Re #23 - always check value of interval time, not just on start

.dockerignore

@@ -1,31 +0,0 @@
-# Git
-.git/
-.gitignore
-
-# GitHub
-.github/
-
-# Byte-compiled / optimized / DLL files
-**/__pycache__
-**/*.py[cod]
-
-# Caches
-.mypy_cache/
-.pytest_cache/
-.ruff_cache/
-
-# Distribution / packaging
-build/
-dist/
-*.egg-info*
-
-# Virtual environment
-.env
-.venv/
-venv/
-
-# IntelliJ IDEA
-.idea/
-
-# Visual Studio
-.vscode/

.github/FUNDING.yml

@@ -1,3 +1,12 @@
 # These are supported funding model platforms
 
 github: dgtlmoon
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+otechie: # Replace with a single Otechie username
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,62 +0,0 @@
----
-name: Bug report
-about: Create a bug report, if you don't follow this template, your report will be DELETED
-title: ''
-labels: 'triage'
-assignees: 'dgtlmoon'
-
----
-
-**DO NOT USE THIS FORM TO REPORT THAT A PARTICULAR WEBSITE IS NOT SCRAPING/WATCHING AS EXPECTED**
-
-This form is only for direct bugs and feature requests todo directly with the software.
-
-Please report watched websites (full URL and _any_ settings) that do not work with changedetection.io as expected [**IN THE DISCUSSION FORUMS**](https://github.com/dgtlmoon/changedetection.io/discussions) or your report will be deleted
-
-CONSIDER TAKING OUT A SUBSCRIPTION FOR A SMALL PRICE PER MONTH, YOU GET THE BENEFIT OF USING OUR PAID PROXIES AND FURTHERING THE DEVELOPMENT OF CHANGEDETECTION.IO
-
-THANK YOU
-
-
-
-
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**Version**
-*Exact version* in the top right area: 0....
-
-**How did you install?**
-
-Docker, Pip, from source directly etc
-
-**To Reproduce**
-
-Steps to reproduce the behavior:
-1. Go to '...'
-2. Click on '....'
-3. Scroll down to '....'
-4. See error
-
-! ALWAYS INCLUDE AN EXAMPLE URL WHERE IT IS POSSIBLE TO RE-CREATE THE ISSUE - USE THE 'SHARE WATCH' FEATURE AND PASTE IN THE SHARE-LINK!
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**Desktop (please complete the following information):**
- - OS: [e.g. iOS] 
- - Browser [e.g. chrome, safari]
- - Version [e.g. 22]
-
-**Smartphone (please complete the following information):**
- - Device: [e.g. iPhone6]
- - OS: [e.g. iOS8.1]
- - Browser [e.g. stock browser, safari]
- - Version [e.g. 22]
-
-**Additional context**
-Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,23 +0,0 @@
----
-name: Feature request
-about: Suggest an idea for this project
-title: '[feature]'
-labels: 'enhancement'
-assignees: ''
-
----
-**Version and OS**
-For example, 0.123 on linux/docker
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Describe the use-case and give concrete real-world examples**
-Attach any HTML/JSON, give links to sites, screenshots etc, we are not mind readers
-
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

.github/dependabot.yml

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

.github/test/Dockerfile-alpine

@@ -1,34 +0,0 @@
-# Taken from https://github.com/linuxserver/docker-changedetection.io/blob/main/Dockerfile
-# Test that we can still build on Alpine (musl modified libc https://musl.libc.org/)
-# Some packages wont install via pypi because they dont have a wheel available under this architecture.
-
-FROM ghcr.io/linuxserver/baseimage-alpine:3.21
-ENV PYTHONUNBUFFERED=1
-
-COPY requirements.txt /requirements.txt
-
-RUN \
- apk add --update --no-cache --virtual=build-dependencies \
-    build-base \
-    cargo \
-    git \
-    jpeg-dev \
-    libc-dev \
-    libffi-dev \
-    libxslt-dev \
-    openssl-dev \
-    python3-dev \
-    zip \
-    zlib-dev && \
-  apk add --update --no-cache \
-    libjpeg \
-    libxslt \
-    nodejs \
-    poppler-utils \
-    python3 && \
-  echo "**** pip3 install test of changedetection.io ****" && \
-  python3 -m venv /lsiopy  && \
-  pip install -U pip wheel setuptools && \
-  pip install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.21/ -r /requirements.txt && \
-  apk del --purge \
-    build-dependencies

.github/workflows/codeql-analysis.yml

@@ -1,62 +0,0 @@
-# For most projects, this workflow file will not need changing; you simply need
-# to commit it to your repository.
-#
-# You may wish to alter this file to override the set of languages analyzed,
-# or to provide custom queries or build logic.
-#
-# ******** NOTE ********
-# We have attempted to detect the languages in your repository. Please check
-# the `language` matrix defined below to confirm you have the correct set of
-# supported CodeQL languages.
-#
-name: "CodeQL"
-
-on:
-  schedule:
-    - cron: '27 9 * * 4'
-
-jobs:
-  analyze:
-    name: Analyze
-    runs-on: ubuntu-latest
-
-    strategy:
-      fail-fast: false
-      matrix:
-        language: [ 'javascript', 'python' ]
-        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python' ]
-        # Learn more:
-        # https://docs.github.com/en/free-pro-team@latest/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#changing-the-languages-that-are-analyzed
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v4
-
-    # Initializes the CodeQL tools for scanning.
-    - name: Initialize CodeQL
-      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.
-        # By default, queries listed here will override any specified in a config file.
-        # Prefix the list here with "+" to use these queries and those in the config file.
-        # queries: ./path/to/local/query, your-org/your-repo/queries@main
-
-    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
-    # If this step fails, then you should remove it and run the build manually (see below)
-    - name: Autobuild
-      uses: github/codeql-action/autobuild@v3
-
-    # ℹ️ Command-line programs to run using the OS shell.
-    # 📚 https://git.io/JvXDl
-
-    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
-    #    and modify them (or add more) to build your code if your project
-    #    uses a compiled language
-
-    #- run: |
-    #   make bootstrap
-    #   make release
-
-    - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3

.github/workflows/containers.yml

@@ -1,136 +0,0 @@
-name: Build and push containers
-
-on:
-  # Automatically triggered by a testing workflow passing, but this is only checked when it lands in the `master`/default branch
-#  workflow_run:
-#    workflows: ["ChangeDetection.io Test"]
-#    branches: [master]
-#    tags: ['0.*']
-#    types: [completed]
-
-  # Or a new tagged release
-  release:
-    types: [published, edited]
-
-  push:
-    branches:
-      - master
-
-jobs:
-  metadata:
-    runs-on: ubuntu-latest
-    steps:
-    - name: Show metadata
-      run: |
-        echo SHA ${{ github.sha }}
-        echo github.ref:  ${{ github.ref }}
-        echo github_ref: $GITHUB_REF
-        echo Event name: ${{ github.event_name }}
-        echo Ref ${{ github.ref }}
-        echo c: ${{ github.event.workflow_run.conclusion }}
-        echo r: ${{ github.event.workflow_run }}
-        echo tname: "${{ github.event.release.tag_name }}"
-        echo headbranch: -${{ github.event.workflow_run.head_branch }}-
-        set
-
-  build-push-containers:
-    runs-on: ubuntu-latest
-    # If the testing workflow has a success, then we build to :latest
-    # Or if we are in a tagged release scenario.
-    if: ${{ github.event.workflow_run.conclusion == 'success' }} || ${{ github.event.release.tag_name }} != ''
-    steps:
-      - uses: actions/checkout@v4
-      - name: Set up Python 3.11
-        uses: actions/setup-python@v5
-        with:
-          python-version: 3.11
-
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install flake8 pytest
-          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-
-      - name: Create release metadata
-        run: |
-          # COPY'ed by Dockerfile into changedetectionio/ of the image, then read by the server in store.py
-          echo ${{ github.sha }} > changedetectionio/source.txt
-          echo ${{ github.ref }} > changedetectionio/tag.txt
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-        with:
-          image: tonistiigi/binfmt:latest
-          platforms: all
-
-      - name: Login to GitHub Container Registry
-        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@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@v3
-        with:
-          install: true
-          version: latest
-          driver-opts: image=moby/buildkit:master
-
-      # master branch -> :dev container tag
-      - name: Build and push :dev
-        id: docker_build
-        if: ${{ github.ref }} == "refs/heads/master"
-        uses: docker/build-push-action@v6
-        with:
-          context: ./
-          file: ./Dockerfile
-          push: true
-          tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
-          platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/v8
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-
-# Looks like this was disabled
-#          provenance: false
-
-      # A new tagged release is required, which builds :tag and :latest
-      - name: Docker meta :tag
-        if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
-        uses: docker/metadata-action@v5
-        id: meta
-        with:
-            images: |
-                ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io
-                ghcr.io/dgtlmoon/changedetection.io
-            tags: |
-                type=semver,pattern={{version}}
-                type=semver,pattern={{major}}.{{minor}}
-                type=semver,pattern={{major}}
-
-      - 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@v6
-        with:
-          context: ./
-          file: ./Dockerfile
-          push: true
-          tags: ${{ steps.meta.outputs.tags }}
-          platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/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 }}
-

.github/workflows/pypi-release.yml

@@ -1,80 +0,0 @@
-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
-        ls -alR 
-        
-        # Find and install the first .whl file
-        find dist -type f -name "*.whl" -exec pip3 install {} \; -quit
-        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/python-app.yml

@@ -0,0 +1,33 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: changedetection.io
+
+
+on: [push, pull_request]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python 3.9
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.9
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install flake8 pytest
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with pytest
+      run: |
+        cd backend; pytest

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

@@ -1,70 +0,0 @@
-name: ChangeDetection.io Container Build 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]
-
-on:
-  push:
-    paths:
-      - 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
-jobs:
-  test-container-build:
-    runs-on: ubuntu-latest
-    steps:
-        - uses: actions/checkout@v4
-        - name: Set up Python 3.11
-          uses: actions/setup-python@v5
-          with:
-            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@v3
-          with:
-            image: tonistiigi/binfmt:latest
-            platforms: all
-
-        - name: Set up Docker Buildx
-          id: buildx
-          uses: docker/setup-buildx-action@v3
-          with:
-            install: true
-            version: latest
-            driver-opts: image=moby/buildkit:master
-
-        # https://github.com/dgtlmoon/changedetection.io/pull/1067
-        # Check we can still build under alpine/musl
-        - name: Test that the docker containers can build (musl via alpine check)
-          id: docker_build_musl
-          uses: docker/build-push-action@v6
-          with:
-            context: ./
-            file: ./.github/test/Dockerfile-alpine
-            platforms: linux/amd64,linux/arm64
-
-        - name: Test that the docker containers can build
-          id: docker_build
-          uses: docker/build-push-action@v6
-          # https://github.com/docker/build-push-action#customizing
-          with:
-            context: ./
-            file: ./Dockerfile
-            platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/v8
-            cache-from: type=local,src=/tmp/.buildx-cache
-            cache-to: type=local,dest=/tmp/.buildx-cache
-

.github/workflows/test-only.yml

@@ -1,45 +0,0 @@
-name: ChangeDetection.io App Test
-
-# Triggers the workflow on push or pull request events
-on: [push, pull_request]
-
-jobs:
-  lint-code:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - name: Lint with flake8
-        run: |
-          pip3 install flake8
-          # stop the build if there are Python syntax errors or undefined names
-          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-          # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-          flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-
-  test-application-3-10:
-    needs: lint-code
-    uses: ./.github/workflows/test-stack-reusable-workflow.yml
-    with:
-      python-version: '3.10'
-
-
-  test-application-3-11:
-    needs: lint-code
-    uses: ./.github/workflows/test-stack-reusable-workflow.yml
-    with:
-      python-version: '3.11'
-
-  test-application-3-12:
-    needs: lint-code
-    uses: ./.github/workflows/test-stack-reusable-workflow.yml
-    with:
-      python-version: '3.12'
-      skip-pypuppeteer: true
-
-  test-application-3-13:
-    needs: lint-code
-    uses: ./.github/workflows/test-stack-reusable-workflow.yml
-    with:
-      python-version: '3.13'
-      skip-pypuppeteer: true
-      

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

@@ -1,241 +0,0 @@
-name: ChangeDetection.io App Test
-
-on:
-  workflow_call:
-    inputs:
-      python-version:
-        description: 'Python version to use'
-        required: true
-        type: string
-        default: '3.11'
-      skip-pypuppeteer:
-        description: 'Skip PyPuppeteer (not supported in 3.11/3.12)'
-        required: false
-        type: boolean
-        default: false
-
-jobs:
-  test-application:
-    runs-on: ubuntu-latest
-    env:
-      PYTHON_VERSION: ${{ inputs.python-version }}
-    steps:
-      - uses: actions/checkout@v4
-
-      # Mainly just for link/flake8
-      - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - name: Build changedetection.io container for testing under Python ${{ env.PYTHON_VERSION }}
-        run: |
-          echo "---- Building for Python ${{ env.PYTHON_VERSION }} -----"
-          # Build a changedetection.io container and start testing inside
-          docker build --build-arg PYTHON_VERSION=${{ env.PYTHON_VERSION }} --build-arg LOGGER_LEVEL=TRACE -t test-changedetectionio .
-          # Debug info
-          docker run test-changedetectionio  bash -c 'pip list'         
-
-      - name: We should be Python ${{ env.PYTHON_VERSION }} ...
-        run: |         
-          docker run test-changedetectionio  bash -c 'python3 --version'
-
-      - name: Spin up ancillary testable services
-        run: |
-          
-          docker network create changedet-network
-          
-          # Selenium
-          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome:4
-          
-          # SocketPuppetBrowser + Extra for custom browser test
-          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser --hostname sockpuppetbrowser --rm -p 3000:3000 dgtlmoon/sockpuppetbrowser:latest                    
-          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser-custom-url --hostname sockpuppetbrowser-custom-url  -p 3001:3000 --rm dgtlmoon/sockpuppetbrowser:latest
-
-      - 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 'pip3 install aiosmtpd && python changedetectionio/tests/smtp/smtp-test-server.py'
-          docker ps
-
-      - name: Show docker container state and other debug info
-        run: |
-          set -x
-          echo "Running processes in docker..."
-          docker ps
-
-      - name: Run Unit Tests
-        run: |
-          # Unit tests
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_watch_model'
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_jinja2_security'
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_semver'
-
-      - name: Test built container with Pytest (generally as requests/plaintext fetching)
-        run: |
-          # All tests
-          echo "run test with pytest"
-          # The default pytest logger_level is TRACE
-          # To change logger_level for pytest(test/conftest.py),
-          # append the docker option. e.g. '-e LOGGER_LEVEL=DEBUG'
-          docker run --name test-cdio-basic-tests --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio && ./run_basic_tests.sh'
-
-# 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 'find .; cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py; pwd;find .'
-
-      - name: Playwright and SocketPuppetBrowser - Restock detection
-        run: |                            
-          # restock detection via playwright - added name=changedet here so that playwright and sockpuppetbrowser can connect to it
-          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
-
-# STRAIGHT TO CDP
-      - name: Pyppeteer and SocketPuppetBrowser - Specific tests in built container
-        if: ${{ inputs.skip-pypuppeteer == false }}
-        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
-        if: ${{ inputs.skip-pypuppeteer == false }}
-        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
-        if: ${{ inputs.skip-pypuppeteer == false }}
-        run: |                            
-          # restock detection via playwright - added name=changedet here so that playwright and sockpuppetbrowser can connect to it
-          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet"  -e "FAST_PUPPETEER_CHROME_FETCHER=True"  -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
-
-# SELENIUM
-      - name: Specific tests in built container for Selenium
-        run: |
-          # Selenium fetch
-          docker run --rm -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py'
-
-      - name: Specific tests in built container for headers and requests checks with Selenium
-        run: |
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
-
-# OTHER STUFF
-      - name: Test SMTP notification mime types
-        run: |
-          # SMTP content types - needs the 'Debug SMTP server/echo message back server' container from above
-          # "mailserver" hostname defined above
-          docker run --rm --network changedet-network test-changedetectionio bash -c 'cd changedetectionio;pytest tests/smtp/test_notification_smtp.py'
-
-      # @todo Add a test via playwright/puppeteer
-      # squid with auth is tested in run_proxy_tests.sh -> tests/proxy_list/test_select_custom_proxy.py
-      - name: Test proxy squid style interaction
-        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 --name test-changedetectionio -p 5556:5000  -d test-changedetectionio
-          sleep 3
-          # Should return 0 (no error) when grep finds it
-          curl --retry-connrefused --retry 6  -s http://localhost:5556 |grep -q checkbox-uuid
-          
-          # and IPv6
-          curl --retry-connrefused --retry 6  -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
-
-          # Check whether TRACE log is enabled.
-          # Also, check whether TRACE 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 [ $? -ne 0 ]
-          then
-            echo "Looks like container was running when it shouldnt be"
-            docker ps
-            exit 1
-          fi
-          
-          # @todo - scan the container log to see the right "graceful shutdown" text exists           
-          docker rm sig-test
-
-      - name: Dump container log
-        if: always()
-        run: |
-          mkdir output-logs
-          docker logs test-cdio-basic-tests > output-logs/test-cdio-basic-tests-stdout-${{ env.PYTHON_VERSION }}.txt
-          docker logs test-cdio-basic-tests 2> output-logs/test-cdio-basic-tests-stderr-${{ env.PYTHON_VERSION }}.txt
-
-      - name: Store everything including test-datastore
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: test-cdio-basic-tests-output-py${{ env.PYTHON_VERSION }}
-          path: .

.gitignore

@@ -1,29 +1,7 @@
-# Byte-compiled / optimized / DLL files
-**/__pycache__
-**/*.py[cod]
-
-# Caches
-.mypy_cache/
-.pytest_cache/
-.ruff_cache/
-
-# Distribution / packaging
-build/
-dist/
-*.egg-info*
-
-# Virtual environment
-.env
-.venv/
-venv/
-
-# IDEs
+__pycache__
 .idea
-.vscode/settings.json
-
-# Datastore files
-datastore/
-test-datastore/
-
-# Memory consumption log
-test-memory.log
+*.pyc
+datastore/url-watches.json
+datastore/*
+__pycache__
+.pytest_cache

COMMERCIAL_LICENCE.md

@@ -1,54 +0,0 @@
-# Generally
-
-In any commercial activity involving 'Hosting' (as defined herein), whether in part or in full, this license must be executed and adhered to.
-
-# Commercial License Agreement
-
-This Commercial License Agreement ("Agreement") is entered into by and between Web Technologies s.r.o. here-in ("Licensor") and (your company or personal name) _____________ ("Licensee"). This Agreement sets forth the terms and conditions under which Licensor provides its software ("Software") and services to Licensee for the purpose of reselling the software either in part or full, as part of any commercial activity where the activity involves a third party.
-
-### Definition of Hosting
-
-For the purposes of this Agreement, "hosting" means making the functionality of the Program or modified version available to third parties as a service. This includes, without limitation:
-- Enabling third parties to interact with the functionality of the Program or modified version remotely through a computer network.
-- Offering a service the value of which entirely or primarily derives from the value of the Program or modified version.
-- Offering a service that accomplishes for users the primary purpose of the Program or modified version.
-
-## 1. Grant of License
-Subject to the terms and conditions of this Agreement, Licensor grants Licensee a non-exclusive, non-transferable license to install, use, and resell the Software. Licensee may:
-- Resell the Software as part of a service offering or as a standalone product.
-- Host the Software on a server and provide it as a hosted service (e.g., Software as a Service - SaaS).
-- Integrate the Software into a larger product or service that is then sold or provided for commercial purposes, where the software is used either in part or full.
-
-## 2. License Fees
-Licensee agrees to pay Licensor the license fees specified in the ordering document. License fees are due and payable as specified in the ordering document. The fees may include initial licensing costs and recurring fees based on the number of end users, instances of the Software resold, or revenue generated from the resale activities.
-
-## 3. Resale Conditions
-Licensee must comply with the following conditions when reselling the Software, whether the software is resold in part or full:
-- Provide end users with access to the source code under the same open-source license conditions as provided by Licensor.
-- Clearly state in all marketing and sales materials that the Software is provided under a commercial license from Licensor, and provide a link back to https://changedetection.io.
-- Ensure end users are aware of and agree to the terms of the commercial license prior to resale.
-- Do not sublicense or transfer the Software to third parties except as part of an authorized resale activity.
-
-## 4. Hosting and Provision of Services
-Licensee may host the Software (either in part or full) on its servers and provide it as a hosted service to end users. The following conditions apply:
-- Licensee must ensure that all hosted versions of the Software comply with the terms of this Agreement.
-- Licensee must provide Licensor with regular reports detailing the number of end users and instances of the hosted service.
-- Any modifications to the Software made by Licensee for hosting purposes must be made available to end users under the same open-source license conditions, unless agreed otherwise.
-
-## 5. Services
-Licensor will provide support and maintenance services as described in the support policy referenced in the ordering document should such an agreement be signed by all parties. Additional fees may apply for support services provided to end users resold by Licensee.
-
-## 6. Reporting and Audits
-Licensee agrees to provide Licensor with regular reports detailing the number of instances, end users, and revenue generated from the resale of the Software. Licensor reserves the right to audit Licensee’s records to ensure compliance with this Agreement.
-
-## 7. Term and Termination
-This Agreement shall commence on the effective date and continue for the period set forth in the ordering document unless terminated earlier in accordance with this Agreement. Either party may terminate this Agreement if the other party breaches any material term and fails to cure such breach within thirty (30) days after receipt of written notice.
-
-## 8. Limitation of Liability and Disclaimer of Warranty
-Executing this commercial license does not waive the Limitation of Liability or Disclaimer of Warranty as stated in the open-source LICENSE provided with the Software. The Software is provided "as is," without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, and noninfringement. In no event shall the authors or copyright holders be liable for any claim, damages, or other liability, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the Software or the use or other dealings in the Software.
-
-## 9. Governing Law
-This Agreement shall be governed by and construed in accordance with the laws of the Czech Republic.
-
-## Contact Information
-For commercial licensing inquiries, please contact contact@changedetection.io and dgtlmoon@gmail.com.

CONTRIBUTING.md

@@ -1,9 +0,0 @@
-Contributing is always welcome!
-
-I am no professional flask developer, if you know a better way that something can be done, please let me know!
-
-Otherwise, it's always best to PR into the `master` branch.
-
-Please be sure that all new functionality has a matching test!
-
-Use `pytest` to validate/test, you can run the existing tests as `pytest tests/test_notification.py` for example

Dockerfile

@@ -1,76 +1,28 @@
-# pip dependencies install stage
+FROM python:3.8-slim
+COPY requirements.txt /tmp/requirements.txt
+RUN pip3 install -r /tmp/requirements.txt
 
-ARG PYTHON_VERSION=3.11
 
-FROM python:${PYTHON_VERSION}-slim-bookworm AS builder
+RUN [ ! -d "/app" ] && mkdir /app
+RUN [ ! -d "/datastore" ] && mkdir /datastore
 
-# See `cryptography` pin comment in requirements.txt
-ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
+# The actual flask app
+COPY backend /app/backend
 
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    g++ \
-    gcc \
-    libc-dev \
-    libffi-dev \
-    libjpeg-dev \
-    libssl-dev \
-    libxslt-dev \
-    make \
-    zlib1g-dev
-
-RUN mkdir /install
-WORKDIR /install
-
-COPY requirements.txt /requirements.txt
-
-# --extra-index-url https://www.piwheels.org/simple  is for cryptography module to be prebuilt (or rustc etc needs to be installed)
-RUN pip install --extra-index-url https://www.piwheels.org/simple  --target=/dependencies -r /requirements.txt
-
-# Playwright is an alternative to Selenium
-# Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
-# https://github.com/dgtlmoon/changedetection.io/pull/1067 also musl/alpine (not supported)
-RUN pip install --target=/dependencies playwright~=1.48.0 \
-    || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
-
-# Final image stage
-FROM python:${PYTHON_VERSION}-slim-bookworm
-LABEL org.opencontainers.image.source="https://github.com/dgtlmoon/changedetection.io"
-
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    libxslt1.1 \
-    # For presenting price amounts correctly in the restock/price detection overview
-    locales \
-    # For pdftohtml
-    poppler-utils \
-    zlib1g \
-    && apt-get clean && rm -rf /var/lib/apt/lists/*
+# The eventlet server wrapper
+COPY changedetection.py /app/changedetection.py
 
+WORKDIR /app
 
 # https://stackoverflow.com/questions/58701233/docker-logs-erroneously-appears-empty-until-container-stops
 ENV PYTHONUNBUFFERED=1
 
-RUN [ ! -d "/datastore" ] && mkdir /datastore
+# Attempt to store the triggered commit
+ARG SOURCE_COMMIT
+ARG SOURCE_BRANCH
+RUN echo "commit: $SOURCE_COMMIT branch: $SOURCE_BRANCH" >/source.txt
+
+CMD [ "python", "./changedetection.py" , "-d", "/datastore"]
 
-# Re #80, sets SECLEVEL=1 in openssl.conf to allow monitoring sites with weak/old cipher suites
-RUN sed -i 's/^CipherString = .*/CipherString = DEFAULT@SECLEVEL=1/' /etc/ssl/openssl.cnf
-
-# Copy modules over to the final image and add their dir to PYTHONPATH
-COPY --from=builder /dependencies /usr/local
-ENV PYTHONPATH=/usr/local
-
-EXPOSE 5000
-
-# The actual flask app module
-COPY changedetectionio /app/changedetectionio
-# Starting wrapper
-COPY changedetection.py /app/changedetection.py
-
-# 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"]
 
 

MANIFEST.in

@@ -1,23 +0,0 @@
-recursive-include changedetectionio/api *
-recursive-include changedetectionio/blueprint *
-recursive-include changedetectionio/content_fetchers *
-recursive-include changedetectionio/conditions *
-recursive-include changedetectionio/model *
-recursive-include changedetectionio/notification *
-recursive-include changedetectionio/processors *
-recursive-include changedetectionio/static *
-recursive-include changedetectionio/templates *
-recursive-include changedetectionio/tests *
-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

README-pip.md

@@ -1,99 +0,0 @@
-## Web Site Change Detection, Monitoring and Notification.
-
-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, 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) 
-
-
-### 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
-- University/organisation news from their website
-- Detect and monitor changes in JSON API responses 
-- JSON API monitoring and alerting
-- Changes in legal and other documents
-- Trigger API calls via notifications when text appears on a website
-- Glue together APIs using the JSON filter and JSON notifications
-- 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(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 $100 using our signup link.
-
-[Oxylabs](https://oxylabs.go2cloud.org/SH2d) is also an excellent proxy provider and well worth using, they offer Residental, ISP, Rotating and many other proxy types to suit your project. 
-
-Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
-
-
-
-```bash
-$ pip3 install changedetection.io
-```
-
-Specify a target for the *datastore path* with `-d` (required) and a *listening port* with `-p` (defaults to `5000`)
-
-```bash
-$ changedetection.io -d /path/to/empty/data/dir -p 5000
-```
-
-
-Then visit http://127.0.0.1:5000 , You should now be able to access the UI.
-
-See https://changedetection.io for more information.
-

README.md

@@ -1,316 +1,63 @@
-## Web Site Change Detection, Restock monitoring and notifications.
+#  changedetection.io
+![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/python-app.yml/badge.svg?branch=master)
+<a href="https://hub.docker.com/r/dgtlmoon/changedetection.io" target="_blank" title="Change detection docker hub">
+  <img src="https://img.shields.io/docker/pulls/dgtlmoon/changedetection.io" alt="Docker Pulls"/>
+</a>
+<a href="https://hub.docker.com/r/dgtlmoon/changedetection.io" target="_blank" title="Change detection docker hub">
+  <img src="https://img.shields.io/docker/v/dgtlmoon/changedetection.io/0.27" alt="Change detection latest tag version"/> 
+</a>
 
-**_Detect website content changes and perform meaningful actions - trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._**
+## Self-hosted change monitoring of web pages.
 
-_Live your data-life pro-actively._ 
+_Know when web pages change! Stay ontop of new information!_
+
+![Self-hosted web page change monitoring application screenshot](screenshot.png?raw=true "Self-hosted web page change monitoring screenshot")
 
 
-[<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)
+#### Example use cases
 
-[![Release Version][release-shield]][release-link] [![Docker Pulls][docker-pulls]][docker-link] [![License][license-shield]](LICENSE.md)
+Know when ...
 
-![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
-
-[**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="Select parts and elements of a web page to monitor for changes"  title="Select parts and elements of a web page to monitor for changes" />](https://changedetection.io?src=github)
-
-### Easily see what changed, examine by word, line, or individual character.
-
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://changedetection.io?src=github)
-
-
-### 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=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.
-
-### Awesome restock and price change notifications
-
-Enable the _"Re-stock & Price detection for single product pages"_ option to activate the best way to monitor product pricing, this will extract any meta-data in the HTML page and give you many options to follow the pricing of the product.
-
-Easily organise and monitor prices for products from the dashboard, get alerts and notifications when the price of a product changes or comes back in stock again!
-
-[<img src="docs/restock-overview.png" style="max-width:100%;" alt="Easily keep an eye on product price changes directly from the UI"  title="Easily keep an eye on product price changes directly from the UI" />](https://changedetection.io?src=github)
-
-Set price change notification parameters, upper and lower price, price change percentage and more.
-Always know when a product for sale drops in price.
-
-[<img src="docs/restock-settings.png" style="max-width:100%;" alt="Set upper lower and percentage price change notification values"  title="Set upper lower and percentage price change notification values" />](https://changedetection.io?src=github)
-
-
-
-### 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)
+- Government department updates (changes are often only on their websites)
+- Local government news (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
-- University/organisation news from their website
-- Detect and monitor changes in JSON API responses 
-- JSON API monitoring and alerting
-- Changes in legal and other documents
-- Trigger API calls via notifications when text appears on a website
-- Glue together APIs using the JSON filter and JSON notifications
-- 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 1 and xPath 2, 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/
-
-### Conditional web page changes
-
-Easily [configure conditional actions](https://changedetection.io/tutorial/conditional-actions-web-page-changes), for example, only trigger when a price is above or below a preset amount, or [when a web page includes (or does not include) a keyword](https://changedetection.io/tutorial/how-monitor-keywords-any-website)
-
-<img src="./docs/web-page-change-conditions.png" style="max-width:80%;" alt="Conditional web page changes"  title="Conditional web page changes"  />
-
-### Schedule web page watches in any timezone, limit by day of week and time.
-
-Easily set a re-check schedule, for example you could limit the web page change detection to only operate during business hours.
-Or perhaps based on a foreign timezone (for example, you want to check for the latest news-headlines in a foreign country at 0900 AM),
-
-<img src="./docs/scheduler.png" style="max-width:80%;" alt="How to monitor web page changes according to a schedule"  title="How to monitor web page changes according to a schedule"  />
-
-Includes quick short-cut buttons to setup a schedule for **business hours only**, or **weekends**.
-
-### 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) ( Or check out the [GitHub repo](https://github.com/dgtlmoon/changedetection.io-browser-extension) ) 
-
-## Installation
-
-### Docker
-
-With Docker composer, just clone this repository and..
+**Get monitoring now! super simple, one command!**
 
 ```bash
-$ docker compose up -d
-```
-
-Docker standalone
-```bash
-$ docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/datastore --name changedetection.io dgtlmoon/changedetection.io
-```
-
-`:latest` tag is our latest stable release, `:dev` tag is our bleeding edge `master` branch.
-
-Alternative docker repository over at ghcr - [ghcr.io/dgtlmoon/changedetection.io](https://ghcr.io/dgtlmoon/changedetection.io)
-
-### Windows
-
-See the install instructions at the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Microsoft-Windows
-
-### Python Pip
-
-Check out our pypi page https://pypi.org/project/changedetection.io/
-
-```bash
-$ pip3 install changedetection.io
-$ 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.
-
-_Now with per-site configurable support for using a fast built in HTTP fetcher or use a Chrome based fetcher for monitoring of JavaScript websites!_
-
-## Updating changedetection.io
-
-### Docker
-```
-docker pull dgtlmoon/changedetection.io
-docker kill $(docker ps -a -f name=changedetection.io -q)
-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
-
-```bash
-docker compose pull && docker compose up -d
-```
-
-See the wiki for more information https://github.com/dgtlmoon/changedetection.io/wiki
-
-
-## Filters
-
-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
-
-ChangeDetection.io supports a massive amount of notifications (including email, office365, custom APIs, etc) when a web-page has a change detected thanks to the <a href="https://github.com/caronc/apprise">apprise</a> library.
-Simply set one or more notification URL's in the _[edit]_ tab of that watch.
-
-Just some examples
-
-    discord://webhook_id/webhook_token
-    flock://app_token/g:channel_id
-    gitter://token/room
-    gchat://workspace/key/token
-    msteams://TokenA/TokenB/TokenC/
-    o365://TenantID:AccountEmail/ClientID/ClientSecret/TargetEmail
-    rocket://user:password@hostname/#Channel
-    mailto://user:pass@example.com?to=receivingAddress@example.com
-    json://someserver.com/custom-api
-    syslog://
- 
-<a href="https://github.com/caronc/apprise#popular-notification-services">And everything else in this list!</a>
-
-<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-notifications.png" style="max-width:100%;" alt="Self-hosted web page change monitoring notifications"  title="Self-hosted web page change monitoring notifications"  />
-
-Now you can also customise your notification content and use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2 templating</a> for their title and body!
-
-## JSON API Monitoring
-
-Detect changes and monitor data in JSON API's by using either JSONPath or jq to filter, parse, and restructure JSON as needed.
-
-![image](https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/json-filter-field-example.png)
-
-This will re-parse the JSON and apply formatting to the text, making it super easy to monitor and detect changes in JSON API results
-
-![image](https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/json-diff-example.png)
-
-### 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 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.
-
-See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/JSON-Selector-Filter-help for more information and examples
-
-### Parse JSON embedded in HTML!
-
-When you enable a `json:` or `jq:` filter, you can even automatically extract and parse embedded JSON inside a HTML page! Amazingly handy for sites that build content based on JSON, such as many e-commerce websites. 
-
-```
-<html>
-...
-<script type="application/ld+json">
-
-{
-   "@context":"http://schema.org/",
-   "@type":"Product",
-   "offers":{
-      "@type":"Offer",
-      "availability":"http://schema.org/InStock",
-      "price":"3949.99",
-      "priceCurrency":"USD",
-      "url":"https://www.newegg.com/p/3D5-000D-001T1"
-   },
-   "description":"Cobratype King Cobra Hero Desktop Gaming PC",
-   "name":"Cobratype King Cobra Hero Desktop Gaming PC",
-   "sku":"3D5-000D-001T1",
-   "itemCondition":"NewCondition"
-}
-</script>
 ```  
 
-`json:$..price` or `jq:..price` would give `3949.99`, or you can extract the whole structure (use a JSONpath test website to validate with)
+Now visit http://127.0.0.1:5000 , You should now be able to access the UI.
 
-The application also supports notifying you that it can follow this information automatically
+#### Updating to latest version
 
+Highly recommended :)
 
-## Proxy Configuration
+```bash
+docker pull dgtlmoon/changedetection.io
+docker kill $(docker ps -a|grep changedetection.io|awk '{print $1}')
+docker rm $(docker ps -a|grep changedetection.io|awk '{print $1}')
+docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/datastore --name changedetection.io dgtlmoon/changedetection.io
+```
+  
+### Screenshots
 
-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.
+Examining differences in content.
 
