timezone Support:
+    {% now 'America/New_York' %}
+    {% now 'Europe/London' %}
+    {% now '' %}  # Uses default timezone from environment.default_timezone
+
+Time Offsets (Addition):
+    {% now 'UTC' + 'hours=2' %}
+    {% now 'UTC' + 'hours=2,minutes=30' %}
+    {% now 'UTC' + 'days=1,hours=2,minutes=15,seconds=10' %}
+
+Time Offsets (Subtraction):
+    {% now 'UTC' - 'minutes=11' %}
+    {% now 'UTC' - 'days=2,minutes=33,seconds=1' %}
+
+Time Offsets with Custom Format:
+    {% now 'UTC' + 'hours=2', '%Y-%m-%d %H:%M:%S' %}
+    # Output: 2015-12-10 01:33:01
+
+Weekday Support (for finding next/previous weekday):
+    {% now 'UTC' + 'weekday=0' %}  # Next Monday (0=Monday, 6=Sunday)
+    {% now 'UTC' + 'weekday=4' %}  # Next Friday
+
+Configuration:
+    - Default timezone: Set via TZ environment variable or override environment.default_timezone
+    - Default format: '%a, %d %b %Y %H:%M:%S' (can be overridden via environment.datetime_format)
+
+Environment Customization:
+    from changedetectionio.jinja2_custom import create_jinja_env
+
+    jinja2_env = create_jinja_env()
+    jinja2_env.default_timezone = 'America/New_York'  # Override default timezone
+    jinja2_env.datetime_format = '%Y-%m-%d %H:%M'      # Override default format
+
+Supported Offset Parameters:
+    - years, months, weeks, days
+    - hours, minutes, seconds, microseconds
+    - weekday (0=Monday through 6=Sunday, must be integer)
+
+Note:
+    This extension uses the Arrow library for timezone-aware datetime handling.
+    All timezone names should be valid IANA timezone identifiers (e.g., 'America/New_York').
+"""
+import arrow
+
+from jinja2 import nodes
+from jinja2.ext import Extension
+import os
+
+class TimeExtension(Extension):
+    """
+    Jinja2 Extension providing the {% now %} tag for timezone-aware date/time rendering.
+
+    This extension adds two attributes to the Jinja2 environment:
+    - datetime_format: Default strftime format string (default: '%a, %d %b %Y %H:%M:%S')
+    - default_timezone: Default timezone for rendering (default: TZ env var or 'UTC')
+
+    Both can be overridden after environment creation by setting the attributes directly.
+    """
+
+    tags = {'now'}
+
+    def __init__(self, environment):
+        """Jinja2 Extension constructor."""
+        super().__init__(environment)
+
+        environment.extend(
+            datetime_format='%a, %d %b %Y %H:%M:%S',
+            default_timezone=os.getenv('TZ', 'UTC').strip()
+        )
+
+    def _datetime(self, timezone, operator, offset, datetime_format):
+        """
+        Get current datetime with time offset applied.
+
+        Args:
+            timezone: IANA timezone identifier (e.g., 'UTC', 'America/New_York') or empty string for default
+            operator: '+' for addition or '-' for subtraction
+            offset: Comma-separated offset parameters (e.g., 'hours=2,minutes=30')
+            datetime_format: strftime format string or None to use environment default
+
+        Returns:
+            Formatted datetime string with offset applied
+
+        Example:
+            _datetime('UTC', '+', 'hours=2,minutes=30', '%Y-%m-%d %H:%M:%S')
+            # Returns current time + 2.5 hours
+        """
+        # Use default timezone if none specified
+        if not timezone or timezone == '':
+            timezone = self.environment.default_timezone
+
+        d = arrow.now(timezone)
