0.44.2

.dockerignore

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

.github/test/Dockerfile-alpine

@@ -0,0 +1,31 @@
+# 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:3.16
+ENV PYTHONUNBUFFERED=1
+
+COPY requirements.txt /requirements.txt
+
+RUN \
+  apk add --update --no-cache --virtual=build-dependencies \
+    cargo \
+    g++ \
+    gcc \
+    libc-dev \
+    libffi-dev \
+    libxslt-dev \
+    make \
+    openssl-dev \
+    py3-wheel \
+    python3-dev \
+    zlib-dev && \
+  apk add --update --no-cache \
+    libxslt \
+    python3 \
+    py3-pip && \
+  echo "**** pip3 install test of changedetection.io ****" && \
+  pip3 install -U pip wheel setuptools && \
+  pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.16/ -r /requirements.txt && \
+  apk del --purge \
+    build-dependencies

.github/workflows/containers.yml

@@ -50,7 +50,6 @@ jobs:
           python -m pip install --upgrade pip
           pip install flake8 pytest
           if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-          if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
 
       - name: Create release metadata
         run: |
@@ -96,9 +95,11 @@ jobs:
           push: true
           tags: |
             ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
-          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
+          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
+# Looks like this was disabled
+#          provenance: false
 
       # A new tagged release is required, which builds :tag and :latest
       - name: Build and push :tag
@@ -114,9 +115,11 @@ jobs:
             ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
             ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest
             ghcr.io/dgtlmoon/changedetection.io:latest
-          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
+          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
+# 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.yml

@@ -1,44 +0,0 @@
-name: PyPi Test and Push tagged release
-
-# Triggers the workflow on push or pull request events
-on:
-  workflow_run:
-    workflows: ["ChangeDetection.io Test"]
-    tags: '*.*'
-    types: [completed]
-
-
-jobs:
-  test-build:
-    runs-on: ubuntu-latest
-    steps:
-
-      - uses: actions/checkout@v2
-      - name: Set up Python 3.9
-        uses: actions/setup-python@v2
-        with:
-          python-version: 3.9
-
-#      - name: Install dependencies
-#        run: |
-#          python -m pip install --upgrade pip
-#          pip install flake8 pytest
-#          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-#          if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
-
-      - name: Test that pip builds without error
-        run: |
-          pip3 --version
-          python3 -m pip install wheel
-          python3 setup.py bdist_wheel
-          python3 -m pip install dist/changedetection.io-*-none-any.whl --force
-          changedetection.io -d /tmp -p 10000 &
-          sleep 3
-          curl http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
-          killall -9 changedetection.io
-
-      # https://github.com/docker/build-push-action/blob/master/docs/advanced/test-before-push.md ?
-      # https://github.com/docker/buildx/issues/59 ? Needs to be one platform?
-
-      # https://github.com/docker/buildx/issues/495#issuecomment-918925854
-#if: ${{ github.event_name == 'release'}}

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

@@ -10,11 +10,13 @@ on:
     paths:
       - requirements.txt
       - Dockerfile
+      - .github/workflows/*
 
   pull_request:
     paths:
       - requirements.txt
       - Dockerfile
+      - .github/workflows/*
 
   # 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
@@ -43,6 +45,16 @@ jobs:
             version: latest
             driver-opts: image=moby/buildkit:master
 
+        # https://github.com/dgtlmoon/changedetection.io/pull/1067
+        # Check we can still build under alpine/musl
+        - name: Test that the docker containers can build (musl via alpine check)
+          id: docker_build_musl
+          uses: docker/build-push-action@v2
+          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@v2
@@ -50,6 +62,7 @@ jobs:
           with:
             context: ./
             file: ./Dockerfile
-            platforms: linux/arm/v7,linux/arm/v6,linux/amd64,linux/arm64,
+            platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
             cache-from: type=local,src=/tmp/.buildx-cache
             cache-to: type=local,dest=/tmp/.buildx-cache
+

.github/workflows/test-only.yml

@@ -8,32 +8,94 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
-      - name: Set up Python 3.9
+
+      # Mainly just for link/flake8
+      - name: Set up Python 3.10
         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
-          if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
+          python-version: '3.10'
 
       - 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
 
-      - name: Unit tests
+      - name: Spin up ancillary testable services
         run: |
-          python3 -m unittest changedetectionio.tests.unit.test_notification_diff
+          
+          docker network create changedet-network
 
-      - name: Test with pytest
+          # Selenium+browserless
+          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome-debug:3.141.59
+          docker run --network changedet-network -d --hostname browserless -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
+
+      - name: Build changedetection.io container for testing
+        run: |         
+          # Build a changedetection.io container and start testing inside
+          docker build . -t test-changedetectionio
+          # Debug info
+          docker run test-changedetectionio  bash -c 'pip list'
+
+      - name: Spin up ancillary SMTP+Echo message test server
         run: |
-          # Each test is totally isolated and performs its own cleanup/reset
-          cd changedetectionio; ./run_all_tests.sh
+          # Debug SMTP server/echo message back server
+          docker run --network changedet-network -d -p 11025:11025 -p 11080:11080  --hostname mailserver test-changedetectionio  bash -c 'python changedetectionio/tests/smtp/smtp-test-server.py' 
 
+      - name: Test built container with pytest
+        run: |
+          # Unit tests
+          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
+          
+          # All tests
+          docker run --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio && ./run_basic_tests.sh'
 
+      - name: Test built container selenium+browserless/playwright
+        run: |
+          
+          # Selenium fetch
+          docker run --rm -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py'
+          
+          # Playwright/Browserless fetch
+          docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
+          
+          # Settings headers playwright tests - Call back in from Browserless, check headers
+          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
+          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
+          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "USE_EXPERIMENTAL_PUPPETEER_FETCH=yes" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'          
+          
+          # restock detection via playwright - added name=changedet here so that playwright/browserless can connect to it
+          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
+
+      - name: Test SMTP notification mime types
+        run: |
+          # SMTP content types - needs the 'Debug SMTP server/echo message back server' container from above
+          docker run --rm  --network changedet-network test-changedetectionio bash -c 'cd changedetectionio;pytest tests/smtp/test_notification_smtp.py'
+
+      - name: Test with puppeteer fetcher and disk cache
+        run: |
+          docker run --rm -e "PUPPETEER_DISK_CACHE=/tmp/data/" -e "USE_EXPERIMENTAL_PUPPETEER_FETCH=yes" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
+          # Browserless would have had -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" added above
+
+      - name: Test proxy interaction
+        run: |
+          cd changedetectionio
+          ./run_proxy_tests.sh
+          cd ..
+
+      - name: Test changedetection.io container starts+runs basically without error
+        run: |
+          docker run -p 5556:5000 -d test-changedetectionio
+          sleep 3
+          # Should return 0 (no error) when grep finds it
+          curl -s http://localhost:5556 |grep -q checkbox-uuid
+          
+          # and IPv6
+          curl -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
+          
+
+#export WEBDRIVER_URL=http://localhost:4444/wd/hub
+#pytest tests/fetchers/test_content.py
+#pytest tests/test_errorhandling.py

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

@@ -0,0 +1,36 @@
+name: ChangeDetection.io PIP package test
+
+# Triggers the workflow on push or pull request events
+
+# This line doesnt work, even tho it is the documented one
+on: [push, pull_request]
+
+  # Changes to requirements.txt packages and Dockerfile may or may not always be compatible with arm etc, so worth testing
+  # @todo: some kind of path filter for requirements.txt and Dockerfile
+jobs:
+  test-pip-build-basics:
+    runs-on: ubuntu-latest
+    steps:
+        - uses: actions/checkout@v2
+
+        - name: Set up Python 3.9
+          uses: actions/setup-python@v2
+          with:
+            python-version: 3.9
+
+
+        - name: Test that the basic pip built package runs without error
+          run: |
+            set -e
+            mkdir dist
+            pip3 install wheel
+            python3 setup.py bdist_wheel            
+            pip3 install -r requirements.txt
+            rm ./changedetection.py
+            rm -rf changedetectio
+            
+            pip3 install dist/changedetection.io*.whl
+            changedetection.io -d /tmp -p 10000 &
+            sleep 3
+            curl http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
+            killall -9 changedetection.io

.gitignore

@@ -8,6 +8,7 @@ __pycache__
 build
 dist
 venv
+test-datastore/*
 test-datastore
 *.egg-info*
 .vscode/settings.json

CONTRIBUTING.md

@@ -7,9 +7,3 @@ Otherwise, it's always best to PR into the `dev` 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
-
-```
-pip3 install -r requirements-dev
-```
-
-this is from https://github.com/dgtlmoon/changedetection.io/blob/master/requirements-dev.txt

Dockerfile

@@ -1,7 +1,7 @@
 # pip dependencies install stage
-FROM python:3.8-slim as builder
+FROM python:3.10-slim-bullseye as builder
 
-# rustc compiler would be needed on ARM type devices but theres an issue with some deps not building..
+# See `cryptography` pin comment in requirements.txt
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
@@ -9,6 +9,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     gcc \
     libc-dev \
     libffi-dev \
+    libjpeg-dev \
     libssl-dev \
     libxslt-dev \
     make \
@@ -23,30 +24,21 @@ RUN pip install --target=/dependencies -r /requirements.txt
 
 # Playwright is an alternative to Selenium
 # Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
-RUN pip install --target=/dependencies playwright~=1.26 \
+# https://github.com/dgtlmoon/changedetection.io/pull/1067 also musl/alpine (not supported)
+RUN pip install --target=/dependencies playwright~=1.27.1 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
-
-RUN pip install --target=/dependencies jq~=1.3 \
-    || echo "WARN: Failed to install JQ. The application can still run, but the Jq: filter option will be disabled."
-
-
 # Final image stage
-FROM python:3.8-slim
+FROM python:3.10-slim-bullseye
 
-# Actual packages needed at runtime, usually due to the notification (apprise) backend
-# rustc compiler would be needed on ARM type devices but theres an issue with some deps not building..
-ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
-
-# Re #93, #73, excluding rustc (adds another 430Mb~)
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    libssl-dev \
-    libffi-dev \
-    gcc \
-    libc-dev \
-    libxslt-dev \
-    zlib1g-dev \
-    g++
+    libssl1.1 \
+    libxslt1.1 \
+    # For pdftohtml
+    poppler-utils \
+    zlib1g \
+    && apt-get clean && rm -rf /var/lib/apt/lists/*
+
 
 # https://stackoverflow.com/questions/58701233/docker-logs-erroneously-appears-empty-until-container-stops
 ENV PYTHONUNBUFFERED=1

MANIFEST.in

@@ -1,9 +1,18 @@
 recursive-include changedetectionio/api *
-recursive-include changedetectionio/templates *
-recursive-include changedetectionio/static *
+recursive-include changedetectionio/blueprint *
 recursive-include changedetectionio/model *
+recursive-include changedetectionio/processors *
+recursive-include changedetectionio/res *
+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
 global-exclude *.pyc
 global-exclude node_modules
-global-exclude venv
+global-exclude venv
+
+global-exclude test-datastore
+global-exclude changedetection.io*dist-info

README-pip.md

@@ -2,10 +2,10 @@
 
 Live your data-life pro-actively, track website content changes and receive notifications via Discord, Email, Slack, Telegram and 70+ more
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=pip)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://changedetection.io)
 
 
-[**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://lemonade.changedetection.io/start) 
+[**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://changedetection.io) 
 
 
 #### Example use cases
@@ -54,5 +54,5 @@ $ changedetection.io -d /path/to/empty/data/dir -p 5000
 
 Then visit http://127.0.0.1:5000 , You should now be able to access the UI.
 
-See https://github.com/dgtlmoon/changedetection.io for more information.
+See https://changedetection.io for more information.
 

README.md

@@ -1,34 +1,55 @@
-## Web Site Change Detection, Monitoring and Notification.
+## Web Site Change Detection, Restock monitoring and notifications.
 
-Live your data-life pro-actively, track website content changes and receive notifications via Discord, Email, Slack, Telegram and 70+ more
+**_Detect website content changes and perform meaningful actions - trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._**
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=github)
+_Live your data-life pro-actively._ 
+
+
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://changedetection.io?src=github)
 
 [![Release Version][release-shield]][release-link] [![Docker Pulls][docker-pulls]][docker-link] [![License][license-shield]](LICENSE.md)
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
-Know when important content changes, we support notifications via Discord, Telegram, Home-Assistant, Slack, Email and 70+ more
-
-[**Don't have time? Let us host it for you! try our $6.99/month subscription - use our proxies and support!**](https://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
+[**Don't have time? Let us host it for you! try our $8.99/month subscription - use our proxies and support!**](https://changedetection.io) , _half the price of other website change monitoring services!_
 
 - Chrome browser included.
 - Super fast, no registration needed setup.
-- Start watching and receiving change notifications instantly.
+- Get started watching and receiving website change notifications straight away.
 
 
-Easily see what changed, examine by word, line, or individual character.
+### Target specific parts of the webpage using the Visual Selector tool.
 
-<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 " />
+Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
+
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://changedetection.io?src=github)
+
+### 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)
 
 
-#### Example use cases
+### 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="Self-hosted web page change monitoring context difference "  title="Website change detection with interactive browser steps, login, cookies etc" />](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.
+
+
+### 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
@@ -41,6 +62,12 @@ Easily see what changed, examine by word, line, or individual character.
 - 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>_
 
@@ -49,24 +76,18 @@ _Need an actual Chrome runner with Javascript support? We support fetching via W
 - Lots of trigger filters, such as "Trigger on text", "Remove text by selector", "Ignore text", "Extract text", also using regular-expressions!
 - Target elements with xPath and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
 - 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.
 
-## Screenshots
-
 Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
 
-### Filter by elements using the Visual Selector tool.
-
-Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
-
-<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />
-
 ## Installation
 
 ### Docker
@@ -84,6 +105,8 @@ $ docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/d
 
 `:latest` tag is our latest stable release, `:dev` tag is our bleeding edge `master` branch.
 
+Alternative docker repository over at ghcr - [ghcr.io/dgtlmoon/changedetection.io](https://ghcr.io/dgtlmoon/changedetection.io)
+
 ### Windows
 
 See the install instructions at the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Microsoft-Windows
@@ -106,8 +129,8 @@ _Now with per-site configurable support for using a fast built in HTTP fetcher o
 ### Docker
 ```
 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 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
 ```
 
@@ -123,7 +146,7 @@ See the wiki for more information https://github.com/dgtlmoon/changedetection.io
 ## Filters
 
 XPath, JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools. 
-(We support LXML `re:test`, `re:math` and `re:replace`.)
+(We support LXML `re:test`, `re:match` and `re:replace`.)
 
 ## Notifications
 
@@ -147,7 +170,7 @@ Just some examples
 
 <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!
+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
 
@@ -167,9 +190,6 @@ One big advantage of `jq` is that you can use logic in your JSON filter, such as
 
 See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/JSON-Selector-Filter-help for more information and examples
 
-Note: `jq` library must be added separately (`pip3 install jq`)
-
-
 ### 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. 
@@ -178,27 +198,48 @@ When you enable a `json:` or `jq:` filter, you can even automatically extract an
 <html>
 ...
 <script type="application/ld+json">
-  {"@context":"http://schema.org","@type":"Product","name":"Nan Optipro Stage 1 Baby Formula  800g","price": 23.50 }
+
+{
+   "@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:$.price` or `jq:.price` would give `23.50`, or you can extract the whole structure
+`json:$..price` or `jq:..price` would give `3949.99`, or you can extract the whole structure (use a JSONpath test website to validate with)
 
-## Proxy configuration
+The application also supports notifying you that it can follow this information automatically
 
-See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration
+
+## Proxy Configuration
+
+See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [BrightData proxy services where possible]( https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support)
 
 ## Raspberry Pi support?
 
 Raspberry Pi and linux/arm/v6 linux/arm/v7 arm64 devices are supported! See the wiki for [details](https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver)
 
+## 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.
 
 
-Firstly, consider taking out a [change detection monthly subscription - unlimited checks and watches](https://lemonade.changedetection.io/start) , even if you don't use it, you still get the warm fuzzy feeling of helping out the project. (And who knows, you might just use it!)
+Firstly, consider taking out a [change detection monthly subscription - unlimited checks and watches](https://changedetection.io?src=github) , even if you don't use it, you still get the warm fuzzy feeling of helping out the project. (And who knows, you might just use it!)
 