-## Raspberry Pi support?
+![Self-hosted web page change monitoring context difference screenshot](screenshot-diff.png?raw=true "Self-hosted web page change monitoring context difference screenshot")
 
-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)
+### Future plans
 
-## Import support
+- Greater configuration of check interval times, page request headers.
+- ~~General options for timeout, default headers~~
+- On change detection, callout to another API (handy for notices/issue trackers)
+- ~~Explore the differences that were detected~~ 
+- Add more options to explore versions of differences
+- Use a graphic/rendered page difference instead of text (see the experimental `selenium-screenshot-diff` branch)
 
-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)
-
-## Support us
-
-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.
-
-
-Consider taking out an officially supported [website change detection subscription](https://changedetection.io?src=github) , even if you don't use it, you still get the warm fuzzy feeling of helping out the project. (And who knows, you might just use it!)
-
-## Commercial Support
-
-I offer commercial support, this software is depended on by network security, aerospace , data-science and data-journalist professionals just to name a few, please reach out at dgtlmoon@gmail.com for any enquiries, I am more than glad to work with your organisation to further the possibilities of what can be done with changedetection.io
-
-
-[release-shield]: https://img.shields.io:/github/v/release/dgtlmoon/changedetection.io?style=for-the-badge
-[docker-pulls]: https://img.shields.io/docker/pulls/dgtlmoon/changedetection.io?style=for-the-badge
-[test-shield]: https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master
-
-[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
-
-## Commercial Licencing
-
-If you are reselling this software either in part or full as part of any commercial arrangement, you must abide by our COMMERCIAL_LICENCE.md found in our code repository, please contact dgtlmoon@gmail.com and contact@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
+ 
+Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/

backend/README-pytest.md

@@ -0,0 +1 @@
+Note: run `pytest` from this directory.

backend/__init__.py

@@ -0,0 +1,668 @@
+#!/usr/bin/python3
+
+
+# @todo logging
+# @todo extra options for url like , verify=False etc.
+# @todo enable https://urllib3.readthedocs.io/en/latest/user-guide.html#ssl as option?
+# @todo option for interval day/6 hour/etc
+# @todo on change detected, config for calling some API
+# @todo make tables responsive!
+# @todo fetch title into json
+# https://distill.io/features
+# proxy per check
+#  - flask_cors, itsdangerous,MarkupSafe
+
+import time
+import os
+import timeago
+
+import threading
+from threading import Event
+
+import queue
+
+from flask import Flask, render_template, request, send_file, send_from_directory, abort, redirect, url_for
+
+from feedgen.feed import FeedGenerator
+from flask import make_response
+import datetime
+import pytz
+
+datastore = None
+
+# Local
+running_update_threads = []
+ticker_thread = None
+
+messages = []
+extra_stylesheets = []
+
+update_q = queue.Queue()
+
+app = Flask(__name__, static_url_path="/var/www/change-detection/backen/static")
+
+# Stop browser caching of assets
+app.config['SEND_FILE_MAX_AGE_DEFAULT'] = 0
+
+app.config.exit = Event()
+
+app.config['NEW_VERSION_AVAILABLE'] = False
+
+# Disables caching of the templates
+app.config['TEMPLATES_AUTO_RELOAD'] = True
+
+
+# We use the whole watch object from the store/JSON so we can see if there's some related status in terms of a thread
+# running or something similar.
+@app.template_filter('format_last_checked_time')
+def _jinja2_filter_datetime(watch_obj, format="%Y-%m-%d %H:%M:%S"):
+    # Worker thread tells us which UUID it is currently processing.
+    for t in running_update_threads:
+        if t.current_uuid == watch_obj['uuid']:
+            return "Checking now.."
+
+    if watch_obj['last_checked'] == 0:
+        return 'Not yet'
+
+    return timeago.format(int(watch_obj['last_checked']), time.time())
+
+
+# @app.context_processor
+# def timeago():
+#    def _timeago(lower_time, now):
+#        return timeago.format(lower_time, now)
+#    return dict(timeago=_timeago)
+
+@app.template_filter('format_timestamp_timeago')
+def _jinja2_filter_datetimestamp(timestamp, format="%Y-%m-%d %H:%M:%S"):
+    return timeago.format(timestamp, time.time())
+    # return timeago.format(timestamp, time.time())
+    # return datetime.datetime.utcfromtimestamp(timestamp).strftime(format)
+
+
+def changedetection_app(config=None, datastore_o=None):
+    global datastore
+    datastore = datastore_o
+
+    app.config.update(dict(DEBUG=True))
+    app.config.update(config or {})
+
+    # Setup cors headers to allow all domains
+    # https://flask-cors.readthedocs.io/en/latest/
+    #    CORS(app)
+
+    # https://github.com/pallets/flask/blob/93dd1709d05a1cf0e886df6223377bdab3b077fb/examples/tutorial/flaskr/__init__.py#L39
+    # You can divide up the stuff like this
+
+    @app.route("/", methods=['GET'])
+    def index():
+        global messages
+
+        limit_tag = request.args.get('tag')
+        rss = request.args.get('rss')
+        mode = request.args.get('mode')
+
+        # Sort by last_changed and add the uuid which is usually the key..
+        sorted_watches = []
+        for uuid, watch in datastore.data['watching'].items():
+
+            if limit_tag != None:
+                # Support for comma separated list of tags.
+                for tag_in_watch in watch['tag'].split(','):
+                    tag_in_watch = tag_in_watch.strip()
+                    if tag_in_watch == limit_tag:
+                        watch['uuid'] = uuid
+                        sorted_watches.append(watch)
+
+            else:
+                watch['uuid'] = uuid
+                sorted_watches.append(watch)
+
+        sorted_watches.sort(key=lambda x: x['last_changed'], reverse=True)
+
+        existing_tags = datastore.get_all_tags()
+
+        if mode == 'stream':
+            import difflib
+
+            import pprint
+            streams = []
+
+            extra_stylesheets = ['/static/css/diff.css']
+            for watch in sorted_watches:
+                if not watch['viewed']:
+
+                    # get last two date keys
+                    dates = list(watch['history'].keys())
+                    # Convert to int, sort and back to str again
+                    dates = [int(i) for i in dates]
+                    dates.sort(reverse=True)
+                    dates = [str(i) for i in dates]
+                    print ("OK", watch['uuid'])
+
+                    if len(dates) < 2:
+                        print ("Skipping", watch['url'])
+                        continue
+                    else:
+                        try:
+                            path = datastore.data['watching'][watch['uuid']]['history'][str(dates[1])]
+                            with open(path,
+                                      encoding='utf-8') as file:
+                                txt1=[line.rstrip() for line in file.readlines()]
+
+                            path = datastore.data['watching'][watch['uuid']]['history'][str(dates[0])]
+                            with open(path,
+                                      encoding='utf-8') as file:
+                                txt2 = [line.rstrip() for line in file.readlines()]
+                        except FileNotFoundError:
+                            print ("Skipping", watch['url'])
+                            continue
+
+                        df = list(difflib.unified_diff(txt1, txt2,n=1))
+                        diff_entry=[]
+                        for line in df:
+                            if line[0] == '-' or line[0] == '+':
+                                diff_entry.append(line)
+
+
+                        # pprint(df)
+                        #s = pprint.pformat(df)
+                        streams.append(diff_entry)
+
+
+            print ("###########", len(streams))
+
+            output = render_template("watch-diff-stream.html",
+                                     streams=streams,
+                                     extra_stylesheets=extra_stylesheets
+                                     )
+            return output
+
+
+        if rss:
+            fg = FeedGenerator()
+            fg.title('changedetection.io')
+            fg.description('Feed description')
+            fg.link(href='https://changedetection.io')
+
+            for watch in sorted_watches:
+                if not watch['viewed']:
+                    fe = fg.add_entry()
+                    fe.title(watch['url'])
+                    fe.link(href=watch['url'])
+                    fe.description(watch['url'])
+                    fe.guid(watch['uuid'], permalink=False)
+                    dt = datetime.datetime.fromtimestamp(int(watch['newest_history_key']))
+                    dt = dt.replace(tzinfo=pytz.UTC)
+                    fe.pubDate(dt)
+
+            response = make_response(fg.rss_str())
+            response.headers.set('Content-Type', 'application/rss+xml')
+            return response
+
+        else:
+            #table = render_template('watch-table.html', watches=sorted_watches)
+            output = render_template("watch-table.html",
+                                     watches=sorted_watches,
+                                     messages=messages,
+                                     tags=existing_tags,
+                                     active_tag=limit_tag,
+                                     has_unviewed=datastore.data['has_unviewed'])
+
+            # Show messages but once.
+            messages = []
+
+        return output
+
+    @app.route("/scrub", methods=['GET', 'POST'])
+    def scrub_page():
+        from pathlib import Path
+
+        global messages
+
+        if request.method == 'POST':
+            confirmtext = request.form.get('confirmtext')
+
+            if confirmtext == 'scrub':
+
+                for txt_file_path in Path(app.config['datastore_path']).rglob('*.txt'):
+                    os.unlink(txt_file_path)
+
+                for uuid, watch in datastore.data['watching'].items():
+                    watch['last_checked'] = 0
+                    watch['last_changed'] = 0
+                    watch['previous_md5'] = None
+                    watch['history'] = {}
+
+                datastore.needs_write = True
+                messages.append({'class': 'ok', 'message': 'Cleaned all version history.'})
+            else:
+                messages.append({'class': 'error', 'message': 'Wrong confirm text.'})
+
+            return redirect(url_for('index'))
+
+        return render_template("scrub.html")
+
+    # If they edited an existing watch, we need to know to reset the current/previous md5 to include
+    # the excluded text.
+    def get_current_checksum_include_ignore_text(uuid):
+
+        import hashlib
+        from backend import fetch_site_status
+
+        # Get the most recent one
+        newest_history_key = datastore.get_val(uuid, 'newest_history_key')
+
+        # 0 means that theres only one, so that there should be no 'unviewed' history availabe
+        if newest_history_key == 0:
+            newest_history_key = list(datastore.data['watching'][uuid]['history'].keys())[0]
+
+        if newest_history_key:
+            with open(datastore.data['watching'][uuid]['history'][newest_history_key],
+                      encoding='utf-8') as file:
+                raw_content = file.read()
+
+                handler = fetch_site_status.perform_site_check(datastore=datastore)
+                stripped_content = handler.strip_ignore_text(raw_content,
+                                                             datastore.data['watching'][uuid]['ignore_text'])
+
+                checksum = hashlib.md5(stripped_content).hexdigest()
+                return checksum
+
+        return datastore.data['watching'][uuid]['previous_md5']
+
+    @app.route("/edit/<string:uuid>", methods=['GET', 'POST'])
+    def edit_page(uuid):
+        global messages
+        import validators
+
+        # More for testing, possible to return the first/only
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+
+        if request.method == 'POST':
+
+            url = request.form.get('url').strip()
+            tag = request.form.get('tag').strip()
+
+            # Extra headers
+            form_headers = request.form.get('headers').strip().split("\n")
+            extra_headers = {}
+            if form_headers:
+                for header in form_headers:
+                    if len(header):
+                        parts = header.split(':', 1)
+                        if len(parts) == 2:
+                            extra_headers.update({parts[0].strip(): parts[1].strip()})
+
+            update_obj = {'url': url,
+                          'tag': tag,
+                          'headers': extra_headers
+                          }
+
+            # Ignore text
+            form_ignore_text = request.form.get('ignore-text').strip()
+            ignore_text = []
+            if len(form_ignore_text):
+                for text in form_ignore_text.split("\n"):
+                    text = text.strip()
+                    if len(text):
+                        ignore_text.append(text)
+
+                datastore.data['watching'][uuid]['ignore_text'] = ignore_text
+
+                # Reset the previous_md5 so we process a new snapshot including stripping ignore text.
+                if len(datastore.data['watching'][uuid]['history']):
+                    update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
+
+            validators.url(url)  # @todo switch to prop/attr/observer
+            datastore.data['watching'][uuid].update(update_obj)
+            datastore.needs_write = True
+
+            messages.append({'class': 'ok', 'message': 'Updated watch.'})
+
+            return redirect(url_for('index'))
+
+        else:
+            output = render_template("edit.html", uuid=uuid, watch=datastore.data['watching'][uuid], messages=messages)
+
+        return output
+
+    @app.route("/settings", methods=['GET', "POST"])
+    def settings_page():
+        global messages
+        if request.method == 'POST':
+            try:
+                minutes = int(request.values.get('minutes').strip())
+            except ValueError:
+                messages.append({'class': 'error', 'message': "Invalid value given, use an integer."})
+
+            else:
+                if minutes >= 5:
+                    datastore.data['settings']['requests']['minutes_between_check'] = minutes
+                    datastore.needs_write = True
+
+                    messages.append({'class': 'ok', 'message': "Updated"})
+                else:
+                    messages.append(
+                        {'class': 'error', 'message': "Must be atleast 5 minutes."})
+
+        output = render_template("settings.html", messages=messages,
+                                 minutes=datastore.data['settings']['requests']['minutes_between_check'])
+        messages = []
+
+        return output
+
+    @app.route("/import", methods=['GET', "POST"])
+    def import_page():
+        import validators
+        global messages
+        remaining_urls = []
+
+        good = 0
+
+        if request.method == 'POST':
+            urls = request.values.get('urls').split("\n")
+            for url in urls:
+                url = url.strip()
+                if len(url) and validators.url(url):
+                    new_uuid = datastore.add_watch(url=url.strip(), tag="")
+                    # Straight into the queue.
+                    update_q.put(new_uuid)
+                    good += 1
+                else:
+                    if len(url):
+                        remaining_urls.append(url)
+
+            messages.append({'class': 'ok', 'message': "{} Imported, {} Skipped.".format(good, len(remaining_urls))})
+
+            if len(remaining_urls) == 0:
+                # Looking good, redirect to index.
+                return redirect(url_for('index'))
+
+        # Could be some remaining, or we could be on GET
+        output = render_template("import.html",
+                                 messages=messages,
+                                 remaining="\n".join(remaining_urls)
+                                 )
+        messages = []
+
+        return output
+
+    # Clear all statuses, so we do not see the 'unviewed' class
+    @app.route("/api/mark-all-viewed", methods=['GET'])
+    def mark_all_viewed():
+
+        # Save the current newest history as the most recently viewed
+        for watch_uuid, watch in datastore.data['watching'].items():
+            datastore.set_last_viewed(watch_uuid, watch['newest_history_key'])
+
+        messages.append({'class': 'ok', 'message': "Cleared all statuses."})
+        return redirect(url_for('index'))
+
+    @app.route("/diff/<string:uuid>", methods=['GET'])
+    def diff_history_page(uuid):
+        global messages
+
+        # More for testing, possible to return the first/only
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+
+        extra_stylesheets = ['/static/css/diff.css']
+        try:
+            watch = datastore.data['watching'][uuid]
+        except KeyError:
+            messages.append({'class': 'error', 'message': "No history found for the specified link, bad link?"})
+            return redirect(url_for('index'))
+
+        dates = list(watch['history'].keys())
+        # Convert to int, sort and back to str again
+        dates = [int(i) for i in dates]
+        dates.sort(reverse=True)
+        dates = [str(i) for i in dates]
+
+        if len(dates) < 2:
+            messages.append(
+                {'class': 'error', 'message': "Not enough saved change detection snapshots to produce a report."})
+            return redirect(url_for('index'))
+
+        # Save the current newest history as the most recently viewed
+        datastore.set_last_viewed(uuid, dates[0])
+
+        newest_file = watch['history'][dates[0]]
+        with open(newest_file, 'r') as f:
+            newest_version_file_contents = f.read()
+
+        previous_version = request.args.get('previous_version')
+
+        try:
+            previous_file = watch['history'][previous_version]
+        except KeyError:
+            # Not present, use a default value, the second one in the sorted list.
+            previous_file = watch['history'][dates[1]]
+
+        with open(previous_file, 'r') as f:
+            previous_version_file_contents = f.read()
+
+        output = render_template("diff.html", watch_a=watch,
+                                 messages=messages,
+                                 newest=newest_version_file_contents,
+                                 previous=previous_version_file_contents,
+                                 extra_stylesheets=extra_stylesheets,
+                                 versions=dates[1:],
+                                 newest_version_timestamp=dates[0],
+                                 current_previous_version=str(previous_version),
+                                 current_diff_url=watch['url'])
+
+        return output
+
+    @app.route("/favicon.ico", methods=['GET'])
+    def favicon():
+        return send_from_directory("/app/static/images", filename="favicon.ico")
+
+    # We're good but backups are even better!
+    @app.route("/backup", methods=['GET'])
+    def get_backup():
+        import zipfile
+        from pathlib import Path
+
+        # create a ZipFile object
+        backupname = "changedetection-backup-{}.zip".format(int(time.time()))
+
+        # We only care about UUIDS from the current index file
+        uuids = list(datastore.data['watching'].keys())
+
+        with zipfile.ZipFile(os.path.join(app.config['datastore_path'], backupname), 'w',
+                             compression=zipfile.ZIP_DEFLATED,
+                             compresslevel=6) as zipObj:
+
+            # Be sure we're written fresh
+            datastore.sync_to_json()
+
+            # Add the index
+            zipObj.write(os.path.join(app.config['datastore_path'], "url-watches.json"))
+            # Add any snapshot data we find
+            for txt_file_path in Path(app.config['datastore_path']).rglob('*.txt'):
+                parent_p = txt_file_path.parent
+                if parent_p.name in uuids:
+                    zipObj.write(txt_file_path)
+
+        return send_file(os.path.join(app.config['datastore_path'], backupname),
+                         as_attachment=True,
+                         mimetype="application/zip",
+                         attachment_filename=backupname)
+
+    @app.route("/static/<string:group>/<string:filename>", methods=['GET'])
+    def static_content(group, filename):
+        # These files should be in our subdirectory
+        full_path = os.path.realpath(__file__)
+        p = os.path.dirname(full_path)
+
+        try:
+            return send_from_directory("{}/static/{}".format(p, group), filename=filename)
+        except FileNotFoundError:
+            abort(404)
+
+    @app.route("/api/add", methods=['POST'])
+    def api_watch_add():
+        global messages
+
+        # @todo add_watch should throw a custom Exception for validation etc
+        new_uuid = datastore.add_watch(url=request.form.get('url').strip(), tag=request.form.get('tag').strip())
+        # Straight into the queue.
+        update_q.put(new_uuid)
+
+        messages.append({'class': 'ok', 'message': 'Watch added.'})
+        return redirect(url_for('index'))
+
+    @app.route("/api/delete", methods=['GET'])
+    def api_delete():
+        global messages
+        uuid = request.args.get('uuid')
+        datastore.delete(uuid)
+        messages.append({'class': 'ok', 'message': 'Deleted.'})
+
+        return redirect(url_for('index'))
+
+    @app.route("/api/checknow", methods=['GET'])
+    def api_watch_checknow():
+
+        global messages
+
+        tag = request.args.get('tag')
+        uuid = request.args.get('uuid')
+        i = 0
+
+        running_uuids = []
+        for t in running_update_threads:
+            running_uuids.append(t.current_uuid)
+
+        # @todo check thread is running and skip
+
+        if uuid:
+            if uuid not in running_uuids:
+                update_q.put(uuid)
+            i = 1
+
+        elif tag != None:
+            # Items that have this current tag
+            for watch_uuid, watch in datastore.data['watching'].items():
+                if (tag != None and tag in watch['tag']):
+                    i += 1
+                    if watch_uuid not in running_uuids:
+                        update_q.put(watch_uuid)
+        else:
+            # No tag, no uuid, add everything.
+            for watch_uuid, watch in datastore.data['watching'].items():
+                i += 1
+                if watch_uuid not in running_uuids:
+                    update_q.put(watch_uuid)
+
+        messages.append({'class': 'ok', 'message': "{} watches are rechecking.".format(i)})
+        return redirect(url_for('index', tag=tag))
+
+    # @todo handle ctrl break
+    ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks).start()
+
+    # Check for new release version
+    threading.Thread(target=check_for_new_version).start()
+    return app
+
+
+# Check for new version and anonymous stats
+def check_for_new_version():
+    import requests
+
+    import urllib3
+    urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+    while not app.config.exit.is_set():
+        try:
+            r = requests.post("https://changedetection.io/check-ver.php",
+                              data={'version': datastore.data['version_tag'],
+                                    'app_guid': datastore.data['app_guid']},
+
+                              verify=False)
+        except:
+            pass
+
+        try:
+            if "new_version" in r.text:
+                app.config['NEW_VERSION_AVAILABLE'] = True
+        except:
+            pass
+
+        # Check daily
+        app.config.exit.wait(86400)
+
+
+# Requests for checking on the site use a pool of thread Workers managed by a Queue.
+class Worker(threading.Thread):
+    current_uuid = None
+
+    def __init__(self, q, *args, **kwargs):
+        self.q = q
+        super().__init__(*args, **kwargs)
+
+    def run(self):
+        from backend import fetch_site_status
+
+        update_handler = fetch_site_status.perform_site_check(datastore=datastore)
+
+        while not app.config.exit.is_set():
+
+            try:
+                uuid = self.q.get(block=False)
+            except queue.Empty:
+                pass
+
+            else:
+                self.current_uuid = uuid
+
+                if uuid in list(datastore.data['watching'].keys()):
+
+                    try:
+                        changed_detected, result, contents = update_handler.run(uuid)
+
+                    except PermissionError as s:
+                        app.logger.error("File permission error updating", uuid, str(s))
+                    else:
+                        if result:
+
+                            datastore.update_watch(uuid=uuid, update_obj=result)
+                            if changed_detected:
+                                # A change was detected
+                                datastore.save_history_text(uuid=uuid, contents=contents, result_obj=result)
+
+                self.current_uuid = None  # Done
+                self.q.task_done()
+
+            app.config.exit.wait(1)
+
+
+# Thread runner to check every minute, look for new watches to feed into the Queue.
+def ticker_thread_check_time_launch_checks():
+    # Spin up Workers.
+    for _ in range(datastore.data['settings']['requests']['workers']):
+        new_worker = Worker(update_q)
+        running_update_threads.append(new_worker)
+        new_worker.start()
+
+    while not app.config.exit.is_set():
+        running_uuids = []
+        for t in running_update_threads:
+            running_uuids.append(t.current_uuid)
+
+        # Look at the dataset, find a stale watch to process
+
+        # Every minute check for new UUIDs to follow up on, should be inside the loop incase it changes.
+        minutes = datastore.data['settings']['requests']['minutes_between_check']
+
+        threshold = time.time() - (minutes * 60)
+        for uuid, watch in datastore.data['watching'].items():
+            if watch['last_checked'] <= threshold:
+                if not uuid in running_uuids and uuid not in update_q.queue:
+                    update_q.put(uuid)
+
+        # Should be low so we can break this out in testing
+        app.config.exit.wait(1)

backend/dev-docker/Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.8-slim
+
+# https://stackoverflow.com/questions/58701233/docker-logs-erroneously-appears-empty-until-container-stops
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+RUN [ ! -d "/datastore" ] && mkdir /datastore
+
+COPY sleep.py /
+CMD [ "python", "/sleep.py" ]
+
+
+

backend/dev-docker/sleep.py

@@ -0,0 +1,7 @@
+import time
+
+print ("Sleep loop, you should run your script from the console")
+
+while True: 
+    # Wait for 5 seconds
+    time.sleep(2)

backend/fetch_site_status.py

@@ -0,0 +1,118 @@
+import time
+import requests
+import hashlib
+from inscriptis import get_text
+import urllib3
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+# Some common stuff here that can be moved to a base class
+class perform_site_check():
+
+    def __init__(self, *args, datastore, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.datastore = datastore
+
+    def strip_ignore_text(self, content, list_ignore_text):
+        ignore = []
+        for k in list_ignore_text:
+            ignore.append(k.encode('utf8'))
+
+        output = []
+        for line in content.splitlines():
+            line = line.encode('utf8')
+
+            # Always ignore blank lines in this mode. (when this function gets called)
+            if len(line.strip()):
+                if not any(skip_text in line for skip_text in ignore):
+                    output.append(line)
+
+        return "\n".encode('utf8').join(output)
+
+
+
+    def run(self, uuid):
+        timestamp = int(time.time())  # used for storage etc too
+        stripped_text_from_html = False
+        changed_detected = False
+
+        update_obj = {'previous_md5': self.datastore.data['watching'][uuid]['previous_md5'],
+                      'history': {},
+                      "last_checked": timestamp
+                      }
+
+        extra_headers = self.datastore.get_val(uuid, 'headers')
+
+        # Tweak the base config with the per-watch ones
+        request_headers = self.datastore.data['settings']['headers']
+        request_headers.update(extra_headers)
+
+        # https://github.com/psf/requests/issues/4525
+        # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
+        # do this by accident.
+        if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
+            request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
+
+        try:
+            timeout = self.datastore.data['settings']['requests']['timeout']
+        except KeyError:
+            # @todo yeah this should go back to the default value in store.py, but this whole object should abstract off it
+            timeout = 15
+
+        try:
+            url = self.datastore.get_val(uuid, 'url')
+
+            r = requests.get(url,
+                             headers=request_headers,
+                             timeout=timeout,
+                             verify=False)
+
+            stripped_text_from_html = get_text(r.text)
+
+        # Usually from networkIO/requests level
+        except (requests.exceptions.ConnectionError, requests.exceptions.ReadTimeout) as e:
+            update_obj["last_error"] = str(e)
+
+            print(str(e))
+
+        except requests.exceptions.MissingSchema:
+            print("Skipping {} due to missing schema/bad url".format(uuid))
+
+        # Usually from html2text level
+        except UnicodeDecodeError as e:
+
+            update_obj["last_error"] = str(e)
+            print(str(e))
+            # figure out how to deal with this cleaner..
+            # 'utf-8' codec can't decode byte 0xe9 in position 480: invalid continuation byte
+
+        else:
+            # 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"] = r.status_code
+            update_obj["last_error"] = False
+
+            if not len(r.text):
+                update_obj["last_error"] = "Empty reply"
+
+            # If there's text to skip
+            # @todo we could abstract out the get_text() to handle this cleaner
+            if len(self.datastore.data['watching'][uuid]['ignore_text']):
+                content = self.strip_ignore_text(stripped_text_from_html,
+                                                 self.datastore.data['watching'][uuid]['ignore_text'])
+            else:
+                content = stripped_text_from_html.encode('utf8')
+
+            fetched_md5 = hashlib.md5(content).hexdigest()
+
+            # could be None or False depending on JSON type
+            if self.datastore.data['watching'][uuid]['previous_md5'] != fetched_md5:
+                changed_detected = True
+
+                # Don't confuse people by updating as last-changed, when it actually just changed from None..
+                if self.datastore.get_val(uuid, 'previous_md5'):
+                    update_obj["last_changed"] = timestamp
+
+                update_obj["previous_md5"] = fetched_md5
+
+        return changed_detected, update_obj, stripped_text_from_html

backend/pytest.ini

@@ -1,7 +1,7 @@
 [pytest]
 addopts = --no-start-live-server --live-server-port=5005
 #testpaths = tests pytest_invenio
-#live_server_scope = function
+#live_server_scope = session
 
 filterwarnings =
     ignore::DeprecationWarning:urllib3.*:

backend/static/css/diff.css

@@ -0,0 +1,66 @@
+table {
+	table-layout: fixed;
+	width: 100%;
+}
+td {
+	width: 33%;
+	padding: 3px 4px;
+	border: 1px solid transparent;
+	vertical-align: top;
+	font: 1em monospace;
+	text-align: left;
+	white-space: pre-wrap;
+}
+h1 {
+	display: inline;
+	font-size: 100%;
+}
+del {
+	text-decoration: none;
+	color: #b30000;
+	background: #fadad7;
+}
+
+ins {
+	background: #eaf2c2;
+	color: #406619;
+	text-decoration: none;
+}
+
+#result {
+	white-space: pre-wrap;
+}
+
+#settings {
+    background: rgba(0,0,0,.05);
+        padding: 1em;
+    border-radius: 10px;
+    margin-bottom: 1em;
+    color: #fff;
+    font-size: 80%;
+}
+#settings label {
+	margin-left: 1em;
+	display: inline-block;
+	font-weight: normal;
+}
+
+.source {
+	position: absolute;
+	right: 1%;
+	top: .2em;
+}
+
+@-moz-document url-prefix() {
+	body {
+		height: 99%; /* Hide scroll bar in Firefox */
+	}
+}
+
+#diff-ui {
+    background: #fff;
+    padding: 2em;
+    margin: 1em;
+    border-radius: 5px;
+    font-size: 9px;
+}

backend/static/css/styles.css

@@ -0,0 +1,273 @@
+/*
+ * -- BASE STYLES --
+ * Most of these are inherited from Base, but I want to change a few.
+ */
+body {
+  color: #333;
+  background: #262626;
+}
+
+.pure-table-even {
+  background: #fff;
+}
+/* Some styles from https://css-tricks.com/ */
+
+a {
+  text-decoration: none;
+  color: #1b98f8;
+}
+a.github-link {
+  color: #fff;
+}
+
+
+.pure-menu-horizontal {
+  background: #fff;
+  padding: 5px;
+  display: flex;
+  justify-content: space-between;
+  border-bottom: 2px solid #ed5900;
+
+  align-items: center;
+}
+
+section.content {
+
+  padding-top: 5em;
+  padding-bottom: 5em;
+  flex-direction: column;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+}
+
+.pure-table.watch-table td {
+  font-size: 80%;
+}
+
+/* table related */
+.watch-table {
+  width: 100%;
+
+}
+
+.watch-table tr.unviewed {
+    font-weight: bold;
+}
+
+.watch-tag-list {
+  color: #e70069;
+  white-space: nowrap;
+}
+
+.box {
+  max-width: 80%;
+  flex-direction: column;
+  display: flex;
+  justify-content: center;
+}
+
+.watch-table .error {
+  color: #a00;
+}
+
+.watch-table td {
+  white-space: nowrap;
+}
+
+.watch-table td.title-col {
+  word-break: break-all;
+  white-space: normal;
+}
+.watch-table th {
+  white-space: nowrap;
+}
+
+.watch-table .title-col a[target="_blank"]::after, .current-diff-url::after {
+  content: url(data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAQElEQVR42qXKwQkAIAxDUUdxtO6/RBQkQZvSi8I/pL4BoGw/XPkh4XigPmsUgh0626AjRsgxHTkUThsG2T/sIlzdTsp52kSS1wAAAABJRU5ErkJggg==);
+  margin: 0 3px 0 5px;
+}
+
+#post-list-buttons {
+  text-align: right;
+  padding: 0px;
+  margin: 0px;
+}
+#post-list-buttons li {
+  display: inline-block;
+}
+
+#post-list-buttons a {
+   border-top-left-radius: initial;
+   border-top-right-radius: initial;
+   border-bottom-left-radius: 5px;
+   border-bottom-right-radius: 5px;
+}
+
+
+body:after {
+  content: "";
+  background: linear-gradient(130deg, #ff7a18, #af002d 41.07%, #319197 76.05%)
+}
+
+body:after, body:before {
+  display: block;
+  height: 600px;
+  position: absolute;
+  top: 0;
+  left: 0;
+  width: 100%;
+  z-index: -1;
+}
+body::after {
+  opacity: 0.91;
+}
+body::before {
+  content: "";
+  background-image: url(/static/images/gradient-border.png);
+}
+body:before {
+  background-size: cover
+}
+
+body:after, body:before {
+  -webkit-clip-path: polygon(100% 0, 0 0, 0 77.5%, 1% 77.4%, 2% 77.1%, 3% 76.6%, 4% 75.9%, 5% 75.05%, 6% 74.05%, 7% 72.95%, 8% 71.75%, 9% 70.55%, 10% 69.3%, 11% 68.05%, 12% 66.9%, 13% 65.8%, 14% 64.8%, 15% 64%, 16% 63.35%, 17% 62.85%, 18% 62.6%, 19% 62.5%, 20% 62.65%, 21% 63%, 22% 63.5%, 23% 64.2%, 24% 65.1%, 25% 66.1%, 26% 67.2%, 27% 68.4%, 28% 69.65%, 29% 70.9%, 30% 72.15%, 31% 73.3%, 32% 74.35%, 33% 75.3%, 34% 76.1%, 35% 76.75%, 36% 77.2%, 37% 77.45%, 38% 77.5%, 39% 77.3%, 40% 76.95%, 41% 76.4%, 42% 75.65%, 43% 74.75%, 44% 73.75%, 45% 72.6%, 46% 71.4%, 47% 70.15%, 48% 68.9%, 49% 67.7%, 50% 66.55%, 51% 65.5%, 52% 64.55%, 53% 63.75%, 54% 63.15%, 55% 62.75%, 56% 62.55%, 57% 62.5%, 58% 62.7%, 59% 63.1%, 60% 63.7%, 61% 64.45%, 62% 65.4%, 63% 66.45%, 64% 67.6%, 65% 68.8%, 66% 70.05%, 67% 71.3%, 68% 72.5%, 69% 73.6%, 70% 74.65%, 71% 75.55%, 72% 76.35%, 73% 76.9%, 74% 77.3%, 75% 77.5%, 76% 77.45%, 77% 77.25%, 78% 76.8%, 79% 76.2%, 80% 75.4%, 81% 74.45%, 82% 73.4%, 83% 72.25%, 84% 71.05%, 85% 69.8%, 86% 68.55%, 87% 67.35%, 88% 66.2%, 89% 65.2%, 90% 64.3%, 91% 63.55%, 92% 63%, 93% 62.65%, 94% 62.5%, 95% 62.55%, 96% 62.8%, 97% 63.3%, 98% 63.9%, 99% 64.75%, 100% 65.7%);
+  clip-path: polygon(100% 0, 0 0, 0 77.5%, 1% 77.4%, 2% 77.1%, 3% 76.6%, 4% 75.9%, 5% 75.05%, 6% 74.05%, 7% 72.95%, 8% 71.75%, 9% 70.55%, 10% 69.3%, 11% 68.05%, 12% 66.9%, 13% 65.8%, 14% 64.8%, 15% 64%, 16% 63.35%, 17% 62.85%, 18% 62.6%, 19% 62.5%, 20% 62.65%, 21% 63%, 22% 63.5%, 23% 64.2%, 24% 65.1%, 25% 66.1%, 26% 67.2%, 27% 68.4%, 28% 69.65%, 29% 70.9%, 30% 72.15%, 31% 73.3%, 32% 74.35%, 33% 75.3%, 34% 76.1%, 35% 76.75%, 36% 77.2%, 37% 77.45%, 38% 77.5%, 39% 77.3%, 40% 76.95%, 41% 76.4%, 42% 75.65%, 43% 74.75%, 44% 73.75%, 45% 72.6%, 46% 71.4%, 47% 70.15%, 48% 68.9%, 49% 67.7%, 50% 66.55%, 51% 65.5%, 52% 64.55%, 53% 63.75%, 54% 63.15%, 55% 62.75%, 56% 62.55%, 57% 62.5%, 58% 62.7%, 59% 63.1%, 60% 63.7%, 61% 64.45%, 62% 65.4%, 63% 66.45%, 64% 67.6%, 65% 68.8%, 66% 70.05%, 67% 71.3%, 68% 72.5%, 69% 73.6%, 70% 74.65%, 71% 75.55%, 72% 76.35%, 73% 76.9%, 74% 77.3%, 75% 77.5%, 76% 77.45%, 77% 77.25%, 78% 76.8%, 79% 76.2%, 80% 75.4%, 81% 74.45%, 82% 73.4%, 83% 72.25%, 84% 71.05%, 85% 69.8%, 86% 68.55%, 87% 67.35%, 88% 66.2%, 89% 65.2%, 90% 64.3%, 91% 63.55%, 92% 63%, 93% 62.65%, 94% 62.5%, 95% 62.55%, 96% 62.8%, 97% 63.3%, 98% 63.9%, 99% 64.75%, 100% 65.7%)
+}
+
+
+.button-small {
+  font-size: 85%;
+}
+
+
+.fetch-error {
+  padding-top: 1em;
+  font-size: 60%;
+  max-width: 400px;
+  display: block;
+}
+
+.edit-form {
+   background: #fff;
+   padding: 2em;
+   margin: 1em;
+   border-radius: 5px;
+}
+.button-secondary {
+    color: white;
+    border-radius: 4px;
+    text-shadow: 0 1px 1px rgba(0, 0, 0, 0.2);
+}
+
+.button-success {
+    background: rgb(28, 184, 65);
+    /* this is a green */
+}
+
+.button-tag {
+    background: rgb(99, 99, 99);
+    color: #fff;
+    font-size: 65%;
+    border-bottom-left-radius: initial;
+    border-bottom-right-radius: initial;
+}
+.button-tag.active {
+    background: #9c9c9c;
+    font-weight: bold;
+}
+.button-error {
+    background: rgb(202, 60, 60);
+    /* this is a maroon */
+}
+
+.button-warning {
+    background: rgb(223, 117, 20);
+    /* this is an orange */
+}
+
+.button-secondary {
+    background: rgb(66, 184, 221);
+    /* this is a light blue */
+}
+
+
+.button-cancel {
+    background: rgb(200, 200, 200);
+    /* this is a green */
+}
+
+.messages {
+    padding: 1em;
+    background: rgba(255,255,255,.2);
+    border-radius: 10px;
+    color: #fff;
+    font-weight: bold;
+}
+
+.pure-form label  {
+  font-weight: bold;
+}
+
+#new-watch-form {
+    background: rgba(0,0,0,.05);
+    padding: 1em;
+    border-radius: 10px;
+    margin-bottom: 1em;
+}
+#new-watch-form legend {
+    color: #fff;
+}
+
+#diff-col {
+    padding-left:40px;
+}
+#diff-jump {
+    position: fixed;
+    left: 0px;
+    top: 80px;
+    background: #fff;
+    padding: 10px;
+    border-top-right-radius: 5px;
+    border-bottom-right-radius: 5px;
+    box-shadow: 5px 0 5px -2px #888;
+}
+
+#diff-jump a {
+    color: #1b98f8;
+    cursor: grabbing;
+    -moz-user-select: none;
+    -webkit-user-select: none;
+    -ms-user-select:none;
+    user-select:none;
+    -o-user-select:none;
+}
+
+footer {
+    padding: 10px;
+    background: #fff;
+    color: #444;
+    text-align: center;
+}
+
+#feed-icon {
+    vertical-align: middle;
+}
+
+#version {
+    position: absolute;
+    top: 80px;
+    right: 0px;
+    font-size: 8px;
+    background: #fff;
+    padding: 10px;
+}
+
+#new-version-text a{
+    color: #e07171;
+}
+
+#diff-stream {
+    font-size: 10px;
+    white-space: pre-wrap;
+}

