Updating pyppeteer-ng (mainly newer pillow release)

Added `prodotto esaurito` - Italian for out of stock

.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 +1,10 @@
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: "weekly"
+    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
@@ -88,16 +88,17 @@ 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
+          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
 
@@ -105,7 +106,7 @@ jobs:
       - 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
@@ -115,19 +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
+          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/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: |
@@ -27,64 +27,197 @@ 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 "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" -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'
           
           # 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: |
+          # 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: 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'
-          
-          # Playwright/Browserless fetch
-          docker run --rm -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'
-          
-          # Settings headers playwright tests - Call back in from Browserless, check headers
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless: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'
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "USE_EXPERIMENTAL_PUPPETEER_FETCH=yes" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless: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'
-          
-          # restock detection via playwright - added name=changedet here so that playwright/browserless can connect to it
-          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless: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'
 
-      - name: Test with puppeteer fetcher and disk cache
+      - name: Specific tests in built container for headers and requests checks with Selenium
         run: |
-          docker run --rm -e "PUPPETEER_DISK_CACHE=/tmp/data/" -e "USE_EXPERIMENTAL_PUPPETEER_FETCH=yes" -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'
-          # Browserless would have had -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" added above
+          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'
 
-      - name: Test proxy interaction
+# 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

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

@@ -1,36 +0,0 @@
-name: ChangeDetection.io PIP package test
-
-# Triggers the workflow on push or pull request events
-
-# This line doesnt work, even tho it is the documented one
-on: [push, pull_request]
-
-  # Changes to requirements.txt packages and Dockerfile may or may not always be compatible with arm etc, so worth testing
-  # @todo: some kind of path filter for requirements.txt and Dockerfile
-jobs:
-  test-pip-build-basics:
-    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 the basic pip built package runs without error
-          run: |
-            set -e
-            mkdir dist
-            pip3 install wheel
-            python3 setup.py bdist_wheel            
-            pip3 install -r requirements.txt
-            rm ./changedetection.py
-            rm -rf changedetectio
-            
-            pip3 install dist/changedetection.io*.whl
-            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

Dockerfile

@@ -1,5 +1,8 @@
 # pip dependencies install stage
-FROM python:3.10-slim-bullseye 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-bullseye
+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

@@ -1,8 +1,8 @@
 recursive-include changedetectionio/api *
 recursive-include changedetectionio/blueprint *
+recursive-include changedetectionio/content_fetchers *
 recursive-include changedetectionio/model *
 recursive-include changedetectionio/processors *
-recursive-include changedetectionio/res *
 recursive-include changedetectionio/static *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/tests *
@@ -10,6 +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://changedetection.io)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring, list of websites with changes"  title="Self-hosted web page change monitoring, list of websites with changes"  />](https://changedetection.io)
 
 
 [**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://changedetection.io) 
 
 
-#### 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

@@ -5,24 +5,25 @@
 _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://changedetection.io?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://changedetection.io) , _half the price of other website change monitoring services!_
+[**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://changedetection.io?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.
 
@@ -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://changedetection.io?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.
@@ -67,13 +68,14 @@ Requires Playwright to be enabled.
 - 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
@@ -85,8 +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
@@ -94,7 +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
@@ -133,10 +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
@@ -144,7 +156,7 @@ 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. 
+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
@@ -183,7 +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.
 
@@ -223,12 +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)
@@ -238,7 +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://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!)
+Firstly, 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!)
 
 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)
 
@@ -258,3 +277,13 @@ 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 distutils.util 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
@@ -199,7 +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
@@ -209,7 +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'):
@@ -240,7 +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,
@@ -275,11 +281,14 @@ class CreateWatch(Resource):
             if tag_limit and not any(v.get('title').lower() == tag_limit for k, v in tags.items()):
                 continue
 
-            list[uuid] = {'url': watch['url'],
-                       'title': watch['title'],
-                       'last_checked': watch['last_checked'],
-                       'last_changed': watch.last_changed,
-                       'last_error': watch['last_error']}
+            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():
@@ -288,6 +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
@@ -300,7 +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

@@ -4,29 +4,21 @@
 # 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 flask import Blueprint, request, make_response
 import os
-import logging
+
 from changedetectionio.store import ChangeDetectionStore
-from changedetectionio import login_optionally_required
+from changedetectionio.flask_app import login_optionally_required
+from loguru import logger
 
 browsersteps_sessions = {}
 io_interface_context = None
@@ -44,7 +36,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
 
         # We keep the playwright session open for many minutes
-        seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
+        keepalive_seconds = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
 
         browsersteps_start_session = {'start_time': time.time()}
 
@@ -56,16 +48,18 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             # 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}"
 
-        # 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_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(
-                os.getenv('PLAYWRIGHT_DRIVER_URL', '') + keepalive)
+            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)
@@ -85,7 +79,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 if parsed.password:
                     proxy['password'] = parsed.password
 
-                print("Browser Steps: UUID {} selected proxy {}".format(watch_uuid, proxy_url))
+                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(
@@ -112,18 +106,43 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         if not watch_uuid:
             return make_response('No Watch UUID specified', 500)
 
-        print("Starting connection with playwright")
-        logging.debug("browser_steps.py connecting")
+        logger.debug("Starting connection with playwright")
+        logger.debug("browser_steps.py connecting")
         browsersteps_sessions[browsersteps_session_id] = start_browsersteps_session(watch_uuid)
-        print("Starting connection with playwright - done")
+        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 playwright._impl._errors
         global browsersteps_sessions
         from changedetectionio.blueprint.browser_steps import browser_steps
 
@@ -161,7 +180,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                                          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)
 

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -4,6 +4,9 @@ import os
 import time
 import re
 from random import randint
+from loguru import logger
+
+from changedetectionio.content_fetchers.base import manage_user_agent
 
 # Two flags, tell the JS which of the "Selector" or "Value" field should be enabled in the front end
 # 0- off, 1- on
@@ -53,7 +56,7 @@ 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 and selector.startswith('/') and not selector.startswith('//'):
             selector = "xpath=" + selector
@@ -72,18 +75,18 @@ class steppable_browser_interface():
 
         action_handler(selector, optional_value)
         self.page.wait_for_timeout(1.5 * 1000)
-        print("Call action done in", time.time() - now)
+        logger.debug(f"Call action done in {time.time()-now:.2f}s")
 
     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(value, timeout=0, wait_until='commit')
-
-        # 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)
+        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
 
     def action_click_element_containing_text(self, selector=None, value=''):
         if not len(value.strip()):
@@ -99,18 +102,19 @@ 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=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:
@@ -122,6 +126,9 @@ 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()))
@@ -138,13 +145,13 @@ class steppable_browser_interface():
     def action_wait_for_text(self, selector, value):
         import json
         v = json.dumps(value)
-        self.page.wait_for_function(f'document.querySelector("body").innerText.includes({v});', timeout=90000)
+        self.page.wait_for_function(f'document.querySelector("body").innerText.includes({v});', timeout=30000)
 
     def action_wait_for_text_in_element(self, selector, value):
         import json
         s = json.dumps(selector)
         v = json.dumps(value)
-        self.page.wait_for_function(f'document.querySelector({s}).innerText.includes({v});', timeout=90000)
+        self.page.wait_for_function(f'document.querySelector({s}).innerText.includes({v});', timeout=30000)
 
     # @todo - in the future make some popout interface to capture what needs to be set
     # https://playwright.dev/python/docs/api/class-keyboard
@@ -164,7 +171,7 @@ 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
@@ -173,6 +180,7 @@ 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(
@@ -187,7 +195,8 @@ 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):
+        self.headers = headers or {}
         self.age_start = time.time()
         self.playwright_browser = playwright_browser
         if self.context is None:
@@ -201,16 +210,17 @@ 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)
@@ -223,11 +233,11 @@ 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):
@@ -238,7 +248,7 @@ 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)
 
@@ -253,7 +263,7 @@ 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?
@@ -273,10 +283,10 @@ 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 +1,116 @@
+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
+
+        status = {'status': '', 'length': 0, 'text': ''}
+        from jinja2 import Environment, BaseLoader
+
+        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'):
+            status['text'] = Environment(loader=BaseLoader()).from_string('{{text|e}}').render({'text': status['text']})
+
+        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

@@ -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/__init__.py

@@ -1,6 +1,6 @@
 from flask import Blueprint, request, make_response, render_template, flash, url_for, redirect
 from changedetectionio.store import ChangeDetectionStore
-from changedetectionio import login_optionally_required
+from changedetectionio.flask_app import login_optionally_required
 
 
 def construct_blueprint(datastore: ChangeDetectionStore):
@@ -11,9 +11,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     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'])
         output = render_template("groups-overview.html",
                                  form=add_form,
-                                 available_tags=datastore.data['settings']['application'].get('tags', {}),
+                                 available_tags=sorted_tags,
                                  )
 
         return output

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

@@ -2,6 +2,10 @@
 {% block content %}
 {% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
+<script>
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test', watch_uuid=uuid)}}";
+</script>
+
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <script>
 
@@ -65,11 +69,12 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                                 {% endif %}
                             </ul>
                         </li>
-                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash,
+                        <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://*[contains(@class, 'sametext')]</code>, <a
+                                <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>

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

@@ -40,7 +40,7 @@
                 <td colspan="3">No website organisational tags/groups configured</td>
             </tr>
             {% endif %}
-            {% for uuid, tag in available_tags.items()  %}
+            {% 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>

