Adding setting

* improving unique key fix

* also bump timestamp along 1 sec

.dockerignore

@@ -1,2 +1,18 @@
 .git
 .github
+changedetectionio/processors/__pycache__
+changedetectionio/api/__pycache__
+changedetectionio/model/__pycache__
+changedetectionio/blueprint/price_data_follower/__pycache__
+changedetectionio/blueprint/tags/__pycache__
+changedetectionio/blueprint/__pycache__
+changedetectionio/blueprint/browser_steps/__pycache__
+changedetectionio/fetchers/__pycache__
+changedetectionio/tests/visualselector/__pycache__
+changedetectionio/tests/restock/__pycache__
+changedetectionio/tests/__pycache__
+changedetectionio/tests/fetchers/__pycache__
+changedetectionio/tests/unit/__pycache__
+changedetectionio/tests/proxy_list/__pycache__
+changedetectionio/__pycache__
+

.github/dependabot.yml

@@ -0,0 +1,14 @@
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: "weekly"
+    "caronc/apprise":
+      versioning-strategy: "increase"
+      schedule:
+        interval: "daily"
+    groups:
+      all:
+        patterns:
+        - "*"

.github/test/Dockerfile-alpine

@@ -2,7 +2,7 @@
 # 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:3.16
+FROM ghcr.io/linuxserver/baseimage-alpine:3.18
 ENV PYTHONUNBUFFERED=1
 
 COPY requirements.txt /requirements.txt
@@ -12,8 +12,10 @@ RUN \
     cargo \
     g++ \
     gcc \
+    jpeg-dev \
     libc-dev \
     libffi-dev \
+    libjpeg \
     libxslt-dev \
     make \
     openssl-dev \
@@ -26,6 +28,6 @@ RUN \
     py3-pip && \
   echo "**** pip3 install test of changedetection.io ****" && \
   pip3 install -U pip wheel setuptools && \
-  pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.16/ -r /requirements.txt && \
+  pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.18/ -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@v2
+      uses: actions/checkout@v4
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v1
+      uses: github/codeql-action/init@v3
       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@v1
+      uses: github/codeql-action/autobuild@v3
 
     # 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@v1
+      uses: github/codeql-action/analyze@v3

.github/workflows/containers.yml

@@ -39,11 +39,11 @@ 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@v2
-      - name: Set up Python 3.9
-        uses: actions/setup-python@v2
+      - uses: actions/checkout@v4
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v5
         with:
-          python-version: 3.9
+          python-version: 3.11
 
       - name: Install dependencies
         run: |
@@ -58,27 +58,27 @@ jobs:
           echo ${{ github.ref }} > changedetectionio/tag.txt
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
+        uses: docker/setup-qemu-action@v3
         with:
           image: tonistiigi/binfmt:latest
           platforms: all
 
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@v1
+        uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Login to Docker Hub Container Registry
-        uses: docker/login-action@v1
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_HUB_USERNAME }}
           password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }}
 
       - name: Set up Docker Buildx
         id: buildx
-        uses: docker/setup-buildx-action@v1
+        uses: docker/setup-buildx-action@v3
         with:
           install: true
           version: latest
@@ -88,23 +88,25 @@ jobs:
       - name: Build and push :dev
         id: docker_build
         if: ${{ github.ref }} == "refs/heads/master"
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v5
         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/v6,linux/arm/v7
-          cache-from: type=local,src=/tmp/.buildx-cache
-          cache-to: type=local,dest=/tmp/.buildx-cache
-          provenance: false
+          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+# Looks like this was disabled
+#          provenance: false
 
       # A new tagged release is required, which builds :tag and :latest
       - name: Build and push :tag
         id: docker_build_tag_release
         if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v5
         with:
           context: ./
           file: ./Dockerfile
@@ -114,18 +116,12 @@ jobs:
             ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
             ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest
             ghcr.io/dgtlmoon/changedetection.io:latest
-          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
-          cache-from: type=local,src=/tmp/.buildx-cache
-          cache-to: type=local,dest=/tmp/.buildx-cache
-          provenance: false
+          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+# Looks like this was disabled
+#          provenance: false
 
       - name: Image digest
         run: echo step SHA ${{ steps.vars.outputs.sha_short }} tag ${{steps.vars.outputs.tag}} branch ${{steps.vars.outputs.branch}} digest ${{ steps.docker_build.outputs.digest }}
 
-      - name: Cache Docker layers
-        uses: actions/cache@v2
-        with:
-          path: /tmp/.buildx-cache
-          key: ${{ runner.os }}-buildx-${{ github.sha }}
-          restore-keys: |
-            ${{ runner.os }}-buildx-

.github/workflows/pypi-release.yml

@@ -0,0 +1,77 @@
+name: Publish Python 🐍distribution 📦 to PyPI and TestPyPI
+
+on: push
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.11"
+    - name: Install pypa/build
+      run: >-
+        python3 -m
+        pip install
+        build
+        --user
+    - name: Build a binary wheel and a source tarball
+      run: python3 -m build
+    - name: Store the distribution packages
+      uses: actions/upload-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+
+
+  test-pypi-package:
+    name: Test the built 📦 package works basically.
+    runs-on: ubuntu-latest
+    needs:
+    - build
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Set up Python 3.11
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.11'
+    - name: Test that the basic pip built package runs without error
+      run: |
+        set -ex
+        sudo pip3 install --upgrade pip 
+        pip3 install dist/changedetection.io*.whl
+        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
+        killall changedetection.io
+
+
+  publish-to-pypi:
+    name: >-
+      Publish Python 🐍 distribution 📦 to PyPI
+    if: startsWith(github.ref, 'refs/tags/')  # only publish to PyPI on tag pushes
+    needs:
+    - test-pypi-package
+    runs-on: ubuntu-latest
+    environment:
+      name: release
+      url: https://pypi.org/p/changedetection.io
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Publish distribution 📦 to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/pypi.yml

@@ -1,38 +0,0 @@
-name: PyPi Test and Push tagged release
-
-# Triggers the workflow on push or pull request events
-on:
-  workflow_run:
-    workflows: ["ChangeDetection.io Test"]
-    tags: '*.*'
-    types: [completed]
-
-
-jobs:
-  test-build:
-    runs-on: ubuntu-latest
-    steps:
-
-      - uses: actions/checkout@v2
-      - name: Set up Python 3.9
-        uses: actions/setup-python@v2
-        with:
-          python-version: 3.9
-
-
-      - name: Test that pip builds without error
-        run: |
-          pip3 --version
-          python3 -m pip install wheel
-          python3 setup.py bdist_wheel
-          python3 -m pip install dist/changedetection.io-*-none-any.whl --force
-          changedetection.io -d /tmp -p 10000 &
-          sleep 3
-          curl http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
-          killall -9 changedetection.io
-
-      # https://github.com/docker/build-push-action/blob/master/docs/advanced/test-before-push.md ?
-      # https://github.com/docker/buildx/issues/59 ? Needs to be one platform?
-
-      # https://github.com/docker/buildx/issues/495#issuecomment-918925854
-#if: ${{ github.event_name == 'release'}}

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

@@ -11,12 +11,14 @@ on:
       - requirements.txt
       - Dockerfile
       - .github/workflows/*
+      - .github/test/Dockerfile*
 
   pull_request:
     paths:
       - requirements.txt
       - Dockerfile
       - .github/workflows/*
+      - .github/test/Dockerfile*
 
   # 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
@@ -24,22 +26,22 @@ jobs:
   test-container-build:
     runs-on: ubuntu-latest
     steps:
-        - uses: actions/checkout@v2
-        - name: Set up Python 3.9
-          uses: actions/setup-python@v2
+        - uses: actions/checkout@v4
+        - name: Set up Python 3.11
+          uses: actions/setup-python@v5
           with:
-            python-version: 3.9
+            python-version: 3.11
 
         # Just test that the build works, some libraries won't compile on ARM/rPi etc
         - name: Set up QEMU
-          uses: docker/setup-qemu-action@v1
+          uses: docker/setup-qemu-action@v3
           with:
             image: tonistiigi/binfmt:latest
             platforms: all
 
         - name: Set up Docker Buildx
           id: buildx
-          uses: docker/setup-buildx-action@v1
+          uses: docker/setup-buildx-action@v3
           with:
             install: true
             version: latest
@@ -49,7 +51,7 @@ jobs:
         # 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@v2
+          uses: docker/build-push-action@v5
           with:
             context: ./
             file: ./.github/test/Dockerfile-alpine
@@ -57,12 +59,12 @@ jobs:
 
         - name: Test that the docker containers can build
           id: docker_build
-          uses: docker/build-push-action@v2
+          uses: docker/build-push-action@v5
           # https://github.com/docker/build-push-action#customizing
           with:
             context: ./
             file: ./Dockerfile
-            platforms: linux/arm/v7,linux/arm/v6,linux/amd64,linux/arm64,
+            platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
             cache-from: type=local,src=/tmp/.buildx-cache
             cache-to: type=local,dest=/tmp/.buildx-cache
 

.github/workflows/test-only.yml

@@ -7,13 +7,13 @@ jobs:
   test-application:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
 
       # Mainly just for link/flake8
-      - name: Set up Python 3.10
-        uses: actions/setup-python@v2
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.11'
 
       - name: Lint with flake8
         run: |
@@ -27,51 +27,198 @@ jobs:
         run: |
           
           docker network create changedet-network
-
-          # Selenium+browserless
-          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome-debug:3.141.59
-          docker run --network changedet-network -d --hostname browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
+          
+          # 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
 
       - name: Build changedetection.io container for testing
         run: |         
           # Build a changedetection.io container and start testing inside
-          docker build . -t test-changedetectionio
+          docker build --build-arg LOGGER_LEVEL=TRACE -t test-changedetectionio .
+          # Debug info
+          docker run test-changedetectionio  bash -c 'pip list'
 
-      - name: Test built container with pytest
+      - name: Spin up ancillary SMTP+Echo message test server
+        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 'python changedetectionio/tests/smtp/smtp-test-server.py' 
+
+      - name: Show docker container state and other debug info
+        run: |
+          set -x
+          echo "Running processes in docker..."
+          docker ps
+
+      - name: Test built container with Pytest (generally as requests/plaintext fetching)
         run: |
-          
           # Unit tests
+          echo "run test with unittest"
           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'
           
           # All tests
-          docker run --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio && ./run_basic_tests.sh'
+          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'
 
-      - name: Test built container selenium+browserless/playwright
+# PLAYWRIGHT/NODE-> CDP
+      - name: Playwright and SocketPuppetBrowser - Specific tests in built container
         run: |
-          
-          # Selenium fetch
-          docker run -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'
-          
-          # Playwright/Browserless fetch
-          docker run -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
+          # 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'
 
-      - name: Test proxy interaction
+
+      - 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 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
+
+      - 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
+        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'
+
+      - name: Pyppeteer and SocketPuppetBrowser - Headers and requests checks
+        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'
+
+      - name: Pyppeteer 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 "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
+      - 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'
+
+      - name: Specific tests in built container 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'
+
+# OTHER STUFF
+      - name: Test SMTP notification mime types
+        run: |
+          # SMTP content types - needs the 'Debug SMTP server/echo message back server' container from 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
         run: |
           cd changedetectionio
           ./run_proxy_tests.sh
           cd ..
 
+      - name: Test proxy SOCKS5 style interaction
+        run: |
+          cd changedetectionio
+          ./run_socks_proxy_tests.sh
+          cd ..
+
+      - 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
         run: |
-          docker run -p 5556:5000 -d test-changedetectionio
+          docker run --name test-changedetectionio -p 5556:5000  -d test-changedetectionio
           sleep 3
           # Should return 0 (no error) when grep finds it
-          curl -s http://localhost:5556 |grep -q checkbox-uuid
+          curl --retry-connrefused --retry 6  -s http://localhost:5556 |grep -q checkbox-uuid
           
           # and IPv6
-          curl -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
-          
+          curl --retry-connrefused --retry 6  -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
 
-#export WEBDRIVER_URL=http://localhost:4444/wd/hub
-#pytest tests/fetchers/test_content.py
-#pytest tests/test_errorhandling.py
+          # Check whether TRACE log is enabled.
+          # Also, check whether TRACE is came from STDERR
+          docker logs test-changedetectionio 2>&1 1>/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
+        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
+            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
+            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.txt
+          docker logs test-cdio-basic-tests 2> output-logs/test-cdio-basic-tests-stderr.txt
+
+      - name: Store container log
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-cdio-basic-tests-output
+          path: output-logs

CONTRIBUTING.md

@@ -2,7 +2,7 @@ Contributing is always welcome!
 
 I am no professional flask developer, if you know a better way that something can be done, please let me know!
 
-Otherwise, it's always best to PR into the `dev` branch.
+Otherwise, it's always best to PR into the `master` branch.
 
 Please be sure that all new functionality has a matching test!
 

Dockerfile

@@ -1,5 +1,8 @@
 # pip dependencies install stage
-FROM python:3.10-slim as builder
+
+# @NOTE! I would love to move to 3.11 but it breaks the async handler in changedetectionio/content_fetchers/puppeteer.py
+#        If you know how to fix it, please do! and test it for both 3.10 and 3.11
+FROM python:3.10-slim-bookworm as builder
 
 # See `cryptography` pin comment in requirements.txt
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
@@ -25,14 +28,13 @@ RUN pip install --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~=1.27.1 \
+RUN pip install --target=/dependencies playwright~=1.41.2 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
-FROM python:3.10-slim
+FROM python:3.10-slim-bookworm
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    libssl1.1 \
     libxslt1.1 \
     # For pdftohtml
     poppler-utils \
@@ -54,12 +56,17 @@ ENV PYTHONPATH=/usr/local
 
 EXPOSE 5000
 
-# The actual flask app
+# The actual flask app module
 COPY changedetectionio /app/changedetectionio
-
-# The eventlet server wrapper
+# Starting wrapper
 COPY changedetection.py /app/changedetection.py
 
-WORKDIR /app
+# Github Action test purpose(test-only.yml).
+# On production, it is effectively LOGGER_LEVEL=''.
+ARG LOGGER_LEVEL=''
+ENV LOGGER_LEVEL "$LOGGER_LEVEL"
+
+WORKDIR /app
+CMD ["python", "./changedetection.py", "-d", "/datastore"]
+
 
-CMD [ "python", "./changedetection.py" , "-d", "/datastore"]

MANIFEST.in

@@ -1,7 +1,8 @@
 recursive-include changedetectionio/api *
 recursive-include changedetectionio/blueprint *
+recursive-include changedetectionio/content_fetchers *
 recursive-include changedetectionio/model *
-recursive-include changedetectionio/res *
+recursive-include changedetectionio/processors *
 recursive-include changedetectionio/static *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/tests *
@@ -9,6 +10,12 @@ prune changedetectionio/static/package-lock.json
 prune changedetectionio/static/styles/node_modules
 prune changedetectionio/static/styles/package-lock.json
 include changedetection.py
+include requirements.txt
+include README-pip.md
 global-exclude *.pyc
 global-exclude node_modules
 global-exclude venv
+
+global-exclude test-datastore
+global-exclude changedetection.io*dist-info
+global-exclude changedetectionio/tests/proxy_socks5/test-datastore

Procfile

@@ -1 +0,0 @@
-web: python3 ./changedetection.py -C -d ./datastore -p $PORT

README-pip.md

@@ -2,19 +2,44 @@
 
 Live your data-life pro-actively, track website content changes and receive notifications via Discord, Email, Slack, Telegram and 70+ 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"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=pip)
+[<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://lemonade.changedetection.io/start) 
+[**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://changedetection.io) 
 
 
-#### Example use cases
+### Target specific parts of the webpage using the Visual Selector tool.
+
+Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
+
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Select parts and elements of a web page to monitor for changes"  title="Select parts and elements of a web page to monitor for changes" />](https://changedetection.io?src=pip)
+
+### Easily see what changed, examine by word, line, or individual character.
+
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://changedetection.io?src=pip)
+
+
+### Perform interactive browser steps
+
+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.
+
+[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more"  title="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more" />](https://changedetection.io?src=pip)
+
+After **Browser Steps** have been run, then visit the **Visual Selector** tab to refine the content you're interested in.
+Requires Playwright to be enabled.
+
+
+### Example use cases
 
 - Products and services have a change in pricing
 - _Out of stock notification_ and _Back In stock notification_
+- Monitor and track PDF file changes, know when a PDF file has text changes.
 - Governmental department updates (changes are often only on their websites)
 - New software releases, security advisories when you're not on their mailing list.
 - Festivals with changes
+- Discogs restock alerts and monitoring
 - Realestate listing changes
 - Know when your favourite whiskey is on sale, or other special deals are announced before anyone else
 - COVID related news from government websites
@@ -27,18 +52,34 @@ Live your data-life pro-actively, track website content changes and receive noti
 - Create RSS feeds based on changes in web content
 - Monitor HTML source code for unexpected changes, strengthen your PCI compliance
 - You have a very sensitive list of URLs to watch and you do _not_ want to use the paid alternatives. (Remember, _you_ are the product)
+- Get notified when certain keywords appear in Twitter search results
+- Proactively search for jobs, get notified when companies update their careers page, search job portals for keywords.
+- Get alerts when new job positions are open on Bamboo HR and other job platforms
+- Website defacement monitoring
+- Pokémon Card Restock Tracker / Pokémon TCG Tracker
+- RegTech - stay ahead of regulatory changes, regulatory compliance
 
 _Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
 
 #### Key Features
 
 - Lots of trigger filters, such as "Trigger on text", "Remove text by selector", "Ignore text", "Extract text", also using regular-expressions!
-- Target elements with xPath and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
+- Target elements with xPath(1.0) and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
 - Switch between fast non-JS and Chrome JS based "fetchers"
+- Track changes in PDF files (Monitor text changed in the PDF, Also monitor PDF filesize and checksums)
 - Easily specify how often a site should be checked
 - Execute JS before extracting text (Good for logging in, see examples in the UI!)
 - Override Request Headers, Specify `POST` or `GET` and other methods
 - Use the "Visual Selector" to help target specific elements
+- 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. 
+
+Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
+
 
 
 ```bash
@@ -54,5 +95,5 @@ $ 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://github.com/dgtlmoon/changedetection.io for more information.
+See https://changedetection.io for more information.
 

README.md

@@ -1,32 +1,33 @@
-## Web Site Change Detection, Monitoring and Notification.
+## Web Site Change Detection, Restock monitoring and notifications.
 
 **_Detect website content changes and perform meaningful actions - trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._**
 
 _Live your data-life pro-actively._ 
 
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=github)
+[<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)
 
 [![Release Version][release-shield]][release-link] [![Docker Pulls][docker-pulls]][docker-link] [![License][license-shield]](LICENSE.md)
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
-[**Don't have time? Let us host it for you! try our $8.99/month subscription - use our proxies and support!**](https://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
+[**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.
 - Get started watching and receiving website change notifications straight away.
-
+- See our [tutorials and how-to page for more inspiration](https://changedetection.io/tutorials) 
 
 ### Target specific parts of the webpage using the Visual Selector tool.
 
 Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://lemonade.changedetection.io/start?src=github)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Select parts and elements of a web page to monitor for changes"  title="Select parts and elements of a web page to monitor for changes" />](https://changedetection.io?src=github)
 
 ### Easily see what changed, examine by word, line, or individual character.
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://lemonade.changedetection.io/start?src=github)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://changedetection.io?src=github)
 
 
 ### Perform interactive browser steps
@@ -35,7 +36,7 @@ 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.
 
-[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Website change detection with interactive browser steps, login, cookies etc" />](https://lemonade.changedetection.io/start?src=github)
+[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more"  title="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more" />](https://changedetection.io?src=github)
 
 After **Browser Steps** have been run, then visit the **Visual Selector** tab to refine the content you're interested in.
 Requires Playwright to be enabled.
@@ -49,6 +50,7 @@ Requires Playwright to be enabled.
 - Governmental department updates (changes are often only on their websites)
 - New software releases, security advisories when you're not on their mailing list.
 - Festivals with changes
+- Discogs restock alerts and monitoring
 - Realestate listing changes
 - Know when your favourite whiskey is on sale, or other special deals are announced before anyone else
 - COVID related news from government websites
@@ -64,13 +66,16 @@ Requires Playwright to be enabled.
 - Get notified when certain keywords appear in Twitter search results
 - Proactively search for jobs, get notified when companies update their careers page, search job portals for keywords.
 - Get alerts when new job positions are open on Bamboo HR and other job platforms
+- Website defacement monitoring
+- Pokémon Card Restock Tracker / Pokémon TCG Tracker
+- RegTech - stay ahead of regulatory changes, regulatory compliance
 
 _Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
 
 #### Key Features
 
 - Lots of trigger filters, such as "Trigger on text", "Remove text by selector", "Ignore text", "Extract text", also using regular-expressions!
-- Target elements with xPath and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
+- Target elements with xPath(1.0) and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
 - Switch between fast non-JS and Chrome JS based "fetchers"
 - Track changes in PDF files (Monitor text changed in the PDF, Also monitor PDF filesize and checksums)
 - Easily specify how often a site should be checked
@@ -82,8 +87,18 @@ _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. 
+
 Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
 
+### We have a Chrome extension!
+
+Easily add the current web page to your changedetection.io tool, simply install the extension and click "Sync" to connect it to your existing changedetection.io install.
+
+[<img src="./docs/chrome-extension-screenshot.png" style="max-width:80%;" alt="Chrome Extension to easily add the current web-page to detect a change."  title="Chrome Extension to easily add the current web-page to detect a change."  />](https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop)
+
+[Goto the Chrome Webstore to download the extension.](https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop)
+
 ## Installation
 
 ### Docker
@@ -91,7 +106,7 @@ Please :star: star :star: this project and help it grow! https://github.com/dgtl
 With Docker composer, just clone this repository and..
 
 ```bash
-$ docker-compose up -d
+$ docker compose up -d
 ```
 
 Docker standalone
@@ -101,6 +116,8 @@ $ docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/d
 
 `:latest` tag is our latest stable release, `:dev` tag is our bleeding edge `master` branch.
 
+Alternative docker repository over at ghcr - [ghcr.io/dgtlmoon/changedetection.io](https://ghcr.io/dgtlmoon/changedetection.io)
+
 ### Windows
 
 See the install instructions at the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Microsoft-Windows
@@ -128,10 +145,10 @@ docker rm $(docker ps -a -f name=changedetection.io -q)
 docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/datastore --name changedetection.io dgtlmoon/changedetection.io
 ```
 
-### docker-compose
+### docker compose
 
 ```bash
-docker-compose pull && docker-compose up -d
+docker compose pull && docker compose up -d
 ```
 
 See the wiki for more information https://github.com/dgtlmoon/changedetection.io/wiki
@@ -139,8 +156,8 @@ See the wiki for more information https://github.com/dgtlmoon/changedetection.io
 
 ## Filters
 
-XPath, JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools. 
-(We support LXML `re:test`, `re:math` and `re:replace`.)
+XPath(1.0), JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools. 
+(We support LXML `re:test`, `re:match` and `re:replace`.)
 
 ## Notifications
 
@@ -178,7 +195,7 @@ This will re-parse the JSON and apply formatting to the text, making it super ea
 
 ### JSONPath or jq?
 
-For more complex parsing, filtering, and modifying of JSON data, jq is recommended due to the built-in operators and functions. Refer to the [documentation](https://stedolan.github.io/jq/manual/) for more specifc information on jq.
+For more complex parsing, filtering, and modifying of JSON data, jq is recommended due to the built-in operators and functions. Refer to the [documentation](https://stedolan.github.io/jq/manual/) for more specific information on jq.
 
 One big advantage of `jq` is that you can use logic in your JSON filter, such as filters to only show items that have a value greater than/less than etc.
 
@@ -218,12 +235,19 @@ The application also supports notifying you that it can follow this information
 
 ## Proxy Configuration
 
-See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [BrightData proxy services where possible]( https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support)
+See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [Bright Data proxy services where possible](https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support) and [Oxylabs](https://oxylabs.go2cloud.org/SH2d) proxy services.
 
 ## Raspberry Pi support?
 
 Raspberry Pi and linux/arm/v6 linux/arm/v7 arm64 devices are supported! See the wiki for [details](https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver)
 
+## Import support
+
+Easily [import your list of websites to watch for changes in Excel .xslx file format](https://changedetection.io/tutorial/how-import-your-website-change-detection-lists-excel), or paste in lists of website URLs as plaintext. 
+
+Excel import is recommended - that way you can better organise tags/groups of websites and other features.
+
+
 ## API Support
 
 Supports managing the website watch list [via our API](https://changedetection.io/docs/api_v1/index.html)
@@ -233,13 +257,7 @@ Supports managing the website watch list [via our API](https://changedetection.i
 Do you use changedetection.io to make money? does it save you time or money? Does it make your life easier? less stressful? Remember, we write this software when we should be doing actual paid work, we have to buy food and pay rent just like you.
 
 
-Firstly, consider taking out a [change detection monthly subscription - unlimited checks and watches](https://lemonade.changedetection.io/start) , even if you don't use it, you still get the warm fuzzy feeling of helping out the project. (And who knows, you might just use it!)
-
-Or directly donate an amount PayPal [![Donate](https://img.shields.io/badge/Donate-PayPal-green.svg)](https://www.paypal.com/donate/?hosted_button_id=7CP6HR9ZCNDYJ)
-
-Or BTC `1PLFN327GyUarpJd7nVe7Reqg9qHx5frNn`
-
-<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/btc-support.png" style="max-width:50%;" alt="Support us!"  />
+Consider taking out an officially supported [website change detection subscription](https://changedetection.io?src=github) , even if you don't use it, you still get the warm fuzzy feeling of helping out the project. (And who knows, you might just use it!)
 
 ## Commercial Support
 
@@ -253,3 +271,13 @@ I offer commercial support, this software is depended on by network security, ae
 [license-shield]: https://img.shields.io/github/license/dgtlmoon/changedetection.io.svg?style=for-the-badge
 [release-link]: https://github.com/dgtlmoon/changedetection.io/releases
 [docker-link]: https://hub.docker.com/r/dgtlmoon/changedetection.io
+
+## Third-party licenses
+
+changedetectionio.html_tools.elementpath_tostring: Copyright (c), 2018-2021, SISSA (Scuola Internazionale Superiore di Studi Avanzati), Licensed under [MIT license](https://github.com/sissaschool/elementpath/blob/master/LICENSE)
+
+## Contributors
+
+Recognition of fantastic contributors to the project
+
+- Constantin Hong https://github.com/Constantin1489

app.json

@@ -1,21 +0,0 @@
-{
-  "name": "ChangeDetection.io",
-  "description": "The best and simplest self-hosted open source website change detection monitoring and notification service.",
-  "keywords": [
-    "changedetection",
-    "website monitoring"
-  ],
-  "repository": "https://github.com/dgtlmoon/changedetection.io",
-  "success_url": "/",
-  "scripts": {
-  },
-  "env": {
-  },
-  "formation": {
-    "web": {
-      "quantity": 1,
-      "size": "free"
-    }
-  },
-  "image": "heroku/python"
-}

changedetection.py

@@ -1,44 +1,6 @@
 #!/usr/bin/python3
 
-# Entry-point for running from the CLI when not installed via Pip, Pip will handle the console_scripts entry_points's from setup.py
-# It's recommended to use `pip3 install changedetection.io` and start with `changedetection.py` instead, it will be linkd to your global path.
-# or Docker.
-# Read more https://github.com/dgtlmoon/changedetection.io/wiki
+# Only exists for direct CLI usage
 
-from changedetectionio import changedetection
-import multiprocessing
-import sys
-import os
-
-def sigchld_handler(_signo, _stack_frame):
-    import sys
-    print('Shutdown: Got SIGCHLD')
-    # https://stackoverflow.com/questions/40453496/python-multiprocessing-capturing-signals-to-restart-child-processes-or-shut-do
-    pid, status = os.waitpid(-1, os.WNOHANG | os.WUNTRACED | os.WCONTINUED)
-
-    print('Sub-process: pid %d status %d' % (pid, status))
-    if status != 0:
-        sys.exit(1)
-
-    raise SystemExit
-
-if __name__ == '__main__':
-
-    #signal.signal(signal.SIGCHLD, sigchld_handler)
-
-    # The only way I could find to get Flask to shutdown, is to wrap it and then rely on the subsystem issuing SIGTERM/SIGKILL
-    parse_process = multiprocessing.Process(target=changedetection.main)
-    parse_process.daemon = True
-    parse_process.start()
-    import time
-
-    try:
-        while True:
-            time.sleep(1)
-            if not parse_process.is_alive():
-                # Process died/crashed for some reason, exit with error set
-                sys.exit(1)
-
-    except KeyboardInterrupt:
-        #parse_process.terminate() not needed, because this process will issue it to the sub-process anyway
-        print ("Exited - CTRL+C")
+import changedetectionio
+changedetectionio.main()

changedetectionio/api/api_v1.py

@@ -1,3 +1,6 @@
+import os
+from changedetectionio.strtobool import strtobool
+
 from flask_expects_json import expects_json
 from changedetectionio import queuedWatchMetaData
 from flask_restful import abort, Resource
@@ -27,18 +30,18 @@ class Watch(Resource):
         self.update_q = kwargs['update_q']
 
     # Get information about a single watch, excluding the history list (can be large)
-    # curl http://localhost:4000/api/v1/watch/<string:uuid>
+    # curl http://localhost:5000/api/v1/watch/<string:uuid>
     # @todo - version2 - ?muted and ?paused should be able to be called together, return the watch struct not "OK"
     # ?recheck=true
     @auth.check_token
     def get(self, uuid):
         """
-        @api {get} /api/v1/watch/:uuid Get a single watch data
+        @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:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?muted=unmuted"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?paused=unpaused"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            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.
@@ -73,7 +76,7 @@ class Watch(Resource):
         # Properties are not returned as a JSON, so add the required props manually
         watch['history_n'] = watch.history_n
         watch['last_changed'] = watch.last_changed
-
+        watch['viewed'] = watch.viewed
         return watch
 
     @auth.check_token
@@ -81,7 +84,7 @@ class Watch(Resource):
         """
         @api {delete} /api/v1/watch/:uuid Delete a watch and related history
         @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            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
@@ -100,7 +103,7 @@ class Watch(Resource):
         @api {put} /api/v1/watch/:uuid Update watch information
         @apiExample {curl} Example usage:
             Update (PUT)
-            curl http://localhost:4000/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"}'
+            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.
@@ -129,13 +132,14 @@ class WatchHistory(Resource):
         self.datastore = kwargs['datastore']
 
     # Get a list of available history for a watch by UUID
-    # curl http://localhost:4000/api/v1/watch/<string:uuid>/history
+    # curl http://localhost:5000/api/v1/watch/<string:uuid>/history
+    @auth.check_token
     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:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
+            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",
@@ -163,7 +167,7 @@ class WatchSingleHistory(Resource):
         @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:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history/1677092977 -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
+            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
         @apiSuccess (200) {String} OK
@@ -179,9 +183,7 @@ class WatchSingleHistory(Resource):
         if timestamp == 'latest':
             timestamp = list(watch.history.keys())[-1]
 
-        # @todo - Check for UTF-8 compatability
-        with open(watch.history[timestamp], 'r') as f:
-            content = f.read()
+        content = watch.get_history_snapshot(timestamp)
 
         response = make_response(content, 200)
         response.mimetype = "text/plain"
@@ -201,7 +203,7 @@ class CreateWatch(Resource):
         @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:4000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "nice list"}'
+            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
@@ -211,7 +213,9 @@ class CreateWatch(Resource):
         json_data = request.get_json()
         url = json_data['url'].strip()
 
-        if not validators.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):
             return "Invalid or unsupported URL", 400
 
         if json_data.get('proxy'):
@@ -220,9 +224,16 @@ class CreateWatch(Resource):
                 return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
 
         extras = copy.deepcopy(json_data)
+
+        # 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'):
+            tags = extras.get('tag')
+            del extras['tag']
+
         del extras['url']
 
-        new_uuid = self.datastore.add_watch(url=url, extras=extras)
+        new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags)
         if new_uuid:
             self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
             return {'uuid': new_uuid}, 201
@@ -235,7 +246,7 @@ class CreateWatch(Resource):
         @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:4000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            curl http://localhost:5000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45"
             {
                 "6a4b7d5c-fee4-4616-9f43-4ac97046b595": {
                     "last_changed": 1677103794,
@@ -261,17 +272,23 @@ class CreateWatch(Resource):
         """
         list = {}
 
-        tag_limit = request.args.get('tag', None)
-        for k, watch in self.datastore.data['watching'].items():
-            if tag_limit:
-                if not tag_limit.lower() in watch.all_tags:
-                    continue
+        tag_limit = request.args.get('tag', '').lower()
 
-            list[k] = {'url': watch['url'],
-                       'title': watch['title'],
-                       'last_checked': watch['last_checked'],
-                       'last_changed': watch.last_changed,
-                       'last_error': watch['last_error']}
+
+        for uuid, watch in self.datastore.data['watching'].items():
+            # Watch tags by name (replace the other calls?)
+            tags = self.datastore.get_all_tags_for_watch(uuid=uuid)
+            if tag_limit and not any(v.get('title').lower() == tag_limit for k, v in tags.items()):
+                continue
+
+            list[uuid] = {
+                'last_changed': watch.last_changed,
+                'last_checked': watch['last_checked'],
+                'last_error': watch['last_error'],
+                'title': watch['title'],
+                'url': watch['url'],
+                'viewed': watch.viewed
+            }
 
         if request.args.get('recheck_all'):
             for uuid in self.datastore.data['watching'].keys():
@@ -280,6 +297,61 @@ class CreateWatch(Resource):
 
         return list, 200
 
+class Import(Resource):
+    def __init__(self, **kwargs):
+        # datastore is a black box dependency
+        self.datastore = kwargs['datastore']
+
+    @auth.check_token
+    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
+        """
+
+        extras = {}
+
+        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
+            else:
+                extras['proxy'] = request.args.get('proxy')
+
+        dedupe = strtobool(request.args.get('dedupe', 'true'))
+
+        tags = request.args.get('tag')
+        tag_uuids = request.args.get('tag_uuids')
+
+        if tag_uuids:
+            tag_uuids = tag_uuids.split(',')
+
+        urls = request.get_data().decode('utf8').splitlines()
+        added = []
+        allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
+        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):
+                return f"Invalid or unsupported URL - {url}", 400
+
+            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)
+
+        return added
+
 class SystemInfo(Resource):
     def __init__(self, **kwargs):
         # datastore is a black box dependency
@@ -292,7 +364,7 @@ class SystemInfo(Resource):
         @api {get} /api/v1/systeminfo Return system info
         @apiDescription Return some info about the current system state
         @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/systeminfo -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            curl http://localhost:5000/api/v1/systeminfo -H"x-api-key:813031b16330fe25e3780cf0325daa45"
             HTTP/1.0 200
             {
                 'queue_size': 10 ,

changedetectionio/blueprint/browser_steps/TODO.txt

@@ -0,0 +1,7 @@
+- This needs an abstraction to directly handle the puppeteer connection methods
+- Then remove the playwright stuff
+- Remove hack redirect at line 65 changedetectionio/processors/__init__.py
+
+The screenshots are base64 encoded/decoded which is very CPU intensive for large screenshots (in playwright) but not
+in the direct puppeteer connection (they are binary end to end)
+

changedetectionio/blueprint/browser_steps/__init__.py

@@ -4,81 +4,150 @@
 # Why?
 # `browsersteps_playwright_browser_interface.chromium.connect_over_cdp()` will only run once without async()
 # - this flask app is not async()
-# - browserless has a single timeout/keepalive which applies to the session made at .connect_over_cdp()
+# - A single timeout/keepalive which applies to the session made at .connect_over_cdp()
 #
 # So it means that we must unfortunately for now just keep a single timer since .connect_over_cdp() was run
 # and know when that reaches timeout/keepalive :( when that time is up, restart the connection and tell the user
 # that their time is up, insert another coin. (reload)
 #
-# Bigger picture
-# - It's horrible that we have this click+wait deal, some nice socket.io solution using something similar
-# to what the browserless debug UI already gives us would be smarter..
 #
-# OR
-# - Some API call that should be hacked into browserless or playwright that we can "/api/bump-keepalive/{session_id}/60"
-# So we can tell it that we need more time (run this on each action)
-#
-# OR
-# - use multiprocessing to bump this over to its own process and add some transport layer (queue/pipes)
 
-from distutils.util import strtobool
+from changedetectionio.strtobool import strtobool
 from flask import Blueprint, request, make_response
 import os
-import logging
+
 from changedetectionio.store import ChangeDetectionStore
-from changedetectionio import login_optionally_required
-browsersteps_live_ui_o = {}
-browsersteps_playwright_browser_interface = None
-browsersteps_playwright_browser_interface_browser = None
-browsersteps_playwright_browser_interface_context = None
-browsersteps_playwright_browser_interface_end_time = None
-browsersteps_playwright_browser_interface_start_time = None
+from changedetectionio.flask_app import login_optionally_required
+from loguru import logger
 
-def cleanup_playwright_session():
+browsersteps_sessions = {}
+io_interface_context = None
 
-    global browsersteps_live_ui_o
-    global browsersteps_playwright_browser_interface
-    global browsersteps_playwright_browser_interface_browser
-    global browsersteps_playwright_browser_interface_context
-    global browsersteps_playwright_browser_interface_end_time
-    global browsersteps_playwright_browser_interface_start_time
-
-    browsersteps_live_ui_o = {}
-    browsersteps_playwright_browser_interface = None
-    browsersteps_playwright_browser_interface_browser = None
-    browsersteps_playwright_browser_interface_end_time = None
-    browsersteps_playwright_browser_interface_start_time = None
-
-    print("Cleaning up old playwright session because time was up, calling .goodbye()")
-    try:
-        browsersteps_playwright_browser_interface_context.goodbye()
-    except Exception as e:
-        print ("Got exception in shutdown, probably OK")
-        print (str(e))
-
-    browsersteps_playwright_browser_interface_context = None
-
-    print ("Cleaning up old playwright session because time was up - done")
 
 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
+        import time
+        global browsersteps_sessions
+        global io_interface_context
+
+
+        # 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()
+
+        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}"
+
+        try:
+            browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(base_url)
+        except Exception as e:
+            if 'ECONNREFUSED' in str(e):
+                return make_response('Unable to start the Playwright Browser session, is it running?', 401)
+            else:
+                # Other errors, bad URL syntax, bad reply etc
+                return make_response(str(e), 401)
+
+        proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
+        proxy = None
+        if proxy_id:
+            proxy_url = datastore.proxy_list.get(proxy_id).get('url')
+            if proxy_url:
+
+                # Playwright needs separate username and password values
+                from urllib.parse import urlparse
+                parsed = urlparse(proxy_url)
+                proxy = {'server': proxy_url}
+
+                if parsed.username:
+                    proxy['username'] = parsed.username
+
+                if parsed.password:
+                    proxy['password'] = parsed.password
+
+                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'],
+            proxy=proxy,
+            start_url=datastore.data['watching'][watch_uuid].get('url')
+        )
+
+        # For test
+        #browsersteps_start_session['browserstepper'].action_goto_url(value="http://example.com?time="+str(time.time()))
+
+        return browsersteps_start_session
+
+
     @login_optionally_required
-    @browser_steps_blueprint.route("/browsersteps_update", methods=['GET', 'POST'])
+    @browser_steps_blueprint.route("/browsersteps_start_session", methods=['GET'])
+    def browsersteps_start_session():
+        # A new session was requested, return sessionID
+
+        import uuid
+        global browsersteps_sessions
+
+        browsersteps_session_id = str(uuid.uuid4())
+        watch_uuid = request.args.get('uuid')
+
+        if not watch_uuid:
+            return make_response('No Watch UUID specified', 500)
+
+        logger.debug("Starting connection with playwright")
+        logger.debug("browser_steps.py connecting")
+        browsersteps_sessions[browsersteps_session_id] = start_browsersteps_session(watch_uuid)
+        logger.debug("Starting connection with playwright - done")
+        return {'browsersteps_session_id': browsersteps_session_id}
+
+    @login_optionally_required
+    @browser_steps_blueprint.route("/browsersteps_image", methods=['GET'])
+    def browser_steps_fetch_screenshot_image():
+        from flask import (
+            make_response,
+            request,
+            send_from_directory,
+        )
+        uuid = request.args.get('uuid')
+        step_n = int(request.args.get('step_n'))
+
+        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))
+            response.headers['Content-type'] = 'image/jpeg'
+            response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+            response.headers['Pragma'] = 'no-cache'
+            response.headers['Expires'] = 0
+            return response
+
+        else:
+            return make_response('Unable to fetch image, is the URL correct? does the watch exist? does the step_type-n.jpeg exist?', 401)
+
+    # A request for an action was received
+    @login_optionally_required
+    @browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
     def browsersteps_ui_update():
         import base64
-        import playwright._impl._api_types
-        import time
-
+        import playwright._impl._errors
+        global browsersteps_sessions
         from changedetectionio.blueprint.browser_steps import browser_steps
 
-        global browsersteps_live_ui_o, browsersteps_playwright_browser_interface_end_time
-        global browsersteps_playwright_browser_interface_browser
-        global browsersteps_playwright_browser_interface
-        global browsersteps_playwright_browser_interface_start_time
-
-        step_n = None
         remaining =0
         uuid = request.args.get('uuid')
 
@@ -87,13 +156,9 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         if not browsersteps_session_id:
             return make_response('No browsersteps_session_id specified', 500)
 
-        # Because we don't "really" run in a context manager ( we make the playwright interface global/long-living )
-        # We need to manage the shutdown when the time is up
-        if browsersteps_playwright_browser_interface_end_time:
-            remaining = browsersteps_playwright_browser_interface_end_time-time.time()
-            if browsersteps_playwright_browser_interface_end_time and remaining <= 0:
-                cleanup_playwright_session()
-                return make_response('Browser session expired, please reload the Browser Steps interface', 401)
+        if not browsersteps_sessions.get(browsersteps_session_id):
+            return make_response('No session exists under that ID', 500)
+
 
         # Actions - step/apply/etc, do the thing and return state
         if request.method == 'POST':
@@ -104,124 +169,58 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             step_n = int(request.form.get('step_n'))
             is_last_step = strtobool(request.form.get('is_last_step'))
 
-            if step_operation == 'Goto site':
-                step_operation = 'goto_url'
-                step_optional_value = None
-                step_selector = datastore.data['watching'][uuid].get('url')
-
             # @todo try.. accept.. nice errors not popups..
             try:
 
-                this_session = browsersteps_live_ui_o.get(browsersteps_session_id)
-                if not this_session:
-                    print("Browser exited")
-                    return make_response('Browser session ran out of time :( Please reload this page.', 401)
-
-                this_session.call_action(action_name=step_operation,
+                browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(action_name=step_operation,
                                          selector=step_selector,
                                          optional_value=step_optional_value)
 
             except Exception as e:
-                print("Exception when calling step operation", step_operation, str(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)
 
             # Get visual selector ready/update its data (also use the current filter info from the page?)
             # When the last 'apply' button was pressed
             # @todo this adds overhead because the xpath selection is happening twice
-            u = this_session.page.url
+            u = browsersteps_sessions[browsersteps_session_id]['browserstepper'].page.url
             if is_last_step and u:
-                (screenshot, xpath_data) = this_session.request_visualselector_data()
+                (screenshot, xpath_data) = browsersteps_sessions[browsersteps_session_id]['browserstepper'].request_visualselector_data()
                 datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
                 datastore.save_xpath_data(watch_uuid=uuid, data=xpath_data)
 
-        # Setup interface
-        if request.method == 'GET':
+#        if not this_session.page:
+#            cleanup_playwright_session()
+#            return make_response('Browser session ran out of time :( Please reload this page.', 401)
 
-            if not browsersteps_playwright_browser_interface:
-                print("Starting connection with playwright")
-                logging.debug("browser_steps.py connecting")
+        # Screenshots and other info only needed on requesting a step (POST)
+        try:
+            state = browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
+        except playwright._impl._api_types.Error as e:
+            return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
 
-                global browsersteps_playwright_browser_interface_context
-                from . import nonContext
-                browsersteps_playwright_browser_interface_context = nonContext.c_sync_playwright()
-                browsersteps_playwright_browser_interface = browsersteps_playwright_browser_interface_context.start()
+        # Use send_file() which is way faster than read/write loop on bytes
+        import json
+        from tempfile import mkstemp
+        from flask import send_file
+        tmp_fd, tmp_file = mkstemp(text=True, suffix=".json", prefix="changedetectionio-")
 
-                time.sleep(1)
-                # At 20 minutes, some other variable is closing it
-                # @todo find out what it is and set it
-                seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
+        output = json.dumps({'screenshot': "data:image/jpeg;base64,{}".format(
+            base64.b64encode(state[0]).decode('ascii')),
+            'xpath_data': state[1],
+            'session_age_start': browsersteps_sessions[browsersteps_session_id]['browserstepper'].age_start,
+            'browser_time_remaining': round(remaining)
+        })
 
-                # keep it alive for 10 seconds more than we advertise, sometimes it helps to keep it shutting down cleanly
-                keepalive = "&timeout={}".format(((seconds_keepalive+3) * 1000))
-                try:
-                    browsersteps_playwright_browser_interface_browser = browsersteps_playwright_browser_interface.chromium.connect_over_cdp(
-                        os.getenv('PLAYWRIGHT_DRIVER_URL', '') + keepalive)
-                except Exception as e:
-                    if 'ECONNREFUSED' in str(e):
-                        return make_response('Unable to start the Playwright session properly, is it running?', 401)
+        with os.fdopen(tmp_fd, 'w') as f:
+            f.write(output)
 