backend/store.py

@@ -0,0 +1,269 @@
+import json
+import uuid as uuid_builder
+import os.path
+from os import path
+from threading import Lock
+
+from copy import deepcopy
+
+import logging
+import time
+import threading
+
+
+# Is there an existing library to ensure some data store (JSON etc) is in sync with CRUD methods?
+# Open a github issue if you know something :)
+# https://stackoverflow.com/questions/6190468/how-to-trigger-function-on-value-change
+class ChangeDetectionStore:
+    lock = Lock()
+
+    def __init__(self, datastore_path="/datastore", include_default_watches=True):
+        self.needs_write = False
+        self.datastore_path = datastore_path
+        self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
+        self.stop_thread = False
+
+        self.__data = {
+            'note': "Hello! If you change this file manually, please be sure to restart your changedetection.io instance!",
+            'watching': {},
+            'settings': {
+                'headers': {
+                    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36',
+                    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
+                    'Accept-Encoding': 'gzip, deflate',  # No support for brolti in python requests yet.
+                    'Accept-Language': 'en-GB,en-US;q=0.9,en;'
+                },
+                'requests': {
+                    'timeout': 15,  # Default 15 seconds
+                    'minutes_between_check': 3 * 60,  # Default 3 hours
+                    'workers': 10  # Number of threads, lower is better for slow connections
+                }
+            }
+        }
+
+        # Base definition for all watchers
+        self.generic_definition = {
+            'url': None,
+            'tag': None,
+            'last_checked': 0,
+            'last_changed': 0,
+            'last_viewed': 0,  # history key value of the last viewed via the [diff] link
+            'newest_history_key': "",
+            'title': None,
+            'previous_md5': "",
+            'uuid': str(uuid_builder.uuid4()),
+            'headers': {},  # Extra headers to send
+            'history': {},  # Dict of timestamp and output stripped filename
+            'ignore_text': [] # List of text to ignore when calculating the comparison checksum
+        }
+
+        if path.isfile('/source.txt'):
+            with open('/source.txt') as f:
+                # Should be set in Dockerfile to look for /source.txt , this will give us the git commit #
+                # So when someone gives us a backup file to examine, we know exactly what code they were running.
+                self.__data['build_sha'] = f.read()
+
+        try:
+            # @todo retest with ", encoding='utf-8'"
+            with open(self.json_store_path) as json_file:
+                from_disk = json.load(json_file)
+
+                # @todo isnt there a way todo this dict.update recursively?
+                # Problem here is if the one on the disk is missing a sub-struct, it wont be present anymore.
+                if 'watching' in from_disk:
+                    self.__data['watching'].update(from_disk['watching'])
+
+                if 'app_guid' in from_disk:
+                    self.__data['app_guid'] = from_disk['app_guid']
+
+                if 'settings' in from_disk:
+                    if 'headers' in from_disk['settings']:
+                        self.__data['settings']['headers'].update(from_disk['settings']['headers'])
+
+                    if 'requests' in from_disk['settings']:
+                        self.__data['settings']['requests'].update(from_disk['settings']['requests'])
+
+                # Reinitialise each `watching` with our generic_definition in the case that we add a new var in the future.
+                # @todo pretty sure theres a python we todo this with an abstracted(?) object!
+                for uuid, watch in self.__data['watching'].items():
+                    _blank = deepcopy(self.generic_definition)
+                    _blank.update(watch)
+                    self.__data['watching'].update({uuid: _blank})
+                    self.__data['watching'][uuid]['newest_history_key'] = self.get_newest_history_key(uuid)
+                    print("Watching:", uuid, self.__data['watching'][uuid]['url'])
+
+        # First time ran, doesnt exist.
+        except (FileNotFoundError, json.decoder.JSONDecodeError):
+            if include_default_watches:
+                print("Creating JSON store at", self.datastore_path)
+
+                self.add_watch(url='http://www.quotationspage.com/random.php', tag='test')
+                self.add_watch(url='https://news.ycombinator.com/', tag='Tech news')
+                self.add_watch(url='https://www.gov.uk/coronavirus', tag='Covid')
+                self.add_watch(url='https://changedetection.io', tag='Tech news')
+
+
+        self.__data['version_tag'] = "0.27"
+
+        if not 'app_guid' in self.__data:
+            self.__data['app_guid'] = str(uuid_builder.uuid4())
+
+        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()
+
+    # Returns the newest key, but if theres only 1 record, then it's counted as not being new, so return 0.
+    def get_newest_history_key(self, uuid):
+        if len(self.__data['watching'][uuid]['history']) == 1:
+            return 0
+
+        dates = list(self.__data['watching'][uuid]['history'].keys())
+        # Convert to int, sort and back to str again
+        dates = [int(i) for i in dates]
+        dates.sort(reverse=True)
+        if len(dates):
+            # always keyed as str
+            return str(dates[0])
+
+        return 0
+
+    def set_last_viewed(self, uuid, timestamp):
+        self.data['watching'][uuid].update({'last_viewed': int(timestamp)})
+        self.needs_write = True
+
+    def update_watch(self, uuid, update_obj):
+
+        with self.lock:
+
+            # In python 3.9 we have the |= dict operator, but that still will lose data on nested structures...
+            for dict_key, d in self.generic_definition.items():
+                if isinstance(d, dict):
+                    if update_obj is not None and dict_key in update_obj:
+                        self.__data['watching'][uuid][dict_key].update(update_obj[dict_key])
+                        del (update_obj[dict_key])
+
+            self.__data['watching'][uuid].update(update_obj)
+            self.__data['watching'][uuid]['newest_history_key'] = self.get_newest_history_key(uuid)
+
+        self.needs_write = True
+
+    @property
+    def data(self):
+
+        has_unviewed = False
+
+        for uuid, v in self.__data['watching'].items():
+            self.__data['watching'][uuid]['newest_history_key'] = self.get_newest_history_key(uuid)
+            if int(v['newest_history_key']) <= int(v['last_viewed']):
+                self.__data['watching'][uuid]['viewed'] = True
+
+            else:
+                self.__data['watching'][uuid]['viewed'] = False
+                has_unviewed = True
+
+        self.__data['has_unviewed'] = has_unviewed
+
+        return self.__data
+
+    def get_all_tags(self):
+        tags = []
+        for uuid, watch in self.data['watching'].items():
+
+            # Support for comma separated list of tags.
+            for tag in watch['tag'].split(','):
+                tag = tag.strip()
+                if tag not in tags:
+                    tags.append(tag)
+
+        tags.sort()
+        return tags
+
+    def delete(self, uuid):
+        with self.lock:
+            if uuid == 'all':
+                self.__data['watching'] = {}
+            else:
+                del (self.__data['watching'][uuid])
+
+            self.needs_write = True
+
+    def url_exists(self, url):
+
+        # Probably their should be dict...
+        for watch in self.data['watching']:
+            if watch['url'] == url:
+                return True
+
+        return False
+
+    def get_val(self, uuid, val):
+        # Probably their should be dict...
+        return self.data['watching'][uuid].get(val)
+
+    def add_watch(self, url, tag):
+        with self.lock:
+            # @todo use a common generic version of this
+            new_uuid = str(uuid_builder.uuid4())
+            _blank = deepcopy(self.generic_definition)
+            _blank.update({
+                'url': url,
+                'tag': tag,
+                'uuid': new_uuid
+            })
+
+            self.data['watching'][new_uuid] = _blank
+
+        # Get the directory ready
+        output_path = "{}/{}".format(self.datastore_path, new_uuid)
+        try:
+            os.mkdir(output_path)
+        except FileExistsError:
+            print(output_path, "already exists.")
+
+        self.sync_to_json()
+        return new_uuid
+
+    # Save some text file to the appropriate path and bump the history
+    # result_obj from fetch_site_status.run()
+    def save_history_text(self, uuid, result_obj, contents):
+
+        output_path = "{}/{}".format(self.datastore_path, uuid)
+        try:
+            os.mkdir(output_path)
+        except FileExistsError:
+            pass
+
+        output_path = "{}/{}".format(self.datastore_path, uuid)
+        fname = "{}/{}-{}.stripped.txt".format(output_path, result_obj['previous_md5'], str(time.time()))
+        with open(fname, 'w') as f:
+            f.write(contents)
+            f.close()
+
+        # Update history with the stripped text for future reference, this will also mean we save the first
+        # Should always be keyed by string(timestamp)
+        self.update_watch(uuid, {"history": {str(result_obj["last_checked"]): fname}})
+
+        return fname
+
+    def sync_to_json(self):
+        print("Saving..")
+        with open(self.json_store_path, 'w') as json_file:
+            json.dump(self.__data, json_file, indent=4)
+            logging.info("Re-saved index")
+
+        self.needs_write = False
+
+    # Thread runner, this helps with thread/write issues when there are many operations that want to update the JSON
+    # by just running periodically in one thread, according to python, dict updates are threadsafe.
+    def save_datastore(self):
+
+        while True:
+            if self.stop_thread:
+                print("Shutting down datastore thread")
+                return
+            if self.needs_write:
+                self.sync_to_json()
+            time.sleep(1)
+
+# body of the constructor

backend/templates/base.html

@@ -0,0 +1,76 @@
+<!doctype html>
+<html lang="en">
+<head>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <meta name="description" content="Self hosted website change detection.">
+    <title>Change Detection</title>
+    <link rel="stylesheet" href="/static/css/pure-min.css">
+    <link rel="stylesheet" href="/static/css/styles.css?ver=1000">
+    {% if extra_stylesheets %}
+        {% for m in extra_stylesheets %}
+        <link rel="stylesheet" href="{{ m }}?ver=1000">
+        {% endfor %}
+    {% endif %}
+</head>
+<body>
+
+<div class="header">
+    <div class="home-menu pure-menu pure-menu-horizontal pure-menu-fixed">
+        <a class="pure-menu-heading" href="/"><strong>Change</strong>Detection.io</a>
+        {% if current_diff_url %}
+        <a class=current-diff-url href="{{ current_diff_url }}"><span style="max-width: 30%; overflow: hidden;">{{ current_diff_url }}</span></a>
+        {% else %}
+        {% if new_version_available %}
+        <span id="new-version-text" class="pure-menu-heading"><a href="https://github.com/dgtlmoon/changedetection.io">A new version is available</a></span>
+        {% endif %}
+        {% endif %}
+
+        <ul class="pure-menu-list">
+
+            <li class="pure-menu-item">
+                <a href="/backup" class="pure-menu-link">BACKUP</a>
+            </li>
+            <li class="pure-menu-item">
+                <a href="/import" class="pure-menu-link">IMPORT</a>
+            </li>
+            <li class="pure-menu-item">
+                <a href="/settings" class="pure-menu-link">SETTINGS</a>
+            </li>
+            <li class="pure-menu-item"><a class="github-link" href="https://github.com/dgtlmoon/changedetection.io">
+                <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>
+            </a></li>
+            <!--
+            <li class="pure-menu-item"><a href="#" class="pure-menu-link">Tour</a></li>
+            <li class="pure-menu-item"><a href="#" class="pure-menu-link">Sign Up</a></li>
+            -->
+        </ul>
+    </div>
+</div>
+<div id="version">v{{ version }}</div>
+<section class="content">
+    <header>
+        {% block header %}{% endblock %}
+    </header>
+
+    {% if messages %}
+    <div class="messages">
+        {% for message in messages %}
+        <div class="flash-message {{ message['class'] }}">{{ message['message'] }}</div>
+        {% endfor %}
+    </div>
+    {% endif %}
+
+
+    {% block content %}
+
+    {% endblock %}
+</section>
+
+</body>
+</html>

backend/templates/diff.html

@@ -0,0 +1,165 @@
+{% extends 'base.html' %}
+
+{% block content %}
+
+<div id="settings">
+    <h1>Differences</h1>
+    <form class="pure-form " action="" method="GET">
+        <fieldset>
+
+            <label for="diffWords" class="pure-checkbox">
+                <input type="radio" name="diff_type" id="diffWords" value="diffWords" /> Words</label>
+            <label for="diffLines" class="pure-checkbox">
+                <input type="radio" name="diff_type" id="diffLines" value="diffLines" checked=""/> Lines</label>
+
+            <label for="diffChars" class="pure-checkbox">
+                <input type="radio" name="diff_type" id="diffChars" value="diffChars"/> Chars</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 %}
+                    <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>
+</div>
+
+<div id="diff-jump">
+    <a onclick="next_diff();">Jump</a>
+</div>
+<div id="diff-ui">
+
+    <table>
+        <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="diff-col">
+                <span id="result"></span>
+            </td>
+        </tr>
+        </tbody>
+    </table>
+    Diff algorithm from the amazing <a href="https://github.com/kpdecker/jsdiff">github.com/kpdecker/jsdiff</a>
+
+</div>
+
+<script src="/static/js/diff.js"></script>
+<script defer="">
+
+
+var a = document.getElementById('a');
+var b = document.getElementById('b');
+var result = document.getElementById('result');
+
+function changed() {
+	var diff = JsDiff[window.diffType](a.textContent, b.textContent);
+	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");
+			node.appendChild(document.createTextNode(diff[i].value));
+
+		} else if (diff[i].added) {
+			node = document.createElement('ins');
+			node.classList.add("change");
+			node.appendChild(document.createTextNode(diff[i].value));
+		} else {
+			node = document.createTextNode(diff[i].value);
+		}
+		fragment.appendChild(node);
+	}
+
+	result.textContent = '';
+	result.appendChild(fragment);
+}
+
+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;
+	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);
+		changed();
+	}
+}
+
+
+var inputs = document.getElementsByClassName('change');
+inputs.current=0;
+
+function next_diff() {
+
+    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;
+    }
+}
+
+
+</script>
+
+
+{% endblock %}

backend/templates/edit.html

@@ -0,0 +1,73 @@
+{% extends 'base.html' %}
+
+{% block content %}
+<div class="edit-form">
+
+
+    <form class="pure-form pure-form-stacked" action="/edit/{{uuid}}" method="POST">
+        <fieldset>
+            <div class="pure-control-group">
+                <label for="url">URL</label>
+                <input type="url" id="url" required="" placeholder="https://..." name="url" value="{{ watch.url}}"
+                       size="50"/>
+                <span class="pure-form-message-inline">This is a required field.</span>
+            </div>
+            <div class="pure-control-group">
+                <label for="tag">Tag</label>
+                <input type="text" placeholder="tag" size="10" id="tag" name="tag" value="{{ watch.tag}}"/>
+                <span class="pure-form-message-inline">Grouping tags, can be a comma separated list.</span>
+            </div>
+
+            <!-- @todo: move to tabs --->
+            <fieldset class="pure-group">
+                <label for="ignore-text">Ignore text</label>
+
+                <textarea id="ignore-text" name="ignore-text" class="pure-input-1-2" placeholder=""
+                          style="width: 100%;
+                            font-family:monospace;
+                            white-space: pre;
+                            overflow-wrap: normal;
+                            overflow-x: scroll;" rows="5">{% for value in watch.ignore_text %}{{ value }}
+{% endfor %}</textarea>
+                <span class="pure-form-message-inline">Each line will be processed separately as an ignore rule.</span>
+
+            </fieldset>
+
+            <!-- @todo: move to tabs --->
+            <fieldset class="pure-group">
+                <label for="headers">Extra request headers</label>
+
+                <textarea id="headers" name="headers" class="pure-input-1-2" placeholder="Example
+Cookie: foobar
+User-Agent: wonderbra 1.0"
+                          style="width: 100%;
+                            font-family:monospace;
+                            white-space: pre;
+                            overflow-wrap: normal;
+                            overflow-x: scroll;" rows="5">{% for key, value in watch.headers.items() %}{{ key }}: {{ value }}
+{% endfor %}</textarea>
+                <br/>
+
+            </fieldset>
+
+
+            <div class="pure-control-group">
+                <button type="submit" class="pure-button pure-button-primary">Save</button>
+            </div>
+            <br/>
+
+            <div class="pure-control-group">
+                <a href="/" class="pure-button button-small button-cancel">Cancel</a>
+                <a href="/api/delete?uuid={{uuid}}"
+                   class="pure-button button-small button-error ">Delete</a>
+
+            </div>
+
+
+        </fieldset>
+    </form>
+
+
+</div>
+
+{% endblock %}

backend/templates/import.html

@@ -0,0 +1,26 @@
+{% extends 'base.html' %}
+
+{% block content %}
+<div class="edit-form">
+
+
+    <form class="pure-form pure-form-aligned" action="/import" method="POST">
+
+        <fieldset class="pure-group">
+            <legend>One URL per line, URLs that do not pass validation will stay in the textarea.</legend>
+
+            <textarea name="urls" class="pure-input-1-2" placeholder="https://"
+                      style="width: 100%;
+                            font-family:monospace;
+                            white-space: pre;
+                            overflow-wrap: normal;
+                            overflow-x: scroll;" rows="25">{{ remaining }}</textarea>
+        </fieldset>
+        <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">Import</button>
+
+    </form>
+
+</div>
+
+{% endblock %}
+

backend/templates/scrub.html

@@ -0,0 +1,43 @@
+{% extends 'base.html' %}
+
+{% block content %}
+<div class="edit-form">
+
+
+    <form class="pure-form pure-form-stacked" action="/scrub" method="POST">
+        <fieldset>
+            <div class="pure-control-group">
+                This will remove all version snapshots/data, but keep your list of URLs. <br/>
+                You may like to use the <strong>BACKUP</strong> link first.<br/>
+
+                Type in the word <strong>scrub</strong> to confirm that you understand!
+                <br/>
+
+            </div>
+
+            <div class="pure-control-group">
+                <br/>
+                <label for="confirmtext">Confirm</label><br/>
+                <input type="text" id="confirmtext" required="" name="confirmtext" value="" size="10"/>
+                <br/>
+
+
+            </div>
+
+
+            <div class="pure-control-group">
+                <button type="submit" class="pure-button pure-button-primary">Scrub!</button>
+            </div>
+            <br/>
+            <div class="pure-control-group">
+                <a href="/" class="pure-button button-small button-cancel">Cancel</a>
+            </div>
+
+
+        </fieldset>
+    </form>
+
+
+</div>
+
+{% endblock %}

backend/templates/settings.html

@@ -0,0 +1,35 @@
+{% extends 'base.html' %}
+
+{% block content %}
+<div class="edit-form">
+
+
+    <form class="pure-form pure-form-stacked" action="/settings" method="POST">
+        <fieldset>
+            <div class="pure-control-group">
+                <label for="minutes">Maximum time in minutes until recheck.</label>
+                <input type="text" id="minutes" required="" name="minutes" value="{{minutes}}"
+                       size="5"/>
+                <span class="pure-form-message-inline">This is a required field.</span>
+            </div>
+
+
+            <br/>
+            <div class="pure-control-group">
+                <button type="submit" class="pure-button pure-button-primary">Save</button>
+            </div>
+            <br/>
+
+            <div class="pure-control-group">
+                <a href="/" class="pure-button button-small button-cancel">Back</a>
+                <a href="/scrub" class="pure-button button-small button-cancel">Reset all version data</a>
+            </div>
+
+
+        </fieldset>
+    </form>
+
+
+</div>
+
+{% endblock %}

backend/templates/watch-diff-stream.html

@@ -0,0 +1,12 @@
+{% extends 'watch-overview.html' %}
+{% block innercontent %}
+Entries: {{ streams|length }}
+
+<div id="diff-stream" class="edit-form">
+    {% for item in streams %}
+        {{ loop.index }}
+{% for diff in item %}{% if diff[0] =='+' %}<ins>{{ diff }}</ins>{% endif %}{% if diff[0] =='-' %}<del>{{ diff }}</del>{% endif %}
+        {% endfor %}
+    {% endfor %}
+</div>
+{% endblock %}

backend/templates/watch-overview.html

@@ -0,0 +1,32 @@
+{% extends 'base.html' %}
+
+{% block content %}
+
+<div class="box">
+
+    <form class="pure-form" action="/api/add" method="POST" id="new-watch-form">
+        <fieldset>
+            <legend>Add a new change detection watch</legend>
+            <input type="url" placeholder="https://..." name="url"/>
+            <input type="text" placeholder="tag" size="10" name="tag" value="{{active_tag if active_tag}}"/>
+            <button type="submit" class="pure-button pure-button-primary">Watch</button>
+        </fieldset>
+        <!-- add extra stuff, like do a http POST and send headers -->
+        <!-- user/pass r = requests.get('https://api.github.com/user', auth=('user', 'pass')) -->
+    </form>
+    <div>
+        <a href="/" class="pure-button button-tag {{'active' if not active_tag }}">All</a>
+        {% for tag in tags %}
+            {% if tag != "" %}
+                <a href="/?tag={{ tag}}" class="pure-button button-tag {{'active' if active_tag == tag }}">{{ tag }}</a>
+            {% endif %}
+        {% endfor %}
+    </div>
+
+    <div id="watch-table-wrapper">
+    {% block innercontent %}
+
+    {% endblock %}
+    </div>
+</div>
+{% endblock %}

backend/templates/watch-table.html

@@ -0,0 +1,64 @@
+{% extends 'watch-overview.html' %}
+{% block innercontent %}
+        <table class="pure-table pure-table-striped watch-table">
+            <thead>
+            <tr>
+                <th>#</th>
+                <th></th>
+                <th>Last Checked</th>
+                <th>Last Changed</th>
+                <th></th>
+            </tr>
+            </thead>
+            <tbody>
+
+
+            {% for watch in watches %}
+            <tr id="{{ watch.uuid }}"
+                class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }}
+                {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
+                {% if watch.newest_history_key| int > watch.last_viewed| int %}unviewed{% endif %}">
+                <td>{{ loop.index }}</td>
+                <td class="title-col">{{watch.title if watch.title is not none else watch.url}}
+                    <a class="external" target=_blank href="{{ watch.url }}"></a>
+                    {% if watch.last_error is defined and watch.last_error != False %}
+                    <div class="fetch-error">{{ watch.last_error }}</div>
+                    {% endif %}
+                    {% if not active_tag %}
+                    <span class="watch-tag-list">{{ watch.tag}}</span>
+                    {% endif %}
+                </td>
+                <td>{{watch|format_last_checked_time}}</td>
+                <td>{% if watch.history|length >= 2 and watch.last_changed %}
+                    {{watch.last_changed|format_timestamp_timeago}}
+                    {% else %}
+                    Not yet
+                    {% endif %}
+                </td>
+                <td>
+                    <a href="/api/checknow?uuid={{ watch.uuid}}{% if request.args.get('tag') %}&tag={{request.args.get('tag')}}{% endif %}"
+                       class="pure-button button-small pure-button-primary">Recheck</a>
+                    <a href="/edit/{{ watch.uuid}}" class="pure-button button-small pure-button-primary">Edit</a>
+                    {% if watch.history|length >= 2 %}
+                    <a href="/diff/{{ watch.uuid}}" class="pure-button button-small pure-button-primary">Diff</a>
+                    {% endif %}
+                </td>
+            </tr>
+            {% endfor %}
+            </tbody>
+        </table>
+        <ul id="post-list-buttons">
+            {% if has_unviewed %}
+            <li>
+                <a href="/api/mark-all-viewed" class="pure-button button-tag ">Mark all viewed</a>
+            </li>
+            {% endif %}
+            <li>
+               <a href="/api/checknow{% if active_tag%}?tag={{active_tag}}{%endif%}" class="pure-button button-tag ">Recheck
+                all {% if active_tag%}in "{{active_tag}}"{%endif%}</a>
+            </li>
+            <li>
+                <a href="{{ url_for('index', tag=active_tag , rss=true)}}"><img id="feed-icon" src="/static/images/Generic_Feed-icon.svg" height="15px"></a>
+            </li>
+        </ul>
+{% endblock %}

backend/tests/conftest.py

@@ -0,0 +1,48 @@
+#!/usr/bin/python3
+
+import pytest
+from backend import changedetection_app
+from backend import store
+import os
+
+
+# https://github.com/pallets/flask/blob/1.1.2/examples/tutorial/tests/test_auth.py
+# Much better boilerplate than the docs
+# https://www.python-boilerplate.com/py3+flask+pytest/
+
+global app
+
+@pytest.fixture(scope='session')
+def app(request):
+    """Create application for the tests."""
+    datastore_path = "./test-datastore"
+
+    try:
+        os.mkdir(datastore_path)
+    except FileExistsError:
+        pass
+
+    try:
+        os.unlink("{}/url-watches.json".format(datastore_path))
+    except FileNotFoundError:
+        pass
+
+    app_config = {'datastore_path': datastore_path}
+    datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], include_default_watches=False)
+    app = changedetection_app(app_config, datastore)
+    app.config['STOP_THREADS'] = True
+
+    def teardown():
+        datastore.stop_thread = True
+        app.config.exit.set()
+        try:
+            os.unlink("{}/url-watches.json".format(datastore_path))
+        except FileNotFoundError:
+            # This is fine in the case of a failure.
+            pass
+
+        assert 1 == 1
+
+    request.addfinalizer(teardown)
+    yield app
+

backend/tests/test_backend.py

@@ -0,0 +1,123 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from urllib.request import urlopen
+import pytest
+
+sleep_time_for_fetch_thread = 3
+
+
+def test_setup_liveserver(live_server):
+    @live_server.app.route('/test-endpoint')
+    def test_endpoint():
+        # Tried using a global var here but didn't seem to work, so reading from a file instead.
+        with open("test-datastore/output.txt", "r") as f:
+            return f.read()
+
+    live_server.start()
+
+    assert 1 == 1
+
+
+def set_original_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/output.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def set_modified_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <p>which has this one new line</p>
+     </br>
+     So let's see what happens.  </br>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/output.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def test_check_basic_change_detection_functionality(client, live_server):
+    set_original_response()
+
+    # Add our URL to the import page
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": url_for('test_endpoint', _external=True)},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # Do this a few times.. ensures we dont accidently set the status
+    for n in range(3):
+        client.get(url_for("api_watch_checknow"), follow_redirects=True)
+
+        # Give the thread time to pick it up
+        time.sleep(sleep_time_for_fetch_thread)
+
+        # It should report nothing found (no new 'unviewed' class)
+        res = client.get(url_for("index"))
+        assert b'unviewed' not in res.data
+        assert b'test-endpoint' in res.data
+
+    #####################
+
+    # Make a change
+    set_modified_response()
+
+    res = urlopen(url_for('test_endpoint', _external=True))
+    assert b'which has this one new line' in res.read()
+
+    # Force recheck
+    res = client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    assert b'1 watches are rechecking.' in res.data
+
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # Now something should be ready, indicated by having a 'unviewed' class
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    # Following the 'diff' link, it should no longer display as 'unviewed' even after we recheck it a few times
+    res = client.get(url_for("diff_history_page", uuid="first"))
+    assert b'Compare newest' in res.data
+
+    time.sleep(2)
+
+    # Do this a few times.. ensures we dont accidently set the status
+    for n in range(2):
+        client.get(url_for("api_watch_checknow"), follow_redirects=True)
+
+        # Give the thread time to pick it up
+        time.sleep(sleep_time_for_fetch_thread)
+
+        # It should report nothing found (no new 'unviewed' class)
+        res = client.get(url_for("index"))
+        assert b'unviewed' not in res.data
+        assert b'test-endpoint' in res.data
+
+    set_original_response()
+
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    time.sleep(sleep_time_for_fetch_thread)
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    # Cleanup everything
+    res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

backend/tests/test_ignore_text.py

@@ -0,0 +1,152 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from urllib.request import urlopen
+import pytest
+
+
+# Unit test of the stripper
+# Always we are dealing in utf-8
+def test_strip_text_func():
+    from backend import fetch_site_status
+
+    test_content = """
+    Some content
+    is listed here
+
+    but sometimes we want to remove the lines.
+
+    but not always."""
+
+    ignore_lines = ["sometimes"]
+
+    fetcher = fetch_site_status.perform_site_check(datastore=False)
+    stripped_content = fetcher.strip_ignore_text(test_content, ignore_lines)
+
+    assert b"sometimes" not in stripped_content
+    assert b"Some content" in stripped_content
+
+
+def set_original_ignore_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+     </body>
+     </html>
+
+    """
+
+    with open("test-datastore/output.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def set_modified_original_ignore_response():
+    test_return_data = """<html>
+       <body>
+     Some NEW nice initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+     </body>
+     </html>
+
+    """
+
+    with open("test-datastore/output.txt", "w") as f:
+        f.write(test_return_data)
+
+
+# Is the same but includes ZZZZZ, 'ZZZZZ' is the last line in ignore_text
+def set_modified_ignore_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <p>Which is across multiple lines</p>
+     <P>ZZZZZ</P>
+     </br>
+     So let's see what happens.  </br>
+     </body>
+     </html>
+
+    """
+
+    with open("test-datastore/output.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def test_check_ignore_text_functionality(client, live_server):
+    sleep_time_for_fetch_thread = 3
+
+    ignore_text = "XXXXX\nYYYYY\nZZZZZ"
+    set_original_ignore_response()
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    # Trigger a check
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # Goto the edit page, add our ignore text
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"ignore-text": ignore_text, "url": test_url, "tag": "", "headers": ""},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+
+    # Check it saved
+    res = client.get(
+        url_for("edit_page", uuid="first"),
+    )
+    assert bytes(ignore_text.encode('utf-8')) in res.data
+
+    # Trigger a check
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+    assert b'/test-endpoint' in res.data
+
+    #  Make a change
+    set_modified_ignore_response()
+
+    # Trigger a check
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+    assert b'/test-endpoint' in res.data
+
+    # Just to be sure.. set a regular modified change..
+    set_modified_original_ignore_response()
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    time.sleep(sleep_time_for_fetch_thread)
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetection.py

@@ -1,6 +1,73 @@
-#!/usr/bin/env python3
+#!/usr/bin/python3
 
-# Only exists for direct CLI usage
+# Launch as a eventlet.wsgi server instance.
 
-import changedetectionio
-changedetectionio.main()
+import getopt
+import sys
+
+import eventlet
+import eventlet.wsgi
+import backend
+
+from backend import store
+
+
+def main(argv):
+    ssl_mode = False
+    port = 5000
+    datastore_path = "./datastore"
+
+    try:
+        opts, args = getopt.getopt(argv, "sd:p:", "purge")
+    except getopt.GetoptError:
+        print('backend.py -s SSL enable -p [port] -d [datastore path]')
+        sys.exit(2)
+
+    for opt, arg in opts:
+        #        if opt == '--purge':
+        # Remove history, the actual files you need to delete manually.
+        #            for uuid, watch in datastore.data['watching'].items():
+        #                watch.update({'history': {}, 'last_checked': 0, 'last_changed': 0, 'previous_md5': None})
+
+        if opt == '-s':
+            ssl_mode = True
+
+        if opt == '-p':
+            port = int(arg)
+
+        if opt == '-d':
+            datastore_path = arg
+
+
+
+    # threads can read from disk every x seconds right?
+    # front end can just save
+    # We just need to know which threads are looking at which UUIDs
+
+    # isnt there some @thingy to attach to each route to tell it, that this route needs a datastore
+    app_config = {'datastore_path': datastore_path}
+
+    datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'])
+    app = backend.changedetection_app(app_config, datastore)
+
+    @app.context_processor
+    def inject_version():
+        return dict(version=datastore.data['version_tag'])
+
+    @app.context_processor
+    def inject_new_version_available():
+        return dict(new_version_available=app.config['NEW_VERSION_AVAILABLE'])
+
+    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(('', port)),
+                                               certfile='cert.pem',
+                                               keyfile='privkey.pem',
+                                               server_side=True), app)
+
+    else:
+        eventlet.wsgi.server(eventlet.listen(('', port)), app)
+
+
+if __name__ == '__main__':
+    main(sys.argv[1:])

changedetectionio/.gitignore

@@ -1,2 +0,0 @@
-test-datastore
-package-lock.json

changedetectionio/__init__.py

@@ -1,208 +0,0 @@
-#!/usr/bin/env python3
-
-# Read more https://github.com/dgtlmoon/changedetection.io/wiki
-
-__version__ = '0.49.13'
-
-from changedetectionio.strtobool import strtobool
-from json.decoder import JSONDecodeError
-import os
-os.environ['EVENTLET_NO_GREENDNS'] = 'yes'
-import eventlet
-import eventlet.wsgi
-import getopt
-import platform
-import signal
-import socket
-import sys
-
-from changedetectionio import store
-from changedetectionio.flask_app import changedetection_app
-from loguru import logger
-
-# Only global so we can access it in the signal handler
-app = None
-datastore = None
-
-def get_version():
-    return __version__
-
-# Parent wrapper or OS sends us a SIGTERM/SIGINT, do everything required for a clean shutdown
-def sigshutdown_handler(_signo, _stack_frame):
-    name = signal.Signals(_signo).name
-    logger.critical(f'Shutdown: Got Signal - {name} ({_signo}), Saving DB to disk and calling shutdown')
-    datastore.sync_to_json()
-    logger.success('Sync JSON to disk complete.')
-    # This will throw a SystemExit exception, because eventlet.wsgi.server doesn't know how to deal with it.
-    # Solution: move to gevent or other server in the future (#2014)
-    datastore.stop_thread = True
-    app.config.exit.set()
-    sys.exit()
-
-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:l:", "port")
-    except getopt.GetoptError:
-        print('backend.py -s SSL enable -h [host] -p [port] -d [datastore path] -l [debug level - TRACE, DEBUG(default), INFO, SUCCESS, WARNING, ERROR, CRITICAL]')
-        sys.exit(2)
-
-    create_datastore_dir = False
-
-    # Set a default logger level
-    logger_level = 'DEBUG'
-    # Set a logger level via shell env variable
-    # Used: Dockerfile for CICD
-    # To set logger level for pytest, see the app function in tests/conftest.py
-    if os.getenv("LOGGER_LEVEL"):
-        level = os.getenv("LOGGER_LEVEL")
-        logger_level = int(level) if level.isdigit() else level.upper()
-
-    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':
-            logger.success("Enabling IPv6 listen support")
-            ipv6_enabled = True
-
-        # Cleanup (remove text files that arent in the index)
-        if opt == '-c':
-            do_cleanup = True
-
-        # Create the datadir if it doesnt exist
-        if opt == '-C':
-            create_datastore_dir = True
-
-        if opt == '-l':
-            logger_level = int(arg) if arg.isdigit() else arg.upper()
-
-    # Without this, a logger will be duplicated
-    logger.remove()
-    try:
-        log_level_for_stdout = { 'DEBUG', 'SUCCESS' }
-        logger.configure(handlers=[
-            {"sink": sys.stdout, "level": logger_level,
-             "filter" : lambda record: record['level'].name in log_level_for_stdout},
-            {"sink": sys.stderr, "level": logger_level,
-             "filter": lambda record: record['level'].name not in log_level_for_stdout},
-            ])
-    # Catch negative number or wrong log level name
-    except ValueError:
-        print("Available log level names: TRACE, DEBUG(default), INFO, SUCCESS,"
-              " WARNING, ERROR, CRITICAL")
-        sys.exit(2)
-
-    # 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:
-            logger.critical(
-                f"ERROR: Directory path for the datastore '{app_config['datastore_path']}'"
-                f" does not exist, cannot start, please make sure the"
-                f" directory exists or specify a directory with the -d option.\n"
-                f"Or use the -C parameter to create the directory.")
-            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
-        logger.critical(f"ERROR: JSON DB or Proxy List JSON at '{app_config['datastore_path']}' appears to be corrupt, aborting.")
-        logger.critical(str(e))
-        return
-
-    app = changedetection_app(app_config, datastore)
-
-    signal.signal(signal.SIGTERM, sigshutdown_handler)
-    signal.signal(signal.SIGINT, sigshutdown_handler)
-    
-    # Custom signal handler for memory cleanup
-    def sigusr_clean_handler(_signo, _stack_frame):
-        from changedetectionio.gc_cleanup import memory_cleanup
-        logger.info('SIGUSR1 received: Running memory cleanup')
-        return memory_cleanup(app)
-
-    # Register the SIGUSR1 signal handler
-    # Only register the signal handler if running on Linux
-    if platform.system() == "Linux":
-        signal.signal(signal.SIGUSR1, sigusr_clean_handler)
-    else:
-        logger.info("SIGUSR1 handler only registered on Linux, skipped.")
-
-    # Go into cleanup mode
-    if do_cleanup:
-        datastore.remove_unused_snapshots()
-
-    app.config['datastore_path'] = datastore_path
-
-
-    @app.context_processor
-    def inject_version():
-        return dict(right_sticky="v{}".format(datastore.data['version_tag']),
-                    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.
-    @app.after_request
-    def hide_referrer(response):
-        if strtobool(os.getenv("HIDE_REFERER", 'false')):
-            response.headers["Referrer-Policy"] = "same-origin"
-
-        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'):
-        logger.info("USE_X_SETTINGS is ENABLED")
-        from werkzeug.middleware.proxy_fix import ProxyFix
-        app.wsgi_app = ProxyFix(app.wsgi_app, x_prefix=1, x_host=1)
-
-    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/api/Import.py