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

@@ -1,746 +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():
-    browser_steps = None
-    browser_steps_screenshot_path = None
-    content = None
-    error = None
-    fetcher_description = "No description"
-    headers = {}
-    status_code = None
-    webdriver_js_execute_code = None
-    xpath_data = None
-    xpath_element_js = ""
-    instock_data = None
-    instock_data_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 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 as e:
-                    print(str(e))
-                    # 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_fetch_browserless_puppeteer(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-
-        from pkg_resources import resource_string
-
-        extra_wait_ms = (int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay) * 1000
-
-        self.xpath_element_js = self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
-        code = resource_string(__name__, "res/puppeteer_fetch.js").decode('utf-8')
-        # In the future inject this is a proper JS package
-        code = code.replace('%xpath_scrape_code%', self.xpath_element_js)
-        code = code.replace('%instock_scrape_code%', self.instock_data_js)
-
-        from requests.exceptions import ConnectTimeout, ReadTimeout
-        wait_browserless_seconds = 240
-
-        browserless_function_url = os.getenv('BROWSERLESS_FUNCTION_URL')
-        from urllib.parse import urlparse
-        if not browserless_function_url:
-            # Convert/try to guess from PLAYWRIGHT_DRIVER_URL
-            o = urlparse(os.getenv('PLAYWRIGHT_DRIVER_URL'))
-            browserless_function_url = o._replace(scheme="http")._replace(path="function").geturl()
-
-
-        # Append proxy connect string
-        if self.proxy:
-            import urllib.parse
-            # Remove username/password if it exists in the URL or you will receive "ERR_NO_SUPPORTED_PROXIES" error
-            # Actual authentication handled by Puppeteer/node
-            o = urlparse(self.proxy.get('server'))
-            proxy_url = urllib.parse.quote(o._replace(netloc="{}:{}".format(o.hostname, o.port)).geturl())
-            browserless_function_url = f"{browserless_function_url}&--proxy-server={proxy_url}&dumpio=true"
-
-
-        try:
-            amp = '&' if '?' in browserless_function_url else '?'
-            response = requests.request(
-                method="POST",
-                json={
-                    "code": code,
-                    "context": {
-                        # Very primitive disk cache - USE WITH EXTREME CAUTION
-                        # Run browserless container  with -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]"
-                        'disk_cache_dir': os.getenv("PUPPETEER_DISK_CACHE", False), # or path to disk cache ending in /, ie /tmp/cache/
-                        'execute_js': self.webdriver_js_execute_code,
-                        'extra_wait_ms': extra_wait_ms,
-                        'include_filters': current_include_filters,
-                        'req_headers': request_headers,
-                        'screenshot_quality': int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)),
-                        'url': url,
-                        'user_agent': request_headers.get('User-Agent', 'Mozilla/5.0'),
-                        'proxy_username': self.proxy.get('username','') if self.proxy else False,
-                        'proxy_password': self.proxy.get('password', '') if self.proxy else False,
-                        'no_cache_list': [
-                            'twitter',
-                            '.pdf'
-                        ],
-                        # Could use https://github.com/easylist/easylist here, or install a plugin
-                        'block_url_list': [
-                            'adnxs.com',
-                            'analytics.twitter.com',
-                            'doubleclick.net',
-                            'google-analytics.com',
-                            'googletagmanager',
-                            'trustpilot.com'
-                        ]
-                    }
-                },
-                # @todo /function needs adding ws:// to http:// rebuild this
-                url=browserless_function_url+f"{amp}--disable-features=AudioServiceOutOfProcess&dumpio=true&--disable-remote-fonts",
-                timeout=wait_browserless_seconds)
-
-        except ReadTimeout:
-            raise PageUnloadable(url=url, status_code=None, message=f"No response from browserless in {wait_browserless_seconds}s")
-        except ConnectTimeout:
-            raise PageUnloadable(url=url, status_code=None, message=f"Timed out connecting to browserless, retrying..")
-        else:
-            # 200 Here means that the communication to browserless worked only, not the page state
-            if response.status_code == 200:
-                import base64
-
-                x = response.json()
-                if not x.get('screenshot'):
-                    # https://github.com/puppeteer/puppeteer/blob/v1.0.0/docs/troubleshooting.md#tips
-                    # https://github.com/puppeteer/puppeteer/issues/1834
-                    # https://github.com/puppeteer/puppeteer/issues/1834#issuecomment-381047051
-                    # Check your memory is shared and big enough
-                    raise ScreenshotUnavailable(url=url, status_code=None)
-
-                if not x.get('content', '').strip():
-                    raise EmptyReply(url=url, status_code=None)
-
-                if x.get('status_code', 200) != 200 and not ignore_status_codes:
-                    raise Non200ErrorCodeReceived(url=url, status_code=x.get('status_code', 200), page_html=x['content'])
-
-                self.content = x.get('content')
-                self.headers = x.get('headers')
-                self.instock_data = x.get('instock_data')
-                self.screenshot = base64.b64decode(x.get('screenshot'))
-                self.status_code = x.get('status_code')
-                self.xpath_data = x.get('xpath_data')
-
-            else:
-                # Some other error from browserless
-                raise PageUnloadable(url=url, status_code=None, message=response.content.decode('utf-8'))
-
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-
-        # For now, USE_EXPERIMENTAL_PUPPETEER_FETCH is not supported by watches with BrowserSteps (for now!)
-        has_browser_steps = self.browser_steps and list(filter(
-                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
-                self.browser_steps))
-
-        if not has_browser_steps:
-            if os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
-                # Temporary backup solution until we rewrite the playwright code
-                return self.run_fetch_browserless_puppeteer(
-                    url,
-                    timeout,
-                    request_headers,
-                    request_body,
-                    request_method,
-                    ignore_status_codes,
-                    current_include_filters,
-                    is_binary)
-
-        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.get('User-Agent', '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.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) + "}")
-            self.instock_data = self.page.evaluate("async () => {" + self.instock_data_js + "}")
-
-            # 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 distutils.util 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 +1,171 @@
+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 = next((v for k, v in headers.items() if k.lower() == "user-agent"), None)
+    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 = filter(
+                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+                self.browser_steps)
+
+            return valid_steps
+
+        return None
+
+    def iterate_browser_steps(self):
+        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+        from playwright._impl._errors import TimeoutError, Error
+        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 = 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 = 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 (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()
+            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()
+
+            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 +1,247 @@
+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)")
+        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)}")
+        else:
+            self.page = await browser.newPage()
+
+        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 +1,91 @@
+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)
+
+        # Make requests use a more modern looking user-agent
+        if not {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None):
+            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
+
+        # 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

@@ -18,12 +18,19 @@ module.exports = async ({page, context}) => {
 
     await page.setBypassCSP(true)
     await page.setExtraHTTPHeaders(req_headers);
-    await page.setUserAgent(user_agent);
+
+    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
@@ -139,7 +146,7 @@ module.exports = async ({page, context}) => {
     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 browserless
+        // 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%});

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

@@ -16,24 +16,23 @@ try {
 }
 
 
-
 // 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
@@ -59,14 +58,14 @@ const findUpTag = (el) => {
 
     // 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;
@@ -82,30 +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
@@ -114,46 +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.
@@ -170,20 +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 {
@@ -192,12 +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");
         }
 
@@ -207,7 +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
             });
         }
     }
@@ -215,7 +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

@@ -35,15 +35,19 @@ def customSequenceMatcher(before, after, include_equal=False, include_removed=Tr
 
 # 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_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):
+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):
 
     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()]
+        previous_version_file_contents = [line.rstrip() for line in previous_version_file_contents.splitlines()]
     else:
         previous_version_file_contents = ""
 
+    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,
@@ -54,4 +58,5 @@ def render_diff(previous_version_file_contents, newest_version_file_contents, in
 
     # 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 distutils.util import strtobool
 
 from wtforms import (
     BooleanField,
@@ -14,14 +15,20 @@ 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,
 )
@@ -36,10 +43,11 @@ valid_method = {
     'PUT',
     'PATCH',
     'DELETE',
+    'OPTIONS',
 }
 
 default_method = 'GET'
-
+allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
 
 class StringListField(StringField):
     widget = widgets.TextArea()
@@ -159,31 +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):
@@ -228,16 +236,19 @@ class ValidateJinja2Template(object):
     def __call__(self, form, field):
         from changedetectionio import notification
 
-        from jinja2 import Environment, BaseLoader, TemplateSyntaxError
+        from jinja2 import Environment, BaseLoader, TemplateSyntaxError, UndefinedError
         from jinja2.meta import find_undeclared_variables
 
 
         try:
             jinja2_env = Environment(loader=BaseLoader)
             jinja2_env.globals.update(notification.valid_tokens)
+
             rendered = jinja2_env.from_string(field.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
 
         ast = jinja2_env.parse(field.data)
         undefined = ", ".join(find_undeclared_variables(ast))
@@ -256,18 +267,23 @@ 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):
     """
@@ -279,11 +295,10 @@ 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))
@@ -312,11 +327,30 @@ 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())
@@ -385,7 +419,7 @@ class commonSettingsForm(Form):
     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")])
@@ -393,6 +427,9 @@ 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):
 
@@ -426,6 +463,7 @@ class watchForm(commonSettingsForm):
     method = SelectField('Request method', choices=valid_method, default=default_method)
     ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
     check_unique_lines = BooleanField('Only trigger when unique lines appear', 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)
@@ -476,9 +514,15 @@ 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
+
+
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
     time_between_check = FormField(TimeBetweenCheckForm)
@@ -487,6 +531,7 @@ 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)
 
     def validate_extra_proxies(self, extra_validators=None):
         for e in self.data['extra_proxies']:
@@ -500,9 +545,12 @@ 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')

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>"
 
+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'})
@@ -76,7 +181,6 @@ def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False
 
     return html_block
 
-
 # Extract/find element
 def extract_element(find='title', html_content=''):
 
@@ -144,7 +248,6 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
 
         # Foreach <script json></script> blob.. just return the first that matches json_filter
         # As a last resort, try to parse the whole <body>
-        s = []
         soup = BeautifulSoup(content, 'html.parser')
 
         if ensure_is_ldjson_info_type:
@@ -170,13 +273,24 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
         
         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)
-                    if json_data.get('@type', False) and json_data.get('@type','').lower() == ensure_is_ldjson_info_type.lower() and stripped_text_from_html:
-                        break
+                    # @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
 
@@ -191,50 +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
@@ -250,16 +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
@@ -267,9 +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)

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,
@@ -52,7 +57,7 @@ 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
-            # @todo validators.url failed on local hostnames (such as referring to ourself when using browserless)
+            # @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:
@@ -132,3 +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

@@ -16,6 +16,7 @@ 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},

changedetectionio/model/Watch.py

@@ -1,9 +1,10 @@
 from distutils.util import strtobool
-import logging
 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
@@ -18,6 +19,8 @@ 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,
@@ -25,6 +28,7 @@ base_config = {
     'extract_text': [],  # Extract text by regex after filters
     'extract_title_as_title': False,
     '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,
@@ -34,12 +38,14 @@ base_config = {
     '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,
@@ -51,6 +57,8 @@ 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': '', # Old system of text name for a tag, to be removed
     'tags': [], # list of UUIDs to App.Tags
@@ -109,14 +117,15 @@ 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
@@ -142,8 +151,14 @@ 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):
         """
@@ -167,9 +182,7 @@ 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):
@@ -201,7 +214,7 @@ 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:
@@ -233,6 +246,14 @@ 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):
@@ -246,6 +267,38 @@ 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]
@@ -491,3 +544,13 @@ class model(dict):
         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
+    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

@@ -1,7 +1,9 @@
 import apprise
+import time
 from jinja2 import Environment, BaseLoader
 from apprise import NotifyFormat
 import json
+from loguru import logger
 
 valid_tokens = {
     'base_url': '',
@@ -9,6 +11,7 @@ valid_tokens = {
     'diff': '',
     'diff_added': '',
     'diff_full': '',
+    'diff_patch': '',
     'diff_removed': '',
     'diff_url': '',
     'preview_url': '',
@@ -45,6 +48,9 @@ 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.URLBase import URLBase
+
     url = kwargs['meta'].get('url')
 
     if url.startswith('post'):
@@ -67,27 +73,59 @@ 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):
 
+    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_body = jinja2_env.from_string(n_object.get('notification_body', '')).render(**notification_parameters)
+    n_title = jinja2_env.from_string(n_object.get('notification_title', '')).render(**notification_parameters)
     n_format = valid_notification_formats.get(
         n_object.get('notification_format', default_notification_format),
         valid_notification_formats[default_notification_format],
@@ -98,100 +136,114 @@ def process_notification(n_object, datastore):
         # 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']:
+            url = url.strip()
+            if not url:
+                logger.warning(f"Process Notification: skipping empty notification URL.")
+                continue
 
-                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]
+            logger.info(">> Process Notification: AppRise notifying {}".format(url))
+            url = jinja2_env.from_string(url).render(**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)
+            # 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.add(url)
+            # 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'
 
-                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)
-                )
+            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]
 
-                apobj.clear()
+            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]
 
-                # Incase it needs to exist in memory for a while after to process(?)
-                apobjs.append(apobj)
+            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
 
-                # 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})
+            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 != '':
+    if uuid:
         watch_title = datastore.data['watching'][uuid].get('title', '')
         tag_list = []
         tags = datastore.get_all_tags_for_watch(uuid)
@@ -204,15 +256,11 @@ def create_notification_parameters(n_object, datastore):
         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)
 
@@ -222,11 +270,12 @@ 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 '',
-            'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object 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,

changedetectionio/processors/__init__.py

@@ -1,15 +1,138 @@
 from abc import abstractmethod
+import os
 import hashlib
-
+import re
+from copy import deepcopy
+from distutils.util import strtobool
+from loguru import logger
 
 class difference_detection_processor():
 
+    browser_steps = None
+    datastore = None
+    fetcher = None
+    screenshot = None
+    watch = None
+    xpath_data = None
 
-    def __init__(self, *args, **kwargs):
+    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):
+
+        # 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 = 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(self, uuid, skip_when_checksum_same=True):
+    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()

changedetectionio/processors/restock_diff.py

@@ -1,11 +1,9 @@
 
-import hashlib
-import os
-import re
-import urllib3
 from . import difference_detection_processor
-from changedetectionio import content_fetcher
 from copy import deepcopy
+from loguru import logger
+import hashlib
+import urllib3
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
@@ -22,11 +20,7 @@ class perform_site_check(difference_detection_processor):
     screenshot = None
     xpath_data = None
 
-    def __init__(self, *args, datastore, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.datastore = datastore
-
-    def run(self, uuid, skip_when_checksum_same=True):
+    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))
@@ -34,87 +28,29 @@ class perform_site_check(difference_detection_processor):
         if not watch:
             raise Exception("Watch no longer exists.")
 