-                browsersteps_playwright_browser_interface_end_time = time.time() + (seconds_keepalive-3)
-                print("Starting connection with playwright - done")
-
-            if not browsersteps_live_ui_o.get(browsersteps_session_id):
-                # Boot up a new session
-                proxy_id = datastore.get_preferred_proxy_for_watch(uuid=uuid)
-                proxy = None
-                if proxy_id:
-                    proxy_url = datastore.proxy_list.get(proxy_id).get('url')
-                    if proxy_url:
-                        proxy = {'server': proxy_url}
-                        print("Browser Steps: UUID {} Using proxy {}".format(uuid, proxy_url))
-
-                # Begin the new "Playwright Context" that re-uses the playwright interface
-                # Each session is a "Playwright Context" as a list, that uses the playwright interface
-                browsersteps_live_ui_o[browsersteps_session_id] = browser_steps.browsersteps_live_ui(
-                    playwright_browser=browsersteps_playwright_browser_interface_browser,
-                    proxy=proxy)
-                this_session = browsersteps_live_ui_o[browsersteps_session_id]
-
-        if not this_session.page:
-            cleanup_playwright_session()
-            return make_response('Browser session ran out of time :( Please reload this page.', 401)
-
-        response = None
-
-        if request.method == 'POST':
-            # Screenshots and other info only needed on requesting a step (POST)
-            try:
-                state = this_session.get_current_state()
-            except playwright._impl._api_types.Error as e:
-                return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
-
-            # Use send_file() which is way faster than read/write loop on bytes
-            import json
-            from tempfile import mkstemp
-            from flask import send_file
-            tmp_fd, tmp_file = mkstemp(text=True, suffix=".json", prefix="changedetectionio-")
-
-            output = json.dumps({'screenshot': "data:image/jpeg;base64,{}".format(
-                base64.b64encode(state[0]).decode('ascii')),
-                'xpath_data': state[1],
-                'session_age_start': this_session.age_start,
-                'browser_time_remaining': round(remaining)
-            })
-
-            with os.fdopen(tmp_fd, 'w') as f:
-                f.write(output)
-
-            response = make_response(send_file(path_or_file=tmp_file,
-                                               mimetype='application/json; charset=UTF-8',
-                                               etag=True))
-            # No longer needed
-            os.unlink(tmp_file)
-
-        elif request.method == 'GET':
-            # Just enough to get the session rolling, it will call for goto-site via POST next
-            response = make_response({
-                'session_age_start': this_session.age_start,
-                'browser_time_remaining': round(remaining)
-            })
+        response = make_response(send_file(path_or_file=tmp_file,
+                                           mimetype='application/json; charset=UTF-8',
+                                           etag=True))
+        # No longer needed
+        os.unlink(tmp_file)
 
         return response
 

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -4,6 +4,10 @@ import os
 import time
 import re
 from random import randint
+from loguru import logger
+
+from changedetectionio.content_fetchers.base import manage_user_agent
+from changedetectionio.safe_jinja import render as jinja_render
 
 # Two flags, tell the JS which of the "Selector" or "Value" field should be enabled in the front end
 # 0- off, 1- on
@@ -25,6 +29,7 @@ browser_step_ui_config = {'Choose one': '0 0',
                           'Execute JS': '0 1',
 #                          'Extract text and use as filter': '1 0',
                           'Goto site': '0 0',
+                          'Goto URL': '0 1',
                           'Press Enter': '0 0',
                           'Select by label': '1 1',
                           'Scroll down': '0 0',
@@ -44,6 +49,10 @@ browser_step_ui_config = {'Choose one': '0 0',
 # ONLY Works in Playwright because we need the fullscreen screenshot
 class steppable_browser_interface():
     page = None
+    start_url = None
+
+    def __init__(self, start_url):
+        self.start_url = start_url
 
     # Convert and perform "Click Button" for example
     def call_action(self, action_name, selector=None, optional_value=None):
@@ -52,37 +61,39 @@ class steppable_browser_interface():
         if call_action_name == 'choose_one':
             return
 
-        print("> action calling", call_action_name)
+        logger.debug(f"> Action calling '{call_action_name}'")
         # https://playwright.dev/python/docs/selectors#xpath-selectors
-        if selector.startswith('/') and not selector.startswith('//'):
+        if selector and selector.startswith('/') and not selector.startswith('//'):
             selector = "xpath=" + selector
 
         action_handler = getattr(self, "action_" + call_action_name)
 
         # Support for Jinja2 variables in the value and selector
-        from jinja2 import Environment
-        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
 
         if selector and ('{%' in selector or '{{' in selector):
-            selector = str(jinja2_env.from_string(selector).render())
+            selector = jinja_render(template_str=selector)
 
         if optional_value and ('{%' in optional_value or '{{' in optional_value):
-            optional_value = str(jinja2_env.from_string(optional_value).render())
+            optional_value = jinja_render(template_str=optional_value)
 
         action_handler(selector, optional_value)
-        self.page.wait_for_timeout(3 * 1000)
-        print("Call action done in", time.time() - now)
+        self.page.wait_for_timeout(1.5 * 1000)
+        logger.debug(f"Call action done in {time.time()-now:.2f}s")
 
-    def action_goto_url(self, url, optional_value):
+    def action_goto_url(self, selector=None, value=None):
         # self.page.set_viewport_size({"width": 1280, "height": 5000})
         now = time.time()
-        response = self.page.goto(url, timeout=0, wait_until='commit')
+        response = self.page.goto(value, timeout=0, wait_until='load')
+        # Should be the same as the puppeteer_fetch.js methods, means, load with no timeout set (skip timeout)
+        #and also wait for seconds ?
+        #await page.waitForTimeout(1000);
+        #await page.waitForTimeout(extra_wait_ms);
+        logger.debug(f"Time to goto URL {time.time()-now:.2f}s")
+        return response
 
-        # Wait_until = commit
-        # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
-        # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
-        # This seemed to solve nearly all 'TimeoutErrors'
-        print("Time to goto URL ", time.time() - now)
+    # 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)
 
     def action_click_element_containing_text(self, selector=None, value=''):
         if not len(value.strip()):
@@ -98,17 +109,19 @@ class steppable_browser_interface():
         self.page.fill(selector, value, timeout=10 * 1000)
 
     def action_execute_js(self, selector, value):
-        self.page.evaluate(value)
+        response = self.page.evaluate(value)
+        return response
 
     def action_click_element(self, selector, value):
-        print("Clicking element")
+        logger.debug("Clicking element")
         if not len(selector.strip()):
             return
-        self.page.click(selector, timeout=10 * 1000, delay=randint(200, 500))
+
+        self.page.click(selector=selector, timeout=30 * 1000, delay=randint(200, 500))
 
     def action_click_element_if_exists(self, selector, value):
-        import playwright._impl._api_types as _api_types
-        print("Clicking element if exists")
+        import playwright._impl._errors as _api_types
+        logger.debug("Clicking element if exists")
         if not len(selector.strip()):
             return
         try:
@@ -120,6 +133,9 @@ class steppable_browser_interface():
             return
 
     def action_click_x_y(self, selector, value):
+        if not re.match(r'^\s?\d+\s?,\s?\d+\s?$', value):
+            raise Exception("'Click X,Y' step should be in the format of '100 , 90'")
+
         x, y = value.strip().split(',')
         x = int(float(x.strip()))
         y = int(float(y.strip()))
@@ -131,7 +147,7 @@ class steppable_browser_interface():
         self.page.wait_for_timeout(1000)
 
     def action_wait_for_seconds(self, selector, value):
-        self.page.wait_for_timeout(int(value) * 1000)
+        self.page.wait_for_timeout(float(value.strip()) * 1000)
 
     def action_wait_for_text(self, selector, value):
         import json
@@ -162,7 +178,7 @@ class steppable_browser_interface():
         self.page.locator(selector, timeout=1000).uncheck(timeout=1000)
 
 
-# Responsible for maintaining a live 'context' with browserless
+# Responsible for maintaining a live 'context' with the chrome CDP
 # @todo - how long do contexts live for anyway?
 class browsersteps_live_ui(steppable_browser_interface):
     context = None
@@ -171,6 +187,7 @@ class browsersteps_live_ui(steppable_browser_interface):
     stale = False
     # bump and kill this if idle after X sec
     age_start = 0
+    headers = {}
 
     # use a special driver, maybe locally etc
     command_executor = os.getenv(
@@ -185,9 +202,11 @@ class browsersteps_live_ui(steppable_browser_interface):
 
     browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
 
-    def __init__(self, playwright_browser, proxy=None):
+    def __init__(self, playwright_browser, proxy=None, headers=None, start_url=None):
+        self.headers = headers or {}
         self.age_start = time.time()
         self.playwright_browser = playwright_browser
+        self.start_url = start_url
         if self.context is None:
             self.connect(proxy=proxy)
 
@@ -199,16 +218,17 @@ class browsersteps_live_ui(steppable_browser_interface):
 
         # @todo handle multiple contexts, bind a unique id from the browser on each req?
         self.context = self.playwright_browser.new_context(
-            # @todo
-            #                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
-            #               proxy=self.proxy,
-            # This is needed to enable JavaScript execution on GitHub and others
-            bypass_csp=True,
-            # Should never be needed
-            accept_downloads=False,
-            proxy=proxy
+            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,
+            ignore_https_errors=True,
+            proxy=proxy,
+            service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
+            # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
+            user_agent=manage_user_agent(headers=self.headers),
         )
 
+
         self.page = self.context.new_page()
 
         # self.page.set_default_navigation_timeout(keep_open)
@@ -221,11 +241,11 @@ class browsersteps_live_ui(steppable_browser_interface):
         # Listen for all console events and handle errors
         self.page.on("console", lambda msg: print(f"Browser steps console - {msg.type}: {msg.text} {msg.args}"))
 
-        print("Time to browser setup", time.time() - now)
+        logger.debug(f"Time to browser setup {time.time()-now:.2f}s")
         self.page.wait_for_timeout(1 * 1000)
 
     def mark_as_closed(self):
-        print("Page closed, cleaning up..")
+        logger.debug("Page closed, cleaning up..")
 
     @property
     def has_expired(self):
@@ -236,7 +256,7 @@ class browsersteps_live_ui(steppable_browser_interface):
     def get_current_state(self):
         """Return the screenshot and interactive elements mapping, generally always called after action_()"""
         from pkg_resources import resource_string
-        xpath_element_js = resource_string(__name__, "../../res/xpath_element_scraper.js").decode('utf-8')
+        xpath_element_js = resource_string(__name__, "../../content_fetchers/res/xpath_element_scraper.js").decode('utf-8')
         now = time.time()
         self.page.wait_for_timeout(1 * 1000)
 
@@ -251,7 +271,7 @@ class browsersteps_live_ui(steppable_browser_interface):
         xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")
         # So the JS will find the smallest one first
         xpath_data['size_pos'] = sorted(xpath_data['size_pos'], key=lambda k: k['width'] * k['height'], reverse=True)
-        print("Time to complete get_current_state of browser", time.time() - now)
+        logger.debug(f"Time to complete get_current_state of browser {time.time()-now:.2f}s")
         # except
         # playwright._impl._api_types.Error: Browser closed.
         # @todo show some countdown timer?
@@ -271,10 +291,10 @@ class browsersteps_live_ui(steppable_browser_interface):
         self.page.evaluate("var include_filters=''")
         from pkg_resources import resource_string
         # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
-        xpath_element_js = resource_string(__name__, "../../res/xpath_element_scraper.js").decode('utf-8')
-        from changedetectionio.content_fetcher import visualselector_xpath_selectors
+        xpath_element_js = resource_string(__name__, "../../content_fetchers/res/xpath_element_scraper.js").decode('utf-8')
+        from changedetectionio.content_fetchers import visualselector_xpath_selectors
         xpath_element_js = xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
         xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")
-        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
 
         return (screenshot, xpath_data)

changedetectionio/blueprint/browser_steps/nonContext.py

@@ -1,5 +1,4 @@
 from playwright.sync_api import PlaywrightContextManager
-import asyncio
 
 # 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

changedetectionio/blueprint/check_proxies/__init__.py

@@ -0,0 +1,118 @@
+from concurrent.futures import ThreadPoolExecutor
+from changedetectionio.store import ChangeDetectionStore
+
+from functools import wraps
+
+from flask import Blueprint
+from flask_login import login_required
+
+STATUS_CHECKING = 0
+STATUS_FAILED = 1
+STATUS_OK = 2
+THREADPOOL_MAX_WORKERS = 3
+_DEFAULT_POOL = ThreadPoolExecutor(max_workers=THREADPOOL_MAX_WORKERS)
+
+
+# Maybe use fetch-time if its >5 to show some expected load time?
+def threadpool(f, executor=None):
+    @wraps(f)
+    def wrap(*args, **kwargs):
+        return (executor or _DEFAULT_POOL).submit(f, *args, **kwargs)
+
+    return wrap
+
+
+def construct_blueprint(datastore: ChangeDetectionStore):
+    check_proxies_blueprint = Blueprint('check_proxies', __name__)
+    checks_in_progress = {}
+
+    @threadpool
+    def long_task(uuid, preferred_proxy):
+        import time
+        from changedetectionio.content_fetchers import exceptions as content_fetcher_exceptions
+        from changedetectionio.processors import text_json_diff
+        from changedetectionio.safe_jinja import render as jinja_render
+
+        status = {'status': '', 'length': 0, 'text': ''}
+
+        contents = ''
+        now = time.time()
+        try:
+            update_handler = text_json_diff.perform_site_check(datastore=datastore, watch_uuid=uuid)
+            update_handler.call_browser()
+        # title, size is len contents not len xfer
+        except content_fetcher_exceptions.Non200ErrorCodeReceived as e:
+            if e.status_code == 404:
+                status.update({'status': 'OK', 'length': len(contents), 'text': f"OK but 404 (page not found)"})
+            elif e.status_code == 403 or e.status_code == 401:
+                status.update({'status': 'ERROR', 'length': len(contents), 'text': f"{e.status_code} - Access denied"})
+            else:
+                status.update({'status': 'ERROR', 'length': len(contents), 'text': f"Status code: {e.status_code}"})
+        except text_json_diff.FilterNotFoundInResponse:
+            status.update({'status': 'OK', 'length': len(contents), 'text': f"OK but CSS/xPath filter not found (page changed layout?)"})
+        except content_fetcher_exceptions.EmptyReply as e:
+            if e.status_code == 403 or e.status_code == 401:
+                status.update({'status': 'ERROR OTHER', 'length': len(contents), 'text': f"Got empty reply with code {e.status_code} - Access denied"})
+            else:
+                status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': f"Empty reply with code {e.status_code}, needs chrome?"})
+        except content_fetcher_exceptions.ReplyWithContentButNoText as e:
+            txt = f"Got reply but with no content - Status code {e.status_code} - It's possible that the filters were found, but contained no usable text (or contained only an image)."
+            status.update({'status': 'ERROR', 'text': txt})
+        except Exception as e:
+            status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': 'Error: '+type(e).__name__+str(e)})
+        else:
+            status.update({'status': 'OK', 'length': len(contents), 'text': ''})
+
+        if status.get('text'):
+            # parse 'text' as text for safety
+            v = {'text': status['text']}
+            status['text'] = jinja_render(template_str='{{text|e}}', **v)
+
+        status['time'] = "{:.2f}s".format(time.time() - now)
+
+        return status
+
+    def _recalc_check_status(uuid):
+
+        results = {}
+        for k, v in checks_in_progress.get(uuid, {}).items():
+            try:
+                r_1 = v.result(timeout=0.05)
+            except Exception as e:
+                # If timeout error?
+                results[k] = {'status': 'RUNNING'}
+
+            else:
+                results[k] = r_1
+
+        return results
+
+    @login_required
+    @check_proxies_blueprint.route("/<string:uuid>/status", methods=['GET'])
+    def get_recheck_status(uuid):
+        results = _recalc_check_status(uuid=uuid)
+        return results
+
+    @login_required
+    @check_proxies_blueprint.route("/<string:uuid>/start", methods=['GET'])
+    def start_check(uuid):
+
+        if not datastore.proxy_list:
+            return
+
+        if checks_in_progress.get(uuid):
+            state = _recalc_check_status(uuid=uuid)
+            for proxy_key, v in state.items():
+                if v.get('status') == 'RUNNING':
+                    return state
+        else:
+            checks_in_progress[uuid] = {}
+
+        for k, v in datastore.proxy_list.items():
+            if not checks_in_progress[uuid].get(k):
+                checks_in_progress[uuid][k] = long_task(uuid=uuid, preferred_proxy=k)
+
+        results = _recalc_check_status(uuid=uuid)
+        return results
+
+    return check_proxies_blueprint

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -1,5 +1,5 @@
 
-from distutils.util import strtobool
+from changedetectionio.strtobool import strtobool
 from flask import Blueprint, flash, redirect, url_for
 from flask_login import login_required
 from changedetectionio.store import ChangeDetectionStore
@@ -18,8 +18,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
     def accept(uuid):
         datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_ACCEPT
         update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
-        return redirect(url_for("form_watch_checknow", uuid=uuid))
-
+        return redirect(url_for("index"))
 
     @login_required
     @price_data_follower_blueprint.route("/<string:uuid>/reject", methods=['GET'])

changedetectionio/blueprint/tags/README.md

@@ -0,0 +1,9 @@
+# Groups tags
+
+## How it works
+
+Watch has a list() of tag UUID's, which relate to a config under application.settings.tags
+
+The 'tag' is actually a watch, because they basically will eventually share 90% of the same config.
+
+So a tag is like an abstract of a watch

changedetectionio/blueprint/tags/__init__.py

@@ -0,0 +1,148 @@
+from flask import Blueprint, request, make_response, render_template, flash, url_for, redirect
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio.flask_app import login_optionally_required
+
+
+def construct_blueprint(datastore: ChangeDetectionStore):
+    tags_blueprint = Blueprint('tags', __name__, template_folder="templates")
+
+    @tags_blueprint.route("/list", methods=['GET'])
+    @login_optionally_required
+    def tags_overview_page():
+        from .form import SingleTag
+        add_form = SingleTag(request.form)
+        sorted_tags = sorted(datastore.data['settings']['application'].get('tags').items(), key=lambda x: x[1]['title'])
+
+        from collections import Counter
+
+        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",
+                                 available_tags=sorted_tags,
+                                 form=add_form,
+                                 tag_count=tag_count
+                                 )
+
+        return output
+
+    @tags_blueprint.route("/add", methods=['POST'])
+    @login_optionally_required
+    def form_tag_add():
+        from .form import SingleTag
+        add_form = SingleTag(request.form)
+
+        if not add_form.validate():
+            for widget, l in add_form.errors.items():
+                flash(','.join(l), 'error')
+            return redirect(url_for('tags.tags_overview_page'))
+
+        title = request.form.get('name').strip()
+
+        if datastore.tag_exists_by_name(title):
+            flash(f'The tag "{title}" already exists', "error")
+            return redirect(url_for('tags.tags_overview_page'))
+
+        datastore.add_tag(title)
+        flash("Tag added")
+
+
+        return redirect(url_for('tags.tags_overview_page'))
+
+    @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']
+        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
+        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)
+
+        flash(f"Tag deleted and removed from {removed} watches")
+        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)
+
+        flash(f"Tag unlinked removed from {unlinked} watches")
+        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'] = []
+        datastore.data['settings']['application']['tags'] = {}
+
+        flash(f"All tags deleted")
+        return redirect(url_for('tags.tags_overview_page'))
+
+    @tags_blueprint.route("/edit/<string:uuid>", methods=['GET'])
+    @login_optionally_required
+    def form_tag_edit(uuid):
+        from changedetectionio import forms
+
+        if uuid == 'first':
+            uuid = list(datastore.data['settings']['application']['tags'].keys()).pop()
+
+        default = datastore.data['settings']['application']['tags'].get(uuid)
+
+        form = forms.watchForm(formdata=request.form if request.method == 'POST' else None,
+                               data=default,
+                               )
+        form.datastore=datastore # needed?
+
+        output = render_template("edit-tag.html",
+                                 data=default,
+                                 form=form,
+                                 settings_application=datastore.data['settings']['application'],
+                                 )
+
+        return output
+
+
+    @tags_blueprint.route("/edit/<string:uuid>", methods=['POST'])
+    @login_optionally_required
+    def form_tag_edit_submit(uuid):
+        from changedetectionio import forms
+        if uuid == 'first':
+            uuid = list(datastore.data['settings']['application']['tags'].keys()).pop()
+
+        default = datastore.data['settings']['application']['tags'].get(uuid)
+
+        form = forms.watchForm(formdata=request.form if request.method == 'POST' else None,
+                               data=default,
+                               )
+        # @todo subclass form so validation works
+        #if not form.validate():
+#            for widget, l in form.errors.items():
+#                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.needs_write_urgent = True
+        flash("Updated")
+
+        return redirect(url_for('tags.tags_overview_page'))
+
+
+    @tags_blueprint.route("/delete/<string:uuid>", methods=['GET'])
+    def form_tag_delete(uuid):
+        return redirect(url_for('tags.tags_overview_page'))
+    return tags_blueprint

changedetectionio/blueprint/tags/form.py

@@ -0,0 +1,22 @@
+from wtforms import (
+    BooleanField,
+    Form,
+    IntegerField,
+    RadioField,
+    SelectField,
+    StringField,
+    SubmitField,
+    TextAreaField,
+    validators,
+)
+
+
+
+class SingleTag(Form):
+
+    name = StringField('Tag name', [validators.InputRequired()], render_kw={"placeholder": "Name"})
+    save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
+
+
+
+

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

@@ -0,0 +1,136 @@
+{% extends 'base.html' %}
+{% block content %}
+{% from '_helpers.html' import render_field, render_checkbox_field, render_button %}
+{% from '_common_fields.html' import render_common_settings_form %}
+<script>
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test', mode="group-settings")}}";
+</script>
+
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script>
+
+/*{% if emailprefix %}*/
+    /*const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');*/
+/*{% endif %}*/
+
+
+</script>
+
+<script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
+<!--<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>-->
+<script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
+
+<div class="edit-form monospaced-textarea">
+
+    <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"><a href="#notifications">Notifications</a></li>
+        </ul>
+    </div>
+
+    <div class="box-wrap inner">
+        <form class="pure-form pure-form-stacked"
+              action="{{ url_for('tags.form_tag_edit', uuid=data.uuid) }}" method="POST">
+             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
+
+            <div class="tab-pane-inner" id="general">
+                <fieldset>
+                    <div class="pure-control-group">
+                        {{ render_field(form.title, placeholder="https://...", required=true, class="m-d") }}
+                    </div>
+                </fieldset>
+            </div>
+
+            <div class="tab-pane-inner" id="filters-and-triggers">
+                    <div class="pure-control-group">
+                        {% set field = render_field(form.include_filters,
+                            rows=5,
+                            placeholder="#example
+xpath://body/div/span[contains(@class, 'example-class')]",
+                            class="m-d")
+                        %}
+                        {{ field }}
+                        {% if '/text()' in  field %}
+                          <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br>
+                        {% endif %}
+                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br>
+
+                    <ul>
+                        <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
+                        <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
+                            <ul>
+                                <li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required,  <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
+                                {% if jq_support %}
+                                <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>.</li>
+                                {% else %}
+                                <li>jq support not installed</li>
+                                {% endif %}
+                            </ul>
+                        </li>
+                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash. To specify XPath to be used explicitly or the XPath rule starts with an XPath function: Prefix with <code>xpath:</code>
+                            <ul>
+                                <li>Example:  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath:count(//*[contains(@class, 'sametext')])</code>, <a
+                                href="http://xpather.com/" target="new">test your XPath here</a></li>
+                                <li>Example: Get all titles from an RSS feed <code>//title/text()</code></li>
+                                <li>To use XPath1.0: Prefix with <code>xpath1:</code></li>
+                            </ul>
+                            </li>
+                    </ul>
+                    Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
+                                href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
+                </span>
+                    </div>
+                <fieldset class="pure-control-group">
+                    {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
+footer
+nav
+.stockticker") }}
+                    <span class="pure-form-message-inline">
+                        <ul>
+                          <li> Remove HTML element(s) by CSS selector before text conversion. </li>
+                          <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
+                        </ul>
+                      </span>
+                </fieldset>
+
+            </div>
+
+            <div class="tab-pane-inner" id="notifications">
+                <fieldset>
+                    <div  class="pure-control-group inline-radio">
+                      {{ render_checkbox_field(form.notification_muted) }}
+                    </div>
+                    {% if is_html_webdriver %}
+                    <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.
+                        </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_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>
+
+                        {{ render_common_settings_form(form, emailprefix, settings_application) }}
+                    </div>
+                </fieldset>
+            </div>
+
+            <div id="actions">
+                <div class="pure-control-group">
+                    {{ render_button(form.save_button) }}
+                </div>
+            </div>
+        </form>
+    </div>
+</div>
+
+{% endblock %}

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

@@ -0,0 +1,62 @@
+{% extends 'base.html' %}
+{% 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>
+
+<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>
+            <div id="watch-add-wrapper-zone">
+                <div>
+                    {{ render_simple_field(form.name, placeholder="watch label / tag") }}
+                </div>
+                <div>
+                    {{ 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>
+        </fieldset>
+    </form>
+    <!-- @todo maybe some overview matrix, 'tick' with which has notification, filter rules etc -->
+    <div id="watch-table-wrapper">
+
+        <table class="pure-table pure-table-striped watch-table group-overview-table">
+            <thead>
+            <tr>
+                <th></th>
+                <th># Watches</th>
+                <th>Tag / Label name</th>
+                <th></th>
+            </tr>
+            </thead>
+            <tbody>
+            <!--
+            @Todo - connect Last checked, Last Changed, Number of Watches etc
+            --->
+            {% if not available_tags|length %}
+            <tr>
+                <td colspan="3">No website organisational tags/groups configured</td>
+            </tr>
+            {% endif %}
+            {% for uuid, tag in available_tags  %}
+            <tr id="{{ uuid }}" class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }}">
+                <td class="watch-controls">
+                    <a class="link-mute state-{{'on' if tag.notification_muted else 'off'}}" href="{{url_for('tags.mute', uuid=tag.uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute" ></a>
+                </td>
+                <td>{{ "{:,}".format(tag_count[uuid]) if uuid in tag_count else 0 }}</td>
+                <td class="title-col inline"> <a href="{{url_for('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>
+                </td>
+            </tr>
+            {% endfor %}
+            </tbody>
+        </table>
+    </div>
+</div>
+{% endblock %}

changedetectionio/changedetection.py

@@ -1,153 +0,0 @@
-#!/usr/bin/python3
-
-# Launch as a eventlet.wsgi server instance.
-
-from distutils.util import strtobool
-from json.decoder import JSONDecodeError
-
-import eventlet
-import eventlet.wsgi
-import getopt
-import os
-import signal
-import socket
-import sys
-
-from . import store, changedetection_app, content_fetcher
-from . import __version__
-
-# Only global so we can access it in the signal handler
-app = None
-datastore = None
-
-def sigterm_handler(_signo, _stack_frame):
-    global app
-    global datastore
-#    app.config.exit.set()
-    print('Shutdown: Got SIGTERM, DB saved to disk')
-    datastore.sync_to_json()
-#    raise SystemExit
-
-def main():
-    global datastore
-    global app
-
-    datastore_path = None
-    do_cleanup = False
-    host = ''
-    ipv6_enabled = False
-    port = os.environ.get('PORT') or 5000
-    ssl_mode = False
-
-    # On Windows, create and use a default path.
-    if os.name == 'nt':
-        datastore_path = os.path.expandvars(r'%APPDATA%\changedetection.io')
-        os.makedirs(datastore_path, exist_ok=True)
-    else:
-        # Must be absolute so that send_from_directory doesnt try to make it relative to backend/
-        datastore_path = os.path.join(os.getcwd(), "../datastore")
-
-    try:
-        opts, args = getopt.getopt(sys.argv[1:], "6Ccsd:h:p:", "port")
-    except getopt.GetoptError:
-        print('backend.py -s SSL enable -h [host] -p [port] -d [datastore path]')
-        sys.exit(2)
-
-    create_datastore_dir = False
-
-    for opt, arg in opts:
-        if opt == '-s':
-            ssl_mode = True
-
-        if opt == '-h':
-            host = arg
-
-        if opt == '-p':
-            port = int(arg)
-
-        if opt == '-d':
-            datastore_path = arg
-
-        if opt == '-6':
-            print ("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
-
-    # isnt there some @thingy to attach to each route to tell it, that this route needs a datastore
-    app_config = {'datastore_path': datastore_path}
-
-    if not os.path.isdir(app_config['datastore_path']):
-        if create_datastore_dir:
-            os.mkdir(app_config['datastore_path'])
-        else:
-            print(
-                "ERROR: Directory path for the datastore '{}' does not exist, cannot start, please make sure the directory exists or specify a directory with the -d option.\n"
-                "Or use the -C parameter to create the directory.".format(app_config['datastore_path']), file=sys.stderr)
-            sys.exit(2)
-
-    try:
-        datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], version_tag=__version__)
-    except JSONDecodeError as e:
-        # Dont' start if the JSON DB looks corrupt
-        print ("ERROR: JSON DB or Proxy List JSON at '{}' appears to be corrupt, aborting".format(app_config['datastore_path']))
-        print(str(e))
-        return
-
-    app = changedetection_app(app_config, datastore)
-
-    signal.signal(signal.SIGTERM, sigterm_handler)
-
-    # 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']),
-                    new_version_available=app.config['NEW_VERSION_AVAILABLE'],
-                    has_password=datastore.data['settings']['application']['password'] != False
-                    )
-
-    # Monitored websites will not receive a Referer header when a user clicks on an outgoing link.
-    # @Note: Incompatible with password login (and maybe other features) for now, submit a PR!
-    @app.after_request
-    def hide_referrer(response):
-        if strtobool(os.getenv("HIDE_REFERER", 'false')):
-            response.headers["Referrer-Policy"] = "no-referrer"
-
-        return response
-
-    # Proxy sub-directory support
-    # Set environment var USE_X_SETTINGS=1 on this script
-    # And then in your proxy_pass settings
-    #
-    #         proxy_set_header Host "localhost";
-    #         proxy_set_header X-Forwarded-Prefix /app;
-
-    if os.getenv('USE_X_SETTINGS'):
-        print ("USE_X_SETTINGS is ENABLED\n")
-        from werkzeug.middleware.proxy_fix import ProxyFix
-        app.wsgi_app = ProxyFix(app.wsgi_app, x_prefix=1, x_host=1)
-
-    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)
-
-    else:
-        eventlet.wsgi.server(eventlet.listen((host, int(port)), s_type), app)
-

changedetectionio/content_fetcher.py

@@ -1,594 +0,0 @@
-import hashlib
-from abc import abstractmethod
-import chardet
-import json
-import logging
-import os
-import requests
-import sys
-import time
-
-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'
-
-class Non200ErrorCodeReceived(Exception):
-    def __init__(self, status_code, url, screenshot=None, xpath_data=None, page_html=None):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        self.xpath_data = xpath_data
-        self.page_text = None
-
-        if page_html:
-            from changedetectionio import html_tools
-            self.page_text = html_tools.html_to_text(page_html)
-        return
-
-class checksumFromPreviousCheckWasTheSame(Exception):
-    def __init__(self):
-        return
-
-class JSActionExceptions(Exception):
-    def __init__(self, status_code, url, screenshot, message=''):
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        self.message = message
-        return
-
-class BrowserStepsStepTimout(Exception):
-    def __init__(self, step_n):
-        self.step_n = step_n
-        return
-
-
-class PageUnloadable(Exception):
-    def __init__(self, status_code, url, message, screenshot=False):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        self.message = message
-        return
-
-class EmptyReply(Exception):
-    def __init__(self, status_code, url, screenshot=None):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        return
-
-class ScreenshotUnavailable(Exception):
-    def __init__(self, status_code, url, page_html=None):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        if page_html:
-            from html_tools import html_to_text
-            self.page_text = html_to_text(page_html)
-        return
-
-class ReplyWithContentButNoText(Exception):
-    def __init__(self, status_code, url, screenshot=None):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        return
-
-class Fetcher():
-    error = None
-    status_code = None
-    content = None
-    headers = None
-    browser_steps = None
-    browser_steps_screenshot_path = None
-
-    fetcher_description = "No description"
-    webdriver_js_execute_code = None
-    xpath_element_js = ""
-
-    xpath_data = None
-
-    # Will be needed in the future by the VisualSelector, always get this where possible.
-    screenshot = False
-    system_http_proxy = os.getenv('HTTP_PROXY')
-    system_https_proxy = os.getenv('HTTPS_PROXY')
-
-    # Time ONTOP of the system defined env minimum time
-    render_extract_delay = 0
-
-    def __init__(self):
-        from pkg_resources import resource_string
-        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
-        self.xpath_element_js = resource_string(__name__, "res/xpath_element_scraper.js").decode('utf-8')
-
-
-    @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):
-        # Should set self.error, self.status_code and self.content
-        pass
-
-    @abstractmethod
-    def quit(self):
-        return
-
-    @abstractmethod
-    def get_last_status_code(self):
-        return self.status_code
-
-    @abstractmethod
-    def screenshot_step(self, step_n):
-        return None
-
-    @abstractmethod
-    # Return true/false if this checker is ready to run, in the case it needs todo some special config check etc
-    def is_ready(self):
-        return True
-
-    def iterate_browser_steps(self):
-        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
-        from playwright._impl._api_types import TimeoutError
-        from jinja2 import Environment
-        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
-
-        step_n = 0
-
-        if self.browser_steps is not None and len(self.browser_steps):
-            interface = steppable_browser_interface()
-            interface.page = self.page
-
-            valid_steps = filter(lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'), self.browser_steps)
-
-            for step in valid_steps:
-                step_n += 1
-                print(">> Iterating check - browser Step n {} - {}...".format(step_n, step['operation']))
-                self.screenshot_step("before-"+str(step_n))
-                self.save_step_html("before-"+str(step_n))
-                try:
-                    optional_value = step['optional_value']
-                    selector = step['selector']
-                    # Support for jinja2 template in step values, with date module added
-                    if '{%' in step['optional_value'] or '{{' in step['optional_value']:
-                        optional_value = str(jinja2_env.from_string(step['optional_value']).render())
-                    if '{%' in step['selector'] or '{{' in step['selector']:
-                        selector = str(jinja2_env.from_string(step['selector']).render())
-
-                    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)
-                except TimeoutError:
-                    # Stop processing here
-                    raise BrowserStepsStepTimout(step_n=step_n)
-
-
-
-    # It's always good to reset these
-    def delete_browser_steps_screenshots(self):
-        import glob
-        if self.browser_steps_screenshot_path is not None:
-            dest = os.path.join(self.browser_steps_screenshot_path, 'step_*.jpeg')
-            files = glob.glob(dest)
-            for f in files:
-                os.unlink(f)
-
-#   Maybe for the future, each fetcher provides its own diff output, could be used for text, image
-#   the current one would return javascript output (as we use JS to generate the diff)
-#
-def available_fetchers():
-    # See the if statement at the bottom of this file for how we switch between playwright and webdriver
-    import inspect
-    p = []
-    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)
-
-    return p
-
-class base_html_playwright(Fetcher):
-    fetcher_description = "Playwright {}/Javascript".format(
-        os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
-    )
-    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
-        fetcher_description += " via '{}'".format(os.getenv("PLAYWRIGHT_DRIVER_URL"))
-
-    browser_type = ''
-    command_executor = ''
-
-    # Configs for Proxy setup
-    # In the ENV vars, is prefixed with "playwright_proxy_", so it is for example "playwright_proxy_server"
-    playwright_proxy_settings_mappings = ['bypass', 'server', 'username', 'password']
-
-    proxy = None
-
-    def __init__(self, proxy_override=None):
-        super().__init__()
-        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
-        self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
-        self.command_executor = os.getenv(
-            "PLAYWRIGHT_DRIVER_URL",
-            'ws://playwright-chrome:3000'
-        ).strip('"')
-
-        # If any proxy settings are enabled, then we should setup the proxy object
-        proxy_args = {}
-        for k in self.playwright_proxy_settings_mappings:
-            v = os.getenv('playwright_proxy_' + k, False)
-            if v:
-                proxy_args[k] = v.strip('"')
-
-        if proxy_args:
-            self.proxy = proxy_args
-
-        # allow per-watch proxy selection override
-        if proxy_override:
-            self.proxy = {'server': proxy_override}
-
-        if self.proxy:
-            # Playwright needs separate username and password values
-            from urllib.parse import urlparse
-            parsed = urlparse(self.proxy.get('server'))
-            if parsed.username:
-                self.proxy['username'] = parsed.username
-                self.proxy['password'] = parsed.password
-
-    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))
-            logging.debug("Saving step screenshot to {}".format(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))
-        logging.debug("Saving step HTML to {}".format(destination))
-        with open(destination, 'w') as f:
-            f.write(content)
-
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-
-        from playwright.sync_api import sync_playwright
-        import playwright._impl._api_types
-
-        self.delete_browser_steps_screenshots()
-        response = None
-        with sync_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.command_executor, timeout=60000)
-
-            # 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(
-                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
-                proxy=self.proxy,
-                # This is needed to enable JavaScript execution on GitHub and others
-                bypass_csp=True,
-                # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
-                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
-                # Should never be needed
-                accept_downloads=False
-            )
-
-            self.page = context.new_page()
-            if len(request_headers):
-                context.set_extra_http_headers(request_headers)
-
-                self.page.set_default_navigation_timeout(90000)
-                self.page.set_default_timeout(90000)
-
-                # 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}"))
-
-            # Goto page
-            try:
-                # Wait_until = commit
-                # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
-                # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
-                # This seemed to solve nearly all 'TimeoutErrors'
-                response = self.page.goto(url, wait_until='commit')
-            except playwright._impl._api_types.Error as e:
-                # Retry once - https://github.com/browserless/chrome/issues/2485
-                # Sometimes errors related to invalid cert's and other can be random
-                print ("Content Fetcher > retrying request got error - ", str(e))
-                time.sleep(1)
-                response = self.page.goto(url, wait_until='commit')
-
-            except Exception as e:
-                print ("Content Fetcher > Other exception when page.goto", str(e))
-                context.close()
-                browser.close()
-                raise PageUnloadable(url=url, status_code=None, message=str(e))
-
-            # Execute any browser steps
-            try:
-                extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-                self.page.wait_for_timeout(extra_wait * 1000)
-
-                if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
-                    self.page.evaluate(self.webdriver_js_execute_code)
-
-            except playwright._impl._api_types.TimeoutError as e:
-                context.close()
-                browser.close()
-                # This can be ok, we will try to grab what we could retrieve
-                pass
-            except Exception as e:
-                print ("Content Fetcher > Other exception when executing custom JS code", str(e))
-                context.close()
-                browser.close()
-                raise PageUnloadable(url=url, status_code=None, message=str(e))
-
-            if response is None:
-                context.close()
-                browser.close()
-                print ("Content Fetcher > Response object was none")
-                raise EmptyReply(url=url, status_code=None)
-
-            # Run Browser Steps here
-            self.iterate_browser_steps()
-
-            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-            time.sleep(extra_wait)
-
-            self.content = self.page.content()
-            self.status_code = response.status
-            if len(self.page.content().strip()) == 0:
-                context.close()
-                browser.close()
-                print ("Content Fetcher > Content was empty")
-                raise EmptyReply(url=url, status_code=response.status)
-
-            self.status_code = response.status
-            self.content = self.page.content()
-            self.headers = response.all_headers()
-
-            # 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.xpath_data = self.page.evaluate("async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
-
-            # 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
-            try:
-                # The actual screenshot
-                self.screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
-            except Exception as e:
-                context.close()
-                browser.close()
-                raise ScreenshotUnavailable(url=url, status_code=None)
-
-            context.close()
-            browser.close()
-
-class base_html_webdriver(Fetcher):
-    if os.getenv("WEBDRIVER_URL"):
-        fetcher_description = "WebDriver Chrome/Javascript via '{}'".format(os.getenv("WEBDRIVER_URL"))
-    else:
-        fetcher_description = "WebDriver Chrome/Javascript"
-
-    command_executor = ''
-
-    # 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
-
-    def __init__(self, proxy_override=None):
-        super().__init__()
-        from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
-
-        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
-        self.command_executor = os.getenv("WEBDRIVER_URL", 'http://browser-chrome:4444/wd/hub').strip('"')
-
-        # 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('"')
-
-        # 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):
-
-        from selenium import webdriver
-        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
-        from selenium.common.exceptions import WebDriverException
-        # request_body, request_method unused for now, until some magic in the future happens.
-
-        # check env for WEBDRIVER_URL
-        self.driver = webdriver.Remote(
-            command_executor=self.command_executor,
-            desired_capabilities=DesiredCapabilities.CHROME,
-            proxy=self.proxy)
-
-        try:
-            self.driver.get(url)
-        except WebDriverException as e:
-            # Be sure we close the session window
-            self.quit()
-            raise
-
-        self.driver.set_window_size(1280, 1024)
-        self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
-
-        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)))
-
-        # @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.common.desired_capabilities import DesiredCapabilities
-
-        self.driver = webdriver.Remote(
-            command_executor=self.command_executor,
-            desired_capabilities=DesiredCapabilities.CHROME)
-
-        # driver.quit() seems to cause better exceptions
-        self.quit()
-        return True
-
-    def quit(self):
-        if self.driver:
-            try:
-                self.driver.quit()
-            except Exception as e:
-                print("Content Fetcher > Exception in chrome shutdown/quit" + str(e))
-
-
-# "html_requests" is listed as the default fetcher in store.py!
-class html_requests(Fetcher):
-    fetcher_description = "Basic fast Plaintext/HTTP Client"
-
-    def __init__(self, proxy_override=None):
-        self.proxy_override = proxy_override
-
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-
-        # Make requests use a more modern looking user-agent
-        if not 'User-Agent' in request_headers:
-            request_headers['User-Agent'] = os.getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT",
-                                                      'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36')
-
-        proxies = {}
-
-        # Allows override the proxy on a per-request basis
-        if self.proxy_override:
-            proxies = {'http': self.proxy_override, 'https': self.proxy_override, 'ftp': self.proxy_override}
-        else:
-            if self.system_http_proxy:
-                proxies['http'] = self.system_http_proxy
-            if self.system_https_proxy:
-                proxies['https'] = self.system_https_proxy
-
-        r = requests.request(method=request_method,
-                             data=request_body,
-                             url=url,
-                             headers=request_headers,
-                             timeout=timeout,
-                             proxies=proxies,
-                             verify=False)
-
-        # 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
-        # This seems to not occur when using webdriver/selenium, it seems to detect the text encoding more reliably.
-        # https://github.com/psf/requests/issues/1604 good info about requests encoding detection
-        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
-
-        if not r.content or not len(r.content):
-            raise EmptyReply(url=url, status_code=r.status_code)
-
-        # @todo test this
-        # @todo maybe you really want to test zero-byte return pages?
-        if r.status_code != 200 and not ignore_status_codes:
-            # maybe check with content works?
-            raise Non200ErrorCodeReceived(url=url, status_code=r.status_code, page_html=r.text)
-
-        self.status_code = r.status_code
-        if is_binary:
-            # Binary files just return their checksum until we add something smarter
-            self.content = hashlib.md5(r.content).hexdigest()
-        else:
-            self.content = r.text
-
-        self.headers = r.headers
-        self.raw_content = r.content
-
-
-# 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)
-if use_playwright_as_chrome_fetcher:
-    html_webdriver = base_html_playwright
-else:
-    html_webdriver = base_html_webdriver

changedetectionio/content_fetchers/__init__.py

@@ -0,0 +1,43 @@
+import sys
+from changedetectionio.strtobool import strtobool
+from loguru import logger
+from changedetectionio.content_fetchers.exceptions import BrowserStepsStepException
+import os
+
+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'
+
+# available_fetchers() will scan this implementation looking for anything starting with html_
+# this information is used in the form selections
+from changedetectionio.content_fetchers.requests import fetcher as html_requests
+
+def available_fetchers():
+    # See the if statement at the bottom of this file for how we switch between playwright and webdriver
+    import inspect
+    p = []
+    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)
+
+    return p
+
+
+# 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)
+if use_playwright_as_chrome_fetcher:
+    # @note - For now, browser steps always uses playwright
+    if not strtobool(os.getenv('FAST_PUPPETEER_CHROME_FETCHER', 'False')):
+        logger.debug('Using Playwright library as fetcher')
+        from .playwright import fetcher as html_webdriver
+    else:
+        logger.debug('Using direct Python Puppeteer library as fetcher')
+        from .puppeteer import fetcher as html_webdriver
+
+else:
+    logger.debug("Falling back to selenium as fetcher")
+    from .webdriver_selenium import fetcher as html_webdriver
+