+
+        # parse shift params from offset and include operator
+        shift_params = {}
+        for param in offset.split(','):
+            interval, value = param.split('=')
+            shift_params[interval.strip()] = float(operator + value.strip())
+
+        # Fix weekday parameter can not be float
+        if 'weekday' in shift_params:
+            shift_params['weekday'] = int(shift_params['weekday'])
+
+        d = d.shift(**shift_params)
+
+        if datetime_format is None:
+            datetime_format = self.environment.datetime_format
+        return d.strftime(datetime_format)
+
+    def _now(self, timezone, datetime_format):
+        """
+        Get current datetime without any offset.
+
+        Args:
+            timezone: IANA timezone identifier (e.g., 'UTC', 'America/New_York') or empty string for default
+            datetime_format: strftime format string or None to use environment default
+
+        Returns:
+            Formatted datetime string for current time
+
+        Example:
+            _now('America/New_York', '%Y-%m-%d %H:%M:%S')
+            # Returns current time in New York timezone
+        """
+        # Use default timezone if none specified
+        if not timezone or timezone == '':
+            timezone = self.environment.default_timezone
+
+        if datetime_format is None:
+            datetime_format = self.environment.datetime_format
+        return arrow.now(timezone).strftime(datetime_format)
+
+    def parse(self, parser):
+        """
+        Parse the {% now %} tag and generate appropriate AST nodes.
+
+        This method is called by Jinja2 when it encounters a {% now %} tag.
+        It parses the tag syntax and determines whether to call _now() or _datetime()
+        based on whether offset operations (+ or -) are present.
+
+        Supported syntax:
+            {% now 'timezone' %}                              -> calls _now()
+            {% now 'timezone', 'format' %}                    -> calls _now()
+            {% now 'timezone' + 'offset' %}                   -> calls _datetime()
+            {% now 'timezone' + 'offset', 'format' %}         -> calls _datetime()
+            {% now 'timezone' - 'offset', 'format' %}         -> calls _datetime()
+
+        Args:
+            parser: Jinja2 parser instance
+
+        Returns:
+            nodes.Output: AST output node containing the formatted datetime string
+        """
+        lineno = next(parser.stream).lineno
+
+        node = parser.parse_expression()
+
+        if parser.stream.skip_if('comma'):
+            datetime_format = parser.parse_expression()
+        else:
+            datetime_format = nodes.Const(None)
+
+        if isinstance(node, nodes.Add):
+            call_method = self.call_method(
+                '_datetime',
+                [node.left, nodes.Const('+'), node.right, datetime_format],
+                lineno=lineno,
+            )
+        elif isinstance(node, nodes.Sub):
+            call_method = self.call_method(
+                '_datetime',
+                [node.left, nodes.Const('-'), node.right, datetime_format],
+                lineno=lineno,
+            )
+        else:
+            call_method = self.call_method(
+                '_now',
+                [node, datetime_format],
+                lineno=lineno,
+            )
+        return nodes.Output([call_method], lineno=lineno)