-        # 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."
-            )
-
         # Unset any existing notification error
         update_obj = {'last_notification_error': False, 'last_error': False}
 
-        request_headers = 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=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')
-
-        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)
-
-        # 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
-
-        # Could be removed if requests/plaintext could also return some info?
-        if prefer_backend != 'html_webdriver':
-            raise Exception("Re-stock detection requires Chrome or compatible webdriver/playwright fetcher to work")
-
-        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')
-
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'))
-        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["last_check_status"] = fetcher.get_last_status_code()
+        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 fetcher.instock_data:
-            fetched_md5 = hashlib.md5(fetcher.instock_data.encode('utf-8')).hexdigest()
+        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 fetcher.instock_data == 'Possibly in stock' else False
+            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=fetcher.status_code)
+            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
@@ -127,5 +63,4 @@ class perform_site_check(difference_detection_processor):
 
         # Always record the new checksum
         update_obj["previous_md5"] = fetched_md5
-
-        return changed_detected, update_obj, fetcher.instock_data.encode('utf-8')
+        return changed_detected, update_obj, self.fetcher.instock_data.encode('utf-8').strip()

changedetectionio/processors/text_json_diff.py

@@ -1,27 +1,30 @@
-# HTML to TEXT/JSON DIFFERENCE FETCHER
+# 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 changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
-from copy import deepcopy
 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'
+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)
@@ -30,28 +33,10 @@ class PDFToHTMLToolNotFound(ValueError):
 # Some common stuff here that can be moved to a base class
 # (set_proxy_from_list)
 class perform_site_check(difference_detection_processor):
-    screenshot = None
-    xpath_data = None
 
-    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 = ""
 
@@ -60,96 +45,25 @@ class perform_site_check(difference_detection_processor):
         if not watch:
             raise Exception("Watch no longer exists.")
 
-        # 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."
-            )
-
         # Unset any existing notification error
         update_obj = {'last_notification_error': False, 'last_error': False}
 
-        # Tweak the base config with the per-watch ones
-        request_headers = 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=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')
-
         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.get_all_headers().get('content-type', '').lower()
+        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
@@ -158,15 +72,24 @@ class perform_site_check(difference_detection_processor):
         # https://stackoverflow.com/questions/41817578/basic-method-chaining ?
         # return content().textfilter().jsonextract().checksumcompare() ?
 
-        is_json = 'application/json' in fetcher.get_all_headers().get('content-type', '').lower()
+        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.get_all_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):
@@ -177,24 +100,26 @@ class perform_site_check(difference_detection_processor):
                 [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 = [*watch.get('include_filters', []), *include_filters_from_tags]
+
+        # 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", []),
@@ -203,7 +128,7 @@ class perform_site_check(difference_detection_processor):
 
         # 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 = len(include_filters_rule) and len(include_filters_rule[0].strip())
         has_subtractive_selectors = len(subtractive_selectors) and len(subtractive_selectors[0].strip())
@@ -215,33 +140,30 @@ class perform_site_check(difference_detection_processor):
         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.get_all_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:
@@ -251,13 +173,19 @@ class perform_site_check(difference_detection_processor):
                         # 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)
@@ -265,21 +193,27 @@ class perform_site_check(difference_detection_processor):
                 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
@@ -289,13 +223,13 @@ class perform_site_check(difference_detection_processor):
             # 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)
+                                             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)
 
@@ -310,12 +244,17 @@ class perform_site_check(difference_detection_processor):
         # 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
@@ -331,16 +270,25 @@ class perform_site_check(difference_detection_processor):
             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''
@@ -394,17 +342,19 @@ class perform_site_check(difference_detection_processor):
         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/res/stock-not-in-stock.js

@@ -1,102 +0,0 @@
-function isItemInStock() {
-  // @todo Pass these in so the same list can be used in non-JS fetchers
-  const outOfStockTexts = [
-    '0 in stock',
-    'agotado',
-    'artikel zurzeit vergriffen',
-    'as soon as stock is available',
-    'available for back order',
-    'backordered',
-    'brak na stanie',
-    'brak w magazynie',
-    'coming soon',
-    'currently have any tickets for this',
-    'currently unavailable',
-    'en rupture de stock',
-    'item is no longer available',
-    'message if back in stock',
-    'nachricht bei',
-    'nicht auf lager',
-    'nicht lieferbar',
-    'nicht zur verfügung',
-    'no disponible temporalmente',
-    'no longer in stock',
-    'no tickets available',
-    'not available',
-    'not currently available',
-    'not in stock',
-    'notify me when available',
-    'não estamos a aceitar encomendas',
-    'out of stock',
-    'out-of-stock',
-    'produkt niedostępny',
-    'sold out',
-    'temporarily out of stock',
-    'temporarily unavailable',
-    'tickets unavailable',
-    'unavailable tickets',
-    'we do not currently have an estimate of when this product will be back in stock.',
-    'zur zeit nicht an lager',
-  ];
-
-
-  const negateOutOfStockRegexs = [
-      '[0-9] in stock'
-  ]
-  var negateOutOfStockRegexs_r = [];
-  for (let i = 0; i < negateOutOfStockRegexs.length; i++) {
-    negateOutOfStockRegexs_r.push(new RegExp(negateOutOfStockRegexs[0], 'g'));
-  }
-
-
-  const elementsWithZeroChildren = Array.from(document.getElementsByTagName('*')).filter(element => element.children.length === 0);
-
-  // REGEXS THAT REALLY MEAN IT'S IN STOCK
-  for (let i = elementsWithZeroChildren.length - 1; i >= 0; i--) {
-    const element = elementsWithZeroChildren[i];
-    if (element.offsetWidth > 0 || element.offsetHeight > 0 || element.getClientRects().length > 0) {
-      var elementText="";
-      if (element.tagName.toLowerCase() === "input") {
-        elementText = element.value.toLowerCase();
-      } else {
-        elementText = element.textContent.toLowerCase();
-      }
-
-      if (elementText.length) {
-        // try which ones could mean its in stock
-        for (let i = 0; i < negateOutOfStockRegexs.length; i++) {
-          if (negateOutOfStockRegexs_r[i].test(elementText)) {
-            return 'Possibly in stock';
-          }
-        }
-      }
-    }
-  }
-
-  // OTHER STUFF THAT COULD BE THAT IT'S OUT OF STOCK
-  for (let i = elementsWithZeroChildren.length - 1; i >= 0; i--) {
-    const element = elementsWithZeroChildren[i];
-    if (element.offsetWidth > 0 || element.offsetHeight > 0 || element.getClientRects().length > 0) {
-      var elementText="";
-      if (element.tagName.toLowerCase() === "input") {
-        elementText = element.value.toLowerCase();
-      } else {
-        elementText = element.textContent.toLowerCase();
-      }
-
-      if (elementText.length) {
-        // and these mean its out of stock
-        for (const outOfStockText of outOfStockTexts) {
-          if (elementText.includes(outOfStockText)) {
-            return elementText; // item is out of stock
-          }
-        }
-      }
-    }
-  }
-
-  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();

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/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

@@ -10,7 +10,7 @@
    viewBox="0 0 7.1975545 4.7993639"
    xml:space="preserve"
    xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg"><defs
+   ><defs
    id="defs19" />
 <g
    id="g14"

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;
@@ -49,7 +49,7 @@ $(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 +61,12 @@ $(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")
 
@@ -160,6 +160,12 @@ $(document).ready(function () {
                     e.offsetX > item.left * y_scale && e.offsetX < item.left * y_scale + item.width * y_scale
 
                 ) {
+                    // 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
+                    }
+
                     // 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']) {
@@ -208,7 +214,7 @@ $(document).ready(function () {
             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();
@@ -261,7 +267,7 @@ $(document).ready(function () {
             // 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 = 500;
+            browser_interface_seconds_remaining = 500;
             set_first_gotosite_disabled();
         }).fail(function (data) {
             console.log(data);
@@ -321,8 +327,14 @@ $(document).ready(function () {
             var s = '<div class="control">' + '<a data-step-index=' + i + ' class="pure-button button-secondary button-green button-xsmall apply" >Apply</a>&nbsp;';
             if (i > 0) {
                 // The first step never gets these (Goto-site)
-                s += '<a data-step-index=' + i + ' class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;' +
-                    '<a data-step-index=' + i + ' class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>';
+                s += `<a data-step-index="${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)
@@ -437,6 +449,24 @@ $(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 +1,13 @@
 $(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)
+            }
+        }
+    })
+
     // 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 +24,76 @@ $(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 +1,120 @@
-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);
+    $('.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"});
+        }
+    })
+    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

@@ -24,14 +24,17 @@ $(document).ready(function() {
     })
 
     data = {
-        window_url : window.location.href,
-        notification_urls : $('.notification-urls').val(),
+      notification_body: $('#notification_body').val(),
+      notification_format: $('#notification_format').val(),
+      notification_title: $('#notification_title').val(),
+      notification_urls: $('.notification-urls').val(),
+      window_url: window.location.href,
     }
-    for (key in data) {
-      if (!data[key].length) {
-        alert(key+" is empty, cannot send test.")
-        return;
-      }
+
+
+    if (!data['notification_urls'].length) {
+      alert("Notification URL list is empty, cannot send test.")
+      return;
     }
 
     $.ajax({

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/toggle-theme.js

@@ -3,45 +3,50 @@
  * Toggles theme between light and dark mode.
  */
 $(document).ready(function () {
-  const button = document.getElementById("toggle-light-mode");
+    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;
-    setCookieValue(!isDarkMode);
-  };
+    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
+    // Search input box behaviour
     const toggle_search = document.getElementById("toggle-search");
-  const search_q = document.getElementById("search-q");
-  window.addEventListener('keydown', function (e) {
+    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();
+        }
+      });
 
-    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();
+      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();
+        }
+      };
     }
-  };
-  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

@@ -149,7 +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

@@ -4,6 +4,14 @@ $(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));
+    })
+
     $("#checkbox-assign-tag").click(function (e) {
         $('#op_extradata').val(prompt("Enter a tag name"));
     });

changedetectionio/static/js/watch-settings.js

@@ -1,40 +1,4 @@
 $(document).ready(function () {
-    function toggle() {
-        if ($('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();
-        }
-    }
-
-    $('input[name="fetch_backend"]').click(function (e) {
-        toggle();
-    });
-    toggle();
-
     $('#notification-setting-reset-to-default').click(function (e) {
         $('#notification_title').val('');
         $('#notification_body').val('');
@@ -42,4 +6,8 @@ $(document).ready(function () {
         $('#notification_urls').val('');
         e.preventDefault();
     });
+    $("#notification-token-toggle").click(function (e) {
+        e.preventDefault();
+        $('#notification-tokens-info').toggle();
+    });
 });

changedetectionio/static/styles/diff.css

@@ -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/_variables.scss

@@ -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

@@ -5,13 +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 {
@@ -54,27 +59,6 @@ a.github-link {
   }
 }
 
-#toggle-light-mode {
-  width: 3rem;
-  .icon-dark {
-    display: none;
-  }
-
-  &.dark {
-    .icon-light {
-      display: none;
-    }
-
-    .icon-dark {
-      display: block;
-    }
-  }
-}
-
-#toggle-search {
-  width: 2rem;
-}
-
 #search-q {
   opacity: 0;
   -webkit-transition: all .9s ease;
@@ -418,8 +402,24 @@ 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) {
@@ -486,7 +486,11 @@ 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 {
@@ -954,37 +958,10 @@ 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 {
@@ -1118,3 +1095,17 @@ ul {
   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 +97,58 @@ 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;
@@ -283,15 +337,13 @@ html[data-darkmode="true"] {
   --color-icon-github-hover: var(--color-grey-700);
   --color-watch-table-error: var(--color-light-red);
   --color-watch-table-row-text: var(--color-grey-800); }
-  html[data-darkmode="true"] #toggle-light-mode .icon-light {
-    display: none; }
-  html[data-darkmode="true"] #toggle-light-mode .icon-dark {
-    display: block; }
   html[data-darkmode="true"] .icon-spread {
     filter: hue-rotate(-10deg) brightness(1.5); }
   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 {
@@ -301,9 +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);
@@ -335,14 +446,6 @@ a.github-link {
   a.github-link:hover {
     color: var(--color-icon-github-hover); }
 