@@ -1,62 +0,0 @@
-import os
-from changedetectionio.strtobool import strtobool
-from flask_restful import abort, Resource
-from flask import request
-import validators
-from . import auth
-
-
-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

changedetectionio/api/Notifications.py

@@ -1,145 +0,0 @@
-from flask_expects_json import expects_json
-from flask_restful import Resource
-from . import auth
-from flask_restful import abort, Resource
-from flask import request
-from . import auth
-from . import schema_create_notification_urls, schema_delete_notification_urls
-
-class Notifications(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-
-    @auth.check_token
-    def get(self):
-        """
-        @api {get} /api/v1/notifications Return Notification URL List
-        @apiDescription Return the Notification URL List from the configuration
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/notifications -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            HTTP/1.0 200
-            {
-                'notification_urls': ["notification-urls-list"]
-            }
-        @apiName Get
-        @apiGroup Notifications
-        """
-
-        notification_urls = self.datastore.data.get('settings', {}).get('application', {}).get('notification_urls', [])        
-
-        return {
-                'notification_urls': notification_urls,
-               }, 200
-    
-    @auth.check_token
-    @expects_json(schema_create_notification_urls)
-    def post(self):
-        """
-        @api {post} /api/v1/notifications Create Notification URLs
-        @apiDescription Add one or more notification URLs from the configuration
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/notifications/batch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"notification_urls": ["url1", "url2"]}'
-        @apiName CreateBatch
-        @apiGroup Notifications
-        @apiSuccess (201) {Object[]} notification_urls List of added notification URLs
-        @apiError (400) {String} Invalid input
-        """
-
-        json_data = request.get_json()
-        notification_urls = json_data.get("notification_urls", [])
-
-        from wtforms import ValidationError
-        try:
-            validate_notification_urls(notification_urls)
-        except ValidationError as e:
-            return str(e), 400
-
-        added_urls = []
-
-        for url in notification_urls:
-            clean_url = url.strip()
-            added_url = self.datastore.add_notification_url(clean_url)
-            if added_url:
-                added_urls.append(added_url)
-
-        if not added_urls:
-            return "No valid notification URLs were added", 400
-
-        return {'notification_urls': added_urls}, 201
-    
-    @auth.check_token
-    @expects_json(schema_create_notification_urls)
-    def put(self):
-        """
-        @api {put} /api/v1/notifications Replace Notification URLs
-        @apiDescription Replace all notification URLs with the provided list (can be empty)
-        @apiExample {curl} Example usage:
-            curl -X PUT http://localhost:5000/api/v1/notifications -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"notification_urls": ["url1", "url2"]}'
-        @apiName Replace
-        @apiGroup Notifications
-        @apiSuccess (200) {Object[]} notification_urls List of current notification URLs
-        @apiError (400) {String} Invalid input
-        """
-        json_data = request.get_json()
-        notification_urls = json_data.get("notification_urls", [])
-
-        from wtforms import ValidationError
-        try:
-            validate_notification_urls(notification_urls)
-        except ValidationError as e:
-            return str(e), 400
-        
-        if not isinstance(notification_urls, list):
-            return "Invalid input format", 400
-
-        clean_urls = [url.strip() for url in notification_urls if isinstance(url, str)]
-        self.datastore.data['settings']['application']['notification_urls'] = clean_urls
-        self.datastore.needs_write = True
-
-        return {'notification_urls': clean_urls}, 200
-        
-    @auth.check_token
-    @expects_json(schema_delete_notification_urls)
-    def delete(self):
-        """
-        @api {delete} /api/v1/notifications Delete Notification URLs
-        @apiDescription Deletes one or more notification URLs from the configuration
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/notifications -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"notification_urls": ["url1", "url2"]}'
-        @apiParam {String[]} notification_urls The notification URLs to delete.
-        @apiName Delete
-        @apiGroup Notifications
-        @apiSuccess (204) {String} OK Deleted
-        @apiError (400) {String} No matching notification URLs found.
-        """
-
-        json_data = request.get_json()
-        urls_to_delete = json_data.get("notification_urls", [])
-        if not isinstance(urls_to_delete, list):
-            abort(400, message="Expected a list of notification URLs.")
-
-        notification_urls = self.datastore.data['settings']['application'].get('notification_urls', [])
-        deleted = []
-
-        for url in urls_to_delete:
-            clean_url = url.strip()
-            if clean_url in notification_urls:
-                notification_urls.remove(clean_url)
-                deleted.append(clean_url)
-
-        if not deleted:
-            abort(400, message="No matching notification URLs found.")
-
-        self.datastore.data['settings']['application']['notification_urls'] = notification_urls
-        self.datastore.needs_write = True
-
-        return 'OK', 204
-    
-def validate_notification_urls(notification_urls):
-    from changedetectionio.forms import ValidateAppRiseServers
-    validator = ValidateAppRiseServers()
-    class DummyForm: pass
-    dummy_form = DummyForm()
-    field = type("Field", (object,), {"data": notification_urls, "gettext": lambda self, x: x})()
-    validator(dummy_form, field)

changedetectionio/api/Search.py

@@ -1,51 +0,0 @@
-from flask_restful import Resource, abort
-from flask import request
-from . import auth
-
-class Search(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-
-    @auth.check_token
-    def get(self):
-        """
-        @api {get} /api/v1/search Search for watches
-        @apiDescription Search watches by URL or title text
-        @apiExample {curl} Example usage:
-            curl "http://localhost:5000/api/v1/search?q=https://example.com/page1" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/search?q=https://example.com/page1?tag=Favourites" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/search?q=https://example.com?partial=true" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiName Search
-        @apiGroup Watch Management
-        @apiQuery {String} q Search query to match against watch URLs and titles
-        @apiQuery {String} [tag] Optional name of tag to limit results (name not UUID)
-        @apiQuery {String} [partial] Allow partial matching of URL query
-        @apiSuccess (200) {Object} JSON Object containing matched watches
-        """
-        query = request.args.get('q', '').strip()
-        tag_limit = request.args.get('tag', '').strip()
-        from changedetectionio.strtobool import strtobool
-        partial = bool(strtobool(request.args.get('partial', '0'))) if 'partial' in request.args else False
-
-        # Require a search query
-        if not query:
-            abort(400, message="Search query 'q' parameter is required")
-
-        # Use the search function from the datastore
-        matching_uuids = self.datastore.search_watches_for_url(query=query, tag_limit=tag_limit, partial=partial)
-
-        # Build the response with watch details
-        results = {}
-        for uuid in matching_uuids:
-            watch = self.datastore.data['watching'].get(uuid)
-            results[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
-            }
-
-        return results, 200

changedetectionio/api/SystemInfo.py

@@ -1,54 +0,0 @@
-from flask_restful import Resource
-from . import auth
-
-
-class SystemInfo(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-        self.update_q = kwargs['update_q']
-
-    @auth.check_token
-    def get(self):
-        """
-        @api {get} /api/v1/systeminfo Return system info
-        @apiDescription Return some info about the current system state
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/systeminfo -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            HTTP/1.0 200
-            {
-                'queue_size': 10 ,
-                'overdue_watches': ["watch-uuid-list"],
-                'uptime': 38344.55,
-                'watch_count': 800,
-                'version': "0.40.1"
-            }
-        @apiName Get Info
-        @apiGroup System Information
-        """
-        import time
-        overdue_watches = []
-
-        # Check all watches and report which have not been checked but should have been
-
-        for uuid, watch in self.datastore.data.get('watching', {}).items():
-            # see if now - last_checked is greater than the time that should have been
-            # this is not super accurate (maybe they just edited it) but better than nothing
-            t = watch.threshold_seconds()
-            if not t:
-                # Use the system wide default
-                t = self.datastore.threshold_seconds
-
-            time_since_check = time.time() - watch.get('last_checked')
-
-            # Allow 5 minutes of grace time before we decide it's overdue
-            if time_since_check - (5 * 60) > t:
-                overdue_watches.append(uuid)
-        from changedetectionio import __version__ as main_version
-        return {
-                   'queue_size': self.update_q.qsize(),
-                   'overdue_watches': overdue_watches,
-                   'uptime': round(time.time() - self.datastore.start_time, 2),
-                   'watch_count': len(self.datastore.data.get('watching', {})),
-                   'version': main_version
-               }, 200

changedetectionio/api/Tags.py

@@ -1,156 +0,0 @@
-from flask_expects_json import expects_json
-from flask_restful import abort, Resource
-from flask import request
-from . import auth
-
-# Import schemas from __init__.py
-from . import schema_tag, schema_create_tag, schema_update_tag
-
-
-class Tag(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-
-    # Get information about a single tag
-    # curl http://localhost:5000/api/v1/tag/<string:uuid>
-    @auth.check_token
-    def get(self, uuid):
-        """
-        @api {get} /api/v1/tag/:uuid Single tag - get data or toggle notification muting.
-        @apiDescription Retrieve tag information and set notification_muted status
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/tag/cc0cfffa-f449-477b-83ea-0caafd1dc091 -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/tag/cc0cfffa-f449-477b-83ea-0caafd1dc091?muted=muted" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiName Tag
-        @apiGroup Tag
-        @apiParam {uuid} uuid Tag unique ID.
-        @apiQuery {String} [muted] =`muted` or =`unmuted` , Sets the MUTE NOTIFICATIONS state
-        @apiSuccess (200) {String} OK When muted operation OR full JSON object of the tag
-        @apiSuccess (200) {JSON} TagJSON JSON Full JSON object of the tag
-        """
-        from copy import deepcopy
-        tag = deepcopy(self.datastore.data['settings']['application']['tags'].get(uuid))
-        if not tag:
-            abort(404, message=f'No tag exists with the UUID of {uuid}')
-
-        if request.args.get('muted', '') == 'muted':
-            self.datastore.data['settings']['application']['tags'][uuid]['notification_muted'] = True
-            return "OK", 200
-        elif request.args.get('muted', '') == 'unmuted':
-            self.datastore.data['settings']['application']['tags'][uuid]['notification_muted'] = False
-            return "OK", 200
-
-        return tag
-
-    @auth.check_token
-    def delete(self, uuid):
-        """
-        @api {delete} /api/v1/tag/:uuid Delete a tag and remove it from all watches
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/tag/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiParam {uuid} uuid Tag unique ID.
-        @apiName DeleteTag
-        @apiGroup Tag
-        @apiSuccess (200) {String} OK Was deleted
-        """
-        if not self.datastore.data['settings']['application']['tags'].get(uuid):
-            abort(400, message='No tag exists with the UUID of {}'.format(uuid))
-
-        # Delete the tag, and any tag reference
-        del self.datastore.data['settings']['application']['tags'][uuid]
-        
-        # Remove tag from all watches
-        for watch_uuid, watch in self.datastore.data['watching'].items():
-            if watch.get('tags') and uuid in watch['tags']:
-                watch['tags'].remove(uuid)
-
-        return 'OK', 204
-
-    @auth.check_token
-    @expects_json(schema_update_tag)
-    def put(self, uuid):
-        """
-        @api {put} /api/v1/tag/:uuid Update tag information
-        @apiExample {curl} Example usage:
-            Update (PUT)
-            curl http://localhost:5000/api/v1/tag/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X PUT -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"title": "New Tag Title"}'
-
-        @apiDescription Updates an existing tag using JSON
-        @apiParam {uuid} uuid Tag unique ID.
-        @apiName UpdateTag
-        @apiGroup Tag
-        @apiSuccess (200) {String} OK Was updated
-        @apiSuccess (500) {String} ERR Some other error
-        """
-        tag = self.datastore.data['settings']['application']['tags'].get(uuid)
-        if not tag:
-            abort(404, message='No tag exists with the UUID of {}'.format(uuid))
-
-        tag.update(request.json)
-        self.datastore.needs_write_urgent = True
-
-        return "OK", 200
-
-
-    @auth.check_token
-    # Only cares for {'title': 'xxxx'}
-    def post(self):
-        """
-        @api {post} /api/v1/watch Create a single tag
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"name": "Work related"}'
-        @apiName Create
-        @apiGroup Tag
-        @apiSuccess (200) {String} OK Was created
-        @apiSuccess (500) {String} ERR Some other error
-        """
-
-        json_data = request.get_json()
-        title = json_data.get("title",'').strip()
-
-
-        new_uuid = self.datastore.add_tag(title=title)
-        if new_uuid:
-            return {'uuid': new_uuid}, 201
-        else:
-            return "Invalid or unsupported tag", 400
-
-class Tags(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-
-    @auth.check_token
-    def get(self):
-        """
-        @api {get} /api/v1/tags List tags
-        @apiDescription Return list of available tags
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/tags -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            {
-                "cc0cfffa-f449-477b-83ea-0caafd1dc091": {
-                    "title": "Tech News",
-                    "notification_muted": false,
-                    "date_created": 1677103794
-                },
-                "e6f5fd5c-dbfe-468b-b8f3-f9d6ff5ad69b": {
-                    "title": "Shopping",
-                    "notification_muted": true,
-                    "date_created": 1676662819
-                }
-            }
-        @apiName ListTags
-        @apiGroup Tag Management
-        @apiSuccess (200) {String} OK JSON dict
-        """
-        result = {}
-        for uuid, tag in self.datastore.data['settings']['application']['tags'].items():
-            result[uuid] = {
-                'date_created': tag.get('date_created', 0),
-                'notification_muted': tag.get('notification_muted', False),
-                'title': tag.get('title', ''),
-                'uuid': tag.get('uuid')
-            }
-
-        return result, 200

changedetectionio/api/Watch.py

@@ -1,297 +0,0 @@
-import os
-from changedetectionio.strtobool import strtobool
-
-from flask_expects_json import expects_json
-from changedetectionio import queuedWatchMetaData
-from flask_restful import abort, Resource
-from flask import request, make_response
-import validators
-from . import auth
-import copy
-
-# Import schemas from __init__.py
-from . import schema, schema_create_watch, schema_update_watch
-
-
-class Watch(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-        self.update_q = kwargs['update_q']
-
-    # Get information about a single watch, excluding the history list (can be large)
-    # 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 Single watch - get data, recheck, pause, mute.
-        @apiDescription Retrieve watch information and set muted/paused status
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?muted=unmuted"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?paused=unpaused"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiName Watch
-        @apiGroup Watch
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiQuery {Boolean} [recheck] Recheck this watch `recheck=1`
-        @apiQuery {String} [paused] =`paused` or =`unpaused` , Sets the PAUSED state
-        @apiQuery {String} [muted] =`muted` or =`unmuted` , Sets the MUTE NOTIFICATIONS state
-        @apiSuccess (200) {String} OK When paused/muted/recheck operation OR full JSON object of the watch
-        @apiSuccess (200) {JSON} WatchJSON JSON Full JSON object of the watch
-        """
-        from copy import deepcopy
-        watch = deepcopy(self.datastore.data['watching'].get(uuid))
-        if not watch:
-            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
-
-        if request.args.get('recheck'):
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-            return "OK", 200
-        if request.args.get('paused', '') == 'paused':
-            self.datastore.data['watching'].get(uuid).pause()
-            return "OK", 200
-        elif request.args.get('paused', '') == 'unpaused':
-            self.datastore.data['watching'].get(uuid).unpause()
-            return "OK", 200
-        if request.args.get('muted', '') == 'muted':
-            self.datastore.data['watching'].get(uuid).mute()
-            return "OK", 200
-        elif request.args.get('muted', '') == 'unmuted':
-            self.datastore.data['watching'].get(uuid).unmute()
-            return "OK", 200
-
-        # Return without history, get that via another API call
-        # Properties are not returned as a JSON, so add the required props manually
-        watch['history_n'] = watch.history_n
-        # attr .last_changed will check for the last written text snapshot on change
-        watch['last_changed'] = watch.last_changed
-        watch['viewed'] = watch.viewed
-        return watch
-
-    @auth.check_token
-    def delete(self, uuid):
-        """
-        @api {delete} /api/v1/watch/:uuid Delete a watch and related history
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiName Delete
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was deleted
-        """
-        if not self.datastore.data['watching'].get(uuid):
-            abort(400, message='No watch exists with the UUID of {}'.format(uuid))
-
-        self.datastore.delete(uuid)
-        return 'OK', 204
-
-    @auth.check_token
-    @expects_json(schema_update_watch)
-    def put(self, uuid):
-        """
-        @api {put} /api/v1/watch/:uuid Update watch information
-        @apiExample {curl} Example usage:
-            Update (PUT)
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X PUT -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "new list"}'
-
-        @apiDescription Updates an existing watch using JSON, accepts the same structure as returned in <a href="#api-Watch-Watch">get single watch information</a>
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiName Update a watch
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was updated
-        @apiSuccess (500) {String} ERR Some other error
-        """
-        watch = self.datastore.data['watching'].get(uuid)
-        if not watch:
-            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
-
-        if request.json.get('proxy'):
-            plist = self.datastore.proxy_list
-            if not request.json.get('proxy') in plist:
-                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
-
-        watch.update(request.json)
-
-        return "OK", 200
-
-
-class WatchHistory(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-
-    # Get a list of available history for a watch by UUID
-    # 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:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
-            {
-                "1676649279": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/cb7e9be8258368262246910e6a2a4c30.txt",
-                "1677092785": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/e20db368d6fc633e34f559ff67bb4044.txt",
-                "1677103794": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/02efdd37dacdae96554a8cc85dc9c945.txt"
-            }
-        @apiName Get list of available stored snapshots for watch
-        @apiGroup Watch History
-        @apiSuccess (200) {String} OK
-        @apiSuccess (404) {String} ERR Not found
-        """
-        watch = self.datastore.data['watching'].get(uuid)
-        if not watch:
-            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
-        return watch.history, 200
-
-
-class WatchSingleHistory(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-
-    @auth.check_token
-    def get(self, uuid, timestamp):
-        """
-        @api {get} /api/v1/watch/<string:uuid>/history/<int:timestamp> Get single snapshot from watch
-        @apiDescription Requires watch `uuid` and `timestamp`. `timestamp` of "`latest`" for latest available snapshot, or <a href="#api-Watch_History-Get_list_of_available_stored_snapshots_for_watch">use the list returned here</a>
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history/1677092977 -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
-        @apiName Get single snapshot content
-        @apiGroup Watch History
-        @apiParam {String} [html]       Optional Set to =1 to return the last HTML (only stores last 2 snapshots, use `latest` as timestamp)
-        @apiSuccess (200) {String} OK
-        @apiSuccess (404) {String} ERR Not found
-        """
-        watch = self.datastore.data['watching'].get(uuid)
-        if not watch:
-            abort(404, message=f"No watch exists with the UUID of {uuid}")
-
-        if not len(watch.history):
-            abort(404, message=f"Watch found but no history exists for the UUID {uuid}")
-
-        if timestamp == 'latest':
-            timestamp = list(watch.history.keys())[-1]
-
-        if request.args.get('html'):
-            content = watch.get_fetched_html(timestamp)
-            if content:
-                response = make_response(content, 200)
-                response.mimetype = "text/html"
-            else:
-                response = make_response("No content found", 404)
-                response.mimetype = "text/plain"
-        else:
-            content = watch.get_history_snapshot(timestamp)
-            response = make_response(content, 200)
-            response.mimetype = "text/plain"
-
-        return response
-
-
-class CreateWatch(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-        self.update_q = kwargs['update_q']
-
-    @auth.check_token
-    @expects_json(schema_create_watch)
-    def post(self):
-        """
-        @api {post} /api/v1/watch Create a single watch
-        @apiDescription Requires atleast `url` set, can accept the same structure as <a href="#api-Watch-Watch">get single watch information</a> to create.
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "nice list"}'
-        @apiName Create
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was created
-        @apiSuccess (500) {String} ERR Some other error
-        """
-
-        json_data = request.get_json()
-        url = json_data['url'].strip()
-
-        # If hosts that only contain alphanumerics are allowed ("localhost" for example)
-        allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
-        if not validators.url(url, simple_host=allow_simplehost):
-            return "Invalid or unsupported URL", 400
-
-        if json_data.get('proxy'):
-            plist = self.datastore.proxy_list
-            if not json_data.get('proxy') in plist:
-                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
-
-        extras = copy.deepcopy(json_data)
-
-        # Because we renamed 'tag' to 'tags' but don't want to change the API (can do this in v2 of the API)
-        tags = None
-        if extras.get('tag'):
-            tags = extras.get('tag')
-            del extras['tag']
-
-        del extras['url']
-
-        new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags)
-        if new_uuid:
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
-            return {'uuid': new_uuid}, 201
-        else:
-            return "Invalid or unsupported URL", 400
-
-    @auth.check_token
-    def get(self):
-        """
-        @api {get} /api/v1/watch List watches
-        @apiDescription Return concise list of available watches and some very basic info
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            {
-                "6a4b7d5c-fee4-4616-9f43-4ac97046b595": {
-                    "last_changed": 1677103794,
-                    "last_checked": 1677103794,
-                    "last_error": false,
-                    "title": "",
-                    "url": "http://www.quotationspage.com/random.php"
-                },
-                "e6f5fd5c-dbfe-468b-b8f3-f9d6ff5ad69b": {
-                    "last_changed": 0,
-                    "last_checked": 1676662819,
-                    "last_error": false,
-                    "title": "QuickLook",
-                    "url": "https://github.com/QL-Win/QuickLook/tags"
-                }
-            }
-
-        @apiParam {String} [recheck_all]       Optional Set to =1 to force recheck of all watches
-        @apiParam {String} [tag]               Optional name of tag to limit results
-        @apiName ListWatches
-        @apiGroup Watch Management
-        @apiSuccess (200) {String} OK JSON dict
-        """
-        list = {}
-
-        tag_limit = request.args.get('tag', '').lower()
-        for uuid, watch in self.datastore.data['watching'].items():
-            # Watch tags by name (replace the other calls?)
-            tags = self.datastore.get_all_tags_for_watch(uuid=uuid)
-            if tag_limit and not any(v.get('title').lower() == tag_limit for k, v in tags.items()):
-                continue
-
-            list[uuid] = {
-                'last_changed': watch.last_changed,
-                'last_checked': watch['last_checked'],
-                'last_error': watch['last_error'],
-                'title': watch['title'],
-                'url': watch['url'],
-                'viewed': watch.viewed
-            }
-
-        if request.args.get('recheck_all'):
-            for uuid in self.datastore.data['watching'].keys():
-                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-            return {'status': "OK"}, 200
-
-        return list, 200

changedetectionio/api/__init__.py

@@ -1,33 +0,0 @@
-import copy
-from . import api_schema
-from ..model import watch_base
-
-# Build a JSON Schema atleast partially based on our Watch model
-watch_base_config = watch_base()
-schema = api_schema.build_watch_json_schema(watch_base_config)
-
-schema_create_watch = copy.deepcopy(schema)
-schema_create_watch['required'] = ['url']
-
-schema_update_watch = copy.deepcopy(schema)
-schema_update_watch['additionalProperties'] = False
-
-# Tag schema is also based on watch_base since Tag inherits from it
-schema_tag = copy.deepcopy(schema)
-schema_create_tag = copy.deepcopy(schema_tag)
-schema_create_tag['required'] = ['title']
-schema_update_tag = copy.deepcopy(schema_tag)
-schema_update_tag['additionalProperties'] = False
-
-schema_notification_urls = copy.deepcopy(schema)
-schema_create_notification_urls = copy.deepcopy(schema_notification_urls)
-schema_create_notification_urls['required'] = ['notification_urls']
-schema_delete_notification_urls = copy.deepcopy(schema_notification_urls)
-schema_delete_notification_urls['required'] = ['notification_urls']
-
-# Import all API resources
-from .Watch import Watch, WatchHistory, WatchSingleHistory, CreateWatch
-from .Tags import Tags, Tag
-from .Import import Import
-from .SystemInfo import SystemInfo
-from .Notifications import Notifications

changedetectionio/api/api_schema.py

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

changedetectionio/api/auth.py

@@ -1,25 +0,0 @@
-from flask import request, make_response, jsonify
-from functools import wraps
-
-
-# Simple API auth key comparison
-# @todo - Maybe short lived token in the future?
-
-def check_token(f):
-    @wraps(f)
-    def decorated(*args, **kwargs):
-        datastore = args[0].datastore
-
-        config_api_token_enabled = datastore.data['settings']['application'].get('api_access_token_enabled')
-        config_api_token = datastore.data['settings']['application'].get('api_access_token')
-
-        # config_api_token_enabled - a UI option in settings if access should obey the key or not
-        if config_api_token_enabled:
-            if request.headers.get('x-api-key') != config_api_token:
-                return make_response(
-                    jsonify("Invalid access - API key invalid."), 403
-                )
-
-        return f(*args, **kwargs)
-
-    return decorated

changedetectionio/auth_decorator.py

@@ -1,33 +0,0 @@
-import os
-from functools import wraps
-from flask import current_app, redirect, request
-from loguru import logger
-
-def login_optionally_required(func):
-    """
-    If password authentication is enabled, verify the user is logged in.
-    To be used as a decorator for routes that should optionally require login.
-    This version is blueprint-friendly as it uses current_app instead of directly accessing app.
-    """
-    @wraps(func)
-    def decorated_view(*args, **kwargs):
-        from flask import current_app
-        import flask_login
-        from flask_login import current_user
-
-        # Access datastore through the app config
-        datastore = current_app.config['DATASTORE']
-        has_password_enabled = datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False)
-
-        # Permitted
-        if request.endpoint and 'diff_history_page' in request.endpoint and datastore.data['settings']['application'].get('shared_diff_access'):
-            return func(*args, **kwargs)
-        elif request.method in flask_login.config.EXEMPT_METHODS:
-            return func(*args, **kwargs)
-        elif current_app.config.get('LOGIN_DISABLED'):
-            return func(*args, **kwargs)
-        elif has_password_enabled and not current_user.is_authenticated:
-            return current_app.login_manager.unauthorized()
-
-        return func(*args, **kwargs)
-    return decorated_view

changedetectionio/blueprint/backups/__init__.py

@@ -1,164 +0,0 @@
-import datetime
-import glob
-import threading
-
-from flask import Blueprint, render_template, send_from_directory, flash, url_for, redirect, abort
-import os
-
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio.flask_app import login_optionally_required
-from loguru import logger
-
-BACKUP_FILENAME_FORMAT = "changedetection-backup-{}.zip"
-
-
-def create_backup(datastore_path, watches: dict):
-    logger.debug("Creating backup...")
-    import zipfile
-    from pathlib import Path
-
-    # create a ZipFile object
-    timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
-    backupname = BACKUP_FILENAME_FORMAT.format(timestamp)
-    backup_filepath = os.path.join(datastore_path, backupname)
-
-    with zipfile.ZipFile(backup_filepath.replace('.zip', '.tmp'), "w",
-                         compression=zipfile.ZIP_DEFLATED,
-                         compresslevel=8) as zipObj:
-
-        # Add the index
-        zipObj.write(os.path.join(datastore_path, "url-watches.json"), arcname="url-watches.json")
-
-        # Add the flask app secret
-        zipObj.write(os.path.join(datastore_path, "secret.txt"), arcname="secret.txt")
-
-        # Add any data in the watch data directory.
-        for uuid, w in watches.items():
-            for f in Path(w.watch_data_dir).glob('*'):
-                zipObj.write(f,
-                             # Use the full path to access the file, but make the file 'relative' in the Zip.
-                             arcname=os.path.join(f.parts[-2], f.parts[-1]),
-                             compress_type=zipfile.ZIP_DEFLATED,
-                             compresslevel=8)
-
-        # Create a list file with just the URLs, so it's easier to port somewhere else in the future
-        list_file = "url-list.txt"
-        with open(os.path.join(datastore_path, list_file), "w") as f:
-            for uuid in watches:
-                url = watches[uuid]["url"]
-                f.write("{}\r\n".format(url))
-        list_with_tags_file = "url-list-with-tags.txt"
-        with open(
-                os.path.join(datastore_path, list_with_tags_file), "w"
-        ) as f:
-            for uuid in watches:
-                url = watches[uuid].get('url')
-                tag = watches[uuid].get('tags', {})
-                f.write("{} {}\r\n".format(url, tag))
-
-        # Add it to the Zip
-        zipObj.write(
-            os.path.join(datastore_path, list_file),
-            arcname=list_file,
-            compress_type=zipfile.ZIP_DEFLATED,
-            compresslevel=8,
-        )
-        zipObj.write(
-            os.path.join(datastore_path, list_with_tags_file),
-            arcname=list_with_tags_file,
-            compress_type=zipfile.ZIP_DEFLATED,
-            compresslevel=8,
-        )
-
-    # Now it's done, rename it so it shows up finally and its completed being written.
-    os.rename(backup_filepath.replace('.zip', '.tmp'), backup_filepath.replace('.tmp', '.zip'))
-
-
-def construct_blueprint(datastore: ChangeDetectionStore):
-    backups_blueprint = Blueprint('backups', __name__, template_folder="templates")
-    backup_threads = []
-
-    @login_optionally_required
-    @backups_blueprint.route("/request-backup", methods=['GET'])
-    def request_backup():
-        if any(thread.is_alive() for thread in backup_threads):
-            flash("A backup is already running, check back in a few minutes", "error")
-            return redirect(url_for('backups.index'))
-
-        if len(find_backups()) > int(os.getenv("MAX_NUMBER_BACKUPS", 100)):
-            flash("Maximum number of backups reached, please remove some", "error")
-            return redirect(url_for('backups.index'))
-
-        # Be sure we're written fresh
-        datastore.sync_to_json()
-        zip_thread = threading.Thread(target=create_backup, args=(datastore.datastore_path, datastore.data.get("watching")))
-        zip_thread.start()
-        backup_threads.append(zip_thread)
-        flash("Backup building in background, check back in a few minutes.")
-
-        return redirect(url_for('backups.index'))
-
-    def find_backups():
-        backup_filepath = os.path.join(datastore.datastore_path, BACKUP_FILENAME_FORMAT.format("*"))
-        backups = glob.glob(backup_filepath)
-        backup_info = []
-
-        for backup in backups:
-            size = os.path.getsize(backup) / (1024 * 1024)
-            creation_time = os.path.getctime(backup)
-            backup_info.append({
-                'filename': os.path.basename(backup),
-                'filesize': f"{size:.2f}",
-                'creation_time': creation_time
-            })
-
-        backup_info.sort(key=lambda x: x['creation_time'], reverse=True)
-
-        return backup_info
-
-    @login_optionally_required
-    @backups_blueprint.route("/download/<string:filename>", methods=['GET'])
-    def download_backup(filename):
-        import re
-        filename = filename.strip()
-        backup_filename_regex = BACKUP_FILENAME_FORMAT.format("\d+")
-
-        full_path = os.path.join(os.path.abspath(datastore.datastore_path), filename)
-        if not full_path.startswith(os.path.abspath(datastore.datastore_path)):
-            abort(404)
-
-        if filename == 'latest':
-            backups = find_backups()
-            filename = backups[0]['filename']
-
-        if not re.match(r"^" + backup_filename_regex + "$", filename):
-            abort(400)  # Bad Request if the filename doesn't match the pattern
-
-        logger.debug(f"Backup download request for '{full_path}'")
-        return send_from_directory(os.path.abspath(datastore.datastore_path), filename, as_attachment=True)
-
-    @login_optionally_required
-    @backups_blueprint.route("", methods=['GET'])
-    def index():
-        backups = find_backups()
-        output = render_template("overview.html",
-                                 available_backups=backups,
-                                 backup_running=any(thread.is_alive() for thread in backup_threads)
-                                 )
-
-        return output
-
-    @login_optionally_required
-    @backups_blueprint.route("/remove-backups", methods=['GET'])
-    def remove_backups():
-
-        backup_filepath = os.path.join(datastore.datastore_path, BACKUP_FILENAME_FORMAT.format("*"))
-        backups = glob.glob(backup_filepath)
-        for backup in backups:
-            os.unlink(backup)
-
-        flash("Backups were deleted.")
-
-        return redirect(url_for('backups.index'))
-
-    return backups_blueprint

changedetectionio/blueprint/backups/templates/overview.html

@@ -1,36 +0,0 @@
-{% extends 'base.html' %}
-{% block content %}
-    {% from '_helpers.html' import render_simple_field, render_field %}
-    <div class="edit-form">
-        <div class="box-wrap inner">
-            <h4>Backups</h4>
-            {% if backup_running %}
-                <p>
-                    <strong>A backup is running!</strong>
-                </p>
-            {% endif %}
-            <p>
-                Here you can download and request a new backup, when a backup is completed you will see it listed below.
-            </p>
-            <br>
-                {% if available_backups %}
-                    <ul>
-                    {% for backup in available_backups %}
-                        <li><a href="{{ url_for('backups.download_backup', filename=backup["filename"]) }}">{{ backup["filename"] }}</a> {{  backup["filesize"] }} Mb</li>
-                    {% endfor %}
-                    </ul>
-                {% else %}
-                    <p>
-                    <strong>No backups found.</strong>
-                    </p>
-                {% endif %}
-
-            <a class="pure-button pure-button-primary" href="{{ url_for('backups.request_backup') }}">Create backup</a>
-            {% if available_backups %}
-                <a class="pure-button button-small button-error " href="{{ url_for('backups.remove_backups') }}">Remove backups</a>
-            {% endif %}
-        </div>
-    </div>
-
-
-{% endblock %}

changedetectionio/blueprint/browser_steps/TODO.txt

@@ -1,7 +0,0 @@
-- 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

@@ -1,222 +0,0 @@
-
-# HORRIBLE HACK BUT WORKS :-) PR anyone?
-#
-# Why?
-# `browsersteps_playwright_browser_interface.chromium.connect_over_cdp()` will only run once without async()
-# - this flask app is not async()
-# - 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)
-#
-#
-
-from changedetectionio.strtobool import strtobool
-from flask import Blueprint, request, make_response
-import os
-
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio.flask_app import login_optionally_required
-from loguru import logger
-
-browsersteps_sessions = {}
-io_interface_context = None
-import json
-import hashlib
-from flask import Response
-
-def construct_blueprint(datastore: ChangeDetectionStore):
-    browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
-
-    def start_browsersteps_session(watch_uuid):
-        from . import nonContext
-        from . import browser_steps
-        import time
-        global io_interface_context
-
-        # We keep the playwright session open for many minutes
-        keepalive_seconds = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
-
-        browsersteps_start_session = {'start_time': time.time()}
-
-        # You can only have one of these running
-        # This should be very fine to leave running for the life of the application
-        # @idea - Make it global so the pool of watch fetchers can use it also
-        if not io_interface_context:
-            io_interface_context = nonContext.c_sync_playwright()
-            # Start the Playwright context, which is actually a nodejs sub-process and communicates over STDIN/STDOUT pipes
-            io_interface_context = io_interface_context.start()
-
-        keepalive_ms = ((keepalive_seconds + 3) * 1000)
-        base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '').strip('"')
-        a = "?" if not '?' in base_url else '&'
-        base_url += a + f"timeout={keepalive_ms}"
-
-        try:
-            browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(base_url)
-        except Exception as e:
-            if 'ECONNREFUSED' in str(e):
-                return make_response('Unable to start the Playwright Browser session, is it running?', 401)
-            else:
-                # Other errors, bad URL syntax, bad reply etc
-                return make_response(str(e), 401)
-
-        proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
-        proxy = None
-        if proxy_id:
-            proxy_url = datastore.proxy_list.get(proxy_id).get('url')
-            if proxy_url:
-
-                # Playwright needs separate username and password values
-                from urllib.parse import urlparse
-                parsed = urlparse(proxy_url)
-                proxy = {'server': proxy_url}
-
-                if parsed.username:
-                    proxy['username'] = parsed.username
-
-                if parsed.password:
-                    proxy['password'] = parsed.password
-
-                logger.debug(f"Browser Steps: UUID {watch_uuid} selected proxy {proxy_url}")
-
-        # Tell Playwright to connect to Chrome and setup a new session via our stepper interface
-        browsersteps_start_session['browserstepper'] = browser_steps.browsersteps_live_ui(
-            playwright_browser=browsersteps_start_session['browser'],
-            proxy=proxy,
-            start_url=datastore.data['watching'][watch_uuid].link,
-            headers=datastore.data['watching'][watch_uuid].get('headers')
-        )
-
-        # For test
-        #browsersteps_start_session['browserstepper'].action_goto_url(value="http://example.com?time="+str(time.time()))
-
-        return browsersteps_start_session
-
-
-    @login_optionally_required
-    @browser_steps_blueprint.route("/browsersteps_start_session", methods=['GET'])
-    def browsersteps_start_session():
-        # A new session was requested, return sessionID
-
-        import uuid
-        browsersteps_session_id = str(uuid.uuid4())
-        watch_uuid = request.args.get('uuid')
-
-        if not watch_uuid:
-            return make_response('No Watch UUID specified', 500)
-
-        logger.debug("Starting connection with playwright")
-        logger.debug("browser_steps.py connecting")
-        browsersteps_sessions[browsersteps_session_id] = start_browsersteps_session(watch_uuid)
-        logger.debug("Starting connection with playwright - done")
-        return {'browsersteps_session_id': browsersteps_session_id}
-
-    @login_optionally_required
-    @browser_steps_blueprint.route("/browsersteps_image", methods=['GET'])
-    def browser_steps_fetch_screenshot_image():
-        from flask import (
-            make_response,
-            request,
-            send_from_directory,
-        )
-        uuid = request.args.get('uuid')
-        step_n = int(request.args.get('step_n'))
-
-        watch = datastore.data['watching'].get(uuid)
-        filename = f"step_before-{step_n}.jpeg" if request.args.get('type', '') == 'before' else f"step_{step_n}.jpeg"
-
-        if step_n and watch and os.path.isfile(os.path.join(watch.watch_data_dir, filename)):
-            response = make_response(send_from_directory(directory=watch.watch_data_dir, path=filename))
-            response.headers['Content-type'] = 'image/jpeg'
-            response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
-            response.headers['Pragma'] = 'no-cache'
-            response.headers['Expires'] = 0
-            return response
-
-        else:
-            return make_response('Unable to fetch image, is the URL correct? does the watch exist? does the step_type-n.jpeg exist?', 401)
-
-    # A request for an action was received
-    @login_optionally_required
-    @browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
-    def browsersteps_ui_update():
-        import base64
-        import playwright._impl._errors
-        from changedetectionio.blueprint.browser_steps import browser_steps
-
-        remaining =0
-        uuid = request.args.get('uuid')
-
-        browsersteps_session_id = request.args.get('browsersteps_session_id')
-
-        if not browsersteps_session_id:
-            return make_response('No browsersteps_session_id specified', 500)
-
-        if not browsersteps_sessions.get(browsersteps_session_id):
-            return make_response('No session exists under that ID', 500)
-
-        is_last_step = False
-        # Actions - step/apply/etc, do the thing and return state
-        if request.method == 'POST':
-            # @todo - should always be an existing session
-            step_operation = request.form.get('operation')
-            step_selector = request.form.get('selector')
-            step_optional_value = request.form.get('optional_value')
-            is_last_step = strtobool(request.form.get('is_last_step'))
-
-            # @todo try.. accept.. nice errors not popups..
-            try:
-
-                browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(action_name=step_operation,
-                                         selector=step_selector,
-                                         optional_value=step_optional_value)
-
-            except Exception as e:
-                logger.error(f"Exception when calling step operation {step_operation} {str(e)}")
-                # Try to find something of value to give back to the user
-                return make_response(str(e).splitlines()[0], 401)
-
-
-#        if not this_session.page:
-#            cleanup_playwright_session()
-#            return make_response('Browser session ran out of time :( Please reload this page.', 401)
-
-        # Screenshots and other info only needed on requesting a step (POST)
-        try:
-            (screenshot, xpath_data) = browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
-            if is_last_step:
-                watch = datastore.data['watching'].get(uuid)
-                u = browsersteps_sessions[browsersteps_session_id]['browserstepper'].page.url
-                if watch and u:
-                    watch.save_screenshot(screenshot=screenshot)
-                    watch.save_xpath_data(data=xpath_data)
-
-        except playwright._impl._api_types.Error as e:
-            return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
-        except Exception as e:
-            return make_response("Error fetching screenshot and element data - " + str(e), 401)
-
-        # SEND THIS BACK TO THE BROWSER
-
-        output = {
-            "screenshot": f"data:image/jpeg;base64,{base64.b64encode(screenshot).decode('ascii')}",
-            "xpath_data": xpath_data,
-            "session_age_start": browsersteps_sessions[browsersteps_session_id]['browserstepper'].age_start,
-            "browser_time_remaining": round(remaining)
-        }
-        json_data = json.dumps(output)
-
-        # Generate an ETag (hash of the response body)
-        etag_hash = hashlib.md5(json_data.encode('utf-8')).hexdigest()
-
-        # Create the response with ETag
-        response = Response(json_data, mimetype="application/json; charset=UTF-8")
-        response.set_etag(etag_hash)
-
-        return response
-
-    return browser_steps_blueprint
-
-