changedetectionio/jinja2_custom/plugins/__init__.py

@@ -0,0 +1,6 @@
+"""
+Jinja2 custom filter plugins for changedetection.io
+"""
+from .regex import regex_replace
+
+__all__ = ['regex_replace']

changedetectionio/jinja2_custom/plugins/regex.py

@@ -0,0 +1,98 @@
+"""
+Regex filter plugin for Jinja2 templates.
+
+Provides regex_replace filter for pattern-based string replacements in templates.
+"""
+import re
+import signal
+from loguru import logger
+
+
+def regex_replace(value: str, pattern: str, replacement: str = '', count: int = 0) -> str:
+    """
+    Replace occurrences of a regex pattern in a string.
+
+    Security: Protected against ReDoS (Regular Expression Denial of Service) attacks:
+    - Limits input value size to prevent excessive processing
+    - Uses timeout mechanism to prevent runaway regex operations
+    - Validates pattern complexity to prevent catastrophic backtracking
+
+    Args:
+        value: The input string to perform replacements on
+        pattern: The regex pattern to search for
+        replacement: The replacement string (default: '')
+        count: Maximum number of replacements (0 = replace all, default: 0)
+
+    Returns:
+        String with replacements applied, or original value on error
+
+    Example:
+        {{ "hello world" | regex_replace("world", "universe") }}
+        {{ diff | regex_replace("<td>([^<]+)</td><td>([^<]+)</td>", "Label1: \\1\\nLabel2: \\2") }}
+
+    Security limits:
+        - Maximum input size: 10MB
+        - Maximum pattern length: 500 characters
+        - Operation timeout: 10 seconds
+        - Dangerous nested quantifier patterns are rejected
+    """
+    # Security limits
+    MAX_INPUT_SIZE = 1024 * 1024 * 10 # 10MB max input size
+    MAX_PATTERN_LENGTH = 500  # Maximum regex pattern length
+    REGEX_TIMEOUT_SECONDS = 10  # Maximum time for regex operation
+
+    # Validate input sizes
+    value_str = str(value)
+    if len(value_str) > MAX_INPUT_SIZE:
+        logger.warning(f"regex_replace: Input too large ({len(value_str)} bytes), truncating")
+        value_str = value_str[:MAX_INPUT_SIZE]
+
+    if len(pattern) > MAX_PATTERN_LENGTH:
+        logger.warning(f"regex_replace: Pattern too long ({len(pattern)} chars), rejecting")
+        return value_str
+
+    # Check for potentially dangerous patterns (basic checks)
+    # Nested quantifiers like (a+)+ can cause catastrophic backtracking
+    dangerous_patterns = [
+        r'\([^)]*\+[^)]*\)\+',  # (x+)+
+        r'\([^)]*\*[^)]*\)\+',  # (x*)+
+        r'\([^)]*\+[^)]*\)\*',  # (x+)*
+        r'\([^)]*\*[^)]*\)\*',  # (x*)*
+    ]
+
+    for dangerous in dangerous_patterns:
+        if re.search(dangerous, pattern):
+            logger.warning(f"regex_replace: Potentially dangerous pattern detected: {pattern}")
+            return value_str
+
+    def timeout_handler(signum, frame):
+        raise TimeoutError("Regex operation timed out")
+
+    try:
+        # Set up timeout for regex operation (Unix-like systems only)
+        # This prevents ReDoS attacks
+        old_handler = None
+        if hasattr(signal, 'SIGALRM'):