 Or directly donate an amount PayPal [![Donate](https://img.shields.io/badge/Donate-PayPal-green.svg)](https://www.paypal.com/donate/?hosted_button_id=7CP6HR9ZCNDYJ)
 
@@ -216,5 +257,5 @@ I offer commercial support, this software is depended on by network security, ae
 [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.com/changedetection.io/releases
+[release-link]: https://github.com/dgtlmoon/changedetection.io/releases
 [docker-link]: https://hub.docker.com/r/dgtlmoon/changedetection.io

changedetection.py

@@ -7,7 +7,7 @@
 
 from changedetectionio import changedetection
 import multiprocessing
-import signal
+import sys
 import os
 
 def sigchld_handler(_signo, _stack_frame):
@@ -35,6 +35,9 @@ if __name__ == '__main__':
     try:
         while True:
             time.sleep(1)
+            if not parse_process.is_alive():
+                # Process died/crashed for some reason, exit with error set
+                sys.exit(1)
 
     except KeyboardInterrupt:
         #parse_process.terminate() not needed, because this process will issue it to the sub-process anyway

changedetectionio/api/api_schema.py

@@ -0,0 +1,117 @@
+# 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
+
+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"},
+        }
+    }
+
+    from changedetectionio.notification import valid_notification_formats
+
+    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()
+
+    # headers ?
+    return schema
+

changedetectionio/api/api_v1.py

@@ -1,11 +1,27 @@
+import os
+from distutils.util 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
 
+# See docs/README.md for rebuilding the docs/apidoc information
 
+from . import api_schema
 
-# https://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html
+# Build a JSON Schema atleast partially based on our Watch model
+from changedetectionio.model.Watch import base_config as watch_base_config
+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
 
 class Watch(Resource):
     def __init__(self, **kwargs):
@@ -15,30 +31,100 @@ class Watch(Resource):
 
     # Get information about a single watch, excluding the history list (can be large)
     # curl http://localhost:4000/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:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            curl "http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?muted=unmuted"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            curl "http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?paused=unpaused"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+        @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((1, uuid))
+            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+            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
+        watch['last_changed'] = watch.last_changed
+
         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:4000/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:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X PUT -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "new list"}'
+
+        @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):
@@ -48,6 +134,21 @@ class WatchHistory(Resource):
     # Get a list of available history for a watch by UUID
     # curl http://localhost:4000/api/v1/watch/<string:uuid>/history
     def get(self, uuid):
+        """
+        @api {get} /api/v1/watch/<string:uuid>/history Get a list of all historical snapshots available for a watch
+        @apiDescription Requires `uuid`, returns list
+        @apiExample {curl} Example usage:
+            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
+            {
+                "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))
@@ -59,11 +160,18 @@ class WatchSingleHistory(Resource):
         # datastore is a black box dependency
         self.datastore = kwargs['datastore']
 
-    # Read a given history snapshot and return its content
-    # <string:timestamp> or "latest"
-    # curl http://localhost:4000/api/v1/watch/<string:uuid>/history/<int:timestamp>
     @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:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history/1677092977 -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
+        @apiName Get single snapshot content
+        @apiGroup Watch History
+        @apiSuccess (200) {String} OK
+        @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))
@@ -74,8 +182,7 @@ class WatchSingleHistory(Resource):
         if timestamp == 'latest':
             timestamp = list(watch.history.keys())[-1]
 
-        with open(watch.history[timestamp], 'r') as f:
-            content = f.read()
+        content = watch.get_history_snapshot(timestamp)
 
         response = make_response(content, 200)
         response.mimetype = "text/plain"
@@ -89,36 +196,99 @@ class CreateWatch(Resource):
         self.update_q = kwargs['update_q']
 
     @auth.check_token
+    @expects_json(schema_create_watch)
     def post(self):
-        # curl http://localhost:4000/api/v1/watch -H "Content-Type: application/json" -d '{"url": "https://my-nice.com", "tag": "one, two" }'
-        json_data = request.get_json()
-        tag = json_data['tag'].strip() if json_data.get('tag') else ''
+        """
+        @api {post} /api/v1/watch Create a single watch
+        @apiDescription Requires atleast `url` set, can accept the same structure as <a href="#api-Watch-Watch">get single watch information</a> to create.
+        @apiExample {curl} Example usage:
+            curl http://localhost:4000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "nice list"}'
+        @apiName Create
+        @apiGroup Watch
+        @apiSuccess (200) {String} OK Was created
+        @apiSuccess (500) {String} ERR Some other error
+        """
 
-        if not validators.url(json_data['url'].strip()):
+        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
 
-        extras = {'title': json_data['title'].strip()} if json_data.get('title') else {}
+        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
 
-        new_uuid = self.datastore.add_watch(url=json_data['url'].strip(), tag=tag, extras=extras)
-        self.update_q.put((1, new_uuid))
-        return {'uuid': new_uuid}, 201
+        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, 'skip_when_checksum_same': True}))
+            return {'uuid': new_uuid}, 201
+        else:
+            return "Invalid or unsupported URL", 400
 
-    # Return concise list of available watches and some very basic info
-    # curl http://localhost:4000/api/v1/watch|python -mjson.tool
-    # ?recheck_all=1 to recheck all
     @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:4000/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 = {}
-        for k, v in self.datastore.data['watching'].items():
-            list[k] = {'url': v['url'],
-                       'title': v['title'],
-                       'last_checked': v['last_checked'],
-                       'last_changed': v.last_changed,
-                       'last_error': v['last_error']}
+
+        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] = {'url': watch['url'],
+                       'title': watch['title'],
+                       'last_checked': watch['last_checked'],
+                       'last_changed': watch.last_changed,
+                       'last_error': watch['last_error']}
 
         if request.args.get('recheck_all'):
             for uuid in self.datastore.data['watching'].keys():
-                self.update_q.put((1, uuid))
+                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
             return {'status': "OK"}, 200
 
         return list, 200
@@ -131,6 +301,22 @@ class SystemInfo(Resource):
 
     @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:4000/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 = []
 
@@ -149,10 +335,11 @@ class SystemInfo(Resource):
             # 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', {}))
+                   'watch_count': len(self.datastore.data.get('watching', {})),
+                   'version': main_version
                }, 200

changedetectionio/blueprint/browser_steps/__init__.py

@@ -0,0 +1,213 @@
+
+# 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()
+# - browserless has a single timeout/keepalive which applies to the session made at .connect_over_cdp()
+#
+# So it means that we must unfortunately for now just keep a single timer since .connect_over_cdp() was run
+# and know when that reaches timeout/keepalive :( when that time is up, restart the connection and tell the user
+# that their time is up, insert another coin. (reload)
+#
+# Bigger picture
+# - It's horrible that we have this click+wait deal, some nice socket.io solution using something similar
+# to what the browserless debug UI already gives us would be smarter..
+#
+# OR
+# - Some API call that should be hacked into browserless or playwright that we can "/api/bump-keepalive/{session_id}/60"
+# So we can tell it that we need more time (run this on each action)
+#
+# OR
+# - use multiprocessing to bump this over to its own process and add some transport layer (queue/pipes)
+
+from distutils.util import strtobool
+from flask import Blueprint, request, make_response
+import os
+import logging
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio import login_optionally_required
+
+browsersteps_sessions = {}
+io_interface_context = None
+
+
+def construct_blueprint(datastore: ChangeDetectionStore):
+    browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
+
+    def start_browsersteps_session(watch_uuid):
+        from . import nonContext
+        from . import browser_steps
+        import time
+        global browsersteps_sessions
+        global io_interface_context
+
+
+        # We keep the playwright session open for many minutes
+        seconds_keepalive = 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()
+
+
+        # keep it alive for 10 seconds more than we advertise, sometimes it helps to keep it shutting down cleanly
+        keepalive = "&timeout={}".format(((seconds_keepalive + 3) * 1000))
+        try:
+            browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(
+                os.getenv('PLAYWRIGHT_DRIVER_URL', '') + keepalive)
+        except Exception as e:
+            if 'ECONNREFUSED' in str(e):
+                return make_response('Unable to start the Playwright Browser session, is it running?', 401)
+            else:
+                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
+
+                print("Browser Steps: UUID {} selected proxy {}".format(watch_uuid, 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)
+
+        # 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
+        global browsersteps_sessions
+
+        browsersteps_session_id = str(uuid.uuid4())
+        watch_uuid = request.args.get('uuid')
+
+        if not watch_uuid:
+            return make_response('No Watch UUID specified', 500)
+
+        print("Starting connection with playwright")
+        logging.debug("browser_steps.py connecting")
+        browsersteps_sessions[browsersteps_session_id] = start_browsersteps_session(watch_uuid)
+        print("Starting connection with playwright - done")
+        return {'browsersteps_session_id': browsersteps_session_id}
+
+    # A request for an action was received
+    @login_optionally_required
+    @browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
+    def browsersteps_ui_update():
+        import base64
+        import playwright._impl._api_types
+        global browsersteps_sessions
+        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)
+
+
+        # 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')
+            step_n = int(request.form.get('step_n'))
+            is_last_step = strtobool(request.form.get('is_last_step'))
+
+            if step_operation == 'Goto site':
+                step_operation = 'goto_url'
+                step_optional_value = datastore.data['watching'][uuid].get('url')
+                step_selector = None
+
+            # @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:
+                print("Exception when calling step operation", step_operation, str(e))
+                # Try to find something of value to give back to the user
+                return make_response(str(e).splitlines()[0], 401)
+
+            # Get visual selector ready/update its data (also use the current filter info from the page?)
+            # When the last 'apply' button was pressed
+            # @todo this adds overhead because the xpath selection is happening twice
+            u = browsersteps_sessions[browsersteps_session_id]['browserstepper'].page.url
+            if is_last_step and u:
+                (screenshot, xpath_data) = browsersteps_sessions[browsersteps_session_id]['browserstepper'].request_visualselector_data()
+                datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
+                datastore.save_xpath_data(watch_uuid=uuid, data=xpath_data)
+
+#        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:
+            state = browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
+        except playwright._impl._api_types.Error as e:
+            return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
+
+        # Use send_file() which is way faster than read/write loop on bytes
+        import json
+        from tempfile import mkstemp
+        from flask import send_file
+        tmp_fd, tmp_file = mkstemp(text=True, suffix=".json", prefix="changedetectionio-")
+
+        output = json.dumps({'screenshot': "data:image/jpeg;base64,{}".format(
+            base64.b64encode(state[0]).decode('ascii')),
+            'xpath_data': state[1],
+            'session_age_start': browsersteps_sessions[browsersteps_session_id]['browserstepper'].age_start,
+            'browser_time_remaining': round(remaining)
+        })
+
+        with os.fdopen(tmp_fd, 'w') as f:
+            f.write(output)
+
+        response = make_response(send_file(path_or_file=tmp_file,
+                                           mimetype='application/json; charset=UTF-8',
+                                           etag=True))
+        # No longer needed
+        os.unlink(tmp_file)
+
+        return response
+
+    return browser_steps_blueprint
+
+

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -0,0 +1,282 @@
+#!/usr/bin/python3
+
+import os
+import time
+import re
+from random import randint
+
+# 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',
+                          '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',
+                          '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',
+                          #                          '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
+
+    # 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
+
+        print("> 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
+        from jinja2 import Environment
+        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
+
+        if selector and ('{%' in selector or '{{' in selector):
+            selector = str(jinja2_env.from_string(selector).render())
+
+        if optional_value and ('{%' in optional_value or '{{' in optional_value):
+            optional_value = str(jinja2_env.from_string(optional_value).render())
+
+        action_handler(selector, optional_value)
+        self.page.wait_for_timeout(1.5 * 1000)
+        print("Call action done in", time.time() - now)
+
+    def action_goto_url(self, selector=None, value=None):
+        # self.page.set_viewport_size({"width": 1280, "height": 5000})
+        now = time.time()
+        response = self.page.goto(value, timeout=0, wait_until='commit')
+
+        # Wait_until = commit
+        # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
+        # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
+        # This seemed to solve nearly all 'TimeoutErrors'
+        print("Time to goto URL ", time.time() - now)
+
+    def action_click_element_containing_text(self, selector=None, value=''):
+        if not len(value.strip()):
+            return
+        elem = self.page.get_by_text(value)
+        if elem.count():
+            elem.first.click(delay=randint(200, 500), timeout=3000)
+
+    def action_enter_text_in_field(self, selector, value):
+        if not len(selector.strip()):
+            return
+
+        self.page.fill(selector, value, timeout=10 * 1000)
+
+    def action_execute_js(self, selector, value):
+        self.page.evaluate(value)
+
+    def action_click_element(self, selector, value):
+        print("Clicking element")
+        if not len(selector.strip()):
+            return
+
+        self.page.click(selector=selector, timeout=30 * 1000, delay=randint(200, 500))
+
+    def action_click_element_if_exists(self, selector, value):
+        import playwright._impl._api_types as _api_types
+        print("Clicking element if exists")
+        if not len(selector.strip()):
+            return
+        try:
+            self.page.click(selector, timeout=10 * 1000, 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):
+        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=90000)
+
+    def action_wait_for_text_in_element(self, selector, value):
+        import json
+        s = json.dumps(selector)
+        v = json.dumps(value)
+        self.page.wait_for_function(f'document.querySelector({s}).innerText.includes({v});', timeout=90000)
+
+    # @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=1000)
+
+    def action_uncheck_checkbox(self, selector, value):
+        self.page.locator(selector, timeout=1000).uncheck(timeout=1000)
+
+
+# Responsible for maintaining a live 'context' with browserless
+# @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
+
+    # 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):
+        self.age_start = time.time()
+        self.playwright_browser = playwright_browser
+        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(
+            # @todo
+            #                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
+            #               proxy=self.proxy,
+            # This is needed to enable JavaScript execution on GitHub and others
+            bypass_csp=True,
+            # Should never be needed
+            accept_downloads=False,
+            proxy=proxy
+        )
+
+        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}"))
+
+        print("Time to browser setup", time.time() - now)
+        self.page.wait_for_timeout(1 * 1000)
+
+    def mark_as_closed(self):
+        print("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_()"""
+        from pkg_resources import resource_string
+        xpath_element_js = resource_string(__name__, "../../res/xpath_element_scraper.js").decode('utf-8')
+        now = time.time()
+        self.page.wait_for_timeout(1 * 1000)
+
+        # The actual screenshot
+        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=40)
+
+        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?
+        elements = 'a,button,input,select,textarea,i,th,td,p,li,h1,h2,h3,h4,div,span'
+        xpath_element_js = xpath_element_js.replace('%ELEMENTS%', elements)
+        xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")
+        # So the JS will find the smallest one first
+        xpath_data['size_pos'] = sorted(xpath_data['size_pos'], key=lambda k: k['width'] * k['height'], reverse=True)
+        print("Time to complete get_current_state of browser", time.time() - now)
+        # except
+        # playwright._impl._api_types.Error: Browser closed.
+        # @todo show some countdown timer?
+        return (screenshot, xpath_data)
+
+    def request_visualselector_data(self):
+        """
+        Does the same that the playwright operation in content_fetcher does
+        This is used to just bump the VisualSelector data so it' ready to go if they click on the tab
+        @todo refactor and remove duplicate code, add include_filters
+        :param xpath_data:
+        :param screenshot:
+        :param current_include_filters:
+        :return:
+        """
+
+        self.page.evaluate("var include_filters=''")
+        from pkg_resources import resource_string
+        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
+        xpath_element_js = resource_string(__name__, "../../res/xpath_element_scraper.js").decode('utf-8')
+        from changedetectionio.content_fetcher import visualselector_xpath_selectors
+        xpath_element_js = xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
+        xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")
+        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+
+        return (screenshot, xpath_data)

changedetectionio/blueprint/browser_steps/nonContext.py

@@ -0,0 +1,18 @@
+from playwright.sync_api import PlaywrightContextManager
+import asyncio
+
+# So playwright wants to run as a context manager, but we do something horrible and hacky
+# we are holding the session open for as long as possible, then shutting it down, and opening a new one
+# 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

@@ -0,0 +1,116 @@
+from concurrent.futures import ThreadPoolExecutor
+
+from functools import wraps
+
+from flask import Blueprint
+from flask_login import login_required
+
+from changedetectionio.processors import text_json_diff
+from changedetectionio.store import ChangeDetectionStore
+
+
+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 import content_fetcher
+
+        status = {'status': '', 'length': 0, 'text': ''}
+        from jinja2 import Environment, BaseLoader
+
+        contents = ''
+        now = time.time()
+        try:
+            update_handler = text_json_diff.perform_site_check(datastore=datastore)
+            changed_detected, update_obj, contents = update_handler.run(uuid, preferred_proxy=preferred_proxy, skip_when_checksum_same=False)
+        # title, size is len contents not len xfer
+        except content_fetcher.Non200ErrorCodeReceived as e:
+            if e.status_code == 404:
+                status.update({'status': 'OK', 'length': len(contents), 'text': f"OK but 404 (page not found)"})
+            elif e.status_code == 403 or e.status_code == 401:
+                status.update({'status': 'ERROR', 'length': len(contents), 'text': f"{e.status_code} - Access denied"})
+            else:
+                status.update({'status': 'ERROR', 'length': len(contents), 'text': f"Status code: {e.status_code}"})
+        except text_json_diff.FilterNotFoundInResponse:
+            status.update({'status': 'OK', 'length': len(contents), 'text': f"OK but CSS/xPath filter not found (page changed layout?)"})
+        except content_fetcher.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 Exception as e:
+            status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': 'Error: '+str(e)})
+        else:
+            status.update({'status': 'OK', 'length': len(contents), 'text': ''})
+
+        if status.get('text'):
+            status['text'] = Environment(loader=BaseLoader()).from_string('{{text|e}}').render({'text': status['text']})
+
+        status['time'] = "{:.2f}s".format(time.time() - now)
+
+        return status
+
+    def _recalc_check_status(uuid):
+
+        results = {}
+        for k, v in checks_in_progress.get(uuid, {}).items():
+            try:
+                r_1 = v.result(timeout=0.05)
+            except Exception as e:
+                # If timeout error?
+                results[k] = {'status': 'RUNNING'}
+
+            else:
+                results[k] = r_1
+
+        return results
+
+    @login_required
+    @check_proxies_blueprint.route("/<string:uuid>/status", methods=['GET'])
+    def get_recheck_status(uuid):
+        results = _recalc_check_status(uuid=uuid)
+        return results
+
+    @login_required
+    @check_proxies_blueprint.route("/<string:uuid>/start", methods=['GET'])
+    def start_check(uuid):
+
+        if not datastore.proxy_list:
+            return
+
+        if checks_in_progress.get(uuid):
+            state = _recalc_check_status(uuid=uuid)
+            for proxy_key, v in state.items():
+                if v.get('status') == 'RUNNING':
+                    return state
+        else:
+            checks_in_progress[uuid] = {}
+
+        for k, v in datastore.proxy_list.items():
+            if not checks_in_progress[uuid].get(k):
+                checks_in_progress[uuid][k] = long_task(uuid=uuid, preferred_proxy=k)
+
+        results = _recalc_check_status(uuid=uuid)
+        return results
+
+    return check_proxies_blueprint