-#toggle-light-mode {
-  width: 3rem; }
-  #toggle-light-mode .icon-dark {
-    display: none; }
-
-#toggle-search {
-  width: 2rem; }
-
 #search-q {
   opacity: 0;
   -webkit-transition: all .9s ease;
@@ -582,11 +685,23 @@ 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; }
@@ -634,7 +749,11 @@ 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 {
@@ -943,6 +1062,7 @@ ul {
 
 #selector-wrapper {
   height: 100%;
+  max-height: 70vh;
   overflow-y: scroll;
   position: relative; }
   #selector-wrapper > img {
@@ -959,7 +1079,7 @@ ul {
 #selector-current-xpath {
   font-size: 80%; }
 
-#webdriver-override-options input[type="number"] {
+#webdriver_delay {
   width: 5em; }
 
 #api-key:hover {
@@ -1060,3 +1180,13 @@ ul {
   .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

@@ -1,3 +1,5 @@
+from distutils.util import strtobool
+
 from flask import (
     flash
 )
@@ -7,7 +9,6 @@ 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 +16,10 @@ 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) ])
 
@@ -37,6 +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
@@ -77,12 +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'})
@@ -90,6 +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
@@ -119,16 +133,13 @@ class ChangeDetectionStore:
             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
 
@@ -173,12 +184,21 @@ class ChangeDetectionStore:
 
     @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')
+
+        # 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):
@@ -214,7 +234,7 @@ class ChangeDetectionStore:
 
         # 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
@@ -224,12 +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,
             })
 
@@ -291,7 +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
@@ -309,7 +335,8 @@ class ChangeDetectionStore:
 
         # Or if UUIDs given directly
         if tag_uuids:
-            apply_extras['tags'] = list(set(apply_extras['tags'] + tag_uuids))
+            for t in tag_uuids:
+                apply_extras['tags'] = list(set(apply_extras['tags'] + [t.strip()]))
 
         # Make any uuids unique
         if apply_extras.get('tags'):
@@ -319,12 +346,15 @@ class ChangeDetectionStore:
 
         new_uuid = new_watch.get('uuid')
 
-        logging.debug("Added URL {} - {}".format(url, new_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
@@ -333,6 +363,8 @@ class ChangeDetectionStore:
         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):
@@ -385,14 +417,13 @@ class ChangeDetectionStore:
 
 
     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:
@@ -405,7 +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
@@ -416,7 +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:
@@ -432,7 +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']:
@@ -445,7 +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
@@ -468,6 +508,8 @@ 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
 
@@ -485,6 +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')
 
@@ -526,7 +571,7 @@ class ChangeDetectionStore:
             if os.path.isfile(filepath):
                 headers.update(parse_headers_from_text_file(filepath))
         except Exception as e:
-            print(f"ERROR reading headers.txt at {filepath}", str(e))
+            logger.error(f"ERROR reading headers.txt at {filepath} {str(e)}")
 
         watch = self.data['watching'].get(uuid)
         if watch:
@@ -537,7 +582,7 @@ class ChangeDetectionStore:
                 if os.path.isfile(filepath):
                     headers.update(parse_headers_from_text_file(filepath))
             except Exception as e:
-                print(f"ERROR reading headers.txt at {filepath}", str(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)
@@ -548,7 +593,7 @@ class ChangeDetectionStore:
                     if os.path.isfile(filepath):
                         headers.update(parse_headers_from_text_file(filepath))
                 except Exception as e:
-                    print(f"ERROR reading headers.txt at {filepath}", str(e))
+                    logger.error(f"ERROR reading headers.txt at {filepath} {str(e)}")
 
         return headers
 
@@ -566,13 +611,13 @@ class ChangeDetectionStore:
     def add_tag(self, name):
         # If name exists, return that
         n = name.strip().lower()
-        print (f">>> Adding new tag - '{n}'")
+        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():
-                print (f">>> Tag {name} already exists")
+                logger.warning(f"Tag '{name}' already exists, skipping creation.")
                 return uuid
 
         # Eventually almost everything todo with a watch will apply as a Tag
@@ -599,17 +644,23 @@ class ChangeDetectionStore:
 
         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):
         return any(v.get('title', '').lower() == tag_name.lower() for k, v in self.__data['settings']['application']['tags'].items())
 
-    # 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):
+    def get_updates_available(self):
         import inspect
-        import shutil
-
         updates_available = []
         for i, o in inspect.getmembers(self, predicate=inspect.ismethod):
             m = re.search(r'update_(\d+)$', i)
@@ -617,9 +668,18 @@ 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))
@@ -627,8 +687,8 @@ 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:
@@ -666,7 +726,7 @@ 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.
@@ -778,15 +838,6 @@ class ChangeDetectionStore:
                 continue
         return
 
-    # We don't know when the date_created was in the past until now, so just add an index number for now.
-    def update_11(self):
-        i = 0
-        for uuid, watch in self.data['watching'].items():
-            if not watch.get('date_created'):
-                watch['date_created'] = i
-            i+=1
-        return
-
     # Create tag objects and their references from existing tag text
     def update_12(self):
         i = 0
@@ -800,3 +851,21 @@ class ChangeDetectionStore:
 
                 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)

changedetectionio/templates/_common_fields.jinja

@@ -13,10 +13,10 @@
                             <div class="pure-form-message-inline">
                               <ul>
                                 <li>Use <a target=_new href="https://github.com/caronc/apprise">AppRise URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.</li>
-                                <li><code>discord://</code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
-                                <li><code>tgram://</code> bots cant send messages to other bots, so you should specify chat ID of non-bot user.</li>
-                                <li><code>tgram://</code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
-                                <li><code>gets://</code>, <code>posts://</code>, <code>puts://</code>, <code>deletes://</code> for direct API calls (or omit the "<code>s</code>" for non-SSL ie <code>get://</code>)</li>
+                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_discord">discord://</a></code> (or <code>https://discord.com/api/webhooks...</code>)) only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
+                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> bots can't send messages to other bots, so you should specify chat ID of non-bot user.</li>
+                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
+                                <li><code>gets://</code>, <code>posts://</code>, <code>puts://</code>, <code>deletes://</code> for direct API calls (or omit the "<code>s</code>" for non-SSL ie <code>get://</code>) <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes#postposts">more help here</a></li>
                                   <li>Accepts the <code>{{ '{{token}}' }}</code> placeholders listed below</li>
                               </ul>
                             </div>
@@ -35,18 +35,14 @@
                             </div>
                             <div class="pure-control-group">
                                 {{ render_field(form.notification_body , rows=5, class="notification-body", placeholder=settings_application['notification_body']) }}
-                                <span class="pure-form-message-inline">Body for all notifications</span>
-                            </div>
-                            <div class="pure-control-group">
-                            <!-- unsure -->
-                                {{ render_field(form.notification_format , class="notification-format") }}
-                                <span class="pure-form-message-inline">Format for all notifications</span>
+                                <span class="pure-form-message-inline">Body for all notifications &dash; You can use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> templating in the notification title, body and URL, and tokens from below.
+                                </span>
+
                             </div>
                             <div class="pure-controls">
-                            <p class="pure-form-message-inline">
-                                You can use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> templating in the notification title, body and URL.
-                            </p>
-
+                                <div id="notification-token-toggle" class="pure-button button-tag button-xsmall">Show token/placeholders</div>
+                            </div>
+                            <div class="pure-controls" style="display: none;" id="notification-tokens-info">
                                 <table class="pure-table" id="token-table">
                                     <thead>
                                     <tr>
@@ -99,9 +95,13 @@
                                         <td><code>{{ '{{diff_full}}' }}</code></td>
                                         <td>The diff output - full difference output</td>
                                     </tr>
+                                    <tr>
+                                        <td><code>{{ '{{diff_patch}}' }}</code></td>
+                                        <td>The diff output - patch in unified format</td>
+                                    </tr>
                                     <tr>
                                         <td><code>{{ '{{current_snapshot}}' }}</code></td>
-                                        <td>The current snapshot value, useful when combined with JSON or CSS filters
+                                        <td>The current snapshot text contents value, useful when combined with JSON or CSS filters
                                         </td>
                                     </tr>
                                     <tr>
@@ -111,12 +111,21 @@
                                     </tbody>
                                 </table>
                                 <div class="pure-form-message-inline">
-                                    <br>
-                                    URLs generated by changedetection.io (such as <code>{{ '{{diff_url}}' }}</code>) require the <code>BASE_URL</code> environment variable set.<br>
-                                    Your <code>BASE_URL</code> var is currently "{{settings_application['current_base_url']}}"
-									<br>
-									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removed%7D%7D-notification-tokens">More Here</a> <br>
+                                    <p>
+									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. <br>
+                                    For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removed%7D%7D-notification-tokens">More Here</a> <br>
+                                    </p>
+                                    <p>
+                                        For JSON payloads, use <strong>|tojson</strong> without quotes for automatic escaping, for example - <code>{ "name": {{ '{{ watch_title|tojson }}' }} }</code>
+                                    </p>
+                                    <p>
+                                        URL encoding, use <strong>|urlencode</strong>, for example - <code>gets://hook-website.com/test.php?title={{ '{{ watch_title|urlencode }}' }}</code>
+                                    </p>
                                 </div>
                             </div>
+                            <div class="pure-control-group">
+                                {{ render_field(form.notification_format , class="notification-format") }}
+                                <span class="pure-form-message-inline">Format for all notifications</span>
+                            </div>
                         </div>
 {% endmacro %}

changedetectionio/templates/_helpers.jinja

@@ -1,7 +1,6 @@
 {% macro render_field(field) %}
-  <div {% if field.errors %} class="error" {% endif %}>{{ field(**kwargs)|safe }}
   <div {% if field.errors %} class="error" {% endif %}>{{ field.label }}</div>
-
+  <div {% if field.errors %} class="error" {% endif %}>{{ field(**kwargs)|safe }}
   {% if field.errors %}
     <ul class=errors>
     {% for error in field.errors %}
@@ -25,18 +24,6 @@
   </div>
 {% endmacro %}
 
-{% macro render_field(field) %}
-  <div {% if field.errors %} class="error" {% endif %}>{{ field.label }}</div>
-  <div {% if field.errors %} class="error" {% endif %}>{{ field(**kwargs)|safe }}
-  {% if field.errors %}
-    <ul class=errors>
-    {% for error in field.errors %}
-      <li>{{ error }}</li>
-    {% endfor %}
-    </ul>
-  {% endif %}
-  </div>
-{% endmacro %}
 
 {% macro render_simple_field(field) %}
   <span class="label {% if field.errors %}error{% endif %}">{{ field.label }}</span>
@@ -52,6 +39,24 @@
 {% endmacro %}
 
 
+{% macro render_nolabel_field(field) %}
+    <span>
+    {{ field(**kwargs)|safe }}
+        {% if field.errors %}
+            <span class="error">
+      {% if field.errors %}
+          <ul class=errors>
+        {% for error in field.errors %}
+            <li>{{ error }}</li>
+        {% endfor %}
+        </ul>
+      {% endif %}
+      </span>
+        {% endif %}
+    </span>
+{% endmacro %}
+
+
 {% macro render_button(field) %}
   {{ field(**kwargs)|safe }}
 {% endmacro %}

changedetectionio/templates/base.html

@@ -8,10 +8,10 @@
     <title>Change Detection{{extra_title}}</title>
     <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}" >
     <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}" >
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}" >
+    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}?v={{ get_css_version() }}" >
     {% if extra_stylesheets %}
       {% for m in extra_stylesheets %}
-        <link rel="stylesheet" href="{{ m }}?ver=1000" >
+        <link rel="stylesheet" href="{{ m }}?ver={{ get_css_version() }}" >
       {% endfor %}
     {% endif %}
 