+            old_handler = signal.signal(signal.SIGALRM, timeout_handler)
+            signal.alarm(REGEX_TIMEOUT_SECONDS)
+
+        try:
+            result = re.sub(pattern, replacement, value_str, count=count)
+        finally:
+            # Cancel the alarm
+            if hasattr(signal, 'SIGALRM'):
+                signal.alarm(0)
+                if old_handler is not None:
+                    signal.signal(signal.SIGALRM, old_handler)
+
+        return result
+
+    except TimeoutError:
+        logger.error(f"regex_replace: Regex operation timed out - possible ReDoS attack. Pattern: {pattern}")
+        return value_str
+    except re.error as e:
+        logger.warning(f"regex_replace: Invalid regex pattern: {e}")
+        return value_str
+    except Exception as e:
+        logger.error(f"regex_replace: Unexpected error: {e}")
+        return value_str

changedetectionio/jinja2_custom/safe_jinja.py

@@ -0,0 +1,64 @@
+"""
+Safe Jinja2 render with max payload sizes
+
+See https://jinja.palletsprojects.com/en/3.1.x/sandbox/#security-considerations
+"""
+
+import jinja2.sandbox
+import typing as t
+import os
+from .extensions.TimeExtension import TimeExtension
+from .plugins import regex_replace
+
+JINJA2_MAX_RETURN_PAYLOAD_SIZE = 1024 * int(os.getenv("JINJA2_MAX_RETURN_PAYLOAD_SIZE_KB", 1024 * 10))
+
+# Default extensions - can be overridden in create_jinja_env()
+DEFAULT_JINJA2_EXTENSIONS = [TimeExtension]
+
+def create_jinja_env(extensions=None, **kwargs) -> jinja2.sandbox.ImmutableSandboxedEnvironment:
+    """
+    Create a sandboxed Jinja2 environment with our custom extensions and default timezone.
+
+    Args:
+        extensions: List of extension classes to use (defaults to DEFAULT_JINJA2_EXTENSIONS)
+        **kwargs: Additional arguments to pass to ImmutableSandboxedEnvironment
+
+    Returns:
+        Configured Jinja2 environment
+    """
+    if extensions is None:
+        extensions = DEFAULT_JINJA2_EXTENSIONS
+
+    jinja2_env = jinja2.sandbox.ImmutableSandboxedEnvironment(
+        extensions=extensions,
+        **kwargs
+    )
+
+    # Get default timezone from environment variable
+    default_timezone = os.getenv('TZ', 'UTC').strip()
+    jinja2_env.default_timezone = default_timezone
+
+    # Register custom filters
+    jinja2_env.filters['regex_replace'] = regex_replace
+
+    return jinja2_env
+
+
+# This is used for notifications etc, so actually it's OK to send custom HTML such as <a href> etc, but it should limit what data is available.
+# (Which also limits available functions that could be called)
+def render(template_str, **args: t.Any) -> str:
+    jinja2_env = create_jinja_env()
+    output = jinja2_env.from_string(template_str).render(args)
+    return output[:JINJA2_MAX_RETURN_PAYLOAD_SIZE]
+
+def render_fully_escaped(content):
+    """
+    Escape HTML content safely.
+
+    MEMORY LEAK FIX: Use markupsafe.escape() directly instead of creating
+    Jinja2 environments (was causing 1M+ compilations per page load).
+    Simpler, faster, and no concerns about environment state.
+    """
+    from markupsafe import escape
+    return str(escape(content))
+