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -0,0 +1,33 @@
+
+from distutils.util 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
+        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+        return redirect(url_for("form_watch_checknow", uuid=uuid))
+
+
+    @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("index"))
+
+
+    return price_data_follower_blueprint
+
+

changedetectionio/blueprint/tags/README.md

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

changedetectionio/blueprint/tags/__init__.py

@@ -0,0 +1,141 @@
+from flask import Blueprint, request, make_response, render_template, flash, url_for, redirect
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio 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)
+        output = render_template("groups-overview.html",
+                                 form=add_form,
+                                 available_tags=datastore.data['settings']['application'].get('tags', {}),
+                                 )
+
+        return output
+
+    @tags_blueprint.route("/add", methods=['POST'])
+    @login_optionally_required
+    def form_tag_add():
+        from .form import SingleTag
+        add_form = SingleTag(request.form)
+
+        if not add_form.validate():
+            for widget, l in add_form.errors.items():
+                flash(','.join(l), 'error')
+            return redirect(url_for('tags.tags_overview_page'))
+
+        title = request.form.get('name').strip()
+
+        if datastore.tag_exists_by_name(title):
+            flash(f'The tag "{title}" already exists', "error")
+            return redirect(url_for('tags.tags_overview_page'))
+
+        datastore.add_tag(title)
+        flash("Tag added")
+
+
+        return redirect(url_for('tags.tags_overview_page'))
+
+    @tags_blueprint.route("/mute/<string:uuid>", methods=['GET'])
+    @login_optionally_required
+    def mute(uuid):
+        if datastore.data['settings']['application']['tags'].get(uuid):
+            datastore.data['settings']['application']['tags'][uuid]['notification_muted'] = not datastore.data['settings']['application']['tags'][uuid]['notification_muted']
+        return redirect(url_for('tags.tags_overview_page'))
+
+    @tags_blueprint.route("/delete/<string:uuid>", methods=['GET'])
+    @login_optionally_required
+    def delete(uuid):
+        removed = 0
+        # Delete the tag, and any tag reference
+        if datastore.data['settings']['application']['tags'].get(uuid):
+            del datastore.data['settings']['application']['tags'][uuid]
+
+        for watch_uuid, watch in datastore.data['watching'].items():
+            if watch.get('tags') and uuid in watch['tags']:
+                removed += 1
+                watch['tags'].remove(uuid)
+
+        flash(f"Tag deleted and removed from {removed} watches")
+        return redirect(url_for('tags.tags_overview_page'))
+
+    @tags_blueprint.route("/unlink/<string:uuid>", methods=['GET'])
+    @login_optionally_required
+    def unlink(uuid):
+        unlinked = 0
+        for watch_uuid, watch in datastore.data['watching'].items():
+            if watch.get('tags') and uuid in watch['tags']:
+                unlinked += 1
+                watch['tags'].remove(uuid)
+
+        flash(f"Tag unlinked removed from {unlinked} watches")
+        return redirect(url_for('tags.tags_overview_page'))
+
+    @tags_blueprint.route("/delete_all", methods=['GET'])
+    @login_optionally_required
+    def delete_all():
+        for watch_uuid, watch in datastore.data['watching'].items():
+            watch['tags'] = []
+        datastore.data['settings']['application']['tags'] = {}
+
+        flash(f"All tags deleted")
+        return redirect(url_for('tags.tags_overview_page'))
+
+    @tags_blueprint.route("/edit/<string:uuid>", methods=['GET'])
+    @login_optionally_required
+    def form_tag_edit(uuid):
+        from changedetectionio import forms
+
+        if uuid == 'first':
+            uuid = list(datastore.data['settings']['application']['tags'].keys()).pop()
+
+        default = datastore.data['settings']['application']['tags'].get(uuid)
+
+        form = forms.watchForm(formdata=request.form if request.method == 'POST' else None,
+                               data=default,
+                               )
+        form.datastore=datastore # needed?
+
+        output = render_template("edit-tag.html",
+                                 data=default,
+                                 form=form,
+                                 settings_application=datastore.data['settings']['application'],
+                                 )
+
+        return output
+
+
+    @tags_blueprint.route("/edit/<string:uuid>", methods=['POST'])
+    @login_optionally_required
+    def form_tag_edit_submit(uuid):
+        from changedetectionio import forms
+        if uuid == 'first':
+            uuid = list(datastore.data['settings']['application']['tags'].keys()).pop()
+
+        default = datastore.data['settings']['application']['tags'].get(uuid)
+
+        form = forms.watchForm(formdata=request.form if request.method == 'POST' else None,
+                               data=default,
+                               )
+        # @todo subclass form so validation works
+        #if not form.validate():
+#            for widget, l in form.errors.items():
+#                flash(','.join(l), 'error')
+#           return redirect(url_for('tags.form_tag_edit_submit', uuid=uuid))
+
+        datastore.data['settings']['application']['tags'][uuid].update(form.data)
+        datastore.needs_write_urgent = True
+        flash("Updated")
+
+        return redirect(url_for('tags.tags_overview_page'))
+
+
+    @tags_blueprint.route("/delete/<string:uuid>", methods=['GET'])
+    def form_tag_delete(uuid):
+        return redirect(url_for('tags.tags_overview_page'))
+    return tags_blueprint

changedetectionio/blueprint/tags/form.py

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

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

@@ -0,0 +1,131 @@
+{% extends 'base.html' %}
+{% block content %}
+{% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
+{% from '_common_fields.jinja' import render_common_settings_form %}
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script>
+
+/*{% if emailprefix %}*/
+    /*const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');*/
+/*{% endif %}*/
+
+
+</script>
+
+<script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
+<!--<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>-->
+<script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
+
+<div class="edit-form monospaced-textarea">
+
+    <div class="tabs collapsable">
+        <ul>
+            <li class="tab" id=""><a href="#general">General</a></li>
+            <li class="tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
+            <li class="tab"><a href="#notifications">Notifications</a></li>
+        </ul>
+    </div>
+
+    <div class="box-wrap inner">
+        <form class="pure-form pure-form-stacked"
+              action="{{ url_for('tags.form_tag_edit', uuid=data.uuid) }}" method="POST">
+             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
+
+            <div class="tab-pane-inner" id="general">
+                <fieldset>
+                    <div class="pure-control-group">
+                        {{ render_field(form.title, placeholder="https://...", required=true, class="m-d") }}
+                    </div>
+                </fieldset>
+            </div>
+
+            <div class="tab-pane-inner" id="filters-and-triggers">
+                    <div class="pure-control-group">
+                        {% set field = render_field(form.include_filters,
+                            rows=5,
+                            placeholder="#example
+xpath://body/div/span[contains(@class, 'example-class')]",
+                            class="m-d")
+                        %}
+                        {{ field }}
+                        {% if '/text()' in  field %}
+                          <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br>
+                        {% endif %}
+                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br>
+
+                    <ul>
+                        <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
+                        <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
+                            <ul>
+                                <li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required,  <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
+                                {% if jq_support %}
+                                <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>.</li>
+                                {% else %}
+                                <li>jq support not installed</li>
+                                {% endif %}
+                            </ul>
+                        </li>
+                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash,
+                            <ul>
+                                <li>Example:  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath://*[contains(@class, 'sametext')]</code>, <a
+                                href="http://xpather.com/" target="new">test your XPath here</a></li>
+                                <li>Example: Get all titles from an RSS feed <code>//title/text()</code></li>
+                            </ul>
+                            </li>
+                    </ul>
+                    Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
+                                href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
+                </span>
+                    </div>
+                <fieldset class="pure-control-group">
+                    {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
+footer
+nav
+.stockticker") }}
+                    <span class="pure-form-message-inline">
+                        <ul>
+                          <li> Remove HTML element(s) by CSS selector before text conversion. </li>
+                          <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
+                        </ul>
+                      </span>
+                </fieldset>
+
+            </div>
+
+            <div class="tab-pane-inner" id="notifications">
+                <fieldset>
+                    <div  class="pure-control-group inline-radio">
+                      {{ render_checkbox_field(form.notification_muted) }}
+                    </div>
+                    {% if is_html_webdriver %}
+                    <div class="pure-control-group inline-radio">
+                      {{ render_checkbox_field(form.notification_screenshot) }}
+                        <span class="pure-form-message-inline">
+                            <strong>Use with caution!</strong> This will easily fill up your email storage quota or flood other storages.
+                        </span>
+                    </div>
+                    {% endif %}
+                    <div class="field-group" id="notification-field-group">
+                        {% if has_default_notification_urls %}
+                        <div class="inline-warning">
+                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!" >
+                            There are <a href="{{ url_for('settings_page')}}#notifications">system-wide notification URLs enabled</a>, this form will override notification settings for this watch only &dash; an empty Notification URL list here will still send notifications.
+                        </div>
+                        {% endif %}
+                        <a href="#notifications" id="notification-setting-reset-to-default" class="pure-button button-xsmall" style="right: 20px; top: 20px; position: absolute; background-color: #5f42dd; border-radius: 4px; font-size: 70%; color: #fff">Use system defaults</a>
+
+                        {{ render_common_settings_form(form, emailprefix, settings_application) }}
+                    </div>
+                </fieldset>
+            </div>
+
+            <div id="actions">
+                <div class="pure-control-group">
+                    {{ render_button(form.save_button) }}
+                </div>
+            </div>
+        </form>
+    </div>
+</div>
+
+{% endblock %}

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

@@ -0,0 +1,60 @@
+{% extends 'base.html' %}
+{% block content %}
+{% from '_helpers.jinja' 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>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.items()  %}
+            <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 class="title-col inline">{{tag.title}}</td>
+                <td>
+                    <a class="pure-button pure-button-primary" href="{{ url_for('tags.form_tag_edit', uuid=uuid) }}">Edit</a>&nbsp;
+                    <a class="pure-button pure-button-primary" href="{{ url_for('tags.delete', uuid=uuid) }}" title="Deletes and removes tag">Delete</a>
+                    <a class="pure-button pure-button-primary" href="{{ url_for('tags.unlink', uuid=uuid) }}" title="Keep the tag but unlink any watches">Unlink</a>
+                </td>
+            </tr>
+            {% endfor %}
+            </tbody>
+        </table>
+    </div>
+</div>
+{% endblock %}

changedetectionio/changedetection.py

@@ -2,19 +2,23 @@
 
 # Launch as a eventlet.wsgi server instance.
 
-import getopt
-import os
-import signal
-import sys
+from distutils.util import strtobool
+from json.decoder import JSONDecodeError
 
 import eventlet
 import eventlet.wsgi
+import getopt
+import os
+import signal
+import socket
+import sys
+
 from . import store, changedetection_app, content_fetcher
 from . import __version__
 
 # Only global so we can access it in the signal handler
-datastore = None
 app = None
+datastore = None
 
 def sigterm_handler(_signo, _stack_frame):
     global app
@@ -27,11 +31,13 @@ def sigterm_handler(_signo, _stack_frame):
 def main():
     global datastore
     global app
-    ssl_mode = False
-    host = ''
-    port = os.environ.get('PORT') or 5000
-    do_cleanup = False
+
     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':
@@ -42,7 +48,7 @@ def main():
         datastore_path = os.path.join(os.getcwd(), "../datastore")
 
     try:
-        opts, args = getopt.getopt(sys.argv[1:], "Ccsd:h:p:", "port")
+        opts, args = getopt.getopt(sys.argv[1:], "6Ccsd:h:p:", "port")
     except getopt.GetoptError:
         print('backend.py -s SSL enable -h [host] -p [port] -d [datastore path]')
         sys.exit(2)
@@ -62,6 +68,10 @@ def main():
         if opt == '-d':
             datastore_path = arg
 
+        if opt == '-6':
+            print ("Enabling IPv6 listen support")
+            ipv6_enabled = True
+
         # Cleanup (remove text files that arent in the index)
         if opt == '-c':
             do_cleanup = True
@@ -82,8 +92,14 @@ def main():
                 "Or use the -C parameter to create the directory.".format(app_config['datastore_path']), file=sys.stderr)
             sys.exit(2)
 
+    try:
+        datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], version_tag=__version__)
+    except JSONDecodeError as e:
+        # Dont' start if the JSON DB looks corrupt
+        print ("ERROR: JSON DB or Proxy List JSON at '{}' appears to be corrupt, aborting".format(app_config['datastore_path']))
+        print(str(e))
+        return
 
-    datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], version_tag=__version__)
     app = changedetection_app(app_config, datastore)
 
     signal.signal(signal.SIGTERM, sigterm_handler)
@@ -102,12 +118,13 @@ def main():
                     has_password=datastore.data['settings']['application']['password'] != False
                     )
 
-    # Monitored websites will not receive a Referer header
-    # when a user clicks on an outgoing link.
+    # Monitored websites will not receive a Referer header when a user clicks on an outgoing link.
+    # @Note: Incompatible with password login (and maybe other features) for now, submit a PR!
     @app.after_request
     def hide_referrer(response):
-        if os.getenv("HIDE_REFERER", False):
+        if strtobool(os.getenv("HIDE_REFERER", 'false')):
             response.headers["Referrer-Policy"] = "no-referrer"
+
         return response
 
     # Proxy sub-directory support
@@ -122,13 +139,15 @@ def main():
         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)),
+        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))), app)
+        eventlet.wsgi.server(eventlet.listen((host, int(port)), s_type), app)
 

changedetectionio/content_fetcher.py

@@ -1,10 +1,14 @@
-from abc import ABC, abstractmethod
+import hashlib
+from abc import abstractmethod
 import chardet
 import json
+import logging
 import os
 import requests
-import time
 import sys
+import time
+
+visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4, header, footer, section, article, aside, details, main, nav, section, summary'
 
 
 class Non200ErrorCodeReceived(Exception):
@@ -22,6 +26,11 @@ class Non200ErrorCodeReceived(Exception):
         return
 
 
+class checksumFromPreviousCheckWasTheSame(Exception):
+    def __init__(self):
+        return
+
+
 class JSActionExceptions(Exception):
     def __init__(self, status_code, url, screenshot, message=''):
         self.status_code = status_code
@@ -30,8 +39,15 @@ class JSActionExceptions(Exception):
         self.message = message
         return
 
+
+class BrowserStepsStepTimout(Exception):
+    def __init__(self, step_n):
+        self.step_n = step_n
+        return
+
+
 class PageUnloadable(Exception):
-    def __init__(self, status_code, url, screenshot=False, message=False):
+    def __init__(self, status_code, url, message, screenshot=False):
         # Set this so we can use it in other parts of the app
         self.status_code = status_code
         self.url = url
@@ -39,6 +55,7 @@ class PageUnloadable(Exception):
         self.message = message
         return
 
+
 class EmptyReply(Exception):
     def __init__(self, status_code, url, screenshot=None):
         # Set this so we can use it in other parts of the app
@@ -47,6 +64,7 @@ class EmptyReply(Exception):
         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
@@ -57,6 +75,7 @@ class ScreenshotUnavailable(Exception):
             self.page_text = html_to_text(page_html)
         return
 
+
 class ReplyWithContentButNoText(Exception):
     def __init__(self, status_code, url, screenshot=None):
         # Set this so we can use it in other parts of the app
@@ -65,140 +84,20 @@ class ReplyWithContentButNoText(Exception):
         self.screenshot = screenshot
         return
 
+
 class Fetcher():
-    error = None
-    status_code = None
+    browser_steps = None
+    browser_steps_screenshot_path = None
     content = None
-    headers = None
-
+    error = None
     fetcher_description = "No description"
+    headers = {}
+    status_code = None
     webdriver_js_execute_code = None
-    xpath_element_js = """               
-                // Include the getXpath script directly, easier than fetching
-                !function(e,n){"object"==typeof exports&&"undefined"!=typeof module?module.exports=n():"function"==typeof define&&define.amd?define(n):(e=e||self).getXPath=n()}(this,function(){return function(e){var n=e;if(n&&n.id)return'//*[@id="'+n.id+'"]';for(var o=[];n&&Node.ELEMENT_NODE===n.nodeType;){for(var i=0,r=!1,d=n.previousSibling;d;)d.nodeType!==Node.DOCUMENT_TYPE_NODE&&d.nodeName===n.nodeName&&i++,d=d.previousSibling;for(d=n.nextSibling;d;){if(d.nodeName===n.nodeName){r=!0;break}d=d.nextSibling}o.push((n.prefix?n.prefix+":":"")+n.localName+(i||r?"["+(i+1)+"]":"")),n=n.parentNode}return o.length?"/"+o.reverse().join("/"):""}});
-
-
-                const findUpTag = (el) => {
-                  let r = el
-                  chained_css = [];
-                  depth=0;
-            
-                // Strategy 1: Keep going up until we hit an ID tag, imagine it's like  #list-widget div h4
-                  while (r.parentNode) {
-                    if(depth==5) {
-                      break;
-                    }
-                    if('' !==r.id) {
-                      chained_css.unshift("#"+CSS.escape(r.id));
-                      final_selector= chained_css.join(' > ');
-                      // Be sure theres only one, some sites have multiples of the same ID tag :-(
-                      if (window.document.querySelectorAll(final_selector).length ==1 ) {
-                        return final_selector;
-                        }
-                      return null;
-                    } else {
-                      chained_css.unshift(r.tagName.toLowerCase());
-                    }
-                    r=r.parentNode;
-                    depth+=1;
-                  }
-                  return null;
-                }
-
-
-                // @todo - if it's SVG or IMG, go into image diff mode
-                var elements = window.document.querySelectorAll("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");
-                var size_pos=[];
-                // after page fetch, inject this JS
-                // build a map of all elements and their positions (maybe that only include text?)
-                var bbox;
-                for (var i = 0; i < elements.length; i++) {   
-                 bbox = elements[i].getBoundingClientRect();
-
-                 // forget really small ones
-                 if (bbox['width'] <20 && bbox['height'] < 20 ) {
-                   continue;
-                 }
-
-                 // @todo the getXpath kind of sucks, it doesnt know when there is for example just one ID sometimes
-                 // it should not traverse when we know we can anchor off just an ID one level up etc..
-                 // maybe, get current class or id, keep traversing up looking for only class or id until there is just one match 
-
-                 // 1st primitive - if it has class, try joining it all and select, if theres only one.. well thats us.
-                 xpath_result=false;
-                 
-                 try {
-                   var d= findUpTag(elements[i]);
-                   if (d) {
-                     xpath_result =d;
-                   }                
-                 } catch (e) {
-                   console.log(e);
-                 }
-                 
-                 // You could swap it and default to getXpath and then try the smarter one
-                 // default back to the less intelligent one
-                 if (!xpath_result) {
-                    try {
-                       // I've seen on FB and eBay that this doesnt work
-                       // ReferenceError: getXPath is not defined at eval (eval at evaluate (:152:29), <anonymous>:67:20) at UtilityScript.evaluate (<anonymous>:159:18) at UtilityScript.<anonymous> (<anonymous>:1:44)
-                       xpath_result = getXPath(elements[i]);
-                     } catch (e) {
-                       console.log(e);
-                       continue;
-                     }            
-                 }
-                 
-                 if(window.getComputedStyle(elements[i]).visibility === "hidden") {
-                   continue;
-                 }
-
-                 size_pos.push({
-                   xpath: xpath_result,
-                   width: Math.round(bbox['width']), 
-                   height: Math.round(bbox['height']), 
-                   left: Math.floor(bbox['left']), 
-                   top: Math.floor(bbox['top']), 
-                   childCount: elements[i].childElementCount
-                 });                 
-                }
-
-
-                // inject the current one set in the css_filter, which may be a CSS rule
-                // used for displaying the current one in VisualSelector, where its not one we generated.
-                if (css_filter.length) {
-                   q=false;                   
-                   try {
-                       // is it xpath?
-                       if (css_filter.startsWith('/') || css_filter.startsWith('xpath:')) {
-                         q=document.evaluate(css_filter.replace('xpath:',''), document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
-                       } else {
-                         q=document.querySelector(css_filter);
-                       }                       
-                   } catch (e) {
-                    // Maybe catch DOMException and alert? 
-                     console.log(e);                       
-                   }
-                   bbox=false;
-                   if(q) {
-                     bbox = q.getBoundingClientRect();
-                   }
-                                   
-                   if (bbox && bbox['width'] >0 && bbox['height']>0) {                       
-                       size_pos.push({
-                           xpath: css_filter,
-                           width: bbox['width'], 
-                           height: bbox['height'],
-                           left: bbox['left'],
-                           top: bbox['top'],
-                           childCount: q.childElementCount
-                         });
-                     }
-                }
-                // Window.width required for proper scaling in the frontend
-                return {'size_pos':size_pos, 'browser_width': window.innerWidth};
-    """
     xpath_data = None
+    xpath_element_js = ""
+    instock_data = None
+    instock_data_js = ""
 