changedetectionio/content_fetchers/base.py

@@ -0,0 +1,173 @@
+import os
+from abc import abstractmethod
+from loguru import logger
+
+from changedetectionio.content_fetchers import BrowserStepsStepException
+
+
+def manage_user_agent(headers, current_ua=''):
+    """
+    Basic setting of user-agent
+
+    NOTE!!!!!! The service that does the actual Chrome fetching should handle any anti-robot techniques
+    THERE ARE MANY WAYS THAT IT CAN BE DETECTED AS A ROBOT!!
+    This does not take care of
+    - Scraping of 'navigator' (platform, productSub, vendor, oscpu etc etc) browser object (navigator.appVersion) etc
+    - TCP/IP fingerprint JA3 etc
+    - Graphic rendering fingerprinting
+    - Your IP being obviously in a pool of bad actors
+    - Too many requests
+    - Scraping of SCH-UA browser replies (thanks google!!)
+    - Scraping of ServiceWorker, new window calls etc
+
+    See https://filipvitas.medium.com/how-to-set-user-agent-header-with-puppeteer-js-and-not-fail-28c7a02165da
+    Puppeteer requests https://github.com/dgtlmoon/pyppeteerstealth
+
+    :param page:
+    :param headers:
+    :return:
+    """
+    # Ask it what the user agent is, if its obviously ChromeHeadless, switch it to the default
+    ua_in_custom_headers = headers.get('User-Agent')
+    if ua_in_custom_headers:
+        return ua_in_custom_headers
+
+    if not ua_in_custom_headers and current_ua:
+        current_ua = current_ua.replace('HeadlessChrome', 'Chrome')
+        return current_ua
+
+    return None
+
+
+class Fetcher():
+    browser_connection_is_custom = None
+    browser_connection_url = None
+    browser_steps = None
+    browser_steps_screenshot_path = None
+    content = None
+    error = None
+    fetcher_description = "No description"
+    headers = {}
+    instock_data = None
+    instock_data_js = ""
+    status_code = None
+    webdriver_js_execute_code = None
+    xpath_data = None
+    xpath_element_js = ""
+
+    # Will be needed in the future by the VisualSelector, always get this where possible.
+    screenshot = False
+    system_http_proxy = os.getenv('HTTP_PROXY')
+    system_https_proxy = os.getenv('HTTPS_PROXY')
+
+    # Time ONTOP of the system defined env minimum time
+    render_extract_delay = 0
+
+    def __init__(self):
+        from pkg_resources import resource_string
+        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
+        self.xpath_element_js = resource_string(__name__, "res/xpath_element_scraper.js").decode('utf-8')
+        self.instock_data_js = resource_string(__name__, "res/stock-not-in-stock.js").decode('utf-8')
+
+    @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):
+        # Should set self.error, self.status_code and self.content
+        pass
+
+    @abstractmethod
+    def quit(self):
+        return
+
+    @abstractmethod
+    def get_last_status_code(self):
+        return self.status_code
+
+    @abstractmethod
+    def screenshot_step(self, step_n):
+        return None
+
+    @abstractmethod
+    # Return true/false if this checker is ready to run, in the case it needs todo some special config check etc
+    def is_ready(self):
+        return True
+
+    def get_all_headers(self):
+        """
+        Get all headers but ensure all keys are lowercase
+        :return:
+        """
+        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
+        from playwright._impl._errors import TimeoutError, Error
+        from changedetectionio.safe_jinja import render as jinja_render
+        step_n = 0
+
+        if self.browser_steps is not None and len(self.browser_steps):
+            interface = steppable_browser_interface(start_url=start_url)
+            interface.page = self.page
+            valid_steps = self.browser_steps_get_valid_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))
+                try:
+                    optional_value = step['optional_value']
+                    selector = step['selector']
+                    # Support for jinja2 template in step values, with date module added
+                    if '{%' in step['optional_value'] or '{{' in step['optional_value']:
+                        optional_value = jinja_render(template_str=step['optional_value'])
+                    if '{%' in step['selector'] or '{{' in step['selector']:
+                        selector = jinja_render(template_str=step['selector'])
+
+                    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)
+                except (Error, TimeoutError) as e:
+                    logger.debug(str(e))
+                    # Stop processing here
+                    raise BrowserStepsStepException(step_n=step_n, original_e=e)
+
+    # It's always good to reset these
+    def delete_browser_steps_screenshots(self):
+        import glob
+        if self.browser_steps_screenshot_path is not None:
+            dest = os.path.join(self.browser_steps_screenshot_path, 'step_*.jpeg')
+            files = glob.glob(dest)
+            for f in files:
+                if os.path.isfile(f):
+                    os.unlink(f)
+
+    def save_step_html(self, param):
+        pass

changedetectionio/content_fetchers/exceptions/__init__.py

@@ -0,0 +1,97 @@
+from loguru import logger
+
+
+class Non200ErrorCodeReceived(Exception):
+    def __init__(self, status_code, url, screenshot=None, xpath_data=None, page_html=None):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        self.xpath_data = xpath_data
+        self.page_text = None
+
+        if page_html:
+            from changedetectionio import html_tools
+            self.page_text = html_tools.html_to_text(page_html)
+        return
+
+
+class checksumFromPreviousCheckWasTheSame(Exception):
+    def __init__(self):
+        return
+
+
+class JSActionExceptions(Exception):
+    def __init__(self, status_code, url, screenshot, message=''):
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        self.message = message
+        return
+
+class BrowserConnectError(Exception):
+    msg = ''
+    def __init__(self, msg):
+        self.msg = msg
+        logger.error(f"Browser connection error {msg}")
+        return
+
+class BrowserFetchTimedOut(Exception):
+    msg = ''
+    def __init__(self, msg):
+        self.msg = msg
+        logger.error(f"Browser processing took too long - {msg}")
+        return
+
+class BrowserStepsStepException(Exception):
+    def __init__(self, step_n, original_e):
+        self.step_n = step_n
+        self.original_e = original_e
+        logger.debug(f"Browser Steps exception at step {self.step_n} {str(original_e)}")
+        return
+
+
+# @todo - make base Exception class that announces via logger()
+class PageUnloadable(Exception):
+    def __init__(self, status_code=None, url='', message='', screenshot=False):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        self.message = message
+        return
+
+class BrowserStepsInUnsupportedFetcher(Exception):
+    def __init__(self, url):
+        self.url = url
+        return
+
+class EmptyReply(Exception):
+    def __init__(self, status_code, url, screenshot=None):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        return
+
+
+class ScreenshotUnavailable(Exception):
+    def __init__(self, status_code, url, page_html=None):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        if page_html:
+            from html_tools import html_to_text
+            self.page_text = html_to_text(page_html)
+        return
+
+
+class ReplyWithContentButNoText(Exception):
+    def __init__(self, status_code, url, screenshot=None, has_filters=False, html_content=''):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        self.has_filters = has_filters
+        self.html_content = html_content
+        return

changedetectionio/content_fetchers/playwright.py

@@ -0,0 +1,208 @@
+import json
+import os
+from urllib.parse import urlparse
+
+from loguru import logger
+
+from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
+from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, ScreenshotUnavailable
+
+class fetcher(Fetcher):
+    fetcher_description = "Playwright {}/Javascript".format(
+        os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
+    )
+    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
+        fetcher_description += " via '{}'".format(os.getenv("PLAYWRIGHT_DRIVER_URL"))
+
+    browser_type = ''
+    command_executor = ''
+
+    # Configs for Proxy setup
+    # In the ENV vars, is prefixed with "playwright_proxy_", so it is for example "playwright_proxy_server"
+    playwright_proxy_settings_mappings = ['bypass', 'server', 'username', 'password']
+
+    proxy = None
+
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
+        super().__init__()
+
+        self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
+
+        if custom_browser_connection_url:
+            self.browser_connection_is_custom = True
+            self.browser_connection_url = custom_browser_connection_url
+        else:
+            # Fallback to fetching from system
+            # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+            self.browser_connection_url = os.getenv("PLAYWRIGHT_DRIVER_URL", 'ws://playwright-chrome:3000').strip('"')
+
+        # If any proxy settings are enabled, then we should setup the proxy object
+        proxy_args = {}
+        for k in self.playwright_proxy_settings_mappings:
+            v = os.getenv('playwright_proxy_' + k, False)
+            if v:
+                proxy_args[k] = v.strip('"')
+
+        if proxy_args:
+            self.proxy = proxy_args
+
+        # allow per-watch proxy selection override
+        if proxy_override:
+            self.proxy = {'server': proxy_override}
+
+        if self.proxy:
+            # Playwright needs separate username and password values
+            parsed = urlparse(self.proxy.get('server'))
+            if parsed.username:
+                self.proxy['username'] = parsed.username
+                self.proxy['password'] = parsed.password
+
+    def screenshot_step(self, step_n=''):
+        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
+
+        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)
+
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None,
+            is_binary=False):
+
+        from playwright.sync_api import sync_playwright
+        import playwright._impl._errors
+        from changedetectionio.content_fetchers import visualselector_xpath_selectors
+        self.delete_browser_steps_screenshots()
+        response = None
+
+        with sync_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)
+
+            # 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(
+                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,
+                ignore_https_errors=True,
+                proxy=self.proxy,
+                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'), # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
+                user_agent=manage_user_agent(headers=request_headers),
+            )
+
+            self.page = 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}"))
+
+            # 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
+            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()
+
+            if response is None:
+                context.close()
+                browser.close()
+                logger.debug("Content Fetcher > Response object was none")
+                raise EmptyReply(url=url, status_code=None)
+
+            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)
+            except playwright._impl._errors.TimeoutError as e:
+                context.close()
+                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()
+                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)
+
+            try:
+                self.status_code = response.status
+            except Exception as e:
+                # 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()
+                raise PageUnloadable(url=url, status_code=None, message=str(e))
+
+            if self.status_code != 200 and not ignore_status_codes:
+                screenshot = self.page.screenshot(type='jpeg', full_page=True,
+                                                  quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
+
+                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
+
+            if len(self.page.content().strip()) == 0:
+                context.close()
+                browser.close()
+                logger.debug("Content Fetcher > Content was empty")
+                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)
+
+            # 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.xpath_data = self.page.evaluate(
+                "async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
+            self.instock_data = self.page.evaluate("async () => {" + self.instock_data_js + "}")
+
+            self.content = self.page.content()
+            # 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
+            try:
+                # The actual screenshot - this always base64 and needs decoding! horrible! huge CPU usage
+                self.screenshot = self.page.screenshot(type='jpeg',
+                                                       full_page=True,
+                                                       quality=int(os.getenv("SCREENSHOT_QUALITY", 72)),
+                                                       )
+            except Exception as e:
+                # It's likely the screenshot was too long/big and something crashed
+                raise ScreenshotUnavailable(url=url, status_code=self.status_code)
+            finally:
+                context.close()
+                browser.close()

changedetectionio/content_fetchers/puppeteer.py

@@ -0,0 +1,269 @@
+import asyncio
+import json
+import os
+import websockets.exceptions
+from urllib.parse import urlparse
+
+from loguru import logger
+
+from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
+from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, BrowserFetchTimedOut, BrowserConnectError
+
+class fetcher(Fetcher):
+    fetcher_description = "Puppeteer/direct {}/Javascript".format(
+        os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
+    )
+    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
+        fetcher_description += " via '{}'".format(os.getenv("PLAYWRIGHT_DRIVER_URL"))
+
+    browser_type = ''
+    command_executor = ''
+
+    proxy = None
+
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
+        super().__init__()
+
+        if custom_browser_connection_url:
+            self.browser_connection_is_custom = True
+            self.browser_connection_url = custom_browser_connection_url
+        else:
+            # Fallback to fetching from system
+            # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+            self.browser_connection_url = os.getenv("PLAYWRIGHT_DRIVER_URL", 'ws://playwright-chrome:3000').strip('"')
+
+        # allow per-watch proxy selection override
+        # @todo check global too?
+        if proxy_override:
+            # Playwright needs separate username and password values
+            parsed = urlparse(proxy_override)
+            if parsed:
+                self.proxy = {'username': parsed.username, 'password': parsed.password}
+                # Add the proxy server chrome start option, the username and password never gets added here
+                # (It always goes in via await self.page.authenticate(self.proxy))
+
+                # @todo filter some injection attack?
+                # check scheme when no scheme
+                proxy_url = parsed.scheme + "://" if parsed.scheme else 'http://'
+                r = "?" if not '?' in self.browser_connection_url else '&'
+                port = ":"+str(parsed.port) if parsed.port else ''
+                q = "?"+parsed.query if parsed.query else ''
+                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 fetch_page(self,
+                         url,
+                         timeout,
+                         request_headers,
+                         request_body,
+                         request_method,
+                         ignore_status_codes,
+                         current_include_filters,
+                         is_binary
+                         ):
+
+        from changedetectionio.content_fetchers import visualselector_xpath_selectors
+        self.delete_browser_steps_screenshots()
+        extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+
+        from pyppeteer import Pyppeteer
+        pyppeteer_instance = Pyppeteer()
+
+        # Connect directly using the specified browser_ws_endpoint
+        # @todo timeout
+        try:
+            browser = await pyppeteer_instance.connect(browserWSEndpoint=self.browser_connection_url,
+                                                       ignoreHTTPSErrors=True
+                                                       )
+        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)}")
+
+        # 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()
+
+        try:
+            from pyppeteerstealth import inject_evasions_into_page
+        except ImportError:
+            logger.debug("pyppeteerstealth module not available, skipping")
+            pass
+        else:
+            # I tried hooking events via self.page.on(Events.Page.DOMContentLoaded, inject_evasions_requiring_obj_to_page)
+            # But I could never get it to fire reliably, so we just inject it straight after
+            await inject_evasions_into_page(self.page)
+
+        # This user agent is similar to what was used when tweaking the evasions in inject_evasions_into_page(..)
+        user_agent = None
+        if request_headers and request_headers.get('User-Agent'):
+            # Request_headers should now be CaaseInsensitiveDict
+            # Remove it so it's not sent again with headers after
+            user_agent = request_headers.pop('User-Agent').strip()
+            await self.page.setUserAgent(user_agent)
+
+        if not user_agent:
+            # Attempt to strip 'HeadlessChrome' etc
+            await self.page.setUserAgent(manage_user_agent(headers=request_headers, current_ua=await self.page.evaluate('navigator.userAgent')))
+
+        await self.page.setBypassCSP(True)
+        if request_headers:
+            await self.page.setExtraHTTPHeaders(request_headers)
+
+        # SOCKS5 with authentication is not supported (yet)
+        # https://github.com/microsoft/playwright/issues/10567
+        self.page.setDefaultNavigationTimeout(0)
+        await self.page.setCacheEnabled(True)
+        if self.proxy and self.proxy.get('username'):
+            # Setting Proxy-Authentication header is deprecated, and doing so can trigger header change errors from Puppeteer
+            # https://github.com/puppeteer/puppeteer/issues/676 ?
+            # https://help.brightdata.com/hc/en-us/articles/12632549957649-Proxy-Manager-How-to-Guides#h_01HAKWR4Q0AFS8RZTNYWRDFJC2
+            # https://cri.dev/posts/2020-03-30-How-to-solve-Puppeteer-Chrome-Error-ERR_INVALID_ARGUMENT/
+            await self.page.authenticate(self.proxy)
+
+        # 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
+
+        # not yet used here, we fallback to playwright when browsersteps is required
+        #            browsersteps_interface = steppable_browser_interface()
+        #            browsersteps_interface.page = self.page
+
+        response = await self.page.goto(url, waitUntil="load")
+
+
+        if response is None:
+            await self.page.close()
+            await browser.close()
+            logger.warning("Content Fetcher > Response object was none")
+            raise EmptyReply(url=url, status_code=None)
+
+        self.headers = response.headers
+
+        try:
+            if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
+                await self.page.evaluate(self.webdriver_js_execute_code)
+        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))
+
+        try:
+            self.status_code = response.status
+        except Exception as e:
+            # 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 self.status_code != 200 and not ignore_status_codes:
+            screenshot = await self.page.screenshot(type_='jpeg',
+                                                    fullPage=True,
+                                                    quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
+
+            raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
+        content = await self.page.content
+        if len(content.strip()) == 0:
+            await self.page.close()
+            await browser.close()
+            logger.error("Content Fetcher > Content was empty")
+            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():
+        #                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
+        if current_include_filters is not None:
+            js = json.dumps(current_include_filters)
+            await self.page.evaluate(f"var include_filters={js}")
+        else:
+            await self.page.evaluate(f"var include_filters=''")
+
+        self.xpath_data = await self.page.evaluate(
+            "async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
+        self.instock_data = await self.page.evaluate("async () => {" + self.instock_data_js + "}")
+
+        self.content = await self.page.content
+        # 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
+        try:
+            self.screenshot = await self.page.screenshot(type_='jpeg',
+                                                         fullPage=True,
+                                                         quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
+        except Exception as e:
+            logger.error("Error fetching screenshot")
+            # // May fail on very large pages with 'WARNING: tile memory limits exceeded, some content may not draw'
+            # // @ todo after text extract, we can place some overlay text with red background to say 'croppped'
+            logger.error('ERROR: content-fetcher page was maybe too large for a screenshot, reverting to viewport only screenshot')
+            try:
+                self.screenshot = await self.page.screenshot(type_='jpeg',
+                                                             fullPage=False,
+                                                             quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
+            except Exception as e:
+                logger.error('ERROR: Failed to get viewport-only reduced screenshot :(')
+                pass
+        finally:
+            # 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):
+
+        #@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)
+
+        # This will work in 3.10 but not >= 3.11 because 3.11 wants tasks only
+        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,
+                current_include_filters=current_include_filters,
+                is_binary=is_binary
+            ), timeout=max_time))
+        except asyncio.TimeoutError:
+            raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))
+

changedetectionio/content_fetchers/requests.py

@@ -0,0 +1,86 @@
+import hashlib
+import os
+
+import chardet
+import requests
+
+from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
+from changedetectionio.content_fetchers.base import Fetcher
+
+
+# "html_requests" is listed as the default fetcher in store.py!
+class fetcher(Fetcher):
+    fetcher_description = "Basic fast Plaintext/HTTP Client"
+
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
+        super().__init__()
+        self.proxy_override = proxy_override
+        # browser_connection_url is none because its always 'launched locally'
+
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None,
+            is_binary=False):
+
+        if self.browser_steps_get_valid_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.
+
+        if self.proxy_override:
+            proxies = {'http': self.proxy_override, 'https': self.proxy_override, 'ftp': self.proxy_override}
+        else:
+            if self.system_http_proxy:
+                proxies['http'] = self.system_http_proxy
+            if self.system_https_proxy:
+                proxies['https'] = self.system_https_proxy
+
+        r = requests.request(method=request_method,
+                             data=request_body,
+                             url=url,
+                             headers=request_headers,
+                             timeout=timeout,
+                             proxies=proxies,
+                             verify=False)
+
+        # 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
+        # This seems to not occur when using webdriver/selenium, it seems to detect the text encoding more reliably.
+        # https://github.com/psf/requests/issues/1604 good info about requests encoding detection
+        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
+
+        self.headers = r.headers
+
+        if not r.content or not len(r.content):
+            raise EmptyReply(url=url, status_code=r.status_code)
+
+        # @todo test this
+        # @todo maybe you really want to test zero-byte return pages?
+        if r.status_code != 200 and not ignore_status_codes:
+            # maybe check with content works?
+            raise Non200ErrorCodeReceived(url=url, status_code=r.status_code, page_html=r.text)
+
+        self.status_code = r.status_code
+        if is_binary:
+            # Binary files just return their checksum until we add something smarter
+            self.content = hashlib.md5(r.content).hexdigest()
+        else:
+            self.content = r.text
+
+
+        self.raw_content = r.content

changedetectionio/content_fetchers/res/puppeteer_fetch.js

@@ -0,0 +1,190 @@
+module.exports = async ({page, context}) => {
+
+    var {
+        url,
+        execute_js,
+        user_agent,
+        extra_wait_ms,
+        req_headers,
+        include_filters,
+        xpath_element_js,
+        screenshot_quality,
+        proxy_username,
+        proxy_password,
+        disk_cache_dir,
+        no_cache_list,
+        block_url_list,
+    } = context;
+
+    await page.setBypassCSP(true)
+    await page.setExtraHTTPHeaders(req_headers);
+
+    if (user_agent) {
+        await page.setUserAgent(user_agent);
+    }
+    // https://ourcodeworld.com/articles/read/1106/how-to-solve-puppeteer-timeouterror-navigation-timeout-of-30000-ms-exceeded
+
+    await page.setDefaultNavigationTimeout(0);
+
+    if (proxy_username) {
+        // Setting Proxy-Authentication header is deprecated, and doing so can trigger header change errors from Puppeteer
+        // https://github.com/puppeteer/puppeteer/issues/676 ?
+        // https://help.brightdata.com/hc/en-us/articles/12632549957649-Proxy-Manager-How-to-Guides#h_01HAKWR4Q0AFS8RZTNYWRDFJC2
+        // https://cri.dev/posts/2020-03-30-How-to-solve-Puppeteer-Chrome-Error-ERR_INVALID_ARGUMENT/
+        await page.authenticate({
+            username: proxy_username,
+            password: proxy_password
+        });
+    }
+
+    await page.setViewport({
+        width: 1024,
+        height: 768,
+        deviceScaleFactor: 1,
+    });
+
+    await page.setRequestInterception(true);
+    if (disk_cache_dir) {
+        console.log(">>>>>>>>>>>>>>> LOCAL DISK CACHE ENABLED <<<<<<<<<<<<<<<<<<<<<");
+    }
+    const fs = require('fs');
+    const crypto = require('crypto');
+
+    function file_is_expired(file_path) {
+        if (!fs.existsSync(file_path)) {
+            return true;
+        }
+        var stats = fs.statSync(file_path);
+        const now_date = new Date();
+        const expire_seconds = 300;
+        if ((now_date / 1000) - (stats.mtime.getTime() / 1000) > expire_seconds) {
+            console.log("CACHE EXPIRED: " + file_path);
+            return true;
+        }
+        return false;
+
+    }
+
+    page.on('request', async (request) => {
+        // General blocking of requests that waste traffic
+        if (block_url_list.some(substring => request.url().toLowerCase().includes(substring))) return request.abort();
+
+        if (disk_cache_dir) {
+            const url = request.url();
+            const key = crypto.createHash('md5').update(url).digest("hex");
+            const dir_path = disk_cache_dir + key.slice(0, 1) + '/' + key.slice(1, 2) + '/' + key.slice(2, 3) + '/';
+
+            // https://stackoverflow.com/questions/4482686/check-synchronously-if-file-directory-exists-in-node-js
+
+            if (fs.existsSync(dir_path + key)) {
+                console.log("* CACHE HIT , using - " + dir_path + key + " - " + url);
+                const cached_data = fs.readFileSync(dir_path + key);
+                // @todo headers can come from dir_path+key+".meta" json file
+                request.respond({
+                    status: 200,
+                    //contentType: 'text/html', //@todo
+                    body: cached_data
+                });
+                return;
+            }
+        }
+        request.continue();
+    });
+
+
+    if (disk_cache_dir) {
+        page.on('response', async (response) => {
+            const url = response.url();
+            // Basic filtering for sane responses
+            if (response.request().method() != 'GET' || response.request().resourceType() == 'xhr' || response.request().resourceType() == 'document' || response.status() != 200) {
+                console.log("Skipping (not useful) - Status:" + response.status() + " Method:" + response.request().method() + " ResourceType:" + response.request().resourceType() + " " + url);
+                return;
+            }
+            if (no_cache_list.some(substring => url.toLowerCase().includes(substring))) {
+                console.log("Skipping (no_cache_list) - " + url);
+                return;
+            }
+            if (url.toLowerCase().includes('data:')) {
+                console.log("Skipping (embedded-data) - " + url);
+                return;
+            }
+            response.buffer().then(buffer => {
+                if (buffer.length > 100) {
+                    console.log("Cache - Saving " + response.request().method() + " - " + url + " - " + response.request().resourceType());
+
+                    const key = crypto.createHash('md5').update(url).digest("hex");
+                    const dir_path = disk_cache_dir + key.slice(0, 1) + '/' + key.slice(1, 2) + '/' + key.slice(2, 3) + '/';
+
+                    if (!fs.existsSync(dir_path)) {
+                        fs.mkdirSync(dir_path, {recursive: true})
+                    }
+
+                    if (fs.existsSync(dir_path + key)) {
+                        if (file_is_expired(dir_path + key)) {
+                            fs.writeFileSync(dir_path + key, buffer);
+                        }
+                    } else {
+                        fs.writeFileSync(dir_path + key, buffer);
+                    }
+                }
+            });
+        });
+    }
+
+    const r = await page.goto(url, {
+        waitUntil: 'load'
+    });
+
+    await page.waitForTimeout(1000);
+    await page.waitForTimeout(extra_wait_ms);
+
+    if (execute_js) {
+        await page.evaluate(execute_js);
+        await page.waitForTimeout(200);
+    }
+
+    var xpath_data;
+    var instock_data;
+    try {
+        // Not sure the best way here, in the future this should be a new package added to npm then run in evaluatedCode
+        // (Once the old playwright is removed)
+        xpath_data = await page.evaluate((include_filters) => {%xpath_scrape_code%}, include_filters);
+        instock_data = await page.evaluate(() => {%instock_scrape_code%});
+    } catch (e) {
+        console.log(e);
+    }
+
+    // Protocol error (Page.captureScreenshot): Cannot take screenshot with 0 width can come from a proxy auth failure
+    // Wrap it here (for now)
+
+    var b64s = false;
+    try {
+        b64s = await page.screenshot({encoding: "base64", fullPage: true, quality: screenshot_quality, type: 'jpeg'});
+    } catch (e) {
+        console.log(e);
+    }
+
+    // May fail on very large pages with 'WARNING: tile memory limits exceeded, some content may not draw'
+    if (!b64s) {
+        // @todo after text extract, we can place some overlay text with red background to say 'croppped'
+        console.error('ERROR: content-fetcher page was maybe too large for a screenshot, reverting to viewport only screenshot');
+        try {
+            b64s = await page.screenshot({encoding: "base64", quality: screenshot_quality, type: 'jpeg'});
+        } catch (e) {
+            console.log(e);
+        }
+    }
+
+    var html = await page.content();
+    return {
+        data: {
+            'content': html,
+            'headers': r.headers(),
+            'instock_data': instock_data,
+            'screenshot': b64s,
+            'status_code': r.status(),
+            'xpath_data': xpath_data
+        },
+        type: 'application/json',
+    };
+};

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

@@ -0,0 +1,192 @@
+// Restock Detector
+// (c) Leigh Morresi dgtlmoon@gmail.com
+//
+// Assumes the product is in stock to begin with, unless the following appears above the fold ;
+// - outOfStockTexts appears above the fold (out of stock)
+// - negateOutOfStockRegex (really is in stock)
+
+function isItemInStock() {
+    // @todo Pass these in so the same list can be used in non-JS fetchers
+    const outOfStockTexts = [
+        ' أخبرني عندما يتوفر',
+        '0 in stock',
+        'actuellement indisponible',
+        'agotado',
+        'article épuisé',
+        'artikel zurzeit vergriffen',
+        'as soon as stock is available',
+        'ausverkauft', // sold out
+        'available for back order',
+        'awaiting stock',
+        'back in stock soon',
+        'back-order or out of stock',
+        'backordered',
+        'benachrichtigt mich', // notify me
+        'brak na stanie',
+        'brak w magazynie',
+        'coming soon',
+        'currently have any tickets for this',
+        'currently unavailable',
+        'dieser artikel ist bald wieder verfügbar',
+        'dostępne wkrótce',
+        'en rupture de stock',
+        'ist derzeit nicht auf lager',
+        'item is no longer available',
+        'let me know when it\'s available',
+        'message if back in stock',
+        'nachricht bei',
+        'nicht auf lager',
+        'nicht lieferbar',
+        'nicht zur verfügung',
+        'niet beschikbaar',
+        'niet leverbaar',
+        'niet op voorraad',
+        'no disponible temporalmente',
+        'no longer in stock',
+        'no tickets available',
+        'not available',
+        'not currently available',
+        'not in stock',
+        'notify me when available',
+        'notify when available',
+        'não estamos a aceitar encomendas',
+        'out of stock',
+        'out-of-stock',
+        'prodotto esaurito',
+        'produkt niedostępny',
+        'sold out',
+        'sold-out',
+        'temporarily out of stock',
+        'temporarily unavailable',
+        'there were no search results for',
+        'this item is currently unavailable',
+        'tickets unavailable',
+        'tijdelijk uitverkocht',
+        'unavailable tickets',
+        'vorbestellung ist bald möglich',
+        'we couldn\'t find any products that match',
+        'we do not currently have an estimate of when this product will be back in stock.',
+        'we don\'t know when or if this item will be back in stock.',
+        'we were not able to find a match',
+        'zur zeit nicht an lager',
+        '品切れ',
+        '已售',
+        '已售完',
+        '품절'
+    ];
+
+
+    const vh = Math.max(document.documentElement.clientHeight || 0, window.innerHeight || 0);
+
+    function getElementBaseText(element) {
+        // .textContent can include text from children which may give the wrong results
+        // scan only immediate TEXT_NODEs, which will be a child of the element
+        var text = "";
+        for (var i = 0; i < element.childNodes.length; ++i)
+            if (element.childNodes[i].nodeType === Node.TEXT_NODE)
+                text += element.childNodes[i].textContent;
+        return text.toLowerCase().trim();
+    }
+
+    const negateOutOfStockRegex = new RegExp('^([0-9] in stock|add to cart|in stock)', '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
+    // and it should be atleast 100px from the top to ignore items in the toolbar, sometimes menu items like "Coming soon" exist
+
+
+// @todo - if it's SVG or IMG, go into image diff mode
+// %ELEMENTS% replaced at injection time because different interfaces use it with different settings
+
+    console.log("Scanning %ELEMENTS%");
+
+    function collectVisibleElements(parent, visibleElements) {
+        if (!parent) return; // Base case: if parent is null or undefined, return
+
+        // Add the parent itself to the visible elements array if it's of the specified types
+        visibleElements.push(parent);
+
+        // Iterate over the parent's children
+        const children = parent.children;
+        for (let i = 0; i < children.length; i++) {
+            const child = children[i];
+            if (
+                child.nodeType === Node.ELEMENT_NODE &&
+                window.getComputedStyle(child).display !== 'none' &&
+                window.getComputedStyle(child).visibility !== 'hidden' &&
+                child.offsetWidth >= 0 &&
+                child.offsetHeight >= 0 &&
+                window.getComputedStyle(child).contentVisibility !== 'hidden'
+            ) {
+                // If the child is an element and is visible, recursively collect visible elements
+                collectVisibleElements(child, visibleElements);
+            }
+        }
+    }
+
+    const elementsToScan = [];
+    collectVisibleElements(document.body, elementsToScan);
+
+    var elementText = "";
+
+    // REGEXS THAT REALLY MEAN IT'S IN STOCK
+    for (let i = elementsToScan.length - 1; i >= 0; i--) {
+        const element = elementsToScan[i];
+
+        // outside the 'fold' or some weird text in the heading area
+        // .getBoundingClientRect() was causing a crash in chrome 119, can only be run on contentVisibility != hidden
+        if (element.getBoundingClientRect().top + window.scrollY >= vh || element.getBoundingClientRect().top + window.scrollY <= 100) {
+            continue
+        }
+
+        elementText = "";
+        if (element.tagName.toLowerCase() === "input") {
+            elementText = element.value.toLowerCase().trim();
+        } else {
+            elementText = getElementBaseText(element);
+        }
+
+        if (elementText.length) {
+            // try which ones could mean its in stock
+            if (negateOutOfStockRegex.test(elementText) && !elementText.includes('(0 products)')) {
+                console.log(`Negating/overriding 'Out of Stock' back to "Possibly in stock" found "${elementText}"`)
+                return 'Possibly in stock';
+            }
+        }
+    }
+
+    // OTHER STUFF THAT COULD BE THAT IT'S OUT OF STOCK
+    for (let i = elementsToScan.length - 1; i >= 0; i--) {
+        const element = elementsToScan[i];
+        // outside the 'fold' or some weird text in the heading area
+        // .getBoundingClientRect() was causing a crash in chrome 119, can only be run on contentVisibility != hidden
+        if (element.getBoundingClientRect().top + window.scrollY >= vh + 150 || element.getBoundingClientRect().top + window.scrollY <= 100) {
+            continue
+        }
+        elementText = "";
+        if (element.tagName.toLowerCase() === "input") {
+            elementText = element.value.toLowerCase().trim();
+        } else {
+            elementText = getElementBaseText(element);
+        }
+
+        if (elementText.length) {
+            // and these mean its out of stock
+            for (const outOfStockText of outOfStockTexts) {
+                if (elementText.includes(outOfStockText)) {
+                    console.log(`Selected 'Out of Stock' - found text "${outOfStockText}" - "${elementText}"`)
+                    return outOfStockText; // item is out of stock
+                }
+            }
+        }
+    }
+
+    console.log(`Returning 'Possibly in stock' - cant' find any useful matching text`)
+    return 'Possibly in stock'; // possibly in stock, cant decide otherwise.
+}
+
+// returns the element text that makes it think it's out of stock
+return isItemInStock().trim()
+
+

changedetectionio/content_fetchers/res/xpath_element_scraper.js

@@ -8,26 +8,31 @@
 // Some pages like https://www.londonstockexchange.com/stock/NCCL/ncondezi-energy-limited/analysis
 // will automatically force a scroll somewhere, so include the position offset
 // Lets hope the position doesnt change while we iterate the bbox's, but this is better than nothing
+var scroll_y = 0;
+try {
+    scroll_y = +document.documentElement.scrollTop || document.body.scrollTop
+} catch (e) {
+    console.log(e);
+}
 
-var scroll_y=+document.documentElement.scrollTop || document.body.scrollTop
 
 // Include the getXpath script directly, easier than fetching
 function getxpath(e) {
-        var n = e;
-        if (n && n.id) return '//*[@id="' + n.id + '"]';
-        for (var o = []; n && Node.ELEMENT_NODE === n.nodeType;) {
-            for (var i = 0, r = !1, d = n.previousSibling; d;) d.nodeType !== Node.DOCUMENT_TYPE_NODE && d.nodeName === n.nodeName && i++, d = d.previousSibling;
-            for (d = n.nextSibling; d;) {
-                if (d.nodeName === n.nodeName) {
-                    r = !0;
-                    break
-                }
-                d = d.nextSibling
+    var n = e;
+    if (n && n.id) return '//*[@id="' + n.id + '"]';
+    for (var o = []; n && Node.ELEMENT_NODE === n.nodeType;) {
+        for (var i = 0, r = !1, d = n.previousSibling; d;) d.nodeType !== Node.DOCUMENT_TYPE_NODE && d.nodeName === n.nodeName && i++, d = d.previousSibling;
+        for (d = n.nextSibling; d;) {
+            if (d.nodeName === n.nodeName) {
+                r = !0;
+                break
             }
-            o.push((n.prefix ? n.prefix + ":" : "") + n.localName + (i || r ? "[" + (i + 1) + "]" : "")), n = n.parentNode
+            d = d.nextSibling
         }
-        return o.length ? "/" + o.reverse().join("/") : ""
+        o.push((n.prefix ? n.prefix + ":" : "") + n.localName + (i || r ? "[" + (i + 1) + "]" : "")), n = n.parentNode
     }
+    return o.length ? "/" + o.reverse().join("/") : ""
+}
 
 const findUpTag = (el) => {
     let r = el
@@ -38,29 +43,29 @@ const findUpTag = (el) => {
     if (el.name !== undefined && el.name.length) {
         var proposed = el.tagName + "[name=" + el.name + "]";
         var proposed_element = window.document.querySelectorAll(proposed);
-        if(proposed_element.length) {
+        if (proposed_element.length) {
             if (proposed_element.length === 1) {
                 return proposed;
             } else {
                 // Some sites change ID but name= stays the same, we can hit it if we know the index
                 // Find all the elements that match and work out the input[n]
-                var n=Array.from(proposed_element).indexOf(el);
+                var n = Array.from(proposed_element).indexOf(el);
                 // Return a Playwright selector for nthinput[name=zipcode]
-                return proposed+" >> nth="+n;
+                return proposed + " >> nth=" + n;
             }
         }
     }
 
     // Strategy 2: Keep going up until we hit an ID tag, imagine it's like  #list-widget div h4
     while (r.parentNode) {
-        if (depth == 5) {
+        if (depth === 5) {
             break;
         }
         if ('' !== r.id) {
             chained_css.unshift("#" + CSS.escape(r.id));
             final_selector = chained_css.join(' > ');
             // Be sure theres only one, some sites have multiples of the same ID tag :-(
-            if (window.document.querySelectorAll(final_selector).length == 1) {
+            if (window.document.querySelectorAll(final_selector).length === 1) {
                 return final_selector;
             }
             return null;
@@ -76,30 +81,60 @@ const findUpTag = (el) => {
 
 // @todo - if it's SVG or IMG, go into image diff mode
 // %ELEMENTS% replaced at injection time because different interfaces use it with different settings
-var elements = window.document.querySelectorAll("%ELEMENTS%");
+
 var size_pos = [];
 // after page fetch, inject this JS
 // build a map of all elements and their positions (maybe that only include text?)
 var bbox;
-for (var i = 0; i < elements.length; i++) {
-    bbox = elements[i].getBoundingClientRect();
+console.log("Scanning %ELEMENTS%");
 
-    // Exclude items that are not interactable or visible
-    if(elements[i].style.opacity === "0") {
-        continue
+function collectVisibleElements(parent, visibleElements) {
+    if (!parent) return; // Base case: if parent is null or undefined, return
+
+
+    // Add the parent itself to the visible elements array if it's of the specified types
+    const tagName = parent.tagName.toLowerCase();
+    if ("%ELEMENTS%".split(',').includes(tagName)) {
+        visibleElements.push(parent);
     }
-    if(elements[i].style.display === "none" || elements[i].style.pointerEvents === "none" ) {
-        continue
+
+    // Iterate over the parent's children
+    const children = parent.children;
+    for (let i = 0; i < children.length; i++) {
+        const child = children[i];
+        if (
+            child.nodeType === Node.ELEMENT_NODE &&
+            window.getComputedStyle(child).display !== 'none' &&
+            window.getComputedStyle(child).visibility !== 'hidden' &&
+            child.offsetWidth >= 0 &&
+            child.offsetHeight >= 0 &&
+            window.getComputedStyle(child).contentVisibility !== 'hidden'
+        ) {
+            // If the child is an element and is visible, recursively collect visible elements
+            collectVisibleElements(child, visibleElements);
+        }
     }
+}
+
+// Create an array to hold the visible elements
+const visibleElementsArray = [];
+
+// Call collectVisibleElements with the starting parent element
+collectVisibleElements(document.body, visibleElementsArray);
+
+
+visibleElementsArray.forEach(function (element) {
+
+    bbox = element.getBoundingClientRect();
 
     // Skip really small ones, and where width or height ==0
-    if (bbox['width'] * bbox['height'] < 100) {
-        continue;
+    if (bbox['width'] * bbox['height'] < 10) {
+        return
     }
 
     // Don't include elements that are offset from canvas
-    if (bbox['top']+scroll_y < 0 || bbox['left'] < 0) {
-        continue;
+    if (bbox['top'] + scroll_y < 0 || bbox['left'] < 0) {
+        return
     }
 
     // @todo the getXpath kind of sucks, it doesnt know when there is for example just one ID sometimes
@@ -108,46 +143,41 @@ for (var i = 0; i < elements.length; i++) {
 
     // 1st primitive - if it has class, try joining it all and select, if theres only one.. well thats us.
     xpath_result = false;
-
     try {
-        var d = findUpTag(elements[i]);
+        var d = findUpTag(element);
         if (d) {
             xpath_result = d;
         }
     } catch (e) {
         console.log(e);
     }
-
     // You could swap it and default to getXpath and then try the smarter one
     // default back to the less intelligent one
     if (!xpath_result) {
         try {
             // I've seen on FB and eBay that this doesnt work
             // ReferenceError: getXPath is not defined at eval (eval at evaluate (:152:29), <anonymous>:67:20) at UtilityScript.evaluate (<anonymous>:159:18) at UtilityScript.<anonymous> (<anonymous>:1:44)
-            xpath_result = getxpath(elements[i]);
+            xpath_result = getxpath(element);
         } catch (e) {
             console.log(e);
-            continue;
+            return
         }
     }
 
-    if (window.getComputedStyle(elements[i]).visibility === "hidden") {
-        continue;
-    }
 
-    // @todo Possible to ONLY list where it's clickable to save JSON xfer size
     size_pos.push({
         xpath: xpath_result,
         width: Math.round(bbox['width']),
         height: Math.round(bbox['height']),
         left: Math.floor(bbox['left']),
-        top: Math.floor(bbox['top'])+scroll_y,
-        tagName: (elements[i].tagName) ? elements[i].tagName.toLowerCase() : '',
-        tagtype: (elements[i].tagName == 'INPUT' && elements[i].type) ? elements[i].type.toLowerCase() : '',
-        isClickable: (elements[i].onclick) || window.getComputedStyle(elements[i]).cursor == "pointer"
+        top: Math.floor(bbox['top']) + scroll_y,
+        tagName: (element.tagName) ? element.tagName.toLowerCase() : '',
+        tagtype: (element.tagName.toLowerCase() === 'input' && element.type) ? element.type.toLowerCase() : '',
+        isClickable: window.getComputedStyle(element).cursor == "pointer"
     });
 
-}
+});
+
 
 // Inject the current one set in the include_filters, which may be a CSS rule
 // used for displaying the current one in VisualSelector, where its not one we generated.
@@ -164,20 +194,33 @@ if (include_filters.length) {
 
         try {
             // is it xpath?
-            if (f.startsWith('/') || f.startsWith('xpath:')) {
-                q = document.evaluate(f.replace('xpath:', ''), document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
+            if (f.startsWith('/') || f.startsWith('xpath')) {
+                var qry_f = f.replace(/xpath(:|\d:)/, '')
+                console.log("[xpath] Scanning for included filter " + qry_f)
+                q = document.evaluate(qry_f, document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
             } else {
+                console.log("[css] Scanning for included filter " + f)
                 q = document.querySelector(f);
             }
         } catch (e) {
             // Maybe catch DOMException and alert?
-            console.log("xpath_element_scraper: Exception selecting element from filter "+f);
+            console.log("xpath_element_scraper: Exception selecting element from filter " + f);
             console.log(e);
         }
 
         if (q) {
+            // Try to resolve //something/text() back to its /something so we can atleast get the bounding box
+            try {
+                if (typeof q.nodeName == 'string' && q.nodeName === '#text') {
+                    q = q.parentElement
+                }
+            } catch (e) {
+                console.log(e)
+                console.log("xpath_element_scraper: #text resolver")
+            }
+
             // #1231 - IN the case XPath attribute filter is applied, we will have to traverse up and find the element.
-            if (q.hasOwnProperty('getBoundingClientRect')) {
+            if (typeof q.getBoundingClientRect == 'function') {
                 bbox = q.getBoundingClientRect();
                 console.log("xpath_element_scraper: Got filter element, scroll from top was " + scroll_y)
             } else {
@@ -186,12 +229,13 @@ if (include_filters.length) {
                     bbox = q.ownerElement.getBoundingClientRect();
                     console.log("xpath_element_scraper: Got filter by ownerElement element, scroll from top was " + scroll_y)
                 } catch (e) {
-                    console.log("xpath_element_scraper: error looking up ownerElement")
+                    console.log(e)
+                    console.log("xpath_element_scraper: error looking up q.ownerElement")
                 }
             }
         }
-        
-        if(!q) {
+
+        if (!q) {
             console.log("xpath_element_scraper: filter element " + f + " was not found");
         }
 
@@ -201,7 +245,7 @@ if (include_filters.length) {
                 width: parseInt(bbox['width']),
                 height: parseInt(bbox['height']),
                 left: parseInt(bbox['left']),
-                top: parseInt(bbox['top'])+scroll_y
+                top: parseInt(bbox['top']) + scroll_y
             });
         }
     }
@@ -209,7 +253,7 @@ if (include_filters.length) {
 
 // Sort the elements so we find the smallest one first, in other words, we find the smallest one matching in that area
 // so that we dont select the wrapping element by mistake and be unable to select what we want
-size_pos.sort((a, b) => (a.width*a.height > b.width*b.height) ? 1 : -1)
+size_pos.sort((a, b) => (a.width * a.height > b.width * b.height) ? 1 : -1)
 
 // Window.width required for proper scaling in the frontend
 return {'size_pos': size_pos, 'browser_width': window.innerWidth};

changedetectionio/content_fetchers/webdriver_selenium.py

@@ -0,0 +1,119 @@
+import os
+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"))
+    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
+
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
+        super().__init__()
+        from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
+
+        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+        if not custom_browser_connection_url:
+            self.browser_connection_url = os.getenv("WEBDRIVER_URL", 'http://browser-chrome:4444/wd/hub').strip('"')
+        else:
+            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('"')
+
+        # 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):
+
+        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()
+        if self.proxy:
+            options.proxy = self.proxy
+
+        self.driver = webdriver.Remote(
+            command_executor=self.browser_connection_url,
+            options=options)
+
+        try:
+            self.driver.get(url)
+        except WebDriverException as e:
+            # Be sure we close the session window
+            self.quit()
+            raise
+
+        self.driver.set_window_size(1280, 1024)
+        self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+
+        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)))
+
+        # @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):
+        if self.driver:
+            try:
+                self.driver.quit()
+            except Exception as e:
+                logger.debug(f"Content Fetcher > Exception in chrome shutdown/quit {str(e)}")

changedetectionio/diff.py

@@ -10,7 +10,7 @@ def same_slicer(l, a, b):
         return l[a:b]
 
 # like .compare but a little different output
-def customSequenceMatcher(before, after, include_equal=False):
+def customSequenceMatcher(before, after, include_equal=False, include_removed=True, include_added=True, include_replaced=True, include_change_type_prefix=True):
     cruncher = difflib.SequenceMatcher(isjunk=lambda x: x in " \\t", a=before, b=after)
 
     # @todo Line-by-line mode instead of buncghed, including `after` that is not in `before` (maybe unset?)
@@ -18,35 +18,45 @@ def customSequenceMatcher(before, after, include_equal=False):
         if include_equal and tag == 'equal':
             g = before[alo:ahi]
             yield g
-        elif tag == 'delete':
-            g = ["(removed) " + i for i in same_slicer(before, alo, ahi)]
+        elif include_removed and tag == 'delete':
+            row_prefix = "(removed) " if include_change_type_prefix else ''
+            g = [ row_prefix + i for i in same_slicer(before, alo, ahi)]
             yield g
-        elif tag == 'replace':
-            g = ["(changed) " + i for i in same_slicer(before, alo, ahi)]
-            g += ["(into   ) " + i for i in same_slicer(after, blo, bhi)]
+        elif include_replaced and tag == 'replace':
+            row_prefix = "(changed) " if include_change_type_prefix else ''
+            g = [row_prefix + i for i in same_slicer(before, alo, ahi)]
+            row_prefix = "(into) " if include_change_type_prefix else ''
+            g += [row_prefix + i for i in same_slicer(after, blo, bhi)]
             yield g
-        elif tag == 'insert':
-            g = ["(added  ) " + i for i in same_slicer(after, blo, bhi)]
+        elif include_added and tag == 'insert':
+            row_prefix = "(added) " if include_change_type_prefix else ''
+            g = [row_prefix + i for i in same_slicer(after, blo, bhi)]
             yield g
 