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -1,332 +0,0 @@
-import os
-import time
-import re
-from random import randint
-from loguru import logger
-
-from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT
-from changedetectionio.content_fetchers.base import manage_user_agent
-from changedetectionio.safe_jinja import render as jinja_render
-
-
-
-# Two flags, tell the JS which of the "Selector" or "Value" field should be enabled in the front end
-# 0- off, 1- on
-browser_step_ui_config = {'Choose one': '0 0',
-                          #                 'Check checkbox': '1 0',
-                          #                 'Click button containing text': '0 1',
-                          #                 'Scroll to bottom': '0 0',
-                          #                 'Scroll to element': '1 0',
-                          #                 'Scroll to top': '0 0',
-                          #                 'Switch to iFrame by index number': '0 1'
-                          #                 'Uncheck checkbox': '1 0',
-                          # @todo
-                          'Check checkbox': '1 0',
-                          'Click X,Y': '0 1',
-                          'Click element if exists': '1 0',
-                          'Click element': '1 0',
-                          'Click element containing text': '0 1',
-                          'Click element containing text if exists': '0 1',
-                          'Enter text in field': '1 1',
-                          'Execute JS': '0 1',
-#                          'Extract text and use as filter': '1 0',
-                          'Goto site': '0 0',
-                          'Goto URL': '0 1',
-                          'Make all child elements visible': '1 0',
-                          'Press Enter': '0 0',
-                          'Select by label': '1 1',
-                          'Scroll down': '0 0',
-                          'Uncheck checkbox': '1 0',
-                          'Wait for seconds': '0 1',
-                          'Wait for text': '0 1',
-                          'Wait for text in element': '1 1',
-                          'Remove elements': '1 0',
-                          #                          'Press Page Down': '0 0',
-                          #                          'Press Page Up': '0 0',
-                          # weird bug, come back to it later
-                          }
-
-
-# Good reference - https://playwright.dev/python/docs/input
-#                  https://pythonmana.com/2021/12/202112162236307035.html
-#
-# ONLY Works in Playwright because we need the fullscreen screenshot
-class steppable_browser_interface():
-    page = None
-    start_url = None
-
-    action_timeout = 10 * 1000
-
-    def __init__(self, start_url):
-        self.start_url = start_url
-
-    # Convert and perform "Click Button" for example
-    def call_action(self, action_name, selector=None, optional_value=None):
-        now = time.time()
-        call_action_name = re.sub('[^0-9a-zA-Z]+', '_', action_name.lower())
-        if call_action_name == 'choose_one':
-            return
-
-        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
-
-        action_handler = getattr(self, "action_" + call_action_name)
-
-        # Support for Jinja2 variables in the value and selector
-
-        if selector and ('{%' in selector or '{{' in selector):
-            selector = jinja_render(template_str=selector)
-
-        if optional_value and ('{%' in optional_value or '{{' in optional_value):
-            optional_value = jinja_render(template_str=optional_value)
-
-        action_handler(selector, optional_value)
-        self.page.wait_for_timeout(1.5 * 1000)
-        logger.debug(f"Call action done in {time.time()-now:.2f}s")
-
-    def action_goto_url(self, 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='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
-
-    # Incase they request to go back to the start
-    def action_goto_site(self, selector=None, value=None):
-        return self.action_goto_url(value=self.start_url)
-
-    def action_click_element_containing_text(self, selector=None, value=''):
-        logger.debug("Clicking element containing text")
-        if not len(value.strip()):
-            return
-        elem = self.page.get_by_text(value)
-        if elem.count():
-            elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
-
-    def action_click_element_containing_text_if_exists(self, selector=None, value=''):
-        logger.debug("Clicking element containing text if exists")
-        if not len(value.strip()):
-            return
-        elem = self.page.get_by_text(value)
-        logger.debug(f"Clicking element containing text - {elem.count()} elements found")
-        if elem.count():
-            elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
-        else:
-            return
-
-    def action_enter_text_in_field(self, selector, value):
-        if not len(selector.strip()):
-            return
-
-        self.page.fill(selector, value, timeout=self.action_timeout)
-
-    def action_execute_js(self, selector, value):
-        response = self.page.evaluate(value)
-        return response
-
-    def action_click_element(self, selector, value):
-        logger.debug("Clicking element")
-        if not len(selector.strip()):
-            return
-
-        self.page.click(selector=selector, timeout=self.action_timeout + 20 * 1000, delay=randint(200, 500))
-
-    def action_click_element_if_exists(self, selector, value):
-        import playwright._impl._errors as _api_types
-        logger.debug("Clicking element if exists")
-        if not len(selector.strip()):
-            return
-        try:
-            self.page.click(selector, timeout=self.action_timeout, delay=randint(200, 500))
-        except _api_types.TimeoutError as e:
-            return
-        except _api_types.Error as e:
-            # Element was there, but page redrew and now its long long gone
-            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()))
-        self.page.mouse.click(x=x, y=y, delay=randint(200, 500))
-
-    def action_scroll_down(self, selector, value):
-        # Some sites this doesnt work on for some reason
-        self.page.mouse.wheel(0, 600)
-        self.page.wait_for_timeout(1000)
-
-    def action_wait_for_seconds(self, selector, value):
-        self.page.wait_for_timeout(float(value.strip()) * 1000)
-
-    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=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=30000)
-
-    # @todo - in the future make some popout interface to capture what needs to be set
-    # https://playwright.dev/python/docs/api/class-keyboard
-    def action_press_enter(self, selector, value):
-        self.page.keyboard.press("Enter", delay=randint(200, 500))
-
-    def action_press_page_up(self, selector, value):
-        self.page.keyboard.press("PageUp", delay=randint(200, 500))
-
-    def action_press_page_down(self, selector, value):
-        self.page.keyboard.press("PageDown", delay=randint(200, 500))
-
-    def action_check_checkbox(self, selector, value):
-        self.page.locator(selector).check(timeout=self.action_timeout)
-
-    def action_uncheck_checkbox(self, selector, value):
-        self.page.locator(selector).uncheck(timeout=self.action_timeout)
-
-    def action_remove_elements(self, selector, value):
-        """Removes all elements matching the given selector from the DOM."""
-        self.page.locator(selector).evaluate_all("els => els.forEach(el => el.remove())")
-
-    def action_make_all_child_elements_visible(self, selector, value):
-        """Recursively makes all child elements inside the given selector fully visible."""
-        self.page.locator(selector).locator("*").evaluate_all("""
-            els => els.forEach(el => {
-                el.style.display = 'block';   // Forces it to be displayed
-                el.style.visibility = 'visible';   // Ensures it's not hidden
-                el.style.opacity = '1';   // Fully opaque
-                el.style.position = 'relative';   // Avoids 'absolute' hiding
-                el.style.height = 'auto';   // Expands collapsed elements
-                el.style.width = 'auto';   // Ensures full visibility
-                el.removeAttribute('hidden');   // Removes hidden attribute
-                el.classList.remove('hidden', 'd-none');  // Removes common CSS hidden classes
-            })
-        """)
-
-# Responsible for maintaining a live 'context' with the chrome CDP
-# @todo - how long do contexts live for anyway?
-class browsersteps_live_ui(steppable_browser_interface):
-    context = None
-    page = None
-    render_extra_delay = 1
-    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(
-        "PLAYWRIGHT_BROWSERSTEPS_DRIVER_URL"
-    )
-    # if not..
-    if not command_executor:
-        command_executor = os.getenv(
-            "PLAYWRIGHT_DRIVER_URL",
-            'ws://playwright-chrome:3000'
-        ).strip('"')
-
-    browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
-
-    def __init__(self, playwright_browser, proxy=None, headers=None, start_url=None):
-        self.headers = headers or {}
-        self.age_start = time.time()
-        self.playwright_browser = playwright_browser
-        self.start_url = start_url
-        if self.context is None:
-            self.connect(proxy=proxy)
-
-    # Connect and setup a new context
-    def connect(self, proxy=None):
-        # Should only get called once - test that
-        keep_open = 1000 * 60 * 5
-        now = time.time()
-
-        # @todo handle multiple contexts, bind a unique id from the browser on each req?
-        self.context = self.playwright_browser.new_context(
-            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)
-        self.page.set_default_timeout(keep_open)
-        # @todo probably this doesnt work
-        self.page.on(
-            "close",
-            self.mark_as_closed,
-        )
-        # 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}"))
-
-        logger.debug(f"Time to browser setup {time.time()-now:.2f}s")
-        self.page.wait_for_timeout(1 * 1000)
-
-
-    def mark_as_closed(self):
-        logger.debug("Page closed, cleaning up..")
-
-    @property
-    def has_expired(self):
-        if not self.page:
-            return True
-
-
-    def get_current_state(self):
-        """Return the screenshot and interactive elements mapping, generally always called after action_()"""
-        import importlib.resources
-        import json
-        # because we for now only run browser steps in playwright mode (not puppeteer mode)
-        from changedetectionio.content_fetchers.playwright import capture_full_page
-
-        xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text()
-
-        now = time.time()
-        self.page.wait_for_timeout(1 * 1000)
-
-        screenshot = capture_full_page(page=self.page)
-
-        logger.debug(f"Time to get screenshot from browser {time.time() - now:.2f}s")
-
-        now = time.time()
-        self.page.evaluate("var include_filters=''")
-        # Go find the interactive elements
-        # @todo in the future, something smarter that can scan for elements with .click/focus etc event handlers?
-
-        self.page.request_gc()
-
-        scan_elements = 'a,button,input,select,textarea,i,th,td,p,li,h1,h2,h3,h4,div,span'
-
-        MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
-        xpath_data = json.loads(self.page.evaluate(xpath_element_js, {
-            "visualselector_xpath_selectors": scan_elements,
-            "max_height": MAX_TOTAL_HEIGHT
-        }))
-        self.page.request_gc()
-
-        # 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)
-        logger.debug(f"Time to scrape xPath element data in browser {time.time()-now:.2f}s")
-
-        # playwright._impl._api_types.Error: Browser closed.
-        # @todo show some countdown timer?
-        return (screenshot, xpath_data)
-

changedetectionio/blueprint/browser_steps/nonContext.py

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

changedetectionio/blueprint/check_proxies/__init__.py

@@ -1,124 +0,0 @@
-import importlib
-from concurrent.futures import ThreadPoolExecutor
-
-from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
-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.safe_jinja import render as jinja_render
-
-        status = {'status': '', 'length': 0, 'text': ''}
-
-        contents = ''
-        now = time.time()
-        try:
-            processor_module = importlib.import_module("changedetectionio.processors.text_json_diff.processor")
-            update_handler = processor_module.perform_site_check(datastore=datastore,
-                                                                 watch_uuid=uuid
-                                                                 )
-
-            update_handler.call_browser(preferred_proxy_id=preferred_proxy)
-        # 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 FilterNotFoundInResponse:
-            status.update({'status': 'OK', 'length': len(contents), 'text': f"OK but CSS/xPath filter not found (page changed layout?)"})
-        except content_fetcher_exceptions.EmptyReply as e:
-            if e.status_code == 403 or e.status_code == 401:
-                status.update({'status': 'ERROR OTHER', 'length': len(contents), 'text': f"Got empty reply with code {e.status_code} - Access denied"})
-            else:
-                status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': f"Empty reply with code {e.status_code}, needs chrome?"})
-        except content_fetcher_exceptions.ReplyWithContentButNoText as e:
-            txt = f"Got reply but with no content - Status code {e.status_code} - It's possible that the filters were found, but contained no usable text (or contained only an image)."
-            status.update({'status': 'ERROR', 'text': txt})
-        except Exception as e:
-            status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': 'Error: '+type(e).__name__+str(e)})
-        else:
-            status.update({'status': 'OK', 'length': len(contents), 'text': ''})
-
-        if status.get('text'):
-            # parse 'text' as text for safety
-            v = {'text': status['text']}
-            status['text'] = jinja_render(template_str='{{text|e}}', **v)
-
-        status['time'] = "{:.2f}s".format(time.time() - now)
-
-        return status
-
-    def _recalc_check_status(uuid):
-
-        results = {}
-        for k, v in checks_in_progress.get(uuid, {}).items():
-            try:
-                r_1 = v.result(timeout=0.05)
-            except Exception as e:
-                # If timeout error?
-                results[k] = {'status': 'RUNNING'}
-
-            else:
-                results[k] = r_1
-
-        return results
-
-    @login_required
-    @check_proxies_blueprint.route("/<string:uuid>/status", methods=['GET'])
-    def get_recheck_status(uuid):
-        results = _recalc_check_status(uuid=uuid)
-        return results
-
-    @login_required
-    @check_proxies_blueprint.route("/<string:uuid>/start", methods=['GET'])
-    def start_check(uuid):
-
-        if not datastore.proxy_list:
-            return
-
-        if checks_in_progress.get(uuid):
-            state = _recalc_check_status(uuid=uuid)
-            for proxy_key, v in state.items():
-                if v.get('status') == 'RUNNING':
-                    return state
-        else:
-            checks_in_progress[uuid] = {}
-
-        for k, v in datastore.proxy_list.items():
-            if not checks_in_progress[uuid].get(k):
-                checks_in_progress[uuid][k] = long_task(uuid=uuid, preferred_proxy=k)
-
-        results = _recalc_check_status(uuid=uuid)
-        return results
-
-    return check_proxies_blueprint

changedetectionio/blueprint/imports/__init__.py

@@ -1,74 +0,0 @@
-from flask import Blueprint, request, redirect, url_for, flash, render_template
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio.auth_decorator import login_optionally_required
-from changedetectionio.blueprint.imports.importer import (
-    import_url_list, 
-    import_distill_io_json, 
-    import_xlsx_wachete, 
-    import_xlsx_custom
-)
-
-def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
-    import_blueprint = Blueprint('imports', __name__, template_folder="templates")
-    
-    @import_blueprint.route("/import", methods=['GET', 'POST'])
-    @login_optionally_required
-    def import_page():
-        remaining_urls = []
-        from changedetectionio import forms
-
-        if request.method == 'POST':
-            # URL List import
-            if request.values.get('urls') and len(request.values.get('urls').strip()):
-                # Import and push into the queue for immediate update check
-                importer_handler = import_url_list()
-                importer_handler.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', 'text_json_diff'))
-                for uuid in importer_handler.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-
-                if len(importer_handler.remaining_data) == 0:
-                    return redirect(url_for('watchlist.index'))
-                else:
-                    remaining_urls = importer_handler.remaining_data
-
-            # Distill.io import
-            if request.values.get('distill-io') and len(request.values.get('distill-io').strip()):
-                # Import and push into the queue for immediate update check
-                d_importer = import_distill_io_json()
-                d_importer.run(data=request.values.get('distill-io'), flash=flash, datastore=datastore)
-                for uuid in d_importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-
-            # XLSX importer
-            if request.files and request.files.get('xlsx_file'):
-                file = request.files['xlsx_file']
-
-                if request.values.get('file_mapping') == 'wachete':
-                    w_importer = import_xlsx_wachete()
-                    w_importer.run(data=file, flash=flash, datastore=datastore)
-                else:
-                    w_importer = import_xlsx_custom()
-                    # Building mapping of col # to col # type
-                    map = {}
-                    for i in range(10):
-                        c = request.values.get(f"custom_xlsx[col_{i}]")
-                        v = request.values.get(f"custom_xlsx[col_type_{i}]")
-                        if c and v:
-                            map[int(c)] = v
-
-                    w_importer.import_profile = map
-                    w_importer.run(data=file, flash=flash, datastore=datastore)
-
-                for uuid in w_importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-
-        # Could be some remaining, or we could be on GET
-        form = forms.importForm(formdata=request.form if request.method == 'POST' else None)
-        output = render_template("import.html",
-                                form=form,
-                                import_url_list_remaining="\n".join(remaining_urls),
-                                original_distill_json=''
-                                )
-        return output
-
-    return import_blueprint

changedetectionio/blueprint/imports/importer.py

@@ -1,302 +0,0 @@
-from abc import abstractmethod
-import time
-from wtforms import ValidationError
-from loguru import logger
-
-from changedetectionio.forms import validate_url
-
-
-class Importer():
-    remaining_data = []
-    new_uuids = []
-    good = 0
-
-    def __init__(self):
-        self.new_uuids = []
-        self.good = 0
-        self.remaining_data = []
-        self.import_profile = None
-
-    @abstractmethod
-    def run(self,
-            data,
-            flash,
-            datastore):
-        pass
-
-
-class import_url_list(Importer):
-    """
-    Imports a list, can be in <code>https://example.com tag1, tag2, last tag</code> format
-    """
-    def run(self,
-            data,
-            flash,
-            datastore,
-            processor=None
-            ):
-
-        urls = data.split("\n")
-        good = 0
-        now = time.time()
-
-        if (len(urls) > 5000):
-            flash("Importing 5,000 of the first URLs from your list, the rest can be imported again.")
-
-        for url in urls:
-            url = url.strip()
-            if not len(url):
-                continue
-
-            tags = ""
-
-            # 'tags' should be a csv list after the URL
-            if ' ' in url:
-                url, tags = url.split(" ", 1)
-
-            # 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 will fail when you add your own IP etc
-            if len(url) and 'http' in url.lower() and good < 5000:
-                extras = None
-                if processor:
-                    extras = {'processor': processor}
-                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False, extras=extras)
-
-                if new_uuid:
-                    # Straight into the queue.
-                    self.new_uuids.append(new_uuid)
-                    good += 1
-                    continue
-
-            # Worked past the 'continue' above, append it to the bad list
-            if self.remaining_data is None:
-                self.remaining_data = []
-            self.remaining_data.append(url)
-
-        flash("{} Imported from list in {:.2f}s, {} Skipped.".format(good, time.time() - now, len(self.remaining_data)))
-
-
-class import_distill_io_json(Importer):
-    def run(self,
-            data,
-            flash,
-            datastore,
-            ):
-
-        import json
-        good = 0
-        now = time.time()
-        self.new_uuids=[]
-
-        # @todo Use JSONSchema like in the API to validate here.
-        
-        try:
-            data = json.loads(data.strip())
-        except json.decoder.JSONDecodeError:
-            flash("Unable to read JSON file, was it broken?", 'error')
-            return
-
-        if not data.get('data'):
-            flash("JSON structure looks invalid, was it broken?", 'error')
-            return
-
-        for d in data.get('data'):
-            d_config = json.loads(d['config'])
-            extras = {'title': d.get('name', None)}
-
-            if len(d['uri']) and good < 5000:
-                try:
-                    # @todo we only support CSS ones at the moment
-                    if d_config['selections'][0]['frames'][0]['excludes'][0]['type'] == 'css':
-                        extras['subtractive_selectors'] = d_config['selections'][0]['frames'][0]['excludes'][0]['expr']
-                except KeyError:
-                    pass
-                except IndexError:
-                    pass
-                extras['include_filters'] = []
-                try:
-                    if d_config['selections'][0]['frames'][0]['includes'][0]['type'] == 'xpath':
-                        extras['include_filters'].append('xpath:' + d_config['selections'][0]['frames'][0]['includes'][0]['expr'])
-                    else:
-                        extras['include_filters'].append(d_config['selections'][0]['frames'][0]['includes'][0]['expr'])
-                except KeyError:
-                    pass
-                except IndexError:
-                    pass
-
-                new_uuid = datastore.add_watch(url=d['uri'].strip(),
-                                               tag=",".join(d.get('tags', [])),
-                                               extras=extras,
-                                               write_to_disk_now=False)
-
-                if new_uuid:
-                    # Straight into the queue.
-                    self.new_uuids.append(new_uuid)
-                    good += 1
-
-        flash("{} Imported from Distill.io in {:.2f}s, {} Skipped.".format(len(self.new_uuids), time.time() - now, len(self.remaining_data)))
-
-
-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 changedetectionio.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/blueprint/imports/templates/import.html

@@ -1,123 +0,0 @@
-{% extends 'base.html' %}
-{% block content %}
-{% from '_helpers.html' import render_field %}
-<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
-<div class="edit-form monospaced-textarea">
-
-    <div class="tabs collapsable">
-        <ul>
-            <li class="tab" id=""><a href="#url-list">URL List</a></li>
-            <li class="tab"><a href="#distill-io">Distill.io</a></li>
-            <li class="tab"><a href="#xlsx">.XLSX &amp; Wachete</a></li>
-        </ul>
-    </div>
-
-    <div class="box-wrap inner">
-        <form class="pure-form" action="{{url_for('imports.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">
-                <div class="pure-control-group">
-                        Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma
-                        (,):
-                        <br>
-                        <p><strong>Example:  </strong><code>https://example.com tag1, tag2, last tag</code></p>
-                        URLs which do not pass validation will stay in the textarea.
-                </div>
-                {{ render_field(form.processor, class="processor") }}
-                
-                <div class="pure-control-group">
-                    <textarea name="urls" class="pure-input-1-2" placeholder="https://"
-                              style="width: 100%;
-                                font-family:monospace;
-                                white-space: pre;
-                                overflow-wrap: normal;
-                                overflow-x: scroll;" rows="25">{{ import_url_list_remaining }}</textarea>
-                 </div>
-                 <div id="quick-watch-processor-type"></div>
-
-            </div>
-
-            <div class="tab-pane-inner" id="distill-io">
-
-
-
-                    <div class="pure-control-group">
-                        Copy and Paste your Distill.io watch 'export' file, this should be a JSON file.<br>
-                        This is <i>experimental</i>, supported fields are <code>name</code>, <code>uri</code>, <code>tags</code>, <code>config:selections</code>, the rest (including <code>schedule</code>) are ignored.
-                        <br>
-                        <p>
-                        How to export? <a href="https://distill.io/docs/web-monitor/how-export-and-import-monitors/">https://distill.io/docs/web-monitor/how-export-and-import-monitors/</a><br>
-                        Be sure to set your default fetcher to Chrome if required.<br>
-                        </p>
-                    </div>
-
-
-                    <textarea name="distill-io" class="pure-input-1-2" style="width: 100%;
-                                font-family:monospace;
-                                white-space: pre;
-                                overflow-wrap: normal;
-                                overflow-x: scroll;" placeholder="Example Distill.io JSON export file
-
-{
-    &quot;client&quot;: {
-        &quot;local&quot;: 1
-    },
-    &quot;data&quot;: [
-        {
-            &quot;name&quot;: &quot;Unraid | News&quot;,
-            &quot;uri&quot;: &quot;https://unraid.net/blog&quot;,
-            &quot;config&quot;: &quot;{\&quot;selections\&quot;:[{\&quot;frames\&quot;:[{\&quot;index\&quot;:0,\&quot;excludes\&quot;:[],\&quot;includes\&quot;:[{\&quot;type\&quot;:\&quot;xpath\&quot;,\&quot;expr\&quot;:\&quot;(//div[@id='App']/div[contains(@class,'flex')]/main[contains(@class,'relative')]/section[contains(@class,'relative')]/div[@class='container']/div[contains(@class,'flex')]/div[contains(@class,'w-full')])[1]\&quot;}]}],\&quot;dynamic\&quot;:true,\&quot;delay\&quot;:2}],\&quot;ignoreEmptyText\&quot;:true,\&quot;includeStyle\&quot;:false,\&quot;dataAttr\&quot;:\&quot;text\&quot;}&quot;,
-            &quot;tags&quot;: [],
-            &quot;content_type&quot;: 2,
-            &quot;state&quot;: 40,
-            &quot;schedule&quot;: &quot;{\&quot;type\&quot;:\&quot;INTERVAL\&quot;,\&quot;params\&quot;:{\&quot;interval\&quot;:4447}}&quot;,
-            &quot;ts&quot;: &quot;2022-03-27T15:51:15.667Z&quot;
-        }
-    ]
-}
-" 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>
-
-    </div>
-</div>
-
-{% endblock %}

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -1,34 +0,0 @@
-
-from changedetectionio.strtobool import strtobool
-from flask import Blueprint, flash, redirect, url_for
-from flask_login import login_required
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio import queuedWatchMetaData
-from queue import PriorityQueue
-
-PRICE_DATA_TRACK_ACCEPT = 'accepted'
-PRICE_DATA_TRACK_REJECT = 'rejected'
-
-def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue):
-
-    price_data_follower_blueprint = Blueprint('price_data_follower', __name__)
-
-    @login_required
-    @price_data_follower_blueprint.route("/<string:uuid>/accept", methods=['GET'])
-    def accept(uuid):
-        datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_ACCEPT
-        datastore.data['watching'][uuid]['processor'] = 'restock_diff'
-        datastore.data['watching'][uuid].clear_watch()
-        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-        return redirect(url_for("watchlist.index"))
-
-    @login_required
-    @price_data_follower_blueprint.route("/<string:uuid>/reject", methods=['GET'])
-    def reject(uuid):
-        datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_REJECT
-        return redirect(url_for("watchlist.index"))
-
-
-    return price_data_follower_blueprint
-
-

changedetectionio/blueprint/rss/__init__.py

@@ -1 +0,0 @@
-RSS_FORMAT_TYPES = [('plaintext', 'Plain text'), ('html', 'HTML Color')]

changedetectionio/blueprint/rss/blueprint.py

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

changedetectionio/blueprint/settings/__init__.py

@@ -1,120 +0,0 @@
-import os
-from copy import deepcopy
-from datetime import datetime
-from zoneinfo import ZoneInfo, available_timezones
-import secrets
-import flask_login
-from flask import Blueprint, render_template, request, redirect, url_for, flash
-
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio.auth_decorator import login_optionally_required
-
-
-def construct_blueprint(datastore: ChangeDetectionStore):
-    settings_blueprint = Blueprint('settings', __name__, template_folder="templates")
-
-    @settings_blueprint.route("", methods=['GET', "POST"])
-    @login_optionally_required
-    def settings_page():
-        from changedetectionio import forms
-
-        default = deepcopy(datastore.data['settings'])
-        if datastore.proxy_list is not None:
-            available_proxies = list(datastore.proxy_list.keys())
-            # When enabled
-            system_proxy = datastore.data['settings']['requests']['proxy']
-            # In the case it doesnt exist anymore
-            if not system_proxy in available_proxies:
-                system_proxy = None
-
-            default['requests']['proxy'] = system_proxy if system_proxy is not None else available_proxies[0]
-            # Used by the form handler to keep or remove the proxy settings
-            default['proxy_list'] = available_proxies[0]
-
-        # Don't use form.data on POST so that it doesnt overrid the checkbox status from the POST status
-        form = forms.globalSettingsForm(formdata=request.form if request.method == 'POST' else None,
-                                        data=default,
-                                        extra_notification_tokens=datastore.get_unique_notification_tokens_available()
-                                        )
-
-        # Remove the last option 'System default'
-        form.application.form.notification_format.choices.pop()
-
-        if datastore.proxy_list is None:
-            # @todo - Couldn't get setattr() etc dynamic addition working, so remove it instead
-            del form.requests.form.proxy
-        else:
-            form.requests.form.proxy.choices = []
-            for p in datastore.proxy_list:
-                form.requests.form.proxy.choices.append(tuple((p, datastore.proxy_list[p]['label'])))
-
-        if request.method == 'POST':
-            # Password unset is a GET, but we can lock the session to a salted env password to always need the password
-            if form.application.form.data.get('removepassword_button', False):
-                # SALTED_PASS means the password is "locked" to what we set in the Env var
-                if not os.getenv("SALTED_PASS", False):
-                    datastore.remove_password()
-                    flash("Password protection removed.", 'notice')
-                    flask_login.logout_user()
-                    return redirect(url_for('settings.settings_page'))
-
-            if form.validate():
-                # Don't set password to False when a password is set - should be only removed with the `removepassword` button
-                app_update = dict(deepcopy(form.data['application']))
-
-                # Never update password with '' or False (Added by wtforms when not in submission)
-                if 'password' in app_update and not app_update['password']:
-                    del (app_update['password'])
-
-                datastore.data['settings']['application'].update(app_update)
-                datastore.data['settings']['requests'].update(form.data['requests'])
-
-                if not os.getenv("SALTED_PASS", False) and len(form.application.form.password.encrypted_password):
-                    datastore.data['settings']['application']['password'] = form.application.form.password.encrypted_password
-                    datastore.needs_write_urgent = True
-                    flash("Password protection enabled.", 'notice')
-                    flask_login.logout_user()
-                    return redirect(url_for('watchlist.index'))
-
-                datastore.needs_write_urgent = True
-                flash("Settings updated.")
-
-            else:
-                flash("An error occurred, please see below.", "error")
-
-        # Convert to ISO 8601 format, all date/time relative events stored as UTC time
-        utc_time = datetime.now(ZoneInfo("UTC")).isoformat()
-
-        output = render_template("settings.html",
-                                api_key=datastore.data['settings']['application'].get('api_access_token'),
-                                available_timezones=sorted(available_timezones()),
-                                emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
-                                extra_notification_token_placeholder_info=datastore.get_unique_notification_token_placeholders_available(),
-                                form=form,
-                                hide_remove_pass=os.getenv("SALTED_PASS", False),
-                                min_system_recheck_seconds=int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3)),
-                                settings_application=datastore.data['settings']['application'],
-                                timezone_default_config=datastore.data['settings']['application'].get('timezone'),
-                                utc_time=utc_time,
-                                )
-
-        return output
-
-    @settings_blueprint.route("/reset-api-key", methods=['GET'])
-    @login_optionally_required
-    def settings_reset_api_key():
-        secret = secrets.token_hex(16)
-        datastore.data['settings']['application']['api_access_token'] = secret
-        datastore.needs_write_urgent = True
-        flash("API Key was regenerated.")
-        return redirect(url_for('settings.settings_page')+'#api')
-        
-    @settings_blueprint.route("/notification-logs", methods=['GET'])
-    @login_optionally_required
-    def notification_logs():
-        from changedetectionio.flask_app import notification_debug_log
-        output = render_template("notification-log.html",
-                               logs=notification_debug_log if len(notification_debug_log) else ["Notification logs are empty - no notifications sent yet."])
-        return output
-
-    return settings_blueprint