     # Will be needed in the future by the VisualSelector, always get this where possible.
     screenshot = False
@@ -208,6 +107,12 @@ class Fetcher():
     # Time ONTOP of the system defined env minimum time
     render_extract_delay = 0
 
+    def __init__(self):
+        from pkg_resources import resource_string
+        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
+        self.xpath_element_js = resource_string(__name__, "res/xpath_element_scraper.js").decode('utf-8')
+        self.instock_data_js = resource_string(__name__, "res/stock-not-in-stock.js").decode('utf-8')
+
     @abstractmethod
     def get_error(self):
         return self.error
@@ -220,7 +125,8 @@ class Fetcher():
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_css_filter=None):
+            current_include_filters=None,
+            is_binary=False):
         # Should set self.error, self.status_code and self.content
         pass
 
@@ -232,11 +138,72 @@ class Fetcher():
     def get_last_status_code(self):
         return self.status_code
 
+    @abstractmethod
+    def screenshot_step(self, step_n):
+        return None
+
     @abstractmethod
     # Return true/false if this checker is ready to run, in the case it needs todo some special config check etc
     def is_ready(self):
         return True
 
+    def get_all_headers(self):
+        """
+        Get all headers but ensure all keys are lowercase
+        :return:
+        """
+        return {k.lower(): v for k, v in self.headers.items()}
+
+    def iterate_browser_steps(self):
+        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+        from playwright._impl._api_types import TimeoutError
+        from jinja2 import Environment
+        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
+
+        step_n = 0
+
+        if self.browser_steps is not None and len(self.browser_steps):
+            interface = steppable_browser_interface()
+            interface.page = self.page
+
+            valid_steps = filter(
+                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+                self.browser_steps)
+
+            for step in valid_steps:
+                step_n += 1
+                print(">> Iterating check - browser Step n {} - {}...".format(step_n, step['operation']))
+                self.screenshot_step("before-" + str(step_n))
+                self.save_step_html("before-" + str(step_n))
+                try:
+                    optional_value = step['optional_value']
+                    selector = step['selector']
+                    # Support for jinja2 template in step values, with date module added
+                    if '{%' in step['optional_value'] or '{{' in step['optional_value']:
+                        optional_value = str(jinja2_env.from_string(step['optional_value']).render())
+                    if '{%' in step['selector'] or '{{' in step['selector']:
+                        selector = str(jinja2_env.from_string(step['selector']).render())
+
+                    getattr(interface, "call_action")(action_name=step['operation'],
+                                                      selector=selector,
+                                                      optional_value=optional_value)
+                    self.screenshot_step(step_n)
+                    self.save_step_html(step_n)
+                except TimeoutError as e:
+                    print(str(e))
+                    # Stop processing here
+                    raise BrowserStepsStepTimout(step_n=step_n)
+
+    # It's always good to reset these
+    def delete_browser_steps_screenshots(self):
+        import glob
+        if self.browser_steps_screenshot_path is not None:
+            dest = os.path.join(self.browser_steps_screenshot_path, 'step_*.jpeg')
+            files = glob.glob(dest)
+            for f in files:
+                if os.path.isfile(f):
+                    os.unlink(f)
+
 
 #   Maybe for the future, each fetcher provides its own diff output, could be used for text, image
 #   the current one would return javascript output (as we use JS to generate the diff)
@@ -273,7 +240,7 @@ class base_html_playwright(Fetcher):
     proxy = None
 
     def __init__(self, proxy_override=None):
-
+        super().__init__()
         # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
         self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
         self.command_executor = os.getenv(
@@ -293,16 +260,145 @@ class base_html_playwright(Fetcher):
 
         # allow per-watch proxy selection override
         if proxy_override:
-            # https://playwright.dev/docs/network#http-proxy
+            self.proxy = {'server': proxy_override}
+
+        if self.proxy:
+            # Playwright needs separate username and password values
             from urllib.parse import urlparse
-            parsed = urlparse(proxy_override)
-            proxy_url = "{}://{}:{}".format(parsed.scheme, parsed.hostname, parsed.port)
-            self.proxy = {'server': proxy_url}
+            parsed = urlparse(self.proxy.get('server'))
             if parsed.username:
                 self.proxy['username'] = parsed.username
-            if parsed.password:
                 self.proxy['password'] = parsed.password
 
+    def screenshot_step(self, step_n=''):
+        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=85)
+
+        if self.browser_steps_screenshot_path is not None:
+            destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.jpeg'.format(step_n))
+            logging.debug("Saving step screenshot to {}".format(destination))
+            with open(destination, 'wb') as f:
+                f.write(screenshot)
+
+    def save_step_html(self, step_n):
+        content = self.page.content()
+        destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.html'.format(step_n))
+        logging.debug("Saving step HTML to {}".format(destination))
+        with open(destination, 'w') as f:
+            f.write(content)
+
+    def run_fetch_browserless_puppeteer(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None,
+            is_binary=False):
+
+        from pkg_resources import resource_string
+
+        extra_wait_ms = (int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay) * 1000
+
+        self.xpath_element_js = self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
+        code = resource_string(__name__, "res/puppeteer_fetch.js").decode('utf-8')
+        # In the future inject this is a proper JS package
+        code = code.replace('%xpath_scrape_code%', self.xpath_element_js)
+        code = code.replace('%instock_scrape_code%', self.instock_data_js)
+
+        from requests.exceptions import ConnectTimeout, ReadTimeout
+        wait_browserless_seconds = 240
+
+        browserless_function_url = os.getenv('BROWSERLESS_FUNCTION_URL')
+        from urllib.parse import urlparse
+        if not browserless_function_url:
+            # Convert/try to guess from PLAYWRIGHT_DRIVER_URL
+            o = urlparse(os.getenv('PLAYWRIGHT_DRIVER_URL'))
+            browserless_function_url = o._replace(scheme="http")._replace(path="function").geturl()
+
+
+        # Append proxy connect string
+        if self.proxy:
+            import urllib.parse
+            # Remove username/password if it exists in the URL or you will receive "ERR_NO_SUPPORTED_PROXIES" error
+            # Actual authentication handled by Puppeteer/node
+            o = urlparse(self.proxy.get('server'))
+            proxy_url = urllib.parse.quote(o._replace(netloc="{}:{}".format(o.hostname, o.port)).geturl())
+            browserless_function_url = f"{browserless_function_url}&--proxy-server={proxy_url}&dumpio=true"
+
+
+        try:
+            amp = '&' if '?' in browserless_function_url else '?'
+            response = requests.request(
+                method="POST",
+                json={
+                    "code": code,
+                    "context": {
+                        # Very primitive disk cache - USE WITH EXTREME CAUTION
+                        # Run browserless container  with -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]"
+                        'disk_cache_dir': os.getenv("PUPPETEER_DISK_CACHE", False), # or path to disk cache ending in /, ie /tmp/cache/
+                        'execute_js': self.webdriver_js_execute_code,
+                        'extra_wait_ms': extra_wait_ms,
+                        'include_filters': current_include_filters,
+                        'req_headers': request_headers,
+                        'screenshot_quality': int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)),
+                        'url': url,
+                        'user_agent': request_headers.get('User-Agent', 'Mozilla/5.0'),
+                        'proxy_username': self.proxy.get('username','') if self.proxy else False,
+                        'proxy_password': self.proxy.get('password', '') if self.proxy else False,
+                        'no_cache_list': [
+                            'twitter',
+                            '.pdf'
+                        ],
+                        # Could use https://github.com/easylist/easylist here, or install a plugin
+                        'block_url_list': [
+                            'adnxs.com',
+                            'analytics.twitter.com',
+                            'doubleclick.net',
+                            'google-analytics.com',
+                            'googletagmanager',
+                            'trustpilot.com'
+                        ]
+                    }
+                },
+                # @todo /function needs adding ws:// to http:// rebuild this
+                url=browserless_function_url+f"{amp}--disable-features=AudioServiceOutOfProcess&dumpio=true&--disable-remote-fonts",
+                timeout=wait_browserless_seconds)
+
+        except ReadTimeout:
+            raise PageUnloadable(url=url, status_code=None, message=f"No response from browserless in {wait_browserless_seconds}s")
+        except ConnectTimeout:
+            raise PageUnloadable(url=url, status_code=None, message=f"Timed out connecting to browserless, retrying..")
+        else:
+            # 200 Here means that the communication to browserless worked only, not the page state
+            if response.status_code == 200:
+                import base64
+
+                x = response.json()
+                if not x.get('screenshot'):
+                    # https://github.com/puppeteer/puppeteer/blob/v1.0.0/docs/troubleshooting.md#tips
+                    # https://github.com/puppeteer/puppeteer/issues/1834
+                    # https://github.com/puppeteer/puppeteer/issues/1834#issuecomment-381047051
+                    # Check your memory is shared and big enough
+                    raise ScreenshotUnavailable(url=url, status_code=None)
+
+                if not x.get('content', '').strip():
+                    raise EmptyReply(url=url, status_code=None)
+
+                if x.get('status_code', 200) != 200 and not ignore_status_codes:
+                    raise Non200ErrorCodeReceived(url=url, status_code=x.get('status_code', 200), page_html=x['content'])
+
+                self.content = x.get('content')
+                self.headers = x.get('headers')
+                self.instock_data = x.get('instock_data')
+                self.screenshot = base64.b64decode(x.get('screenshot'))
+                self.status_code = x.get('status_code')
+                self.xpath_data = x.get('xpath_data')
+
+            else:
+                # Some other error from browserless
+                raise PageUnloadable(url=url, status_code=None, message=response.content.decode('utf-8'))
+
     def run(self,
             url,
             timeout,
@@ -310,13 +406,32 @@ class base_html_playwright(Fetcher):
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_css_filter=None):
+            current_include_filters=None,
+            is_binary=False):
+
+        # For now, USE_EXPERIMENTAL_PUPPETEER_FETCH is not supported by watches with BrowserSteps (for now!)
+        has_browser_steps = self.browser_steps and list(filter(
+                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+                self.browser_steps))
+
+        if not has_browser_steps:
+            if os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
+                # Temporary backup solution until we rewrite the playwright code
+                return self.run_fetch_browserless_puppeteer(
+                    url,
+                    timeout,
+                    request_headers,
+                    request_body,
+                    request_method,
+                    ignore_status_codes,
+                    current_include_filters,
+                    is_binary)
 
         from playwright.sync_api import sync_playwright
         import playwright._impl._api_types
-        from playwright._impl._api_types import Error, TimeoutError
-        response = None
 
+        self.delete_browser_steps_screenshots()
+        response = None
         with sync_playwright() as p:
             browser_type = getattr(p, self.browser_type)
 
@@ -328,97 +443,97 @@ class base_html_playwright(Fetcher):
             # Set user agent to prevent Cloudflare from blocking the browser
             # Use the default one configured in the App.py model that's passed from fetch_site_status.py
             context = browser.new_context(
-                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
+                user_agent=request_headers.get('User-Agent', 'Mozilla/5.0'),
                 proxy=self.proxy,
                 # This is needed to enable JavaScript execution on GitHub and others
                 bypass_csp=True,
+                # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
+                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
                 # Should never be needed
                 accept_downloads=False
             )
 
+            self.page = context.new_page()
             if len(request_headers):
                 context.set_extra_http_headers(request_headers)
 
-            page = context.new_page()
-            try:
-                page.set_default_navigation_timeout(90000)
-                page.set_default_timeout(90000)
+                self.page.set_default_navigation_timeout(90000)
+                self.page.set_default_timeout(90000)
 
                 # Listen for all console events and handle errors
-                page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
+                self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
 
-                # Bug - never set viewport size BEFORE page.goto
+            # Goto page
+            try:
+                # Wait_until = commit
+                # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
+                # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
+                # This seemed to solve nearly all 'TimeoutErrors'
+                response = self.page.goto(url, wait_until='commit')
+            except playwright._impl._api_types.Error as e:
+                # Retry once - https://github.com/browserless/chrome/issues/2485
+                # Sometimes errors related to invalid cert's and other can be random
+                print("Content Fetcher > retrying request got error - ", str(e))
+                time.sleep(1)
+                response = self.page.goto(url, wait_until='commit')
 
-                # Waits for the next navigation. Using Python context manager
-                # prevents a race condition between clicking and waiting for a navigation.
-                with page.expect_navigation():
-                    response = page.goto(url, wait_until='load')
+            except Exception as e:
+                print("Content Fetcher > Other exception when page.goto", str(e))
+                context.close()
+                browser.close()
+                raise PageUnloadable(url=url, status_code=None, message=str(e))
 
+            # Execute any browser steps
+            try:
+                extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+                self.page.wait_for_timeout(extra_wait * 1000)
+
+                if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
+                    self.page.evaluate(self.webdriver_js_execute_code)
 
             except playwright._impl._api_types.TimeoutError as e:
                 context.close()
                 browser.close()
                 # This can be ok, we will try to grab what we could retrieve
                 pass
-
             except Exception as e:
-                print("other exception when page.goto")
-                print(str(e))
+                print("Content Fetcher > Other exception when executing custom JS code", str(e))
                 context.close()
                 browser.close()
-                raise PageUnloadable(url=url, status_code=None, message=e.message)
+                raise PageUnloadable(url=url, status_code=None, message=str(e))
 
             if response is None:
                 context.close()
                 browser.close()
-                print("response object was none")
+                print("Content Fetcher > Response object was none")
                 raise EmptyReply(url=url, status_code=None)
 
+            # Run Browser Steps here
+            self.iterate_browser_steps()
 
-            # Removed browser-set-size, seemed to be needed to make screenshots work reliably in older playwright versions
-            # Was causing exceptions like 'waiting for page but content is changing' etc
-            # https://www.browserstack.com/docs/automate/playwright/change-browser-window-size 1280x720 should be the default
-                        
             extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
             time.sleep(extra_wait)
 
-            if self.webdriver_js_execute_code is not None:
-                try:
-                    page.evaluate(self.webdriver_js_execute_code)
-                except Exception as e:
-                    # Is it possible to get a screenshot?
-                    error_screenshot = False
-                    try:
-                        page.screenshot(type='jpeg',
-                                        clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024},
-                                        quality=1)
+            self.content = self.page.content()
+            self.status_code = response.status
+            if len(self.page.content().strip()) == 0:
+                context.close()
+                browser.close()
+                print("Content Fetcher > Content was empty")
+                raise EmptyReply(url=url, status_code=response.status)
 
-                        # The actual screenshot
-                        error_screenshot = page.screenshot(type='jpeg',
-                                                           full_page=True,
-                                                           quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
-                    except Exception as s:
-                        pass
-
-                    raise JSActionExceptions(status_code=response.status, screenshot=error_screenshot, message=str(e), url=url)
-
-                else:
-                    # JS eval was run, now we also wait some time if possible to let the page settle
-                    if self.render_extract_delay:
-                        page.wait_for_timeout(self.render_extract_delay * 1000)
-
-            page.wait_for_timeout(500)
-
-            self.content = page.content()
             self.status_code = response.status
             self.headers = response.all_headers()
 
-            if current_css_filter is not None:
-                page.evaluate("var css_filter={}".format(json.dumps(current_css_filter)))
+            # 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:
-                page.evaluate("var css_filter=''")
+                self.page.evaluate("var include_filters=''")
 
-            self.xpath_data = page.evaluate("async () => {" + self.xpath_element_js + "}")
+            self.xpath_data = self.page.evaluate(
+                "async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
+            self.instock_data = self.page.evaluate("async () => {" + self.instock_data_js + "}")
 
             # Bug 3 in Playwright screenshot handling
             # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
@@ -428,26 +543,17 @@ class base_html_playwright(Fetcher):
             # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
             # acceptable screenshot quality here
             try:
-                # Quality set to 1 because it's not used, just used as a work-around for a bug, no need to change this.
-                page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024}, quality=1)
                 # The actual screenshot
-                self.screenshot = page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+                self.screenshot = self.page.screenshot(type='jpeg', full_page=True,
+                                                       quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
             except Exception as e:
                 context.close()
                 browser.close()
                 raise ScreenshotUnavailable(url=url, status_code=None)
 
-            if len(self.content.strip()) == 0:
-                context.close()
-                browser.close()
-                print("Content was empty")
-                raise EmptyReply(url=url, status_code=None, screenshot=self.screenshot)
-
             context.close()
             browser.close()
 
-            if not ignore_status_codes and self.status_code!=200:
-                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, page_html=self.content, screenshot=self.screenshot)
 
 class base_html_webdriver(Fetcher):
     if os.getenv("WEBDRIVER_URL"):
@@ -465,6 +571,7 @@ class base_html_webdriver(Fetcher):
     proxy = None
 
     def __init__(self, proxy_override=None):
+        super().__init__()
         from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
 
         # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
@@ -497,7 +604,8 @@ class base_html_webdriver(Fetcher):
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_css_filter=None):
+            current_include_filters=None,
+            is_binary=False):
 
         from selenium import webdriver
         from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
@@ -541,7 +649,6 @@ class base_html_webdriver(Fetcher):
     def is_ready(self):
         from selenium import webdriver
         from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
-        from selenium.common.exceptions import WebDriverException
 
         self.driver = webdriver.Remote(
             command_executor=self.command_executor,
@@ -556,7 +663,7 @@ class base_html_webdriver(Fetcher):
             try:
                 self.driver.quit()
             except Exception as e:
-                print("Exception in chrome shutdown/quit" + str(e))
+                print("Content Fetcher > Exception in chrome shutdown/quit" + str(e))
 
 
 # "html_requests" is listed as the default fetcher in store.py!
@@ -573,7 +680,8 @@ class html_requests(Fetcher):
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_css_filter=None):
+            current_include_filters=None,
+            is_binary=False):
 