 # only_differences - only return info about the differences, no context
-# line_feed_sep could be "<br/>" or "<li>" or "\n" etc
-def render_diff(previous_file, newest_file, include_equal=False, line_feed_sep="\n"):
-    with open(newest_file, 'r') as f:
-        newest_version_file_contents = f.read()
-        newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
+# line_feed_sep could be "<br>" or "<li>" or "\n" etc
+def render_diff(previous_version_file_contents, newest_version_file_contents, include_equal=False, include_removed=True, include_added=True, include_replaced=True, line_feed_sep="\n", include_change_type_prefix=True, patch_format=False):
 
-    if previous_file:
-        with open(previous_file, 'r') as f:
-            previous_version_file_contents = f.read()
-            previous_version_file_contents = [line.rstrip() for line in previous_version_file_contents.splitlines()]
+    newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
+
+    if previous_version_file_contents:
+        previous_version_file_contents = [line.rstrip() for line in previous_version_file_contents.splitlines()]
     else:
         previous_version_file_contents = ""
 
-    rendered_diff = customSequenceMatcher(previous_version_file_contents,
-                                          newest_version_file_contents,
-                                          include_equal)
+    if patch_format:
+        patch = difflib.unified_diff(previous_version_file_contents, newest_version_file_contents)
+        return line_feed_sep.join(patch)
+
+    rendered_diff = customSequenceMatcher(before=previous_version_file_contents,
+                                          after=newest_version_file_contents,
+                                          include_equal=include_equal,
+                                          include_removed=include_removed,
+                                          include_added=include_added,
+                                          include_replaced=include_replaced,
+                                          include_change_type_prefix=include_change_type_prefix)
 
     # Recursively join lists
     f = lambda L: line_feed_sep.join([f(x) if type(x) is list else x for x in L])
-    return f(rendered_diff)
+    p= f(rendered_diff)
+    return p

changedetectionio/forms.py

@@ -1,5 +1,6 @@
 import os
 import re
+from changedetectionio.strtobool import strtobool
 
 from wtforms import (
     BooleanField,
@@ -14,30 +15,39 @@ from wtforms import (
     validators,
     widgets
 )
+from flask_wtf.file import FileField, FileAllowed
 from wtforms.fields import FieldList
+
 from wtforms.validators import ValidationError
 
+from validators.url import url as url_validator
+
+
 # default
 # each select <option data-enabled="enabled-0-0"
 from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
 
-from changedetectionio import content_fetcher
+from changedetectionio import html_tools, content_fetchers
+
 from changedetectionio.notification import (
     valid_notification_formats,
 )
 
 from wtforms.fields import FormField
 
+dictfilt = lambda x, y: dict([ (i,x[i]) for i in x if i in set(y) ])
+
 valid_method = {
     'GET',
     'POST',
     'PUT',
     'PATCH',
     'DELETE',
+    'OPTIONS',
 }
 
 default_method = 'GET'
-
+allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
 
 class StringListField(StringField):
     widget = widgets.TextArea()
@@ -90,6 +100,29 @@ class SaltyPasswordField(StringField):
         else:
             self.data = False
 
+class StringTagUUID(StringField):
+
+   # process_formdata(self, valuelist) handled manually in POST handler
+
+    # Is what is shown when field <input> is rendered
+    def _value(self):
+        # Tag UUID to name, on submit it will convert it back (in the submit handler of init.py)
+        if self.data and type(self.data) is list:
+            tag_titles = []
+            for i in self.data:
+                tag = self.datastore.data['settings']['application']['tags'].get(i)
+                if tag:
+                    tag_title = tag.get('title')
+                    if tag_title:
+                        tag_titles.append(tag_title)
+
+            return ', '.join(tag_titles)
+
+        if not self.data:
+            return ''
+
+        return 'error'
+
 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")])
@@ -134,31 +167,31 @@ class ValidateContentFetcherIsReady(object):
         self.message = message
 
     def __call__(self, form, field):
-        import urllib3.exceptions
-        from changedetectionio import content_fetcher
+        return
 
+# AttributeError: module 'changedetectionio.content_fetcher' has no attribute 'extra_browser_unlocked<>ASDF213r123r'
         # Better would be a radiohandler that keeps a reference to each class
-        if field.data is not None and field.data != 'system':
-            klass = getattr(content_fetcher, field.data)
-            some_object = klass()
-            try:
-                ready = some_object.is_ready()
-
-            except urllib3.exceptions.MaxRetryError as e:
-                driver_url = some_object.command_executor
-                message = field.gettext('Content fetcher \'%s\' did not respond.' % (field.data))
-                message += '<br/>' + field.gettext(
-                    'Be sure that the selenium/webdriver runner is running and accessible via network from this container/host.')
-                message += '<br/>' + field.gettext('Did you follow the instructions in the wiki?')
-                message += '<br/><br/>' + field.gettext('WebDriver Host: %s' % (driver_url))
-                message += '<br/><a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">Go here for more information</a>'
-                message += '<br/>'+field.gettext('Content fetcher did not respond properly, unable to use it.\n %s' % (str(e)))
-
-                raise ValidationError(message)
-
-            except Exception as e:
-                message = field.gettext('Content fetcher \'%s\' did not respond properly, unable to use it.\n %s')
-                raise ValidationError(message % (field.data, e))
+        # if field.data is not None and field.data != 'system':
+        #     klass = getattr(content_fetcher, field.data)
+        #     some_object = klass()
+        #     try:
+        #         ready = some_object.is_ready()
+        #
+        #     except urllib3.exceptions.MaxRetryError as e:
+        #         driver_url = some_object.command_executor
+        #         message = field.gettext('Content fetcher \'%s\' did not respond.' % (field.data))
+        #         message += '<br>' + field.gettext(
+        #             'Be sure that the selenium/webdriver runner is running and accessible via network from this container/host.')
+        #         message += '<br>' + field.gettext('Did you follow the instructions in the wiki?')
+        #         message += '<br><br>' + field.gettext('WebDriver Host: %s' % (driver_url))
+        #         message += '<br><a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">Go here for more information</a>'
+        #         message += '<br>'+field.gettext('Content fetcher did not respond properly, unable to use it.\n %s' % (str(e)))
+        #
+        #         raise ValidationError(message)
+        #
+        #     except Exception as e:
+        #         message = field.gettext('Content fetcher \'%s\' did not respond properly, unable to use it.\n %s')
+        #         raise ValidationError(message % (field.data, e))
 
 
 class ValidateNotificationBodyAndTitleWhenURLisSet(object):
@@ -203,18 +236,26 @@ class ValidateJinja2Template(object):
     def __call__(self, form, field):
         from changedetectionio import notification
 
-        from jinja2 import Environment, BaseLoader, TemplateSyntaxError
+        from jinja2 import BaseLoader, TemplateSyntaxError, UndefinedError
+        from jinja2.sandbox import ImmutableSandboxedEnvironment
         from jinja2.meta import find_undeclared_variables
+        import jinja2.exceptions
 
+        # Might be a list of text, or might be just text (like from the apprise url list)
+        joined_data = ' '.join(map(str, field.data)) if isinstance(field.data, list) else f"{field.data}"
 
         try:
-            jinja2_env = Environment(loader=BaseLoader)
+            jinja2_env = ImmutableSandboxedEnvironment(loader=BaseLoader)
             jinja2_env.globals.update(notification.valid_tokens)
-            rendered = jinja2_env.from_string(field.data).render()
+            jinja2_env.from_string(joined_data).render()
         except TemplateSyntaxError as e:
             raise ValidationError(f"This is not a valid Jinja2 template: {e}") from e
+        except UndefinedError as e:
+            raise ValidationError(f"A variable or function is not defined: {e}") from e
+        except jinja2.exceptions.SecurityError as e:
+            raise ValidationError(f"This is not a valid Jinja2 template: {e}") from e
 
-        ast = jinja2_env.parse(field.data)
+        ast = jinja2_env.parse(joined_data)
         undefined = ", ".join(find_undeclared_variables(ast))
         if undefined:
             raise ValidationError(
@@ -231,18 +272,23 @@ class validateURL(object):
         self.message = message
 
     def __call__(self, form, field):
-        import validators
+        # This should raise a ValidationError() or not
+        validate_url(field.data)
 
-        try:
-            validators.url(field.data.strip())
-        except validators.ValidationFailure:
-            message = field.gettext('\'%s\' is not a valid URL.' % (field.data.strip()))
-            raise ValidationError(message)
-
-        from .model.Watch import is_safe_url
-        if not is_safe_url(field.data):
-            raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX')
+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."
+        # This should be wtforms.validators.
+        raise ValidationError(message)
 
+    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):
     """
@@ -254,11 +300,10 @@ class ValidateListRegex(object):
     def __call__(self, form, field):
 
         for line in field.data:
-            if line[0] == '/' and line[-1] == '/':
-                # Because internally we dont wrap in /
-                line = line.strip('/')
+            if re.search(html_tools.PERL_STYLE_REGEX, line, re.IGNORECASE):
                 try:
-                    re.compile(line)
+                    regex = html_tools.perl_style_slash_enclosed_regex_to_options(line)
+                    re.compile(regex)
                 except re.error:
                     message = field.gettext('RegEx \'%s\' is not a valid regular expression.')
                     raise ValidationError(message % (line))
@@ -287,11 +332,30 @@ class ValidateCSSJSONXPATHInput(object):
                 return
 
             # Does it look like XPath?
-            if line.strip()[0] == '/':
+            if line.strip()[0] == '/' or line.strip().startswith('xpath:'):
+                if not self.allow_xpath:
+                    raise ValidationError("XPath not permitted in this field!")
+                from lxml import etree, html
+                import elementpath
+                # xpath 2.0-3.1
+                from elementpath.xpath3 import XPath3Parser
+                tree = html.fromstring("<html></html>")
+                line = line.replace('xpath:', '')
+
+                try:
+                    elementpath.select(tree, line.strip(), parser=XPath3Parser)
+                except elementpath.ElementPathError as e:
+                    message = field.gettext('\'%s\' is not a valid XPath expression. (%s)')
+                    raise ValidationError(message % (line, str(e)))
+                except:
+                    raise ValidationError("A system-error occurred when validating your XPath expression")
+
+            if line.strip().startswith('xpath1:'):
                 if not self.allow_xpath:
                     raise ValidationError("XPath not permitted in this field!")
                 from lxml import etree, html
                 tree = html.fromstring("<html></html>")
+                line = re.sub(r'^xpath1:', '', line)
 
                 try:
                     tree.xpath(line.strip())
@@ -344,23 +408,33 @@ class ValidateCSSJSONXPATHInput(object):
                     raise ValidationError("A system-error occurred when validating your jq expression")
 
 class quickWatchForm(Form):
-    url = fields.URLField('URL', validators=[validateURL()])
-    tag = StringField('Group tag', [validators.Optional()])
-    watch_submit_button = SubmitField('Watch', render_kw={"class": "pure-button pure-button-primary"})
-    edit_and_watch_submit_button = SubmitField('Edit > Watch', render_kw={"class": "pure-button pure-button-primary"})
+    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"})
 
 
 # Common to a single watch and the global settings
 class commonSettingsForm(Form):
-    notification_urls = StringListField('Notification URL List', validators=[validators.Optional(), ValidateAppRiseServers()])
+
+    notification_urls = StringListField('Notification URL List', validators=[validators.Optional(), ValidateAppRiseServers(), ValidateJinja2Template()])
     notification_title = StringField('Notification Title', default='ChangeDetection.io Notification - {{ watch_url }}', validators=[validators.Optional(), ValidateJinja2Template()])
     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())
-    fetch_backend = RadioField(u'Fetch Method', choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    fetch_backend = RadioField(u'Fetch Method', choices=content_fetchers.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     extract_title_as_title = BooleanField('Extract <title> from document and use as watch title', default=False)
     webdriver_delay = IntegerField('Wait seconds before extracting text', validators=[validators.Optional(), validators.NumberRange(min=1,
                                                                                                                                     message="Should contain one or more seconds")])
+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')})
+
 
 class SingleBrowserStep(Form):
 
@@ -376,9 +450,10 @@ class SingleBrowserStep(Form):
 class watchForm(commonSettingsForm):
 
     url = fields.URLField('URL', validators=[validateURL()])
-    tag = StringField('Group tag', [validators.Optional()], default='')
+    tags = StringTagUUID('Group tag', [validators.Optional()], default='')
 
     time_between_check = FormField(TimeBetweenCheckForm)
+    time_between_check_use_default = BooleanField('Use global settings for time between check', default=False)
 
     include_filters = StringListField('CSS/JSONPath/JQ/XPath Filters', [ValidateCSSJSONXPATHInput()], default='')
 
@@ -393,11 +468,20 @@ class watchForm(commonSettingsForm):
     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 new lines appear', default=False)
+    check_unique_lines = BooleanField('Only trigger when unique lines appear', default=False)
+    sort_text_alphabetically =  BooleanField('Sort text alphabetically', 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)
+
+    # @todo this class could be moved to its own text_json_diff_watchForm and this goes to restock_diff_Watchform perhaps
+    in_stock_only = BooleanField('Only trigger when product goes BACK to in-stock', default=True)
+
     trigger_text = StringListField('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 if text matches', [validators.Optional(), ValidateListRegex()])
+    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()])
 
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
@@ -421,11 +505,9 @@ class watchForm(commonSettingsForm):
             result = False
 
         # Attempt to validate jinja2 templates in the URL
-        from jinja2 import Environment
-        # Jinja2 available in URLs along with https://pypi.org/project/jinja2-time/
-        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
         try:
-            ready_url = str(jinja2_env.from_string(self.url.data).render())
+            from changedetectionio.safe_jinja import render as jinja_render
+            jinja_render(template_str=self.url.data)
         except Exception as e:
             self.url.errors.append('Invalid template syntax')
             result = False
@@ -436,9 +518,19 @@ 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": "http://user:pass@...:3128", "size":50})
+    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
 
+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
+
+class DefaultUAInputForm(Form):
+    html_requests = StringField('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>"})
+
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
     time_between_check = FormField(TimeBetweenCheckForm)
@@ -447,6 +539,9 @@ class globalSettingsRequestForm(Form):
                                   render_kw={"style": "width: 5em;"},
                                   validators=[validators.NumberRange(min=0, message="Should contain zero or more seconds")])
     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")
 
     def validate_extra_proxies(self, extra_validators=None):
         for e in self.data['extra_proxies']:
@@ -460,16 +555,25 @@ class globalSettingsRequestForm(Form):
 class globalSettingsApplicationForm(commonSettingsForm):
 
     api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
-    base_url = StringField('Base URL', validators=[validators.Optional()])
+    base_url = StringField('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_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    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_xpath=False, allow_json=False)])
     ignore_whitespace = BooleanField('Ignore whitespace')
     password = SaltyPasswordField()
+    pager_size = IntegerField('Pager size',
+                              render_kw={"style": "width: 5em;"},
+                              validators=[validators.NumberRange(min=0,
+                                                                 message="Should be atleast zero (disabled)")])
     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,
+                                      validators=[validators.Optional()])
     filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',
                                                                   render_kw={"style": "width: 5em;"},
                                                                   validators=[validators.NumberRange(min=0,

changedetectionio/html_tools.py

@@ -1,23 +1,44 @@
 
 from bs4 import BeautifulSoup
 from inscriptis import get_text
-from inscriptis.model.config import ParserConfig
 from jsonpath_ng.ext import parse
 from typing import List
+from inscriptis.css_profiles import CSS_PROFILES, HtmlElement
+from inscriptis.html_properties import Display
+from inscriptis.model.config import ParserConfig
+from xml.sax.saxutils import escape as xml_escape
 import json
 import re
 
-# HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
-TEXT_FILTER_LIST_LINE_SUFFIX = "<br/>"
 
+# HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
+TEXT_FILTER_LIST_LINE_SUFFIX = "<br>"
+
+PERL_STYLE_REGEX = r'^/(.*?)/([a-z]*)?$'
 # 'price' , 'lowPrice', 'highPrice' are usually under here
-# all of those may or may not appear on different websites
-LD_JSON_PRODUCT_OFFER_SELECTOR = "json:$..offers"
+# 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"]
 
 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
+def perl_style_slash_enclosed_regex_to_options(regex):
+
+    res = re.search(PERL_STYLE_REGEX, regex, re.IGNORECASE)
+
+    if res:
+        flags = res.group(2) if res.group(2) else 'i'
+        regex = f"(?{flags}){res.group(1)}"
+    else:
+        # Fall back to just ignorecase as an option
+        regex = f"(?i){regex}"
+
+    return regex
+
 # Given a CSS Rule, and a blob of HTML, return the blob of HTML that matches
 def include_filters(include_filters, html_content, append_pretty_line_formatting=False):
     soup = BeautifulSoup(html_content, "html.parser")
@@ -48,12 +69,96 @@ def element_removal(selectors: List[str], html_content):
     selector = ",".join(selectors)
     return subtractive_css_selector(selector, html_content)
 
+def elementpath_tostring(obj):
+    """
+    change elementpath.select results to string type
+    # The MIT License (MIT), Copyright (c), 2018-2021, SISSA (Scuola Internazionale Superiore di Studi Avanzati)
+    # https://github.com/sissaschool/elementpath/blob/dfcc2fd3d6011b16e02bf30459a7924f547b47d0/elementpath/xpath_tokens.py#L1038
+    """
+
+    import elementpath
+    from decimal import Decimal
+    import math
+
+    if obj is None:
+        return ''
+    # https://elementpath.readthedocs.io/en/latest/xpath_api.html#elementpath.select
+    elif isinstance(obj, elementpath.XPathNode):
+        return obj.string_value
+    elif isinstance(obj, bool):
+        return 'true' if obj else 'false'
+    elif isinstance(obj, Decimal):
+        value = format(obj, 'f')
+        if '.' in value:
+            return value.rstrip('0').rstrip('.')
+        return value
+
+    elif isinstance(obj, float):
+        if math.isnan(obj):
+            return 'NaN'
+        elif math.isinf(obj):
+            return str(obj).upper()
+
+        value = str(obj)
+        if '.' in value:
+            value = value.rstrip('0').rstrip('.')
+        if '+' in value:
+            value = value.replace('+', '')
+        if 'e' in value:
+            return value.upper()
+        return value
+
+    return str(obj)
 
 # Return str Utf-8 of matched rules
-def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False):
+def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_rss=False):
+    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')
+        else:
+            html_block += elementpath_tostring(element)
+
+    return html_block
+
+# Return str Utf-8 of matched rules
+# 'xpath1:'
+def xpath1_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_rss=False):
     from lxml import etree, html
 
-    tree = html.fromstring(bytes(html_content, encoding='utf-8'))
+    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'})
@@ -64,19 +169,18 @@ def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False
         # 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'])):
+        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) == etree._ElementStringResult:
-            html_block += str(element)
-        elif type(element) == etree._ElementUnicodeResult:
-            html_block += str(element)
+        # Some kind of text, UTF-8 or other
+        if isinstance(element, (str, bytes)):
+            html_block += element
         else:
+            # Return the HTML which will get parsed as text
             html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
 
     return html_block
 
-
 # Extract/find element
 def extract_element(find='title', html_content=''):
 
@@ -137,45 +241,58 @@ def _get_stripped_text_from_json_match(match):
 def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None):
     stripped_text_from_html = False
 
-    # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded <script type=ldjson>
+    # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded within HTML tags
     try:
         stripped_text_from_html = _parse_json(json.loads(content), json_filter)
     except json.JSONDecodeError:
 
         # Foreach <script json></script> blob.. just return the first that matches json_filter
-        s = []
+        # As a last resort, try to parse the whole <body>
         soup = BeautifulSoup(content, 'html.parser')
 
         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')
 
-
-        if not bs_result:
-            raise JSONNotFound("No parsable JSON found in this document")
-
+        bs_jsons = []
         for result in bs_result:
             # Skip empty tags, and things that dont even look like JSON
-            if not result.string or not '{' in result.string:
+            if not result.text or '{' not in result.text:
                 continue
-                
             try:
-                json_data = json.loads(result.string)
+                json_data = json.loads(result.text)
+                bs_jsons.append(json_data)
             except json.JSONDecodeError:
-                # Just skip it
+                # Skip objects which cannot be parsed
                 continue
-            else:
-                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)
-                        if json_data.get('@type', False) and json_data.get('@type','').lower() == ensure_is_ldjson_info_type.lower() and stripped_text_from_html:
-                            break
-                elif stripped_text_from_html:
-                    break
+
+        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 (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
+                    if json_data.get('@type') and stripped_text_from_html:
+                        try:
+                            if json_data.get('@type') == str or json_data.get('@type') == dict:
+                                types = [json_data.get('@type')] if isinstance(json_data.get('@type'), str) else json_data.get('@type')
+                                if ensure_is_ldjson_info_type.lower() in [x.lower().strip() for x in types]:
+                                    break
+                        except:
+                            continue
+
+            elif stripped_text_from_html:
+                break
 
     if not stripped_text_from_html:
         # Re 265 - Just return an empty string when filter not found
@@ -188,50 +305,56 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
 #
 # wordlist - list of regex's (str) or words (str)
 def strip_ignore_text(content, wordlist, mode="content"):
-    ignore = []
-    ignore_regex = []
-
-    # @todo check this runs case insensitive
-    for k in wordlist:
-
-        # Is it a regex?
-        if k[0] == '/':
-            ignore_regex.append(k.strip(" /"))
-        else:
-            ignore.append(k)
-
     i = 0
     output = []
+    ignore_text = []
+    ignore_regex = []
     ignored_line_numbers = []
+
+    for k in wordlist:
+        # Is it a regex?
+        res = re.search(PERL_STYLE_REGEX, k, re.IGNORECASE)
+        if res:
+            ignore_regex.append(re.compile(perl_style_slash_enclosed_regex_to_options(k)))
+        else:
+            ignore_text.append(k.strip())
+
     for line in content.splitlines():
         i += 1
         # Always ignore blank lines in this mode. (when this function gets called)
+        got_match = False
         if len(line.strip()):
-            regex_matches = False
+            for l in ignore_text:
+                if l.lower() in line.lower():
+                    got_match = True
 
-            # if any of these match, skip
-            for regex in ignore_regex:
-                try:
-                    if re.search(regex, line, re.IGNORECASE):
-                        regex_matches = True
-                except Exception as e:
-                    continue
+            if not got_match:
+                for r in ignore_regex:
+                    if r.search(line):
+                        got_match = True
 
-            if not regex_matches and not any(skip_text.lower() in line.lower() for skip_text in ignore):
+            if not got_match:
+                # Not ignored
                 output.append(line.encode('utf8'))
             else:
                 ignored_line_numbers.append(i)
 
 
-
     # Used for finding out what to highlight
     if mode == "line numbers":
         return ignored_line_numbers
 
     return "\n".encode('utf8').join(output)
 
+def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False) -> str:
+    pattern = '<!\[CDATA\[(\s*(?:.(?<!\]\]>)\s*)*)\]\]>'
+    def repl(m):
+        text = m.group(1)
+        return xml_escape(html_to_text(html_content=text)).strip()
 
-def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
+    return re.sub(pattern, repl, html_content)
+
+def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=False) -> str:
     """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
@@ -247,16 +370,21 @@ def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
     #  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
+            annotation_rules={"a": ["hyperlink"]},
+            display_links=True
         )
-
-    # otherwise set config to None
+    # otherwise set config to None/default
     else:
         parser_config = None
 
-    # get text and annotations via inscriptis
+    # 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)
 
     return text_content
@@ -264,9 +392,18 @@ def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
 
 # Does LD+JSON exist with a @type=='product' and a .price set anywhere?
 def has_ldjson_product_info(content):
+    pricing_data = ''
+
     try:
-        pricing_data = extract_json_as_string(content=content, json_filter=LD_JSON_PRODUCT_OFFER_SELECTOR, ensure_is_ldjson_info_type="product")
-    except JSONNotFound as e:
+        if not 'application/ld+json' in content:
+            return False
+
+        for filter in LD_JSON_PRODUCT_OFFER_SELECTORS:
+            pricing_data += extract_json_as_string(content=content,
+                                                  json_filter=filter,
+                                                  ensure_is_ldjson_info_type="product")
+
+    except Exception as e:
         # Totally fine
         return False
     x=bool(pricing_data)
@@ -287,3 +424,18 @@ def workarounds_for_obfuscations(content):
     content = re.sub('<!--\s+-->', '', content)
 
     return content
+
+
+def get_triggered_text(content, trigger_text):
+    triggered_text = []
+    result = strip_ignore_text(content=content,
+                               wordlist=trigger_text,
+                               mode="line numbers")
+
+    i = 1
+    for p in content.splitlines():
+        if i in result:
+            triggered_text.append(p)
+        i += 1
+
+    return triggered_text

changedetectionio/importer.py

@@ -1,6 +1,10 @@
 from abc import ABC, abstractmethod
 import time
 import validators
+from wtforms import ValidationError
+from loguru import logger
+
+from changedetectionio.forms import validate_url
 
 
 class Importer():
@@ -12,6 +16,7 @@ class Importer():
         self.new_uuids = []
         self.good = 0
         self.remaining_data = []
+        self.import_profile = None
 
     @abstractmethod
     def run(self,
@@ -29,6 +34,7 @@ class import_url_list(Importer):
             data,
             flash,
             datastore,
+            processor=None
             ):
 
         urls = data.split("\n")
@@ -51,8 +57,13 @@ class import_url_list(Importer):
 
             # Flask wtform validators wont work with basic auth, use validators package
             # Up to 5000 per batch so we dont flood the server
-            if len(url) and validators.url(url.replace('source:', '')) and good < 5000:
-                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False)
+            # @todo validators.url will fail when you add your own IP etc
+            if len(url) and 'http' in url.lower() and good < 5000:
+                extras = None
+                if processor:
+                    extras = {'processor': processor}
+                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False, extras=extras)
+
                 if new_uuid:
                     # Straight into the queue.
                     self.new_uuids.append(new_uuid)
@@ -79,7 +90,8 @@ class import_distill_io_json(Importer):
         now = time.time()
         self.new_uuids=[]
 
-
+        # @todo Use JSONSchema like in the API to validate here.
+        
         try:
             data = json.loads(data.strip())
         except json.decoder.JSONDecodeError:
@@ -114,11 +126,8 @@ class import_distill_io_json(Importer):
                 except IndexError:
                     pass
 
-
-                if d.get('tags', False):
-                    extras['tag'] = ", ".join(d['tags'])
-
                 new_uuid = datastore.add_watch(url=d['uri'].strip(),
+                                               tag=",".join(d.get('tags', [])),
                                                extras=extras,
                                                write_to_disk_now=False)
 
@@ -128,3 +137,167 @@ class import_distill_io_json(Importer):
                     good += 1
 
         flash("{} 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):
+
+    def run(self,
+            data,
+            flash,
+            datastore,
+            ):
+
+        good = 0
+        now = time.time()
+        self.new_uuids = []
+
+        from openpyxl import load_workbook
+
+        try:
+            wb = load_workbook(data)
+        except Exception as e:
+            # @todo correct except
+            flash("Unable to read export XLSX file, something wrong with the file?", 'error')
+            return
+
+        row_id = 2
+        for row in wb.active.iter_rows(min_row=row_id):
+            try:
+                extras = {}
+                data = {}
+                for cell in row:
+                    if not cell.value:
+                        continue
+                    column_title = wb.active.cell(row=1, column=cell.column).value.strip().lower()
+                    data[column_title] = cell.value
+
+                # Forced switch to webdriver/playwright/etc
+                dynamic_wachet = str(data.get('dynamic wachet', '')).strip().lower()  # Convert bool to str to cover all cases
+                # libreoffice and others can have it as =FALSE() =TRUE(), or bool(true)
+                if 'true' in dynamic_wachet or dynamic_wachet == '1':
+                    extras['fetch_backend'] = 'html_webdriver'
+                elif 'false' in dynamic_wachet or dynamic_wachet == '0':
+                    extras['fetch_backend'] = 'html_requests'
+
+                if data.get('xpath'):
+                    # @todo split by || ?
+                    extras['include_filters'] = [data.get('xpath')]
+                if data.get('name'):
+                    extras['title'] = data.get('name').strip()
+                if data.get('interval (min)'):
+                    minutes = int(data.get('interval (min)'))
+                    hours, minutes = divmod(minutes, 60)
+                    days, hours = divmod(hours, 24)
+                    weeks, days = divmod(days, 7)
+                    extras['time_between_check'] = {'weeks': weeks, 'days': days, 'hours': hours, 'minutes': minutes, 'seconds': 0}
+
+                # At minimum a URL is required.
+                if data.get('url'):
+                    try:
+                        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')
+                        # 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)
+                    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')
+            else:
+                row_id += 1
+
+        flash(
+            "{} imported from Wachete .xlsx in {:.2f}s".format(len(self.new_uuids), time.time() - now))
+
+
+class import_xlsx_custom(Importer):
+
+    def run(self,
+            data,
+            flash,
+            datastore,
+            ):
+
+        good = 0
+        now = time.time()
+        self.new_uuids = []
+
+        from openpyxl import load_workbook
+
+        try:
+            wb = load_workbook(data)
+        except Exception as e:
+            # @todo correct except
+            flash("Unable to read export XLSX file, something wrong with the file?", 'error')
+            return
+
+        # @todo cehck atleast 2 rows, same in other method
+        from .forms import validate_url
+        row_i = 1
+
+        try:
+            for row in wb.active.iter_rows():
+                url = None
+                tags = None
+                extras = {}
+
+                for cell in row:
+                    if not self.import_profile.get(cell.col_idx):
+                        continue
+                    if not cell.value:
+                        continue
+
+                    cell_map = self.import_profile.get(cell.col_idx)
+
+                    cell_val = str(cell.value).strip()  # could be bool
+
+                    if cell_map == 'url':
+                        url = cell.value.strip()
+                        try:
+                            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')
+                            # Don't bother processing anything else on this row
+                            url = None
+                            break
+                    elif cell_map == 'tag':
+                        tags = cell.value.strip()
+                    elif cell_map == 'include_filters':
+                        # @todo validate?
+                        extras['include_filters'] = [cell.value.strip()]
+                    elif cell_map == 'interval_minutes':
+                        hours, minutes = divmod(int(cell_val), 60)
+                        days, hours = divmod(hours, 24)
+                        weeks, days = divmod(days, 7)
+                        extras['time_between_check'] = {'weeks': weeks, 'days': days, 'hours': hours, 'minutes': minutes, 'seconds': 0}
+                    else:
+                        extras[cell_map] = cell_val
+
+                # At minimum a URL is required.
+                if url:
+                    new_uuid = datastore.add_watch(url=url,
+                                                   extras=extras,
+                                                   tag=tags,
+                                                   write_to_disk_now=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')
+        else:
+            row_i += 1
+
+        flash(
+            "{} imported from custom .xlsx in {:.2f}s".format(len(self.new_uuids), time.time() - now))

changedetectionio/model/App.py

@@ -6,6 +6,7 @@ from changedetectionio.notification import (
 )
 
 _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT = 6
+DEFAULT_SETTINGS_HEADERS_USERAGENT='Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36'
 
 class model(dict):
     base_config = {
@@ -16,32 +17,41 @@ class model(dict):
                 },
                 'requests': {
                     'extra_proxies': [], # Configurable extra proxies via the UI
+                    'extra_browsers': [],  # Configurable extra proxies via the UI
                     'jitter_seconds': 0,
                     '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
+                    'default_ua': {
+                        'html_requests': getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT", DEFAULT_SETTINGS_HEADERS_USERAGENT),
+                        'html_webdriver': None,
+                    }
                 },
                 'application': {
+                    # Custom notification content
                     'api_access_token_enabled': True,
-                    'password': False,
                     'base_url' : None,
-                    'extract_title_as_title': False,
                     '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': [],
                     'ignore_whitespace': True,
-                    'render_anchor_tag_content': False,
-                    'notification_urls': [], # Apprise URL list
-                    # Custom notification content
-                    'notification_title': default_notification_title,
                     'notification_body': default_notification_body,
                     'notification_format': default_notification_format,
+                    'notification_title': default_notification_title,
+                    'notification_urls': [], # Apprise URL list
+                    'pager_size': 50,
+                    'password': False,
+                    'render_anchor_tag_content': False,
+                    'rss_access_token': None,
+                    'rss_hide_muted_watches': True,
                     'schema_version' : 0,
                     'shared_diff_access': False,
-                    'webdriver_delay': None  # Extra delay in seconds before extracting text
+                    'webdriver_delay': None , # Extra delay in seconds before extracting text
+                    'tags': {} #@todo use Tag.model initialisers
                 }
             }
         }
@@ -49,3 +59,15 @@ class model(dict):
     def __init__(self, *arg, **kw):
         super(model, self).__init__(*arg, **kw)
         self.update(self.base_config)
+
+
+def parse_headers_from_text_file(filepath):
+    headers = {}
+    with open(filepath, 'r') as f:
+        for l in f.readlines():
+            l = l.strip()
+            if not l.startswith('#') and ':' in l:
+                (k, v) = l.split(':')
+                headers[k.strip()] = v.strip()
+
+    return headers

changedetectionio/model/Tag.py

@@ -0,0 +1,19 @@
+from .Watch import base_config
+import uuid
+
+class model(dict):
+
+    def __init__(self, *arg, **kw):
+
+        self.update(base_config)
+
+        self['uuid'] = str(uuid.uuid4())
+
+        if kw.get('default'):
+            self.update(kw['default'])
+            del kw['default']
+
+
+        # Goes at the end so we update the default object with the initialiser
+        super(model, self).__init__(*arg, **kw)
+

changedetectionio/model/Watch.py

@@ -1,15 +1,18 @@
-from distutils.util import strtobool
-import logging
+from changedetectionio.strtobool import strtobool
+from changedetectionio.safe_jinja import render as jinja_render
+
 import os
 import re
 import time
 import uuid
+from pathlib import Path
+from loguru import logger
 
 # Allowable protocols, protects against javascript: etc
 # file:// is further checked by ALLOW_FILE_URI
 SAFE_PROTOCOL_REGEX='^(http|https|ftp|file):'
 
-minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
+minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
 mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
 
 from changedetectionio.notification import (
@@ -18,22 +21,33 @@ from changedetectionio.notification import (
 
 base_config = {
     'body': None,
+    'browser_steps': [],
+    'browser_steps_last_error_step': None,
     'check_unique_lines': False,  # On change-detected, compare against all history if its something new
     'check_count': 0,
+    'date_created': None,
     'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
     'extract_text': [],  # Extract text by regex after filters
     'extract_title_as_title': False,
-    'fetch_backend': 'system',
+    'fetch_backend': 'system', # plaintext, playwright etc
+    'fetch_time': 0.0,
+    'processor': 'text_json_diff', # could be restock_diff or others from .processors
     'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
+    'filter_text_added': True,
+    'filter_text_replaced': True,
+    'filter_text_removed': True,
     'has_ldjson_price_data': None,
     'track_ldjson_price_data': None,
     'headers': {},  # Extra headers to send
     'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+    'in_stock' : None,
+    'in_stock_only' : True, # Only trigger change on going to instock from out-of-stock
     'include_filters': [],
     'last_checked': 0,
     'last_error': False,
     'last_viewed': 0,  # history key value of the last viewed via the [diff] link
     'method': 'GET',
+    'notification_alert_count': 0,
     # Custom notification content
     'notification_body': None,
     'notification_format': default_notification_format_for_watch,
@@ -45,13 +59,17 @@ base_config = {
     'previous_md5': False,
     'previous_md5_before_filters': False,  # Used for skipping changedetection entirely
     'proxy': None,  # Preferred proxy connection
+    'remote_server_reply': None, # From 'server' reply header
+    'sort_text_alphabetically': False,
     'subtractive_selectors': [],
-    'tag': None,
+    'tag': '', # Old system of text name for a tag, to be removed
+    'tags': [], # list of UUIDs to App.Tags
     'text_should_not_be_present': [],  # Text that should not present
     # Re #110, so then if this is set to None, we know to use the default value instead
     # Requires setting to None on submit if it's the same as the default
     # Should be all None by default, so we use the system default in this case.
     'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
+    'time_between_check_use_default': True,
     'title': None,
     'trigger_text': [],  # List of text or regex to wait for until a change is detected
     'url': '',
@@ -102,14 +120,15 @@ class model(dict):
 
     @property
     def viewed(self):
-        if int(self['last_viewed']) >= int(self.newest_history_key) :
+        # Don't return viewed when last_viewed is 0 and newest_key is 0
+        if int(self['last_viewed']) and int(self['last_viewed']) >= int(self.newest_history_key) :
             return True
 
         return False
 
     def ensure_data_dir_exists(self):
         if not os.path.isdir(self.watch_data_dir):
-            print ("> Creating data dir {}".format(self.watch_data_dir))
+            logger.debug(f"> Creating data dir {self.watch_data_dir}")
             os.mkdir(self.watch_data_dir)
 
     @property
@@ -121,12 +140,11 @@ class model(dict):
 
         ready_url = url
         if '{%' in url or '{{' in url:
-            from jinja2 import Environment
             # Jinja2 available in URLs along with https://pypi.org/project/jinja2-time/
-            jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
             try:
-                ready_url = str(jinja2_env.from_string(url).render())
+                ready_url = jinja_render(template_str=url)
             except Exception as e:
+                logger.critical(f"Invalid URL template for: '{url}' - {str(e)}")
                 from flask import (
                     flash, Markup, url_for
                 )
@@ -135,8 +153,14 @@ class model(dict):
                 flash(message, 'error')
                 return ''
 
+        if ready_url.startswith('source:'):
+            ready_url=ready_url.replace('source:', '')
         return ready_url
 
+    @property
+    def is_source_type_url(self):
+        return self.get('url', '').startswith('source:')
+
     @property
     def get_fetch_backend(self):
         """
@@ -160,9 +184,7 @@ class model(dict):
     @property
     def label(self):
         # Used for sorting
-        if self['title']:
-            return self['title']
-        return self['url']
+        return self.get('title') if self.get('title') else self.get('url')
 
     @property
     def last_changed(self):
@@ -194,7 +216,7 @@ class model(dict):
         # Read the history file as a dict
         fname = os.path.join(self.watch_data_dir, "history.txt")
         if os.path.isfile(fname):
-            logging.debug("Reading history index " + str(time.time()))
+            logger.debug(f"Reading watch history index for {self.get('uuid')}")
             with open(fname, "r") as f:
                 for i in f.readlines():
                     if ',' in i:
@@ -226,6 +248,14 @@ class model(dict):
         fname = os.path.join(self.watch_data_dir, "history.txt")
         return os.path.isfile(fname)
 
+    @property
+    def has_browser_steps(self):
+        has_browser_steps = self.get('browser_steps') and list(filter(
+            lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+            self.get('browser_steps')))
+
+        return has_browser_steps
+
     # Returns the newest key, but if theres only 1 record, then it's counted as not being new, so return 0.
     @property
     def newest_history_key(self):
@@ -239,27 +269,89 @@ class model(dict):
         bump = self.history
         return self.__newest_history_key
 
+    # Given an arbitrary timestamp, find the closest next key
+    # For example, last_viewed = 1000 so it should return the next 1001 timestamp
+    #
+    # used for the [diff] button so it can preset a smarter from_version
+    @property
+    def get_next_snapshot_key_to_last_viewed(self):
+
+        """Unfortunately for now timestamp is stored as string key"""
+        keys = list(self.history.keys())
+        if not keys:
+            return None
+
+        last_viewed = int(self.get('last_viewed'))
+        prev_k = keys[0]
+        sorted_keys = sorted(keys, key=lambda x: int(x))
+        sorted_keys.reverse()
+
+        # When the 'last viewed' timestamp is greater than the newest snapshot, return second last
+        if last_viewed > int(sorted_keys[0]):
+            return sorted_keys[1]
+
+        for k in sorted_keys:
+            if int(k) < last_viewed:
+                if prev_k == sorted_keys[0]:
+                    # Return the second last one so we dont recommend the same version compares itself
+                    return sorted_keys[1]
+
+                return prev_k
+            prev_k = k
+
+        return keys[0]
+
+    def get_history_snapshot(self, timestamp):
+        import brotli
+        filepath = self.history[timestamp]
+
+        # See if a brotli versions exists and switch to that
+        if not filepath.endswith('.br') and os.path.isfile(f"{filepath}.br"):
+            filepath = f"{filepath}.br"
+
+        # OR in the backup case that the .br does not exist, but the plain one does
+        if filepath.endswith('.br') and not os.path.isfile(filepath):
+            if os.path.isfile(filepath.replace('.br', '')):
+                filepath = filepath.replace('.br', '')
+
+        if filepath.endswith('.br'):
+            # Brotli doesnt have a fileheader to detect it, so we rely on filename
+            # https://www.rfc-editor.org/rfc/rfc7932
+            with open(filepath, 'rb') as f:
+                return(brotli.decompress(f.read()).decode('utf-8'))
+
+        with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+            return f.read()
+
     # Save some text file to the appropriate path and bump the history
     # result_obj from fetch_site_status.run()
     def save_history_text(self, contents, timestamp, snapshot_id):
+        import brotli
 
         self.ensure_data_dir_exists()
 
         # Small hack so that we sleep just enough to allow 1 second  between history snapshots
         # this is because history.txt indexes/keys snapshots by epoch seconds and we dont want dupe keys
         if self.__newest_history_key and int(timestamp) == int(self.__newest_history_key):
-            time.sleep(timestamp - self.__newest_history_key)
+            logger.warning(f"Timestamp {timestamp} already exists, waiting 1 seconds so we have a unique key in history.txt")
+            timestamp = str(int(timestamp) + 1)
+            time.sleep(1)
 
-        snapshot_fname = f"{snapshot_id}.txt"
+        threshold = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
+        skip_brotli = strtobool(os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False'))
 
-        # Only write if it does not exist, this is so that we dont bother re-saving the same data by checksum under different filenames.
-        dest = os.path.join(self.watch_data_dir, snapshot_fname)
-        if not os.path.exists(dest):
-            # in /diff/ and /preview/ we are going to assume for now that it's UTF-8 when reading
-            # most sites are utf-8 and some are even broken utf-8
-            with open(dest, 'wb') as f:
-                f.write(contents)
-                f.close()
+        if not skip_brotli and len(contents) > threshold:
+            snapshot_fname = f"{snapshot_id}.txt.br"
+            dest = os.path.join(self.watch_data_dir, snapshot_fname)
+            if not os.path.exists(dest):
+                with open(dest, 'wb') as f:
+                    f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
+        else:
+            snapshot_fname = f"{snapshot_id}.txt"
+            dest = os.path.join(self.watch_data_dir, snapshot_fname)
+            if not os.path.exists(dest):
+                with open(dest, 'wb') as f:
+                    f.write(contents)
 
         # Append to index
         # @todo check last char was \n
@@ -274,6 +366,7 @@ class model(dict):
         # @todo bump static cache of the last timestamp so we dont need to examine the file to set a proper ''viewed'' status
         return snapshot_fname
 
+    @property
     @property
     def has_empty_checktime(self):
         # using all() + dictionary comprehension
@@ -296,7 +389,8 @@ class model(dict):
         # Compare each lines (set) against each history text file (set) looking for something new..
         existing_history = set({})
         for k, v in self.history.items():
-            alist = set([line.decode('utf-8').strip().lower() for line in open(v, 'rb')])
+            content = self.get_history_snapshot(k)
+            alist = set([line.strip().lower() for line in content.splitlines()])
             existing_history = existing_history.union(alist)
 
         # Check that everything in local_lines(new stuff) already exists in existing_history - it should
@@ -311,17 +405,6 @@ class model(dict):
         # False is not an option for AppRise, must be type None
         return None
 
-    def get_screenshot_as_jpeg(self):
-
-        # Created by save_screenshot()
-        fname = os.path.join(self.watch_data_dir, "last-screenshot.jpg")
-        if os.path.isfile(fname):
-            return fname
-
-        # False is not an option for AppRise, must be type None
-        return None
-
-
     def __get_file_ctime(self, filename):
         fname = os.path.join(self.watch_data_dir, filename)
         if os.path.isfile(fname):
@@ -368,6 +451,7 @@ class model(dict):
             return fname
         return False
 