@@ -37,7 +37,7 @@
     <div class="header">
       <div class="home-menu pure-menu pure-menu-horizontal pure-menu-fixed" id="nav-menu">
         {% if has_password and not current_user.is_authenticated %}
-          <a class="pure-menu-heading" href="https://github.com/dgtlmoon/changedetection.io" rel="noopener">
+          <a class="pure-menu-heading" href="https://changedetection.io" rel="noopener">
             <strong>Change</strong>Detection.io</a>
         {% else %}
           <a class="pure-menu-heading" href="{{url_for('index')}}">
@@ -49,7 +49,7 @@
         {% else %}
           {% if new_version_available and not(has_password and not current_user.is_authenticated) %}
             <span id="new-version-text" class="pure-menu-heading">
-              <a href="https://github.com/dgtlmoon/changedetection.io">A new version is available</a>
+              <a href="https://changedetection.io">A new version is available</a>
             </span>
           {% endif %}
         {% endif %}
@@ -77,7 +77,7 @@
             {% endif %}
           {% else %}
             <li class="pure-menu-item">
-              <a class="pure-menu-link" href="https://github.com/dgtlmoon/changedetection.io">Website Change Detection and Notification.</a>
+              <a class="pure-menu-link" href="https://changedetection.io">Website Change Detection and Notification.</a>
             </li>
           {% endif %}
           {% if current_user.is_authenticated %}
@@ -85,6 +85,7 @@
               <a href="{{url_for('logout')}}" class="pure-menu-link">LOG OUT</a>
             </li>
           {% endif %}
+          {% if current_user.is_authenticated or not has_password %}
           <li class="pure-menu-item pure-form" id="search-menu-item">
             <!-- We use GET here so it offers people a chance to set bookmarks etc -->
             <form name="searchForm" action="" method="GET">
@@ -95,6 +96,7 @@
               </button>
             </form>
           </li>
+          {% endif %}
           <li class="pure-menu-item">
             <button class="toggle-button" id ="toggle-light-mode" type="button" title="Toggle Light/Dark Mode">
               <span class="visually-hidden">Toggle light/dark mode</span>
@@ -106,6 +108,20 @@
               </span>
             </button>
           </li>
+          <li class="pure-menu-item" id="heart-us">
+                <svg
+                   fill="#ff0000"
+                   class="bi bi-heart"
+                   preserveAspectRatio="xMidYMid meet"
+                   viewBox="0 0 16.9 16.1"
+                   id="svg-heart"
+                   xmlns="http://www.w3.org/2000/svg"
+                   >
+                  <path id="heartpath" d="M 5.338316,0.50302766 C 0.71136983,0.50647126 -3.9576371,7.2707777 8.5004254,15.503028 23.833425,5.3700277 13.220206,-2.5384409 8.6762066,1.6475589 c -0.060791,0.054322 -0.11943,0.1110064 -0.1757812,0.1699219 -0.057,-0.059 -0.1157813,-0.116875 -0.1757812,-0.171875 C 7.4724566,0.86129334 6.4060729,0.50223298 5.338316,0.50302766 Z"
+                     style="fill:var(--color-background);fill-opacity:1;stroke:#ff0000;stroke-opacity:1" />
+                </svg>
+
+          </li>
           <li class="pure-menu-item">
             <a class="github-link" href="https://github.com/dgtlmoon/changedetection.io">
               {% include "svgs/github.svg" %}
@@ -121,14 +137,63 @@
     {% endif %}
     {% if left_sticky %}
       <div class="sticky-tab" id="left-sticky">
-        <a href="{{url_for('preview_page', uuid=uuid)}}">Show current snapshot</a>
+        <a href="{{url_for('preview_page', uuid=uuid)}}">Show current snapshot</a><br>
+          Visualise <strong>triggers</strong> and <strong>ignored text</strong>
       </div>
     {% endif %}
     {% if right_sticky %}
       <div class="sticky-tab" id="right-sticky">{{ right_sticky }}</div>
     {% endif %}
     <section class="content">
-      <header>
+        <div id="overlay">
+            <div class="content">
+                <h4>Try our Chrome extension</h4>
+                <p>
+                    <a id="chrome-extension-link"
+                       title="Try our new Chrome Extension!"
+                       href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
+                        <img src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}">
+                        Chrome Webstore
+                    </a>
+                </p>
+
+                Easily add the current web-page from your browser directly into your changedetection.io tool, more great features coming soon!
+
+                <h4>Changedetection.io needs your support!</h4>
+                <p>
+                    You can help us by supporting changedetection.io on these platforms;
+                </p>
+                <p>
+                <ul>
+                    <li>
+                        <a href="https://alternativeto.net/software/changedetection-io/about/">Rate us at
+                        AlternativeTo.net</a>
+                    </li>
+                <li>
+                    <a href="https://github.com/dgtlmoon/changedetection.io">Star us on GitHub</a>
+                </li>
+                <li>
+                    <a href="https://twitter.com/change_det_io">Follow us at Twitter/X</a>
+                </li>
+                <li>
+                    <a href="https://www.linkedin.com/company/changedetection-io">Check us out on LinkedIn</a>
+                </li>
+                <li>
+                    And tell your friends and colleagues :)
+                </li>
+                </ul>
+                <p>
+                    The more popular changedetection.io is, the more time we can dedicate to adding amazing features!
+                </p>
+                <p>
+                    Many thanks :)<br>
+                </p>
+                <p>
+                    <i>changedetection.io team</i>
+                </p>
+            </div>
+        </div>
+        <header>
         {% block header %}{% endblock %}
       </header>
 

changedetectionio/templates/diff.html

@@ -6,14 +6,38 @@
     {% if last_error_screenshot %}
     const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
     {% endif %}
+
+    const highlight_submit_ignore_url="{{url_for('highlight_submit_ignore_url', uuid=uuid)}}";
+
 </script>
 <script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
 <div id="settings">
-    <h1>Differences</h1>
-    <form class="pure-form " action="" method="GET">
+    <form class="pure-form " action="" method="GET" id="diff-form">
         <fieldset>
-
+            {% if versions|length >= 1 %}
+                <strong>Compare</strong>
+                <del class="change"><span>from</span></del>
+                <select id="diff-version" name="from_version" class="needs-localtime">
+                    {% for version in versions|reverse %}
+                        <option value="{{ version }}" {% if version== from_version %} selected="" {% endif %}>
+                            {{ version }}
+                        </option>
+                    {% endfor %}
+                </select>
+                <ins class="change"><span>to</span></ins>
+                <select id="current-version" name="to_version" class="needs-localtime">
+                    {% for version in versions|reverse %}
+                        <option value="{{ version }}" {% if version== to_version %} selected="" {% endif %}>
+                            {{ version }}
+                        </option>
+                    {% endfor %}
+                </select>
+                <button type="submit" class="pure-button pure-button-primary">Go</button>
+            {% endif %}
+        </fieldset>
+        <fieldset>
+            <strong>Style</strong>
             <label for="diffWords" class="pure-checkbox">
                 <input type="radio" name="diff_type" id="diffWords" value="diffWords"> Words</label>
             <label for="diffLines" class="pure-checkbox">
@@ -23,32 +47,20 @@
                 <input type="radio" name="diff_type" id="diffChars" value="diffChars"> Chars</label>
             <!-- @todo - when mimetype is JSON, select this by default? -->
             <label for="diffJson" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffJson" value="diffJson" > JSON</label>
+                <input type="radio" name="diff_type" id="diffJson" value="diffJson"> JSON</label>
 
-            {% if versions|length >= 1 %}
-            <label for="diff-version">Compare newest (<span id="current-v-date"></span>) with</label>
-            <select id="diff-version" name="previous_version">
-                {% for version in versions|reverse %}
-                <option value="{{version}}" {% if version== current_previous_version %} selected="" {% endif %}>
-                    {{version}}
-                </option>
-                {% endfor %}
-            </select>
-            <button type="submit" class="pure-button pure-button-primary">Go</button>
-            {% endif %}
-        </fieldset>
-    </form>
-    <del>Removed text</del>
-    <ins>Inserted Text</ins>
-    <span>
+            <span>
         <!-- https://github.com/kpdecker/jsdiff/issues/389 ? -->
         <label for="ignoreWhitespace" class="pure-checkbox" id="label-diff-ignorewhitespace">
-            <input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace" > Ignore Whitespace</label>
+            <input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace"> Ignore Whitespace</label>
     </span>
+        </fieldset>
+    </form>
+
 </div>
 
 <div id="diff-jump">
-    <a onclick="next_diff();">Jump</a>
+    <a id="jump-next-diff" title="Jump to next difference">Jump</a>
 </div>
 
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
@@ -76,8 +88,6 @@
     </div>
 
      <div class="tab-pane-inner" id="text">
-         <div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.</div>
-
          {% if password_enabled_and_share_is_off %}
            <div class="tip">Pro-tip: You can enable <strong>"share access when password is enabled"</strong> from settings</div>
          {% endif %}
@@ -88,10 +98,10 @@
              <tbody>
              <tr>
                  <!-- just proof of concept copied straight from github.com/kpdecker/jsdiff -->
-                 <td id="a" style="display: none;">{{previous}}</td>
-                 <td id="b" style="display: none;">{{newest}}</td>
+                 <td id="a" style="display: none;">{{from_version_file_contents}}</td>
+                 <td id="b" style="display: none;">{{to_version_file_contents}}</td>
                  <td id="diff-col">
-                     <span id="result"></span>
+                     <span id="result" class="highlightable-filter"></span>
                  </td>
              </tr>
              </tbody>

changedetectionio/templates/edit.html

@@ -3,20 +3,24 @@
 {% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='vis.js')}}" defer></script>
 <script>
-    const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
-    const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
-    const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
-    const playwright_enabled={% if playwright_enabled %} true {% else %} false {% endif %};
-
+    const browser_steps_available_screenshots=JSON.parse('{{ watch.get_browsersteps_available_screenshots|tojson }}');
+    const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
+    const browser_steps_fetch_screenshot_image_url="{{url_for('browser_steps.browser_steps_fetch_screenshot_image', uuid=uuid)}}";
+    const browser_steps_last_error_step={{ watch.browser_steps_last_error_step|tojson }};
+    const browser_steps_start_url="{{url_for('browser_steps.browsersteps_start_session', uuid=uuid)}}";
+    const browser_steps_sync_url="{{url_for('browser_steps.browsersteps_ui_update', uuid=uuid)}}";
 {% if emailprefix %}
     const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');
 {% endif %}
-
-    const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
-    const browser_steps_start_url="{{url_for('browser_steps.browsersteps_start_session', uuid=uuid)}}";
-    const browser_steps_sync_url="{{url_for('browser_steps.browsersteps_ui_update', uuid=uuid)}}";
-
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test', watch_uuid=uuid)}}";
+    const playwright_enabled={% if playwright_enabled %} true {% else %} false {% endif %};
+    const recheck_proxy_start_url="{{url_for('check_proxies.start_check', uuid=uuid)}}";
+    const proxy_recheck_status_url="{{url_for('check_proxies.get_recheck_status', uuid=uuid)}}";
+    const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
+    const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
+    const default_system_fetch_backend="{{ settings_application['fetch_backend'] }}";
 </script>
 
 <script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
@@ -27,6 +31,8 @@
 <script src="{{url_for('static_content', group='js', filename='browser-steps.js')}}" defer></script>
 {% endif %}
 
+<script src="{{url_for('static_content', group='js', filename='recheck-proxy.js')}}" defer></script>
+
 <div class="edit-form monospaced-textarea">
 