         # Make requests use a more modern looking user-agent
         if not 'User-Agent' in request_headers:
@@ -603,10 +711,12 @@ class html_requests(Fetcher):
         # For example - some sites don't tell us it's utf-8, but return utf-8 content
         # This seems to not occur when using webdriver/selenium, it seems to detect the text encoding more reliably.
         # https://github.com/psf/requests/issues/1604 good info about requests encoding detection
-        if not r.headers.get('content-type') or not 'charset=' in r.headers.get('content-type'):
-            encoding = chardet.detect(r.content)['encoding']
-            if encoding:
-                r.encoding = encoding
+        if not is_binary:
+            # Don't run this for PDF (and requests identified as binary) takes a _long_ time
+            if not r.headers.get('content-type') or not 'charset=' in r.headers.get('content-type'):
+                encoding = chardet.detect(r.content)['encoding']
+                if encoding:
+                    r.encoding = encoding
 
         if not r.content or not len(r.content):
             raise EmptyReply(url=url, status_code=r.status_code)
@@ -618,8 +728,14 @@ class html_requests(Fetcher):
             raise Non200ErrorCodeReceived(url=url, status_code=r.status_code, page_html=r.text)
 
         self.status_code = r.status_code
-        self.content = r.text
+        if is_binary:
+            # Binary files just return their checksum until we add something smarter
+            self.content = hashlib.md5(r.content).hexdigest()
+        else:
+            self.content = r.text
+
         self.headers = r.headers
+        self.raw_content = r.content
 
 
 # Decide which is the 'real' HTML webdriver, this is more a system wide config

changedetectionio/dev-docker/Dockerfile

@@ -1,14 +0,0 @@
-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" ]
-
-
-

changedetectionio/dev-docker/sleep.py

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

changedetectionio/diff.py

@@ -10,7 +10,7 @@ def same_slicer(l, a, b):
         return l[a:b]
 
 # like .compare but a little different output
-def customSequenceMatcher(before, after, include_equal=False):
+def customSequenceMatcher(before, after, include_equal=False, include_removed=True, include_added=True, include_replaced=True, include_change_type_prefix=True):
     cruncher = difflib.SequenceMatcher(isjunk=lambda x: x in " \\t", a=before, b=after)
 
     # @todo Line-by-line mode instead of buncghed, including `after` that is not in `before` (maybe unset?)
@@ -18,35 +18,41 @@ def customSequenceMatcher(before, after, include_equal=False):
         if include_equal and tag == 'equal':
             g = before[alo:ahi]
             yield g
-        elif tag == 'delete':
-            g = ["(removed) " + i for i in same_slicer(before, alo, ahi)]
+        elif include_removed and tag == 'delete':
+            row_prefix = "(removed) " if include_change_type_prefix else ''
+            g = [ row_prefix + i for i in same_slicer(before, alo, ahi)]
             yield g
-        elif tag == 'replace':
-            g = ["(changed) " + i for i in same_slicer(before, alo, ahi)]
-            g += ["(into   ) " + i for i in same_slicer(after, blo, bhi)]
+        elif include_replaced and tag == 'replace':
+            row_prefix = "(changed) " if include_change_type_prefix else ''
+            g = [row_prefix + i for i in same_slicer(before, alo, ahi)]
+            row_prefix = "(into) " if include_change_type_prefix else ''
+            g += [row_prefix + i for i in same_slicer(after, blo, bhi)]
             yield g
-        elif tag == 'insert':
-            g = ["(added  ) " + i for i in same_slicer(after, blo, bhi)]
+        elif include_added and tag == 'insert':
+            row_prefix = "(added) " if include_change_type_prefix else ''
+            g = [row_prefix + i for i in same_slicer(after, blo, bhi)]
             yield g
 
 # only_differences - only return info about the differences, no context
-# line_feed_sep could be "<br/>" or "<li>" or "\n" etc
-def render_diff(previous_file, newest_file, include_equal=False, line_feed_sep="\n"):
-    with open(newest_file, 'r') as f:
-        newest_version_file_contents = f.read()
-        newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
+# line_feed_sep could be "<br>" or "<li>" or "\n" etc
+def render_diff(previous_version_file_contents, newest_version_file_contents, include_equal=False, include_removed=True, include_added=True, include_replaced=True, line_feed_sep="\n", include_change_type_prefix=True):
 
-    if previous_file:
-        with open(previous_file, 'r') as f:
-            previous_version_file_contents = f.read()
+    newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
+
+    if previous_version_file_contents:
             previous_version_file_contents = [line.rstrip() for line in previous_version_file_contents.splitlines()]
     else:
         previous_version_file_contents = ""
 
-    rendered_diff = customSequenceMatcher(previous_version_file_contents,
-                                          newest_version_file_contents,
-                                          include_equal)
+    rendered_diff = customSequenceMatcher(before=previous_version_file_contents,
+                                          after=newest_version_file_contents,
+                                          include_equal=include_equal,
+                                          include_removed=include_removed,
+                                          include_added=include_added,
+                                          include_replaced=include_replaced,
+                                          include_change_type_prefix=include_change_type_prefix)
 
     # Recursively join lists
     f = lambda L: line_feed_sep.join([f(x) if type(x) is list else x for x in L])
-    return f(rendered_diff)
+    p= f(rendered_diff)
+    return p

changedetectionio/fetch_site_status.py

@@ -1,303 +0,0 @@
-import hashlib
-import logging
-import os
-import re
-import time
-import urllib3
-
-from changedetectionio import content_fetcher, html_tools
-
-urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
-
-
-# Some common stuff here that can be moved to a base class
-# (set_proxy_from_list)
-class perform_site_check():
-    screenshot = None
-    xpath_data = None
-
-    def __init__(self, *args, datastore, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.datastore = datastore
-
-    # Doesn't look like python supports forward slash auto enclosure in re.findall
-    # So convert it to inline flag "foobar(?i)" type configuration
-    def forward_slash_enclosed_regex_to_options(self, regex):
-        res = re.search(r'^/(.*?)/(\w+)$', regex, re.IGNORECASE)
-
-        if res:
-            regex = res.group(1)
-            regex += '(?{})'.format(res.group(2))
-        else:
-            regex += '(?{})'.format('i')
-
-        return regex
-
-
-    def run(self, uuid):
-        from jinja2 import Environment
-
-        changed_detected = False
-        screenshot = False  # as bytes
-        stripped_text_from_html = ""
-
-        watch = self.datastore.data['watching'].get(uuid)
-        if not watch:
-            return
-
-        # Protect against file:// access
-        if re.search(r'^file', watch['url'], re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
-            raise Exception(
-                "file:// type access is denied for security reasons."
-            )
-
-        # Unset any existing notification error
-        update_obj = {'last_notification_error': False, 'last_error': False}
-
-        extra_headers =self.datastore.data['watching'][uuid].get('headers')
-
-        # Tweak the base config with the per-watch ones
-        request_headers = self.datastore.data['settings']['headers'].copy()
-        request_headers.update(extra_headers)
-
-        # https://github.com/psf/requests/issues/4525
-        # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
-        # do this by accident.
-        if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
-            request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
-
-        timeout = self.datastore.data['settings']['requests'].get('timeout')
-
-        # Jinja2 available in URLs along with https://pypi.org/project/jinja2-time/
-        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
-        url = str(jinja2_env.from_string(watch.get('url')).render())
-
-        request_body = self.datastore.data['watching'][uuid].get('body')
-        request_method = self.datastore.data['watching'][uuid].get('method')
-        ignore_status_codes = self.datastore.data['watching'][uuid].get('ignore_status_codes', False)
-
-        # source: support
-        is_source = False
-        if url.startswith('source:'):
-            url = url.replace('source:', '')
-            is_source = True
-
-        # Pluggable content fetcher
-        prefer_backend = watch['fetch_backend']
-        if hasattr(content_fetcher, prefer_backend):
-            klass = getattr(content_fetcher, prefer_backend)
-        else:
-            # If the klass doesnt exist, just use a default
-            klass = getattr(content_fetcher, "html_requests")
-
-        proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=uuid)
-        proxy_url = None
-        if proxy_id:
-            proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
-            print ("UUID {} Using proxy {}".format(uuid, proxy_url))
-
-        fetcher = klass(proxy_override=proxy_url)
-
-        # Configurable per-watch or global extra delay before extracting text (for webDriver types)
-        system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
-        if watch['webdriver_delay'] is not None:
-            fetcher.render_extract_delay = watch['webdriver_delay']
-        elif system_webdriver_delay is not None:
-            fetcher.render_extract_delay = system_webdriver_delay
-
-        if watch['webdriver_js_execute_code'] is not None and watch['webdriver_js_execute_code'].strip():
-            fetcher.webdriver_js_execute_code = watch['webdriver_js_execute_code']
-
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch['css_filter'])
-        fetcher.quit()
-
-        self.screenshot = fetcher.screenshot
-        self.xpath_data = fetcher.xpath_data
-
-        # Fetching complete, now filters
-        # @todo move to class / maybe inside of fetcher abstract base?
-
-        # @note: I feel like the following should be in a more obvious chain system
-        #  - Check filter text
-        #  - Is the checksum different?
-        #  - Do we convert to JSON?
-        # https://stackoverflow.com/questions/41817578/basic-method-chaining ?
-        # return content().textfilter().jsonextract().checksumcompare() ?
-
-        is_json = 'application/json' in fetcher.headers.get('Content-Type', '')
-        is_html = not is_json
-
-        # source: support, basically treat it as plaintext
-        if is_source:
-            is_html = False
-            is_json = False
-
-        css_filter_rule = watch['css_filter']
-        subtractive_selectors = watch.get(
-            "subtractive_selectors", []
-        ) + self.datastore.data["settings"]["application"].get(
-            "global_subtractive_selectors", []
-        )
-
-        has_filter_rule = css_filter_rule and len(css_filter_rule.strip())
-        has_subtractive_selectors = subtractive_selectors and len(subtractive_selectors[0].strip())
-
-        if is_json and not has_filter_rule:
-            css_filter_rule = "json:$"
-            has_filter_rule = True
-
-        if has_filter_rule:
-            json_filter_prefixes = ['json:', 'jq:']
-            if any(prefix in css_filter_rule for prefix in json_filter_prefixes):
-                stripped_text_from_html = html_tools.extract_json_as_string(content=fetcher.content, json_filter=css_filter_rule)
-                is_html = False
-
-        if is_html or is_source:
-            
-            # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-            fetcher.content = html_tools.workarounds_for_obfuscations(fetcher.content)
-            html_content = fetcher.content
-
-            # If not JSON,  and if it's not text/plain..
-            if 'text/plain' in fetcher.headers.get('Content-Type', '').lower():
-                # Don't run get_text or xpath/css filters on plaintext
-                stripped_text_from_html = html_content
-            else:
-                # Then we assume HTML
-                if has_filter_rule:
-                    # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
-                    if css_filter_rule[0] == '/' or css_filter_rule.startswith('xpath:'):
-                        html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule.replace('xpath:', ''),
-                                                               html_content=fetcher.content)
-                    else:
-                        # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-                        html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content)
-
-                if has_subtractive_selectors:
-                    html_content = html_tools.element_removal(subtractive_selectors, html_content)
-
-                if not is_source:
-                    # extract text
-                    stripped_text_from_html = \
-                        html_tools.html_to_text(
-                            html_content,
-                            render_anchor_tag_content=self.datastore.data["settings"][
-                                "application"].get(
-                                "render_anchor_tag_content", False)
-                        )
-
-                elif is_source:
-                    stripped_text_from_html = html_content
-
-            # Re #340 - return the content before the 'ignore text' was applied
-            text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
-
-        # Re #340 - return the content before the 'ignore text' was applied
-        text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
-
-        # Treat pages with no renderable text content as a change? No by default
-        empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
-        if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
-            raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot)
-
-        # We rely on the actual text in the html output.. many sites have random script vars etc,
-        # in the future we'll implement other mechanisms.
-
-        update_obj["last_check_status"] = fetcher.get_last_status_code()
-
-        # If there's text to skip
-        # @todo we could abstract out the get_text() to handle this cleaner
-        text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
-        if len(text_to_ignore):
-            stripped_text_from_html = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
-        else:
-            stripped_text_from_html = stripped_text_from_html.encode('utf8')
-
-        # 615 Extract text by regex
-        extract_text = watch.get('extract_text', [])
-        if len(extract_text) > 0:
-            regex_matched_output = []
-            for s_re in extract_text:
-                # incase they specified something in '/.../x'
-                regex = self.forward_slash_enclosed_regex_to_options(s_re)
-                result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
-
-                for l in result:
-                    if type(l) is tuple:
-                        #@todo - some formatter option default (between groups)
-                        regex_matched_output += list(l) + [b'\n']
-                    else:
-                        # @todo - some formatter option default (between each ungrouped result)
-                        regex_matched_output += [l] + [b'\n']
-
-            # Now we will only show what the regex matched
-            stripped_text_from_html = b''
-            text_content_before_ignored_filter = b''
-            if regex_matched_output:
-                # @todo some formatter for presentation?
-                stripped_text_from_html = b''.join(regex_matched_output)
-                text_content_before_ignored_filter = stripped_text_from_html
-
-
-        # Re #133 - if we should strip whitespaces from triggering the change detected comparison
-        if self.datastore.data['settings']['application'].get('ignore_whitespace', False):
-            fetched_md5 = hashlib.md5(stripped_text_from_html.translate(None, b'\r\n\t ')).hexdigest()
-        else:
-            fetched_md5 = hashlib.md5(stripped_text_from_html).hexdigest()
-
-        ############ Blocking rules, after checksum #################
-        blocked = False
-
-        if len(watch['trigger_text']):
-            # Assume blocked
-            blocked = True
-            # Filter and trigger works the same, so reuse it
-            # It should return the line numbers that match
-            result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
-                                                  wordlist=watch['trigger_text'],
-                                                  mode="line numbers")
-            # Unblock if the trigger was found
-            if result:
-                blocked = False
-
-
-        if len(watch['text_should_not_be_present']):
-            # If anything matched, then we should block a change from happening
-            result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
-                                                  wordlist=watch['text_should_not_be_present'],
-                                                  mode="line numbers")
-            if result:
-                blocked = True
-
-        # The main thing that all this at the moment comes down to :)
-        if watch['previous_md5'] != fetched_md5:
-            changed_detected = True
-
-        # Looks like something changed, but did it match all the rules?
-        if blocked:
-            changed_detected = False
-
-        # Extract title as title
-        if is_html:
-            if self.datastore.data['settings']['application']['extract_title_as_title'] or watch['extract_title_as_title']:
-                if not watch['title'] or not len(watch['title']):
-                    update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
-
-        if changed_detected:
-            if watch.get('check_unique_lines', False):
-                has_unique_lines = watch.lines_contain_something_unique_compared_to_history(lines=stripped_text_from_html.splitlines())
-                # One or more lines? unsure?
-                if not has_unique_lines:
-                    logging.debug("check_unique_lines: UUID {} didnt have anything new setting change_detected=False".format(uuid))
-                    changed_detected = False
-                else:
-                    logging.debug("check_unique_lines: UUID {} had unique content".format(uuid))
-
-        # Always record the new checksum
-        update_obj["previous_md5"] = fetched_md5
-
-        # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
-        if not watch.get('previous_md5'):
-            watch['previous_md5'] = fetched_md5
-
-        return changed_detected, update_obj, text_content_before_ignored_filter

changedetectionio/forms.py

@@ -1,11 +1,11 @@
+import os
 import re
+from distutils.util import strtobool
 
 from wtforms import (
     BooleanField,
-    Field,
     Form,
     IntegerField,
-    PasswordField,
     RadioField,
     SelectField,
     StringField,
@@ -13,20 +13,24 @@ from wtforms import (
     TextAreaField,
     fields,
     validators,
-    widgets,
+    widgets
 )
+from wtforms.fields import FieldList
 from wtforms.validators import ValidationError
 
+# default
+# each select <option data-enabled="enabled-0-0"
+from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
+
 from changedetectionio import content_fetcher
 from changedetectionio.notification import (
-    default_notification_body,
-    default_notification_format,
-    default_notification_title,
     valid_notification_formats,
 )
 
 from wtforms.fields import FormField
 
+dictfilt = lambda x, y: dict([ (i,x[i]) for i in x if i in set(y) ])
+
 valid_method = {
     'GET',
     'POST',
@@ -89,6 +93,29 @@ class SaltyPasswordField(StringField):
         else:
             self.data = False
 
+class StringTagUUID(StringField):
+
+   # process_formdata(self, valuelist) handled manually in POST handler
+
+    # Is what is shown when field <input> is rendered
+    def _value(self):
+        # Tag UUID to name, on submit it will convert it back (in the submit handler of init.py)
+        if self.data and type(self.data) is list:
+            tag_titles = []
+            for i in self.data:
+                tag = self.datastore.data['settings']['application']['tags'].get(i)
+                if tag:
+                    tag_title = tag.get('title')
+                    if tag_title:
+                        tag_titles.append(tag_title)
+
+            return ', '.join(tag_titles)
+
+        if not self.data:
+            return ''
+
+        return 'error'
+
 class TimeBetweenCheckForm(Form):
     weeks = IntegerField('Weeks', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
     days = IntegerField('Days', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
@@ -137,7 +164,7 @@ class ValidateContentFetcherIsReady(object):
         from changedetectionio import content_fetcher
 
         # Better would be a radiohandler that keeps a reference to each class
-        if field.data is not None:
+        if field.data is not None and field.data != 'system':
             klass = getattr(content_fetcher, field.data)
             some_object = klass()
             try:
@@ -146,12 +173,12 @@ class ValidateContentFetcherIsReady(object):
             except urllib3.exceptions.MaxRetryError as e:
                 driver_url = some_object.command_executor
                 message = field.gettext('Content fetcher \'%s\' did not respond.' % (field.data))
-                message += '<br/>' + field.gettext(
+                message += '<br>' + field.gettext(
                     'Be sure that the selenium/webdriver runner is running and accessible via network from this container/host.')
-                message += '<br/>' + field.gettext('Did you follow the instructions in the wiki?')
-                message += '<br/><br/>' + field.gettext('WebDriver Host: %s' % (driver_url))
-                message += '<br/><a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">Go here for more information</a>'
-                message += '<br/>'+field.gettext('Content fetcher did not respond properly, unable to use it.\n %s' % (str(e)))
+                message += '<br>' + field.gettext('Did you follow the instructions in the wiki?')
+                message += '<br><br>' + field.gettext('WebDriver Host: %s' % (driver_url))
+                message += '<br><a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">Go here for more information</a>'
+                message += '<br>'+field.gettext('Content fetcher did not respond properly, unable to use it.\n %s' % (str(e)))
 
                 raise ValidationError(message)
 