+
     def pause(self):
         self['paused'] = True
 
@@ -397,8 +481,8 @@ class model(dict):
         # self.history will be keyed with the full path
         for k, fname in self.history.items():
             if os.path.isfile(fname):
-                with open(fname, "r") as f:
-                    contents = f.read()
+                if True:
+                    contents = self.get_history_snapshot(k)
                     res = re.findall(regex, contents, re.MULTILINE)
                     if res:
                         if not csv_writer:
@@ -430,7 +514,48 @@ class model(dict):
 
         return csv_output_filename
 
+
+    def has_special_diff_filter_options_set(self):
+
+        # All False - nothing would be done, so act like it's not processable
+        if not self.get('filter_text_added', True) and not self.get('filter_text_replaced', True) and not self.get('filter_text_removed', True):
+            return False
+
+        # Or one is set
+        if not self.get('filter_text_added', True) or not self.get('filter_text_replaced', True) or not self.get('filter_text_removed', True):
+            return True
+
+        # None is set
+        return False
+
+
+    def get_last_fetched_before_filters(self):
+        import brotli
+        filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
+
+        if not os.path.isfile(filepath):
+            # If a previous attempt doesnt yet exist, just snarf the previous snapshot instead
+            dates = list(self.history.keys())
+            if len(dates):
+                return self.get_history_snapshot(dates[-1])
+            else:
+                return ''
+
+        with open(filepath, 'rb') as f:
+            return(brotli.decompress(f.read()).decode('utf-8'))
+
+    def save_last_fetched_before_filters(self, contents):
+        import brotli
+        filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
+        with open(filepath, 'wb') as f:
+            f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
+
     @property
-    # Return list of tags, stripped and lowercase, used for searching
-    def all_tags(self):
-        return [s.strip().lower() for s in self.get('tag','').split(',')]
+    def get_browsersteps_available_screenshots(self):
+        "For knowing which screenshots are available to show the user in BrowserSteps UI"
+        available = []
+        for f in Path(self.watch_data_dir).glob('step_before-*.jpeg'):
+            step_n=re.search(r'step_before-(\d+)', f.name)
+            if step_n:
+                available.append(step_n.group(1))
+        return available

changedetectionio/notification.py

@@ -1,19 +1,24 @@
 import apprise
-from jinja2 import Environment, BaseLoader
+import time
 from apprise import NotifyFormat
 import json
+from loguru import logger
 
 valid_tokens = {
     'base_url': '',
-    'watch_url': '',
-    'watch_uuid': '',
-    'watch_title': '',
-    'watch_tag': '',
+    'current_snapshot': '',
     'diff': '',
+    'diff_added': '',
     'diff_full': '',
+    'diff_patch': '',
+    'diff_removed': '',
     'diff_url': '',
     'preview_url': '',
-    'current_snapshot': ''
+    'triggered_text': '',
+    'watch_tag': '',
+    'watch_title': '',
+    'watch_url': '',
+    'watch_uuid': '',
 }
 
 default_notification_format_for_watch = 'System default'
@@ -42,6 +47,9 @@ from apprise.decorators import notify
 @notify(on="puts")
 def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
     import requests
+    from apprise.utils import parse_url as apprise_parse_url
+    from apprise import URLBase
+
     url = kwargs['meta'].get('url')
 
     if url.startswith('post'):
@@ -64,141 +72,196 @@ def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
     url = url.replace('delete://', 'http://')
     url = url.replace('deletes://', 'https://')
 
-    # Try to auto-guess if it's JSON
     headers = {}
+    params = {}
+    auth = None
+
+    # Convert /foobar?+some-header=hello to proper header dictionary
+    results = apprise_parse_url(url)
+    if results:
+        # Add our headers that the user can potentially over-ride if they wish
+        # to to our returned result set and tidy entries by unquoting them
+        headers = {URLBase.unquote(x): URLBase.unquote(y)
+                   for x, y in results['qsd+'].items()}
+
+        # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
+        # In Apprise, it relies on prefixing each request arg with "-", because it uses say &method=update as a flag for apprise
+        # but here we are making straight requests, so we need todo convert this against apprise's logic
+        for k, v in results['qsd'].items():
+            if not k.strip('+-') in results['qsd+'].keys():
+                params[URLBase.unquote(k)] = URLBase.unquote(v)
+
+        # Determine Authentication
+        auth = ''
+        if results.get('user') and results.get('password'):
+            auth = (URLBase.unquote(results.get('user')), URLBase.unquote(results.get('user')))
+        elif results.get('user'):
+            auth = (URLBase.unquote(results.get('user')))
+
+    # Try to auto-guess if it's JSON
     try:
         json.loads(body)
-        headers = {'Content-Type': 'application/json; charset=utf-8'}
+        headers['Content-Type'] = 'application/json; charset=utf-8'
     except ValueError as e:
         pass
 
-
-    r(url, headers=headers, data=body)
+    r(results.get('url'),
+      auth=auth,
+      data=body,
+      headers=headers,
+      params=params
+      )
 
 
 def process_notification(n_object, datastore):
 
+    from .safe_jinja import render as jinja_render
+    now = time.time()
+    if n_object.get('notification_timestamp'):
+        logger.trace(f"Time since queued {now-n_object['notification_timestamp']:.3f}s")
     # Insert variables into the notification content
     notification_parameters = create_notification_parameters(n_object, datastore)
 
-    # Get the notification body from datastore
-    jinja2_env = Environment(loader=BaseLoader)
-    n_body = jinja2_env.from_string(n_object.get('notification_body', default_notification_body)).render(**notification_parameters)
-    n_title = jinja2_env.from_string(n_object.get('notification_title', default_notification_title)).render(**notification_parameters)
     n_format = valid_notification_formats.get(
-        n_object['notification_format'],
+        n_object.get('notification_format', default_notification_format),
         valid_notification_formats[default_notification_format],
     )
-    
+
+    # If we arrived with 'System default' then look it up
+    if n_format == default_notification_format_for_watch and datastore.data['settings']['application'].get('notification_format') != default_notification_format_for_watch:
+        # Initially text or whatever
+        n_format = datastore.data['settings']['application'].get('notification_format', valid_notification_formats[default_notification_format])
+
+    logger.trace(f"Complete notification body including Jinja and placeholders calculated in  {time.time() - now:.3f}s")
+
     # https://github.com/caronc/apprise/wiki/Development_LogCapture
     # Anything higher than or equal to WARNING (which covers things like Connection errors)
     # raise it as an exception
-    apobjs=[]
-    sent_objs=[]
+
+    sent_objs = []
     from .apprise_asset import asset
-    for url in n_object['notification_urls']:
-        url = jinja2_env.from_string(url).render(**notification_parameters)
-        apobj = apprise.Apprise(debug=True, asset=asset)
-        url = url.strip()
-        if len(url):
-            print(">> Process Notification: AppRise notifying {}".format(url))
-            with apprise.LogCapture(level=apprise.logging.DEBUG) as logs:
-                # Re 323 - Limit discord length to their 2000 char limit total or it wont send.
-                # Because different notifications may require different pre-processing, run each sequentially :(
-                # 2000 bytes minus -
-                #     200 bytes for the overhead of the _entire_ json payload, 200 bytes for {tts, wait, content} etc headers
-                #     Length of URL - Incase they specify a longer custom avatar_url
+    apobj = apprise.Apprise(debug=True, asset=asset)
 
-                # So if no avatar_url is specified, add one so it can be correctly calculated into the total payload
-                k = '?' if not '?' in url else '&'
-                if not 'avatar_url' in url \
-                        and not url.startswith('mail') \
-                        and not url.startswith('post') \
-                        and not url.startswith('get') \
-                        and not url.startswith('delete') \
-                        and not url.startswith('put'):
-                    url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
+    if not n_object.get('notification_urls'):
+        return None
 
-                if url.startswith('tgram://'):
-                    # Telegram only supports a limit subset of HTML, remove the '<br/>' we place in.
-                    # re https://github.com/dgtlmoon/changedetection.io/issues/555
-                    # @todo re-use an existing library we have already imported to strip all non-allowed tags
-                    n_body = n_body.replace('<br/>', '\n')
-                    n_body = n_body.replace('</br>', '\n')
-                    # real limit is 4096, but minus some for extra metadata
-                    payload_max_size = 3600
-                    body_limit = max(0, payload_max_size - len(n_title))
-                    n_title = n_title[0:payload_max_size]
-                    n_body = n_body[0:body_limit]
+    with apprise.LogCapture(level=apprise.logging.DEBUG) as logs:
+        for url in n_object['notification_urls']:
 
-                elif url.startswith('discord://') or url.startswith('https://discordapp.com/api/webhooks') or url.startswith('https://discord.com/api'):
-                    # real limit is 2000, but minus some for extra metadata
-                    payload_max_size = 1700
-                    body_limit = max(0, payload_max_size - len(n_title))
-                    n_title = n_title[0:payload_max_size]
-                    n_body = n_body[0:body_limit]
+            # Get the notification body from datastore
+            n_body = jinja_render(template_str=n_object.get('notification_body', ''), **notification_parameters)
+            n_title = jinja_render(template_str=n_object.get('notification_title', ''), **notification_parameters)
 
-                elif url.startswith('mailto'):
-                    # Apprise will default to HTML, so we need to override it
-                    # So that whats' generated in n_body is in line with what is going to be sent.
-                    # https://github.com/caronc/apprise/issues/633#issuecomment-1191449321
-                    if not 'format=' in url and (n_format == 'text' or n_format == 'markdown'):
-                        prefix = '?' if not '?' in url else '&'
-                        url = "{}{}format={}".format(url, prefix, n_format)
+            url = url.strip()
+            if not url:
+                logger.warning(f"Process Notification: skipping empty notification URL.")
+                continue
 
-                apobj.add(url)
+            logger.info(">> Process Notification: AppRise notifying {}".format(url))
+            url = jinja_render(template_str=url, **notification_parameters)
 
-                apobj.notify(
-                    title=n_title,
-                    body=n_body,
-                    body_format=n_format,
-                    # False is not an option for AppRise, must be type None
-                    attach=n_object.get('screenshot', None)
-                )
+            # Re 323 - Limit discord length to their 2000 char limit total or it wont send.
+            # Because different notifications may require different pre-processing, run each sequentially :(
+            # 2000 bytes minus -
+            #     200 bytes for the overhead of the _entire_ json payload, 200 bytes for {tts, wait, content} etc headers
+            #     Length of URL - Incase they specify a longer custom avatar_url
 
-                apobj.clear()
+            # So if no avatar_url is specified, add one so it can be correctly calculated into the total payload
+            k = '?' if not '?' in url else '&'
+            if not 'avatar_url' in url \
+                    and not url.startswith('mail') \
+                    and not url.startswith('post') \
+                    and not url.startswith('get') \
+                    and not url.startswith('delete') \
+                    and not url.startswith('put'):
+                url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
 
-                # Incase it needs to exist in memory for a while after to process(?)
-                apobjs.append(apobj)
+            if url.startswith('tgram://'):
+                # Telegram only supports a limit subset of HTML, remove the '<br>' we place in.
+                # re https://github.com/dgtlmoon/changedetection.io/issues/555
+                # @todo re-use an existing library we have already imported to strip all non-allowed tags
+                n_body = n_body.replace('<br>', '\n')
+                n_body = n_body.replace('</br>', '\n')
+                # real limit is 4096, but minus some for extra metadata
+                payload_max_size = 3600
+                body_limit = max(0, payload_max_size - len(n_title))
+                n_title = n_title[0:payload_max_size]
+                n_body = n_body[0:body_limit]
 
-                # Returns empty string if nothing found, multi-line string otherwise
-                log_value = logs.getvalue()
-                if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
-                    raise Exception(log_value)
-                
-                sent_objs.append({'title': n_title,
-                                  'body': n_body,
-                                  'url' : url,
-                                  'body_format': n_format})
+            elif url.startswith('discord://') or url.startswith('https://discordapp.com/api/webhooks') or url.startswith(
+                    'https://discord.com/api'):
+                # real limit is 2000, but minus some for extra metadata
+                payload_max_size = 1700
+                body_limit = max(0, payload_max_size - len(n_title))
+                n_title = n_title[0:payload_max_size]
+                n_body = n_body[0:body_limit]
+
+            elif url.startswith('mailto'):
+                # Apprise will default to HTML, so we need to override it
+                # So that whats' generated in n_body is in line with what is going to be sent.
+                # https://github.com/caronc/apprise/issues/633#issuecomment-1191449321
+                if not 'format=' in url and (n_format == 'Text' or n_format == 'Markdown'):
+                    prefix = '?' if not '?' in url else '&'
+                    # Apprise format is lowercase text https://github.com/caronc/apprise/issues/633
+                    n_format = n_format.lower()
+                    url = f"{url}{prefix}format={n_format}"
+                # If n_format == HTML, then apprise email should default to text/html and we should be sending HTML only
+
+            apobj.add(url)
+
+            sent_objs.append({'title': n_title,
+                              'body': n_body,
+                              'url': url,
+                              'body_format': n_format})
+
+        # Blast off the notifications tht are set in .add()
+        apobj.notify(
+            title=n_title,
+            body=n_body,
+            body_format=n_format,
+            # False is not an option for AppRise, must be type None
+            attach=n_object.get('screenshot', None)
+        )
+
+        # Give apprise time to register an error
+        time.sleep(3)
+
+        # Returns empty string if nothing found, multi-line string otherwise
+        log_value = logs.getvalue()
+
+        if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
+            raise Exception(log_value)
 
     # Return what was sent for better logging - after the for loop
     return sent_objs
 
 
 # Notification title + body content parameters get created here.
+# ( Where we prepare the tokens in the notification to be replaced with actual values )
 def create_notification_parameters(n_object, datastore):
     from copy import deepcopy
 
     # in the case we send a test notification from the main settings, there is no UUID.
     uuid = n_object['uuid'] if 'uuid' in n_object else ''
 
-    if uuid != '':
-        watch_title = datastore.data['watching'][uuid]['title']
-        watch_tag = datastore.data['watching'][uuid]['tag']
+    if uuid:
+        watch_title = datastore.data['watching'][uuid].get('title', '')
+        tag_list = []
+        tags = datastore.get_all_tags_for_watch(uuid)
+        if tags:
+            for tag_uuid, tag in tags.items():
+                tag_list.append(tag.get('title'))
+        watch_tag = ', '.join(tag_list)
     else:
         watch_title = 'Change Detection'
         watch_tag = ''
 
     # Create URLs to customise the notification with
-    base_url = datastore.data['settings']['application']['base_url']
+    # active_base_url - set in store.py data property
+    base_url = datastore.data['settings']['application'].get('active_base_url')
 
     watch_url = n_object['watch_url']
 
-    # Re #148 - Some people have just {{ base_url }} in the body or title, but this may break some notification services
-    #           like 'Join', so it's always best to atleast set something obvious so that they are not broken.
-    if base_url == '':
-        base_url = "<base-url-env-var-not-set>"
-
     diff_url = "{}/diff/{}".format(base_url, uuid)
     preview_url = "{}/preview/{}".format(base_url, uuid)
 
@@ -208,16 +271,20 @@ def create_notification_parameters(n_object, datastore):
     # Valid_tokens also used as a field validator
     tokens.update(
         {
-            'base_url': base_url if base_url is not None else '',
+            'base_url': base_url,
+            'current_snapshot': n_object.get('current_snapshot', ''),
+            'diff': n_object.get('diff', ''),  # Null default in the case we use a test
+            'diff_added': n_object.get('diff_added', ''),  # Null default in the case we use a test
+            'diff_full': n_object.get('diff_full', ''),  # Null default in the case we use a test
+            'diff_patch': n_object.get('diff_patch', ''),  # Null default in the case we use a test
+            'diff_removed': n_object.get('diff_removed', ''),  # Null default in the case we use a test
+            'diff_url': diff_url,
+            'preview_url': preview_url,
+            'triggered_text': n_object.get('triggered_text', ''),
+            'watch_tag': watch_tag if watch_tag is not None else '',
+            'watch_title': watch_title if watch_title is not None else '',
             'watch_url': watch_url,
             'watch_uuid': uuid,
-            'watch_title': watch_title if watch_title is not None else '',
-            'watch_tag': watch_tag if watch_tag is not None else '',
-            'diff_url': diff_url,
-            'diff': n_object.get('diff', ''),  # Null default in the case we use a test
-            'diff_full': n_object.get('diff_full', ''),  # Null default in the case we use a test
-            'preview_url': preview_url,
-            'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else ''
         })
 
     return tokens

changedetectionio/processors/README.md

@@ -0,0 +1,11 @@
+# Change detection post-processors
+
+The concept here is to be able to switch between different domain specific problems to solve.
+
+- `text_json_diff` The traditional text and JSON comparison handler
+- `restock_diff` Only cares about detecting if a product looks like it has some text that suggests that it's out of stock, otherwise assumes that it's in stock.
+
+Some suggestions for the future
+
+- `graphical` 
+- `restock_and_price` - extract price AND stock text

changedetectionio/processors/__init__.py

@@ -0,0 +1,153 @@
+from abc import abstractmethod
+from changedetectionio.strtobool import strtobool
+from copy import deepcopy
+from loguru import logger
+import hashlib
+import os
+import re
+
+class difference_detection_processor():
+
+    browser_steps = None
+    datastore = None
+    fetcher = None
+    screenshot = None
+    watch = None
+    xpath_data = None
+
+    def __init__(self, *args, datastore, watch_uuid, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.datastore = datastore
+        self.watch = deepcopy(self.datastore.data['watching'].get(watch_uuid))
+
+    def call_browser(self):
+        from requests.structures import CaseInsensitiveDict
+        # Protect against file:// access
+        if re.search(r'^file://', self.watch.get('url', '').strip(), re.IGNORECASE):
+            if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
+                raise Exception(
+                    "file:// type access is denied for security reasons."
+                )
+
+        url = self.watch.link
+
+        # Requests, playwright, other browser via wss:// etc, fetch_extra_something
+        prefer_fetch_backend = self.watch.get('fetch_backend', 'system')
+
+        # Proxy ID "key"
+        preferred_proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=self.watch.get('uuid'))
+
+        # Pluggable content self.fetcher
+        if not prefer_fetch_backend or prefer_fetch_backend == 'system':
+            prefer_fetch_backend = self.datastore.data['settings']['application'].get('fetch_backend')
+
+        # In the case that the preferred fetcher was a browser config with custom connection URL..
+        # @todo - on save watch, if its extra_browser_ then it should be obvious it will use playwright (like if its requests now..)
+        custom_browser_connection_url = None
+        if prefer_fetch_backend.startswith('extra_browser_'):
+            (t, key) = prefer_fetch_backend.split('extra_browser_')
+            connection = list(
+                filter(lambda s: (s['browser_name'] == key), self.datastore.data['settings']['requests'].get('extra_browsers', [])))
+            if connection:
+                prefer_fetch_backend = 'html_webdriver'
+                custom_browser_connection_url = connection[0].get('browser_connection_url')
+
+        # PDF should be html_requests because playwright will serve it up (so far) in a embedded page
+        # @todo https://github.com/dgtlmoon/changedetection.io/issues/2019
+        # @todo needs test to or a fix
+        if self.watch.is_pdf:
+           prefer_fetch_backend = "html_requests"
+
+        # Grab the right kind of 'fetcher', (playwright, requests, etc)
+        from changedetectionio import content_fetchers
+        if hasattr(content_fetchers, prefer_fetch_backend):
+            # @todo TEMPORARY HACK - SWITCH BACK TO PLAYWRIGHT FOR BROWSERSTEPS
+            if prefer_fetch_backend == 'html_webdriver' and self.watch.has_browser_steps:
+                # This is never supported in selenium anyway
+                logger.warning("Using playwright fetcher override for possible puppeteer request in browsersteps, because puppetteer:browser steps is incomplete.")
+                from changedetectionio.content_fetchers.playwright import fetcher as playwright_fetcher
+                fetcher_obj = playwright_fetcher
+            else:
+                fetcher_obj = getattr(content_fetchers, prefer_fetch_backend)
+        else:
+            # What it referenced doesnt exist, Just use a default
+            fetcher_obj = getattr(content_fetchers, "html_requests")
+
+        proxy_url = None
+        if preferred_proxy_id:
+            # Custom browser endpoints should NOT have a proxy added
+            if not prefer_fetch_backend.startswith('extra_browser_'):
+                proxy_url = self.datastore.proxy_list.get(preferred_proxy_id).get('url')
+                logger.debug(f"Selected proxy key '{preferred_proxy_id}' as proxy URL '{proxy_url}' for {url}")
+            else:
+                logger.debug(f"Skipping adding proxy data when custom Browser endpoint is specified. ")
+
+        # Now call the fetcher (playwright/requests/etc) with arguments that only a fetcher would need.
+        # When browser_connection_url is None, it method should default to working out whats the best defaults (os env vars etc)
+        self.fetcher = fetcher_obj(proxy_override=proxy_url,
+                                   custom_browser_connection_url=custom_browser_connection_url
+                                   )
+
+        if self.watch.has_browser_steps:
+            self.fetcher.browser_steps = self.watch.get('browser_steps', [])
+            self.fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, self.watch.get('uuid'))
+
+        # Tweak the base config with the per-watch ones
+        request_headers = CaseInsensitiveDict()
+
+        ua = self.datastore.data['settings']['requests'].get('default_ua')
+        if ua and ua.get(prefer_fetch_backend):
+            request_headers.update({'User-Agent': ua.get(prefer_fetch_backend)})
+
+        request_headers.update(self.watch.get('headers', {}))
+        request_headers.update(self.datastore.get_all_base_headers())
+        request_headers.update(self.datastore.get_all_headers_in_textfile_for_watch(uuid=self.watch.get('uuid')))
+
+        # https://github.com/psf/requests/issues/4525
+        # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
+        # do this by accident.
+        if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
+            request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
+
+        timeout = self.datastore.data['settings']['requests'].get('timeout')
+
+        request_body = self.watch.get('body')
+        request_method = self.watch.get('method')
+        ignore_status_codes = self.watch.get('ignore_status_codes', False)
+
+        # Configurable per-watch or global extra delay before extracting text (for webDriver types)
+        system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
+        if self.watch.get('webdriver_delay'):
+            self.fetcher.render_extract_delay = self.watch.get('webdriver_delay')
+        elif system_webdriver_delay is not None:
+            self.fetcher.render_extract_delay = system_webdriver_delay
+
+        if self.watch.get('webdriver_js_execute_code') is not None and self.watch.get('webdriver_js_execute_code').strip():
+            self.fetcher.webdriver_js_execute_code = self.watch.get('webdriver_js_execute_code')
+
+        # Requests for PDF's, images etc should be passwd the is_binary flag
+        is_binary = self.watch.is_pdf
+
+        # And here we go! call the right browser with browser-specific settings
+        self.fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, self.watch.get('include_filters'),
+                    is_binary=is_binary)
+
+        #@todo .quit here could go on close object, so we can run JS if change-detected
+        self.fetcher.quit()
+
+        # After init, call run_changedetection() which will do the actual change-detection
+
+    @abstractmethod
+    def run_changedetection(self, uuid, skip_when_checksum_same=True):
+        update_obj = {'last_notification_error': False, 'last_error': False}
+        some_data = 'xxxxx'
+        update_obj["previous_md5"] = hashlib.md5(some_data.encode('utf-8')).hexdigest()
+        changed_detected = False
+        return changed_detected, update_obj, ''.encode('utf-8')
+
+
+def available_processors():
+    from . import restock_diff, text_json_diff
+    x=[('text_json_diff', text_json_diff.name), ('restock_diff', restock_diff.name)]
+    # @todo Make this smarter with introspection of sorts.
+    return x

changedetectionio/processors/restock_diff.py

@@ -0,0 +1,66 @@
+
+from . import difference_detection_processor
+from copy import deepcopy
+from loguru import logger
+import hashlib
+import urllib3
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+name = 'Re-stock detection for single product pages'
+description = 'Detects if the product goes back to in-stock'
+
+class UnableToExtractRestockData(Exception):
+    def __init__(self, status_code):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        return
+
+class perform_site_check(difference_detection_processor):
+    screenshot = None
+    xpath_data = None
+
+    def run_changedetection(self, uuid, skip_when_checksum_same=True):
+
+        # DeepCopy so we can be sure we don't accidently change anything by reference
+        watch = deepcopy(self.datastore.data['watching'].get(uuid))
+
+        if not watch:
+            raise Exception("Watch no longer exists.")
+
+        # Unset any existing notification error
+        update_obj = {'last_notification_error': False, 'last_error': False}
+
+        self.screenshot = self.fetcher.screenshot
+        self.xpath_data = self.fetcher.xpath_data
+
+        # Track the content type
+        update_obj['content_type'] = self.fetcher.headers.get('Content-Type', '')
+        update_obj["last_check_status"] = self.fetcher.get_last_status_code()
+
+        # Main detection method
+        fetched_md5 = None
+        if self.fetcher.instock_data:
+            fetched_md5 = hashlib.md5(self.fetcher.instock_data.encode('utf-8')).hexdigest()
+            # 'Possibly in stock' comes from stock-not-in-stock.js when no string found above the fold.
+            update_obj["in_stock"] = True if self.fetcher.instock_data == 'Possibly in stock' else False
+            logger.debug(f"Watch UUID {uuid} restock check returned '{self.fetcher.instock_data}' from JS scraper.")
+        else:
+            raise UnableToExtractRestockData(status_code=self.fetcher.status_code)
+
+        # The main thing that all this at the moment comes down to :)
+        changed_detected = False
+        logger.debug(f"Watch UUID {uuid} restock check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
+
+        if watch.get('previous_md5') and watch.get('previous_md5') != fetched_md5:
+            # Yes if we only care about it going to instock, AND we are in stock
+            if watch.get('in_stock_only') and update_obj["in_stock"]:
+                changed_detected = True
+
+            if not watch.get('in_stock_only'):
+                # All cases
+                changed_detected = True
+
+        # Always record the new checksum
+        update_obj["previous_md5"] = fetched_md5
+        return changed_detected, update_obj, self.fetcher.instock_data.encode('utf-8').strip()

changedetectionio/processors/text_json_diff.py

@@ -1,21 +1,30 @@
+# HTML to TEXT/JSON DIFFERENCE self.fetcher
+
 import hashlib
 import json
-import logging
 import os
 import re
 import urllib3
 
-from changedetectionio import content_fetcher, html_tools
+from . import difference_detection_processor
+from ..html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text
+from changedetectionio import html_tools, content_fetchers
 from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
+import changedetectionio.content_fetchers
 from copy import deepcopy
+from loguru import logger
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
+name = 'Webpage Text/HTML, JSON and PDF changes'
+description = 'Detects all text changes where possible'
+json_filter_prefixes = ['json:', 'jq:']
 
 class FilterNotFoundInResponse(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
 
+
 class PDFToHTMLToolNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
@@ -23,129 +32,38 @@ class PDFToHTMLToolNotFound(ValueError):
 
 # Some common stuff here that can be moved to a base class
 # (set_proxy_from_list)
-class perform_site_check():
-    screenshot = None
-    xpath_data = None
+class perform_site_check(difference_detection_processor):
 
-    def __init__(self, *args, datastore, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.datastore = datastore
-
-    # Doesn't look like python supports forward slash auto enclosure in re.findall
-    # So convert it to inline flag "foobar(?i)" type configuration
-    def forward_slash_enclosed_regex_to_options(self, regex):
-        res = re.search(r'^/(.*?)/(\w+)$', regex, re.IGNORECASE)
-
-        if res:
-            regex = res.group(1)
-            regex += '(?{})'.format(res.group(2))
-        else:
-            regex += '(?{})'.format('i')
-
-        return regex
-
-    def run(self, uuid, skip_when_checksum_same=True):
+    def run_changedetection(self, uuid, skip_when_checksum_same=True):
         changed_detected = False
+        html_content = ""
         screenshot = False  # as bytes
         stripped_text_from_html = ""
 
         # DeepCopy so we can be sure we don't accidently change anything by reference
         watch = deepcopy(self.datastore.data['watching'].get(uuid))
-
         if not watch:
-            return
-
-        # Protect against file:// access
-        if re.search(r'^file', watch.get('url', ''), re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
-            raise Exception(
-                "file:// type access is denied for security reasons."
-            )
+            raise Exception("Watch no longer exists.")
 
         # Unset any existing notification error
         update_obj = {'last_notification_error': False, 'last_error': False}
 
-        extra_headers = watch.get('headers', [])
-
-        # Tweak the base config with the per-watch ones
-        request_headers = deepcopy(self.datastore.data['settings']['headers'])
-        request_headers.update(extra_headers)
-
-        # https://github.com/psf/requests/issues/4525
-        # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
-        # do this by accident.
-        if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
-            request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
-
-        timeout = self.datastore.data['settings']['requests'].get('timeout')
-
         url = watch.link
 
-        request_body = self.datastore.data['watching'][uuid].get('body')
-        request_method = self.datastore.data['watching'][uuid].get('method')
-        ignore_status_codes = self.datastore.data['watching'][uuid].get('ignore_status_codes', False)
-
-        # source: support
-        is_source = False
-        if url.startswith('source:'):
-            url = url.replace('source:', '')
-            is_source = True
-
-        # Pluggable content fetcher
-        prefer_backend = watch.get_fetch_backend
-        if not prefer_backend or prefer_backend == 'system':
-            prefer_backend = self.datastore.data['settings']['application']['fetch_backend']
-
-        if hasattr(content_fetcher, prefer_backend):
-            klass = getattr(content_fetcher, prefer_backend)
-        else:
-            # If the klass doesnt exist, just use a default
-            klass = getattr(content_fetcher, "html_requests")
-
-        proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=uuid)
-        proxy_url = None
-        if proxy_id:
-            proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
-            print("UUID {} Using proxy {}".format(uuid, proxy_url))
-
-        fetcher = klass(proxy_override=proxy_url)
-
-        # Configurable per-watch or global extra delay before extracting text (for webDriver types)
-        system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
-        if watch['webdriver_delay'] is not None:
-            fetcher.render_extract_delay = watch.get('webdriver_delay')
-        elif system_webdriver_delay is not None:
-            fetcher.render_extract_delay = system_webdriver_delay
-
-        # Possible conflict
-        if prefer_backend == 'html_webdriver':
-            fetcher.browser_steps = watch.get('browser_steps', None)
-            fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, uuid)
-
-        if watch.get('webdriver_js_execute_code') is not None and watch.get('webdriver_js_execute_code').strip():
-            fetcher.webdriver_js_execute_code = watch.get('webdriver_js_execute_code')
-
-        # requests for PDF's, images etc should be passwd the is_binary flag
-        is_binary = watch.is_pdf
-
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'), is_binary=is_binary)
-        fetcher.quit()
-
-        self.screenshot = fetcher.screenshot
-        self.xpath_data = fetcher.xpath_data
+        self.screenshot = self.fetcher.screenshot
+        self.xpath_data = self.fetcher.xpath_data
 
         # Track the content type
-        update_obj['content_type'] = fetcher.headers.get('Content-Type', '')
+        update_obj['content_type'] = self.fetcher.get_all_headers().get('content-type', '').lower()
 
         # Watches added automatically in the queue manager will skip if its the same checksum as the previous run
         # Saves a lot of CPU
-        update_obj['previous_md5_before_filters'] = hashlib.md5(fetcher.content.encode('utf-8')).hexdigest()
+        update_obj['previous_md5_before_filters'] = hashlib.md5(self.fetcher.content.encode('utf-8')).hexdigest()
         if skip_when_checksum_same:
             if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
-                raise content_fetcher.checksumFromPreviousCheckWasTheSame()
-
+                raise content_fetchers.exceptions.checksumFromPreviousCheckWasTheSame()
 
         # Fetching complete, now filters
-        # @todo move to class / maybe inside of fetcher abstract base?
 
         # @note: I feel like the following should be in a more obvious chain system
         #  - Check filter text
@@ -154,15 +72,24 @@ class perform_site_check():
         # https://stackoverflow.com/questions/41817578/basic-method-chaining ?
         # return content().textfilter().jsonextract().checksumcompare() ?
 
-        is_json = 'application/json' in fetcher.headers.get('Content-Type', '')
+        is_json = 'application/json' in self.fetcher.get_all_headers().get('content-type', '').lower()
         is_html = not is_json
+        is_rss = False
+
+        ctype_header = self.fetcher.get_all_headers().get('content-type', '').lower()
+        # Go into RSS preprocess for converting CDATA/comment to usable text
+        if any(substring in ctype_header for substring in ['application/xml', 'application/rss', 'text/xml']):
+            if '<rss' in self.fetcher.content[:100].lower():
+                self.fetcher.content = cdata_in_document_to_text(html_content=self.fetcher.content)
+                is_rss = True
 
         # source: support, basically treat it as plaintext
-        if is_source:
+        if watch.is_source_type_url:
             is_html = False
             is_json = False
 
-        if watch.is_pdf or 'application/pdf' in fetcher.headers.get('Content-Type', '').lower():
+        inline_pdf = self.fetcher.get_all_headers().get('content-disposition', '') and '%PDF-1' in self.fetcher.content[:10]
+        if watch.is_pdf or 'application/pdf' in self.fetcher.get_all_headers().get('content-type', '').lower() or inline_pdf:
             from shutil import which
             tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
             if not which(tool):
@@ -173,34 +100,38 @@ class perform_site_check():
                 [tool, '-stdout', '-', '-s', 'out.pdf', '-i'],
                 stdout=subprocess.PIPE,
                 stdin=subprocess.PIPE)
-            proc.stdin.write(fetcher.raw_content)
+            proc.stdin.write(self.fetcher.raw_content)
             proc.stdin.close()
-            fetcher.content = proc.stdout.read().decode('utf-8')
+            self.fetcher.content = proc.stdout.read().decode('utf-8')
             proc.wait(timeout=60)
 
             # Add a little metadata so we know if the file changes (like if an image changes, but the text is the same
             # @todo may cause problems with non-UTF8?
             metadata = "<p>Added by changedetection.io: Document checksum - {} Filesize - {} bytes</p>".format(
-                hashlib.md5(fetcher.raw_content).hexdigest().upper(),
-                len(fetcher.content))
+                hashlib.md5(self.fetcher.raw_content).hexdigest().upper(),
+                len(self.fetcher.content))
 
-            fetcher.content = fetcher.content.replace('</body>', metadata + '</body>')
+            self.fetcher.content = self.fetcher.content.replace('</body>', metadata + '</body>')
 
+        # Better would be if Watch.model could access the global data also
+        # and then use getattr https://docs.python.org/3/reference/datamodel.html#object.__getitem__
+        # https://realpython.com/inherit-python-dict/ instead of doing it procedurely
+        include_filters_from_tags = self.datastore.get_tag_overrides_for_watch(uuid=uuid, attr='include_filters')
 
-        include_filters_rule = deepcopy(watch.get('include_filters', []))
-        # include_filters_rule = watch['include_filters']
-        subtractive_selectors = watch.get(
-            "subtractive_selectors", []
-        ) + self.datastore.data["settings"]["application"].get(
-            "global_subtractive_selectors", []
-        )
+        # 1845 - remove duplicated filters in both group and watch include filter
+        include_filters_rule = list(dict.fromkeys(watch.get('include_filters', []) + include_filters_from_tags))
+
+        subtractive_selectors = [*self.datastore.get_tag_overrides_for_watch(uuid=uuid, attr='subtractive_selectors'),
+                                 *watch.get("subtractive_selectors", []),
+                                 *self.datastore.data["settings"]["application"].get("global_subtractive_selectors", [])
+                                 ]
 
         # Inject a virtual LD+JSON price tracker rule
         if watch.get('track_ldjson_price_data', '') == PRICE_DATA_TRACK_ACCEPT:
-            include_filters_rule.append(html_tools.LD_JSON_PRODUCT_OFFER_SELECTOR)
+            include_filters_rule += html_tools.LD_JSON_PRODUCT_OFFER_SELECTORS
 
-        has_filter_rule = include_filters_rule and len("".join(include_filters_rule).strip())
-        has_subtractive_selectors = subtractive_selectors and len(subtractive_selectors[0].strip())
+        has_filter_rule = len(include_filters_rule) and len(include_filters_rule[0].strip())
+        has_subtractive_selectors = len(subtractive_selectors) and len(subtractive_selectors[0].strip())
 
         if is_json and not has_filter_rule:
             include_filters_rule.append("json:$")
@@ -209,33 +140,30 @@ class perform_site_check():
         if is_json:
             # Sort the JSON so we dont get false alerts when the content is just re-ordered
             try:
-                fetcher.content = json.dumps(json.loads(fetcher.content), sort_keys=True)
+                self.fetcher.content = json.dumps(json.loads(self.fetcher.content), sort_keys=True)
             except Exception as e:
                 # Might have just been a snippet, or otherwise bad JSON, continue
                 pass
 
         if has_filter_rule:
-            json_filter_prefixes = ['json:', 'jq:']
             for filter in include_filters_rule:
                 if any(prefix in filter for prefix in json_filter_prefixes):
-                    stripped_text_from_html += html_tools.extract_json_as_string(content=fetcher.content, json_filter=filter)
+                    stripped_text_from_html += html_tools.extract_json_as_string(content=self.fetcher.content, json_filter=filter)
                     is_html = False
 
-
-
-        if is_html or is_source:
+        if is_html or watch.is_source_type_url:
 
             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-            fetcher.content = html_tools.workarounds_for_obfuscations(fetcher.content)
-            html_content = fetcher.content
+            self.fetcher.content = html_tools.workarounds_for_obfuscations(self.fetcher.content)
+            html_content = self.fetcher.content
 
             # If not JSON,  and if it's not text/plain..
-            if 'text/plain' in fetcher.headers.get('Content-Type', '').lower():
+            if 'text/plain' in self.fetcher.get_all_headers().get('content-type', '').lower():
                 # Don't run get_text or xpath/css filters on plaintext
                 stripped_text_from_html = html_content
             else:
                 # Does it have some ld+json price data? used for easier monitoring
-                update_obj['has_ldjson_price_data'] = html_tools.has_ldjson_product_info(fetcher.content)
+                update_obj['has_ldjson_price_data'] = html_tools.has_ldjson_product_info(self.fetcher.content)
 
                 # Then we assume HTML
                 if has_filter_rule:
@@ -245,13 +173,19 @@ class perform_site_check():
                         # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
                         if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
                             html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
-                                                                    html_content=fetcher.content,
-                                                                    append_pretty_line_formatting=not is_source)
+                                                                    html_content=self.fetcher.content,
+                                                                    append_pretty_line_formatting=not watch.is_source_type_url,
+                                                                    is_rss=is_rss)
+                        elif filter_rule.startswith('xpath1:'):
+                            html_content += html_tools.xpath1_filter(xpath_filter=filter_rule.replace('xpath1:', ''),
+                                                                    html_content=self.fetcher.content,
+                                                                    append_pretty_line_formatting=not watch.is_source_type_url,
+                                                                    is_rss=is_rss)
                         else:
                             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
                             html_content += html_tools.include_filters(include_filters=filter_rule,
-                                                                       html_content=fetcher.content,
-                                                                       append_pretty_line_formatting=not is_source)
+                                                                       html_content=self.fetcher.content,
+                                                                       append_pretty_line_formatting=not watch.is_source_type_url)
 
                     if not html_content.strip():
                         raise FilterNotFoundInResponse(include_filters_rule)
@@ -259,29 +193,68 @@ class perform_site_check():
                 if has_subtractive_selectors:
                     html_content = html_tools.element_removal(subtractive_selectors, html_content)
 
-                if is_source:
+                if watch.is_source_type_url:
                     stripped_text_from_html = html_content
                 else:
                     # extract text
                     do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
                     stripped_text_from_html = \
                         html_tools.html_to_text(
-                            html_content,
-                            render_anchor_tag_content=do_anchor
+                            html_content=html_content,
+                            render_anchor_tag_content=do_anchor,
+                            is_rss=is_rss # #1874 activate the <title workaround hack
                         )
 
+        if watch.get('sort_text_alphabetically') and stripped_text_from_html:
+            # Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap
+            # we end up with 'Some text\n\n', sorting will add all those extra \n at the start, so we remove them here.
+            stripped_text_from_html = stripped_text_from_html.replace('\n\n', '\n')
+            stripped_text_from_html = '\n'.join( sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower() ))
+
         # Re #340 - return the content before the 'ignore text' was applied
         text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
+        # @todo whitespace coming from missing rtrim()?
+        # stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
+        # Rewrite's the processing text based on only what diff result they want to see
+        if watch.has_special_diff_filter_options_set() and len(watch.history.keys()):
+            # Now the content comes from the diff-parser and not the returned HTTP traffic, so could be some differences
+            from .. import diff
+            # needs to not include (added) etc or it may get used twice
+            # Replace the processed text with the preferred result
+            rendered_diff = diff.render_diff(previous_version_file_contents=watch.get_last_fetched_before_filters(),
+                                             newest_version_file_contents=stripped_text_from_html,
+                                             include_equal=False,  # not the same lines
+                                             include_added=watch.get('filter_text_added', True),
+                                             include_removed=watch.get('filter_text_removed', True),
+                                             include_replaced=watch.get('filter_text_replaced', True),
+                                             line_feed_sep="\n",
+                                             include_change_type_prefix=False)
+
+            watch.save_last_fetched_before_filters(text_content_before_ignored_filter)
+
+            if not rendered_diff and stripped_text_from_html:
+                # We had some content, but no differences were found
+                # Store our new file as the MD5 so it will trigger in the future
+                c = hashlib.md5(text_content_before_ignored_filter.translate(None, b'\r\n\t ')).hexdigest()
+                return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8')
+            else:
+                stripped_text_from_html = rendered_diff
+
         # Treat pages with no renderable text content as a change? No by default
         empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
         if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
-            raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot)
+            raise content_fetchers.exceptions.ReplyWithContentButNoText(url=url,
+                                                            status_code=self.fetcher.get_last_status_code(),
+                                                            screenshot=screenshot,
+                                                            has_filters=has_filter_rule,
+                                                            html_content=html_content
+                                                            )
 
         # We rely on the actual text in the html output.. many sites have random script vars etc,
         # in the future we'll implement other mechanisms.
 