changedetectionio/languages.py

@@ -0,0 +1,110 @@
+"""
+Language configuration for i18n support
+Automatically discovers available languages from translations directory
+"""
+import os
+from pathlib import Path
+
+
+def get_timeago_locale(flask_locale):
+    """
+    Convert Flask-Babel locale codes to timeago library locale codes.
+
+    The Python timeago library (https://github.com/hustcc/timeago) supports 48 locales
+    but uses different naming conventions than Flask-Babel. This function maps between them.
+
+    Notable differences:
+    - Chinese: Flask uses 'zh', timeago uses 'zh_CN'
+    - Portuguese: Flask uses 'pt', timeago uses 'pt_PT' or 'pt_BR'
+    - Swedish: Flask uses 'sv', timeago uses 'sv_SE'
+    - Norwegian: Flask uses 'no', timeago uses 'nb_NO' or 'nn_NO'
+    - Hindi: Flask uses 'hi', timeago uses 'in_HI'
+    - Czech: Flask uses 'cs', but timeago doesn't support Czech - fallback to English
+
+    Args:
+        flask_locale (str): Flask-Babel locale code (e.g., 'cs', 'zh', 'pt')
+
+    Returns:
+        str: timeago library locale code (e.g., 'en', 'zh_CN', 'pt_PT')
+    """
+    locale_map = {
+        'zh': 'zh_CN',      # Chinese Simplified
+        # timeago library just hasn't been updated to use the more modern locale naming convention, before BCP 47 / RFC 5646.
+        'zh_TW': 'zh_TW',   # Chinese Traditional (timeago uses zh_TW)
+        'zh_Hant_TW': 'zh_TW',  # Flask-Babel normalizes zh_TW to zh_Hant_TW, map back to timeago's zh_TW
+        'pt': 'pt_PT',      # Portuguese (Portugal)
+        'sv': 'sv_SE',      # Swedish
+        'no': 'nb_NO',      # Norwegian Bokmål
+        'hi': 'in_HI',      # Hindi
+        'cs': 'en',         # Czech not supported by timeago, fallback to English
+        'en_GB': 'en',      # British English - timeago uses 'en'
+        'en_US': 'en',      # American English - timeago uses 'en'
+    }
+    return locale_map.get(flask_locale, flask_locale)
+
+# Language metadata: flag icon CSS class and native name
+# Using flag-icons library: https://flagicons.lipis.dev/
+LANGUAGE_DATA = {
+    'en_GB': {'flag': 'fi fi-gb fis', 'name': 'English (UK)'},
+    'en_US': {'flag': 'fi fi-us fis', 'name': 'English (US)'},
+    'de': {'flag': 'fi fi-de fis', 'name': 'Deutsch'},
+    'fr': {'flag': 'fi fi-fr fis', 'name': 'Français'},
+    'ko': {'flag': 'fi fi-kr fis', 'name': '한국어'},
+    'cs': {'flag': 'fi fi-cz fis', 'name': 'Čeština'},
+    'es': {'flag': 'fi fi-es fis', 'name': 'Español'},
+    'pt': {'flag': 'fi fi-pt fis', 'name': 'Português'},
+    'it': {'flag': 'fi fi-it fis', 'name': 'Italiano'},
+    'ja': {'flag': 'fi fi-jp fis', 'name': '日本語'},
+    'zh': {'flag': 'fi fi-cn fis', 'name': '中文 (简体)'},
+    'zh_Hant_TW': {'flag': 'fi fi-tw fis', 'name': '繁體中文'},
+    'ru': {'flag': 'fi fi-ru fis', 'name': 'Русский'},
+    'pl': {'flag': 'fi fi-pl fis', 'name': 'Polski'},
+    'nl': {'flag': 'fi fi-nl fis', 'name': 'Nederlands'},
+    'sv': {'flag': 'fi fi-se fis', 'name': 'Svenska'},
+    'da': {'flag': 'fi fi-dk fis', 'name': 'Dansk'},
+    'no': {'flag': 'fi fi-no fis', 'name': 'Norsk'},
+    'fi': {'flag': 'fi fi-fi fis', 'name': 'Suomi'},
+    'tr': {'flag': 'fi fi-tr fis', 'name': 'Türkçe'},
+    'ar': {'flag': 'fi fi-sa fis', 'name': 'العربية'},
+    'hi': {'flag': 'fi fi-in fis', 'name': 'हिन्दी'},
+}
+
+
+def get_available_languages():
+    """
+    Discover available languages by scanning the translations directory
+    Returns a dict of available languages with their metadata
+    """
+    translations_dir = Path(__file__).parent / 'translations'
+
+    available = {}
+
+    # Scan for translation directories
+    if translations_dir.exists():
+        for lang_dir in translations_dir.iterdir():
+            if lang_dir.is_dir() and lang_dir.name in LANGUAGE_DATA:
+                # Check if messages.po exists
+                po_file = lang_dir / 'LC_MESSAGES' / 'messages.po'
+                if po_file.exists():
+                    available[lang_dir.name] = LANGUAGE_DATA[lang_dir.name]
+
+    # If no English variants found, fall back to adding en_GB as default
+    if 'en_GB' not in available and 'en_US' not in available:
+        available['en_GB'] = LANGUAGE_DATA['en_GB']
+
+    return available
+
+
+def get_language_codes():
+    """Get list of available language codes"""
+    return list(get_available_languages().keys())
+
+
+def get_flag_for_locale(locale):
+    """Get flag emoji for a locale, or globe if unknown"""
+    return LANGUAGE_DATA.get(locale, {}).get('flag', '🌐')
+
+
+def get_name_for_locale(locale):
+    """Get native name for a locale"""
+    return LANGUAGE_DATA.get(locale, {}).get('name', locale.upper())