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

@@ -1,19 +0,0 @@
-{% extends 'base.html' %}
-
-{% block content %}
-<div class="edit-form">
-     <div class="inner">
-
-         <h4 style="margin-top: 0px;">Notification debug log</h4>
-                <div id="notification-error-log">
-                <ul style="font-size: 80%; margin:0px; padding: 0 0 0 7px">
-                {% for log in logs|reverse %}
-                    <li>{{log}}</li>
-                {% endfor %}
-                </ul>
-                </div>
-
-     </div>
-</div>
-
-{% endblock %}

changedetectionio/blueprint/settings/templates/settings.html

@@ -1,320 +0,0 @@
-{% extends 'base.html' %}
-
-{% block content %}
-{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_time_schedule_form %}
-{% from '_common_fields.html' import render_common_settings_form %}
-<script>
-    const notification_base_url="{{url_for('ui.ui_notification.ajax_callback_send_notification_test', mode="global-settings")}}";
-{% 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='plugins.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>
-<script src="{{url_for('static_content', group='js', filename='scheduler.js')}}" defer></script>
-<div class="edit-form">
-    <div class="tabs collapsable">
-        <ul>
-            <li class="tab" id=""><a href="#general">General</a></li>
-            <li class="tab"><a href="#notifications">Notifications</a></li>
-            <li class="tab"><a href="#fetching">Fetching</a></li>
-            <li class="tab"><a href="#filters">Global Filters</a></li>
-            <li class="tab"><a href="#ui-options">UI Options</a></li>
-            <li class="tab"><a href="#api">API</a></li>
-            <li class="tab"><a href="#timedate">Time &amp Date</a></li>
-            <li class="tab"><a href="#proxies">CAPTCHA &amp; Proxies</a></li>
-        </ul>
-    </div>
-    <div class="box-wrap inner">
-        <form class="pure-form pure-form-stacked settings" action="{{url_for('settings.settings_page')}}" method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
-            <div class="tab-pane-inner" id="general">
-                <fieldset>
-                    <div class="pure-control-group">
-                        {{ render_field(form.requests.form.time_between_check, class="time-check-widget") }}
-                        <span class="pure-form-message-inline">Default recheck time for all watches, current system minimum is <i>{{min_system_recheck_seconds}}</i> seconds (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Misc-system-settings#enviroment-variables">more info</a>).</span>
-                            <div id="time-between-check-schedule">
-                                <!-- Start Time and End Time -->
-                                <div id="limit-between-time">
-                                    {{ render_time_schedule_form(form.requests, available_timezones, timezone_default_config) }}
-                                </div>
-                        </div>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.requests.form.jitter_seconds, class="jitter_seconds") }}
-                        <span class="pure-form-message-inline">Example - 3 seconds random jitter could trigger up to 3 seconds earlier or up to 3 seconds later</span>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.application.form.filter_failure_notification_threshold_attempts, class="filter_failure_notification_threshold_attempts") }}
-                        <span class="pure-form-message-inline">After this many consecutive times that the CSS/xPath filter is missing, send a notification
-                            <br>
-                        Set to <strong>0</strong> to disable
-                        </span>
-                    </div>
-                    <div class="pure-control-group">
-                        {% if not hide_remove_pass %}
-                            {% if current_user.is_authenticated %}
-                                {{ render_button(form.application.form.removepassword_button) }}
-                            {% else %}
-                            {{ render_field(form.application.form.password) }}
-                            <span class="pure-form-message-inline">Password protection for your changedetection.io application.</span>
-                            {% endif %}
-                        {% else %}
-                            <span class="pure-form-message-inline">Password is locked.</span>
-                        {% endif %}
-                    </div>
-
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.application.form.shared_diff_access, class="shared_diff_access") }}
-                        <span class="pure-form-message-inline">Allow access to view watch diff page when password is enabled (Good for sharing the diff page)
-                        </span>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.application.form.rss_hide_muted_watches) }}
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.application.form.pager_size) }}
-                        <span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.application.form.rss_content_format) }}
-                        <span class="pure-form-message-inline">Love RSS? Does your reader support HTML? Set it here</span>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.application.form.extract_title_as_title) }}
-                        <span class="pure-form-message-inline">Note: This will automatically apply to all existing watches.</span>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.application.form.empty_pages_are_a_change) }}
-                        <span class="pure-form-message-inline">When a request returns no content, or the HTML does not contain any text, is this considered a change?</span>
-                    </div>
-                {% if form.requests.proxy %}
-                    <div class="pure-control-group inline-radio">
-                        {{ render_field(form.requests.form.proxy, class="fetch-backend-proxy") }}
-                        <span class="pure-form-message-inline">
-                        Choose a default proxy for all watches
-                        </span>
-                    </div>
-                {% endif %}
-                </fieldset>
-            </div>
-
-            <div class="tab-pane-inner" id="notifications">
-                <fieldset>
-                    <div class="field-group">
-                        {{ render_common_settings_form(form.application.form, emailprefix, settings_application, extra_notification_token_placeholder_info) }}
-                    </div>
-                </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">
-                <div class="pure-control-group inline-radio">
-                    {{ render_field(form.application.form.fetch_backend, class="fetch-backend") }}
-                    <span class="pure-form-message-inline">
-                        <p>Use the <strong>Basic</strong> method (default) where your watched sites don't need Javascript to render.</p>
-                        <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
-                    </span>
-                </div>
-                <fieldset class="pure-group" id="webdriver-override-options" data-visible-for="application-fetch_backend=html_webdriver">
-                    <div class="pure-form-message-inline">
-                        <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
-                        <br>
-                        This will wait <i>n</i> seconds before extracting the text.
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.application.form.webdriver_delay) }}
-                    </div>
-                </fieldset>
-                <div class="pure-control-group inline-radio">
-                    {{ render_field(form.requests.form.default_ua) }}
-                    <span class="pure-form-message-inline">
-                        Applied to all requests.<br><br>
-                        Note: Simply changing the User-Agent often does not defeat anti-robot technologies, it's important to consider <a href="https://changedetection.io/tutorial/what-are-main-types-anti-robot-mechanisms">all of the ways that the browser is detected</a>.
-                    </span>
-                </div>
-                <div class="pure-control-group">
-                                        <br>
-                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
-
-                </div>
-            </div>
-
-            <div class="tab-pane-inner" id="filters">
-
-                    <fieldset class="pure-group">
-                    {{ render_checkbox_field(form.application.form.ignore_whitespace) }}
-                    <span class="pure-form-message-inline">Ignore whitespace, tabs and new-lines/line-feeds when considering if a change was detected.<br>
-                    <i>Note:</i> Changing this will change the status of your existing watches, possibly trigger alerts etc.
-                    </span>
-                    </fieldset>
-                <fieldset class="pure-group">
-                    {{ render_checkbox_field(form.application.form.render_anchor_tag_content) }}
-                    <span class="pure-form-message-inline">Render anchor tag content, default disabled, when enabled renders links as <code>(link text)[https://somesite.com]</code>
-                        <br>
-                    <i>Note:</i> Changing this could affect the content of your existing watches, possibly trigger alerts etc.
-                    </span>
-                    </fieldset>
-                    <fieldset class="pure-group">
-                      {{ render_field(form.application.form.global_subtractive_selectors, rows=5, placeholder="header
-footer
-nav
-.stockticker
-//*[contains(text(), 'Advertisement')]") }}
-                      <span class="pure-form-message-inline">
-                        <ul>
-                          <li> Remove HTML element(s) by CSS and XPath selectors before text conversion. </li>
-                          <li> Don't paste HTML here, use only CSS and XPath selectors </li>
-                          <li> Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML. </li>
-                        </ul>
-                      </span>
-                    </fieldset>
-                    <fieldset class="pure-group">
-                    {{ render_field(form.application.form.global_ignore_text, rows=5, placeholder="Some text to ignore in a line
-/some.regex\d{2}/ for case-INsensitive regex
-                    ") }}
-                    <span class="pure-form-message-inline">Note: This is applied globally in addition to the per-watch rules.</span><br>
-                    <span class="pure-form-message-inline">
-                        <ul>
-                            <li>Matching text will be <strong>ignored</strong> in the text snapshot (you can still see it but it wont trigger a change)</li>
-                            <li>Note: This is applied globally in addition to the per-watch rules.</li>
-                            <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
-                            <li>Changing this will affect the comparison checksum which may trigger an alert</li>
-                        </ul>
-                     </span>
-                    </fieldset>
-           </div>
-
-            <div class="tab-pane-inner" id="api">
-                <h4>API Access</h4>
-                <p>Drive your changedetection.io via API, More about <a href="https://github.com/dgtlmoon/changedetection.io/wiki/API-Reference">API access here</a></p>
-
-                <div class="pure-control-group">
-                    {{ render_checkbox_field(form.application.form.api_access_token_enabled) }}
-                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header - required for the Chrome Extension to work</div><br>
-                    <div class="pure-form-message-inline"><br>API Key <span id="api-key">{{api_key}}</span>
-                        <span style="display:none;" id="api-key-copy" >copy</span>
-                    </div>
-                </div>
-                <div class="pure-control-group">
-                    <a href="{{url_for('settings.settings_reset_api_key')}}" class="pure-button button-small button-cancel">Regenerate API key</a>
-                </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 alt="Chrome store icon" src="{{ url_for('static_content', group='images', filename='google-chrome-icon.png') }}" alt="Chrome">
-                            Chrome Webstore
-                        </a>
-                    </p>
-                </div>
-            </div>
-            <div class="tab-pane-inner" id="timedate">
-                <div class="pure-control-group">
-                    Ensure the settings below are correct, they are used to manage the time schedule for checking your web page watches.
-                </div>
-                <div class="pure-control-group">
-                    <p><strong>UTC Time &amp Date from Server:</strong> <span id="utc-time" >{{ utc_time }}</span></p>
-                    <p><strong>Local Time &amp Date in Browser:</strong> <span class="local-time" data-utc="{{ utc_time }}"></span></p>
-                    <p>
-                       {{ render_field(form.application.form.timezone) }}
-                        <datalist id="timezones" style="display: none;">
-                            {% for tz_name in available_timezones %}
-                                <option value="{{ tz_name }}">{{ tz_name }}</option>
-                            {% endfor %}
-                        </datalist>
-                    </p>
-                </div>
-            </div>
-            <div class="tab-pane-inner" id="ui-options">
-                <div class="pure-control-group">
-                    {{ render_checkbox_field(form.application.form.ui.form.open_diff_in_new_tab, class="open_diff_in_new_tab") }}
-                    <span class="pure-form-message-inline">Enable this setting to open the diff page in a new tab. If disabled, the diff page will open in the current tab.</span>
-                </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>
-                            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><strong>Tip</strong>: "Residential" and "Mobile" proxy type can be more successfull than "Data Center" for blocked websites.
-
-                <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">
-                <div class="pure-control-group">
-                    {{ render_button(form.save_button) }}
-                    <a href="{{url_for('watchlist.index')}}" class="pure-button button-small button-cancel">Back</a>
-                    <a href="{{url_for('ui.clear_all_history')}}" class="pure-button button-small button-error">Clear Snapshot History</a>
-                </div>
-            </div>
-        </form>
-    </div>
-</div>
-
-{% endblock %}

changedetectionio/blueprint/tags/README.md

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

changedetectionio/blueprint/tags/__init__.py

@@ -1,191 +0,0 @@
-from flask import Blueprint, request, render_template, flash, url_for, redirect
-
-
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio.flask_app import login_optionally_required
-
-
-def construct_blueprint(datastore: ChangeDetectionStore):
-    tags_blueprint = Blueprint('tags', __name__, template_folder="templates")
-
-    @tags_blueprint.route("/list", methods=['GET'])
-    @login_optionally_required
-    def tags_overview_page():
-        from .form import SingleTag
-        add_form = SingleTag(request.form)
-
-        sorted_tags = sorted(datastore.data['settings']['application'].get('tags').items(), key=lambda x: x[1]['title'])
-
-        from collections import Counter
-
-        tag_count = Counter(tag for watch in datastore.data['watching'].values() if watch.get('tags') for tag in watch['tags'])
-
-        output = render_template("groups-overview.html",
-                                 available_tags=sorted_tags,
-                                 form=add_form,
-                                 tag_count=tag_count
-                                 )
-
-        return output
-
-    @tags_blueprint.route("/add", methods=['POST'])
-    @login_optionally_required
-    def form_tag_add():
-        from .form import SingleTag
-        add_form = SingleTag(request.form)
-
-        if not add_form.validate():
-            for widget, l in add_form.errors.items():
-                flash(','.join(l), 'error')
-            return redirect(url_for('tags.tags_overview_page'))
-
-        title = request.form.get('name').strip()
-
-        if datastore.tag_exists_by_name(title):
-            flash(f'The tag "{title}" already exists', "error")
-            return redirect(url_for('tags.tags_overview_page'))
-
-        datastore.add_tag(title)
-        flash("Tag added")
-
-
-        return redirect(url_for('tags.tags_overview_page'))
-
-    @tags_blueprint.route("/mute/<string:uuid>", methods=['GET'])
-    @login_optionally_required
-    def mute(uuid):
-        if datastore.data['settings']['application']['tags'].get(uuid):
-            datastore.data['settings']['application']['tags'][uuid]['notification_muted'] = not datastore.data['settings']['application']['tags'][uuid]['notification_muted']
-        return redirect(url_for('tags.tags_overview_page'))
-
-    @tags_blueprint.route("/delete/<string:uuid>", methods=['GET'])
-    @login_optionally_required
-    def delete(uuid):
-        removed = 0
-        # Delete the tag, and any tag reference
-        if datastore.data['settings']['application']['tags'].get(uuid):
-            del datastore.data['settings']['application']['tags'][uuid]
-
-        for watch_uuid, watch in datastore.data['watching'].items():
-            if watch.get('tags') and uuid in watch['tags']:
-                removed += 1
-                watch['tags'].remove(uuid)
-
-        flash(f"Tag deleted and removed from {removed} watches")
-        return redirect(url_for('tags.tags_overview_page'))
-
-    @tags_blueprint.route("/unlink/<string:uuid>", methods=['GET'])
-    @login_optionally_required
-    def unlink(uuid):
-        unlinked = 0
-        for watch_uuid, watch in datastore.data['watching'].items():
-            if watch.get('tags') and uuid in watch['tags']:
-                unlinked += 1
-                watch['tags'].remove(uuid)
-
-        flash(f"Tag unlinked removed from {unlinked} watches")
-        return redirect(url_for('tags.tags_overview_page'))
-
-    @tags_blueprint.route("/delete_all", methods=['GET'])
-    @login_optionally_required
-    def delete_all():
-        for watch_uuid, watch in datastore.data['watching'].items():
-            watch['tags'] = []
-        datastore.data['settings']['application']['tags'] = {}
-
-        flash(f"All tags deleted")
-        return redirect(url_for('tags.tags_overview_page'))
-
-    @tags_blueprint.route("/edit/<string:uuid>", methods=['GET'])
-    @login_optionally_required
-    def form_tag_edit(uuid):
-        from changedetectionio.blueprint.tags.form import group_restock_settings_form
-        if uuid == 'first':
-            uuid = list(datastore.data['settings']['application']['tags'].keys()).pop()
-
-        default = datastore.data['settings']['application']['tags'].get(uuid)
-        if not default:
-            flash("Tag not found", "error")
-            return redirect(url_for('watchlist.index'))
-
-        form = group_restock_settings_form(
-                                       formdata=request.form if request.method == 'POST' else None,
-                                       data=default,
-                                       extra_notification_tokens=datastore.get_unique_notification_tokens_available(),
-                                       default_system_settings = datastore.data['settings'],
-                                       )
-
-        template_args = {
-            'data': default,
-            'form': form,
-            'watch': default,
-            'extra_notification_token_placeholder_info': datastore.get_unique_notification_token_placeholders_available(),
-        }
-
-        included_content = {}
-        if form.extra_form_content():
-            # So that the extra panels can access _helpers.html etc, we set the environment to load from templates/
-            # And then render the code from the module
-            from jinja2 import Environment, FileSystemLoader
-            import importlib.resources
-            templates_dir = str(importlib.resources.files("changedetectionio").joinpath('templates'))
-            env = Environment(loader=FileSystemLoader(templates_dir))
-            template_str = """{% from '_helpers.html' import render_field, render_checkbox_field, render_button %}
-        <script>        
-            $(document).ready(function () {
-                toggleOpacity('#overrides_watch', '#restock-fieldset-price-group', true);
-            });
-        </script>            
-                <fieldset>
-                    <div class="pure-control-group">
-                        <fieldset class="pure-group">
-                        {{ render_checkbox_field(form.overrides_watch) }}
-                        <span class="pure-form-message-inline">Used for watches in "Restock & Price detection" mode</span>
-                        </fieldset>
-                </fieldset>
-                """
-            template_str += form.extra_form_content()
-            template = env.from_string(template_str)
-            included_content = template.render(**template_args)
-
-        output = render_template("edit-tag.html",
-                                 settings_application=datastore.data['settings']['application'],
-                                 extra_tab_content=form.extra_tab_content() if form.extra_tab_content() else None,
-                                 extra_form_content=included_content,
-                                 **template_args
-                                 )
-
-        return output
-
-
-    @tags_blueprint.route("/edit/<string:uuid>", methods=['POST'])
-    @login_optionally_required
-    def form_tag_edit_submit(uuid):
-        from changedetectionio.blueprint.tags.form import group_restock_settings_form
-        if uuid == 'first':
-            uuid = list(datastore.data['settings']['application']['tags'].keys()).pop()
-
-        default = datastore.data['settings']['application']['tags'].get(uuid)
-
-        form = group_restock_settings_form(formdata=request.form if request.method == 'POST' else None,
-                               data=default,
-                               extra_notification_tokens=datastore.get_unique_notification_tokens_available()
-                               )
-        # @todo subclass form so validation works
-        #if not form.validate():
-#            for widget, l in form.errors.items():
-#                flash(','.join(l), 'error')
-#           return redirect(url_for('tags.form_tag_edit_submit', uuid=uuid))
-
-        datastore.data['settings']['application']['tags'][uuid].update(form.data)
-        datastore.data['settings']['application']['tags'][uuid]['processor'] = 'restock_diff'
-        datastore.needs_write_urgent = True
-        flash("Updated")
-
-        return redirect(url_for('tags.tags_overview_page'))
-
-
-    @tags_blueprint.route("/delete/<string:uuid>", methods=['GET'])
-    def form_tag_delete(uuid):
-        return redirect(url_for('tags.tags_overview_page'))
-    return tags_blueprint

changedetectionio/blueprint/tags/form.py

@@ -1,21 +0,0 @@
-from wtforms import (
-    Form,
-    StringField,
-    SubmitField,
-    validators,
-)
-from wtforms.fields.simple import BooleanField
-
-from changedetectionio.processors.restock_diff.forms import processor_settings_form as restock_settings_form
-
-class group_restock_settings_form(restock_settings_form):
-    overrides_watch = BooleanField('Activate for individual watches in this tag/group?', default=False)
-
-class SingleTag(Form):
-
-    name = StringField('Tag name', [validators.InputRequired()], render_kw={"placeholder": "Name"})
-    save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
-
-
-
-

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

@@ -1,100 +0,0 @@
-{% extends 'base.html' %}
-{% block content %}
-{% from '_helpers.html' import render_field, render_checkbox_field, render_button %}
-{% from '_common_fields.html' import render_common_settings_form %}
-<script>
-    const notification_base_url="{{url_for('ui.ui_notification.ajax_callback_send_notification_test', mode="group-settings")}}";
-</script>
-
-<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
-<script>
-
-/*{% if emailprefix %}*/
-    /*const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');*/
-/*{% endif %}*/
-
-{% set has_tag_filters_extra='' %}
-
-</script>
-
-<script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
-<script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
-
-<div class="edit-form monospaced-textarea">
-
-    <div class="tabs collapsable">
-        <ul>
-            <li class="tab" id=""><a href="#general">General</a></li>
-            <li class="tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
-            {% if extra_tab_content %}
-            <li class="tab"><a href="#extras_tab">{{ extra_tab_content }}</a></li>
-            {% endif %}
-            <li class="tab"><a href="#notifications">Notifications</a></li>
-        </ul>
-    </div>
-
-    <div class="box-wrap inner">
-        <form class="pure-form pure-form-stacked"
-              action="{{ url_for('tags.form_tag_edit', uuid=data.uuid) }}" method="POST">
-             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
-
-            <div class="tab-pane-inner" id="general">
-                <fieldset>
-                    <div class="pure-control-group">
-                        {{ render_field(form.title, placeholder="https://...", required=true, class="m-d") }}
-                    </div>
-                </fieldset>
-            </div>
-
-            <div class="tab-pane-inner" id="filters-and-triggers">
-                <p>These settings are <strong><i>added</i></strong> to any existing watch configurations.</p>
-                {% include "edit/include_subtract.html" %}
-                <div class="text-filtering border-fieldset">
-                    <h3>Text filtering</h3>
-                    {% include "edit/text-options.html" %}
-                </div>
-            </div>
-
-        {# rendered sub Template #}
-        {% if extra_form_content %}
-            <div class="tab-pane-inner" id="extras_tab">
-            {{ extra_form_content|safe }}
-            </div>
-        {% endif %}
-            <div class="tab-pane-inner" id="notifications">
-                <fieldset>
-                    <div  class="pure-control-group inline-radio">
-                      {{ render_checkbox_field(form.notification_muted) }}
-                    </div>
-                    {% if 1 %}
-                    <div class="pure-control-group inline-radio">
-                      {{ render_checkbox_field(form.notification_screenshot) }}
-                        <span class="pure-form-message-inline">
-                            <strong>Use with caution!</strong> This will easily fill up your email storage quota or flood other storages.
-                        </span>
-                    </div>
-                    {% endif %}
-                    <div class="field-group" id="notification-field-group">
-                        {% if has_default_notification_urls %}
-                        <div class="inline-warning">
-                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!" >
-                            There are <a href="{{ url_for('settings.settings_page')}}#notifications">system-wide notification URLs enabled</a>, this form will override notification settings for this watch only &dash; an empty Notification URL list here will still send notifications.
-                        </div>
-                        {% endif %}
-                        <a href="#notifications" id="notification-setting-reset-to-default" class="pure-button button-xsmall" style="right: 20px; top: 20px; position: absolute; background-color: #5f42dd; border-radius: 4px; font-size: 70%; color: #fff">Use system defaults</a>
-
-                        {{ render_common_settings_form(form, emailprefix, settings_application, extra_notification_token_placeholder_info) }}
-                    </div>
-                </fieldset>
-            </div>
-
-            <div id="actions">
-                <div class="pure-control-group">
-                    {{ render_button(form.save_button) }}
-                </div>
-            </div>
-        </form>
-    </div>
-</div>
-
-{% endblock %}

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

@@ -1,62 +0,0 @@
-{% extends 'base.html' %}
-{% block content %}
-{% from '_helpers.html' import render_simple_field, render_field %}
-<script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
-
-<div class="box">
-    <form class="pure-form" action="{{ url_for('tags.form_tag_add') }}" method="POST" id="new-watch-form">
-        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
-        <fieldset>
-            <legend>Add a new organisational tag</legend>
-            <div id="watch-add-wrapper-zone">
-                <div>
-                    {{ render_simple_field(form.name, placeholder="watch label / tag") }}
-                </div>
-                <div>
-                    {{ render_simple_field(form.save_button, title="Save" ) }}
-                </div>
-            </div>
-            <br>
-            <div style="color: #fff;">Groups allows you to manage filters and notifications for multiple watches under a single organisational tag.</div>
-        </fieldset>
-    </form>
-    <!-- @todo maybe some overview matrix, 'tick' with which has notification, filter rules etc -->
-    <div id="watch-table-wrapper">
-
-        <table class="pure-table pure-table-striped watch-table group-overview-table">
-            <thead>
-            <tr>
-                <th></th>
-                <th># Watches</th>
-                <th>Tag / Label name</th>
-                <th></th>
-            </tr>
-            </thead>
-            <tbody>
-            <!--
-            @Todo - connect Last checked, Last Changed, Number of Watches etc
-            --->
-            {% if not available_tags|length %}
-            <tr>
-                <td colspan="3">No website organisational tags/groups configured</td>
-            </tr>
-            {% endif %}
-            {% for uuid, tag in available_tags  %}
-            <tr id="{{ uuid }}" class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }}">
-                <td class="watch-controls">
-                    <a class="link-mute state-{{'on' if tag.notification_muted else 'off'}}" href="{{url_for('tags.mute', uuid=tag.uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute" ></a>
-                </td>
-                <td>{{ "{:,}".format(tag_count[uuid]) if uuid in tag_count else 0 }}</td>
-                <td class="title-col inline"> <a href="{{url_for('watchlist.index', tag=uuid) }}">{{ tag.title }}</a></td>
-                <td>
-                    <a class="pure-button pure-button-primary" href="{{ url_for('tags.form_tag_edit', uuid=uuid) }}">Edit</a>&nbsp;
-                    <a class="pure-button pure-button-primary" href="{{ url_for('tags.delete', uuid=uuid) }}" title="Deletes and removes tag">Delete</a>
-                    <a class="pure-button pure-button-primary" href="{{ url_for('tags.unlink', uuid=uuid) }}" title="Keep the tag but unlink any watches">Unlink</a>
-                </td>
-            </tr>
-            {% endfor %}
-            </tbody>
-        </table>
-    </div>
-</div>
-{% endblock %}

changedetectionio/blueprint/ui/__init__.py

@@ -1,305 +0,0 @@
-import time
-from flask import Blueprint, request, redirect, url_for, flash, render_template, session
-from loguru import logger
-from functools import wraps
-
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio.blueprint.ui.edit import construct_blueprint as construct_edit_blueprint
-from changedetectionio.blueprint.ui.notification import construct_blueprint as construct_notification_blueprint
-from changedetectionio.blueprint.ui.views import construct_blueprint as construct_views_blueprint
-
-def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_update_threads, queuedWatchMetaData):
-    ui_blueprint = Blueprint('ui', __name__, template_folder="templates")
-    
-    # Register the edit blueprint
-    edit_blueprint = construct_edit_blueprint(datastore, update_q, queuedWatchMetaData)
-    ui_blueprint.register_blueprint(edit_blueprint)
-    
-    # Register the notification blueprint
-    notification_blueprint = construct_notification_blueprint(datastore)
-    ui_blueprint.register_blueprint(notification_blueprint)
-    
-    # Register the views blueprint
-    views_blueprint = construct_views_blueprint(datastore, update_q, queuedWatchMetaData)
-    ui_blueprint.register_blueprint(views_blueprint)
-    
-    # Import the login decorator
-    from changedetectionio.auth_decorator import login_optionally_required
-
-    @ui_blueprint.route("/clear_history/<string:uuid>", methods=['GET'])
-    @login_optionally_required
-    def clear_watch_history(uuid):
-        try:
-            datastore.clear_watch_history(uuid)
-        except KeyError:
-            flash('Watch not found', 'error')
-        else:
-            flash("Cleared snapshot history for watch {}".format(uuid))
-
-        return redirect(url_for('watchlist.index'))
-
-    @ui_blueprint.route("/clear_history", methods=['GET', 'POST'])
-    @login_optionally_required
-    def clear_all_history():
-        if request.method == 'POST':
-            confirmtext = request.form.get('confirmtext')
-
-            if confirmtext == 'clear':
-                for uuid in datastore.data['watching'].keys():
-                    datastore.clear_watch_history(uuid)
-
-                flash("Cleared snapshot history for all watches")
-            else:
-                flash('Incorrect confirmation text.', 'error')
-
-            return redirect(url_for('watchlist.index'))
-
-        output = render_template("clear_all_history.html")
-        return output
-
-    # Clear all statuses, so we do not see the 'unviewed' class
-    @ui_blueprint.route("/form/mark-all-viewed", methods=['GET'])
-    @login_optionally_required
-    def mark_all_viewed():
-        # Save the current newest history as the most recently viewed
-        with_errors = request.args.get('with_errors') == "1"
-        for watch_uuid, watch in datastore.data['watching'].items():
-            if with_errors and not watch.get('last_error'):
-                continue
-            datastore.set_last_viewed(watch_uuid, int(time.time()))
-
-        return redirect(url_for('watchlist.index'))
-
-    @ui_blueprint.route("/delete", methods=['GET'])
-    @login_optionally_required
-    def form_delete():
-        uuid = request.args.get('uuid')
-
-        if uuid != 'all' and not uuid in datastore.data['watching'].keys():
-            flash('The watch by UUID {} does not exist.'.format(uuid), 'error')
-            return redirect(url_for('watchlist.index'))
-
-        # More for testing, possible to return the first/only
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
-        datastore.delete(uuid)
-        flash('Deleted.')
-
-        return redirect(url_for('watchlist.index'))
-
-    @ui_blueprint.route("/clone", methods=['GET'])
-    @login_optionally_required
-    def form_clone():
-        uuid = request.args.get('uuid')
-        # More for testing, possible to return the first/only
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
-
-        new_uuid = datastore.clone(uuid)
-
-        if not datastore.data['watching'].get(uuid).get('paused'):
-            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
-
-        flash('Cloned, you are editing the new watch.')
-
-        return redirect(url_for("ui.ui_edit.edit_page", uuid=new_uuid))
-
-    @ui_blueprint.route("/checknow", methods=['GET'])
-    @login_optionally_required
-    def form_watch_checknow():
-        # Forced recheck will skip the 'skip if content is the same' rule (, 'reprocess_existing_data': True})))
-        tag = request.args.get('tag')
-        uuid = request.args.get('uuid')
-        with_errors = request.args.get('with_errors') == "1"
-
-        i = 0
-
-        running_uuids = []
-        for t in running_update_threads:
-            running_uuids.append(t.current_uuid)
-
-        if uuid:
-            if uuid not in running_uuids:
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-                i += 1
-
-        else:
-            # Recheck all, including muted
-            # Get most overdue first
-            for k in sorted(datastore.data['watching'].items(), key=lambda item: item[1].get('last_checked', 0)):
-                watch_uuid = k[0]
-                watch = k[1]
-                if not watch['paused']:
-                    if watch_uuid not in running_uuids:
-                        if with_errors and not watch.get('last_error'):
-                            continue
-
-                        if tag != None and tag not in watch['tags']:
-                            continue
-
-                        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
-                        i += 1
-
-        if i == 1:
-            flash("Queued 1 watch for rechecking.")
-        if i > 1:
-            flash(f"Queued {i} watches for rechecking.")
-        if i == 0:
-            flash("No watches available to recheck.")
-
-        return redirect(url_for('watchlist.index'))
-
-    @ui_blueprint.route("/form/checkbox-operations", methods=['POST'])
-    @login_optionally_required
-    def form_watch_list_checkbox_operations():
-        op = request.form['op']
-        uuids = request.form.getlist('uuids')
-
-        if (op == 'delete'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.delete(uuid.strip())
-            flash("{} watches deleted".format(len(uuids)))
-
-        elif (op == 'pause'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid.strip()]['paused'] = True
-            flash("{} watches paused".format(len(uuids)))
-
-        elif (op == 'unpause'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid.strip()]['paused'] = False
-            flash("{} watches unpaused".format(len(uuids)))
-
-        elif (op == 'mark-viewed'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.set_last_viewed(uuid, int(time.time()))
-            flash("{} watches updated".format(len(uuids)))
-
-        elif (op == 'mute'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid.strip()]['notification_muted'] = True
-            flash("{} watches muted".format(len(uuids)))
-
-        elif (op == 'unmute'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid.strip()]['notification_muted'] = False
-            flash("{} watches un-muted".format(len(uuids)))
-
-        elif (op == 'recheck'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    # Recheck and require a full reprocessing
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-            flash("{} watches queued for rechecking".format(len(uuids)))
-
-        elif (op == 'clear-errors'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid]["last_error"] = False
-            flash(f"{len(uuids)} watches errors cleared")
-
-        elif (op == 'clear-history'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.clear_watch_history(uuid)
-            flash("{} watches cleared/reset.".format(len(uuids)))
-
-        elif (op == 'notification-default'):
-            from changedetectionio.notification import (
-                default_notification_format_for_watch
-            )
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid.strip()]['notification_title'] = None
-                    datastore.data['watching'][uuid.strip()]['notification_body'] = None
-                    datastore.data['watching'][uuid.strip()]['notification_urls'] = []
-                    datastore.data['watching'][uuid.strip()]['notification_format'] = default_notification_format_for_watch
-            flash("{} watches set to use default notification settings".format(len(uuids)))
-
-        elif (op == 'assign-tag'):
-            op_extradata = request.form.get('op_extradata', '').strip()
-            if op_extradata:
-                tag_uuid = datastore.add_tag(title=op_extradata)
-                if op_extradata and tag_uuid:
-                    for uuid in uuids:
-                        uuid = uuid.strip()
-                        if datastore.data['watching'].get(uuid):
-                            # Bug in old versions caused by bad edit page/tag handler
-                            if isinstance(datastore.data['watching'][uuid]['tags'], str):
-                                datastore.data['watching'][uuid]['tags'] = []
-
-                            datastore.data['watching'][uuid]['tags'].append(tag_uuid)
-
-            flash(f"{len(uuids)} watches were tagged")
-
-        return redirect(url_for('watchlist.index'))
-
-
-    @ui_blueprint.route("/share-url/<string:uuid>", methods=['GET'])
-    @login_optionally_required
-    def form_share_put_watch(uuid):
-        """Given a watch UUID, upload the info and return a share-link
-           the share-link can be imported/added"""
-        import requests
-        import json
-        from copy import deepcopy
-
-        # more for testing
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
-
-        # copy it to memory as trim off what we dont need (history)
-        watch = deepcopy(datastore.data['watching'].get(uuid))
-        # For older versions that are not a @property
-        if (watch.get('history')):
-            del (watch['history'])
-
-        # for safety/privacy
-        for k in list(watch.keys()):
-            if k.startswith('notification_'):
-                del watch[k]
-
-        for r in['uuid', 'last_checked', 'last_changed']:
-            if watch.get(r):
-                del (watch[r])
-
-        # Add the global stuff which may have an impact
-        watch['ignore_text'] += datastore.data['settings']['application']['global_ignore_text']
-        watch['subtractive_selectors'] += datastore.data['settings']['application']['global_subtractive_selectors']
-
-        watch_json = json.dumps(watch)
-
-        try:
-            r = requests.request(method="POST",
-                                 data={'watch': watch_json},
-                                 url="https://changedetection.io/share/share",
-                                 headers={'App-Guid': datastore.data['app_guid']})
-            res = r.json()
-
-            # Add to the flask session
-            session['share-link'] = f"https://changedetection.io/share/{res['share_key']}"
-
-
-        except Exception as e:
-            logger.error(f"Error sharing -{str(e)}")
-            flash(f"Could not share, something went wrong while communicating with the share server - {str(e)}", 'error')
-
-        return redirect(url_for('watchlist.index'))
-
-    return ui_blueprint

changedetectionio/blueprint/ui/edit.py

@@ -1,334 +0,0 @@
-import time
-from copy import deepcopy
-import os
-import importlib.resources
-from flask import Blueprint, request, redirect, url_for, flash, render_template, make_response, send_from_directory, abort
-from loguru import logger
-from jinja2 import Environment, FileSystemLoader
-
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio.auth_decorator import login_optionally_required
-from changedetectionio.time_handler import is_within_schedule
-
-def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
-    edit_blueprint = Blueprint('ui_edit', __name__, template_folder="../ui/templates")
-    
-    def _watch_has_tag_options_set(watch):
-        """This should be fixed better so that Tag is some proper Model, a tag is just a Watch also"""
-        for tag_uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
-            if tag_uuid in watch.get('tags', []) and (tag.get('include_filters') or tag.get('subtractive_selectors')):
-                return True
-
-    @edit_blueprint.route("/edit/<string:uuid>", methods=['GET', 'POST'])
-    @login_optionally_required
-    # https://stackoverflow.com/questions/42984453/wtforms-populate-form-with-data-if-data-exists
-    # https://wtforms.readthedocs.io/en/3.0.x/forms/#wtforms.form.Form.populate_obj ?
-    def edit_page(uuid):
-        from changedetectionio import forms
-        from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
-        from changedetectionio import processors
-        import importlib
-
-        # More for testing, possible to return the first/only
-        if not datastore.data['watching'].keys():
-            flash("No watches to edit", "error")
-            return redirect(url_for('watchlist.index'))
-
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
-
-        if not uuid in datastore.data['watching']:
-            flash("No watch with the UUID %s found." % (uuid), "error")
-            return redirect(url_for('watchlist.index'))
-
-        switch_processor = request.args.get('switch_processor')
-        if switch_processor:
-            for p in processors.available_processors():
-                if p[0] == switch_processor:
-                    datastore.data['watching'][uuid]['processor'] = switch_processor
-                    flash(f"Switched to mode - {p[1]}.")
-                    datastore.clear_watch_history(uuid)
-                    redirect(url_for('ui_edit.edit_page', uuid=uuid))
-
-        # be sure we update with a copy instead of accidently editing the live object by reference
-        default = deepcopy(datastore.data['watching'][uuid])
-
-        # Defaults for proxy choice
-        if datastore.proxy_list is not None:  # When enabled
-            # @todo
-            # Radio needs '' not None, or incase that the chosen one no longer exists
-            if default['proxy'] is None or not any(default['proxy'] in tup for tup in datastore.proxy_list):
-                default['proxy'] = ''
-        # proxy_override set to the json/text list of the items
-
-        # Does it use some custom form? does one exist?
-        processor_name = datastore.data['watching'][uuid].get('processor', '')
-        processor_classes = next((tpl for tpl in processors.find_processors() if tpl[1] == processor_name), None)
-        if not processor_classes:
-            flash(f"Cannot load the edit form for processor/plugin '{processor_classes[1]}', plugin missing?", 'error')
-            return redirect(url_for('watchlist.index'))
-
-        parent_module = processors.get_parent_module(processor_classes[0])
-
-        try:
-            # Get the parent of the "processor.py" go up one, get the form (kinda spaghetti but its reusing existing code)
-            forms_module = importlib.import_module(f"{parent_module.__name__}.forms")
-            # Access the 'processor_settings_form' class from the 'forms' module
-            form_class = getattr(forms_module, 'processor_settings_form')
-        except ModuleNotFoundError as e:
-            # .forms didnt exist
-            form_class = forms.processor_text_json_diff_form
-        except AttributeError as e:
-            # .forms exists but no useful form
-            form_class = forms.processor_text_json_diff_form
-
-        form = form_class(formdata=request.form if request.method == 'POST' else None,
-                          data=default,
-                          extra_notification_tokens=default.extra_notification_token_values(),
-                          default_system_settings=datastore.data['settings']
-                          )
-
-        # For the form widget tag UUID back to "string name" for the field
-        form.tags.datastore = datastore
-
-        # Used by some forms that need to dig deeper
-        form.datastore = datastore
-        form.watch = default
-
-        for p in datastore.extra_browsers:
-            form.fetch_backend.choices.append(p)
-
-        form.fetch_backend.choices.append(("system", 'System settings default'))
-
-        # form.browser_steps[0] can be assumed that we 'goto url' first
-
-        if datastore.proxy_list is None:
-            # @todo - Couldn't get setattr() etc dynamic addition working, so remove it instead
-            del form.proxy
-        else:
-            form.proxy.choices = [('', 'Default')]
-            for p in datastore.proxy_list:
-                form.proxy.choices.append(tuple((p, datastore.proxy_list[p]['label'])))
-
-
-        if request.method == 'POST' and form.validate():
-
-            # If they changed processor, it makes sense to reset it.
-            if datastore.data['watching'][uuid].get('processor') != form.data.get('processor'):
-                datastore.data['watching'][uuid].clear_watch()
-                flash("Reset watch history due to change of processor")
-
-            extra_update_obj = {
-                'consecutive_filter_failures': 0,
-                'last_error' : False
-            }
-
-            if request.args.get('unpause_on_save'):
-                extra_update_obj['paused'] = False
-
-            extra_update_obj['time_between_check'] = form.time_between_check.data
-
-             # Ignore text
-            form_ignore_text = form.ignore_text.data
-            datastore.data['watching'][uuid]['ignore_text'] = form_ignore_text
-
-            # Be sure proxy value is None
-            if datastore.proxy_list is not None and form.data['proxy'] == '':
-                extra_update_obj['proxy'] = None
-
-            # Unsetting all filter_text methods should make it go back to default
-            # This particularly affects tests running
-            if 'filter_text_added' in form.data and not form.data.get('filter_text_added') \
-                    and 'filter_text_replaced' in form.data and not form.data.get('filter_text_replaced') \
-                    and 'filter_text_removed' in form.data and not form.data.get('filter_text_removed'):
-                extra_update_obj['filter_text_added'] = True
-                extra_update_obj['filter_text_replaced'] = True
-                extra_update_obj['filter_text_removed'] = True
-
-            # Because wtforms doesn't support accessing other data in process_ , but we convert the CSV list of tags back to a list of UUIDs
-            tag_uuids = []
-            if form.data.get('tags'):
-                # Sometimes in testing this can be list, dont know why
-                if type(form.data.get('tags')) == list:
-                    extra_update_obj['tags'] = form.data.get('tags')
-                else:
-                    for t in form.data.get('tags').split(','):
-                        tag_uuids.append(datastore.add_tag(title=t))
-                    extra_update_obj['tags'] = tag_uuids
-
-            datastore.data['watching'][uuid].update(form.data)
-            datastore.data['watching'][uuid].update(extra_update_obj)
-
-            if not datastore.data['watching'][uuid].get('tags'):
-                # Force it to be a list, because form.data['tags'] will be string if nothing found
-                # And del(form.data['tags'] ) wont work either for some reason
-                datastore.data['watching'][uuid]['tags'] = []
-
-            # Recast it if need be to right data Watch handler
-            watch_class = processors.get_custom_watch_obj_for_processor(form.data.get('processor'))
-            datastore.data['watching'][uuid] = watch_class(datastore_path=datastore.datastore_path, default=datastore.data['watching'][uuid])
-            flash("Updated watch - unpaused!" if request.args.get('unpause_on_save') else "Updated watch.")
-
-            # Re #286 - We wait for syncing new data to disk in another thread every 60 seconds
-            # But in the case something is added we should save straight away
-            datastore.needs_write_urgent = True
-
-            # Do not queue on edit if its not within the time range
-
-            # @todo maybe it should never queue anyway on edit...
-            is_in_schedule = True
-            watch = datastore.data['watching'].get(uuid)
-
-            if watch.get('time_between_check_use_default'):
-                time_schedule_limit = datastore.data['settings']['requests'].get('time_schedule_limit', {})
-            else:
-                time_schedule_limit = watch.get('time_schedule_limit')
-
-            tz_name = time_schedule_limit.get('timezone')
-            if not tz_name:
-                tz_name = datastore.data['settings']['application'].get('timezone', 'UTC')
-
-            if time_schedule_limit and time_schedule_limit.get('enabled'):
-                try:
-                    is_in_schedule = is_within_schedule(time_schedule_limit=time_schedule_limit,
-                                                      default_tz=tz_name
-                                                      )
-                except Exception as e:
-                    logger.error(
-                        f"{uuid} - Recheck scheduler, error handling timezone, check skipped - TZ name '{tz_name}' - {str(e)}")
-                    return False
-
-            #############################
-            if not datastore.data['watching'][uuid].get('paused') and is_in_schedule:
-                # Queue the watch for immediate recheck, with a higher priority
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-
-            # Diff page [edit] link should go back to diff page
-            if request.args.get("next") and request.args.get("next") == 'diff':
-                return redirect(url_for('ui.ui_views.diff_history_page', uuid=uuid))
-
-            return redirect(url_for('watchlist.index', tag=request.args.get("tag",'')))
-
-        else:
-            if request.method == 'POST' and not form.validate():
-                flash("An error occurred, please see below.", "error")
-
-            # JQ is difficult to install on windows and must be manually added (outside requirements.txt)
-            jq_support = True
-            try:
-                import jq
-            except ModuleNotFoundError:
-                jq_support = False
-
-            watch = datastore.data['watching'].get(uuid)
-
-            # if system or watch is configured to need a chrome type browser
-            system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
-            watch_needs_selenium_or_playwright = False
-            if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
-                watch_needs_selenium_or_playwright = True
-
-
-            from zoneinfo import available_timezones
-
-            # Only works reliably with Playwright
-
-            template_args = {
-                'available_processors': processors.available_processors(),
-                'available_timezones': sorted(available_timezones()),
-                'browser_steps_config': browser_step_ui_config,
-                'emailprefix': os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
-                'extra_notification_token_placeholder_info': datastore.get_unique_notification_token_placeholders_available(),
-                'extra_processor_config': form.extra_tab_content(),
-                'extra_title': f" - Edit - {watch.label}",
-                'form': form,
-                'has_default_notification_urls': True if len(datastore.data['settings']['application']['notification_urls']) else False,
-                'has_extra_headers_file': len(datastore.get_all_headers_in_textfile_for_watch(uuid=uuid)) > 0,
-                'has_special_tag_options': _watch_has_tag_options_set(watch=watch),
-                'jq_support': jq_support,
-                'playwright_enabled': os.getenv('PLAYWRIGHT_DRIVER_URL', False),
-                'settings_application': datastore.data['settings']['application'],
-                'system_has_playwright_configured': os.getenv('PLAYWRIGHT_DRIVER_URL'),
-                'system_has_webdriver_configured': os.getenv('WEBDRIVER_URL'),
-                'visual_selector_data_ready': datastore.visualselector_data_is_ready(watch_uuid=uuid),
-                'timezone_default_config': datastore.data['settings']['application'].get('timezone'),
-                'using_global_webdriver_wait': not default['webdriver_delay'],
-                'uuid': uuid,
-                'watch': watch,
-                'watch_needs_selenium_or_playwright': watch_needs_selenium_or_playwright,
-            }
-
-            included_content = None
-            if form.extra_form_content():
-                # So that the extra panels can access _helpers.html etc, we set the environment to load from templates/
-                # And then render the code from the module
-                templates_dir = str(importlib.resources.files("changedetectionio").joinpath('templates'))
-                env = Environment(loader=FileSystemLoader(templates_dir))
-                template = env.from_string(form.extra_form_content())
-                included_content = template.render(**template_args)
-
-            output = render_template("edit.html",
-                                     extra_tab_content=form.extra_tab_content() if form.extra_tab_content() else None,
-                                     extra_form_content=included_content,
-                                     **template_args
-                                     )
-
-        return output
-
-    @edit_blueprint.route("/edit/<string:uuid>/get-html", methods=['GET'])
-    @login_optionally_required
-    def watch_get_latest_html(uuid):
-        from io import BytesIO
-        from flask import send_file
-        import brotli
-
-        watch = datastore.data['watching'].get(uuid)
-        if watch and watch.history.keys() and os.path.isdir(watch.watch_data_dir):
-            latest_filename = list(watch.history.keys())[-1]
-            html_fname = os.path.join(watch.watch_data_dir, f"{latest_filename}.html.br")
-            with open(html_fname, 'rb') as f:
-                if html_fname.endswith('.br'):
-                    # Read and decompress the Brotli file
-                    decompressed_data = brotli.decompress(f.read())
-                else:
-                    decompressed_data = f.read()
-
-            buffer = BytesIO(decompressed_data)
-
-            return send_file(buffer, as_attachment=True, download_name=f"{latest_filename}.html", mimetype='text/html')
-
-        # Return a 500 error
-        abort(500)
-
-    # Ajax callback
-    @edit_blueprint.route("/edit/<string:uuid>/preview-rendered", methods=['POST'])
-    @login_optionally_required
-    def watch_get_preview_rendered(uuid):
-        '''For when viewing the "preview" of the rendered text from inside of Edit'''
-        from flask import jsonify
-        from changedetectionio.processors.text_json_diff import prepare_filter_prevew
-        result = prepare_filter_prevew(watch_uuid=uuid, form_data=request.form, datastore=datastore)
-        return jsonify(result)
-
-    @edit_blueprint.route("/highlight_submit_ignore_url", methods=['POST'])
-    @login_optionally_required
-    def highlight_submit_ignore_url():
-        import re
-        mode = request.form.get('mode')
-        selection = request.form.get('selection')
-
-        uuid = request.args.get('uuid','')
-        if datastore.data["watching"].get(uuid):
-            if mode == 'exact':
-                for l in selection.splitlines():
-                    datastore.data["watching"][uuid]['ignore_text'].append(l.strip())
-            elif mode == 'digit-regex':
-                for l in selection.splitlines():
-                    # Replace any series of numbers with a regex
-                    s = re.escape(l.strip())
-                    s = re.sub(r'[0-9]+', r'\\d+', s)
-                    datastore.data["watching"][uuid]['ignore_text'].append('/' + s + '/')
-
-        return f"<a href={url_for('ui.ui_views.preview_page', uuid=uuid)}>Click to preview</a>"
-    
-    return edit_blueprint