     <div class="tabs collapsable">
@@ -46,6 +52,7 @@
             <li class="tab"><a href="#restock">Restock Detection</a></li>
             {% endif %}
             <li class="tab"><a href="#notifications">Notifications</a></li>
+            <li class="tab"><a href="#stats">Stats</a></li>
         </ul>
     </div>
 
@@ -106,21 +113,21 @@
                         <span class="pure-form-message-inline">
                             <p>Use the <strong>Basic</strong> method (default) where your watched site doesn't need Javascript to render.</p>
                             <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
-                            Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using BrightData Proxies, find out more here.</a>
+                            Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
                         </span>
                     </div>
                 {% if form.proxy %}
                     <div class="pure-control-group inline-radio">
-                        {{ render_field(form.proxy, class="fetch-backend-proxy") }}
+                          <div>{{ form.proxy.label }} <a href="" id="check-all-proxies" class="pure-button button-secondary button-xsmall" >Check/Scan all</a></div>
+                          <div>{{ form.proxy(class="fetch-backend-proxy") }}</div>
                         <span class="pure-form-message-inline">
                         Choose a proxy for this watch
                         </span>
                     </div>
                 {% endif %}
-                    <div  class="pure-control-group inline-radio">
-                        {{ render_checkbox_field(form.ignore_status_codes) }}
-                    </div>
-                <fieldset id="webdriver-override-options">
+
+                <!-- webdriver always -->
+                <fieldset data-visible-for="fetch_backend=html_webdriver"  style="display: none;">
                     <div class="pure-control-group">
                         {{ render_field(form.webdriver_delay) }}
                         <div class="pure-form-message-inline">
@@ -133,23 +140,40 @@
                         </div>
                     </div>
                     <div class="pure-control-group">
+                        <a class="pure-button button-secondary button-xsmall show-advanced">Show advanced options</a>
+                    </div>
+                    <div class="advanced-options"  style="display: none;">
                         {{ render_field(form.webdriver_js_execute_code) }}
                         <div class="pure-form-message-inline">
-                            Run this code before performing change detection, handy for filling in fields and other actions <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Run-JavaScript-before-change-detection">More help and examples here</a>
+                            Run this code before performing change detection, handy for filling in fields and other
+                            actions <a
+                                href="https://github.com/dgtlmoon/changedetection.io/wiki/Run-JavaScript-before-change-detection">More
+                            help and examples here</a>
                         </div>
                     </div>
                 </fieldset>
-                <fieldset class="pure-group" id="requests-override-options">
-                    {% if not playwright_enabled %}
-                        <div class="pure-form-message-inline">
-                            <strong>Request override is currently only used by the <i>Basic fast Plaintext/HTTP Client</i> method.</strong>
-                        </div>
-                    {% endif %}
-                    <div class="pure-control-group" id="request-method">
-                        {{ render_field(form.method) }}
+                <!-- html requests always -->
+                <fieldset data-visible-for="fetch_backend=html_requests">
+                    <div class="pure-control-group">
+                        <a class="pure-button button-secondary button-xsmall show-advanced">Show advanced options</a>
                     </div>
-                    <div class="pure-control-group" id="request-headers">
-{{ render_field(form.headers, rows=5, placeholder="Example
+                    <div class="advanced-options"  style="display: none;">
+                        <div class="pure-control-group" id="request-method">
+                            {{ render_field(form.method) }}
+                        </div>
+                        <div id="request-body">
+                                            {{ render_field(form.body, rows=5, placeholder="Example
+{
+   \"name\":\"John\",
+   \"age\":30,
+   \"car\":null
+}") }}
+                        </div>
+                    </div>
+                </fieldset>
+            <!-- hmm -->
+                <div class="pure-control-group advanced-options"  style="display: none;">
+                    {{ render_field(form.headers, rows=5, placeholder="Example
 Cookie: foobar
 User-Agent: wonderbra 1.0") }}
 
@@ -162,17 +186,12 @@ User-Agent: wonderbra 1.0") }}
                             <br>
                             (Not supported by Selenium browser)
                         </div>
-
                     </div>
-                    <div class="pure-control-group" id="request-body">
-                                        {{ render_field(form.body, rows=5, placeholder="Example
-{
-   \"name\":\"John\",
-   \"age\":30,
-   \"car\":null
-}") }}
+            <fieldset data-visible-for="fetch_backend=html_requests fetch_backend=html_webdriver" >
+                    <div class="pure-control-group inline-radio advanced-options"  style="display: none;">
+                    {{ render_checkbox_field(form.ignore_status_codes) }}
                     </div>
-                </fieldset>
+            </fieldset>
             </div>
             {% if playwright_enabled %}
             <div class="tab-pane-inner" id="browser-steps">
@@ -209,7 +228,7 @@ User-Agent: wonderbra 1.0") }}
                                 </div>
                             </div>
                             <div id="browser-steps-fieldlist" style="padding-left: 1em;  width: 350px; font-size: 80%;" >
-                                <span id="browserless-seconds-remaining">Loading</span> <span style="font-size: 80%;"> (<a target=_new href="https://github.com/dgtlmoon/changedetection.io/pull/478/files#diff-1a79d924d1840c485238e66772391268a89c95b781d69091384cf1ea1ac146c9R4">?</a>) </span>
+                                <span id="browser-seconds-remaining">Loading</span> <span style="font-size: 80%;"> (<a target=_new href="https://github.com/dgtlmoon/changedetection.io/pull/478/files#diff-1a79d924d1840c485238e66772391268a89c95b781d69091384cf1ea1ac146c9R4">?</a>) </span>
                                 {{ render_field(form.browser_steps) }}
                             </div>
                         </div>
@@ -283,11 +302,12 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                                 {% endif %}
                             </ul>
                         </li>
-                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash,
+                        <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://*[contains(@class, 'sametext')]</code>, <a
+                                <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>
@@ -319,6 +339,10 @@ nav
                     <span class="pure-form-message-inline">When content is merely moved in a list, it will also trigger an <strong>addition</strong>, consider enabling <code><strong>Only trigger when unique lines appear</strong></code></span>
                 </fieldset>
 
+                <fieldset class="pure-control-group">
+                    {{ render_checkbox_field(form.sort_text_alphabetically) }}
+                    <span class="pure-form-message-inline">Helps reduce changes detected caused by sites shuffling lines around, combine with <i>check unique lines</i> below.</span>
+                </fieldset>
                 <fieldset class="pure-control-group">
                     {{ render_checkbox_field(form.check_unique_lines) }}
                     <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
@@ -374,15 +398,17 @@ Unavailable") }}
                         {{ render_field(form.extract_text, rows=5, placeholder="\d+ online") }}
                         <span class="pure-form-message-inline">
                     <ul>
-                        <li>Extracts text in the final output (line by line) after other filters using regular expressions;
+                        <li>Extracts text in the final output (line by line) after other filters using regular expressions or string match;
                             <ul>
                                 <li>Regular expression &dash; example <code>/reports.+?2022/i</code></li>
+                                <li>Don't forget to consider the white-space at the start of a line <code>/.+?reports.+?2022/i</code></li>
                                 <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br></li>
                                 <li>Keyword example &dash; example <code>Out of stock</code></li>
                                 <li>Use groups to extract just that text &dash; example <code>/reports.+?(\d+)/i</code> returns a list of years only</li>
+                                <li>Example - match lines containing a keyword <code>/.*icecream.*/</code></li>
                             </ul>
                         </li>
-                        <li>One line per regular-expression/ string match</li>
+                        <li>One line per regular-expression/string match</li>
                     </ul>
                         </span>
                     </div>
@@ -436,7 +462,39 @@ Unavailable") }}
                 </fieldset>
             </div>
             {% endif %}
-
+            <div class="tab-pane-inner" id="stats">
+                <div class="pure-control-group">
+                    <style>
+                    #stats-table tr > td:first-child {
+                        font-weight: bold;
+                    }
+                    </style>
+                    <table class="pure-table" id="stats-table">
+                        <tbody>
+                        <tr>
+                            <td>Check count</td>
+                            <td>{{ "{:,}".format( watch.check_count) }}</td>
+                        </tr>
+                        <tr>
+                            <td>Consecutive filter failures</td>
+                            <td>{{ "{:,}".format( watch.consecutive_filter_failures) }}</td>
+                        </tr>
+                        <tr>
+                            <td>History length</td>
+                            <td>{{ "{:,}".format(watch.history|length) }}</td>
+                        </tr>
+                        <tr>
+                            <td>Last fetch time</td>
+                            <td>{{ watch.fetch_time }}s</td>
+                        </tr>
+                        <tr>
+                            <td>Notification alert count</td>
+                            <td>{{ watch.notification_alert_count }}</td>
+                        </tr>
+                        </tbody>
+                    </table>
+                </div>
+            </div>
             <div id="actions">
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}

changedetectionio/templates/import.html

@@ -8,11 +8,12 @@
         <ul>
             <li class="tab" id=""><a href="#url-list">URL List</a></li>
             <li class="tab"><a href="#distill-io">Distill.io</a></li>
+            <li class="tab"><a href="#xlsx">.XLSX &amp; Wachete</a></li>
         </ul>
     </div>
 
     <div class="box-wrap inner">
-        <form class="pure-form pure-form-aligned" action="{{url_for('import_page')}}" method="POST">
+        <form class="pure-form" action="{{url_for('import_page')}}" method="POST" enctype="multipart/form-data">
             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
             <div class="tab-pane-inner" id="url-list">
                     <legend>
@@ -79,6 +80,42 @@
 " rows="25">{{ original_distill_json }}</textarea>
 
             </div>
+            <div class="tab-pane-inner" id="xlsx">
+            <fieldset>
+                <div class="pure-control-group">
+                {{ render_field(form.xlsx_file, class="processor") }}
+                </div>
+                <div class="pure-control-group">
+                    {{ render_field(form.file_mapping, class="processor") }}
+                </div>
+            </fieldset>
+                <div class="pure-control-group">
+                <span class="pure-form-message-inline">
+                    Table of custom column and data types mapping for the <strong>Custom mapping</strong> File mapping type.
+                </span>
+                    <table style="border: 1px solid #aaa; padding: 0.5rem; border-radius: 4px;">
+                        <tr>
+                            <td><strong>Column #</strong></td>
+                            {% for n in range(4) %}
+                                <td><input type="number" name="custom_xlsx[col_{{n}}]" style="width: 4rem;" min="1"></td>
+                            {%  endfor %}
+                        </tr>
+                        <tr>
+                            <td><strong>Type</strong></td>
+                            {% for n in range(4) %}
+                                <td><select name="custom_xlsx[col_type_{{n}}]">
+                                    <option value="" style="color: #aaa"> -- none --</option>
+                                    <option value="url">URL</option>
+                                    <option value="title">Title</option>
+                                    <option value="include_filters">CSS/xPath filter</option>
+                                    <option value="tag">Group / Tag name(s)</option>
+                                    <option value="interval_minutes">Recheck time (minutes)</option>
+                                </select></td>
+                            {%  endfor %}
+                        </tr>
+                    </table>
+                </div>
+            </div>
             <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">Import</button>
         </form>
 

changedetectionio/templates/preview.html

@@ -6,6 +6,7 @@
     {% if last_error_screenshot %}
     const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
     {% endif %}
+    const highlight_submit_ignore_url="{{url_for('highlight_submit_ignore_url', uuid=uuid)}}";
 </script>
 <script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
@@ -20,7 +21,7 @@
         {% endif %}
     </ul>
 </div>
-
+<form><input type="hidden" name="csrf_token" value="{{ csrf_token() }}"></form>
 <div id="diff-ui">
     <div class="tab-pane-inner" id="error-text">
         <div class="snapshot-age error">{{watch.error_text_ctime|format_seconds_ago}} seconds ago</div>
@@ -36,11 +37,12 @@
 