changedetectionio/model/App.py

@@ -1,6 +1,7 @@
 from os import getenv
+from copy import deepcopy
 
-from changedetectionio.blueprint.rss import RSS_FORMAT_TYPES
+from changedetectionio.blueprint.rss import RSS_FORMAT_TYPES, RSS_CONTENT_FORMAT_DEFAULT
 
 from changedetectionio.notification import (
     default_notification_body,
@@ -28,7 +29,7 @@ class model(dict):
                     'proxy': None, # Preferred proxy connection
                     'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
                     'timeout': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
-                    'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "10")),  # Number of threads, lower is better for slow connections
+                    'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "5")),  # Number of threads, lower is better for slow connections
                     'default_ua': {
                         'html_requests': getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT", DEFAULT_SETTINGS_HEADERS_USERAGENT),
                         'html_webdriver': None,
@@ -36,15 +37,19 @@ class model(dict):
                 },
                 'application': {
                     # Custom notification content
+                    'all_paused': False,
+                    'all_muted': False,
                     'api_access_token_enabled': True,
                     'base_url' : None,
                     'empty_pages_are_a_change': False,
-                    'extract_title_as_title': False,
                     'fetch_backend': getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
                     'filter_failure_notification_threshold_attempts': _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT,
                     'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
                     'global_subtractive_selectors': [],
+                    'history_snapshot_max_length': None,
                     'ignore_whitespace': True,
+                    'ignore_status_codes': False, #@todo implement, as ternary.
+                    'ssim_threshold': '0.96',  # Default SSIM threshold for screenshot comparison
                     'notification_body': default_notification_body,
                     'notification_format': default_notification_format,
                     'notification_title': default_notification_title,
@@ -53,15 +58,23 @@ class model(dict):
                     'password': False,
                     'render_anchor_tag_content': False,
                     'rss_access_token': None,
-                    'rss_content_format': RSS_FORMAT_TYPES[0][0],
+                    'rss_content_format': RSS_CONTENT_FORMAT_DEFAULT,
+                    'rss_template_type': 'system_default',
+                    'rss_template_override': None,
+                    'rss_diff_length': 5,
                     'rss_hide_muted_watches': True,
+                    'rss_reader_mode': False,
+                    'scheduler_timezone_default': None,  # Default IANA timezone name
                     'schema_version' : 0,
                     'shared_diff_access': False,
-                    'webdriver_delay': None , # Extra delay in seconds before extracting text
+                    'strip_ignored_lines': False,
                     'tags': {}, #@todo use Tag.model initialisers
-                    'timezone': None, # Default IANA timezone name
+                    'webdriver_delay': None , # Extra delay in seconds before extracting text
                     'ui': {
+                        'use_page_title_in_list': True,
                         'open_diff_in_new_tab': True,
+                        'socket_io_enabled': True,
+                        'favicons_enabled': True
                     },
                 }
             }
@@ -69,12 +82,13 @@ class model(dict):
 
     def __init__(self, *arg, **kw):
         super(model, self).__init__(*arg, **kw)
-        self.update(self.base_config)
+        # CRITICAL: deepcopy to avoid sharing mutable objects between instances
+        self.update(deepcopy(self.base_config))
 
 
 def parse_headers_from_text_file(filepath):
     headers = {}
-    with open(filepath, 'r') as f:
+    with open(filepath, 'r', encoding='utf-8') as f:
         for l in f.readlines():
             l = l.strip()
             if not l.startswith('#') and ':' in l:

changedetectionio/model/Tag.py

@@ -1,10 +1,48 @@
+"""
+Tag/Group domain model for organizing and overriding watch settings.
+
+ARCHITECTURE NOTE: Configuration Override Hierarchy
+===================================================
+
+Tags can override Watch settings when overrides_watch=True.
+Current implementation requires manual checking in processors:
+
+    for tag_uuid in watch.get('tags'):
+        tag = datastore['settings']['application']['tags'][tag_uuid]
+        if tag.get('overrides_watch'):
+            restock_settings = tag.get('restock_settings', {})
+            break
+
+With Pydantic, this would be automatic via chain resolution:
+    Watch → Tag (first with overrides_watch) → Global
+
+See: Watch.py model docstring for full Pydantic architecture explanation
+See: processors/restock_diff/processor.py:184-192 for current manual implementation
+"""
 
 from changedetectionio.model import watch_base
+from changedetectionio.model.persistence import EntityPersistenceMixin
 
+class model(EntityPersistenceMixin, watch_base):
+    """
+    Tag domain model - groups watches and can override their settings.
 
-class model(watch_base):
+    Tags inherit from watch_base to reuse all the same fields as Watch.
+    When overrides_watch=True, tag settings take precedence over watch settings
+    for all watches in this tag/group.
+
+    Fields:
+        overrides_watch (bool): If True, this tag's settings override watch settings
+        title (str): Display name for this tag/group
+        uuid (str): Unique identifier
+        ... (all fields from watch_base can be set as tag-level overrides)
+
+    Resolution order when overrides_watch=True:
+        Watch.field → Tag.field (if overrides_watch) → Global.field
+    """
 
     def __init__(self, *arg, **kw):
+        # Parent class (watch_base) handles __datastore and __datastore_path
         super(model, self).__init__(*arg, **kw)
 
         self['overrides_watch'] = kw.get('default', {}).get('overrides_watch')
@@ -12,3 +50,7 @@ class model(watch_base):
         if kw.get('default'):
             self.update(kw['default'])
             del kw['default']
+
+    # _save_to_disk() method provided by EntityPersistenceMixin
+    # commit() and _get_commit_data() methods inherited from watch_base
+    # Tag uses default _get_commit_data() (includes all keys)