@@ -192,7 +219,7 @@ class ValidateAppRiseServers(object):
                 message = field.gettext('\'%s\' is not a valid AppRise URL.' % (server_url))
                 raise ValidationError(message)
 
-class ValidateTokensList(object):
+class ValidateJinja2Template(object):
     """
     Validates that a {token} is from a valid set
     """
@@ -201,14 +228,27 @@ class ValidateTokensList(object):
 
     def __call__(self, form, field):
         from changedetectionio import notification
-        regex = re.compile('{.*?}')
-        for p in re.findall(regex, field.data):
-            if not p.strip('{}') in notification.valid_tokens:
-                message = field.gettext('Token \'%s\' is not a valid token.')
-                raise ValidationError(message % (p))
-            
+
+        from jinja2 import Environment, BaseLoader, TemplateSyntaxError
+        from jinja2.meta import find_undeclared_variables
+
+
+        try:
+            jinja2_env = Environment(loader=BaseLoader)
+            jinja2_env.globals.update(notification.valid_tokens)
+            rendered = jinja2_env.from_string(field.data).render()
+        except TemplateSyntaxError as e:
+            raise ValidationError(f"This is not a valid Jinja2 template: {e}") from e
+
+        ast = jinja2_env.parse(field.data)
+        undefined = ", ".join(find_undeclared_variables(ast))
+        if undefined:
+            raise ValidationError(
+                f"The following tokens used in the notification are not valid: {undefined}"
+            )
+
 class validateURL(object):
-    
+
     """
        Flask wtform validators wont work with basic auth
     """
@@ -218,12 +258,19 @@ class validateURL(object):
 
     def __call__(self, form, field):
         import validators
+        # If hosts that only contain alphanumerics are allowed ("localhost" for example)
+        allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
         try:
-            validators.url(field.data.strip())
+            validators.url(field.data.strip(), simple_host=allow_simplehost)
         except validators.ValidationFailure:
             message = field.gettext('\'%s\' is not a valid URL.' % (field.data.strip()))
             raise ValidationError(message)
 
+        from .model.Watch import is_safe_url
+        if not is_safe_url(field.data):
+            raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX')
+
+
 class ValidateListRegex(object):
     """
     Validates that anything that looks like a regex passes as a regex
@@ -323,33 +370,51 @@ class ValidateCSSJSONXPATHInput(object):
                 except:
                     raise ValidationError("A system-error occurred when validating your jq expression")
 
-
 class quickWatchForm(Form):
+    from . import processors
+
     url = fields.URLField('URL', validators=[validateURL()])
-    tag = StringField('Group tag', [validators.Optional()])
+    tags = StringTagUUID('Group tag', [validators.Optional()])
     watch_submit_button = SubmitField('Watch', render_kw={"class": "pure-button pure-button-primary"})
+    processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
     edit_and_watch_submit_button = SubmitField('Edit > Watch', render_kw={"class": "pure-button pure-button-primary"})
 
 
 # Common to a single watch and the global settings
 class commonSettingsForm(Form):
-    notification_urls = StringListField('Notification URL list', validators=[validators.Optional(), ValidateAppRiseServers()])
-    notification_title = StringField('Notification title', validators=[validators.Optional(), ValidateTokensList()])
-    notification_body = TextAreaField('Notification body', validators=[validators.Optional(), ValidateTokensList()])
+
+    notification_urls = StringListField('Notification URL List', validators=[validators.Optional(), ValidateAppRiseServers()])
+    notification_title = StringField('Notification Title', default='ChangeDetection.io Notification - {{ watch_url }}', validators=[validators.Optional(), ValidateJinja2Template()])
+    notification_body = TextAreaField('Notification Body', default='{{ watch_url }} had a change.', validators=[validators.Optional(), ValidateJinja2Template()])
     notification_format = SelectField('Notification format', choices=valid_notification_formats.keys())
-    fetch_backend = RadioField(u'Fetch method', choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    fetch_backend = RadioField(u'Fetch Method', choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     extract_title_as_title = BooleanField('Extract <title> from document and use as watch title', default=False)
     webdriver_delay = IntegerField('Wait seconds before extracting text', validators=[validators.Optional(), validators.NumberRange(min=1,
                                                                                                                                     message="Should contain one or more seconds")])
+class importForm(Form):
+    from . import processors
+    processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
+    urls = TextAreaField('URLs')
+
+class SingleBrowserStep(Form):
+
+    operation = SelectField('Operation', [validators.Optional()], choices=browser_step_ui_config.keys())
+
+    # maybe better to set some <script>var..
+    selector = StringField('Selector', [validators.Optional()], render_kw={"placeholder": "CSS or xPath selector"})
+    optional_value = StringField('value', [validators.Optional()], render_kw={"placeholder": "Value"})
+#   @todo move to JS? ajax fetch new field?
+#    remove_button = SubmitField('-', render_kw={"type": "button", "class": "pure-button pure-button-primary", 'title': 'Remove'})
+#    add_button = SubmitField('+', render_kw={"type": "button", "class": "pure-button pure-button-primary", 'title': 'Add new step after'})
 
 class watchForm(commonSettingsForm):
 
     url = fields.URLField('URL', validators=[validateURL()])
-    tag = StringField('Group tag', [validators.Optional()], default='')
+    tags = StringTagUUID('Group tag', [validators.Optional()], default='')
 
     time_between_check = FormField(TimeBetweenCheckForm)
 
-    css_filter = StringField('CSS/JSON/XPATH Filter', [ValidateCSSJSONXPATHInput()], default='')
+    include_filters = StringListField('CSS/JSONPath/JQ/XPath Filters', [ValidateCSSJSONXPATHInput()], default='')
 
     subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
 
@@ -362,10 +427,19 @@ class watchForm(commonSettingsForm):
     body = TextAreaField('Request body', [validators.Optional()])
     method = SelectField('Request method', choices=valid_method, default=default_method)
     ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
-    check_unique_lines = BooleanField('Only trigger when new lines appear', default=False)
-    trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
-    text_should_not_be_present = StringListField('Block change-detection if text matches', [validators.Optional(), ValidateListRegex()])
+    check_unique_lines = BooleanField('Only trigger when unique lines appear', default=False)
 
+    filter_text_added = BooleanField('Added lines', default=True)
+    filter_text_replaced = BooleanField('Replaced/changed lines', default=True)
+    filter_text_removed = BooleanField('Removed lines', default=True)
+
+    # @todo this class could be moved to its own text_json_diff_watchForm and this goes to restock_diff_Watchform perhaps
+    in_stock_only = BooleanField('Only trigger when product goes BACK to in-stock', default=True)
+
+    trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
+    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
+        browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
+    text_should_not_be_present = StringListField('Block change-detection while text matches', [validators.Optional(), ValidateListRegex()])
     webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
 
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
@@ -375,6 +449,7 @@ class watchForm(commonSettingsForm):
         'Send a notification when the filter can no longer be found on the page', default=False)
 
     notification_muted = BooleanField('Notifications Muted / Off', default=False)
+    notification_screenshot = BooleanField('Attach screenshot to notification (where possible)', default=False)
 
     def validate(self, **kwargs):
         if not super().validate():
@@ -387,9 +462,25 @@ class watchForm(commonSettingsForm):
             self.body.errors.append('Body must be empty when Request Method is set to GET')
             result = False
 
+        # Attempt to validate jinja2 templates in the URL
+        from jinja2 import Environment
+        # Jinja2 available in URLs along with https://pypi.org/project/jinja2-time/
+        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
+        try:
+            ready_url = str(jinja2_env.from_string(self.url.data).render())
+        except Exception as e:
+            self.url.errors.append('Invalid template syntax')
+            result = False
         return result
 
 
+class SingleExtraProxy(Form):
+
+    # maybe better to set some <script>var..
+    proxy_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
+    proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "http://user:pass@...:3128", "size":50})
+    # @todo do the validation here instead
+
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
     time_between_check = FormField(TimeBetweenCheckForm)
@@ -397,21 +488,34 @@ class globalSettingsRequestForm(Form):
     jitter_seconds = IntegerField('Random jitter seconds ± check',
                                   render_kw={"style": "width: 5em;"},
                                   validators=[validators.NumberRange(min=0, message="Should contain zero or more seconds")])
+    extra_proxies = FieldList(FormField(SingleExtraProxy), min_entries=5)
+
+    def validate_extra_proxies(self, extra_validators=None):
+        for e in self.data['extra_proxies']:
+            if e.get('proxy_name') or e.get('proxy_url'):
+                if not e.get('proxy_name','').strip() or not e.get('proxy_url','').strip():
+                    self.extra_proxies.errors.append('Both a name, and a Proxy URL is required.')
+                    return False
+
 
 # datastore.data['settings']['application']..
 class globalSettingsApplicationForm(commonSettingsForm):
 
-    base_url = StringField('Base URL', validators=[validators.Optional()])
-    global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
-    global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
-    ignore_whitespace = BooleanField('Ignore whitespace')
-    removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
-    empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
-    render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
-    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
+    base_url = StringField('Base URL', validators=[validators.Optional()])
+    empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
+    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
+    global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
+    ignore_whitespace = BooleanField('Ignore whitespace')
     password = SaltyPasswordField()
-
+    pager_size = IntegerField('Pager size',
+                              render_kw={"style": "width: 5em;"},
+                              validators=[validators.NumberRange(min=0,
+                                                                 message="Should be atleast zero (disabled)")])
+    removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
+    render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
+    shared_diff_access = BooleanField('Allow access to view diff page when password is enabled', default=False, validators=[validators.Optional()])
     filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',
                                                                   render_kw={"style": "width: 5em;"},
                                                                   validators=[validators.NumberRange(min=0,
@@ -426,3 +530,8 @@ class globalSettingsForm(Form):
     requests = FormField(globalSettingsRequestForm)
     application = FormField(globalSettingsApplicationForm)
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
+
+
+class extractDataForm(Form):
+    extract_regex = StringField('RegEx to extract', validators=[validators.Length(min=1, message="Needs a RegEx")])
+    extract_submit_button = SubmitField('Extract as CSV', render_kw={"class": "pure-button pure-button-primary"})

changedetectionio/html_tools.py

@@ -7,26 +7,34 @@ from typing import List
 import json
 import re
 
-class FilterNotFoundInResponse(ValueError):
-    def __init__(self, msg):
-        ValueError.__init__(self, msg)
+# HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
+TEXT_FILTER_LIST_LINE_SUFFIX = "<br>"
+
+# 'price' , 'lowPrice', 'highPrice' are usually under here
+# all of those may or may not appear on different websites
+LD_JSON_PRODUCT_OFFER_SELECTOR = "json:$..offers"
 
 class JSONNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
-
-
+        
 # Given a CSS Rule, and a blob of HTML, return the blob of HTML that matches
-def css_filter(css_filter, html_content):
+def include_filters(include_filters, html_content, append_pretty_line_formatting=False):
     soup = BeautifulSoup(html_content, "html.parser")
     html_block = ""
-    r = soup.select(css_filter, separator="")
-    if len(html_content) > 0 and len(r) == 0:
-        raise FilterNotFoundInResponse(css_filter)
-    for item in r:
-        html_block += str(item)
+    r = soup.select(include_filters, separator="")
 
-    return html_block + "\n"
+    for element in r:
+        # When there's more than 1 match, then add the suffix to separate each line
+        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
+        # (This way each 'match' reliably has a new-line in the diff)
+        # Divs are converted to 4 whitespaces by inscriptis
+        if append_pretty_line_formatting and len(html_block) and not element.name in (['br', 'hr', 'div', 'p']):
+            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
+
+        html_block += str(element)
+
+    return html_block
 
 def subtractive_css_selector(css_selector, html_content):
     soup = BeautifulSoup(html_content, "html.parser")
@@ -42,25 +50,29 @@ def element_removal(selectors: List[str], html_content):
 
 
 # Return str Utf-8 of matched rules
-def xpath_filter(xpath_filter, html_content):
+def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False):
     from lxml import etree, html
 
     tree = html.fromstring(bytes(html_content, encoding='utf-8'))
     html_block = ""
 
     r = tree.xpath(xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'})
-    if len(html_content) > 0 and len(r) == 0:
-        raise FilterNotFoundInResponse(xpath_filter)
-
     #@note: //title/text() wont work where <title>CDATA..
 
     for element in r:
+        # When there's more than 1 match, then add the suffix to separate each line
+        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
+        # (This way each 'match' reliably has a new-line in the diff)
+        # Divs are converted to 4 whitespaces by inscriptis
+        if append_pretty_line_formatting and len(html_block) and (not hasattr( element, 'tag' ) or not element.tag in (['br', 'hr', 'div', 'p'])):
+            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
+
         if type(element) == etree._ElementStringResult:
-            html_block += str(element) + "<br/>"
+            html_block += str(element)
         elif type(element) == etree._ElementUnicodeResult:
-            html_block += str(element) + "<br/>"
+            html_block += str(element)
         else:
-            html_block += etree.tostring(element, pretty_print=True).decode('utf-8') + "<br/>"
+            html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
 
     return html_block
 
@@ -119,37 +131,54 @@ def _get_stripped_text_from_json_match(match):
 
     return stripped_text_from_html
 
-def extract_json_as_string(content, json_filter):
-
+# content - json
+# json_filter - ie json:$..price
+# ensure_is_ldjson_info_type - str "product", optional, "@type == product" (I dont know how to do that as a json selector)
+def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None):
     stripped_text_from_html = False
 
-    # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded <script type=ldjson>
+    # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded within HTML tags
     try:
         stripped_text_from_html = _parse_json(json.loads(content), json_filter)
     except json.JSONDecodeError:
 
         # Foreach <script json></script> blob.. just return the first that matches json_filter
+        # As a last resort, try to parse the whole <body>
         s = []
         soup = BeautifulSoup(content, 'html.parser')
-        bs_result = soup.findAll('script')
 
-        if not bs_result:
-            raise JSONNotFound("No parsable JSON found in this document")
+        if ensure_is_ldjson_info_type:
+            bs_result = soup.findAll('script', {"type": "application/ld+json"})
+        else:
+            bs_result = soup.findAll('script')
+        bs_result += soup.findAll('body')
 
+        bs_jsons = []
         for result in bs_result:
             # Skip empty tags, and things that dont even look like JSON
-            if not result.string or not '{' in result.string:
+            if not result.text or '{' not in result.text:
                 continue
-                
             try:
-                json_data = json.loads(result.string)
+                json_data = json.loads(result.text)
+                bs_jsons.append(json_data)
             except json.JSONDecodeError:
-                # Just skip it
+                # Skip objects which cannot be parsed
                 continue
-            else:
-                stripped_text_from_html = _parse_json(json_data, json_filter)
-                if stripped_text_from_html:
-                    break
+
+        if not bs_jsons:
+            raise JSONNotFound("No parsable JSON found in this document")
+        
+        for json_data in bs_jsons:
+            stripped_text_from_html = _parse_json(json_data, json_filter)
+            if ensure_is_ldjson_info_type:
+                # Could sometimes be list, string or something else random
+                if isinstance(json_data, dict):
+                    # If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
+                    # (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
+                    if json_data.get('@type', False) and json_data.get('@type','').lower() == ensure_is_ldjson_info_type.lower() and stripped_text_from_html:
+                        break
+            elif stripped_text_from_html:
+                break
 
     if not stripped_text_from_html:
         # Re 265 - Just return an empty string when filter not found
@@ -235,6 +264,18 @@ def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
 
     return text_content
 
+
+# Does LD+JSON exist with a @type=='product' and a .price set anywhere?
+def has_ldjson_product_info(content):
+    try:
+        pricing_data = extract_json_as_string(content=content, json_filter=LD_JSON_PRODUCT_OFFER_SELECTOR, ensure_is_ldjson_info_type="product")
+    except JSONNotFound as e:
+        # Totally fine
+        return False
+    x=bool(pricing_data)
+    return x
+
+
 def workarounds_for_obfuscations(content):
     """
     Some sites are using sneaky tactics to make prices and other information un-renderable by Inscriptis
@@ -249,3 +290,18 @@ def workarounds_for_obfuscations(content):
     content = re.sub('<!--\s+-->', '', content)
 
     return content
+
+
+def get_triggered_text(content, trigger_text):
+    triggered_text = []
+    result = strip_ignore_text(content=content,
+                               wordlist=trigger_text,
+                               mode="line numbers")
+
+    i = 1
+    for p in content.splitlines():
+        if i in result:
+            triggered_text.append(p)
+        i += 1
+
+    return triggered_text

changedetectionio/importer.py

@@ -29,6 +29,7 @@ class import_url_list(Importer):
             data,
             flash,
             datastore,
+            processor=None
             ):
 
         urls = data.split("\n")
@@ -51,8 +52,13 @@ class import_url_list(Importer):
 
             # Flask wtform validators wont work with basic auth, use validators package
             # Up to 5000 per batch so we dont flood the server
-            if len(url) and validators.url(url.replace('source:', '')) and good < 5000:
-                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False)
+            # @todo validators.url failed on local hostnames (such as referring to ourself when using browserless)
+            if len(url) and 'http' in url.lower() and good < 5000:
+                extras = None
+                if processor:
+                    extras = {'processor': processor}
+                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False, extras=extras)
+
                 if new_uuid:
                     # Straight into the queue.
                     self.new_uuids.append(new_uuid)
@@ -79,7 +85,8 @@ class import_distill_io_json(Importer):
         now = time.time()
         self.new_uuids=[]
 
-
+        # @todo Use JSONSchema like in the API to validate here.
+        
         try:
             data = json.loads(data.strip())
         except json.decoder.JSONDecodeError:
@@ -103,22 +110,19 @@ class import_distill_io_json(Importer):
                     pass
                 except IndexError:
                     pass
-
+                extras['include_filters'] = []
                 try:
-                    extras['css_filter'] = d_config['selections'][0]['frames'][0]['includes'][0]['expr']
                     if d_config['selections'][0]['frames'][0]['includes'][0]['type'] == 'xpath':
-                        extras['css_filter'] = 'xpath:' + extras['css_filter']
-
+                        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
 