changedetectionio/blueprint/ui/notification.py

@@ -1,108 +0,0 @@
-from flask import Blueprint, request, make_response
-import random
-from loguru import logger
-
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio.auth_decorator import login_optionally_required
-
-def construct_blueprint(datastore: ChangeDetectionStore):
-    notification_blueprint = Blueprint('ui_notification', __name__, template_folder="../ui/templates")
-    
-    # AJAX endpoint for sending a test
-    @notification_blueprint.route("/notification/send-test/<string:watch_uuid>", methods=['POST'])
-    @notification_blueprint.route("/notification/send-test", methods=['POST'])
-    @notification_blueprint.route("/notification/send-test/", methods=['POST'])
-    @login_optionally_required
-    def ajax_callback_send_notification_test(watch_uuid=None):
-
-        # Watch_uuid could be unset in the case it`s used in tag editor, global settings
-        import apprise
-        from changedetectionio.notification.handler import process_notification
-        from changedetectionio.notification.apprise_plugin.assets import apprise_asset
-
-        from changedetectionio.notification.apprise_plugin.custom_handlers import apprise_http_custom_handler
-
-        apobj = apprise.Apprise(asset=apprise_asset)
-
-        is_global_settings_form = request.args.get('mode', '') == 'global-settings'
-        is_group_settings_form = request.args.get('mode', '') == 'group-settings'
-
-        # Use an existing random one on the global/main settings form
-        if not watch_uuid and (is_global_settings_form or is_group_settings_form) \
-                and datastore.data.get('watching'):
-            logger.debug(f"Send test notification - Choosing random Watch {watch_uuid}")
-            watch_uuid = random.choice(list(datastore.data['watching'].keys()))
-
-        if not watch_uuid:
-            return make_response("Error: You must have atleast one watch configured for 'test notification' to work", 400)
-
-        watch = datastore.data['watching'].get(watch_uuid)
-
-        notification_urls = None
-
-        if request.form.get('notification_urls'):
-            notification_urls = request.form['notification_urls'].strip().splitlines()
-
-        if not notification_urls:
-            logger.debug("Test notification - Trying by group/tag in the edit form if available")
-            # On an edit page, we should also fire off to the tags if they have notifications
-            if request.form.get('tags') and request.form['tags'].strip():
-                for k in request.form['tags'].split(','):
-                    tag = datastore.tag_exists_by_name(k.strip())
-                    notification_urls = tag.get('notifications_urls') if tag and tag.get('notifications_urls') else None
-
-        if not notification_urls and not is_global_settings_form and not is_group_settings_form:
-            # In the global settings, use only what is typed currently in the text box
-            logger.debug("Test notification - Trying by global system settings notifications")
-            if datastore.data['settings']['application'].get('notification_urls'):
-                notification_urls = datastore.data['settings']['application']['notification_urls']
-
-        if not notification_urls:
-            return 'Error: No Notification URLs set/found'
-
-        for n_url in notification_urls:
-            if len(n_url.strip()):
-                if not apobj.add(n_url):
-                    return f'Error:  {n_url} is not a valid AppRise URL.'
-
-        try:
-            # use the same as when it is triggered, but then override it with the form test values
-            n_object = {
-                'watch_url': request.form.get('window_url', "https://changedetection.io"),
-                'notification_urls': notification_urls
-            }
-
-            # Only use if present, if not set in n_object it should use the default system value
-            if 'notification_format' in request.form and request.form['notification_format'].strip():
-                n_object['notification_format'] = request.form.get('notification_format', '').strip()
-
-            if 'notification_title' in request.form and request.form['notification_title'].strip():
-                n_object['notification_title'] = request.form.get('notification_title', '').strip()
-            elif datastore.data['settings']['application'].get('notification_title'):
-                n_object['notification_title'] = datastore.data['settings']['application'].get('notification_title')
-            else:
-                n_object['notification_title'] = "Test title"
-
-            if 'notification_body' in request.form and request.form['notification_body'].strip():
-                n_object['notification_body'] = request.form.get('notification_body', '').strip()
-            elif datastore.data['settings']['application'].get('notification_body'):
-                n_object['notification_body'] = datastore.data['settings']['application'].get('notification_body')
-            else:
-                n_object['notification_body'] = "Test body"
-
-            n_object['as_async'] = False
-            n_object.update(watch.extra_notification_token_values())
-            sent_obj = process_notification(n_object, datastore)
-
-        except Exception as e:
-            e_str = str(e)
-            # Remove this text which is not important and floods the container
-            e_str = e_str.replace(
-                "DEBUG - <class 'apprise.decorators.base.CustomNotifyPlugin.instantiate_plugin.<locals>.CustomNotifyPluginWrapper'>",
-                '')
-
-            return make_response(e_str, 400)
-
-        return 'OK - Sent test notifications'
-
-    return notification_blueprint

changedetectionio/blueprint/ui/templates/clear_all_history.html

@@ -1,49 +0,0 @@
-{% extends 'base.html' %} {% block content %}
-<div class="edit-form">
-  <div class="box-wrap inner">
-    <form
-      class="pure-form pure-form-stacked"
-      action="{{url_for('ui.clear_all_history')}}"
-      method="POST"
-    >
-      <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
-      <fieldset>
-        <div class="pure-control-group">
-          This will remove version history (snapshots) for ALL watches, but keep
-          your list of URLs! <br />
-          You may like to use the <strong>BACKUP</strong> link first.<br />
-        </div>
-        <br />
-        <div class="pure-control-group">
-          <label for="confirmtext">Confirmation text</label>
-          <input
-            type="text"
-            id="confirmtext"
-            required=""
-            name="confirmtext"
-            value=""
-            size="10"
-          />
-          <span class="pure-form-message-inline"
-            >Type in the word <strong>clear</strong> to confirm that you
-            understand.</span
-          >
-        </div>
-        <br />
-        <div class="pure-control-group">
-          <button type="submit" class="pure-button pure-button-primary">
-            Clear History!
-          </button>
-        </div>
-        <br />
-        <div class="pure-control-group">
-          <a href="{{url_for('watchlist.index')}}" class="pure-button button-cancel"
-            >Cancel</a
-          >
-        </div>
-      </fieldset>
-    </form>
-  </div>
-</div>
-
-{% endblock %}

changedetectionio/blueprint/ui/views.py

@@ -1,220 +0,0 @@
-from flask import Blueprint, request, redirect, url_for, flash, render_template, make_response, send_from_directory, abort
-from flask_login import current_user
-import os
-import time
-from copy import deepcopy
-
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio.auth_decorator import login_optionally_required
-from changedetectionio import html_tools
-
-def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
-    views_blueprint = Blueprint('ui_views', __name__, template_folder="../ui/templates")
-    
-    @views_blueprint.route("/preview/<string:uuid>", methods=['GET'])
-    @login_optionally_required
-    def preview_page(uuid):
-        content = []
-        versions = []
-        timestamp = None
-
-        # More for testing, possible to return the first/only
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
-
-        try:
-            watch = datastore.data['watching'][uuid]
-        except KeyError:
-            flash("No history found for the specified link, bad link?", "error")
-            return redirect(url_for('watchlist.index'))
-
-        system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
-        extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
-
-        is_html_webdriver = False
-        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
-            is_html_webdriver = True
-        triggered_line_numbers = []
-        if datastore.data['watching'][uuid].history_n == 0 and (watch.get_error_text() or watch.get_error_snapshot()):
-            flash("Preview unavailable - No fetch/check completed or triggers not reached", "error")
-        else:
-            # So prepare the latest preview or not
-            preferred_version = request.args.get('version')
-            versions = list(watch.history.keys())
-            timestamp = versions[-1]
-            if preferred_version and preferred_version in versions:
-                timestamp = preferred_version
-
-            try:
-                versions = list(watch.history.keys())
-                content = watch.get_history_snapshot(timestamp)
-
-                triggered_line_numbers = html_tools.strip_ignore_text(content=content,
-                                                                      wordlist=watch['trigger_text'],
-                                                                      mode='line numbers'
-                                                                      )
-
-            except Exception as e:
-                content.append({'line': f"File doesnt exist or unable to read timestamp {timestamp}", 'classes': ''})
-
-        output = render_template("preview.html",
-                                 content=content,
-                                 current_version=timestamp,
-                                 history_n=watch.history_n,
-                                 extra_stylesheets=extra_stylesheets,
-                                 extra_title=f" - Diff - {watch.label} @ {timestamp}",
-                                 triggered_line_numbers=triggered_line_numbers,
-                                 current_diff_url=watch['url'],
-                                 screenshot=watch.get_screenshot(),
-                                 watch=watch,
-                                 uuid=uuid,
-                                 is_html_webdriver=is_html_webdriver,
-                                 last_error=watch['last_error'],
-                                 last_error_text=watch.get_error_text(),
-                                 last_error_screenshot=watch.get_error_snapshot(),
-                                 versions=versions
-                                )
-
-        return output
-
-    @views_blueprint.route("/diff/<string:uuid>", methods=['GET', 'POST'])
-    @login_optionally_required
-    def diff_history_page(uuid):
-        from changedetectionio import forms
-
-        # More for testing, possible to return the first/only
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
-
-        extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
-        try:
-            watch = datastore.data['watching'][uuid]
-        except KeyError:
-            flash("No history found for the specified link, bad link?", "error")
-            return redirect(url_for('watchlist.index'))
-
-        # For submission of requesting an extract
-        extract_form = forms.extractDataForm(request.form)
-        if request.method == 'POST':
-            if not extract_form.validate():
-                flash("An error occurred, please see below.", "error")
-
-            else:
-                extract_regex = request.form.get('extract_regex').strip()
-                output = watch.extract_regex_from_all_history(extract_regex)
-                if output:
-                    watch_dir = os.path.join(datastore.datastore_path, uuid)
-                    response = make_response(send_from_directory(directory=watch_dir, path=output, as_attachment=True))
-                    response.headers['Content-type'] = 'text/csv'
-                    response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
-                    response.headers['Pragma'] = 'no-cache'
-                    response.headers['Expires'] = 0
-                    return response
-
-                flash('Nothing matches that RegEx', 'error')
-                redirect(url_for('ui_views.diff_history_page', uuid=uuid)+'#extract')
-
-        history = watch.history
-        dates = list(history.keys())
-
-        if len(dates) < 2:
-            flash("Not enough saved change detection snapshots to produce a report.", "error")
-            return redirect(url_for('watchlist.index'))
-
-        # Save the current newest history as the most recently viewed
-        datastore.set_last_viewed(uuid, time.time())
-
-        # Read as binary and force decode as UTF-8
-        # Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
-        from_version = request.args.get('from_version')
-        from_version_index = -2  # second newest
-        if from_version and from_version in dates:
-            from_version_index = dates.index(from_version)
-        else:
-            from_version = dates[from_version_index]
-
-        try:
-            from_version_file_contents = watch.get_history_snapshot(dates[from_version_index])
-        except Exception as e:
-            from_version_file_contents = f"Unable to read to-version at index {dates[from_version_index]}.\n"
-
-        to_version = request.args.get('to_version')
-        to_version_index = -1
-        if to_version and to_version in dates:
-            to_version_index = dates.index(to_version)
-        else:
-            to_version = dates[to_version_index]
-
-        try:
-            to_version_file_contents = watch.get_history_snapshot(dates[to_version_index])
-        except Exception as e:
-            to_version_file_contents = "Unable to read to-version at index{}.\n".format(dates[to_version_index])
-
-        screenshot_url = watch.get_screenshot()
-
-        system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
-
-        is_html_webdriver = False
-        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
-            is_html_webdriver = True
-
-        password_enabled_and_share_is_off = False
-        if datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False):
-            password_enabled_and_share_is_off = not datastore.data['settings']['application'].get('shared_diff_access')
-
-        output = render_template("diff.html",
-                                 current_diff_url=watch['url'],
-                                 from_version=str(from_version),
-                                 to_version=str(to_version),
-                                 extra_stylesheets=extra_stylesheets,
-                                 extra_title=f" - Diff - {watch.label}",
-                                 extract_form=extract_form,
-                                 is_html_webdriver=is_html_webdriver,
-                                 last_error=watch['last_error'],
-                                 last_error_screenshot=watch.get_error_snapshot(),
-                                 last_error_text=watch.get_error_text(),
-                                 left_sticky=True,
-                                 newest=to_version_file_contents,
-                                 newest_version_timestamp=dates[-1],
-                                 password_enabled_and_share_is_off=password_enabled_and_share_is_off,
-                                 from_version_file_contents=from_version_file_contents,
-                                 to_version_file_contents=to_version_file_contents,
-                                 screenshot=screenshot_url,
-                                 uuid=uuid,
-                                 versions=dates, # All except current/last
-                                 watch_a=watch
-                                 )
-
-        return output
-
-    @views_blueprint.route("/form/add/quickwatch", methods=['POST'])
-    @login_optionally_required
-    def form_quick_watch_add():
-        from changedetectionio import forms
-        form = forms.quickWatchForm(request.form)
-
-        if not form.validate():
-            for widget, l in form.errors.items():
-                flash(','.join(l), 'error')
-            return redirect(url_for('watchlist.index'))
-
-        url = request.form.get('url').strip()
-        if datastore.url_exists(url):
-            flash(f'Warning, URL {url} already exists', "notice")
-
-        add_paused = request.form.get('edit_and_watch_submit_button') != None
-        processor = request.form.get('processor', 'text_json_diff')
-        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tags').strip(), extras={'paused': add_paused, 'processor': processor})
-
-        if new_uuid:
-            if add_paused:
-                flash('Watch added in Paused state, saving will unpause.')
-                return redirect(url_for('ui.ui_edit.edit_page', uuid=new_uuid, unpause_on_save=1, tag=request.args.get('tag')))
-            else:
-                # Straight into the queue.
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
-                flash("Watch added.")
-
-        return redirect(url_for('watchlist.index', tag=request.args.get('tag','')))
-
-    return views_blueprint

changedetectionio/blueprint/watchlist/__init__.py

@@ -1,111 +0,0 @@
-import os
-import time
-
-from flask import Blueprint, request, make_response, render_template, redirect, url_for, flash, session
-from flask_login import current_user
-from flask_paginate import Pagination, get_page_parameter
-
-from changedetectionio import forms
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio.auth_decorator import login_optionally_required
-
-def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
-    watchlist_blueprint = Blueprint('watchlist', __name__, template_folder="templates")
-    
-    @watchlist_blueprint.route("/", methods=['GET'])
-    @login_optionally_required
-    def index():
-        active_tag_req = request.args.get('tag', '').lower().strip()
-        active_tag_uuid = active_tag = None
-
-        # Be sure limit_tag is a uuid
-        if active_tag_req:
-            for uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
-                if active_tag_req == tag.get('title', '').lower().strip() or active_tag_req == uuid:
-                    active_tag = tag
-                    active_tag_uuid = uuid
-                    break
-
-        # Redirect for the old rss path which used the /?rss=true
-        if request.args.get('rss'):
-            return redirect(url_for('rss.feed', tag=active_tag_uuid))
-
-        op = request.args.get('op')
-        if op:
-            uuid = request.args.get('uuid')
-            if op == 'pause':
-                datastore.data['watching'][uuid].toggle_pause()
-            elif op == 'mute':
-                datastore.data['watching'][uuid].toggle_mute()
-
-            datastore.needs_write = True
-            return redirect(url_for('watchlist.index', tag = active_tag_uuid))
-
-        # Sort by last_changed and add the uuid which is usually the key..
-        sorted_watches = []
-        with_errors = request.args.get('with_errors') == "1"
-        errored_count = 0
-        search_q = request.args.get('q').strip().lower() if request.args.get('q') else False
-        for uuid, watch in datastore.data['watching'].items():
-            if with_errors and not watch.get('last_error'):
-                continue
-
-            if active_tag_uuid and not active_tag_uuid in watch['tags']:
-                    continue
-            if watch.get('last_error'):
-                errored_count += 1
-
-            if search_q:
-                if (watch.get('title') and search_q in watch.get('title').lower()) or search_q in watch.get('url', '').lower():
-                    sorted_watches.append(watch)
-                elif watch.get('last_error') and search_q in watch.get('last_error').lower():
-                    sorted_watches.append(watch)
-            else:
-                sorted_watches.append(watch)
-
-        form = forms.quickWatchForm(request.form)
-        page = request.args.get(get_page_parameter(), type=int, default=1)
-        total_count = len(sorted_watches)
-
-        pagination = Pagination(page=page,
-                                total=total_count,
-                                per_page=datastore.data['settings']['application'].get('pager_size', 50), css_framework="semantic")
-
-        sorted_tags = sorted(datastore.data['settings']['application'].get('tags').items(), key=lambda x: x[1]['title'])
-        output = render_template(
-            "watch-overview.html",
-                                 active_tag=active_tag,
-                                 active_tag_uuid=active_tag_uuid,
-                                 app_rss_token=datastore.data['settings']['application'].get('rss_access_token'),
-                                 datastore=datastore,
-                                 errored_count=errored_count,
-                                 form=form,
-                                 guid=datastore.data['app_guid'],
-                                 has_proxies=datastore.proxy_list,
-                                 has_unviewed=datastore.has_unviewed,
-                                 hosted_sticky=os.getenv("SALTED_PASS", False) == False,
-                                 now_time_server=time.time(),
-                                 pagination=pagination,
-                                 queued_uuids=[q_uuid.item['uuid'] for q_uuid in update_q.queue],
-                                 search_q=request.args.get('q', '').strip(),
-                                 sort_attribute=request.args.get('sort') if request.args.get('sort') else request.cookies.get('sort'),
-                                 sort_order=request.args.get('order') if request.args.get('order') else request.cookies.get('order'),
-                                 system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),
-                                 tags=sorted_tags,
-                                 watches=sorted_watches
-                                 )
-
-        if session.get('share-link'):
-            del(session['share-link'])
-
-        resp = make_response(output)
-
-        # The template can run on cookie or url query info
-        if request.args.get('sort'):
-            resp.set_cookie('sort', request.args.get('sort'))
-        if request.args.get('order'):
-            resp.set_cookie('order', request.args.get('order'))
-
-        return resp
-        
-    return watchlist_blueprint

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

@@ -1,254 +0,0 @@
-{% extends 'base.html' %}
-{% block content %}
-{% from '_helpers.html' import render_simple_field, render_field, render_nolabel_field, sort_by_title %}
-<script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
-<script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
-<script>let nowtimeserver={{ now_time_server }};</script>
-
-<style>
-.checking-now .last-checked {
-    background-image: linear-gradient(to bottom, transparent 0%, rgba(0,0,0,0.05) 40%, rgba(0,0,0,0.1) 100%);
-    background-size: 0 100%;
-    background-repeat: no-repeat;
-    transition: background-size 0.9s ease
-}
-</style>
-<div class="box">
-
-    <form class="pure-form" action="{{ url_for('ui.ui_views.form_quick_watch_add', tag=active_tag_uuid) }}" method="POST" id="new-watch-form">
-        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
-        <fieldset>
-            <legend>Add a new change detection watch</legend>
-            <div id="watch-add-wrapper-zone">
-
-                    {{ render_nolabel_field(form.url, placeholder="https://...", required=true) }}
-                    {{ render_nolabel_field(form.tags, value=active_tag.title if active_tag_uuid else '', placeholder="watch label / tag") }}
-                    {{ render_nolabel_field(form.watch_submit_button, title="Watch this URL!" ) }}
-                    {{ render_nolabel_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
-            </div>
-            <div id="quick-watch-processor-type">
-                {{ render_simple_field(form.processor) }}
-            </div>
-
-        </fieldset>
-        <span style="color:#eee; font-size: 80%;"><img alt="Create a shareable link" style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" > Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></span>
-    </form>
-
-    <form class="pure-form" action="{{ url_for('ui.form_watch_list_checkbox_operations') }}" method="POST" id="watch-list-form">
-    <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
-    <input type="hidden" id="op_extradata" name="op_extradata" value="" >
-    <div id="checkbox-operations">
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="pause">Pause</button>
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="unpause">UnPause</button>
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="mute">Mute</button>
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="unmute">UnMute</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="recheck">Recheck</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="assign-tag" id="checkbox-assign-tag">Tag</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="mark-viewed">Mark viewed</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default">Use default notification</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="clear-errors">Clear errors</button>
-        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="clear-history">Clear/reset history</button>
-        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="delete">Delete</button>
-    </div>
-    {% if watches|length >= pagination.per_page %}
-        {{ pagination.info }}
-    {% endif %}
-    {% if search_q %}<div id="search-result-info">Searching "<strong><i>{{search_q}}</i></strong>"</div>{% endif %}
-    <div>
-        <a href="{{url_for('watchlist.index')}}" class="pure-button button-tag {{'active' if not active_tag_uuid }}">All</a>
-
-    <!-- tag list -->
-    {% for uuid, tag in tags %}
-        {% if tag != "" %}
-            <a href="{{url_for('watchlist.index', tag=uuid) }}" class="pure-button button-tag {{'active' if active_tag_uuid == uuid }}">{{ tag.title }}</a>
-        {% endif %}
-    {% endfor %}
-    </div>
-
-    {% set sort_order = sort_order or 'asc' %}
-    {% set sort_attribute = sort_attribute or 'last_changed'  %}
-    {% set pagination_page = request.args.get('page', 0) %}
-    {% set cols_required = 6 %}
-    {% set any_has_restock_price_processor = datastore.any_watches_have_processor_by_name("restock_diff") %}
-    {% if any_has_restock_price_processor %}
-        {% set cols_required = cols_required + 1 %}
-    {% endif %}
-
-    <div id="watch-table-wrapper">
-
-        <table class="pure-table pure-table-striped watch-table">
-            <thead>
-            <tr>
-                {% set link_order = "desc" if sort_order  == 'asc' else "asc" %}
-                {% set arrow_span = "" %}
-                <th><input style="vertical-align: middle" type="checkbox" id="check-all" > <a class="{{ 'active '+link_order if sort_attribute == 'date_created' else 'inactive' }}"  href="{{url_for('watchlist.index', sort='date_created', order=link_order, tag=active_tag_uuid)}}"># <span class='arrow {{link_order}}'></span></a></th>
-                <th class="empty-cell"></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('watchlist.index', sort='label', order=link_order, tag=active_tag_uuid)}}">Website <span class='arrow {{link_order}}'></span></a></th>
-             {% if any_has_restock_price_processor %}
-                <th>Restock &amp; Price</th>
-             {% endif %}
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('watchlist.index', sort='last_checked', order=link_order, tag=active_tag_uuid)}}"><span class="hide-on-mobile">Last</span> Checked <span class='arrow {{link_order}}'></span></a></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('watchlist.index', sort='last_changed', order=link_order, tag=active_tag_uuid)}}"><span class="hide-on-mobile">Last</span> Changed <span class='arrow {{link_order}}'></span></a></th>
-                <th class="empty-cell"></th>
-            </tr>
-            </thead>
-            <tbody>
-            {% if not watches|length %}
-            <tr>
-                <td colspan="{{ cols_required }}" style="text-wrap: wrap;">No website watches configured, please add a URL in the box above, or <a href="{{ url_for('imports.import_page')}}" >import a list</a>.</td>
-            </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 %}
-                {% set checking_now = is_checking_now(watch) %}
-            <tr id="{{ watch.uuid }}"
-                class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }} processor-{{ watch['processor'] }}
-                {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
-                {% if watch.last_notification_error is defined and watch.last_notification_error != False %}error{% endif %}
-                {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
-                {% if is_unviewed %}unviewed{% endif %}
-                {% if watch.has_restock_info %} has-restock-info {% if watch['restock']['in_stock'] %}in-stock{% else %}not-in-stock{% endif %} {% else %}no-restock-info{% endif %}
-                {% if watch.uuid in queued_uuids %}queued{% endif %}
-                {% if checking_now %}checking-now{% endif %}
-                ">
-                <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span>{{ loop.index+pagination.skip }}</span></td>
-                <td class="inline watch-controls">
-                    {% if not watch.paused %}
-                    <a class="state-off" href="{{url_for('watchlist.index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause" ></a>
-                    {% else %}
-                    <a class="state-on" href="{{url_for('watchlist.index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause" ></a>
-                    {% endif %}
-                    {% set mute_label = 'UnMute notification' if watch.notification_muted else 'Mute notification' %}
-                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('watchlist.index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="{{ mute_label }}" title="{{ mute_label }}" class="icon icon-mute" ></a>
-                </td>
-                <td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
-                    <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
-                    <a class="link-spread" href="{{url_for('ui.form_share_put_watch', uuid=watch.uuid)}}"><img src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" ></a>
-
-                    {% if watch.get_fetch_backend == "html_webdriver"
-                         or (  watch.get_fetch_backend == "system" and system_default_fetcher == 'html_webdriver'  )
-                         or "extra_browser_" in watch.get_fetch_backend
-                    %}
-                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='google-chrome-icon.png')}}" alt="Using a Chrome browser" title="Using a Chrome browser" >
-                    {% endif %}
-
-                    {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" >{% endif %}
-                    {% if watch.has_browser_steps %}<img class="status-icon status-browsersteps" src="{{url_for('static_content', group='images', filename='steps.svg')}}" title="Browser Steps is enabled" >{% endif %}
-                    {% if watch.last_error is defined and watch.last_error != False %}
-                    <div class="fetch-error">{{ watch.last_error }}
-
-                        {% if '403' in watch.last_error %}
-                            {% if has_proxies %}
-                                <a href="{{ url_for('settings.settings_page', uuid=watch.uuid) }}#proxies">Try other proxies/location</a>&nbsp;
-                            {% endif %}
-                            <a href="{{ url_for('settings.settings_page', uuid=watch.uuid) }}#proxies">Try adding external proxies/locations</a>
-                        
-                        {% endif %}
-                        {% if 'empty result or contain only an image' in watch.last_error %}
-                            <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Detecting-changes-in-images">more help here</a>.
-                        {% endif %}
-                    </div>
-                    {% endif %}
-                    {% if watch.last_notification_error is defined and watch.last_notification_error != False %}
-                    <div class="fetch-error notification-error"><a href="{{url_for('settings.notification_logs')}}">{{ watch.last_notification_error }}</a></div>
-                    {% endif %}
-
-                    {% if watch['processor'] == 'text_json_diff'  %}
-                        {% if watch['has_ldjson_price_data'] and not watch['track_ldjson_price_data']  %}
-                        <div class="ldjson-price-track-offer">Switch to Restock & Price watch mode? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
-                        {% endif %}
-                    {% endif %}
-                    {% if watch['processor'] == 'restock_diff' %}
-                        <span class="tracking-ldjson-price-data" title="Automatically following embedded price information"><img src="{{url_for('static_content', group='images', filename='price-tag-icon.svg')}}"  class="status-icon price-follow-tag-icon" > Price</span>
-                    {% endif %}
-                    {% for watch_tag_uuid, watch_tag in datastore.get_all_tags_for_watch(watch['uuid']).items() %}
-                      <span class="watch-tag-list">{{ watch_tag.title }}</span>
-                    {% endfor %}
-                </td>
-            <!-- @todo make it so any watch handler obj can expose this --->
-{% if any_has_restock_price_processor %}
-                <td class="restock-and-price">
-                    {% if watch['processor'] == 'restock_diff'  %}
-                        {% if watch.has_restock_info %}
-                            <span class="restock-label {{'in-stock' if watch['restock']['in_stock'] else 'not-in-stock' }}" title="Detecting restock and price">
-                                <!-- maybe some object watch['processor'][restock_diff] or.. -->
-                                 {% if watch['restock']['in_stock'] %} In stock {% else %} Not in stock {% endif %}
-                            </span>
-                        {% endif %}
-
-                        {% if watch.get('restock') and watch['restock']['price'] != None %}
-                            {% if watch['restock']['price'] != None %}
-                                <span class="restock-label price" title="Price">
-                                {{ watch['restock']['price']|format_number_locale }} {{ watch['restock']['currency'] }}
-                                </span>
-                            {% endif %}
-                        {% elif not watch.has_restock_info %}
-                            <span class="restock-label error">No information</span>
-                        {% endif %}
-                    {% endif %}
-                </td>
-{% endif %}
-            {#last_checked becomes fetch-start-time#}
-                <td class="last-checked" data-timestamp="{{ watch.last_checked }}" {% if checking_now %} data-fetchduration={{ watch.fetch_time }} data-eta_complete="{{ watch.last_checked+watch.fetch_time }}" {% endif %} >
-                    {% if checking_now %}
-                        <span class="spinner"></span><span> Checking now</span>
-                    {% else %}
-                        {{watch|format_last_checked_time|safe}}</td>
-                    {% endif %}
-
-                <td class="last-changed" data-timestamp="{{ watch.last_changed }}">{% if watch.history_n >=2 and watch.last_changed >0 %}
-                    {{watch.last_changed|format_timestamp_timeago}}
-                    {% else %}
-                    Not yet
-                    {% endif %}
-                </td>
-                <td>
-                    <a {% if watch.uuid in queued_uuids %}disabled="true"{% endif %} href="{{ url_for('ui.form_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}"
-                       class="recheck pure-button pure-button-primary">{% if watch.uuid in queued_uuids %}Queued{% else %}Recheck{% endif %}</a>
-                    <a href="{{ url_for('ui.ui_edit.edit_page', uuid=watch.uuid, tag=active_tag_uuid)}}#general" class="pure-button pure-button-primary">Edit</a>
-                    {% if watch.history_n >= 2 %}
-
-                        {% set open_diff_in_new_tab = datastore.data['settings']['application']['ui'].get('open_diff_in_new_tab') %}
-                        {% set target_attr = ' target="' ~ watch.uuid ~ '"' if open_diff_in_new_tab else '' %}
-
-                        {%  if is_unviewed %}
-                           <a href="{{ url_for('ui.ui_views.diff_history_page', uuid=watch.uuid, from_version=watch.get_from_version_based_on_last_viewed) }}" {{target_attr}} class="pure-button pure-button-primary diff-link">History</a>
-                        {% else %}
-                           <a href="{{ url_for('ui.ui_views.diff_history_page', uuid=watch.uuid)}}" {{target_attr}} class="pure-button pure-button-primary diff-link">History</a>
-                        {% endif %}
-
-                    {% else %}
-                        {% if watch.history_n == 1 or (watch.history_n ==0 and watch.error_text_ctime )%}
-                            <a href="{{ url_for('ui.ui_views.preview_page', uuid=watch.uuid)}}" {{target_attr}} class="pure-button pure-button-primary">Preview</a>
-                        {% endif %}
-                    {% endif %}
-                </td>
-            </tr>
-            {% endfor %}
-            </tbody>
-        </table>
-        <ul id="post-list-buttons">
-            {% if errored_count %}
-            <li>
-                <a href="{{url_for('watchlist.index', with_errors=1, tag=request.args.get('tag')) }}" class="pure-button button-tag button-error ">With errors ({{ errored_count }})</a>
-            </li>
-            {% endif %}
-            {% if has_unviewed %}
-            <li>
-                <a href="{{url_for('ui.mark_all_viewed',with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Mark all viewed</a>
-            </li>
-            {% endif %}
-            <li>
-               <a href="{{ url_for('ui.form_watch_checknow', tag=active_tag_uuid, with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Recheck
-                all {% if active_tag_uuid %} in "{{active_tag.title}}"{%endif%}</a>
-            </li>
-            <li>
-                <a href="{{ url_for('rss.feed', tag=active_tag_uuid, token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='generic_feed-icon.svg')}}" height="15"></a>
-            </li>
-        </ul>
-        {{ pagination.links }}
-    </div>
-    </form>
-</div>
-{% endblock %}