-        update_obj["last_check_status"] = fetcher.get_last_status_code()
+        update_obj["last_check_status"] = self.fetcher.get_last_status_code()
 
         # If there's text to skip
         # @todo we could abstract out the get_text() to handle this cleaner
@@ -297,16 +270,25 @@ class perform_site_check():
             regex_matched_output = []
             for s_re in extract_text:
                 # incase they specified something in '/.../x'
-                regex = self.forward_slash_enclosed_regex_to_options(s_re)
-                result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
+                if re.search(PERL_STYLE_REGEX, s_re, re.IGNORECASE):
+                    regex = html_tools.perl_style_slash_enclosed_regex_to_options(s_re)
+                    result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
 
-                for l in result:
-                    if type(l) is tuple:
-                        # @todo - some formatter option default (between groups)
-                        regex_matched_output += list(l) + [b'\n']
-                    else:
-                        # @todo - some formatter option default (between each ungrouped result)
-                        regex_matched_output += [l] + [b'\n']
+                    for l in result:
+                        if type(l) is tuple:
+                            # @todo - some formatter option default (between groups)
+                            regex_matched_output += list(l) + [b'\n']
+                        else:
+                            # @todo - some formatter option default (between each ungrouped result)
+                            regex_matched_output += [l] + [b'\n']
+                else:
+                    # Doesnt look like regex, just hunt for plaintext and return that which matches
+                    # `stripped_text_from_html` will be bytes, so we must encode s_re also to bytes
+                    r = re.compile(re.escape(s_re.encode('utf-8')), re.IGNORECASE)
+                    res = r.findall(stripped_text_from_html)
+                    if res:
+                        for match in res:
+                            regex_matched_output += [match] + [b'\n']
 
             # Now we will only show what the regex matched
             stripped_text_from_html = b''
@@ -331,6 +313,7 @@ class perform_site_check():
             blocked = True
             # Filter and trigger works the same, so reuse it
             # It should return the line numbers that match
+            # Unblock flow if the trigger was found (some text remained after stripped what didnt match)
             result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
                                                   wordlist=trigger_text,
                                                   mode="line numbers")
@@ -359,17 +342,19 @@ class perform_site_check():
         if is_html:
             if self.datastore.data['settings']['application'].get('extract_title_as_title') or watch['extract_title_as_title']:
                 if not watch['title'] or not len(watch['title']):
-                    update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
+                    update_obj['title'] = html_tools.extract_element(find='title', html_content=self.fetcher.content)
+
+        logger.debug(f"Watch UUID {uuid} content check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
 
         if changed_detected:
             if watch.get('check_unique_lines', False):
                 has_unique_lines = watch.lines_contain_something_unique_compared_to_history(lines=stripped_text_from_html.splitlines())
                 # One or more lines? unsure?
                 if not has_unique_lines:
-                    logging.debug("check_unique_lines: UUID {} didnt have anything new setting change_detected=False".format(uuid))
+                    logger.debug(f"check_unique_lines: UUID {uuid} didnt have anything new setting change_detected=False")
                     changed_detected = False
                 else:
-                    logging.debug("check_unique_lines: UUID {} had unique content".format(uuid))
+                    logger.debug(f"check_unique_lines: UUID {uuid} had unique content")
 
         # Always record the new checksum
         update_obj["previous_md5"] = fetched_md5

changedetectionio/run_basic_tests.sh

@@ -28,3 +28,11 @@ pytest tests/test_notification.py
 # Re-run with HIDE_REFERER set - could affect login
 export HIDE_REFERER=True
 pytest tests/test_access_control.py
+
+# Re-run a few tests that will trigger brotli based storage
+export SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD=5
+pytest tests/test_access_control.py
+pytest tests/test_notification.py
+pytest tests/test_backend.py
+pytest tests/test_rss.py
+pytest tests/test_unique_lines.py

changedetectionio/run_custom_browser_url_tests.sh

@@ -0,0 +1,46 @@
+#!/bin/bash
+
+# run some tests and look if the 'custom-browser-search-string=1' connect string appeared in the correct containers
+
+# @todo do it again but with the puppeteer one
+
+# enable debug
+set -x
+
+# A extra browser is configured, but we never chose to use it, so it should NOT show in the logs
+docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/custom_browser_url/test_custom_browser_url.py::test_request_not_via_custom_browser_url'
+docker logs sockpuppetbrowser-custom-url &>log-custom.txt
+grep 'custom-browser-search-string=1' log-custom.txt
+if [ $? -ne 1 ]
+then
+  echo "Saw a request in 'sockpuppetbrowser-custom-url' container with 'custom-browser-search-string=1' when I should not - log-custom.txt"
+  exit 1
+fi
+
+docker logs sockpuppetbrowser &>log.txt
+grep 'custom-browser-search-string=1' log.txt
+if [ $? -ne 1 ]
+then
+  echo "Saw a request in 'browser' container with 'custom-browser-search-string=1' when I should not"
+  exit 1
+fi
+
+# Special connect string should appear in the custom-url container, but not in the 'default' one
+docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/custom_browser_url/test_custom_browser_url.py::test_request_via_custom_browser_url'
+docker logs sockpuppetbrowser-custom-url &>log-custom.txt
+grep 'custom-browser-search-string=1' log-custom.txt
+if [ $? -ne 0 ]
+then
+  echo "Did not see request in 'sockpuppetbrowser-custom-url' container with 'custom-browser-search-string=1' when I should - log-custom.txt"
+  exit 1
+fi
+
+docker logs sockpuppetbrowser &>log.txt
+grep 'custom-browser-search-string=1' log.txt
+if [ $? -ne 1 ]
+then
+  echo "Saw a request in 'browser' container with 'custom-browser-search-string=1' when I should not"
+  exit 1
+fi
+
+

changedetectionio/run_proxy_tests.sh

@@ -2,13 +2,15 @@
 
 # exit when any command fails
 set -e
+# enable debug
+set -x
 
 # Test proxy list handling, starting two squids on different ports
 # Each squid adds a different header to the response, which is the main thing we test for.
 docker run --network changedet-network -d --name squid-one --hostname squid-one --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
 docker run --network changedet-network -d --name squid-two --hostname squid-two --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
 
-# Used for configuring a custom proxy URL via the UI
+# Used for configuring a custom proxy URL via the UI - with username+password auth
 docker run --network changedet-network -d \
   --name squid-custom \
   --hostname squid-custom \
@@ -19,21 +21,22 @@ docker run --network changedet-network -d \
 
 
 ## 2nd test actually choose the preferred proxy from proxies.json
-
 docker run --network changedet-network \
   -v `pwd`/tests/proxy_list/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
   test-changedetectionio \
   bash -c 'cd changedetectionio && pytest tests/proxy_list/test_multiple_proxy.py'
 
-
-## Should be a request in the default "first" squid
+set +e
+echo "- Looking for chosen.changedetection.io request in squid-one - it should NOT be here"
 docker logs squid-one 2>/dev/null|grep chosen.changedetection.io
-if [ $? -ne 0 ]
+if [ $? -ne 1 ]
 then
-  echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy - squid one)"
+  echo "Saw a request to chosen.changedetection.io in the squid logs (while checking preferred proxy - squid one) WHEN I SHOULD NOT"
   exit 1
 fi
 
+set -e
+echo "- Looking for chosen.changedetection.io request in squid-two"
 # And one in the 'second' squid (user selects this as preferred)
 docker logs squid-two 2>/dev/null|grep chosen.changedetection.io
 if [ $? -ne 0 ]
@@ -42,15 +45,14 @@ then
   exit 1
 fi
 
-
 # Test the UI configurable proxies
-
 docker run --network changedet-network \
   test-changedetectionio \
   bash -c 'cd changedetectionio && pytest tests/proxy_list/test_select_custom_proxy.py'
 
 
 # Should see a request for one.changedetection.io in there
+echo "- Looking for .changedetection.io request in squid-custom"
 docker logs squid-custom 2>/dev/null|grep "TCP_TUNNEL.200.*changedetection.io"
 if [ $? -ne 0 ]
 then
@@ -58,4 +60,25 @@ then
   exit 1
 fi
 
+# Test "no-proxy" option
+docker run --network changedet-network \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_list/test_noproxy.py'
+
+# We need to handle grep returning 1
+set +e
+# Check request was never seen in any container
+for c in $(echo "squid-one squid-two squid-custom"); do
+  echo ....Checking $c
+  docker logs $c &> $c.txt
+  grep noproxy $c.txt
+  if [ $? -ne 1 ]
+  then
+    echo "Saw request for noproxy in $c container"
+    cat $c.txt
+    exit 1
+  fi
+done
+
+
 docker kill squid-one squid-two squid-custom

changedetectionio/run_socks_proxy_tests.sh

@@ -0,0 +1,43 @@
+#!/bin/bash
+
+# exit when any command fails
+set -e
+# enable debug
+set -x
+
+
+# SOCKS5 related - start simple Socks5 proxy server
+# SOCKSTEST=xyz should show in the logs of this service to confirm it fetched
+docker run --network changedet-network -d --hostname socks5proxy --rm  --name socks5proxy -p 1080:1080 -e PROXY_USER=proxy_user123 -e PROXY_PASSWORD=proxy_pass123 serjs/go-socks5-proxy
+docker run --network changedet-network -d --hostname socks5proxy-noauth --rm  -p 1081:1080 --name socks5proxy-noauth  serjs/go-socks5-proxy
+
+echo "---------------------------------- SOCKS5 -------------------"
+# SOCKS5 related - test from proxies.json
+docker run --network changedet-network \
+  -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
+  --rm \
+  -e "SOCKSTEST=proxiesjson" \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+
+# SOCKS5 related - by manually entering in UI
+docker run --network changedet-network \
+  --rm \
+  -e "SOCKSTEST=manual" \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy.py'
+
+# SOCKS5 related - test from proxies.json via playwright - NOTE- PLAYWRIGHT DOESNT SUPPORT AUTHENTICATING PROXY
+docker run --network changedet-network \
+  -e "SOCKSTEST=manual-playwright" \
+  -v `pwd`/tests/proxy_socks5/proxies.json-example-noauth:/app/changedetectionio/test-datastore/proxies.json \
+  -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" \
+  --rm \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+
+echo "socks5 server logs"
+docker logs socks5proxy
+echo "----------------------------------"
+
+docker kill socks5proxy socks5proxy-noauth

changedetectionio/safe_jinja.py

@@ -0,0 +1,18 @@
+"""
+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
+
+JINJA2_MAX_RETURN_PAYLOAD_SIZE = 1024 * int(os.getenv("JINJA2_MAX_RETURN_PAYLOAD_SIZE_KB", 1024 * 10))
+
+
+def render(template_str, **args: t.Any) -> str:
+    jinja2_env = jinja2.sandbox.ImmutableSandboxedEnvironment(extensions=['jinja2_time.TimeExtension'])
+    output = jinja2_env.from_string(template_str).render(args)
+    return output[:JINJA2_MAX_RETURN_PAYLOAD_SIZE]
+

changedetectionio/static/images/bell-off.svg

@@ -1,4 +1,4 @@
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<svg width="15" height="16.363636" viewBox="0 0 15 16.363636" xmlns="http://www.w3.org/2000/svg" xmlns:svg="http://www.w3.org/2000/svg">
+<svg width="15" height="16.363636" viewBox="0 0 15 16.363636" xmlns="http://www.w3.org/2000/svg" >
   <path d="m 14.318182,11.762045 v 1.1925 H 5.4102273 L 11.849318,7.1140909 C 12.234545,9.1561364 12.54,11.181818 14.318182,11.762045 Z m -6.7984093,4.601591 c 1.0759091,0 2.0256823,-0.955909 2.0256823,-2.045454 H 5.4545455 c 0,1.089545 0.9879545,2.045454 2.0652272,2.045454 z M 15,2.8622727 0.9177273,15.636136 0,14.627045 l 1.8443182,-1.6725 h -1.1625 v -1.1925 C 4.0070455,10.677273 2.1784091,4.5388636 5.3611364,2.6897727 5.8009091,2.4347727 6.0709091,1.9609091 6.0702273,1.4488636 v -0.00205 C 6.0702273,0.64772727 6.7104545,0 7.5,0 8.2895455,0 8.9297727,0.64772727 8.9297727,1.4468182 v 0.00205 C 8.9290909,1.9602319 9.199773,2.4354591 9.638864,2.6897773 10.364318,3.111141 10.827273,3.7568228 11.1525,4.5129591 L 14.085682,1.8531818 Z M 6.8181818,1.3636364 C 6.8181818,1.74 7.1236364,2.0454545 7.5,2.0454545 7.8763636,2.0454545 8.1818182,1.74 8.1818182,1.3636364 8.1818182,0.98795455 7.8763636,0.68181818 7.5,0.68181818 c -0.3763636,0 -0.6818182,0.30613637 -0.6818182,0.68181822 z" id="path2" style="fill:#f8321b;stroke-width:0.681818;fill-opacity:1"/>
 </svg>

changedetectionio/static/images/brightdata.svg

@@ -0,0 +1,58 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   height="59.553207"
+   viewBox="-0.36 95.21 25.082135 59.553208"
+   width="249.99138"
+   version="1.1"
+   id="svg12"
+   sodipodi:docname="brightdata.svg"
+   inkscape:version="1.1.2 (0a00cf5339, 2022-02-04)"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   >
+  <defs
+     id="defs16" />
+  <sodipodi:namedview
+     id="namedview14"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageshadow="2"
+     inkscape:pageopacity="0.0"
+     inkscape:pagecheckerboard="0"
+     showgrid="false"
+     fit-margin-top="0"
+     fit-margin-left="0"
+     fit-margin-right="0"
+     fit-margin-bottom="0"
+     inkscape:zoom="0.9464"
+     inkscape:cx="22.189349"
+     inkscape:cy="-90.870668"
+     inkscape:window-width="1920"
+     inkscape:window-height="1051"
+     inkscape:window-x="1920"
+     inkscape:window-y="0"
+     inkscape:window-maximized="1"
+     inkscape:current-layer="svg12" />
+  <path
+     d="m -34.416031,129.28 c -3.97,-2.43 -5.1,-6.09 -4.32,-10.35 0.81,-4.4 3.95,-6.75 8.04,-7.75 4.23,-1.04 8.44,-0.86 12.3,1.5 0.63,0.39 0.93,0.03 1.31,-0.29 1.5,-1.26 3.27,-1.72 5.189999,-1.83 0.79,-0.05 1.04,0.24 1.01,1.01 -0.05,1.31 -0.04,2.63 0,3.95 0.02,0.65 -0.19,0.93 -0.87,0.89 -0.889999,-0.04 -1.789999,0.03 -2.669999,-0.02 -0.82,-0.04 -1.08,0.1 -0.88,1.04 0.83,3.9 -0.06,7.37 -3.1,10.06 -2.76,2.44 -6.13,3.15 -9.72,3.04 -0.51,-0.02 -1.03,-0.02 -1.52,-0.13 -1.22,-0.25 -1.96,0.14 -2.19,1.41 -0.28,1.54 0.16,2.62 1.37,3.07 0.84,0.31 1.74,0.35 2.63,0.39 2.97,0.13 5.95,-0.18 8.91,0.21 2.93,0.39 5.69,1.16 6.85,4.25 1.269999,3.38 0.809999,6.62 -1.48,9.47 -2.73,3.39 -6.52,4.78 -10.66,5.33 -3.53,0.48 -7.04,0.27 -10.39,-1.11 -3.89,-1.6 -5.75,-4.95 -4.84,-8.72 0.51,-2.11 1.85,-3.58 3.69,-4.65 0.38,-0.22 0.93,-0.32 0.28,-0.96 -2.91,-2.83 -2.85,-6.16 0.1,-8.95 0.28,-0.26 0.6,-0.53 0.96,-0.86 z m 8.07,21.5 c 0.95,0.04 1.87,-0.13 2.78,-0.33 1.89,-0.42 3.51,-1.3 4.49,-3.06 1.82,-3.25 0.24,-6.2 -3.37,-6.58 -2.88,-0.3 -5.76,0.24 -8.63,-0.13 -0.53,-0.07 -0.75,0.34 -0.95,0.71 -1.16,2.24 -1.08,4.53 0,6.73 1.15,2.34 3.46,2.48 5.68,2.66 z m -5,-30.61 c -0.03,1.67 0.08,3.19 0.74,4.61 0.76,1.62 2.17,2.42 4.03,2.31 1.62,-0.1 2.9,-1.12 3.36,-2.84 0.66,-2.46 0.69,-4.95 0.01,-7.42 -0.49,-1.76 -1.7,-2.64 -3.56,-2.7 -2.08,-0.07 -3.37,0.7 -4.04,2.42 -0.47,1.21 -0.6,2.47 -0.54,3.62 z m 32.9399993,6.56 c 0,2.59 0.05,5.18 -0.02,7.77 -0.03,1.03 0.31,1.46 1.32,1.52 0.65,0.04 1.61,-0.09 1.82,0.57 0.26,0.81 0.11,1.76 0.06,2.65 -0.03,0.48 -0.81,0.39 -0.81,0.39 l -11.47,0.01 c 0,0 -0.95,-0.21 -0.88,-0.88 0.03,-0.29 0.04,-0.6 0,-0.89 -0.19,-1.24 0.21,-1.92 1.58,-1.9 0.99,0.01 1.28,-0.52 1.28,-1.53 -0.05,-8.75 -0.05,-17.49 0,-26.24 0.01,-1.15 -0.36,-1.62 -1.44,-1.67 -0.17,-0.01 -0.34,-0.04 -0.5,-0.07 -1.43,-0.22 -2.12,-1.57 -1.53,-2.91 0.15,-0.35 0.43,-0.36 0.72,-0.4 2.94,-0.41 5.88,-0.81 8.82000002,-1.23 0.81999998,-0.12 0.99999998,0.27 0.98999998,1.01 -0.02,3.35 0,6.71 0.02,10.06 0,0.35 -0.23,0.84 0.18,1.03 0.38,0.17 0.69,-0.25 0.99,-0.45 2.56,-1.74 5.33,-2.73 8.4900007,-2.56 3.51005,0.19 5.65005,1.95 6.35005,5.46 0.42,2.09 0.52,4.21 0.51,6.33 -0.02,3.86 0.05,7.73 -0.04,11.59 -0.02,1.12 0.37,1.5 1.39,1.6 0.61,0.05 1.55,-0.13 1.74,0.47 0.26,0.85 0.12,1.84 0.1,2.77 -0.01,0.41 -0.69,0.37 -0.69,0.37 l -11.4700504,0.01 c 0,0 -0.81,-0.29 -0.8,-0.85 0.01,-0.38 0.04,-0.77 -0.01,-1.15 -0.13,-1.01 0.32,-1.52 1.31,-1.56 1.0600004,-0.05 1.3800004,-0.55 1.3500004,-1.63 -0.14,-4.84 0.16,-9.68 -0.18,-14.51 -0.26,-3.66 -2.1100004,-4.95 -5.6700007,-3.99 -0.25,0.07 -0.49,0.15 -0.73,0.22 -2.57,0.8 -2.79,1.09 -2.79,3.71 0.01,2.3 0.01,4.59 0.01,6.88 z M -109.26603,122.56 c 0,-4.75 -0.02,-9.51 0.02,-14.26 0.01,-0.92 -0.17,-1.47 -1.19,-1.45 -0.16,0 -0.33,-0.07 -0.5,-0.1 -1.56,-0.27 -2.24,-1.47 -1.69,-2.92 0.14,-0.37 0.41,-0.38 0.7,-0.42 2.98,-0.41 5.97,-0.81 8.94,-1.24 0.85,-0.12 0.88,0.33 0.88,0.96 -0.01,3.01 -0.01,6.03 0,9.04 0,0.4 -0.18,0.96 0.27,1.16 0.36,0.16 0.66,-0.3 0.96,-0.52 4.729999,-3.51 12.459999,-2.61 14.889999,4.48 1.89,5.51 1.91,11.06 -0.96,16.28 -2.37,4.31 -6.19,6.49 -11.15,6.59 -3.379999,0.07 -6.679999,-0.3 -9.909999,-1.37 -0.93,-0.31 -1.3,-0.78 -1.28,-1.83 0.05,-4.81 0.02,-9.6 0.02,-14.4 z m 7.15,3.89 c 0,2.76 0.02,5.52 -0.01,8.28 -0.01,0.76 0.18,1.29 0.91,1.64 1.899999,0.9 4.299999,0.5 5.759999,-1.01 0.97,-1 1.56,-2.21 1.96,-3.52 1.03,-3.36 0.97,-6.78 0.61,-10.22 a 9.991,9.991 0 0 0 -0.93,-3.29 c -1.47,-3.06 -4.67,-3.85 -7.439999,-1.86 -0.6,0.43 -0.88,0.93 -0.87,1.7 0.04,2.76 0.01,5.52 0.01,8.28 z"
+     fill="#4280f6"
+     id="path2" />
+  <path
+     d="m 68.644019,137.2 c -1.62,1.46 -3.41,2.56 -5.62,2.96 -4.4,0.8 -8.7,-1.39 -10.49,-5.49 -2.31,-5.31 -2.3,-10.67 -0.1,-15.98 2.31,-5.58 8.29,-8.65 14.24,-7.46 1.71,0.34 1.9,0.18 1.9,-1.55 0,-0.68 -0.05,-1.36 0.01,-2.04 0.09,-1.02 -0.25,-1.54 -1.34,-1.43 -0.64,0.06 -1.26,-0.1 -1.88,-0.21 -1.32,-0.24 -1.6,-0.62 -1.37,-1.97 0.07,-0.41 0.25,-0.57 0.65,-0.62 2.63,-0.33 5.27,-0.66 7.9,-1.02 1.04,-0.14 1.17,0.37 1.17,1.25 -0.02,10.23 -0.02,20.45 -0.01,30.68 v 1.02 c 0.02,0.99 0.35,1.6 1.52,1.47 0.52,-0.06 1.35,-0.27 1.25,0.73 -0.08,0.8 0.58,1.93 -0.94,2.18 -1.29,0.22 -2.51,0.69 -3.86,0.65 -2.04,-0.06 -2.3,-0.23 -2.76,-2.19 -0.09,-0.3 0.06,-0.67 -0.27,-0.98 z m -0.07,-12.46 c 0,-2.8 -0.04,-5.6 0.02,-8.39 0.02,-0.9 -0.28,-1.47 -1.05,-1.81 -3.18,-1.4 -7.54,-0.8 -9.3,2.87 -0.83,1.74 -1.31,3.54 -1.49,5.46 -0.28,2.93 -0.38,5.83 0.61,8.65 0.73,2.09 1.81,3.9 4.11,4.67 2.49,0.83 4.55,-0.04 6.5,-1.48 0.54,-0.4 0.62,-0.95 0.61,-1.57 -0.02,-2.8 -0.01,-5.6 -0.01,-8.4 z m 28.79,2.53 c 0,3.24 0.04,5.83 -0.02,8.41 -0.02,1 0.19,1.49 1.309998,1.41 0.55,-0.04 1.460003,-0.46 1.520003,0.73 0.05,1.02 0.1,1.89 -1.330003,2.08 -1.289998,0.17 -2.559998,0.51 -3.889998,0.48 -1.88,-0.05 -2.15,-0.26 -2.42,-2.15 -0.04,-0.27 0.14,-0.65 -0.22,-0.79 -0.34,-0.13 -0.5,0.24 -0.72,0.42 -3.61,3 -8.15,3.4 -11.64,1.08 -1.61,-1.07 -2.49,-2.63 -2.67,-4.43 -0.51,-5.13 0.77,-7.91 6.3,-10.22 2.44,-1.02 5.07,-1.27 7.68,-1.49 0.77,-0.07 1.03,-0.28 1.02,-1.05 -0.03,-1.48 -0.05,-2.94 -0.64,-4.36 -0.59,-1.42 -1.67,-1.92 -3.08,-2.03 -3.04,-0.24 -5.88,0.5 -8.63,1.71 -0.51,0.23 -1.19,0.75 -1.48,-0.13 -0.26,-0.77 -1.35,-1.61 0.05,-2.47 3.27,-2 6.7,-3.44 10.61,-3.42 1.44,0.01 2.88,0.27 4.21,0.81 2.67,1.08 3.44,3.4 3.8,5.99 0.46,3.37 0.1,6.73 0.24,9.42 z m -5.09,2.9 c 0,-1.23 -0.01,-2.46 0,-3.69 0,-0.52 -0.06,-0.98 -0.75,-0.84 -1.45,0.3 -2.93,0.28 -4.37,0.69 -3.71,1.04 -5.46,4.48 -3.97,8.03 0.51,1.22 1.48,1.98 2.79,2.16 2.01,0.28 3.86,-0.29 5.6,-1.28 0.54,-0.31 0.73,-0.76 0.72,-1.37 -0.05,-1.23 -0.02,-2.47 -0.02,-3.7 z m 43.060001,-2.89 c 0,2.72 0.01,5.43 -0.01,8.15 0,0.66 0.02,1.21 0.91,1.12 0.54,-0.06 0.99,0.12 0.86,0.75 -0.15,0.71 0.56,1.7 -0.58,2.09 -1.55,0.52 -3.16,0.59 -4.77,0.4 -0.99,-0.12 -1.12,-1.01 -1.18,-1.73 -0.08,-1.15 -0.16,-1.45 -1.24,-0.54 -3.41,2.87 -8.05,3.17 -11.43,0.88 -1.75,-1.18 -2.49,-2.91 -2.7,-4.94 -0.64,-6.24 3.16,-8.74 7.83,-10.17 2.04,-0.62 4.14,-0.8 6.24,-0.99 0.81,-0.07 1,-0.36 0.98,-1.09 -0.04,-1.31 0.04,-2.62 -0.42,-3.89 -0.57,-1.57 -1.53,-2.34 -3.18,-2.45 -3.03,-0.21 -5.88,0.46 -8.64,1.66 -0.6,0.26 -1.25,0.81 -1.68,-0.2 -0.34,-0.8 -1.08,-1.61 0.16,-2.36 4.12,-2.5 8.44,-4.16 13.36,-3.07 3.21,0.71 4.89,2.91 5.26,6.34 0.18,1.69 0.22,3.37 0.22,5.07 0.01,1.66 0.01,3.32 0.01,4.97 z m -5.09,2.54 c 0,-1.27 -0.03,-2.54 0.01,-3.81 0.02,-0.74 -0.27,-1.02 -0.98,-0.92 -1.21,0.17 -2.43,0.28 -3.62,0.55 -3.72,0.83 -5.47,3.48 -4.82,7.21 0.29,1.66 1.57,2.94 3.21,3.16 2.02,0.27 3.85,-0.34 5.57,-1.34 0.49,-0.29 0.64,-0.73 0.63,-1.29 -0.02,-1.18 0,-2.37 0,-3.56 z"
+     fill="#c8dbfb"
+     id="path4" />
+  <path
+     d="m 26.314019,125.77 c 0,-2.89 -0.05,-5.77 0.02,-8.66 0.03,-1.04 -0.33,-1.39 -1.31,-1.24 a 0.7,0.7 0 0 1 -0.25,0 c -0.57,-0.18 -1.44,0.48 -1.68,-0.58 -0.35,-1.48 -0.02,-2.3 1.21,-2.7 1.3,-0.43 2.16,-1.26 2.76,-2.46 0.78,-1.56 1.44,-3.17 1.91,-4.84 0.18,-0.63 0.47,-0.86 1.15,-0.88 3.28,-0.09 3.27,-0.11 3.32,3.17 0.01,1.06 0.09,2.12 0.09,3.18 -0.01,0.67 0.27,0.89 0.91,0.88 1.61,-0.02 3.23,0.03 4.84,-0.02 0.77,-0.02 1.01,0.23 1.03,1.01 0.08,3.27 0.1,3.27 -3.09,3.27 -0.93,0 -1.87,0.03 -2.8,-0.01 -0.67,-0.02 -0.89,0.26 -0.88,0.91 0.04,5.43 0.04,10.86 0.12,16.29 0.02,1.7 0.75,2.26 2.46,2.1 1.1,-0.1 2.19,-0.26 3.23,-0.65 0.59,-0.22 0.89,-0.09 1.14,0.53 0.93,2.29 0.92,2.37 -1.32,3.52 -2.54,1.3 -5.22,1.99 -8.1,1.79 -2.27,-0.16 -3.68,-1.27 -4.35,-3.45 -0.3,-0.98 -0.41,-1.99 -0.41,-3.01 z m -97.67005,-8.99 c 0.57,-0.84 1.11,-1.74 1.76,-2.55 1.68,-2.09 3.68,-3.62 6.54,-3.66 1.08,-0.01 1.63,0.28 1.57,1.52 -0.1,2.08 -0.05,4.16 -0.02,6.24 0.01,0.74 -0.17,0.96 -0.96,0.76 -2.36,-0.59 -4.71,-0.42 -7.03,0.28 -0.8,0.24 -1.16,0.62 -1.15,1.52 0.05,4.5 0.04,9 0,13.5 -0.01,0.89 0.29,1.16 1.15,1.2 1.23,0.06 2.44,0.32 3.67,0.39 0.75,0.05 0.91,0.38 0.89,1.04 -0.06,2.86 0.29,2.28 -2.25,2.3 -4.2,0.04 -8.41,-0.02 -12.61,0.03 -0.91,0.01 -1.39,-0.18 -1.22,-1.18 0.02,-0.12 0,-0.25 0,-0.38 0.02,-2.1 -0.24,-1.88 1.77,-2.04 1.33,-0.11 1.6,-0.67 1.58,-1.9 -0.07,-5.35 -0.04,-10.7 -0.02,-16.05 0,-0.78 -0.17,-1.2 -1,-1.46 -2.21,-0.68 -2.7,-1.69 -2.22,-3.99 0.11,-0.52 0.45,-0.56 0.82,-0.62 2.22,-0.34 4.44,-0.7 6.67,-0.99 0.99,-0.13 1.82,0.7 1.84,1.76 0.03,1.4 0.03,2.8 0.04,4.2 -0.01,0.02 0.06,0.04 0.18,0.08 z m 25.24,6.59 c 0,3.69 0.04,7.38 -0.03,11.07 -0.02,1.04 0.31,1.48 1.32,1.49 0.29,0 0.59,0.12 0.88,0.13 0.93,0.01 1.18,0.47 1.16,1.37 -0.05,2.19 0,2.19 -2.24,2.19 -3.48,0 -6.96,-0.04 -10.44,0.03 -1.09,0.02 -1.47,-0.33 -1.3,-1.36 0.02,-0.12 0.02,-0.26 0,-0.38 -0.28,-1.39 0.39,-1.96 1.7,-1.9 1.36,0.06 1.76,-0.51 1.74,-1.88 -0.09,-5.17 -0.08,-10.35 0,-15.53 0.02,-1.22 -0.32,-1.87 -1.52,-2.17 -0.57,-0.14 -1.47,-0.11 -1.57,-0.85 -0.15,-1.04 -0.05,-2.11 0.01,-3.17 0.02,-0.34 0.44,-0.35 0.73,-0.39 2.81,-0.39 5.63,-0.77 8.44,-1.18 0.92,-0.14 1.15,0.2 1.14,1.09 -0.04,3.8 -0.02,7.62 -0.02,11.44 z"
+     fill="#4280f6"
+     id="path6" />
+  <path
+     d="m 101.44402,125.64 c 0,-3.18 -0.03,-6.37 0.02,-9.55 0.02,-0.94 -0.26,-1.36 -1.22,-1.22 -0.21,0.03 -0.430003,0.04 -0.630003,0 -0.51,-0.12 -1.35,0.39 -1.44,-0.55 -0.08,-0.85 -0.429998,-1.87 0.93,-2.24 2.080003,-0.57 2.720003,-2.39 3.350003,-4.17 0.31,-0.88 0.62,-1.76 0.87,-2.66 0.18,-0.64 0.52,-0.85 1.19,-0.84 2.46,0.05 2,-0.15 2.04,2.04 0.02,1.1 0.08,2.21 -0.02,3.31 -0.11,1.16 0.46,1.52 1.46,1.53 1.78,0.01 3.57,0.04 5.35,-0.01 0.82,-0.02 1.12,0.23 1.11,1.08 -0.05,2.86 0.19,2.49 -2.42,2.51 -1.53,0.01 -3.06,0.02 -4.59,-0.01 -0.65,-0.01 -0.9,0.22 -0.9,0.89 0.02,5.52 0,11.04 0.03,16.56 0,0.67 0.14,1.34 0.25,2.01 0.17,1.04 1.17,1.62 2.59,1.42 1.29,-0.19 2.57,-0.49 3.86,-0.69 0.43,-0.07 1.05,-0.47 1.19,0.4 0.12,0.75 1.05,1.61 -0.09,2.24 -2.09,1.16 -4.28,2.07 -6.71,2.16 -1.05,0.04 -2.13,0.2 -3.16,-0.14 -1.92,-0.65 -3.03,-2.28 -3.05,-4.51 -0.02,-3.19 -0.01,-6.37 -0.01,-9.56 z"
+     fill="#c8dbfb"
+     id="path8" />
+  <path
+     d="m -50.816031,95.21 c 0.19,2.160002 1.85,3.240002 2.82,4.740002 0.25,0.379998 0.48,0.109998 0.67,-0.16 0.21,-0.31 0.6,-1.21 1.15,-1.28 -0.35,1.38 -0.04,3.149998 0.16,4.449998 0.49,3.05 -1.22,5.64 -4.07,6.18 -3.38,0.65 -6.22,-2.21 -5.6,-5.62 0.23,-1.24 1.37,-2.5 0.77,-3.699998 -0.85,-1.7 0.54,-0.52 0.79,-0.22 1.04,1.199998 1.21,0.09 1.45,-0.55 0.24,-0.63 0.31,-1.31 0.47,-1.97 0.19,-0.770002 0.55,-1.400002 1.39,-1.870002 z"
+     fill="#4280f6"
+     id="path10" />
+</svg>

changedetectionio/static/images/copy.svg

@@ -12,7 +12,7 @@
    xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
    xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
    xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg"><defs
+   ><defs
      id="defs11" /><sodipodi:namedview
      id="namedview9"
      pagecolor="#ffffff"

changedetectionio/static/images/email.svg

@@ -0,0 +1,37 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Uploaded to: SVG Repo, www.svgrepo.com, Generator: SVG Repo Mixer Tools -->
+
+<svg
+   fill="#FFFFFF"
+   height="7.5005589"
+   width="11.248507"
+   version="1.1"
+   id="Layer_1"
+   viewBox="0 0 7.1975545 4.7993639"
+   xml:space="preserve"
+   xmlns="http://www.w3.org/2000/svg"
+   ><defs
+   id="defs19" />
+<g
+   id="g14"
+   transform="matrix(-0.01406065,0,0,0.01406065,7.1975543,-1.1990922)">
+	<g
+   id="g12">
+		<g
+   id="g10">
+			<path
+   d="M 468.373,85.28 H 45.333 C 21.227,85.28 0,105.76 0,129.014 V 383.2 c 0,23.147 21.227,43.413 45.333,43.413 h 422.933 c 23.68,0 43.627,-19.84 43.627,-43.413 V 129.014 C 512,105.334 492.053,85.28 468.373,85.28 Z m 0,320 H 45.333 c -12.373,0 -24,-10.773 -24,-22.08 V 129.014 c 0,-11.307 11.84,-22.4 24,-22.4 h 422.933 c 11.733,0 22.293,10.667 22.293,22.4 V 383.2 h 0.107 c 10e-4,11.734 -10.453,22.08 -22.293,22.08 z"
+   id="path2" />
+			<path
+   d="m 440.853,153.974 c -3.307,-4.907 -9.92,-6.187 -14.827,-2.987 L 256,264.48 85.973,151.094 c -4.907,-3.2 -11.52,-1.707 -14.72,3.2 -3.093,4.8 -1.813,11.307 2.88,14.507 l 176,117.333 c 3.627,2.347 8.213,2.347 11.84,0 l 176,-117.333 c 4.8,-3.201 6.187,-9.921 2.88,-14.827 z"
+   id="path4" />
+			<path
+   d="m 143.573,257.654 c -0.107,0.107 -0.32,0.213 -0.427,0.32 L 68.48,311.307 c -4.907,3.307 -6.187,9.92 -2.88,14.827 3.307,4.907 9.92,6.187 14.827,2.88 0.107,-0.107 0.32,-0.213 0.427,-0.32 l 74.667,-53.333 c 4.907,-3.307 6.187,-9.92 2.88,-14.827 -3.308,-4.907 -9.921,-6.187 -14.828,-2.88 z"
+   id="path6" />
+			<path
+   d="m 443.947,311.627 c -0.107,-0.107 -0.32,-0.213 -0.427,-0.32 l -74.667,-53.333 c -4.693,-3.52 -11.413,-2.56 -14.933,2.133 -3.52,4.693 -2.56,11.413 2.133,14.933 0.107,0.107 0.32,0.213 0.427,0.32 l 74.667,53.333 c 4.693,3.52 11.413,2.56 14.933,-2.133 3.52,-4.693 2.56,-11.413 -2.133,-14.933 z"
+   id="path8" />
+		</g>
+	</g>
+</g>
+</svg>

changedetectionio/static/images/generic-icon.svg

@@ -0,0 +1,3 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+<svg width="61.649mm" height="61.649mm" version="1.1" viewBox="0 0 61.649 61.649" xml:space="preserve" xmlns="http://www.w3.org/2000/svg"><g transform="translate(66.269 -15.463)" fill="#3056d3"><g transform="matrix(1.423 0 0 1.423 101.16 69.23)" fill="#3056d3"><g transform="matrix(.8229 0 0 .8229 -23.378 -2.3935)" fill="#3056d3"><path d="m-88.248-43.007a26.323 26.323 0 0 0-26.323 26.323 26.323 26.323 0 0 0 26.323 26.323 26.323 26.323 0 0 0 26.323-26.323 26.323 26.323 0 0 0-26.323-26.323zm0 2.8417a23.482 23.482 0 0 1 23.482 23.482 23.482 23.482 0 0 1-23.482 23.482 23.482 23.482 0 0 1-23.482-23.482 23.482 23.482 0 0 1 23.482-23.482z"/><g transform="matrix(.26458 0 0 .26458 -115.65 -44.085)"><path d="m33.02 64.43c0.35-0.05 2.04-0.13 2.04-0.13h25.53s3.17 0.32 3.67 0.53c2.5 1.05 3.98 1.89 6.04 3.57 0.72 0.58 4.12 4.01 4.12 4.01l51.67 57.39s1.61 1.65 1.97 1.94c1.2 0.97 2.48 1.96 3.98 2.32 0.5 0.12 2.72 0.21 2.72 0.21h27.32l-8.83-9.04s-1.31-1.65-1.44-1.94c-0.45-0.93-0.59-2.59-0.13-3.51 0.35-0.69 1.46-1.87 2.23-1.98 1.03-0.14 2.12-0.39 3.02 0.14 0.33 0.2 1.64 1.32 1.64 1.32l17.49 17.49s1.35 1.09 1.6 1.6c0.17 0.34 0.29 0.82 0.15 1.18-0.17 0.42-1.42 1.63-1.42 1.63l-0.94 0.98-15.69 16.37s-1.44 1.4-1.79 1.67c-0.76 0.6-1.99 0.89-2.96 0.9-1.03 0-2.62-1.11-3.26-1.91-0.6-0.76-1.1-2.22-0.77-3.13 0.16-0.45 1.28-1.85 1.28-1.85l11.36-11.3-29.47-0.02-1.68 0.09s-4.16-0.66-5.26-1.03c-1.63-0.56-3.44-1.82-4.75-2.93-0.39-0.33-1.8-1.92-1.8-1.92l-51.7-59.28s-2-2.06-2.43-2.43c-1.37-1.17-2-1.62-3.76-2.34-0.44-0.18-3.45-0.55-3.45-0.55l-24.13-0.22s-2.23-0.15-2.61-0.22c-1.08-0.21-2.16-1.07-2.81-1.83-0.79-0.92-0.59-3.06 0.06-4.09 0.57-0.89 2.14-1.52 3.19-1.66z"/><path d="m86.1 109.7-17.13 19.65s-2 2.06-2.43 2.43c-1.37 1.17-2 1.62-3.76 2.34-0.44 0.18-3.45 0.55-3.45 0.55l-24.13 0.22s-2.23 0.15-2.61 0.22c-1.08 0.21-2.16 1.07-2.81 1.83-0.79 0.92-0.59 3.06 0.06 4.09 0.57 0.89 2.14 1.52 3.19 1.66 0.35 0.05 2.04 0.13 2.04 0.13h25.53s3.17-0.32 3.67-0.53c2.5-1.05 3.98-1.89 6.04-3.57 0.72-0.58 4.12-4.01 4.12-4.01l17.38-19.3z"/><path d="m177.81 67.6c-0.17-0.42-1.42-1.63-1.42-1.63l-0.94-0.98-15.69-16.37s-1.44-1.4-1.79-1.67c-0.76-0.6-1.99-0.89-2.96-0.9-1.03 0-2.62 1.11-3.26 1.91-0.6 0.76-1.1 2.22-0.77 3.13 0.16 0.45 1.28 1.85 1.28 1.85l11.36 11.3-29.47 0.02-1.68-0.09s-4.16 0.66-5.26 1.03c-1.63 0.56-3.44 1.82-4.75 2.93-0.39 0.33-1.8 1.92-1.8 1.92l-18.91 21.69 5.98 5.98 18.38-20.41s1.61-1.65 1.97-1.94c1.2-0.97 2.48-1.96 3.98-2.32 0.5-0.12 2.72-0.21 2.72-0.21h27.32l-8.83 9.04s-1.31 1.65-1.44 1.94c-0.45 0.93-0.59 2.59-0.13 3.51 0.35 0.69 1.46 1.87 2.23 1.98 1.03 0.14 2.12 0.39 3.02-0.14 0.33-0.2 1.64-1.32 1.64-1.32l17.49-17.49s1.35-1.09 1.6-1.6c0.17-0.34 0.29-0.82 0.15-1.18z"/></g></g></g></g></svg>

changedetectionio/static/images/notice.svg

@@ -9,7 +9,7 @@
    id="svg5"
    xmlns:xlink="http://www.w3.org/1999/xlink"
    xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg">
+   >
   <defs
      id="defs2" />
   <g

changedetectionio/static/images/pause.svg

@@ -3,7 +3,6 @@
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:cc="http://creativecommons.org/ns#"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
-   xmlns:svg="http://www.w3.org/2000/svg"
    xmlns="http://www.w3.org/2000/svg"
    version="1.1"
    id="Capa_1"

changedetectionio/static/images/play.svg

@@ -13,7 +13,6 @@
    xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
    xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
    xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:cc="http://creativecommons.org/ns#"
    xmlns:dc="http://purl.org/dc/elements/1.1/"><sodipodi:namedview

changedetectionio/static/images/spread-white.svg

@@ -6,7 +6,7 @@
    version="1.1"
    id="svg6"
    xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg">
+   >
   <defs
      id="defs10" />
   <path

changedetectionio/static/images/spread.svg

@@ -1,5 +1,5 @@
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<svg width="18" height="19.92" viewBox="0 0 18 19.92" xmlns="http://www.w3.org/2000/svg" xmlns:svg="http://www.w3.org/2000/svg">
+<svg width="18" height="19.92" viewBox="0 0 18 19.92" xmlns="http://www.w3.org/2000/svg" >
   <path d="M -3,-2 H 21 V 22 H -3 Z" fill="none" id="path2"/>
   <path d="m 15,14.08 c -0.76,0 -1.44,0.3 -1.96,0.77 L 5.91,10.7 C 5.96,10.47 6,10.24 6,10 6,9.76 5.96,9.53 5.91,9.3 L 12.96,5.19 C 13.5,5.69 14.21,6 15,6 16.66,6 18,4.66 18,3 18,1.34 16.66,0 15,0 c -1.66,0 -3,1.34 -3,3 0,0.24 0.04,0.47 0.09,0.7 L 5.04,7.81 C 4.5,7.31 3.79,7 3,7 1.34,7 0,8.34 0,10 c 0,1.66 1.34,3 3,3 0.79,0 1.5,-0.31 2.04,-0.81 l 7.12,4.16 c -0.05,0.21 -0.08,0.43 -0.08,0.65 0,1.61 1.31,2.92 2.92,2.92 1.61,0 2.92,-1.31 2.92,-2.92 0,-1.61 -1.31,-2.92 -2.92,-2.92 z" id="path4" style="fill:#0078e7;fill-opacity:1"/>
 </svg>

changedetectionio/static/images/steps.svg

@@ -0,0 +1,44 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   aria-hidden="true"
+   viewBox="0 0 19.966091 17.999964"
+   class="css-1oqmxjn"
+   version="1.1"
+   id="svg4"
+   sodipodi:docname="steps.svg"
+   width="19.966091"
+   height="17.999964"
+   inkscape:version="1.1.2 (0a00cf5339, 2022-02-04)"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg">
+  <defs
+     id="defs8" />
+  <sodipodi:namedview
+     id="namedview6"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageshadow="2"
+     inkscape:pageopacity="0.0"
+     inkscape:pagecheckerboard="0"
+     showgrid="false"
+     fit-margin-top="0"
+     fit-margin-left="0"
+     fit-margin-right="0"
+     fit-margin-bottom="0"
+     inkscape:zoom="8.6354167"
+     inkscape:cx="-1.3896261"
+     inkscape:cy="6.1375151"
+     inkscape:window-width="1280"
+     inkscape:window-height="667"
+     inkscape:window-x="2419"
+     inkscape:window-y="250"
+     inkscape:window-maximized="0"
+     inkscape:current-layer="svg4" />
+  <path
+     d="m 16.95807,12.000003 c -0.7076,0.0019 -1.3917,0.2538 -1.9316,0.7113 -0.5398,0.4575 -0.9005,1.091 -1.0184,1.7887 H 5.60804 c -0.80847,0.0297 -1.60693,-0.1865 -2.29,-0.62 -0.26632,-0.1847 -0.48375,-0.4315 -0.63356,-0.7189 -0.14982,-0.2874 -0.22753,-0.607 -0.22644,-0.9311 -0.02843,-0.3931 0.03646,-0.7873 0.1894,-1.1505 0.15293,-0.3632 0.38957,-0.6851 0.6906,-0.9395 0.66628,-0.4559004 1.4637,-0.6807004 2.27,-0.6400004 h 8.35003 c 0.8515,-0.0223 1.6727,-0.3206 2.34,-0.85 0.3971,-0.3622 0.7076,-0.8091 0.9084,-1.3077 0.2008,-0.49857 0.2868,-1.03596 0.2516,-1.57229 0.0113,-0.47161 -0.0887,-0.93924 -0.292,-1.36493 -0.2033,-0.4257 -0.5041,-0.79745 -0.878,-1.08507 -0.7801,-0.55815 -1.7212,-0.84609 -2.68,-0.82 H 5.95804 c -0.12537,-0.7417 -0.5248,-1.40924 -1.11913,-1.87032996 -0.59434,-0.46108 -1.3402,-0.68207 -2.08979,-0.61917 -0.74958,0.06291 -1.44818,0.40512 -1.95736,0.95881 C 0.28259,1.5230126 0,2.2477926 0,3.0000126 c 0,0.75222 0.28259,1.47699 0.79176,2.03068 0.50918,0.55369 1.20778,0.8959 1.95736,0.95881 0.74959,0.0629 1.49545,-0.15808 2.08979,-0.61917 0.59433,-0.46109 0.99376,-1.12863 1.11913,-1.87032 h 7.70003 c 0.7353,-0.03061 1.4599,0.18397 2.06,0.61 0.2548,0.19335 0.4595,0.445 0.597,0.73385 0.1375,0.28884 0.2036,0.60644 0.193,0.92615 0.0316,0.38842 -0.0247,0.77898 -0.165,1.14258 -0.1402,0.36361 -0.3607,0.69091 -0.645,0.95741 -0.5713,0.4398 -1.2799,0.663 -2,0.63 H 5.69804 c -1.03259,-0.0462 -2.05065,0.2568 -2.89,0.86 -0.43755,0.3361 -0.78838,0.7720004 -1.02322,1.2712004 -0.23484,0.4993 -0.34688,1.0474 -0.32678,1.5988 -0.00726,0.484 0.10591,0.9622 0.32934,1.3916 0.22344,0.4295 0.55012,0.7966 0.95066,1.0684 0.85039,0.5592 1.85274,0.8421 2.87,0.81 h 8.40003 c 0.0954,0.5643 0.3502,1.0896 0.7343,1.5138 0.3842,0.4242 0.8817,0.7297 1.4338,0.8803 0.5521,0.1507 1.1358,0.1403 1.6822,-0.0299 0.5464,-0.1702 1.0328,-0.4932 1.4016,-0.9308 0.3688,-0.4376 0.6048,-0.9716 0.6801,-1.5389 0.0752,-0.5673 -0.0134,-1.1444 -0.2554,-1.663 -0.242,-0.5186 -0.6273,-0.9572 -1.1104,-1.264 -0.4831,-0.3068 -1.0439,-0.469 -1.6162,-0.4675 z m 0,5 c -0.3956,0 -0.7823,-0.1173 -1.1112,-0.3371 -0.3289,-0.2197 -0.5852,-0.5321 -0.7366,-0.8975 -0.1514,-0.3655 -0.191,-0.7676 -0.1138,-1.1556 0.0772,-0.3879 0.2677,-0.7443 0.5474,-1.024 0.2797,-0.2797 0.636,-0.4702 1.024,-0.5474 0.388,-0.0771 0.7901,-0.0375 1.1555,0.1138 0.3655,0.1514 0.6778,0.4078 0.8976,0.7367 0.2198,0.3289 0.3371,0.7155 0.3371,1.1111 0,0.5304 -0.2107,1.0391 -0.5858,1.4142 -0.3751,0.3751 -0.8838,0.5858 -1.4142,0.5858 z"
+     id="path2"
+     style="fill:#777777;fill-opacity:1" />
+</svg>

changedetectionio/static/js/browser-steps.js

@@ -10,7 +10,7 @@ $(document).ready(function () {
         }
     })
     var browsersteps_session_id;
-    var browserless_seconds_remaining = 0;
+    var browser_interface_seconds_remaining = 0;
     var apply_buttons_disabled = false;
     var include_text_elements = $("#include_text_elements");
     var xpath_data = false;
@@ -26,7 +26,8 @@ $(document).ready(function () {
         set_scale();
     });
     // Should always be disabled
-    $('#browser_steps >li:first-child select').val('Goto site').attr('disabled', 'disabled');
+    $('#browser_steps-0-operation option[value="Goto site"]').prop("selected", "selected");
+    $('#browser_steps-0-operation').attr('disabled', 'disabled');
 
     $('#browsersteps-click-start').click(function () {
         $("#browsersteps-click-start").fadeOut();
@@ -49,7 +50,7 @@ $(document).ready(function () {
         $('#browsersteps-img').removeAttr('src');
         $("#browsersteps-click-start").show();
         $("#browsersteps-selector-wrapper .spinner").hide();
-        browserless_seconds_remaining = 0;
+        browser_interface_seconds_remaining = 0;
         browsersteps_session_id = false;
         apply_buttons_disabled = false;
         ctx.clearRect(0, 0, c.width, c.height);
@@ -61,12 +62,12 @@ $(document).ready(function () {
         $('#browser_steps >li:first-child').css('opacity', '0.5');
     }
 