-
-                if d.get('tags', False):
-                    extras['tag'] = ", ".join(d['tags'])
-
                 new_uuid = datastore.add_watch(url=d['uri'].strip(),
+                                               tag=",".join(d.get('tags', [])),
                                                extras=extras,
                                                write_to_disk_now=False)
 

changedetectionio/model/App.py

@@ -15,31 +15,35 @@ class model(dict):
                 'headers': {
                 },
                 'requests': {
-                    'timeout': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
-                    'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
+                    'extra_proxies': [], # Configurable extra proxies via the UI
                     'jitter_seconds': 0,
+                    'proxy': None, # Preferred proxy connection
+                    'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
+                    'timeout': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
                     'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "10")),  # Number of threads, lower is better for slow connections
-                    'proxy': None # Preferred proxy connection
                 },
                 'application': {
+                    # Custom notification content
                     'api_access_token_enabled': True,
-                    'password': False,
                     'base_url' : None,
-                    'extract_title_as_title': False,
                     'empty_pages_are_a_change': False,
+                    'extract_title_as_title': False,
                     'fetch_backend': getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
                     'filter_failure_notification_threshold_attempts': _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT,
                     'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
                     'global_subtractive_selectors': [],
                     'ignore_whitespace': True,
-                    'render_anchor_tag_content': False,
-                    'notification_urls': [], # Apprise URL list
-                    # Custom notification content
-                    'notification_title': default_notification_title,
                     'notification_body': default_notification_body,
                     'notification_format': default_notification_format,
+                    'notification_title': default_notification_title,
+                    'notification_urls': [], # Apprise URL list
+                    'pager_size': 50,
+                    'password': False,
+                    'render_anchor_tag_content': False,
                     'schema_version' : 0,
-                    'webdriver_delay': None  # Extra delay in seconds before extracting text
+                    'shared_diff_access': False,
+                    'webdriver_delay': None , # Extra delay in seconds before extracting text
+                    'tags': {} #@todo use Tag.model initialisers
                 }
             }
         }
@@ -47,3 +51,15 @@ class model(dict):
     def __init__(self, *arg, **kw):
         super(model, self).__init__(*arg, **kw)
         self.update(self.base_config)
+
+
+def parse_headers_from_text_file(filepath):
+    headers = {}
+    with open(filepath, 'r') as f:
+        for l in f.readlines():
+            l = l.strip()
+            if not l.startswith('#') and ':' in l:
+                (k, v) = l.split(':')
+                headers[k.strip()] = v.strip()
+
+    return headers

changedetectionio/model/Tag.py

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

changedetectionio/model/Watch.py

@@ -1,6 +1,13 @@
-import os
-import uuid as uuid_builder
 from distutils.util import strtobool
+import logging
+import os
+import re
+import time
+import uuid
+
+# Allowable protocols, protects against javascript: etc
+# file:// is further checked by ALLOW_FILE_URI
+SAFE_PROTOCOL_REGEX='^(http|https|ftp|file):'
 
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
 mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
@@ -9,58 +16,84 @@ from changedetectionio.notification import (
     default_notification_format_for_watch
 )
 
+base_config = {
+    'body': None,
+    'check_unique_lines': False,  # On change-detected, compare against all history if its something new
+    'check_count': 0,
+    'date_created': None,
+    'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
+    'extract_text': [],  # Extract text by regex after filters
+    'extract_title_as_title': False,
+    'fetch_backend': 'system', # plaintext, playwright etc
+    'processor': 'text_json_diff', # could be restock_diff or others from .processors
+    'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
+    'filter_text_added': True,
+    'filter_text_replaced': True,
+    'filter_text_removed': True,
+    'has_ldjson_price_data': None,
+    'track_ldjson_price_data': None,
+    'headers': {},  # Extra headers to send
+    'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+    'in_stock_only' : True, # Only trigger change on going to instock from out-of-stock
+    'include_filters': [],
+    'last_checked': 0,
+    'last_error': False,
+    'last_viewed': 0,  # history key value of the last viewed via the [diff] link
+    'method': 'GET',
+    # Custom notification content
+    'notification_body': None,
+    'notification_format': default_notification_format_for_watch,
+    'notification_muted': False,
+    'notification_title': None,
+    'notification_screenshot': False,  # Include the latest screenshot if available and supported by the apprise URL
+    'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
+    'paused': False,
+    'previous_md5': False,
+    'previous_md5_before_filters': False,  # Used for skipping changedetection entirely
+    'proxy': None,  # Preferred proxy connection
+    'subtractive_selectors': [],
+    'tag': '', # Old system of text name for a tag, to be removed
+    'tags': [], # list of UUIDs to App.Tags
+    'text_should_not_be_present': [],  # Text that should not present
+    # Re #110, so then if this is set to None, we know to use the default value instead
+    # Requires setting to None on submit if it's the same as the default
+    # Should be all None by default, so we use the system default in this case.
+    'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
+    'title': None,
+    'trigger_text': [],  # List of text or regex to wait for until a change is detected
+    'url': '',
+    'uuid': str(uuid.uuid4()),
+    'webdriver_delay': None,
+    'webdriver_js_execute_code': None,  # Run before change-detection
+}
+
+
+def is_safe_url(test_url):
+    # See https://github.com/dgtlmoon/changedetection.io/issues/1358
+
+    # Remove 'source:' prefix so we dont get 'source:javascript:' etc
+    # 'source:' is a valid way to tell us to return the source
+
+    r = re.compile(re.escape('source:'), re.IGNORECASE)
+    test_url = r.sub('', test_url)
+
+    pattern = re.compile(os.getenv('SAFE_PROTOCOL_REGEX', SAFE_PROTOCOL_REGEX), re.IGNORECASE)
+    if not pattern.match(test_url.strip()):
+        return False
+
+    return True
 
 class model(dict):
     __newest_history_key = None
-    __history_n=0
-    __base_config = {
-            'url': None,
-            'tag': None,
-            'last_checked': 0,
-            'paused': False,
-            'last_viewed': 0,  # history key value of the last viewed via the [diff] link
-            #'newest_history_key': 0,
-            'title': None,
-            'previous_md5': False,
-            'uuid': str(uuid_builder.uuid4()),
-            'headers': {},  # Extra headers to send
-            'body': None,
-            'method': 'GET',
-            #'history': {},  # Dict of timestamp and output stripped filename
-            'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
-            # Custom notification content
-            'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
-            'notification_title': None,
-            'notification_body': None,
-            'notification_format': default_notification_format_for_watch,
-            'notification_muted': False,
-            'css_filter': '',
-            'last_error': False,
-            'extract_text': [],  # Extract text by regex after filters
-            'subtractive_selectors': [],
-            'trigger_text': [],  # List of text or regex to wait for until a change is detected
-            'text_should_not_be_present': [], # Text that should not present
-            'fetch_backend': None,
-            'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
-            'consecutive_filter_failures': 0, # Every time the CSS/xPath filter cannot be located, reset when all is fine.
-            'extract_title_as_title': False,
-            'check_unique_lines': False, # On change-detected, compare against all history if its something new
-            'proxy': None, # Preferred proxy connection
-            # Re #110, so then if this is set to None, we know to use the default value instead
-            # Requires setting to None on submit if it's the same as the default
-            # Should be all None by default, so we use the system default in this case.
-            'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
-            'webdriver_delay': None,
-            'webdriver_js_execute_code': None, # Run before change-detection
-        }
+    __history_n = 0
     jitter_seconds = 0
 
     def __init__(self, *arg, **kw):
 
-        self.update(self.__base_config)
+        self.update(base_config)
         self.__datastore_path = kw['datastore_path']
 
-        self['uuid'] = str(uuid_builder.uuid4())
+        self['uuid'] = str(uuid.uuid4())
 
         del kw['datastore_path']
 
@@ -82,10 +115,54 @@ class model(dict):
         return False
 
     def ensure_data_dir_exists(self):
-        target_path = os.path.join(self.__datastore_path, self['uuid'])
-        if not os.path.isdir(target_path):
-            print ("> Creating data dir {}".format(target_path))
-            os.mkdir(target_path)
+        if not os.path.isdir(self.watch_data_dir):
+            print ("> Creating data dir {}".format(self.watch_data_dir))
+            os.mkdir(self.watch_data_dir)
+
+    @property
+    def link(self):
+
+        url = self.get('url', '')
+        if not is_safe_url(url):
+            return 'DISABLED'
+
+        ready_url = url
+        if '{%' in url or '{{' in url:
+            from jinja2 import Environment
+            # Jinja2 available in URLs along with https://pypi.org/project/jinja2-time/
+            jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
+            try:
+                ready_url = str(jinja2_env.from_string(url).render())
+            except Exception as e:
+                from flask import (
+                    flash, Markup, url_for
+                )
+                message = Markup('<a href="{}#general">The URL {} is invalid and cannot be used, click to edit</a>'.format(
+                    url_for('edit_page', uuid=self.get('uuid')), self.get('url', '')))
+                flash(message, 'error')
+                return ''
+
+        return ready_url
+
+    @property
+    def get_fetch_backend(self):
+        """
+        Like just using the `fetch_backend` key but there could be some logic
+        :return:
+        """
+        # Maybe also if is_image etc?
+        # This is because chrome/playwright wont render the PDF in the browser and we will just fetch it and use pdf2html to see the text.
+        if self.is_pdf:
+            return 'html_requests'
+
+        return self.get('fetch_backend')
+
+    @property
+    def is_pdf(self):
+        # content_type field is set in the future
+        # https://github.com/dgtlmoon/changedetection.io/issues/1392
+        # Not sure the best logic here
+        return self.get('url', '').lower().endswith('.pdf') or 'pdf' in self.get('content_type', '').lower()
 
     @property
     def label(self):
@@ -109,18 +186,39 @@ class model(dict):
 
     @property
     def history(self):
+        """History index is just a text file as a list
+            {watch-uuid}/history.txt
+
+            contains a list like
+
+            {epoch-time},{filename}\n
+
+            We read in this list as the history information
+
+        """
         tmp_history = {}
-        import logging
-        import time
 
         # Read the history file as a dict
-        fname = os.path.join(self.__datastore_path, self.get('uuid'), "history.txt")
+        fname = os.path.join(self.watch_data_dir, "history.txt")
         if os.path.isfile(fname):
             logging.debug("Reading history index " + str(time.time()))
             with open(fname, "r") as f:
                 for i in f.readlines():
                     if ',' in i:
                         k, v = i.strip().split(',', 2)
+
+                        # The index history could contain a relative path, so we need to make the fullpath
+                        # so that python can read it
+                        if not '/' in v and not '\'' in v:
+                            v = os.path.join(self.watch_data_dir, v)
+                        else:
+                            # It's possible that they moved the datadir on older versions
+                            # So the snapshot exists but is in a different path
+                            snapshot_fname = v.split('/')[-1]
+                            proposed_new_path = os.path.join(self.watch_data_dir, snapshot_fname)
+                            if not os.path.exists(v) and os.path.exists(proposed_new_path):
+                                v = proposed_new_path
+
                         tmp_history[k] = v
 
         if len(tmp_history):
@@ -132,7 +230,7 @@ class model(dict):
 
     @property
     def has_history(self):
-        fname = os.path.join(self.__datastore_path, self.get('uuid'), "history.txt")
+        fname = os.path.join(self.watch_data_dir, "history.txt")
         return os.path.isfile(fname)
 
     # Returns the newest key, but if theres only 1 record, then it's counted as not being new, so return 0.
@@ -148,28 +246,59 @@ class model(dict):
         bump = self.history
         return self.__newest_history_key
 
+    def get_history_snapshot(self, timestamp):
+        import brotli
+        filepath = self.history[timestamp]
+
+        # See if a brotli versions exists and switch to that
+        if not filepath.endswith('.br') and os.path.isfile(f"{filepath}.br"):
+            filepath = f"{filepath}.br"
+
+        # OR in the backup case that the .br does not exist, but the plain one does
+        if filepath.endswith('.br') and not os.path.isfile(filepath):
+            if os.path.isfile(filepath.replace('.br', '')):
+                filepath = filepath.replace('.br', '')
+
+        if filepath.endswith('.br'):
+            # Brotli doesnt have a fileheader to detect it, so we rely on filename
+            # https://www.rfc-editor.org/rfc/rfc7932
+            with open(filepath, 'rb') as f:
+                return(brotli.decompress(f.read()).decode('utf-8'))
+
+        with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+            return f.read()
+
     # Save some text file to the appropriate path and bump the history
     # result_obj from fetch_site_status.run()
-    def save_history_text(self, contents, timestamp):
-        import uuid
-        import logging
-
-        output_path = os.path.join(self.__datastore_path, self['uuid'])
+    def save_history_text(self, contents, timestamp, snapshot_id):
+        import brotli
 
         self.ensure_data_dir_exists()
-        snapshot_fname = os.path.join(output_path, str(uuid.uuid4()))
 
-        logging.debug("Saving history text {}".format(snapshot_fname))
+        # Small hack so that we sleep just enough to allow 1 second  between history snapshots
+        # this is because history.txt indexes/keys snapshots by epoch seconds and we dont want dupe keys
+        if self.__newest_history_key and int(timestamp) == int(self.__newest_history_key):
+            time.sleep(timestamp - self.__newest_history_key)
 
-        # in /diff/ and /preview/ we are going to assume for now that it's UTF-8 when reading
-        # most sites are utf-8 and some are even broken utf-8
-        with open(snapshot_fname, 'wb') as f:
-            f.write(contents)
-            f.close()
+        threshold = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
+        skip_brotli = strtobool(os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False'))
+
+        if not skip_brotli and len(contents) > threshold:
+            snapshot_fname = f"{snapshot_id}.txt.br"
+            dest = os.path.join(self.watch_data_dir, snapshot_fname)
+            if not os.path.exists(dest):
+                with open(dest, 'wb') as f:
+                    f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
+        else:
+            snapshot_fname = f"{snapshot_id}.txt"
+            dest = os.path.join(self.watch_data_dir, snapshot_fname)
+            if not os.path.exists(dest):
+                with open(dest, 'wb') as f:
+                    f.write(contents)
 
         # Append to index
         # @todo check last char was \n
-        index_fname = os.path.join(output_path, "history.txt")
+        index_fname = os.path.join(self.watch_data_dir, "history.txt")
         with open(index_fname, 'a') as f:
             f.write("{},{}\n".format(timestamp, snapshot_fname))
             f.close()
@@ -202,7 +331,8 @@ class model(dict):
         # Compare each lines (set) against each history text file (set) looking for something new..
         existing_history = set({})
         for k, v in self.history.items():
-            alist = set([line.decode('utf-8').strip().lower() for line in open(v, 'rb')])
+            content = self.get_history_snapshot(k)
+            alist = set([line.strip().lower() for line in content.splitlines()])
             existing_history = existing_history.union(alist)
 
         # Check that everything in local_lines(new stuff) already exists in existing_history - it should
@@ -210,14 +340,15 @@ class model(dict):
         return not local_lines.issubset(existing_history)
 
     def get_screenshot(self):
-        fname = os.path.join(self.__datastore_path, self['uuid'], "last-screenshot.png")
+        fname = os.path.join(self.watch_data_dir, "last-screenshot.png")
         if os.path.isfile(fname):
             return fname
 
-        return False
+        # False is not an option for AppRise, must be type None
+        return None
 
     def __get_file_ctime(self, filename):
-        fname = os.path.join(self.__datastore_path, self['uuid'], filename)
+        fname = os.path.join(self.watch_data_dir, filename)
         if os.path.isfile(fname):
             return int(os.path.getmtime(fname))
         return False
@@ -242,9 +373,14 @@ class model(dict):
     def snapshot_error_screenshot_ctime(self):
         return self.__get_file_ctime('last-error-screenshot.png')
 
+    @property
+    def watch_data_dir(self):
+        # The base dir of the watch data
+        return os.path.join(self.__datastore_path, self['uuid'])
+    
     def get_error_text(self):
         """Return the text saved from a previous request that resulted in a non-200 error"""
-        fname = os.path.join(self.__datastore_path, self['uuid'], "last-error.txt")
+        fname = os.path.join(self.watch_data_dir, "last-error.txt")
         if os.path.isfile(fname):
             with open(fname, 'r') as f:
                 return f.read()
@@ -252,7 +388,106 @@ class model(dict):
 
     def get_error_snapshot(self):
         """Return path to the screenshot that resulted in a non-200 error"""
-        fname = os.path.join(self.__datastore_path, self['uuid'], "last-error-screenshot.png")
+        fname = os.path.join(self.watch_data_dir, "last-error-screenshot.png")
         if os.path.isfile(fname):
             return fname
         return False
+
+
+    def pause(self):
+        self['paused'] = True
+
+    def unpause(self):
+        self['paused'] = False
+
+    def toggle_pause(self):
+        self['paused'] ^= True
+
+    def mute(self):
+        self['notification_muted'] = True
+
+    def unmute(self):
+        self['notification_muted'] = False
+
+    def toggle_mute(self):
+        self['notification_muted'] ^= True
+
+    def extract_regex_from_all_history(self, regex):
+        import csv
+        import re
+        import datetime
+        csv_output_filename = False
+        csv_writer = False
+        f = None
+
+        # self.history will be keyed with the full path
+        for k, fname in self.history.items():
+            if os.path.isfile(fname):
+                if True:
+                    contents = self.get_history_snapshot(k)
+                    res = re.findall(regex, contents, re.MULTILINE)
+                    if res:
+                        if not csv_writer:
+                            # A file on the disk can be transferred much faster via flask than a string reply
+                            csv_output_filename = 'report.csv'
+                            f = open(os.path.join(self.watch_data_dir, csv_output_filename), 'w')
+                            # @todo some headers in the future
+                            #fieldnames = ['Epoch seconds', 'Date']
+                            csv_writer = csv.writer(f,
+                                                    delimiter=',',
+                                                    quotechar='"',
+                                                    quoting=csv.QUOTE_MINIMAL,
+                                                    #fieldnames=fieldnames
+                                                    )
+                            csv_writer.writerow(['Epoch seconds', 'Date'])
+                            # csv_writer.writeheader()
+
+                        date_str = datetime.datetime.fromtimestamp(int(k)).strftime('%Y-%m-%d %H:%M:%S')
+                        for r in res:
+                            row = [k, date_str]
+                            if isinstance(r, str):
+                                row.append(r)
+                            else:
+                                row+=r
+                            csv_writer.writerow(row)
+
+        if f:
+            f.close()
+
+        return csv_output_filename
+
+
+    def has_special_diff_filter_options_set(self):
+
+        # All False - nothing would be done, so act like it's not processable
+        if not self.get('filter_text_added', True) and not self.get('filter_text_replaced', True) and not self.get('filter_text_removed', True):
+            return False
+
+        # Or one is set
+        if not self.get('filter_text_added', True) or not self.get('filter_text_replaced', True) or not self.get('filter_text_removed', True):
+            return True
+
+        # None is set
+        return False
+
+
+    def get_last_fetched_before_filters(self):
+        import brotli
+        filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
+
+        if not os.path.isfile(filepath):
+            # If a previous attempt doesnt yet exist, just snarf the previous snapshot instead
+            dates = list(self.history.keys())
+            if len(dates):
+                return self.get_history_snapshot(dates[-1])
+            else:
+                return ''
+
+        with open(filepath, 'rb') as f:
+            return(brotli.decompress(f.read()).decode('utf-8'))
+
+    def save_last_fetched_before_filters(self, contents):
+        import brotli
+        filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
+        with open(filepath, 'wb') as f:
+            f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))

changedetectionio/notification.py

@@ -1,23 +1,28 @@
 import apprise
+from jinja2 import Environment, BaseLoader
 from apprise import NotifyFormat
+import json
 
 valid_tokens = {
     'base_url': '',
-    'watch_url': '',
-    'watch_uuid': '',
-    'watch_title': '',
-    'watch_tag': '',
+    'current_snapshot': '',
     'diff': '',
+    'diff_added': '',
     'diff_full': '',
+    'diff_removed': '',
     'diff_url': '',
     'preview_url': '',
-    'current_snapshot': ''
+    'triggered_text': '',
+    'watch_tag': '',
+    'watch_title': '',
+    'watch_url': '',
+    'watch_uuid': '',
 }
 
 default_notification_format_for_watch = 'System default'
 default_notification_format = 'Text'
-default_notification_body = '{watch_url} had a change.\n---\n{diff}\n---\n'
-default_notification_title = 'ChangeDetection.io Notification - {watch_url}'
+default_notification_body = '{{watch_url}} had a change.\n---\n{{diff}}\n---\n'
+default_notification_title = 'ChangeDetection.io Notification - {{watch_url}}'
 
 valid_notification_formats = {
     'Text': NotifyFormat.TEXT,
@@ -27,25 +32,73 @@ valid_notification_formats = {
     default_notification_format_for_watch: default_notification_format_for_watch
 }
 