changedetectionio/conditions/__init__.py

@@ -1,134 +0,0 @@
-from flask import Blueprint
-
-from json_logic.builtins import BUILTINS
-
-from .exceptions import EmptyConditionRuleRowNotUsable
-from .pluggy_interface import plugin_manager  # Import the pluggy plugin manager
-from . import default_plugin
-
-# List of all supported JSON Logic operators
-operator_choices = [
-    (None, "Choose one - Operator"),
-    (">", "Greater Than"),
-    ("<", "Less Than"),
-    (">=", "Greater Than or Equal To"),
-    ("<=", "Less Than or Equal To"),
-    ("==", "Equals"),
-    ("!=", "Not Equals"),
-    ("in", "Contains"),
-    ("!in", "Does Not Contain"),
-]
-
-# Fields available in the rules
-field_choices = [
-    (None, "Choose one - Field"),
-]
-
-# The data we will feed the JSON Rules to see if it passes the test/conditions or not
-EXECUTE_DATA = {}
-
-
-# Define the extended operations dictionary
-CUSTOM_OPERATIONS = {
-    **BUILTINS,  # Include all standard operators
-}
-
-def filter_complete_rules(ruleset):
-    rules = [
-        rule for rule in ruleset
-        if all(value not in ("", False, "None", None) for value in [rule["operator"], rule["field"], rule["value"]])
-    ]
-    return rules
-
-def convert_to_jsonlogic(logic_operator: str, rule_dict: list):
-    """
-    Convert a structured rule dict into a JSON Logic rule.
-
-    :param rule_dict: Dictionary containing conditions.
-    :return: JSON Logic rule as a dictionary.
-    """
-
-
-    json_logic_conditions = []
-
-    for condition in rule_dict:
-        operator = condition["operator"]
-        field = condition["field"]
-        value = condition["value"]
-
-        if not operator or operator == 'None' or not value or not field:
-            raise EmptyConditionRuleRowNotUsable()
-
-        # Convert value to int/float if possible
-        try:
-            if isinstance(value, str) and "." in value and str != "None":
-                value = float(value)
-            else:
-                value = int(value)
-        except (ValueError, TypeError):
-            pass  # Keep as a string if conversion fails
-
-        # Handle different JSON Logic operators properly
-        if operator == "in":
-            json_logic_conditions.append({"in": [value, {"var": field}]})  # value first
-        elif operator in ("!", "!!", "-"):
-            json_logic_conditions.append({operator: [{"var": field}]})  # Unary operators
-        elif operator in ("min", "max", "cat"):
-            json_logic_conditions.append({operator: value})  # Multi-argument operators
-        else:
-            json_logic_conditions.append({operator: [{"var": field}, value]})  # Standard binary operators
-
-    return {logic_operator: json_logic_conditions} if len(json_logic_conditions) > 1 else json_logic_conditions[0]
-
-
-def execute_ruleset_against_all_plugins(current_watch_uuid: str, application_datastruct, ephemeral_data={} ):
-    """
-    Build our data and options by calling our plugins then pass it to jsonlogic and see if the conditions pass
-
-    :param ruleset: JSON Logic rule dictionary.
-    :param extracted_data: Dictionary containing the facts.   <-- maybe the app struct+uuid
-    :return: Dictionary of plugin results.
-    """
-    from json_logic import jsonLogic
-
-    EXECUTE_DATA = {}
-    result = True
-    
-    watch = application_datastruct['watching'].get(current_watch_uuid)
-
-    if watch and watch.get("conditions"):
-        logic_operator = "and" if watch.get("conditions_match_logic", "ALL") == "ALL" else "or"
-        complete_rules = filter_complete_rules(watch['conditions'])
-        if complete_rules:
-            # Give all plugins a chance to update the data dict again (that we will test the conditions against)
-            for plugin in plugin_manager.get_plugins():
-                new_execute_data = plugin.add_data(current_watch_uuid=current_watch_uuid,
-                                                   application_datastruct=application_datastruct,
-                                                   ephemeral_data=ephemeral_data)
-
-                if new_execute_data and isinstance(new_execute_data, dict):
-                    EXECUTE_DATA.update(new_execute_data)
-
-            # Create the ruleset
-            ruleset = convert_to_jsonlogic(logic_operator=logic_operator, rule_dict=complete_rules)
-            
-            # Pass the custom operations dictionary to jsonLogic
-            if not jsonLogic(logic=ruleset, data=EXECUTE_DATA, operations=CUSTOM_OPERATIONS):
-                result = False
-
-    return {'executed_data': EXECUTE_DATA, 'result': result}
-
-# Load plugins dynamically
-for plugin in plugin_manager.get_plugins():
-    new_ops = plugin.register_operators()
-    if isinstance(new_ops, dict):
-        CUSTOM_OPERATIONS.update(new_ops)
-
-    new_operator_choices = plugin.register_operator_choices()
-    if isinstance(new_operator_choices, list):
-        operator_choices.extend(new_operator_choices)
-
-    new_field_choices = plugin.register_field_choices()
-    if isinstance(new_field_choices, list):
-        field_choices.extend(new_field_choices)
-

changedetectionio/conditions/blueprint.py

@@ -1,81 +0,0 @@
-# Flask Blueprint Definition
-import json
-
-from flask import Blueprint
-
-from changedetectionio.conditions import execute_ruleset_against_all_plugins
-
-
-def construct_blueprint(datastore):
-    from changedetectionio.flask_app import login_optionally_required
-
-    conditions_blueprint = Blueprint('conditions', __name__, template_folder="templates")
-
-    @conditions_blueprint.route("/<string:watch_uuid>/verify-condition-single-rule", methods=['POST'])
-    @login_optionally_required
-    def verify_condition_single_rule(watch_uuid):
-        """Verify a single condition rule against the current snapshot"""
-        from changedetectionio.processors.text_json_diff import prepare_filter_prevew
-        from flask import request, jsonify
-        from copy import deepcopy
-
-        ephemeral_data = {}
-
-        # Get the watch data
-        watch = datastore.data['watching'].get(watch_uuid)
-        if not watch:
-            return jsonify({'status': 'error', 'message': 'Watch not found'}), 404
-
-        # First use prepare_filter_prevew to process the form data
-        # This will return text_after_filter which is after all current form settings are applied
-        # Create ephemeral data with the text from the current snapshot
-
-        try:
-            # Call prepare_filter_prevew to get a processed version of the content with current form settings
-            # We'll ignore the returned response and just use the datastore which is modified by the function
-
-            # this should apply all filters etc so then we can run the CONDITIONS against the final output text
-            result = prepare_filter_prevew(datastore=datastore,
-                                           form_data=request.form,
-                                           watch_uuid=watch_uuid)
-
-            ephemeral_data['text'] = result.get('after_filter', '')
-            # Create a temporary watch data structure with this single rule
-            tmp_watch_data = deepcopy(datastore.data['watching'].get(watch_uuid))
-
-            # Override the conditions in the temporary watch
-            rule_json = request.args.get("rule")
-            rule = json.loads(rule_json) if rule_json else None
-
-            # Should be key/value of field, operator, value
-            tmp_watch_data['conditions'] = [rule]
-            tmp_watch_data['conditions_match_logic'] = "ALL"  # Single rule, so use ALL
-
-            # Create a temporary application data structure for the rule check
-            temp_app_data = {
-                'watching': {
-                    watch_uuid: tmp_watch_data
-                }
-            }
-
-            # Execute the rule against the current snapshot with form data
-            result = execute_ruleset_against_all_plugins(
-                current_watch_uuid=watch_uuid,
-                application_datastruct=temp_app_data,
-                ephemeral_data=ephemeral_data
-            )
-
-            return jsonify({
-                'status': 'success',
-                'result': result.get('result'),
-                'data': result.get('executed_data'),
-                'message': 'Condition passes' if result else 'Condition does not pass'
-            })
-
-        except Exception as e:
-            return jsonify({
-                'status': 'error',
-                'message': f'Error verifying condition: {str(e)}'
-            }), 500
-
-    return conditions_blueprint

changedetectionio/conditions/default_plugin.py

@@ -1,78 +0,0 @@
-import re
-
-import pluggy
-from price_parser import Price
-from loguru import logger
-
-hookimpl = pluggy.HookimplMarker("changedetectionio_conditions")
-
-
-@hookimpl
-def register_operators():
-    def starts_with(_, text, prefix):
-        return text.lower().strip().startswith(str(prefix).strip().lower())
-
-    def ends_with(_, text, suffix):
-        return text.lower().strip().endswith(str(suffix).strip().lower())
-
-    def length_min(_, text, strlen):
-        return len(text) >= int(strlen)
-
-    def length_max(_, text, strlen):
-        return len(text) <= int(strlen)
-
-    # ✅ Custom function for case-insensitive regex matching
-    def contains_regex(_, text, pattern):
-        """Returns True if `text` contains `pattern` (case-insensitive regex match)."""
-        return bool(re.search(pattern, str(text), re.IGNORECASE))
-
-    # ✅ Custom function for NOT matching case-insensitive regex
-    def not_contains_regex(_, text, pattern):
-        """Returns True if `text` does NOT contain `pattern` (case-insensitive regex match)."""
-        return not bool(re.search(pattern, str(text), re.IGNORECASE))
-
-    return {
-        "!contains_regex": not_contains_regex,
-        "contains_regex": contains_regex,
-        "ends_with": ends_with,
-        "length_max": length_max,
-        "length_min": length_min,
-        "starts_with": starts_with,
-    }
-
-@hookimpl
-def register_operator_choices():
-    return [
-        ("starts_with", "Text Starts With"),
-        ("ends_with", "Text Ends With"),
-        ("length_min", "Length minimum"),
-        ("length_max", "Length maximum"),
-        ("contains_regex", "Text Matches Regex"),
-        ("!contains_regex", "Text Does NOT Match Regex"),
-    ]
-
-@hookimpl
-def register_field_choices():
-    return [
-        ("extracted_number", "Extracted number after 'Filters & Triggers'"),
-#        ("meta_description", "Meta Description"),
-#        ("meta_keywords", "Meta Keywords"),
-        ("page_filtered_text", "Page text after 'Filters & Triggers'"),
-        #("page_title", "Page <title>"), # actual page title <title>
-    ]
-
-@hookimpl
-def add_data(current_watch_uuid, application_datastruct, ephemeral_data):
-
-    res = {}
-    if 'text' in ephemeral_data:
-        res['page_filtered_text'] = ephemeral_data['text']
-
-        # Better to not wrap this in try/except so that the UI can see any errors
-        price = Price.fromstring(ephemeral_data.get('text'))
-        if price and price.amount != None:
-            # This is slightly misleading, it's extracting a PRICE not a Number..
-            res['extracted_number'] = float(price.amount)
-            logger.debug(f"Extracted number result: '{price}' - returning float({res['extracted_number']})")
-
-    return res

changedetectionio/conditions/exceptions.py

@@ -1,6 +0,0 @@
-class EmptyConditionRuleRowNotUsable(Exception):
-    def __init__(self):
-        super().__init__("One of the 'conditions' rulesets is incomplete, cannot run.")
-
-    def __str__(self):
-        return self.args[0]

changedetectionio/conditions/form.py

@@ -1,44 +0,0 @@
-# Condition Rule Form (for each rule row)
-from wtforms import Form, SelectField, StringField, validators
-from wtforms import validators
-
-class ConditionFormRow(Form):
-
-    # ✅ Ensure Plugins Are Loaded BEFORE Importing Choices
-    from changedetectionio.conditions import plugin_manager
-    from changedetectionio.conditions import operator_choices, field_choices
-    field = SelectField(
-        "Field",
-        choices=field_choices,
-        validators=[validators.Optional()]
-    )
-
-    operator = SelectField(
-        "Operator",
-        choices=operator_choices,
-        validators=[validators.Optional()]
-    )
-
-    value = StringField("Value", validators=[validators.Optional()], render_kw={"placeholder": "A value"})
-
-    def validate(self, extra_validators=None):
-        # First, run the default validators
-        if not super().validate(extra_validators):
-            return False
-
-        # Custom validation logic
-        # If any of the operator/field/value is set, then they must be all set
-        if any(value not in ("", False, "None", None) for value in [self.operator.data, self.field.data, self.value.data]):
-            if not self.operator.data or self.operator.data == 'None':
-                self.operator.errors.append("Operator is required.")
-                return False
-
-            if not self.field.data or self.field.data == 'None':
-                self.field.errors.append("Field is required.")
-                return False
-
-            if not self.value.data:
-                self.value.errors.append("Value is required.")
-                return False
-
-        return True  # Only return True if all conditions pass

changedetectionio/conditions/pluggy_interface.py

@@ -1,44 +0,0 @@
-import pluggy
-from . import default_plugin  # Import the default plugin
-
-# ✅ Ensure that the namespace in HookspecMarker matches PluginManager
-PLUGIN_NAMESPACE = "changedetectionio_conditions"
-
-hookspec = pluggy.HookspecMarker(PLUGIN_NAMESPACE)
-hookimpl = pluggy.HookimplMarker(PLUGIN_NAMESPACE)
-
-
-class ConditionsSpec:
-    """Hook specifications for extending JSON Logic conditions."""
-
-    @hookspec
-    def register_operators():
-        """Return a dictionary of new JSON Logic operators."""
-        pass
-
-    @hookspec
-    def register_operator_choices():
-        """Return a list of new operator choices."""
-        pass
-
-    @hookspec
-    def register_field_choices():
-        """Return a list of new field choices."""
-        pass
-
-    @hookspec
-    def add_data(current_watch_uuid, application_datastruct, ephemeral_data):
-        """Add to the datadict"""
-        pass
-
-# ✅ Set up Pluggy Plugin Manager
-plugin_manager = pluggy.PluginManager(PLUGIN_NAMESPACE)
-
-# ✅ Register hookspecs (Ensures they are detected)
-plugin_manager.add_hookspecs(ConditionsSpec)
-
-# ✅ Register built-in plugins manually
-plugin_manager.register(default_plugin, "default_plugin")
-
-# ✅ Discover installed plugins from external packages (if any)
-plugin_manager.load_setuptools_entrypoints(PLUGIN_NAMESPACE)

changedetectionio/content_fetchers/__init__.py

@@ -1,63 +0,0 @@
-import sys
-from changedetectionio.strtobool import strtobool
-from loguru import logger
-from changedetectionio.content_fetchers.exceptions import BrowserStepsStepException
-import os
-
-# Visual Selector scraper - 'Button' is there because some sites have <button>OUT OF STOCK</button>.
-visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4,header,footer,section,article,aside,details,main,nav,section,summary,button'
-
-SCREENSHOT_MAX_HEIGHT_DEFAULT = 20000
-SCREENSHOT_DEFAULT_QUALITY = 40
-
-# Maximum total height for the final image (When in stitch mode).
-# We limit this to 16000px due to the huge amount of RAM that was being used
-# Example: 16000 × 1400 × 3 = 67,200,000 bytes ≈ 64.1 MB (not including buffers in PIL etc)
-SCREENSHOT_MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
-
-# The size at which we will switch to stitching method, when below this (and
-# MAX_TOTAL_HEIGHT which can be set by a user) we will use the default
-# screenshot method.
-SCREENSHOT_SIZE_STITCH_THRESHOLD = 8000
-
-# 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
-
-
-import importlib.resources
-XPATH_ELEMENT_JS = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text(encoding='utf-8')
-INSTOCK_DATA_JS = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text(encoding='utf-8')
-
-
-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

@@ -1,175 +0,0 @@
-import os
-from abc import abstractmethod
-from loguru import logger
-
-from changedetectionio.content_fetchers import BrowserStepsStepException
-
-
-def manage_user_agent(headers, current_ua=''):
-    """
-    Basic setting of user-agent
-
-    NOTE!!!!!! The service that does the actual Chrome fetching should handle any anti-robot techniques
-    THERE ARE MANY WAYS THAT IT CAN BE DETECTED AS A ROBOT!!
-    This does not take care of
-    - Scraping of 'navigator' (platform, productSub, vendor, oscpu etc etc) browser object (navigator.appVersion) etc
-    - TCP/IP fingerprint JA3 etc
-    - Graphic rendering fingerprinting
-    - Your IP being obviously in a pool of bad actors
-    - Too many requests
-    - Scraping of SCH-UA browser replies (thanks google!!)
-    - Scraping of ServiceWorker, new window calls etc
-
-    See https://filipvitas.medium.com/how-to-set-user-agent-header-with-puppeteer-js-and-not-fail-28c7a02165da
-    Puppeteer requests https://github.com/dgtlmoon/pyppeteerstealth
-
-    :param page:
-    :param headers:
-    :return:
-    """
-    # Ask it what the user agent is, if its obviously ChromeHeadless, switch it to the default
-    ua_in_custom_headers = headers.get('User-Agent')
-    if ua_in_custom_headers:
-        return ua_in_custom_headers
-
-    if not ua_in_custom_headers and current_ua:
-        current_ua = current_ua.replace('HeadlessChrome', 'Chrome')
-        return current_ua
-
-    return None
-
-
-class Fetcher():
-    browser_connection_is_custom = None
-    browser_connection_url = None
-    browser_steps = None
-    browser_steps_screenshot_path = None
-    content = None
-    error = None
-    fetcher_description = "No description"
-    headers = {}
-    instock_data = None
-    instock_data_js = ""
-    status_code = None
-    webdriver_js_execute_code = None
-    xpath_data = None
-    xpath_element_js = ""
-
-    # Will be needed in the future by the VisualSelector, always get this where possible.
-    screenshot = False
-    system_http_proxy = os.getenv('HTTP_PROXY')
-    system_https_proxy = os.getenv('HTTPS_PROXY')
-
-    # Time ONTOP of the system defined env minimum time
-    render_extract_delay = 0
-
-    @abstractmethod
-    def get_error(self):
-        return self.error
-
-    @abstractmethod
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False,
-            empty_pages_are_a_change=False):
-        # Should set self.error, self.status_code and self.content
-        pass
-
-    @abstractmethod
-    def quit(self, watch=None):
-        return
-
-    @abstractmethod
-    def get_last_status_code(self):
-        return self.status_code
-
-    @abstractmethod
-    def screenshot_step(self, step_n):
-        if self.browser_steps_screenshot_path and not os.path.isdir(self.browser_steps_screenshot_path):
-            logger.debug(f"> Creating data dir {self.browser_steps_screenshot_path}")
-            os.mkdir(self.browser_steps_screenshot_path)
-        return None
-
-    @abstractmethod
-    # Return true/false if this checker is ready to run, in the case it needs todo some special config check etc
-    def is_ready(self):
-        return True
-
-    def get_all_headers(self):
-        """
-        Get all headers but ensure all keys are lowercase
-        :return:
-        """
-        return {k.lower(): v for k, v in self.headers.items()}
-
-    def browser_steps_get_valid_steps(self):
-        if self.browser_steps is not None and len(self.browser_steps):
-            valid_steps = list(filter(
-                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one'),
-                self.browser_steps))
-
-            # Just incase they selected Goto site by accident with older JS
-            if valid_steps and valid_steps[0]['operation'] == 'Goto site':
-                del(valid_steps[0])
-
-            return valid_steps
-
-        return None
-
-    def iterate_browser_steps(self, start_url=None):
-        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
-        from playwright._impl._errors import TimeoutError, Error
-        from changedetectionio.safe_jinja import render as jinja_render
-        step_n = 0
-
-        if self.browser_steps is not None and len(self.browser_steps):
-            interface = steppable_browser_interface(start_url=start_url)
-            interface.page = self.page
-            valid_steps = self.browser_steps_get_valid_steps()
-
-            for step in valid_steps:
-                step_n += 1
-                logger.debug(f">> Iterating check - browser Step n {step_n} - {step['operation']}...")
-                self.screenshot_step("before-" + str(step_n))
-                self.save_step_html("before-" + str(step_n))
-
-                try:
-                    optional_value = step['optional_value']
-                    selector = step['selector']
-                    # Support for jinja2 template in step values, with date module added
-                    if '{%' in step['optional_value'] or '{{' in step['optional_value']:
-                        optional_value = jinja_render(template_str=step['optional_value'])
-                    if '{%' in step['selector'] or '{{' in step['selector']:
-                        selector = jinja_render(template_str=step['selector'])
-
-                    getattr(interface, "call_action")(action_name=step['operation'],
-                                                      selector=selector,
-                                                      optional_value=optional_value)
-                    self.screenshot_step(step_n)
-                    self.save_step_html(step_n)
-                except (Error, TimeoutError) as e:
-                    logger.debug(str(e))
-                    # Stop processing here
-                    raise BrowserStepsStepException(step_n=step_n, original_e=e)
-
-    # It's always good to reset these
-    def delete_browser_steps_screenshots(self):
-        import glob
-        if self.browser_steps_screenshot_path is not None:
-            dest = os.path.join(self.browser_steps_screenshot_path, 'step_*.jpeg')
-            files = glob.glob(dest)
-            for f in files:
-                if os.path.isfile(f):
-                    os.unlink(f)
-
-    def save_step_html(self, step_n):
-        if self.browser_steps_screenshot_path and not os.path.isdir(self.browser_steps_screenshot_path):
-            logger.debug(f"> Creating data dir {self.browser_steps_screenshot_path}")
-            os.mkdir(self.browser_steps_screenshot_path)
-        pass

changedetectionio/content_fetchers/exceptions/__init__.py

@@ -1,97 +0,0 @@
-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 changedetectionio.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='', xpath_data=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.has_filters = has_filters
-        self.html_content = html_content
-        self.xpath_data = xpath_data
-        return

changedetectionio/content_fetchers/playwright.py

@@ -1,318 +0,0 @@
-import json
-import os
-from urllib.parse import urlparse
-
-from loguru import logger
-
-from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT, visualselector_xpath_selectors, \
-    SCREENSHOT_SIZE_STITCH_THRESHOLD, SCREENSHOT_MAX_TOTAL_HEIGHT, XPATH_ELEMENT_JS, INSTOCK_DATA_JS
-from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
-from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, ScreenshotUnavailable
-
-def capture_full_page(page):
-    import os
-    import time
-    from multiprocessing import Process, Pipe
-
-    start = time.time()
-
-    page_height = page.evaluate("document.documentElement.scrollHeight")
-    page_width = page.evaluate("document.documentElement.scrollWidth")
-    original_viewport = page.viewport_size
-
-    logger.debug(f"Playwright viewport size {page.viewport_size} page height {page_height} page width {page_width}")
-
-    # Use an approach similar to puppeteer: set a larger viewport and take screenshots in chunks
-    step_size = SCREENSHOT_SIZE_STITCH_THRESHOLD # Size that won't cause GPU to overflow
-    screenshot_chunks = []
-    y = 0
-
-    if page_height > page.viewport_size['height']:
-        if page_height < step_size:
-            step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
-        logger.debug(f"Setting bigger viewport to step through large page width W{page.viewport_size['width']}xH{step_size} because page_height > viewport_size")
-        # Set viewport to a larger size to capture more content at once
-        page.set_viewport_size({'width': page.viewport_size['width'], 'height': step_size})
-
-    # Capture screenshots in chunks up to the max total height
-    while y < min(page_height, SCREENSHOT_MAX_TOTAL_HEIGHT):
-        page.request_gc()
-        page.evaluate(f"window.scrollTo(0, {y})")
-        page.request_gc()
-        screenshot_chunks.append(page.screenshot(
-            type="jpeg",
-            full_page=False,
-            quality=int(os.getenv("SCREENSHOT_QUALITY", 72))
-        ))
-        y += step_size
-        page.request_gc()
-
-    # Restore original viewport size
-    page.set_viewport_size({'width': original_viewport['width'], 'height': original_viewport['height']})
-
-    # If we have multiple chunks, stitch them together
-    if len(screenshot_chunks) > 1:
-        from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker
-        logger.debug(f"Screenshot stitching {len(screenshot_chunks)} chunks together")
-        parent_conn, child_conn = Pipe()
-        p = Process(target=stitch_images_worker, args=(child_conn, screenshot_chunks, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
-        p.start()
-        screenshot = parent_conn.recv_bytes()
-        p.join()
-        logger.debug(
-            f"Screenshot (chunked/stitched) - Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
-        # Explicit cleanup
-        del screenshot_chunks
-        del p
-        del parent_conn, child_conn
-        screenshot_chunks = None
-        return screenshot
-
-    logger.debug(
-        f"Screenshot Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
-
-    return screenshot_chunks[0]
-
-
-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=''):
-        super().screenshot_step(step_n=step_n)
-        screenshot = capture_full_page(page=self.page)
-
-
-        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):
-        super().save_step_html(step_n=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,
-            empty_pages_are_a_change=False):
-
-        from playwright.sync_api import sync_playwright
-        import playwright._impl._errors
-        import time
-        self.delete_browser_steps_screenshots()
-        response = None
-
-        with sync_playwright() as p:
-            browser_type = getattr(p, self.browser_type)
-
-            # Seemed to cause a connection Exception even tho I can see it connect
-            # self.browser = browser_type.connect(self.command_executor, timeout=timeout*1000)
-            # 60,000 connection timeout only
-            browser = browser_type.connect_over_cdp(self.browser_connection_url, timeout=60000)
-
-            # SOCKS5 with authentication is not supported (yet)
-            # https://github.com/microsoft/playwright/issues/10567
-
-            # Set user agent to prevent Cloudflare from blocking the browser
-            # Use the default one configured in the App.py model that's passed from fetch_site_status.py
-            context = browser.new_context(
-                accept_downloads=False,  # Should never be needed
-                bypass_csp=True,  # This is needed to enable JavaScript execution on GitHub and others
-                extra_http_headers=request_headers,
-                ignore_https_errors=True,
-                proxy=self.proxy,
-                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'), # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
-                user_agent=manage_user_agent(headers=request_headers),
-            )
-
-            self.page = context.new_page()
-
-            # Listen for all console events and handle errors
-            self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
-
-            # Re-use as much code from browser steps as possible so its the same
-            from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
-            browsersteps_interface = steppable_browser_interface(start_url=url)
-            browsersteps_interface.page = self.page
-
-            response = browsersteps_interface.action_goto_url(value=url)
-            self.headers = response.all_headers()
-
-            if response is None:
-                context.close()
-                browser.close()
-                logger.debug("Content Fetcher > Response object from the browser communication 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 = capture_full_page(self.page)
-                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
-
-            if not empty_pages_are_a_change and len(self.page.content().strip()) == 0:
-                logger.debug("Content Fetcher > Content was empty, empty_pages_are_a_change = False")
-                context.close()
-                browser.close()
-                raise EmptyReply(url=url, status_code=response.status)
-
-            # Run Browser Steps here
-            if self.browser_steps_get_valid_steps():
-                self.iterate_browser_steps(start_url=url)
-
-            self.page.wait_for_timeout(extra_wait * 1000)
-
-            now = time.time()
-            # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
-            if current_include_filters is not None:
-                self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
-            else:
-                self.page.evaluate("var include_filters=''")
-            self.page.request_gc()
-
-            # request_gc before and after evaluate to free up memory
-            # @todo browsersteps etc
-            MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
-            self.xpath_data = self.page.evaluate(XPATH_ELEMENT_JS, {
-                "visualselector_xpath_selectors": visualselector_xpath_selectors,
-                "max_height": MAX_TOTAL_HEIGHT
-            })
-            self.page.request_gc()
-
-            self.instock_data = self.page.evaluate(INSTOCK_DATA_JS)
-            self.page.request_gc()
-
-            self.content = self.page.content()
-            self.page.request_gc()
-            logger.debug(f"Scrape xPath element data in browser done in {time.time() - now:.2f}s")
-
-            # Bug 3 in Playwright screenshot handling
-            # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
-            # JPEG is better here because the screenshots can be very very large
-
-            # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
-            # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
-            # acceptable screenshot quality here
-            try:
-                # The actual screenshot - this always base64 and needs decoding! horrible! huge CPU usage
-                self.screenshot = capture_full_page(page=self.page)
-
-            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:
-                # Request garbage collection one more time before closing
-                try:
-                    self.page.request_gc()
-                except:
-                    pass
-                
-                # Clean up resources properly
-                try:
-                    self.page.request_gc()
-                except:
-                    pass
-
-                try:
-                    self.page.close()
-                except:
-                    pass
-                self.page = None
-
-                try:
-                    context.close()
-                except:
-                    pass
-                context = None
-
-                try:
-                    browser.close()
-                except:
-                    pass
-                browser = None
-
-
-

changedetectionio/content_fetchers/puppeteer.py

@@ -1,324 +0,0 @@
-import asyncio
-import json
-import os
-import websockets.exceptions
-from urllib.parse import urlparse
-
-from loguru import logger
-
-from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT, visualselector_xpath_selectors, \
-    SCREENSHOT_SIZE_STITCH_THRESHOLD, SCREENSHOT_DEFAULT_QUALITY, XPATH_ELEMENT_JS, INSTOCK_DATA_JS, \
-    SCREENSHOT_MAX_TOTAL_HEIGHT
-from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
-from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, BrowserFetchTimedOut, \
-    BrowserConnectError
-
-
-# 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
-
-# Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
-# which will significantly increase the IO size between the server and client, it's recommended to use the lowest
-# acceptable screenshot quality here
-async def capture_full_page(page):
-    import os
-    import time
-    from multiprocessing import Process, Pipe
-
-    start = time.time()
-
-    page_height = await page.evaluate("document.documentElement.scrollHeight")
-    page_width = await page.evaluate("document.documentElement.scrollWidth")
-    original_viewport = page.viewport
-
-    logger.debug(f"Puppeteer viewport size {page.viewport} page height {page_height} page width {page_width}")
-
-    # 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
-
-
-    step_size = SCREENSHOT_SIZE_STITCH_THRESHOLD # Something that will not cause the GPU to overflow when taking the screenshot
-    screenshot_chunks = []
-    y = 0
-    if page_height > page.viewport['height']:
-        if page_height < step_size:
-            step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
-        await page.setViewport({'width': page.viewport['width'], 'height': step_size})
-
-    while y < min(page_height, SCREENSHOT_MAX_TOTAL_HEIGHT):
-        await page.evaluate(f"window.scrollTo(0, {y})")
-        screenshot_chunks.append(await page.screenshot(type_='jpeg',
-                                                       fullPage=False,
-                                                       quality=int(os.getenv("SCREENSHOT_QUALITY", 72))))
-        y += step_size
-
-    await page.setViewport({'width': original_viewport['width'], 'height': original_viewport['height']})
-
-    if len(screenshot_chunks) > 1:
-        from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker
-        logger.debug(f"Screenshot stitching {len(screenshot_chunks)} chunks together")
-        parent_conn, child_conn = Pipe()
-        p = Process(target=stitch_images_worker, args=(child_conn, screenshot_chunks, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
-        p.start()
-        screenshot = parent_conn.recv_bytes()
-        p.join()
-        logger.debug(
-            f"Screenshot (chunked/stitched) - Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
-
-        screenshot_chunks = None
-        return screenshot
-
-    logger.debug(
-        f"Screenshot Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
-    return screenshot_chunks[0]
-
-
-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,
-                         empty_pages_are_a_change
-                         ):
-
-        self.delete_browser_steps_screenshots()
-        extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-
-        from pyppeteer import Pyppeteer
-        pyppeteer_instance = Pyppeteer()
-
-        # Connect directly using the specified browser_ws_endpoint
-        # @todo timeout
-        try:
-            browser = await pyppeteer_instance.connect(browserWSEndpoint=self.browser_connection_url,
-                                                       ignoreHTTPSErrors=True
-                                                       )
-        except websockets.exceptions.InvalidStatusCode as e:
-            raise BrowserConnectError(msg=f"Error while trying to connect the browser, Code {e.status_code} (check your access, whitelist IP, password etc)")
-        except websockets.exceptions.InvalidURI:
-            raise BrowserConnectError(msg=f"Error connecting to the browser, check your browser connection address (should be ws:// or wss://")
-        except Exception as e:
-            raise BrowserConnectError(msg=f"Error connecting to the browser {str(e)}")
-
-        # Better is to launch chrome with the URL as arg
-        # non-headless - newPage() will launch an extra tab/window, .browser should already contain 1 page/tab
-        # headless - ask a new page
-        self.page = (pages := await browser.pages) and len(pages) or await browser.newPage()
-
-        try:
-            from pyppeteerstealth import inject_evasions_into_page
-        except ImportError:
-            logger.debug("pyppeteerstealth module not available, skipping")
-            pass
-        else:
-            # I tried hooking events via self.page.on(Events.Page.DOMContentLoaded, inject_evasions_requiring_obj_to_page)
-            # But I could never get it to fire reliably, so we just inject it straight after
-            await inject_evasions_into_page(self.page)
-
-        # This user agent is similar to what was used when tweaking the evasions in inject_evasions_into_page(..)
-        user_agent = None
-        if request_headers and request_headers.get('User-Agent'):
-            # Request_headers should now be CaaseInsensitiveDict
-            # Remove it so it's not sent again with headers after
-            user_agent = request_headers.pop('User-Agent').strip()
-            await self.page.setUserAgent(user_agent)
-
-        if not user_agent:
-            # Attempt to strip 'HeadlessChrome' etc
-            await self.page.setUserAgent(manage_user_agent(headers=request_headers, current_ua=await self.page.evaluate('navigator.userAgent')))
-
-        await self.page.setBypassCSP(True)
-        if request_headers:
-            await self.page.setExtraHTTPHeaders(request_headers)
-
-        # SOCKS5 with authentication is not supported (yet)
-        # https://github.com/microsoft/playwright/issues/10567
-        self.page.setDefaultNavigationTimeout(0)
-        await self.page.setCacheEnabled(True)
-        if self.proxy and self.proxy.get('username'):
-            # Setting Proxy-Authentication header is deprecated, and doing so can trigger header change errors from Puppeteer
-            # https://github.com/puppeteer/puppeteer/issues/676 ?
-            # https://help.brightdata.com/hc/en-us/articles/12632549957649-Proxy-Manager-How-to-Guides#h_01HAKWR4Q0AFS8RZTNYWRDFJC2
-            # https://cri.dev/posts/2020-03-30-How-to-solve-Puppeteer-Chrome-Error-ERR_INVALID_ARGUMENT/
-            await self.page.authenticate(self.proxy)
-
-        # Re-use as much code from browser steps as possible so its the same
-        # from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
-
-        # not yet used here, we fallback to playwright when browsersteps is required
-        #            browsersteps_interface = steppable_browser_interface()
-        #            browsersteps_interface.page = self.page
-
-        response = await self.page.goto(url, waitUntil="load")
-
-
-        if response is None:
-            await self.page.close()
-            await browser.close()
-            logger.warning("Content Fetcher > Response object was none (as in, the response from the browser was empty, not just the content)")
-            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 capture_full_page(page=self.page)
-
-            raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
-
-        content = await self.page.content
-
-        if not empty_pages_are_a_change and len(content.strip()) == 0:
-            logger.error("Content Fetcher > Content was empty (empty_pages_are_a_change is False), closing browsers")
-            await self.page.close()
-            await browser.close()
-            raise EmptyReply(url=url, status_code=response.status)
-
-        # Run Browser Steps here
-        # @todo not yet supported, we switch to playwright in this case
-        #            if self.browser_steps_get_valid_steps():
-        #                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:
-            js = json.dumps(current_include_filters)
-            await self.page.evaluate(f"var include_filters={js}")
-        else:
-            await self.page.evaluate(f"var include_filters=''")
-
-        MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
-        self.xpath_data = await self.page.evaluate(XPATH_ELEMENT_JS, {
-            "visualselector_xpath_selectors": visualselector_xpath_selectors,
-            "max_height": MAX_TOTAL_HEIGHT
-        })
-        if not self.xpath_data:
-            raise Exception(f"Content Fetcher > xPath scraper failed. Please report this URL so we can fix it :)")
-
-        self.instock_data = await self.page.evaluate(INSTOCK_DATA_JS)
-
-        self.content = await self.page.content
-
-        self.screenshot = await capture_full_page(page=self.page)
-
-        # It's good to log here in the case that the browser crashes on shutting down but we still get the data we need
-        logger.success(f"Fetching '{url}' complete, closing page")
-        await self.page.close()
-        logger.success(f"Fetching '{url}' complete, closing browser")
-        await browser.close()
-        logger.success(f"Fetching '{url}' complete, exiting puppeteer fetch.")
-
-    async def main(self, **kwargs):
-        await self.fetch_page(**kwargs)
-
-    def run(self, url, timeout, request_headers, request_body, request_method, ignore_status_codes=False,
-            current_include_filters=None, is_binary=False, empty_pages_are_a_change=False):
-
-        #@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,
-                empty_pages_are_a_change=empty_pages_are_a_change
-            ), timeout=max_time))
-        except asyncio.TimeoutError:
-            raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))
-