-    // Show seconds remaining until playwright/browserless needs to restart the session
+    // Show seconds remaining until the browser interface needs to restart the session
     // (See comment at the top of changedetectionio/blueprint/browser_steps/__init__.py )
     setInterval(() => {
-        if (browserless_seconds_remaining >= 1) {
-            document.getElementById('browserless-seconds-remaining').innerText = browserless_seconds_remaining + " seconds remaining in session";
-            browserless_seconds_remaining -= 1;
+        if (browser_interface_seconds_remaining >= 1) {
+            document.getElementById('browser-seconds-remaining').innerText = browser_interface_seconds_remaining + " seconds remaining in session";
+            browser_interface_seconds_remaining -= 1;
         }
     }, "1000")
 
@@ -114,11 +115,11 @@ $(document).ready(function () {
             e.preventDefault()
         });
 
+        // When the mouse moves we know which element it should be above
+        // mousedown will link that to the UI (select the right action, highlight etc)
         $('#browsersteps-selector-canvas').bind('mousedown', function (e) {
             // https://developer.mozilla.org/en-US/docs/Web/API/MouseEvent
             e.preventDefault()
-            console.log(e);
-            console.log("current xpath in index is " + current_selected_i);
             last_click_xy = {'x': parseInt((1 / x_scale) * e.offsetX), 'y': parseInt((1 / y_scale) * e.offsetY)}
             process_selected(current_selected_i);
             current_selected_i = false;
@@ -132,6 +133,7 @@ $(document).ready(function () {
             }
         });
 
+        // Debounce and find the current most 'interesting' element we are hovering above
         $('#browsersteps-selector-canvas').bind('mousemove', function (e) {
             if (!xpath_data) {
                 return;
@@ -151,41 +153,46 @@ $(document).ready(function () {
             current_selected_i = false;
             // Reverse order - the most specific one should be deeper/"laster"
             // Basically, find the most 'deepest'
-            //$('#browsersteps-selector-canvas').css('cursor', 'pointer');
-            for (var i = xpath_data['size_pos'].length; i !== 0; i--) {
-                // draw all of them? let them choose somehow?
-                var sel = xpath_data['size_pos'][i - 1];
+            var possible_elements = [];
+            xpath_data['size_pos'].forEach(function (item, index) {
                 // If we are in a bounding-box
-                if (e.offsetY > sel.top * y_scale && e.offsetY < sel.top * y_scale + sel.height * y_scale
+                if (e.offsetY > item.top * y_scale && e.offsetY < item.top * y_scale + item.height * y_scale
                     &&
-                    e.offsetX > sel.left * y_scale && e.offsetX < sel.left * y_scale + sel.width * y_scale
+                    e.offsetX > item.left * y_scale && e.offsetX < item.left * y_scale + item.width * y_scale
 
                 ) {
-                    // Only highlight these interesting types
-                    if (1) {
-                        ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                        ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                        current_selected_i = i - 1;
-                        break;
+                    // Ignore really large ones, because we are scraping 'div' also from xpath_element_scraper but
+                    // that div or whatever could be some wrapper and would generally make you select the whole page
+                    if (item.width > 800 && item.height > 400) {
+                        return
+                    }
 
-                        // find the smallest one at this x,y
-                        // does it mean sort the xpath list by size (w*h) i think so!
-                    } else {
-
-                        if (include_text_elements[0].checked === true) {
-                            // blue one with background instead?
-                            ctx.fillStyle = 'rgba(0,0,255, 0.1)';
-                            ctx.strokeStyle = 'rgba(0,0,200, 0.7)';
-                            $('#browsersteps-selector-canvas').css('cursor', 'grab');
-                            ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                            ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                            current_selected_i = i - 1;
-                            break;
-                        }
+                    // There could be many elements here, record them all and then we'll find out which is the most 'useful'
+                    // (input, textarea, button, A etc)
+                    if (item.width < xpath_data['browser_width']) {
+                        possible_elements.push(item);
                     }
                 }
+            });
+
+            // Find the best one
+            if (possible_elements.length) {
+                possible_elements.forEach(function (item, index) {
+                  if (["a", "input", "textarea", "button"].includes(item['tagName'])) {
+                      current_selected_i = item;
+                  }
+                });
+
+                if (!current_selected_i) {
+                    current_selected_i = possible_elements[0];
+                }
+
+                sel = xpath_data['size_pos'][current_selected_i];
+                ctx.strokeRect(current_selected_i.left * x_scale, current_selected_i.top * y_scale, current_selected_i.width * x_scale, current_selected_i.height * y_scale);
+                ctx.fillRect(current_selected_i.left * x_scale, current_selected_i.top * y_scale, current_selected_i.width * x_scale, current_selected_i.height * y_scale);
             }
 
+
         }.debounce(10));
     });
 
@@ -195,45 +202,37 @@ $(document).ready(function () {
 
 
     // callback for clicking on an xpath on the canvas
-    function process_selected(xpath_data_index) {
+    function process_selected(selected_in_xpath_list) {
         found_something = false;
         var first_available = $("ul#browser_steps li.empty").first();
 
 
-        if (xpath_data_index !== false) {
+        if (selected_in_xpath_list !== false) {
             // Nothing focused, so fill in a new one
             // if inpt type button or <button>
             // from the top, find the next not used one and use it
-            var x = xpath_data['size_pos'][xpath_data_index];
+            var x = selected_in_xpath_list;
             console.log(x);
             if (x && first_available.length) {
                 // @todo will it let you click shit that has a layer ontop? probably not.
-                if (x['tagtype'] === 'text' || x['tagtype'] === 'email' || x['tagName'] === 'textarea' || x['tagtype'] === 'password' || x['tagtype'] === 'search') {
+                if (x['tagtype'] === 'text' || x['tagtype'] === 'number' || x['tagtype'] === 'email' || x['tagName'] === 'textarea' || x['tagtype'] === 'password' || x['tagtype'] === 'search') {
                     $('select', first_available).val('Enter text in field').change();
                     $('input[type=text]', first_available).first().val(x['xpath']);
                     $('input[placeholder="Value"]', first_available).addClass('ok').click().focus();
                     found_something = true;
                 } else {
-                    if (x['isClickable'] || x['tagName'].startsWith('h') || x['tagName'] === 'a' || x['tagName'] === 'button' || x['tagtype'] === 'submit' || x['tagtype'] === 'checkbox' || x['tagtype'] === 'radio' || x['tagtype'] === 'li') {
+                    // There's no good way (that I know) to find if this
+                    // see https://stackoverflow.com/questions/446892/how-to-find-event-listeners-on-a-dom-node-in-javascript-or-in-debugging
+                    // https://codepen.io/azaslavsky/pen/DEJVWv
+
+                    // So we dont know if its really a clickable element or not :-(
+                    // Assume it is - then we dont fill the pages with unreliable "Click X,Y" selections
+                    // If you switch to "Click X,y" after an element here is setup, it will give the last co-ords anyway
+                    //if (x['isClickable'] || x['tagName'].startsWith('h') || x['tagName'] === 'a' || x['tagName'] === 'button' || x['tagtype'] === 'submit' || x['tagtype'] === 'checkbox' || x['tagtype'] === 'radio' || x['tagtype'] === 'li') {
                         $('select', first_available).val('Click element').change();
                         $('input[type=text]', first_available).first().val(x['xpath']);
                         found_something = true;
-                    }
-                }
-
-                first_available.xpath_data_index = xpath_data_index;
-
-                if (!found_something) {
-                    if (include_text_elements[0].checked === true) {
-                        // Suggest that we use as filter?
-                        // @todo filters should always be in the last steps, nothing non-filter after it
-                        found_something = true;
-                        ctx.strokeStyle = 'rgba(0,0,255, 0.9)';
-                        ctx.fillStyle = 'rgba(0,0,255, 0.1)';
-                        $('select', first_available).val('Extract text and use as filter').change();
-                        $('input[type=text]', first_available).first().val(x['xpath']);
-                        include_text_elements[0].checked = false;
-                    }
+                    //}
                 }
             }
         }
@@ -248,7 +247,7 @@ $(document).ready(function () {
 
     function start() {
         console.log("Starting browser-steps UI");
-        browsersteps_session_id = Date.now();
+        browsersteps_session_id = false;
         // @todo This setting of the first one should be done at the datalayer but wtforms doesnt wanna play nice
         $('#browser_steps >li:first-child').removeClass('empty');
         set_first_gotosite_disabled();
@@ -256,7 +255,7 @@ $(document).ready(function () {
         $('.clear,.remove', $('#browser_steps >li:first-child')).hide();
         $.ajax({
             type: "GET",
-            url: browser_steps_sync_url + "&browsersteps_session_id=" + browsersteps_session_id,
+            url: browser_steps_start_url,
             statusCode: {
                 400: function () {
                     // More than likely the CSRF token was lost when the server restarted
@@ -264,12 +263,12 @@ $(document).ready(function () {
                 }
             }
         }).done(function (data) {
-            xpath_data = data.xpath_data;
             $("#loading-status-text").fadeIn();
+            browsersteps_session_id = data.browsersteps_session_id;
             // This should trigger 'Goto site'
             console.log("Got startup response, requesting Goto-Site (first) step fake click");
             $('#browser_steps >li:first-child .apply').click();
-            browserless_seconds_remaining = data.browser_time_remaining;
+            browser_interface_seconds_remaining = 500;
             set_first_gotosite_disabled();
         }).fail(function (data) {
             console.log(data);
@@ -329,8 +328,14 @@ $(document).ready(function () {
             var s = '<div class="control">' + '<a data-step-index=' + i + ' class="pure-button button-secondary button-green button-xsmall apply" >Apply</a>&nbsp;';
             if (i > 0) {
                 // The first step never gets these (Goto-site)
-                s += '<a data-step-index=' + i + ' class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;' +
-                    '<a data-step-index=' + i + ' class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>';
+                s += `<a data-step-index="${i}" class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;` +
+                    `<a data-step-index="${i}" class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>`;
+
+                // if a screenshot is available
+                if (browser_steps_available_screenshots.includes(i.toString())) {
+                    var d = (browser_steps_last_error_step === i+1) ? 'before' : 'after';
+                    s += `&nbsp;<a data-step-index="${i}" class="pure-button button-secondary button-xsmall show-screenshot" title="Show screenshot from last run" data-type="${d}">Pic</a>&nbsp;`;
+                }
             }
             s += '</div>';
             $(this).append(s)
@@ -430,7 +435,6 @@ $(document).ready(function () {
             apply_buttons_disabled = false;
             $("#browsersteps-img").css('opacity', 1);
             $('ul#browser_steps li .control .apply').css('opacity', 1);
-            browserless_seconds_remaining = data.browser_time_remaining;
             $("#loading-status-text").hide();
             set_first_gotosite_disabled();
         }).fail(function (data) {
@@ -446,6 +450,24 @@ $(document).ready(function () {
 
     });
 
+    $('ul#browser_steps li .control .show-screenshot').click(function (element) {
+        var step_n = $(event.currentTarget).data('step-index');
+        w = window.open(this.href, "_blank", "width=640,height=480");
+        const t = $(event.currentTarget).data('type');
+
+        const url = browser_steps_fetch_screenshot_image_url + `&step_n=${step_n}&type=${t}`;
+        w.document.body.innerHTML = `<!DOCTYPE html>
+            <html lang="en">
+                <body>
+                    <img src="${url}" style="width: 100%" alt="Browser Step at step ${step_n} from last run." title="Browser Step at step ${step_n} from last run."/>
+                </body>
+        </html>`;
+        w.document.title = `Browser Step at step ${step_n} from last run.`;
+    });
+
+    if (browser_steps_last_error_step) {
+        $("ul#browser_steps>li:nth-child("+browser_steps_last_error_step+")").addClass("browser-step-with-error");
+    }
 
     $("ul#browser_steps select").change(function () {
         set_greyed_state();

changedetectionio/static/js/diff-overview.js

@@ -1,4 +1,20 @@
 $(document).ready(function () {
+    var csrftoken = $('input[name=csrf_token]').val();
+    $.ajaxSetup({
+        beforeSend: function (xhr, settings) {
+            if (!/^(GET|HEAD|OPTIONS|TRACE)$/i.test(settings.type) && !this.crossDomain) {
+                xhr.setRequestHeader("X-CSRFToken", csrftoken)
+            }
+        }
+    })
+
+    $('.needs-localtime').each(function () {
+        for (var option of this.options) {
+            var dateObject = new Date(option.value * 1000);
+            option.label = dateObject.toLocaleString(undefined, {dateStyle: "full", timeStyle: "medium"});
+        }
+    });
+
     // Load it when the #screenshot tab is in use, so we dont give a slow experience when waiting for the text diff to load
     window.addEventListener('hashchange', function (e) {
         toggle(location.hash);
@@ -15,11 +31,76 @@ $(document).ready(function () {
             $("#settings").hide();
         } else if (hash_name === '#extract') {
             $("#settings").hide();
-        }
-
-
-        else {
+        } else {
             $("#settings").show();
         }
     }
+
+    const article = $('.highlightable-filter')[0];
+
+    // We could also add the  'touchend' event for touch devices, but since
+    // most iOS/Android browsers already show a dialog when you select
+    // text (often with a Share option) we'll skip that
+    article.addEventListener('mouseup', dragTextHandler, false);
+    article.addEventListener('mousedown', clean, false);
+
+    function clean(event) {
+      $("#highlightSnippet").remove();
+    }
+
+
+    function dragTextHandler(event) {
+        console.log('mouseupped');
+
+        // Check if any text was selected
+        if (window.getSelection().toString().length > 0) {
+
+            // Find out how much (if any) user has scrolled
+            var scrollTop = (window.pageYOffset !== undefined) ? window.pageYOffset : (document.documentElement || document.body.parentNode || document.body).scrollTop;
+
+            // Get cursor position
+            const posX = event.clientX;
+            const posY = event.clientY + 20 + scrollTop;
+
+            // Append HTML to the body, create the "Tweet Selection" dialog
+            document.body.insertAdjacentHTML('beforeend', '<div id="highlightSnippet" style="position: absolute; top: ' + posY + 'px; left: ' + posX + 'px;"><div class="pure-form-message-inline" style="font-size: 70%">Ignore any change on any line which contains the selected text.</div><br><a data-mode="exact" href="javascript:void(0);" class="pure-button button-secondary button-xsmall">Ignore exact text</a>&nbsp;</div>');
+
+            if (/\d/.test(window.getSelection().toString())) {
+                // Offer regex replacement
+                document.getElementById("highlightSnippet").insertAdjacentHTML('beforeend', '<a data-mode="digit-regex"  href="javascript:void(0);" class="pure-button button-secondary button-xsmall">Ignore text including number changes</a>');
+            }
+
+            $('#highlightSnippet a').bind('click', function (e) {
+                if(!window.getSelection().toString().trim().length) {
+                    alert('Oops no text selected!');
+                    return;
+                }
+
+                $.ajax({
+                    type: "POST",
+                    url: highlight_submit_ignore_url,
+                    data: {'mode': $(this).data('mode'), 'selection': window.getSelection().toString()},
+                    statusCode: {
+                        400: function () {
+                            // More than likely the CSRF token was lost when the server restarted
+                            alert("There was a problem processing the request, please reload the page.");
+                        }
+                    }
+                }).done(function (data) {
+                    $("#highlightSnippet").html(data)
+                }).fail(function (data) {
+                    console.log(data);
+                    alert('There was an error communicating with the server.');
+                });
+            });
+
+        }
+    }
+
+    $('#diff-form').on('submit', function (e) {
+        if ($('select[name=from_version]').val() === $('select[name=to_version]').val()) {
+            e.preventDefault();
+            alert('Error - You are trying to compare the same version.');
+        }
+    });
 });

changedetectionio/static/js/diff-render.js

@@ -1,110 +1,115 @@
-var a = document.getElementById("a");
-var b = document.getElementById("b");
-var result = document.getElementById("result");
+$(document).ready(function () {
+    var a = document.getElementById("a");
+    var b = document.getElementById("b");
+    var result = document.getElementById("result");
+    var inputs;
 
-function changed() {
-  // https://github.com/kpdecker/jsdiff/issues/389
-  // I would love to use `{ignoreWhitespace: true}` here but it breaks the formatting
-  options = {
-    ignoreWhitespace: document.getElementById("ignoreWhitespace").checked,
-  };
+    $('#jump-next-diff').click(function () {
 
-  var diff = Diff[window.diffType](a.textContent, b.textContent, options);
-  var fragment = document.createDocumentFragment();
-  for (var i = 0; i < diff.length; i++) {
-    if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
-      var swap = diff[i];
-      diff[i] = diff[i + 1];
-      diff[i + 1] = swap;
+        var element = inputs[inputs.current];
+        var headerOffset = 80;
+        var elementPosition = element.getBoundingClientRect().top;
+        var offsetPosition = elementPosition - headerOffset + window.scrollY;
+
+        window.scrollTo({
+            top: offsetPosition,
+            behavior: "smooth",
+        });
+
+        inputs.current++;
+        if (inputs.current >= inputs.length) {
+            inputs.current = 0;
+        }
+    });
+
+    function changed() {
+        // https://github.com/kpdecker/jsdiff/issues/389
+        // I would love to use `{ignoreWhitespace: true}` here but it breaks the formatting
+        options = {
+            ignoreWhitespace: document.getElementById("ignoreWhitespace").checked,
+        };
+
+        var diff = Diff[window.diffType](a.textContent, b.textContent, options);
+        var fragment = document.createDocumentFragment();
+        for (var i = 0; i < diff.length; i++) {
+            if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
+                var swap = diff[i];
+                diff[i] = diff[i + 1];
+                diff[i + 1] = swap;
+            }
+
+            var node;
+            if (diff[i].removed) {
+                node = document.createElement("del");
+                node.classList.add("change");
+                const wrapper = node.appendChild(document.createElement("span"));
+                wrapper.appendChild(document.createTextNode(diff[i].value));
+            } else if (diff[i].added) {
+                node = document.createElement("ins");
+                node.classList.add("change");
+                const wrapper = node.appendChild(document.createElement("span"));
+                wrapper.appendChild(document.createTextNode(diff[i].value));
+            } else {
+                node = document.createTextNode(diff[i].value);
+            }
+            fragment.appendChild(node);
+        }
+
+        result.textContent = "";
+        result.appendChild(fragment);
+
+        // For nice mouse-over hover/title information
+        const removed_current_option = $('#diff-version option:selected')
+        if (removed_current_option) {
+            $('del').each(function () {
+                $(this).prop('title', 'Removed '+removed_current_option[0].label);
+            });
+        }
+        const inserted_current_option = $('#current-version option:selected')
+        if (removed_current_option) {
+            $('ins').each(function () {
+                $(this).prop('title', 'Inserted '+inserted_current_option[0].label);
+            });
+        }
+        // Set the list of possible differences to jump to
+        inputs = document.querySelectorAll('#diff-ui .change')
+        // Set the "current" diff pointer
+        inputs.current = 0;
+        // Goto diff
+        $('#jump-next-diff').click();
     }
 
-    var node;
-    if (diff[i].removed) {
-      node = document.createElement("del");
-      node.classList.add("change");
-      const wrapper = node.appendChild(document.createElement("span"));
-      wrapper.appendChild(document.createTextNode(diff[i].value));
-    } else if (diff[i].added) {
-      node = document.createElement("ins");
-      node.classList.add("change");
-      const wrapper = node.appendChild(document.createElement("span"));
-      wrapper.appendChild(document.createTextNode(diff[i].value));
-    } else {
-      node = document.createTextNode(diff[i].value);
-    }
-    fragment.appendChild(node);
-  }
 
-  result.textContent = "";
-  result.appendChild(fragment);
-
-  // Jump at start
-  inputs.current = 0;
-  next_diff();
-}
-
-window.onload = function () {
-  /* Convert what is options from UTC time.time() to local browser time */
-  var diffList = document.getElementById("diff-version");
-  if (typeof diffList != "undefined" && diffList != null) {
-    for (var option of diffList.options) {
-      var dateObject = new Date(option.value * 1000);
-      option.label = dateObject.toLocaleString();
-    }
-  }
-
-  /* Set current version date as local time in the browser also */
-  var current_v = document.getElementById("current-v-date");
-  var dateObject = new Date(newest_version_timestamp * 1000);
-  current_v.innerHTML = dateObject.toLocaleString();
-  onDiffTypeChange(
-    document.querySelector('#settings [name="diff_type"]:checked'),
-  );
-  changed();
-};
-
-a.onpaste = a.onchange = b.onpaste = b.onchange = changed;
-
-if ("oninput" in a) {
-  a.oninput = b.oninput = changed;
-} else {
-  a.onkeyup = b.onkeyup = changed;
-}
-
-function onDiffTypeChange(radio) {
-  window.diffType = radio.value;
-  // Not necessary
-  //	document.title = "Diff " + radio.value.slice(4);
-}
-
-var radio = document.getElementsByName("diff_type");
-for (var i = 0; i < radio.length; i++) {
-  radio[i].onchange = function (e) {
-    onDiffTypeChange(e.target);
+    onDiffTypeChange(
+        document.querySelector('#settings [name="diff_type"]:checked'),
+    );
     changed();
-  };
-}
 
-document.getElementById("ignoreWhitespace").onchange = function (e) {
-  changed();
-};
+    a.onpaste = a.onchange = b.onpaste = b.onchange = changed;
 
-var inputs = document.getElementsByClassName("change");
-inputs.current = 0;
+    if ("oninput" in a) {
+        a.oninput = b.oninput = changed;
+    } else {
+        a.onkeyup = b.onkeyup = changed;
+    }
 
-function next_diff() {
-  var element = inputs[inputs.current];
-  var headerOffset = 80;
-  var elementPosition = element.getBoundingClientRect().top;
-  var offsetPosition = elementPosition - headerOffset + window.scrollY;
+    function onDiffTypeChange(radio) {
+        window.diffType = radio.value;
+        // Not necessary
+        //	document.title = "Diff " + radio.value.slice(4);
+    }
 
-  window.scrollTo({
-    top: offsetPosition,
-    behavior: "smooth",
-  });
+    var radio = document.getElementsByName("diff_type");
+    for (var i = 0; i < radio.length; i++) {
+        radio[i].onchange = function (e) {
+            onDiffTypeChange(e.target);
+            changed();
+        };
+    }
+
+    document.getElementById("ignoreWhitespace").onchange = function (e) {
+        changed();
+    };
+
+});
 
-  inputs.current++;
-  if (inputs.current >= inputs.length) {
-    inputs.current = 0;
-  }
-}

changedetectionio/static/js/global-settings.js

@@ -1,19 +1,4 @@
 $(document).ready(function () {
-    function toggle() {
-        if ($('input[name="application-fetch_backend"]:checked').val() != 'html_requests') {
-            $('#requests-override-options').hide();
-            $('#webdriver-override-options').show();
-        } else {
-            $('#requests-override-options').show();
-            $('#webdriver-override-options').hide();
-        }
-    }
-
-    $('input[name="application-fetch_backend"]').click(function (e) {
-        toggle();
-    });
-    toggle();
-
     $("#api-key").hover(
         function () {
             $("#api-key-copy").html('copy').fadeIn();
@@ -32,5 +17,10 @@ $(document).ready(function () {
         window.getSelection().removeAllRanges();
 
     });
+
+    $("#notification-token-toggle").click(function (e) {
+        e.preventDefault();
+        $('#notification-tokens-info').toggle();
+    });
 });
 

changedetectionio/static/js/notifications.js

@@ -24,19 +24,15 @@ $(document).ready(function() {
     })
 
     data = {
-        window_url : window.location.href,
-        notification_urls : $('.notification-urls').val(),
-        notification_title : $('.notification-title').val(),
-        notification_body : $('.notification-body').val(),
-        notification_format : $('.notification-format').val(),
-    }
-    for (key in data) {
-      if (!data[key].length) {
-        alert(key+" is empty, cannot send test.")
-        return;
-      }
+      notification_body: $('#notification_body').val(),
+      notification_format: $('#notification_format').val(),
+      notification_title: $('#notification_title').val(),
+      notification_urls: $('.notification-urls').val(),
+      tags: $('#tags').val(),
+      window_url: window.location.href,
     }
 
+
     $.ajax({
       type: "POST",
       url: notification_base_url,
@@ -49,7 +45,7 @@ $(document).ready(function() {
       }
     }).done(function(data){
       console.log(data);
-      alert('Sent');
+      alert(data);
     }).fail(function(data){
       console.log(data);
       alert('There was an error communicating with the server.');

changedetectionio/static/js/preview.js

@@ -0,0 +1,53 @@
+function redirect_to_version(version) {
+    var currentUrl = window.location.href;
+    var baseUrl = currentUrl.split('?')[0]; // Base URL without query parameters
+    var anchor = '';
+
+    // Check if there is an anchor
+    if (baseUrl.indexOf('#') !== -1) {
+        anchor = baseUrl.substring(baseUrl.indexOf('#'));
+        baseUrl = baseUrl.substring(0, baseUrl.indexOf('#'));
+    }
+    window.location.href = baseUrl + '?version=' + version + anchor;
+}
+
+document.addEventListener('keydown', function (event) {
+    var selectElement = document.getElementById('preview-version');
+    if (selectElement) {
+        var selectedOption = selectElement.querySelector('option:checked');
+        if (selectedOption) {
+            if (event.key === 'ArrowLeft') {
+                if (selectedOption.previousElementSibling) {
+                    redirect_to_version(selectedOption.previousElementSibling.value);
+                }
+            } else if (event.key === 'ArrowRight') {
+                if (selectedOption.nextElementSibling) {
+                    redirect_to_version(selectedOption.nextElementSibling.value);
+                }
+            }
+        }
+    }
+});
+
+
+document.getElementById('preview-version').addEventListener('change', function () {
+    redirect_to_version(this.value);
+});
+
+var selectElement = document.getElementById('preview-version');
+if (selectElement) {
+    var selectedOption = selectElement.querySelector('option:checked');
+    if (selectedOption) {
+        if (selectedOption.previousElementSibling) {
+            document.getElementById('btn-previous').href = "?version=" + selectedOption.previousElementSibling.value;
+        } else {
+            document.getElementById('btn-previous').remove()
+        }
+        if (selectedOption.nextElementSibling) {
+            document.getElementById('btn-next').href = "?version=" + selectedOption.nextElementSibling.value;
+        } else {
+            document.getElementById('btn-next').remove()
+        }
+
+    }
+}

changedetectionio/static/js/recheck-proxy.js

@@ -0,0 +1,87 @@
+$(function () {
+    /* add container before each proxy location to show status */
+
+    var option_li = $('.fetch-backend-proxy li').filter(function() {
+        return $("input",this)[0].value.length >0;
+    });
+
+    //var option_li = $('.fetch-backend-proxy li');
+    var isActive = false;
+    $(option_li).prepend('<div class="proxy-status"></div>');
+    $(option_li).append('<div class="proxy-timing"></div><div class="proxy-check-details"></div>');
+
+    function set_proxy_check_status(proxy_key, state) {
+        // select input by value name
+        const proxy_li = $('input[value="' + proxy_key + '" ]').parent();
+        if (state['status'] === 'RUNNING') {
+            $('.proxy-status', proxy_li).html('<span class="spinner"></span>');
+        }
+        if (state['status'] === 'OK') {
+            $('.proxy-status', proxy_li).html('<span style="color: green; font-weight: bold" >OK</span>');
+            $('.proxy-check-details', proxy_li).html(state['text']);
+        }
+        if (state['status'] === 'ERROR' || state['status'] === 'ERROR OTHER') {
+            $('.proxy-status', proxy_li).html('<span style="color: red; font-weight: bold" >X</span>');
+            $('.proxy-check-details', proxy_li).html(state['text']);
+        }
+        $('.proxy-timing', proxy_li).html(state['time']);
+    }
+
+
+    function pollServer() {
+        if (isActive) {
+            window.setTimeout(function () {
+                $.ajax({
+                    url: proxy_recheck_status_url,
+                    success: function (data) {
+                        var all_done = true;
+                        $.each(data, function (proxy_key, state) {
+                            set_proxy_check_status(proxy_key, state);
+                            if (state['status'] === 'RUNNING') {
+                                all_done = false;
+                            }
+                        });
+
+                        if (all_done) {
+                            console.log("Shutting down poller, all done.")
+                            isActive = false;
+                        } else {
+                            pollServer();
+                        }
+                    },
+                    error: function () {
+                        //ERROR HANDLING
+                        pollServer();
+                    }
+                });
+            }, 2000);
+        }
+    }
+
+    $('#check-all-proxies').click(function (e) {
+        e.preventDefault()
+        $('body').addClass('proxy-check-active');
+        $('.proxy-check-details').html('');
+        $('.proxy-status').html('<span class="spinner"></span>').fadeIn();
+        $('.proxy-timing').html('');
+
+        // Request start, needs CSRF?
+        $.ajax({
+            type: "GET",
+            url: recheck_proxy_start_url,
+        }).done(function (data) {
+            $.each(data, function (proxy_key, state) {
+                set_proxy_check_status(proxy_key, state['status'])
+            });
+            isActive = true;
+            pollServer();
+
+        }).fail(function (data) {
+            console.log(data);
+            alert('There was an error communicating with the server.');
+        });
+
+    });
+
+});
+

changedetectionio/static/js/tabs.js

@@ -12,7 +12,7 @@ window.addEventListener('hashchange', function () {
 var has_errors = document.querySelectorAll(".messages .error");
 if (!has_errors.length) {
     if (document.location.hash == "") {
-        document.querySelector(".tabs ul li:first-child a").click();
+        location.replace(document.querySelector(".tabs ul li:first-child a").hash);
     } else {
         set_active_tab();
     }

changedetectionio/static/js/toggle-theme.js

@@ -3,22 +3,50 @@
  * Toggles theme between light and dark mode.
  */
 $(document).ready(function () {
-  const button = document.getElementsByClassName("toggle-theme")[0];
+    const button = document.getElementById("toggle-light-mode");
 
-  button.onclick = () => {
-    const htmlElement = document.getElementsByTagName("html");
-    const isDarkMode = htmlElement[0].dataset.darkmode === "true";
-    htmlElement[0].dataset.darkmode = !isDarkMode;
-    if (isDarkMode) {
-      button.classList.remove("dark");
-      setCookieValue(false);
-    } else {
-      button.classList.add("dark");
-      setCookieValue(true);
+    button.onclick = () => {
+        const htmlElement = document.getElementsByTagName("html");
+        const isDarkMode = htmlElement[0].dataset.darkmode === "true";
+        htmlElement[0].dataset.darkmode = !isDarkMode;
+        setCookieValue(!isDarkMode);
+    };
+
+    const setCookieValue = (value) => {
+        document.cookie = `css_dark_mode=${value};max-age=31536000;path=/`
     }
-  };
 
-  const setCookieValue = (value) => {
-    document.cookie = `css_dark_mode=${value};max-age=31536000;path=/`
-  }
+    // Search input box behaviour
+    const toggle_search = document.getElementById("toggle-search");
+    const search_q = document.getElementById("search-q");
+    if(search_q) {
+      window.addEventListener('keydown', function (e) {
+        if (e.altKey == true && e.keyCode == 83) {
+          search_q.classList.toggle('expanded');
+          search_q.focus();
+        }
+      });
+
+      search_q.onkeydown = (e) => {
+        var key = e.keyCode || e.which;
+        if (key === 13) {
+          document.searchForm.submit();
+        }
+      };
+      toggle_search.onclick = () => {
+        // Could be that they want to search something once text is in there
+        if (search_q.value.length) {
+          document.searchForm.submit();
+        } else {
+          // If not..
+          search_q.classList.toggle('expanded');
+          search_q.focus();
+        }
+      };
+    }
+
+    $('#heart-us').click(function () {
+        $("#overlay").toggleClass('visible');
+        heartpath.style.fill = document.getElementById("overlay").classList.contains("visible") ? '#ff0000' : 'var(--color-background)';
+    });
 });

changedetectionio/static/js/vis.js

@@ -0,0 +1,29 @@
+$(document).ready(function () {
+
+    // Lazy Hide/Show elements mechanism
+    $('[data-visible-for]').hide();
+    function show_related_elem(e) {
+        var n = $(e).attr('name') + "=" + $(e).val();
+        if (n === 'fetch_backend=system') {
+            n = "fetch_backend=" + default_system_fetch_backend;
+        }
+        $(`[data-visible-for~="${n}"]`).show();
+    }
+    $(':radio').on('keyup keypress blur change click', function (e) {
+        $(`[data-visible-for]`).hide();
+        $('.advanced-options').hide();
+        show_related_elem(this);
+    });
+
+    $(':radio:checked').each(function (e) {
+       show_related_elem(this);
+    })
+
+
+    // Show advanced
+    $('.show-advanced').click(function (e) {
+        $(this).closest('.tab-pane-inner').find('.advanced-options').each(function (e) {
+            $(this).toggle();
+        })
+    });
+});

changedetectionio/static/js/visual-selector.js

@@ -61,7 +61,12 @@ $(document).ready(function () {
     function bootstrap_visualselector() {
         if (1) {
             // bootstrap it, this will trigger everything else
-            $("img#selector-background").bind('load', function () {
+            $("img#selector-background").on("error", function () {
+                $('.fetching-update-notice').html("<strong>Ooops!</strong> The VisualSelector tool needs atleast one fetched page, please unpause the watch and/or wait for the watch to complete fetching and then reload this page.");
+                $('.fetching-update-notice').css('color','#bb0000');
+                $('#selector-current-xpath').hide();
+                $('#clear-selector').hide();
+            }).bind('load', function () {
                 console.log("Loaded background...");
                 c = document.getElementById("selector-canvas");
                 // greyed out fill context
@@ -79,10 +84,11 @@ $(document).ready(function () {
             }).attr("src", screenshot_url);
         }
         // Tell visualSelector that the image should update
-        var s = $("img#selector-background").attr('src')+"?"+ new Date().getTime();
-        $("img#selector-background").attr('src',s)
+        var s = $("img#selector-background").attr('src') + "?" + new Date().getTime();
+        $("img#selector-background").attr('src', s)
     }
 
+    // This is fired once the img src is loaded in bootstrap_visualselector()
     function fetch_data() {
         // Image is ready
         $('.fetching-update-notice').html("Fetching element data..");
@@ -99,7 +105,8 @@ $(document).ready(function () {
             reflow_selector();
             $('.fetching-update-notice').fadeOut();
         });
-    };
+
+    }
 
 
     function set_scale() {
@@ -142,7 +149,7 @@ $(document).ready(function () {
             // @todo In the future paint all that match
             for (const c of current_default_xpath) {
                 for (var i = selector_data['size_pos'].length; i !== 0; i--) {
-                    if (selector_data['size_pos'][i - 1].xpath === c) {
+                    if (selector_data['size_pos'][i - 1].xpath.trim() === c.trim()) {
                         console.log("highlighting " + c);
                         current_selected_i = i - 1;
                         highlight_current_selected_i();

changedetectionio/static/js/watch-overview.js

@@ -1,31 +1,53 @@
 $(function () {
-  // Remove unviewed status when normally clicked
-  $('.diff-link').click(function () {
-    $(this).closest('.unviewed').removeClass('unviewed');
-  });
+    // Remove unviewed status when normally clicked
+    $('.diff-link').click(function () {
+        $(this).closest('.unviewed').removeClass('unviewed');
+    });
 
+    $('td[data-timestamp]').each(function () {
+        $(this).prop('title', new Intl.DateTimeFormat(undefined,
+            {
+                dateStyle: 'full',
+                timeStyle: 'long'
+            }).format($(this).data('timestamp') * 1000));
+    })
 
-  $('.with-share-link > *').click(function () {
-      $("#copied-clipboard").remove();
+    $("#checkbox-assign-tag").click(function (e) {
+        $('#op_extradata').val(prompt("Enter a tag name"));
+    });
 
-      var range = document.createRange();
-      var n=$("#share-link")[0];
-      range.selectNode(n);
-      window.getSelection().removeAllRanges();
-      window.getSelection().addRange(range);
-      document.execCommand("copy");
-      window.getSelection().removeAllRanges();
+    $('.with-share-link > *').click(function () {
+        $("#copied-clipboard").remove();
 
-      $('.with-share-link').append('<span style="font-size: 80%; color: #fff;" id="copied-clipboard">Copied to clipboard</span>');
-      $("#copied-clipboard").fadeOut(2500, function() {
-       $(this).remove();
-      });
-  });
+        var range = document.createRange();
+        var n = $("#share-link")[0];
+        range.selectNode(n);
+        window.getSelection().removeAllRanges();
+        window.getSelection().addRange(range);
+        document.execCommand("copy");
+        window.getSelection().removeAllRanges();
+
+        $('.with-share-link').append('<span style="font-size: 80%; color: #fff;" id="copied-clipboard">Copied to clipboard</span>');
+        $("#copied-clipboard").fadeOut(2500, function () {
+            $(this).remove();
+        });
+    });
+
+    $(".watch-table tr").click(function (event) {
+        var tagName = event.target.tagName.toLowerCase();
+        if (tagName === 'tr' || tagName === 'td') {
+            var x = $('input[type=checkbox]', this);
+            if (x) {
+                $(x).click();
+            }
+        }
+    });
 
     // checkboxes - check all
     $("#check-all").click(function (e) {
         $('input[type=checkbox]').not(this).prop('checked', this.checked);
     });
+
     // checkboxes - show/hide buttons
     $("input[type=checkbox]").click(function (e) {
         if ($('input[type=checkbox]:checked').length) {

changedetectionio/static/js/watch-settings.js

@@ -1,40 +1,18 @@
-$(document).ready(function () {
-    function toggle() {
-        if ($('input[name="fetch_backend"]:checked').val() == 'html_webdriver') {
-            if (playwright_enabled) {
-                // playwright supports headers, so hide everything else
-                // See #664
-                $('#requests-override-options #request-method').hide();
-                $('#requests-override-options #request-body').hide();
-
-                // @todo connect this one up
-                $('#ignore-status-codes-option').hide();
-            } else {
-                // selenium/webdriver doesnt support anything afaik, hide it all
-                $('#requests-override-options').hide();
-            }
-
-            $('#webdriver-override-options').show();
-
-        } else if ($('input[name="fetch_backend"]:checked').val() == 'system') {
-            $('#requests-override-options #request-method').hide();
-            $('#requests-override-options #request-body').hide();
-            $('#ignore-status-codes-option').hide();
-            $('#requests-override-options').hide();
-            $('#webdriver-override-options').hide();
-        } else {
-
-            $('#requests-override-options').show();
-            $('#requests-override-options *:hidden').show();
-            $('#webdriver-override-options').hide();
-        }
+function toggleOpacity(checkboxSelector, fieldSelector) {
+    const checkbox = document.querySelector(checkboxSelector);
+    const fields = document.querySelectorAll(fieldSelector);
+    function updateOpacity() {
+        const opacityValue = checkbox.checked ? 0.6 : 1;
+        fields.forEach(field => {
+            field.style.opacity = opacityValue;
+        });
     }
+    // Initial setup
+    updateOpacity();
+    checkbox.addEventListener('change', updateOpacity);
+}
 
-    $('input[name="fetch_backend"]').click(function (e) {
-        toggle();
-    });
-    toggle();
-
+$(document).ready(function () {
     $('#notification-setting-reset-to-default').click(function (e) {
         $('#notification_title').val('');
         $('#notification_body').val('');
@@ -42,4 +20,11 @@ $(document).ready(function () {
         $('#notification_urls').val('');
         e.preventDefault();
     });
+    $("#notification-token-toggle").click(function (e) {
+        e.preventDefault();
+        $('#notification-tokens-info').toggle();
+    });
+
+    toggleOpacity('#time_between_check_use_default', '#time_between_check');
 });
+

changedetectionio/static/styles/diff.css

@@ -68,7 +68,7 @@
   --color-last-checked: #bbb;
   --color-text-footer: #444;
   --color-border-watch-table-cell: #eee;
-  --color-text-watch-tag-list: #e70069;
+  --color-text-watch-tag-list: rgba(231, 0, 105, 0.4);
   --color-background-new-watch-form: rgba(0, 0, 0, 0.05);
   --color-background-new-watch-input: var(--color-white);
   --color-text-new-watch-input: var(--color-text);
@@ -111,7 +111,7 @@ html[data-darkmode="true"] {
   --color-background-input: var(--color-grey-350);
   --color-text-input-description: var(--color-grey-600);
   --color-text-input-placeholder: var(--color-grey-600);
-  --color-text-watch-tag-list: #fa3e92;
+  --color-text-watch-tag-list: rgba(250, 62, 146, 0.4);
   --color-background-code: var(--color-grey-200);
   --color-background-tab: rgba(0, 0, 0, 0.2);
   --color-background-tab-hover: rgba(0, 0, 0, 0.5);
@@ -126,6 +126,8 @@ html[data-darkmode="true"] {
   html[data-darkmode="true"] .watch-table .title-col a[target="_blank"]::after,
   html[data-darkmode="true"] .watch-table .current-diff-url::after {
     filter: invert(0.5) hue-rotate(10deg) brightness(2); }
+  html[data-darkmode="true"] .watch-table .status-browsersteps {
+    filter: invert(0.5) hue-rotate(10deg) brightness(1.5); }
   html[data-darkmode="true"] .watch-table .watch-controls .state-off img {
     opacity: 0.3; }
   html[data-darkmode="true"] .watch-table .watch-controls .state-on img {
@@ -187,6 +189,10 @@ ins {
     padding: 0.5em; }
   #settings ins {
     padding: 0.5em; }
+  #settings option:checked {
+    font-weight: bold; }
+  #settings [type=radio], #settings [type=checkbox] {
+    vertical-align: middle; }
 
 .source {
   position: absolute;
@@ -218,3 +224,10 @@ td#diff-col div {
   text-align: center; }
   .tab-pane-inner#screenshot img {
     max-width: 99%; }
+
+#highlightSnippet {
+  background: var(--color-background);
+  padding: 1em;
+  border-radius: 5px;
+  background: var(--color-background);
+  box-shadow: 1px 1px 4px var(--color-shadow-jump); }

changedetectionio/static/styles/scss/diff.scss

@@ -77,6 +77,13 @@ ins {
   ins {
     padding: 0.5em;
   }
+
+  option:checked {
+    font-weight: bold;
+  }
+  [type=radio],[type=checkbox] {
+    vertical-align: middle;
+  }
 }
 
 .source {
@@ -119,3 +126,11 @@ td#diff-col div {
     max-width: 99%;
   }
 }
+
+#highlightSnippet {
+  background: var(--color-background);
+  padding: 1em;
+  border-radius: 5px;
+  background: var(--color-background);
+  box-shadow: 1px 1px 4px var(--color-shadow-jump);
+}

changedetectionio/static/styles/scss/parts/_browser-steps.scss

@@ -6,6 +6,10 @@
   }
 
   li {
+    &.browser-step-with-error {
+      background-color: #ffd6d6;
+      border-radius: 4px;
+    }
     &:not(:first-child) {
       &:hover {
         opacity: 1.0;
@@ -44,7 +48,7 @@
 #browser-steps .flex-wrapper {
   display: flex;
   flex-flow: row;
-  height: 600px; /*@todo make this dynamic */
+  height: 70vh;
 }
 
 /*  this is duplicate :( */

changedetectionio/static/styles/scss/parts/_darkmode.scss

@@ -0,0 +1,25 @@
+
+#toggle-light-mode {
+/*  width: 3rem;*/
+  /* default */
+  .icon-dark {
+    display: none;
+  }
+
+}
+
+html[data-darkmode="true"] {
+  #toggle-light-mode {
+    .icon-light {
+      display: none;
+    }
+
+    .icon-dark {
+      display: block;
+    }
+  }
+}
+
+
+
+

changedetectionio/static/styles/scss/parts/_extra_browsers.scss

@@ -0,0 +1,24 @@
+ul#requests-extra_browsers {
+  list-style: none;
+  /* tidy up the table to look more "inline" */
+  li {
+    > label {
+      display: none;
+    }
+
+  }
+
+  /* each proxy entry is a `table` */
+  table {
+    tr {
+      display: inline;
+    }
+  }
+}
+
+#extra-browsers-setting {
+  border: 1px solid var(--color-grey-800);
+  border-radius: 4px;
+  margin: 1em;
+   padding: 1em;
+}

changedetectionio/static/styles/scss/parts/_extra_proxies.scss

@@ -7,6 +7,7 @@ ul#requests-extra_proxies {
     }
 
   }
+
   /* each proxy entry is a `table` */
   table {
     tr {
@@ -15,3 +16,54 @@ ul#requests-extra_proxies {
   }
 }
 