     <div class="tab-pane-inner" id="text">
         <div class="snapshot-age">{{watch.snapshot_text_ctime|format_timestamp_timeago}}</div>
-        <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span>
+        <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span> <span class="tip"><strong>Pro-tip</strong>: Highlight text to add to ignore filters</span>
+
         <table>
             <tbody>
             <tr>
-                <td id="diff-col">
+                <td id="diff-col" class="highlightable-filter">
                     {% for row in content %}
                     <div class="{{row.classes}}">{{row.line}}</div>
                     {% endfor %}

changedetectionio/templates/settings.html

@@ -4,14 +4,14 @@
 {% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
 <script>
-    const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test', watch_uuid=uuid)}}";
 {% if emailprefix %}
     const email_notification_prefix=JSON.parse('{{emailprefix|tojson}}');
 {% endif %}
 </script>
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
-
+<script src="{{url_for('static_content', group='js', filename='vis.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
 <div class="edit-form">
     <div class="tabs collapsable">
@@ -62,14 +62,6 @@
                         <span class="pure-form-message-inline">Allow access to view watch diff page when password is enabled (Good for sharing the diff page)
                         </span>
                     </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.application.form.base_url, placeholder="http://yoursite.com:5000/",
-                        class="m-d") }}
-                        <span class="pure-form-message-inline">
-                            Base URL used for the <code>{{ '{{ base_url }}' }}</code> token in notifications and RSS links.<br>Default value is the ENV var 'BASE_URL' (Currently "{{settings_application['current_base_url']}}"),
-                            <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">read more here</a>.
-                        </span>
-                    </div>
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.pager_size) }}
                         <span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
@@ -100,6 +92,13 @@
                         {{ render_common_settings_form(form.application.form, emailprefix, settings_application) }}
                     </div>
                 </fieldset>
+                <div class="pure-control-group" id="notification-base-url">
+                    {{ render_field(form.application.form.base_url, class="m-d") }}
+                    <span class="pure-form-message-inline">
+                        Base URL used for the <code>{{ '{{ base_url }}' }}</code> token in notification links.<br>
+                        Default value is the system environment variable '<code>BASE_URL</code>' - <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">read more here</a>.
+                    </span>
+                </div>
             </div>
 
             <div class="tab-pane-inner" id="fetching">
@@ -110,9 +109,9 @@
                         <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
                     </span>
                     <br>
-                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using BrightData Proxies, find out more here.</a>
+                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
                 </div>
-                <fieldset class="pure-group" id="webdriver-override-options">
+                <fieldset class="pure-group" id="webdriver-override-options" data-visible-for="application-fetch_backend=html_webdriver">
                     <div class="pure-form-message-inline">
                         <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
                         <br>
@@ -169,32 +168,93 @@ nav
            </div>
 
             <div class="tab-pane-inner" id="api">
-
+                <h4>API Access</h4>
                 <p>Drive your changedetection.io via API, More about <a href="https://github.com/dgtlmoon/changedetection.io/wiki/API-Reference">API access here</a></p>
 
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.api_access_token_enabled) }}
-                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header</div><br>
+                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header - required for the Chrome Extension to work</div><br>
                     <div class="pure-form-message-inline"><br>API Key <span id="api-key">{{api_key}}</span>
                         <span style="display:none;" id="api-key-copy" >copy</span>
                     </div>
                 </div>
+                <div class="pure-control-group">
+                    <a href="{{url_for('settings_reset_api_key')}}" class="pure-button button-small button-cancel">Regenerate API key</a>
+                </div>
+                <div class="pure-control-group">
+                    <h4>Chrome Extension</h4>
+                    <p>Easily add any web-page to your changedetection.io installation from within Chrome.</p>
+                    <strong>Step 1</strong> Install the extension, <strong>Step 2</strong> Navigate to this page,
+                    <strong>Step 3</strong> Open the extension from the toolbar and click "<i>Sync API Access</i>"
+                    <p>
+                        <a id="chrome-extension-link"
+                           title="Try our new Chrome Extension!"
+                           href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
+                            <img src="{{ url_for('static_content', group='images', filename='Google-Chrome-icon.png') }}">
+                            Chrome Webstore
+                        </a>
+                    </p>
+                </div>
             </div>
             <div class="tab-pane-inner" id="proxies">
+                <div id="recommended-proxy">
+                    <div>
+                        <img style="height: 2em;" src="{{url_for('static_content', group='images', filename='brightdata.svg')}}" alt="BrightData Proxy Provider">
+                        <p>BrightData offer world-class proxy services, "Data Center" proxies are a very affordable way to proxy your requests, whilst <strong><a href="https://brightdata.grsm.io/n0r16zf7eivq">WebUnlocker</a></strong> can help solve most CAPTCHAs.</p>
+                        <p>
+                            BrightData offer many <a href="https://brightdata.com/proxy-types" target="new">many different types of proxies</a>, it is worth reading about what is best for your use-case.
+                        </p>
 
-                <p><strong>Tip</strong>: You can connect to websites using <a href="https://brightdata.grsm.io/n0r16zf7eivq">BrightData</a> proxies, their service <strong>WebUnlocker</strong> will solve most CAPTCHAs, whilst their <strong>Residential Proxies</strong> may help to avoid CAPTCHA altogether. </p>
-                <p>It may be easier to try <strong>WebUnlocker</strong> first, WebUnlocker also supports country selection.</p>
+                        <p>
+                            When you have <a href="https://brightdata.grsm.io/n0r16zf7eivq">registered</a>, enabled the required services, visit the <A href="https://brightdata.com/cp/api_example?">API example page</A>, then select <strong>Python</strong>, set the country you wish to use, then copy+paste the access Proxy URL into the "Extra Proxies" boxes below.<br>
+                        </p>
+                        <p>
+                            The Proxy URL with BrightData should start with <code>http://brd-customer...</code>
+                        </p>
+                        <p>When you sign up using <a href="https://brightdata.grsm.io/n0r16zf7eivq">https://brightdata.grsm.io/n0r16zf7eivq</a> BrightData will match any first deposit up to $150</p>
+                    </div>
+                    <div>
+                        <img style="height: 2em;"
+                             src="{{url_for('static_content', group='images', filename='oxylabs.svg')}}"
+                             alt="Oxylabs Proxy Provider">
+                        <p>
+                            Collect public data at scale with industry-leading web scraping solutions and the world’s
+                            largest ethical proxy network.
+                        </p>
+                        <p>
+                            Oxylabs also provide a <a href="https://oxylabs.io/products/web-unblocker"><strong>WebUnlocker</strong></a>
+                            proxy that bypasses sophisticated anti-bot systems, so you don’t have to.<br>
+                        </p>
+                        <p>
+                            Serve over <a href="https://oxylabs.io/location-proxy">195 countries</a>, providing <a
+                                href="https://oxylabs.io/products/residential-proxy-pool">Residential</a>, <a
+                                href="https://oxylabs.io/products/mobile-proxies">Mobile</a> and <a
+                                href="https://oxylabs.io/products/rotating-isp-proxies">ISP proxies</a> and much more.
+                        </p>
+                        <p>
+                            Use the promo code <strong>boost35</strong> with this link <a href="https://oxylabs.go2cloud.org/SH2d">https://oxylabs.go2cloud.org/SH2d</a> for 35% off Residential, Mobile proxies, Web Unblocker, and Scraper APIs. Built-in proxies enable you to access data from all around the world and help overcome anti-bot solutions.
+
+                        </p>
+
+                        
+                    </div>
+                </div>
                 <p>
-                    When you have <a href="https://brightdata.grsm.io/n0r16zf7eivq">registered</a>, enabled the required services, visit the <A href="https://brightdata.com/cp/api_example?">API example page</A>, then select <strong>Python</strong>, set the country you wish to use, then copy+paste the example URL below<br>
-                    The Proxy URL with BrightData should start with <code>http://brd-customer...</code>
+                    Your proxy provider may need to whitelist our IP of <code>204.15.192.195</code>
                 </p>
+               <p><strong>Tip</strong>: "Residential" and "Mobile" proxy type can be more successfull than "Data Center" for blocked websites.
 
-                <p>When you sign up using <a href="https://brightdata.grsm.io/n0r16zf7eivq">https://brightdata.grsm.io/n0r16zf7eivq</a> BrightData will match any first deposit up to $150</p>
-
-
-                <div class="pure-control-group">
-                    {{ render_field(form.requests.form.extra_proxies) }}
-                    <span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span>
+                <div class="pure-control-group" id="extra-proxies-setting">
+                {{ render_field(form.requests.form.extra_proxies) }}
+                <span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span><br>
+                <span class="pure-form-message-inline">SOCKS5 proxies with authentication are only supported with 'plain requests' fetcher, for other fetchers you should whitelist the IP access instead</span>
+                </div>
+                <div class="pure-control-group" id="extra-browsers-setting">
+                    <p>
+                    <span class="pure-form-message-inline"><i>Extra Browsers</i> can be attached to further defeat CAPTCHA's on websites that are particularly hard to scrape.</span><br>
+                    <span class="pure-form-message-inline">Simply paste the connection address into the box, <a href="https://changedetection.io/tutorial/using-bright-datas-scraping-browser-pass-captchas-and-other-protection-when-monitoring">More instructions and examples here</a> </span>
+                    </p>
+                    {{ render_field(form.requests.form.extra_browsers) }}
                 </div>
             </div>
             <div id="actions">

changedetectionio/templates/svgs/github.svg

@@ -1,3 +1,6 @@
-<svg class="octicon octicon-mark-github v-align-middle" height="32" viewbox="0 0 16 16" version="1.1" width="32" aria-hidden="true">
-  <path fill-rule="evenodd" d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0016 8c0-4.42-3.58-8-8-8z"></path>
+<svg class="octicon octicon-mark-github v-align-middle"  viewbox="0 0 16 16" version="1.1" aria-hidden="true">
+    <path
+     fill-rule="evenodd"
+     d="M 8,0 C 3.58,0 0,3.58 0,8 c 0,3.54 2.29,6.53 5.47,7.59 0.4,0.07 0.55,-0.17 0.55,-0.38 0,-0.19 -0.01,-0.82 -0.01,-1.49 C 4,14.09 3.48,13.23 3.32,12.78 3.23,12.55 2.84,11.84 2.5,11.65 2.22,11.5 1.82,11.13 2.49,11.12 3.12,11.11 3.57,11.7 3.72,11.94 4.44,13.15 5.59,12.81 6.05,12.6 6.12,12.08 6.33,11.73 6.56,11.53 4.78,11.33 2.92,10.64 2.92,7.58 2.92,6.71 3.23,5.99 3.74,5.43 3.66,5.23 3.38,4.41 3.82,3.31 c 0,0 0.67,-0.21 2.2,0.82 0.64,-0.18 1.32,-0.27 2,-0.27 0.68,0 1.36,0.09 2,0.27 1.53,-1.04 2.2,-0.82 2.2,-0.82 0.44,1.1 0.16,1.92 0.08,2.12 0.51,0.56 0.82,1.27 0.82,2.15 0,3.07 -1.87,3.75 -3.65,3.95 0.29,0.25 0.54,0.73 0.54,1.48 0,1.07 -0.01,1.93 -0.01,2.2 0,0.21 0.15,0.46 0.55,0.38 A 8.013,8.013 0 0 0 16,8 C 16,3.58 12.42,0 8,0 Z"
+     id="path2" />
 </svg>