+#request {
+  /* Auto proxy scan/checker */
+  label[for=proxy] {
+    display: inline-block;
+  }
+}
+
+body.proxy-check-active {
+  #request {
+    .proxy-status {
+      width: 2em;
+    }
+
+    .proxy-check-details {
+      font-size: 80%;
+      color: #555;
+      display: block;
+      padding-left: 4em;
+    }
+
+    .proxy-timing {
+      font-size: 80%;
+      padding-left: 1rem;
+      color: var(--color-link);
+    }
+  }
+}
+
+
+#recommended-proxy {
+  display: grid;
+  gap: 2rem;
+    @media  (min-width: 991px) {
+      grid-template-columns: repeat(2, 1fr);
+    }
+
+  > div {
+    border: 1px #aaa solid;
+    border-radius: 4px;
+    padding: 1em;
+  }
+
+  padding-bottom: 1em;
+}
+
+#extra-proxies-setting {
+  border: 1px solid var(--color-grey-800);
+  border-radius: 4px;
+    margin: 1em;
+   padding: 1em;
+}

changedetectionio/static/styles/scss/parts/_love.scss

@@ -0,0 +1,38 @@
+#overlay {
+
+  opacity: 0.95;
+  position: fixed;
+
+  width: 350px;
+  max-width: 100%;
+  height: 100%;
+  top: 0;
+  right: -350px;
+  background-color: var(--color-table-stripe);
+  z-index: 2;
+
+  transform: translateX(0);
+  transition: transform .5s ease;
+
+
+  &.visible {
+    transform: translateX(-100%);
+
+  }
+
+  .content {
+    font-size: 0.875rem;
+    padding: 1rem;
+    margin-top: 5rem;
+    max-width: 400px;
+    color: var(--color-watch-table-row-text);
+  }
+}
+
+#heartpath {
+  &:hover {
+    fill: #ff0000 !important;
+    transition: all ease 0.3s !important;
+  }
+  transition: all ease 0.3s !important;
+}

changedetectionio/static/styles/scss/parts/_menu.scss

@@ -0,0 +1,25 @@
+.pure-menu-link {
+  padding: 0.5rem 1em;
+  line-height: 1.2rem;
+}
+
+.pure-menu-item {
+  svg {
+    height: 1.2rem;
+  }
+  * {
+    vertical-align: middle;
+  }
+  .github-link {
+    height: 1.8rem;
+    display: block;
+    svg {
+      height: 100%;
+    }
+  }
+  .bi-heart {
+    &:hover {
+      cursor: pointer;
+    }
+  }
+}

changedetectionio/static/styles/scss/parts/_pagination.scss

@@ -0,0 +1,37 @@
+.pagination-page-info {
+  color: #fff;
+  font-size: 0.85rem;
+  text-transform: capitalize;
+}
+
+.pagination.menu {
+  > * {
+    display: inline-block;
+  }
+
+  li {
+    display: inline-block;
+  }
+
+  a {
+    padding: 0.65rem;
+    margin: 3px;
+    border: none;
+    background: #444;
+    border-radius: 2px;
+    color: var(--color-text-button);
+    &.disabled {
+      display: none;
+    }
+    &.active {
+      font-weight: bold;
+      background: #888;
+    }
+
+    &:hover {
+      background: #999;
+    }
+  }
+
+
+}

changedetectionio/static/styles/scss/parts/_variables.scss

@@ -75,7 +75,7 @@
   --color-text-footer: #444;
   --color-border-watch-table-cell: #eee;
 
-  --color-text-watch-tag-list: #e70069;
+  --color-text-watch-tag-list: rgba(231, 0, 105, 0.4);
   --color-background-new-watch-form: rgba(0, 0, 0, 0.05);
   --color-background-new-watch-input: var(--color-white);
   --color-text-new-watch-input: var(--color-text);
@@ -127,7 +127,7 @@ html[data-darkmode="true"] {
   --color-background-input: var(--color-grey-350);
   --color-text-input-description: var(--color-grey-600);
   --color-text-input-placeholder: var(--color-grey-600);
-  --color-text-watch-tag-list: #fa3e92;
+  --color-text-watch-tag-list: rgba(250, 62, 146, 0.4);
   --color-background-code: var(--color-grey-200);
 
   --color-background-tab: rgba(0, 0, 0, 0.2);
@@ -152,6 +152,10 @@ html[data-darkmode="true"] {
       filter: invert(.5) hue-rotate(10deg) brightness(2);
     }
 
+    .status-browsersteps {
+      filter: invert(.5) hue-rotate(10deg) brightness(1.5);
+    }
+
     .watch-controls {
       .state-off {
         img {

changedetectionio/static/styles/scss/parts/_visualselector.scss

@@ -0,0 +1,28 @@
+
+#selector-wrapper {
+  height: 100%;
+  max-height: 70vh;
+  overflow-y: scroll;
+  position: relative;
+
+  //width: 100%;
+  >img {
+    position: absolute;
+    z-index: 4;
+    max-width: 100%;
+  }
+
+  >canvas {
+    position: relative;
+    z-index: 5;
+    max-width: 100%;
+
+    &:hover {
+      cursor: pointer;
+    }
+  }
+}
+
+#selector-current-xpath {
+  font-size: 80%;
+}

changedetectionio/static/styles/scss/styles.scss

@@ -5,12 +5,18 @@
 @import "parts/_arrows";
 @import "parts/_browser-steps";
 @import "parts/_extra_proxies";
+@import "parts/_extra_browsers";
+@import "parts/_pagination";
 @import "parts/_spinners";
 @import "parts/_variables";
+@import "parts/_darkmode";
+@import "parts/_menu";
+@import "parts/_love";
 
 body {
   color: var(--color-text);
   background: var(--color-background-page);
+  font-family: Helvetica Neue, Helvetica, Lucida Grande, Arial, Ubuntu, Cantarell, Fira Sans, sans-serif;
 }
 
 .visually-hidden {
@@ -53,8 +59,26 @@ a.github-link {
   }
 }
 
-button.toggle-theme {
-  width: 4rem;
+#search-q {
+  opacity: 0;
+  -webkit-transition: all .9s ease;
+  -moz-transition: all .9s ease;
+  transition: all .9s ease;
+  width: 0;
+  display: none;
+  &.expanded {
+    width: auto;
+    display: inline-block;
+
+    opacity: 1;
+  }
+}
+#search-result-info {
+  color: #fff;
+}
+
+button.toggle-button {
+  vertical-align: middle;
   background: transparent;
   border: none;
   cursor: pointer;
@@ -73,19 +97,7 @@ button.toggle-theme {
     display: block;
   }
 
-  .icon-dark {
-    display: none;
-  }
 
-  &.dark {
-    .icon-light {
-      display: none;
-    }
-
-    .icon-dark {
-      display: block;
-    }
-  }
 }
 
 .pure-menu-horizontal {
@@ -175,8 +187,11 @@ code {
 }
 
 .watch-tag-list {
-  color: var(--color-text-watch-tag-list);
+  color: var(--color-white);
   white-space: nowrap;
+  background: var(--color-text-watch-tag-list);
+  border-radius: 5px;
+  padding: 2px 5px;
 }
 
 .box {
@@ -228,7 +243,6 @@ body::after {
 body::before {
   // background-image set in base.html so it works with reverse proxies etc
   content: "";
-  background-size: cover
 }
 
 body:after,
@@ -241,6 +255,10 @@ body:before {
   font-size: 85%;
 }
 
+.button-xsmall {
+  font-size: 70%;
+}
+
 .fetch-error {
   padding-top: 1em;
   font-size: 80%;
@@ -386,8 +404,24 @@ label {
   }
 
   #watch-add-wrapper-zone {
-    >div {
-      display: inline-block;
+
+    @media only screen and (min-width: 760px) {
+      display: flex;
+      gap: 0.3rem;
+      flex-direction: row;
+    }
+    /* URL field grows always, other stay static in width */
+    > span {
+      flex-grow: 0;
+
+      input {
+        width: 100%;
+        padding-right: 1em;
+      }
+
+      &:first-child {
+        flex-grow: 1;
+      }
     }
 
     @media only screen and (max-width: 760px) {
@@ -454,7 +488,11 @@ footer {
   padding: 10px;
 
   &#left-sticky {
-    left: 0px;
+    left: 0;
+    position: fixed;
+    border-top-right-radius: 5px;
+    border-bottom-right-radius: 5px;
+    box-shadow: 1px 1px 4px var(--color-shadow-jump);
   }
 
   &#right-sticky {
@@ -891,6 +929,24 @@ body.full-width {
   }
 }
 
+.border-fieldset {
+  h3 {
+    margin-top: 0;
+  }
+  border: 1px solid #ccc;
+  padding: 1rem;
+  border-radius: 5px;
+  margin-bottom: 1rem;
+  fieldset:last-of-type {
+    padding-bottom: 0;
+    .pure-control-group {
+      padding-bottom: 0;
+    }
+  }
+}
+
+
+
 ul {
   padding-left: 1em;
   padding-top: 0px;
@@ -907,37 +963,10 @@ ul {
   }
 }
 
-#selector-wrapper {
-  height: 100%;
-  overflow-y: scroll;
-  position: relative;
+@import "parts/_visualselector";
 
-  //width: 100%;
-  >img {
-    position: absolute;
-    z-index: 4;
-    max-width: 100%;
-  }
-
-  >canvas {
-    position: relative;
-    z-index: 5;
-    max-width: 100%;
-
-    &:hover {
-      cursor: pointer;
-    }
-  }
-}
-
-#selector-current-xpath {
-  font-size: 80%;
-}
-
-#webdriver-override-options {
-  input[type="number"] {
+#webdriver_delay {
     width: 5em;
-  }
 }
 
 #api-key {
@@ -1044,3 +1073,47 @@ ul {
   vertical-align: middle;
 }
 
+
+#quick-watch-processor-type {
+  color: #fff;
+  ul {
+    padding: 0.3rem;
+
+    li {
+      list-style: none;
+      font-size: 0.8rem;
+      > * {
+        display: inline-block;
+      }
+    }
+  }
+
+}
+
+.restock-label {
+  &.in-stock {
+    background-color: var(--color-background-button-green);
+    color: #fff;
+  }
+  &.not-in-stock {
+    background-color: var(--color-background-button-cancel);
+    color: #777;
+  }
+  padding: 3px;
+  border-radius: 3px;
+  white-space: nowrap;
+}
+
+#chrome-extension-link {
+  img {
+    height: 21px;
+    padding: 2px;
+    vertical-align: middle;
+  }
+
+  padding: 9px;
+  border: 1px solid var(--color-grey-800);
+  border-radius: 10px;
+  vertical-align: middle;
+}
+

changedetectionio/static/styles/styles.css

@@ -26,6 +26,9 @@
   #browser_steps li {
     list-style: decimal;
     padding: 5px; }
+    #browser_steps li.browser-step-with-error {
+      background-color: #ffd6d6;
+      border-radius: 4px; }
     #browser_steps li:not(:first-child):hover {
       opacity: 1.0; }
     #browser_steps li .control {
@@ -50,8 +53,7 @@
 #browser-steps .flex-wrapper {
   display: flex;
   flex-flow: row;
-  height: 600px;
-  /*@todo make this dynamic */ }
+  height: 70vh; }
 
 /*  this is duplicate :( */
 #browsersteps-selector-wrapper {
@@ -95,6 +97,84 @@ ul#requests-extra_proxies {
   ul#requests-extra_proxies table tr {
     display: inline; }
 
+#request {
+  /* Auto proxy scan/checker */ }
+  #request label[for=proxy] {
+    display: inline-block; }
+
+body.proxy-check-active #request .proxy-status {
+  width: 2em; }
+
+body.proxy-check-active #request .proxy-check-details {
+  font-size: 80%;
+  color: #555;
+  display: block;
+  padding-left: 4em; }
+
+body.proxy-check-active #request .proxy-timing {
+  font-size: 80%;
+  padding-left: 1rem;
+  color: var(--color-link); }
+
+#recommended-proxy {
+  display: grid;
+  gap: 2rem;
+  padding-bottom: 1em; }
+  @media (min-width: 991px) {
+    #recommended-proxy {
+      grid-template-columns: repeat(2, 1fr); } }
+  #recommended-proxy > div {
+    border: 1px #aaa solid;
+    border-radius: 4px;
+    padding: 1em; }
+
+#extra-proxies-setting {
+  border: 1px solid var(--color-grey-800);
+  border-radius: 4px;
+  margin: 1em;
+  padding: 1em; }
+
+ul#requests-extra_browsers {
+  list-style: none;
+  /* tidy up the table to look more "inline" */
+  /* each proxy entry is a `table` */ }
+  ul#requests-extra_browsers li > label {
+    display: none; }
+  ul#requests-extra_browsers table tr {
+    display: inline; }
+
+#extra-browsers-setting {
+  border: 1px solid var(--color-grey-800);
+  border-radius: 4px;
+  margin: 1em;
+  padding: 1em; }
+
+.pagination-page-info {
+  color: #fff;
+  font-size: 0.85rem;
+  text-transform: capitalize; }
+
+.pagination.menu > * {
+  display: inline-block; }
+
+.pagination.menu li {
+  display: inline-block; }
+
+.pagination.menu a {
+  padding: 0.65rem;
+  margin: 3px;
+  border: none;
+  background: #444;
+  border-radius: 2px;
+  color: var(--color-text-button); }
+  .pagination.menu a.disabled {
+    display: none; }
+  .pagination.menu a.active {
+    font-weight: bold;
+    background: #888; }
+  .pagination.menu a:hover {
+    background: #999; }
+
 /* spinner */
 .spinner,
 .spinner:after {
@@ -204,7 +284,7 @@ ul#requests-extra_proxies {
   --color-last-checked: #bbb;
   --color-text-footer: #444;
   --color-border-watch-table-cell: #eee;
-  --color-text-watch-tag-list: #e70069;
+  --color-text-watch-tag-list: rgba(231, 0, 105, 0.4);
   --color-background-new-watch-form: rgba(0, 0, 0, 0.05);
   --color-background-new-watch-input: var(--color-white);
   --color-text-new-watch-input: var(--color-text);
@@ -247,7 +327,7 @@ html[data-darkmode="true"] {
   --color-background-input: var(--color-grey-350);
   --color-text-input-description: var(--color-grey-600);
   --color-text-input-placeholder: var(--color-grey-600);
-  --color-text-watch-tag-list: #fa3e92;
+  --color-text-watch-tag-list: rgba(250, 62, 146, 0.4);
   --color-background-code: var(--color-grey-200);
   --color-background-tab: rgba(0, 0, 0, 0.2);
   --color-background-tab-hover: rgba(0, 0, 0, 0.5);
@@ -262,6 +342,8 @@ html[data-darkmode="true"] {
   html[data-darkmode="true"] .watch-table .title-col a[target="_blank"]::after,
   html[data-darkmode="true"] .watch-table .current-diff-url::after {
     filter: invert(0.5) hue-rotate(10deg) brightness(2); }
+  html[data-darkmode="true"] .watch-table .status-browsersteps {
+    filter: invert(0.5) hue-rotate(10deg) brightness(1.5); }
   html[data-darkmode="true"] .watch-table .watch-controls .state-off img {
     opacity: 0.3; }
   html[data-darkmode="true"] .watch-table .watch-controls .state-on img {
@@ -271,9 +353,68 @@ html[data-darkmode="true"] {
     html[data-darkmode="true"] .watch-table .unviewed.error {
       color: var(--color-watch-table-error); }
 
+#toggle-light-mode {
+  /*  width: 3rem;*/
+  /* default */ }
+  #toggle-light-mode .icon-dark {
+    display: none; }
+
+html[data-darkmode="true"] #toggle-light-mode .icon-light {
+  display: none; }
+
+html[data-darkmode="true"] #toggle-light-mode .icon-dark {
+  display: block; }
+
+.pure-menu-link {
+  padding: 0.5rem 1em;
+  line-height: 1.2rem; }
+
+.pure-menu-item svg {
+  height: 1.2rem; }
+
+.pure-menu-item * {
+  vertical-align: middle; }
+
+.pure-menu-item .github-link {
+  height: 1.8rem;
+  display: block; }
+  .pure-menu-item .github-link svg {
+    height: 100%; }
+
+.pure-menu-item .bi-heart:hover {
+  cursor: pointer; }
+
+#overlay {
+  opacity: 0.95;
+  position: fixed;
+  width: 350px;
+  max-width: 100%;
+  height: 100%;
+  top: 0;
+  right: -350px;
+  background-color: var(--color-table-stripe);
+  z-index: 2;
+  transform: translateX(0);
+  transition: transform .5s ease; }
+  #overlay.visible {
+    transform: translateX(-100%); }
+  #overlay .content {
+    font-size: 0.875rem;
+    padding: 1rem;
+    margin-top: 5rem;
+    max-width: 400px;
+    color: var(--color-watch-table-row-text); }
+
+#heartpath {
+  transition: all ease 0.3s !important; }
+  #heartpath:hover {
+    fill: #ff0000 !important;
+    transition: all ease 0.3s !important; }
+
 body {
   color: var(--color-text);
-  background: var(--color-background-page); }
+  background: var(--color-background-page);
+  font-family: Helvetica Neue, Helvetica, Lucida Grande, Arial, Ubuntu, Cantarell, Fira Sans, sans-serif; }
 
 .visually-hidden {
   clip: rect(0 0 0 0);
@@ -305,23 +446,32 @@ a.github-link {
   a.github-link:hover {
     color: var(--color-icon-github-hover); }
 
-button.toggle-theme {
-  width: 4rem;
+#search-q {
+  opacity: 0;
+  -webkit-transition: all .9s ease;
+  -moz-transition: all .9s ease;
+  transition: all .9s ease;
+  width: 0;
+  display: none; }
+  #search-q.expanded {
+    width: auto;
+    display: inline-block;
+    opacity: 1; }
+
+#search-result-info {
+  color: #fff; }
+
+button.toggle-button {
+  vertical-align: middle;
   background: transparent;
   border: none;
   cursor: pointer;
   color: var(--color-icon-github); }
-  button.toggle-theme:hover {
+  button.toggle-button:hover {
     color: var(--color-icon-github-hover); }
-  button.toggle-theme svg {
+  button.toggle-button svg {
     fill: currentColor; }
-  button.toggle-theme .icon-light {
-    display: block; }
-  button.toggle-theme .icon-dark {
-    display: none; }
-  button.toggle-theme.dark .icon-light {
-    display: none; }
-  button.toggle-theme.dark .icon-dark {
+  button.toggle-button .icon-light {
     display: block; }
 
 .pure-menu-horizontal {
@@ -382,8 +532,11 @@ code {
     margin: 0 3px 0 5px; }
 
 .watch-tag-list {
-  color: var(--color-text-watch-tag-list);
-  white-space: nowrap; }
+  color: var(--color-white);
+  white-space: nowrap;
+  background: var(--color-text-watch-tag-list);
+  border-radius: 5px;
+  padding: 2px 5px; }
 
 .box {
   max-width: 80%;
@@ -421,8 +574,7 @@ body::after {
   opacity: 0.91; }
 
 body::before {
-  content: "";
-  background-size: cover; }
+  content: ""; }
 
 body:after,
 body:before {
@@ -432,6 +584,9 @@ body:before {
 .button-small {
   font-size: 85%; }
 
+.button-xsmall {
+  font-size: 70%; }
+
 .fetch-error {
   padding-top: 1em;
   font-size: 80%;
@@ -532,11 +687,23 @@ label:hover {
   #new-watch-form legend {
     color: var(--color-text-legend);
     font-weight: bold; }
-  #new-watch-form #watch-add-wrapper-zone > div {
-    display: inline-block; }
-  @media only screen and (max-width: 760px) {
-    #new-watch-form #watch-add-wrapper-zone #url {
-      width: 100%; } }
+  #new-watch-form #watch-add-wrapper-zone {
+    /* URL field grows always, other stay static in width */ }
+    @media only screen and (min-width: 760px) {
+      #new-watch-form #watch-add-wrapper-zone {
+        display: flex;
+        gap: 0.3rem;
+        flex-direction: row; } }
+    #new-watch-form #watch-add-wrapper-zone > span {
+      flex-grow: 0; }
+      #new-watch-form #watch-add-wrapper-zone > span input {
+        width: 100%;
+        padding-right: 1em; }
+      #new-watch-form #watch-add-wrapper-zone > span:first-child {
+        flex-grow: 1; }
+    @media only screen and (max-width: 760px) {
+      #new-watch-form #watch-add-wrapper-zone #url {
+        width: 100%; } }
 
 #diff-col {
   padding-left: 40px; }
@@ -584,7 +751,11 @@ footer {
   background: var(--color-background);
   padding: 10px; }
   .sticky-tab#left-sticky {
-    left: 0px; }
+    left: 0;
+    position: fixed;
+    border-top-right-radius: 5px;
+    border-bottom-right-radius: 5px;
+    box-shadow: 1px 1px 4px var(--color-shadow-jump); }
   .sticky-tab#right-sticky {
     right: 0px; }
   .sticky-tab#hosted-sticky {
@@ -870,6 +1041,18 @@ body.full-width .edit-form {
     .edit-form .pure-form-message-inline code {
       font-size: .875em; }
 
+.border-fieldset {
+  border: 1px solid #ccc;
+  padding: 1rem;
+  border-radius: 5px;
+  margin-bottom: 1rem; }
+  .border-fieldset h3 {
+    margin-top: 0; }
+  .border-fieldset fieldset:last-of-type {
+    padding-bottom: 0; }
+    .border-fieldset fieldset:last-of-type .pure-control-group {
+      padding-bottom: 0; }
+
 ul {
   padding-left: 1em;
   padding-top: 0px;
@@ -882,6 +1065,7 @@ ul {
 
 #selector-wrapper {
   height: 100%;
+  max-height: 70vh;
   overflow-y: scroll;
   position: relative; }
   #selector-wrapper > img {
@@ -898,7 +1082,7 @@ ul {
 #selector-current-xpath {
   font-size: 80%; }
 
-#webdriver-override-options input[type="number"] {
+#webdriver_delay {
   width: 5em; }
 
 #api-key:hover {
@@ -980,3 +1164,34 @@ ul {
   display: inline-block;
   height: 0.8rem;
   vertical-align: middle; }
+
+#quick-watch-processor-type {
+  color: #fff; }
+  #quick-watch-processor-type ul {
+    padding: 0.3rem; }
+    #quick-watch-processor-type ul li {
+      list-style: none;
+      font-size: 0.8rem; }
+      #quick-watch-processor-type ul li > * {
+        display: inline-block; }
+
+.restock-label {
+  padding: 3px;
+  border-radius: 3px;
+  white-space: nowrap; }
+  .restock-label.in-stock {
+    background-color: var(--color-background-button-green);
+    color: #fff; }
+  .restock-label.not-in-stock {
+    background-color: var(--color-background-button-cancel);
+    color: #777; }
+
+#chrome-extension-link {
+  padding: 9px;
+  border: 1px solid var(--color-grey-800);
+  border-radius: 10px;
+  vertical-align: middle; }
+  #chrome-extension-link img {
+    height: 21px;
+    padding: 2px;
+    vertical-align: middle; }

changedetectionio/store.py

@@ -1,13 +1,14 @@
+from changedetectionio.strtobool import strtobool
+
 from flask import (
     flash
 )
 
 from . model import App, Watch
-from copy import deepcopy
+from copy import deepcopy, copy
 from os import path, unlink
 from threading import Lock
 import json
-import logging
 import os
 import re
 import requests
@@ -15,6 +16,12 @@ import secrets
 import threading
 import time
 import uuid as uuid_builder
+from loguru import logger
+
+# Because the server will run as a daemon and wont know the URL for notification links when firing off a notification
+BASE_URL_NOT_SET_TEXT = '("Base URL" not set - see settings - notifications)'
+
+dictfilt = lambda x, y: dict([ (i,x[i]) for i in x if i in set(y) ])
 
 # Is there an existing library to ensure some data store (JSON etc) is in sync with CRUD methods?
 # Open a github issue if you know something :)
@@ -35,6 +42,7 @@ class ChangeDetectionStore:
         self.__data = App.model()
         self.datastore_path = datastore_path
         self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
+        logger.info(f"Datastore path is '{self.json_store_path}'")
         self.needs_write = False
         self.start_time = time.time()
         self.stop_thread = False
@@ -75,12 +83,12 @@ class ChangeDetectionStore:
                 for uuid, watch in self.__data['watching'].items():
                     watch['uuid']=uuid
                     self.__data['watching'][uuid] = Watch.model(datastore_path=self.datastore_path, default=watch)
-                    print("Watching:", uuid, self.__data['watching'][uuid]['url'])
+                    logger.info(f"Watching: {uuid} {self.__data['watching'][uuid]['url']}")
 
         # First time ran, Create the datastore.
         except (FileNotFoundError):
             if include_default_watches:
-                print("No JSON DB found at {}, creating JSON store at {}".format(self.json_store_path, self.datastore_path))
+                logger.critical(f"No JSON DB found at {self.json_store_path}, creating JSON store at {self.datastore_path}")
                 self.add_watch(url='https://news.ycombinator.com/',
                                tag='Tech news',
                                extras={'fetch_backend': 'html_requests'})
@@ -88,6 +96,14 @@ class ChangeDetectionStore:
                 self.add_watch(url='https://changedetection.io/CHANGELOG.txt',
                                tag='changedetection.io',
                                extras={'fetch_backend': 'html_requests'})
+
+            updates_available = self.get_updates_available()
+            self.__data['settings']['application']['schema_version'] = updates_available.pop()
+
+        else:
+            # Bump the update version by running updates
+            self.run_updates()
+
         self.__data['version_tag'] = version_tag
 
         # Just to test that proxies.json if it exists, doesnt throw a parsing error on startup
@@ -108,25 +124,22 @@ class ChangeDetectionStore:
                 self.__data['app_guid'] = str(uuid_builder.uuid4())
 
         # Generate the URL access token for RSS feeds
-        if not 'rss_access_token' in self.__data['settings']['application']:
+        if not self.__data['settings']['application'].get('rss_access_token'):
             secret = secrets.token_hex(16)
             self.__data['settings']['application']['rss_access_token'] = secret
 
         # Generate the API access token
-        if not 'api_access_token' in self.__data['settings']['application']:
+        if not self.__data['settings']['application'].get('api_access_token'):
             secret = secrets.token_hex(16)
             self.__data['settings']['application']['api_access_token'] = secret
 
-        # Bump the update version by running updates
-        self.run_updates()
-
         self.needs_write = True
 
         # Finally start the thread that will manage periodic data saves to JSON
         save_data_thread = threading.Thread(target=self.save_datastore).start()
 
     def set_last_viewed(self, uuid, timestamp):
-        logging.debug("Setting watch UUID: {} last viewed to {}".format(uuid, int(timestamp)))
+        logger.debug(f"Setting watch UUID: {uuid} last viewed to {int(timestamp)}")
         self.data['watching'][uuid].update({'last_viewed': int(timestamp)})
         self.needs_write = True
 
@@ -165,32 +178,27 @@ class ChangeDetectionStore:
     @property
     def has_unviewed(self):
         for uuid, watch in self.__data['watching'].items():
-            if watch.viewed == False:
+            if watch.history_n >= 2 and watch.viewed == False:
                 return True
         return False
 
     @property
     def data(self):
-        # Re #152, Return env base_url if not overriden, @todo also prefer the proxy pass url
-        env_base_url = os.getenv('BASE_URL','')
-        if not self.__data['settings']['application']['base_url']:
-          self.__data['settings']['application']['base_url'] = env_base_url.strip('" ')
+        # Re #152, Return env base_url if not overriden
+        # Re #148 - Some people have just {{ base_url }} in the body or title, but this may break some notification services
+        #           like 'Join', so it's always best to atleast set something obvious so that they are not broken.
 
-        return self.__data
+        active_base_url = BASE_URL_NOT_SET_TEXT
+        if self.__data['settings']['application'].get('base_url'):
+            active_base_url = self.__data['settings']['application'].get('base_url')
+        elif os.getenv('BASE_URL'):
+            active_base_url = os.getenv('BASE_URL')
 
-    def get_all_tags(self):
-        tags = []
-        for uuid, watch in self.data['watching'].items():
-            if watch['tag'] is None:
-                continue
-            # Support for comma separated list of tags.
-            for tag in watch['tag'].split(','):
-                tag = tag.strip()
-                if tag not in tags:
-                    tags.append(tag)
-
-        tags.sort()
-        return tags
+        # I looked at various ways todo the following, but in the end just copying the dict seemed simplest/most reliable
+        # even given the memory tradeoff - if you know a better way.. maybe return d|self.__data.. or something
+        d = self.__data
+        d['settings']['application']['active_base_url'] = active_base_url.strip('" ')
+        return d
 
     # Delete a single watch by UUID
     def delete(self, uuid):
@@ -204,29 +212,29 @@ class ChangeDetectionStore:
                 # GitHub #30 also delete history records
                 for uuid in self.data['watching']:
                     path = pathlib.Path(os.path.join(self.datastore_path, uuid))
-                    shutil.rmtree(path)
-                    self.needs_write_urgent = True
+                    if os.path.exists(path):
+                        shutil.rmtree(path)
 
             else:
                 path = pathlib.Path(os.path.join(self.datastore_path, uuid))
-                shutil.rmtree(path)
+                if os.path.exists(path):
+                    shutil.rmtree(path)
                 del self.data['watching'][uuid]
 
-            self.needs_write_urgent = True
+        self.needs_write_urgent = True
 
     # Clone a watch by UUID
     def clone(self, uuid):
-        url = self.data['watching'][uuid]['url']
-        tag = self.data['watching'][uuid]['tag']
+        url = self.data['watching'][uuid].get('url')
         extras = self.data['watching'][uuid]
-        new_uuid = self.add_watch(url=url, tag=tag, extras=extras)
+        new_uuid = self.add_watch(url=url, extras=extras)
         return new_uuid
 
     def url_exists(self, url):
 
         # Probably their should be dict...
         for watch in self.data['watching'].values():
-            if watch['url'] == url:
+            if watch['url'].lower() == url.lower():
                 return True
 
         return False
@@ -236,12 +244,18 @@ class ChangeDetectionStore:
         import pathlib
 
         self.__data['watching'][uuid].update({
-                'last_checked': 0,
+                'browser_steps_last_error_step' : None,
+                'check_count': 0,
+                'fetch_time' : 0.0,
                 'has_ldjson_price_data': None,
+                'in_stock': None,
+                'last_checked': 0,
                 'last_error': False,
                 'last_notification_error': False,
                 'last_viewed': 0,
                 'previous_md5': False,
+                'previous_md5_before_filters': False,
+                'remote_server_reply': None,
                 'track_ldjson_price_data': None,
             })
 
@@ -254,16 +268,14 @@ class ChangeDetectionStore:
 
         self.needs_write_urgent = True
 
-    def add_watch(self, url, tag="", extras=None, write_to_disk_now=True):
+    def add_watch(self, url, tag='', extras=None, tag_uuids=None, write_to_disk_now=True):
 
         if extras is None:
             extras = {}
-        # should always be str
-        if tag is None or not tag:
-            tag = ''
 
         # Incase these are copied across, assume it's a reference and deepcopy()
         apply_extras = deepcopy(extras)
+        apply_extras['tags'] = [] if not apply_extras.get('tags') else apply_extras.get('tags')
 
         # Was it a share link? try to fetch the data
         if (url.startswith("https://changedetection.io/share/")):
@@ -287,8 +299,10 @@ class ChangeDetectionStore:
                     'method',
                     'paused',
                     'previous_md5',
+                    'processor',
                     'subtractive_selectors',
                     'tag',
+                    'tags',
                     'text_should_not_be_present',
                     'title',
                     'trigger_text',
@@ -303,7 +317,7 @@ class ChangeDetectionStore:
                             apply_extras['include_filters'] = [res['css_filter']]
 
             except Exception as e:
-                logging.error("Error fetching metadata for shared watch link", url, str(e))
+                logger.error(f"Error fetching metadata for shared watch link {url} {str(e)}")
                 flash("Error fetching metadata for {}".format(url), 'error')
                 return False
         from .model.Watch import is_safe_url
@@ -311,28 +325,46 @@ class ChangeDetectionStore:
             flash('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX', 'error')
             return None
 
-        with self.lock:
-            # #Re 569
-            new_watch = Watch.model(datastore_path=self.datastore_path, default={
-                'url': url,
-                'tag': tag
-            })
+        if tag and type(tag) == str:
+            # Then it's probably a string of the actual tag by name, split and add it
+            for t in tag.split(','):
+                # for each stripped tag, add tag as UUID
+                for a_t in t.split(','):
+                    tag_uuid = self.add_tag(a_t)
+                    apply_extras['tags'].append(tag_uuid)
 
-            new_uuid = new_watch['uuid']
-            logging.debug("Added URL {} - {}".format(url, new_uuid))
+        # Or if UUIDs given directly
+        if tag_uuids:
+            for t in tag_uuids:
+                apply_extras['tags'] = list(set(apply_extras['tags'] + [t.strip()]))
 
-            for k in ['uuid', 'history', 'last_checked', 'last_changed', 'newest_history_key', 'previous_md5', 'viewed']:
-                if k in apply_extras:
-                    del apply_extras[k]
+        # Make any uuids unique
+        if apply_extras.get('tags'):
+            apply_extras['tags'] = list(set(apply_extras.get('tags')))
 
-            new_watch.update(apply_extras)
-            self.__data['watching'][new_uuid] = new_watch
+        new_watch = Watch.model(datastore_path=self.datastore_path, url=url)
+
+        new_uuid = new_watch.get('uuid')
+
+        logger.debug(f"Adding URL {url} - {new_uuid}")
+
+        for k in ['uuid', 'history', 'last_checked', 'last_changed', 'newest_history_key', 'previous_md5', 'viewed']:
+            if k in apply_extras:
+                del apply_extras[k]
+
+        if not apply_extras.get('date_created'):
+            apply_extras['date_created'] = int(time.time())
+
+        new_watch.update(apply_extras)
+        new_watch.ensure_data_dir_exists()
+        self.__data['watching'][new_uuid] = new_watch
 
-        self.__data['watching'][new_uuid].ensure_data_dir_exists()
 
         if write_to_disk_now:
             self.sync_to_json()
 
+        logger.debug(f"Added '{url}'")
+
         return new_uuid
 
     def visualselector_data_is_ready(self, watch_uuid):
@@ -360,42 +392,38 @@ class ChangeDetectionStore:
             f.write(screenshot)
             f.close()
 
-        # Make a JPEG that's used in notifications (due to being a smaller size) available
-        from PIL import Image
-        im1 = Image.open(target_path)
-        im1.convert('RGB').save(target_path.replace('.png','.jpg'), quality=int(os.getenv("NOTIFICATION_SCREENSHOT_JPG_QUALITY", 75)))
-
 
     def save_error_text(self, watch_uuid, contents):
         if not self.data['watching'].get(watch_uuid):
             return
-        target_path = os.path.join(self.datastore_path, watch_uuid, "last-error.txt")
 
+        self.data['watching'][watch_uuid].ensure_data_dir_exists()
+        target_path = os.path.join(self.datastore_path, watch_uuid, "last-error.txt")
         with open(target_path, 'w') as f:
             f.write(contents)
 
     def save_xpath_data(self, watch_uuid, data, as_error=False):
+
         if not self.data['watching'].get(watch_uuid):
             return
         if as_error:
             target_path = os.path.join(self.datastore_path, watch_uuid, "elements-error.json")
         else:
             target_path = os.path.join(self.datastore_path, watch_uuid, "elements.json")
-
+        self.data['watching'][watch_uuid].ensure_data_dir_exists()
         with open(target_path, 'w') as f:
             f.write(json.dumps(data))
             f.close()
 
 
     def sync_to_json(self):
-        logging.info("Saving JSON..")
-        print("Saving JSON..")
+        logger.info("Saving JSON..")
         try:
             data = deepcopy(self.__data)
         except RuntimeError as e:
             # Try again in 15 seconds
             time.sleep(15)
-            logging.error ("! Data changed when writing to JSON, trying again.. %s", str(e))
+            logger.error(f"! Data changed when writing to JSON, trying again.. {str(e)}")
             self.sync_to_json()
             return
         else:
@@ -408,7 +436,7 @@ class ChangeDetectionStore:
                     json.dump(data, json_file, indent=4)
                 os.replace(self.json_store_path+".tmp", self.json_store_path)
             except Exception as e:
-                logging.error("Error writing JSON!! (Main JSON file save was skipped) : %s", str(e))
+                logger.error(f"Error writing JSON!! (Main JSON file save was skipped) : {str(e)}")
 
             self.needs_write = False
             self.needs_write_urgent = False
@@ -419,7 +447,16 @@ class ChangeDetectionStore:
 
         while True:
             if self.stop_thread:
-                print("Shutting down datastore thread")
+                # Suppressing "Logging error in Loguru Handler #0" during CICD.
+                # Not a meaningful difference for a real use-case just for CICD.
+                # the side effect is a "Shutting down datastore thread" message
+                # at the end of each test.
+                # But still more looking better.
+                import sys
+                logger.remove()
+                logger.add(sys.stderr)
+
+                logger.critical("Shutting down datastore thread")
                 return
 
             if self.needs_write or self.needs_write_urgent:
@@ -435,7 +472,7 @@ class ChangeDetectionStore:
     # Go through the datastore path and remove any snapshots that are not mentioned in the index
     # This usually is not used, but can be handy.
     def remove_unused_snapshots(self):
-        print ("Removing snapshots from datastore that are not in the index..")
+        logger.info("Removing snapshots from datastore that are not in the index..")
 
         index=[]
         for uuid in self.data['watching']:
@@ -448,7 +485,7 @@ class ChangeDetectionStore:
         for uuid in self.data['watching']:
             for item in pathlib.Path(self.datastore_path).rglob(uuid+"/*.txt"):
                 if not str(item) in index:
-                    print ("Removing",item)
+                    logger.info(f"Removing {item}")
                     unlink(item)
 
     @property
@@ -471,12 +508,12 @@ class ChangeDetectionStore:
                     k = "ui-" + str(i) + proxy.get('proxy_name')
                     proxy_list[k] = {'label': proxy.get('proxy_name'), 'url': proxy.get('proxy_url')}
 
+        if proxy_list and strtobool(os.getenv('ENABLE_NO_PROXY_OPTION', 'True')):
+            proxy_list["no-proxy"] = {'label': "No proxy", 'url': ''}
 
         return proxy_list if len(proxy_list) else None
 
 
-
-
     def get_preferred_proxy_for_watch(self, uuid):
         """
         Returns the preferred proxy by ID key
@@ -490,6 +527,9 @@ class ChangeDetectionStore:
         # If it's a valid one
         watch = self.data['watching'].get(uuid)
 
+        if strtobool(os.getenv('ENABLE_NO_PROXY_OPTION', 'True')) and watch.get('proxy') == "no-proxy":
+            return None
+
         if watch.get('proxy') and watch.get('proxy') in list(self.proxy_list.keys()):
             return watch.get('proxy')
 
@@ -508,14 +548,121 @@ class ChangeDetectionStore:
 
         return None
 
-    # Run all updates
-    # IMPORTANT - Each update could be run even when they have a new install and the schema is correct
-    #             So therefor - each `update_n` should be very careful about checking if it needs to actually run
-    #             Probably we should bump the current update schema version with each tag release version?
-    def run_updates(self):
-        import inspect
-        import shutil
+    @property
+    def has_extra_headers_file(self):
+        filepath = os.path.join(self.datastore_path, 'headers.txt')
+        return os.path.isfile(filepath)
 
+    def get_all_base_headers(self):
+        headers = {}
+        # Global app settings
+        headers.update(self.data['settings'].get('headers', {}))
+
+        return headers
+
+    def get_all_headers_in_textfile_for_watch(self, uuid):
+        from .model.App import parse_headers_from_text_file
+        headers = {}
+
+        # Global in /datastore/headers.txt
+        filepath = os.path.join(self.datastore_path, 'headers.txt')
+        try:
+            if os.path.isfile(filepath):
+                headers.update(parse_headers_from_text_file(filepath))
+        except Exception as e:
+            logger.error(f"ERROR reading headers.txt at {filepath} {str(e)}")
+
+        watch = self.data['watching'].get(uuid)
+        if watch:
+
+            # In /datastore/xyz-xyz/headers.txt
+            filepath = os.path.join(watch.watch_data_dir, 'headers.txt')
+            try:
+                if os.path.isfile(filepath):
+                    headers.update(parse_headers_from_text_file(filepath))
+            except Exception as e:
+                logger.error(f"ERROR reading headers.txt at {filepath} {str(e)}")
+
+            # In /datastore/tag-name.txt
+            tags = self.get_all_tags_for_watch(uuid=uuid)
+            for tag_uuid, tag in tags.items():
+                fname = "headers-"+re.sub(r'[\W_]', '', tag.get('title')).lower().strip() + ".txt"
+                filepath = os.path.join(self.datastore_path, fname)
+                try:
+                    if os.path.isfile(filepath):
+                        headers.update(parse_headers_from_text_file(filepath))
+                except Exception as e:
+                    logger.error(f"ERROR reading headers.txt at {filepath} {str(e)}")
+
+        return headers
+
+    def get_tag_overrides_for_watch(self, uuid, attr):
+        tags = self.get_all_tags_for_watch(uuid=uuid)
+        ret = []
+
+        if tags:
+            for tag_uuid, tag in tags.items():
+                if attr in tag and tag[attr]:
+                    ret=[*ret, *tag[attr]]
+
+        return ret
+
+    def add_tag(self, name):
+        # If name exists, return that
+        n = name.strip().lower()
+        logger.debug(f">>> Adding new tag - '{n}'")
+        if not n:
+            return False
+
+        for uuid, tag in self.__data['settings']['application'].get('tags', {}).items():
+            if n == tag.get('title', '').lower().strip():
+                logger.warning(f"Tag '{name}' already exists, skipping creation.")
+                return uuid
+
+        # Eventually almost everything todo with a watch will apply as a Tag
+        # So we use the same model as a Watch
+        with self.lock:
+            new_tag = Watch.model(datastore_path=self.datastore_path, default={
+                'title': name.strip(),
+                'date_created': int(time.time())
+            })
+
+            new_uuid = new_tag.get('uuid')
+
+            self.__data['settings']['application']['tags'][new_uuid] = new_tag
+
+        return new_uuid
+
+    def get_all_tags_for_watch(self, uuid):
+        """This should be in Watch model but Watch doesn't have access to datastore, not sure how to solve that yet"""
+        watch = self.data['watching'].get(uuid)
+
+        # Should return a dict of full tag info linked by UUID
+        if watch:
+            return dictfilt(self.__data['settings']['application']['tags'], watch.get('tags', []))
+
+        return {}
+
+    @property
+    def extra_browsers(self):
+        res = []
+        p = list(filter(
+            lambda s: (s.get('browser_name') and s.get('browser_connection_url')),
+            self.__data['settings']['requests'].get('extra_browsers', [])))
+        if p:
+            for i in p:
+                res.append(("extra_browser_"+i['browser_name'], i['browser_name']))
+
+        return res
+
+    def tag_exists_by_name(self, tag_name):
+        # Check if any tag dictionary has a 'title' attribute matching the provided tag_name
+        tags = self.__data['settings']['application']['tags'].values()
+        return next((v for v in tags if v.get('title', '').lower() == tag_name.lower()),
+                    None)
+
+    def get_updates_available(self):
+        import inspect
         updates_available = []
         for i, o in inspect.getmembers(self, predicate=inspect.ismethod):
             m = re.search(r'update_(\d+)$', i)
@@ -523,9 +670,18 @@ class ChangeDetectionStore:
                 updates_available.append(int(m.group(1)))
         updates_available.sort()
 
+        return updates_available
+
+    # Run all updates
+    # IMPORTANT - Each update could be run even when they have a new install and the schema is correct
+    #             So therefor - each `update_n` should be very careful about checking if it needs to actually run
+    #             Probably we should bump the current update schema version with each tag release version?
+    def run_updates(self):
+        import shutil
+        updates_available = self.get_updates_available()
         for update_n in updates_available:
             if update_n > self.__data['settings']['application']['schema_version']:
-                print ("Applying update_{}".format((update_n)))
+                logger.critical(f"Applying update_{update_n}")
                 # Wont exist on fresh installs
                 if os.path.exists(self.json_store_path):
                     shutil.copyfile(self.json_store_path, self.datastore_path+"/url-watches-before-{}.json".format(update_n))
@@ -533,8 +689,8 @@ class ChangeDetectionStore:
                 try:
                     update_method = getattr(self, "update_{}".format(update_n))()
                 except Exception as e:
-                    print("Error while trying update_{}".format((update_n)))
-                    print(e)
+                    logger.error(f"Error while trying update_{update_n}")
+                    logger.error(e)
                     # Don't run any more updates
                     return
                 else:
@@ -572,7 +728,7 @@ class ChangeDetectionStore:
                         with open(os.path.join(target_path, "history.txt"), "w") as f:
                             f.writelines(history)
                     else:
-                        logging.warning("Datastore history directory {} does not exist, skipping history import.".format(target_path))
+                        logger.warning(f"Datastore history directory {target_path} does not exist, skipping history import.")
 
                 # No longer needed, dynamically pulled from the disk when needed.
                 # But we should set it back to a empty dict so we don't break if this schema runs on an earlier version.
@@ -683,3 +839,48 @@ class ChangeDetectionStore:
             except:
                 continue
         return
+
+    # Create tag objects and their references from existing tag text
+    def update_12(self):
+        i = 0
+        for uuid, watch in self.data['watching'].items():
+            # Split out and convert old tag string
+            tag = watch.get('tag')
+            if tag:
+                tag_uuids = []
+                for t in tag.split(','):
+                    tag_uuids.append(self.add_tag(name=t))
+
+                self.data['watching'][uuid]['tags'] = tag_uuids
+
+    # #1775 - Update 11 did not update the records correctly when adding 'date_created' values for sorting
+    def update_13(self):
+        i = 0
+        for uuid, watch in self.data['watching'].items():
+            if not watch.get('date_created'):
+                self.data['watching'][uuid]['date_created'] = i
+            i+=1
+        return
+
+    # #1774 - protect xpath1 against migration
+    def update_14(self):
+        for awatch in self.__data["watching"]:
+            if self.__data["watching"][awatch]['include_filters']:
+                for num, selector in enumerate(self.__data["watching"][awatch]['include_filters']):
+                    if selector.startswith('/'):
+                        self.__data["watching"][awatch]['include_filters'][num] = 'xpath1:' + selector
+                    if selector.startswith('xpath:'):
+                        self.__data["watching"][awatch]['include_filters'][num] = selector.replace('xpath:', 'xpath1:', 1)
+
+    # Use more obvious default time setting
+    def update_15(self):
+        for uuid in self.__data["watching"]:
+            if self.__data["watching"][uuid]['time_between_check'] == self.__data['settings']['requests']['time_between_check']:
+                # What the old logic was, which was pretty confusing
+                self.__data["watching"][uuid]['time_between_check_use_default'] = True
+            elif all(value is None or value == 0 for value in self.__data["watching"][uuid]['time_between_check'].values()):
+                self.__data["watching"][uuid]['time_between_check_use_default'] = True
+            else:
+                # Something custom here
+                self.__data["watching"][uuid]['time_between_check_use_default'] = False
+