changedetectionio/templates/svgs/search-icon.svg

@@ -1 +1 @@
-<?xml version="1.0" encoding="utf-8"?><svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0 0 122.879 119.799" enable-background="new 0 0 122.879 119.799" xml:space="preserve"><g><path d="M49.988,0h0.016v0.007C63.803,0.011,76.298,5.608,85.34,14.652c9.027,9.031,14.619,21.515,14.628,35.303h0.007v0.033v0.04 h-0.007c-0.005,5.557-0.917,10.905-2.594,15.892c-0.281,0.837-0.575,1.641-0.877,2.409v0.007c-1.446,3.66-3.315,7.12-5.547,10.307 l29.082,26.139l0.018,0.016l0.157,0.146l0.011,0.011c1.642,1.563,2.536,3.656,2.649,5.78c0.11,2.1-0.543,4.248-1.979,5.971 l-0.011,0.016l-0.175,0.203l-0.035,0.035l-0.146,0.16l-0.016,0.021c-1.565,1.642-3.654,2.534-5.78,2.646 c-2.097,0.111-4.247-0.54-5.971-1.978l-0.015-0.011l-0.204-0.175l-0.029-0.024L78.761,90.865c-0.88,0.62-1.778,1.209-2.687,1.765 c-1.233,0.755-2.51,1.466-3.813,2.115c-6.699,3.342-14.269,5.222-22.272,5.222v0.007h-0.016v-0.007 c-13.799-0.004-26.296-5.601-35.338-14.645C5.605,76.291,0.016,63.805,0.007,50.021H0v-0.033v-0.016h0.007 c0.004-13.799,5.601-26.296,14.645-35.338C23.683,5.608,36.167,0.016,49.955,0.007V0H49.988L49.988,0z M50.004,11.21v0.007h-0.016 h-0.033V11.21c-10.686,0.007-20.372,4.35-27.384,11.359C15.56,29.578,11.213,39.274,11.21,49.973h0.007v0.016v0.033H11.21 c0.007,10.686,4.347,20.367,11.359,27.381c7.009,7.012,16.705,11.359,27.403,11.361v-0.007h0.016h0.033v0.007 c10.686-0.007,20.368-4.348,27.382-11.359c7.011-7.009,11.358-16.702,11.36-27.4h-0.006v-0.016v-0.033h0.006 c-0.006-10.686-4.35-20.372-11.358-27.384C70.396,15.56,60.703,11.213,50.004,11.21L50.004,11.21z"/></g></svg>
+<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0 0 122.879 119.799" enable-background="new 0 0 122.879 119.799" xml:space="preserve"><g><path d="M49.988,0h0.016v0.007C63.803,0.011,76.298,5.608,85.34,14.652c9.027,9.031,14.619,21.515,14.628,35.303h0.007v0.033v0.04 h-0.007c-0.005,5.557-0.917,10.905-2.594,15.892c-0.281,0.837-0.575,1.641-0.877,2.409v0.007c-1.446,3.66-3.315,7.12-5.547,10.307 l29.082,26.139l0.018,0.016l0.157,0.146l0.011,0.011c1.642,1.563,2.536,3.656,2.649,5.78c0.11,2.1-0.543,4.248-1.979,5.971 l-0.011,0.016l-0.175,0.203l-0.035,0.035l-0.146,0.16l-0.016,0.021c-1.565,1.642-3.654,2.534-5.78,2.646 c-2.097,0.111-4.247-0.54-5.971-1.978l-0.015-0.011l-0.204-0.175l-0.029-0.024L78.761,90.865c-0.88,0.62-1.778,1.209-2.687,1.765 c-1.233,0.755-2.51,1.466-3.813,2.115c-6.699,3.342-14.269,5.222-22.272,5.222v0.007h-0.016v-0.007 c-13.799-0.004-26.296-5.601-35.338-14.645C5.605,76.291,0.016,63.805,0.007,50.021H0v-0.033v-0.016h0.007 c0.004-13.799,5.601-26.296,14.645-35.338C23.683,5.608,36.167,0.016,49.955,0.007V0H49.988L49.988,0z M50.004,11.21v0.007h-0.016 h-0.033V11.21c-10.686,0.007-20.372,4.35-27.384,11.359C15.56,29.578,11.213,39.274,11.21,49.973h0.007v0.016v0.033H11.21 c0.007,10.686,4.347,20.367,11.359,27.381c7.009,7.012,16.705,11.359,27.403,11.361v-0.007h0.016h0.033v0.007 c10.686-0.007,20.368-4.348,27.382-11.359c7.011-7.009,11.358-16.702,11.36-27.4h-0.006v-0.016v-0.033h0.006 c-0.006-10.686-4.35-20.372-11.358-27.384C70.396,15.56,60.703,11.213,50.004,11.21L50.004,11.21z"/></g></svg>

changedetectionio/templates/watch-overview.html

@@ -1,6 +1,6 @@
 {% extends 'base.html' %}
 {% block content %}
-{% from '_helpers.jinja' import render_simple_field, render_field %}
+{% from '_helpers.jinja' import render_simple_field, render_field, render_nolabel_field, sort_by_title %}
 <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
 <script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
 
@@ -11,17 +11,14 @@
         <fieldset>
             <legend>Add a new change detection watch</legend>
             <div id="watch-add-wrapper-zone">
-                <div>
-                    {{ render_simple_field(form.url, placeholder="https://...", required=true) }}
-                    {{ render_simple_field(form.tags, value=tags[active_tag].title if active_tag else '', placeholder="watch label / tag") }}
-                </div>
-                <div>
-                    {{ render_simple_field(form.watch_submit_button, title="Watch this URL!" ) }}
-                    {{ render_simple_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
-                </div>
+
+                    {{ render_nolabel_field(form.url, placeholder="https://...", required=true) }}
+                    {{ render_nolabel_field(form.tags, value=active_tag.title if active_tag else '', placeholder="watch label / tag") }}
+                    {{ render_nolabel_field(form.watch_submit_button, title="Watch this URL!" ) }}
+                    {{ render_nolabel_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
             </div>
             <div id="quick-watch-processor-type">
-                {{ render_simple_field(form.processor, title="Edit first then Watch") }}
+                {{ render_simple_field(form.processor) }}
             </div>
 
         </fieldset>
@@ -40,6 +37,7 @@
         <button class="pure-button button-secondary button-xsmall" name="op" value="assign-tag" id="checkbox-assign-tag">Tag</button>
         <button class="pure-button button-secondary button-xsmall" name="op" value="mark-viewed">Mark viewed</button>
         <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default">Use default notification</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="clear-errors">Clear errors</button>
         <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="clear-history">Clear/reset history</button>
         <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="delete">Delete</button>
     </div>
@@ -49,11 +47,13 @@
     {% if search_q %}<div id="search-result-info">Searching "<strong><i>{{search_q}}</i></strong>"</div>{% endif %}
     <div>
         <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag }}">All</a>
-        {% for uuid, tag in tags.items() %}
-            {% if tag != "" %}
-                <a href="{{url_for('index', tag=uuid) }}" class="pure-button button-tag {{'active' if active_tag == uuid }}">{{ tag.title }}</a>
-            {% endif %}
-        {% endfor %}
+
+    <!-- tag list -->
+    {% for uuid, tag in tags %}
+        {% if tag != "" %}
+            <a href="{{url_for('index', tag=uuid) }}" class="pure-button button-tag {{'active' if active_tag_uuid == uuid }}">{{ tag.title }}</a>
+        {% endif %}
+    {% endfor %}
     </div>
 
     {% set sort_order = sort_order or 'asc' %}
@@ -82,12 +82,15 @@
             </tr>
             {% endif %}
             {% for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))|pagination_slice(skip=pagination.skip) %}
+
+                {% set is_unviewed =  watch.newest_history_key| int > watch.last_viewed and watch.history_n>=2 %}
+
             <tr id="{{ watch.uuid }}"
                 class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }} processor-{{ watch['processor'] }}
                 {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
                 {% if watch.last_notification_error is defined and watch.last_notification_error != False %}error{% endif %}
                 {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
-                {% if watch.newest_history_key| int > watch.last_viewed and watch.history_n>=2 %}unviewed{% endif %}
+                {% if is_unviewed %}unviewed{% endif %}
                 {% if watch.uuid in queued_uuids %}queued{% endif %}">
                 <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span>{{ loop.index+pagination.skip }}</span></td>
                 <td class="inline watch-controls">
@@ -104,11 +107,13 @@
 
                     {% if watch.get_fetch_backend == "html_webdriver"
                          or (  watch.get_fetch_backend == "system" and system_default_fetcher == 'html_webdriver'  )
+                         or "extra_browser_" in watch.get_fetch_backend
                     %}
-                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a chrome browser" >
+                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a Chrome browser" >
                     {% endif %}
 
                     {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" >{% endif %}
+                    {% if watch.has_browser_steps %}<img class="status-icon status-browsersteps" src="{{url_for('static_content', group='images', filename='steps.svg')}}" title="Browser Steps is enabled" >{% endif %}
                     {% if watch.last_error is defined and watch.last_error != False %}
                     <div class="fetch-error">{{ watch.last_error }}
 
@@ -119,6 +124,9 @@
                             <a href="{{ url_for('settings_page', uuid=watch.uuid) }}#proxies">Try adding external proxies/locations</a>
                         
                         {% endif %}
+                        {% if 'empty result or contain only an image' in watch.last_error %}
+                            <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Detecting-changes-in-images">more help here</a>.
+                        {% endif %}
                     </div>
                     {% endif %}
                     {% if watch.last_notification_error is defined and watch.last_notification_error != False %}
@@ -137,7 +145,7 @@
                     {% if watch['processor'] == 'restock_diff'  %}
                     <span class="restock-label {{'in-stock' if watch['in_stock'] else 'not-in-stock' }}" title="detecting restock conditions">
                         <!-- maybe some object watch['processor'][restock_diff] or.. -->
-                        {% if watch['last_checked'] %}
+                        {% if watch['last_checked'] and watch['in_stock'] != None %}
                             {% if watch['in_stock'] %} In stock {% else %} Not in stock {% endif %}
                         {% else %}
                             Not yet checked
@@ -151,8 +159,8 @@
                     {% endfor %}
 
                 </td>
-                <td class="last-checked">{{watch|format_last_checked_time|safe}}</td>
-                <td class="last-changed">{% if watch.history_n >=2 and watch.last_changed >0 %}
+                <td class="last-checked" data-timestamp="{{ watch.last_checked }}">{{watch|format_last_checked_time|safe}}</td>
+                <td class="last-changed" data-timestamp="{{ watch.last_changed }}">{% if watch.history_n >=2 and watch.last_changed >0 %}
                     {{watch.last_changed|format_timestamp_timeago}}
                     {% else %}
                     Not yet
@@ -163,7 +171,13 @@
                        class="recheck pure-button pure-button-primary">{% if watch.uuid in queued_uuids %}Queued{% else %}Recheck{% endif %}</a>
                     <a href="{{ url_for('edit_page', uuid=watch.uuid)}}" class="pure-button pure-button-primary">Edit</a>
                     {% if watch.history_n >= 2 %}
-                    <a href="{{ url_for('diff_history_page', uuid=watch.uuid) }}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+
+                        {%  if is_unviewed %}
+                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid, from_version=watch.get_next_snapshot_key_to_last_viewed) }}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+                        {% else %}
+                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+                        {% endif %}
+
                     {% else %}
                         {% if watch.history_n == 1 or (watch.history_n ==0 and watch.error_text_ctime )%}
                             <a href="{{ url_for('preview_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button pure-button-primary">Preview</a>
@@ -175,14 +189,19 @@
             </tbody>
         </table>
         <ul id="post-list-buttons">
+            {% if errored_count %}
+            <li>
+                <a href="{{url_for('index', with_errors=1, tag=request.args.get('tag')) }}" class="pure-button button-tag button-error ">With errors ({{ errored_count }})</a>
+            </li>
+            {% endif %}
             {% if has_unviewed %}
             <li>
-                <a href="{{url_for('mark_all_viewed', tag=request.args.get('tag')) }}" class="pure-button button-tag ">Mark all viewed</a>
+                <a href="{{url_for('mark_all_viewed',with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Mark all viewed</a>
             </li>
             {% endif %}
             <li>
-               <a href="{{ url_for('form_watch_checknow', tag=active_tag) }}" class="pure-button button-tag ">Recheck
-                all {% if active_tag%} in "{{tags[active_tag].title}}"{%endif%}</a>
+               <a href="{{ url_for('form_watch_checknow', tag=active_tag_uuid, with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Recheck
+                all {% if active_tag_uuid %} in "{{active_tag.title}}"{%endif%}</a>
             </li>
             <li>
                 <a href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='Generic_Feed-icon.svg')}}" height="15"></a>