-def process_notification(n_object, datastore):
+# include the decorator
+from apprise.decorators import notify
 
-    # Get the notification body from datastore
-    n_body = n_object.get('notification_body', default_notification_body)
-    n_title = n_object.get('notification_title', default_notification_title)
-    n_format = valid_notification_formats.get(
-        n_object['notification_format'],
-        valid_notification_formats[default_notification_format],
-    )
+@notify(on="delete")
+@notify(on="deletes")
+@notify(on="get")
+@notify(on="gets")
+@notify(on="post")
+@notify(on="posts")
+@notify(on="put")
+@notify(on="puts")
+def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
+    import requests
+    url = kwargs['meta'].get('url')
+
+    if url.startswith('post'):
+        r = requests.post
+    elif url.startswith('get'):
+        r = requests.get
+    elif url.startswith('put'):
+        r = requests.put
+    elif url.startswith('delete'):
+        r = requests.delete
+
+    url = url.replace('post://', 'http://')
+    url = url.replace('posts://', 'https://')
+    url = url.replace('put://', 'http://')
+    url = url.replace('puts://', 'https://')
+    url = url.replace('get://', 'http://')
+    url = url.replace('gets://', 'https://')
+    url = url.replace('put://', 'http://')
+    url = url.replace('puts://', 'https://')
+    url = url.replace('delete://', 'http://')
+    url = url.replace('deletes://', 'https://')
+
+    # Try to auto-guess if it's JSON
+    headers = {}
+    try:
+        json.loads(body)
+        headers = {'Content-Type': 'application/json; charset=utf-8'}
+    except ValueError as e:
+        pass
+
+
+    r(url, headers=headers, data=body)
+
+
+def process_notification(n_object, datastore):
 
     # Insert variables into the notification content
     notification_parameters = create_notification_parameters(n_object, datastore)
 
-    for n_k in notification_parameters:
-        token = '{' + n_k + '}'
-        val = notification_parameters[n_k]
-        n_title = n_title.replace(token, val)
-        n_body = n_body.replace(token, val)
+    # Get the notification body from datastore
+    jinja2_env = Environment(loader=BaseLoader)
+    n_body = jinja2_env.from_string(n_object.get('notification_body', default_notification_body)).render(**notification_parameters)
+    n_title = jinja2_env.from_string(n_object.get('notification_title', default_notification_title)).render(**notification_parameters)
+    n_format = valid_notification_formats.get(
+        n_object.get('notification_format', default_notification_format),
+        valid_notification_formats[default_notification_format],
+    )
 
+    # If we arrived with 'System default' then look it up
+    if n_format == default_notification_format_for_watch and datastore.data['settings']['application'].get('notification_format') != default_notification_format_for_watch:
+        # Initially text or whatever
+        n_format = datastore.data['settings']['application'].get('notification_format', valid_notification_formats[default_notification_format])
+
+    
     # https://github.com/caronc/apprise/wiki/Development_LogCapture
     # Anything higher than or equal to WARNING (which covers things like Connection errors)
     # raise it as an exception
@@ -53,6 +106,7 @@ def process_notification(n_object, datastore):
     sent_objs=[]
     from .apprise_asset import asset
     for url in n_object['notification_urls']:
+        url = jinja2_env.from_string(url).render(**notification_parameters)
         apobj = apprise.Apprise(debug=True, asset=asset)
         url = url.strip()
         if len(url):
@@ -66,14 +120,19 @@ def process_notification(n_object, datastore):
 
                 # So if no avatar_url is specified, add one so it can be correctly calculated into the total payload
                 k = '?' if not '?' in url else '&'
-                if not 'avatar_url' in url and not url.startswith('mail'):
+                if not 'avatar_url' in url \
+                        and not url.startswith('mail') \
+                        and not url.startswith('post') \
+                        and not url.startswith('get') \
+                        and not url.startswith('delete') \
+                        and not url.startswith('put'):
                     url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
 
                 if url.startswith('tgram://'):
-                    # Telegram only supports a limit subset of HTML, remove the '<br/>' we place in.
+                    # Telegram only supports a limit subset of HTML, remove the '<br>' we place in.
                     # re https://github.com/dgtlmoon/changedetection.io/issues/555
                     # @todo re-use an existing library we have already imported to strip all non-allowed tags
-                    n_body = n_body.replace('<br/>', '\n')
+                    n_body = n_body.replace('<br>', '\n')
                     n_body = n_body.replace('</br>', '\n')
                     # real limit is 4096, but minus some for extra metadata
                     payload_max_size = 3600
@@ -92,16 +151,22 @@ def process_notification(n_object, datastore):
                     # Apprise will default to HTML, so we need to override it
                     # So that whats' generated in n_body is in line with what is going to be sent.
                     # https://github.com/caronc/apprise/issues/633#issuecomment-1191449321
-                    if not 'format=' in url and (n_format == 'text' or n_format == 'markdown'):
+                    if not 'format=' in url and (n_format == 'Text' or n_format == 'Markdown'):
                         prefix = '?' if not '?' in url else '&'
+                        # Apprise format is lowercase text https://github.com/caronc/apprise/issues/633
+                        n_format = n_format.tolower()
                         url = "{}{}format={}".format(url, prefix, n_format)
+                    # If n_format == HTML, then apprise email should default to text/html and we should be sending HTML only
 
                 apobj.add(url)
 
                 apobj.notify(
                     title=n_title,
                     body=n_body,
-                    body_format=n_format)
+                    body_format=n_format,
+                    # False is not an option for AppRise, must be type None
+                    attach=n_object.get('screenshot', None)
+                )
 
                 apobj.clear()
 
@@ -130,8 +195,13 @@ def create_notification_parameters(n_object, datastore):
     uuid = n_object['uuid'] if 'uuid' in n_object else ''
 
     if uuid != '':
-        watch_title = datastore.data['watching'][uuid]['title']
-        watch_tag = datastore.data['watching'][uuid]['tag']
+        watch_title = datastore.data['watching'][uuid].get('title', '')
+        tag_list = []
+        tags = datastore.get_all_tags_for_watch(uuid)
+        if tags:
+            for tag_uuid, tag in tags.items():
+                tag_list.append(tag.get('title'))
+        watch_tag = ', '.join(tag_list)
     else:
         watch_title = 'Change Detection'
         watch_tag = ''
@@ -141,7 +211,7 @@ def create_notification_parameters(n_object, datastore):
 
     watch_url = n_object['watch_url']
 
-    # Re #148 - Some people have just {base_url} in the body or title, but this may break some notification services
+    # Re #148 - Some people have just {{ base_url }} in the body or title, but this may break some notification services
     #           like 'Join', so it's always best to atleast set something obvious so that they are not broken.
     if base_url == '':
         base_url = "<base-url-env-var-not-set>"
@@ -156,15 +226,18 @@ def create_notification_parameters(n_object, datastore):
     tokens.update(
         {
             'base_url': base_url if base_url is not None else '',
+            'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else '',
+            'diff': n_object.get('diff', ''),  # Null default in the case we use a test
+            'diff_added': n_object.get('diff_added', ''),  # Null default in the case we use a test
+            'diff_full': n_object.get('diff_full', ''),  # Null default in the case we use a test
+            'diff_removed': n_object.get('diff_removed', ''),  # Null default in the case we use a test
+            'diff_url': diff_url,
+            'preview_url': preview_url,
+            'triggered_text': n_object.get('triggered_text', ''),
+            'watch_tag': watch_tag if watch_tag is not None else '',
+            'watch_title': watch_title if watch_title is not None else '',
             'watch_url': watch_url,
             'watch_uuid': uuid,
-            'watch_title': watch_title if watch_title is not None else '',
-            'watch_tag': watch_tag if watch_tag is not None else '',
-            'diff_url': diff_url,
-            'diff': n_object.get('diff', ''),  # Null default in the case we use a test
-            'diff_full': n_object.get('diff_full', ''),  # Null default in the case we use a test
-            'preview_url': preview_url,
-            'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else ''
         })
 
     return tokens

changedetectionio/processors/README.md

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

changedetectionio/processors/__init__.py

@@ -0,0 +1,24 @@
+from abc import abstractmethod
+import hashlib
+
+
+class difference_detection_processor():
+
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+    @abstractmethod
+    def run(self, uuid, skip_when_checksum_same=True, preferred_proxy=None):
+        update_obj = {'last_notification_error': False, 'last_error': False}
+        some_data = 'xxxxx'
+        update_obj["previous_md5"] = hashlib.md5(some_data.encode('utf-8')).hexdigest()
+        changed_detected = False
+        return changed_detected, update_obj, ''.encode('utf-8')
+
+
+def available_processors():
+    from . import restock_diff, text_json_diff
+    x=[('text_json_diff', text_json_diff.name), ('restock_diff', restock_diff.name)]
+    # @todo Make this smarter with introspection of sorts.
+    return x

changedetectionio/processors/restock_diff.py

@@ -0,0 +1,131 @@
+
+import hashlib
+import os
+import re
+import urllib3
+from . import difference_detection_processor
+from changedetectionio import content_fetcher
+from copy import deepcopy
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+name = 'Re-stock detection for single product pages'
+description = 'Detects if the product goes back to in-stock'
+
+class UnableToExtractRestockData(Exception):
+    def __init__(self, status_code):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        return
+
+class perform_site_check(difference_detection_processor):
+    screenshot = None
+    xpath_data = None
+
+    def __init__(self, *args, datastore, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.datastore = datastore
+
+    def run(self, uuid, skip_when_checksum_same=True):
+
+        # DeepCopy so we can be sure we don't accidently change anything by reference
+        watch = deepcopy(self.datastore.data['watching'].get(uuid))
+
+        if not watch:
+            raise Exception("Watch no longer exists.")
+
+        # Protect against file:// access
+        if re.search(r'^file', watch.get('url', ''), re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
+            raise Exception(
+                "file:// type access is denied for security reasons."
+            )
+
+        # Unset any existing notification error
+        update_obj = {'last_notification_error': False, 'last_error': False}
+
+        request_headers = watch.get('headers', [])
+        request_headers.update(self.datastore.get_all_base_headers())
+        request_headers.update(self.datastore.get_all_headers_in_textfile_for_watch(uuid=uuid))
+
+        # https://github.com/psf/requests/issues/4525
+        # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
+        # do this by accident.
+        if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
+            request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
+
+        timeout = self.datastore.data['settings']['requests'].get('timeout')
+
+        url = watch.link
+
+        request_body = self.datastore.data['watching'][uuid].get('body')
+        request_method = self.datastore.data['watching'][uuid].get('method')
+        ignore_status_codes = self.datastore.data['watching'][uuid].get('ignore_status_codes', False)
+
+        # Pluggable content fetcher
+        prefer_backend = watch.get_fetch_backend
+        if not prefer_backend or prefer_backend == 'system':
+            prefer_backend = self.datastore.data['settings']['application']['fetch_backend']
+
+        if hasattr(content_fetcher, prefer_backend):
+            klass = getattr(content_fetcher, prefer_backend)
+        else:
+            # If the klass doesnt exist, just use a default
+            klass = getattr(content_fetcher, "html_requests")
+
+        proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=uuid)
+        proxy_url = None
+        if proxy_id:
+            proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
+            print("UUID {} Using proxy {}".format(uuid, proxy_url))
+
+        fetcher = klass(proxy_override=proxy_url)
+
+        # Configurable per-watch or global extra delay before extracting text (for webDriver types)
+        system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
+        if watch['webdriver_delay'] is not None:
+            fetcher.render_extract_delay = watch.get('webdriver_delay')
+        elif system_webdriver_delay is not None:
+            fetcher.render_extract_delay = system_webdriver_delay
+
+        # Could be removed if requests/plaintext could also return some info?
+        if prefer_backend != 'html_webdriver':
+            raise Exception("Re-stock detection requires Chrome or compatible webdriver/playwright fetcher to work")
+
+        if watch.get('webdriver_js_execute_code') is not None and watch.get('webdriver_js_execute_code').strip():
+            fetcher.webdriver_js_execute_code = watch.get('webdriver_js_execute_code')
+
+        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'))
+        fetcher.quit()
+
+        self.screenshot = fetcher.screenshot
+        self.xpath_data = fetcher.xpath_data
+
+        # Track the content type
+        update_obj['content_type'] = fetcher.headers.get('Content-Type', '')
+        update_obj["last_check_status"] = fetcher.get_last_status_code()
+
+        # Main detection method
+        fetched_md5 = None
+        if fetcher.instock_data:
+            fetched_md5 = hashlib.md5(fetcher.instock_data.encode('utf-8')).hexdigest()
+            # 'Possibly in stock' comes from stock-not-in-stock.js when no string found above the fold.
+            update_obj["in_stock"] = True if fetcher.instock_data == 'Possibly in stock' else False
+        else:
+            raise UnableToExtractRestockData(status_code=fetcher.status_code)
+
+        # The main thing that all this at the moment comes down to :)
+        changed_detected = False
+
+        if watch.get('previous_md5') and watch.get('previous_md5') != fetched_md5:
+            # Yes if we only care about it going to instock, AND we are in stock
+            if watch.get('in_stock_only') and update_obj["in_stock"]:
+                changed_detected = True
+
+            if not watch.get('in_stock_only'):
+                # All cases
+                changed_detected = True
+
+        # Always record the new checksum
+        update_obj["previous_md5"] = fetched_md5
+
+        return changed_detected, update_obj, fetcher.instock_data.encode('utf-8')

changedetectionio/processors/text_json_diff.py

@@ -0,0 +1,420 @@
+# HTML to TEXT/JSON DIFFERENCE FETCHER
+
+import hashlib
+import json
+import logging
+import os
+import re
+import urllib3
+
+from changedetectionio import content_fetcher, html_tools
+from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
+from copy import deepcopy
+from . import difference_detection_processor
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+
+name =  'Webpage Text/HTML, JSON and PDF changes'
+description = 'Detects all text changes where possible'
+
+class FilterNotFoundInResponse(ValueError):
+    def __init__(self, msg):
+        ValueError.__init__(self, msg)
+
+class PDFToHTMLToolNotFound(ValueError):
+    def __init__(self, msg):
+        ValueError.__init__(self, msg)
+
+
+# Some common stuff here that can be moved to a base class
+# (set_proxy_from_list)
+class perform_site_check(difference_detection_processor):
+    screenshot = None
+    xpath_data = None
+
+    def __init__(self, *args, datastore, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.datastore = datastore
+
+    # Doesn't look like python supports forward slash auto enclosure in re.findall
+    # So convert it to inline flag "foobar(?i)" type configuration
+    def forward_slash_enclosed_regex_to_options(self, regex):
+        res = re.search(r'^/(.*?)/(\w+)$', regex, re.IGNORECASE)
+
+        if res:
+            regex = res.group(1)
+            regex += '(?{})'.format(res.group(2))
+        else:
+            regex += '(?{})'.format('i')
+
+        return regex
+
+    def run(self, uuid, skip_when_checksum_same=True, preferred_proxy=None):
+        changed_detected = False
+        screenshot = False  # as bytes
+        stripped_text_from_html = ""
+
+        # DeepCopy so we can be sure we don't accidently change anything by reference
+        watch = deepcopy(self.datastore.data['watching'].get(uuid))
+        if not watch:
+            raise Exception("Watch no longer exists.")
+
+        # Protect against file:// access
+        if re.search(r'^file', watch.get('url', ''), re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
+            raise Exception(
+                "file:// type access is denied for security reasons."
+            )
+
+        # Unset any existing notification error
+        update_obj = {'last_notification_error': False, 'last_error': False}
+
+        # Tweak the base config with the per-watch ones
+        request_headers = watch.get('headers', [])
+        request_headers.update(self.datastore.get_all_base_headers())
+        request_headers.update(self.datastore.get_all_headers_in_textfile_for_watch(uuid=uuid))
+
+        # https://github.com/psf/requests/issues/4525
+        # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
+        # do this by accident.
+        if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
+            request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
+
+        timeout = self.datastore.data['settings']['requests'].get('timeout')
+
+        url = watch.link
+
+        request_body = self.datastore.data['watching'][uuid].get('body')
+        request_method = self.datastore.data['watching'][uuid].get('method')
+        ignore_status_codes = self.datastore.data['watching'][uuid].get('ignore_status_codes', False)
+
+        # source: support
+        is_source = False
+        if url.startswith('source:'):
+            url = url.replace('source:', '')
+            is_source = True
+
+        # Pluggable content fetcher
+        prefer_backend = watch.get_fetch_backend
+        if not prefer_backend or prefer_backend == 'system':
+            prefer_backend = self.datastore.data['settings']['application']['fetch_backend']
+
+        if hasattr(content_fetcher, prefer_backend):
+            klass = getattr(content_fetcher, prefer_backend)
+        else:
+            # If the klass doesnt exist, just use a default
+            klass = getattr(content_fetcher, "html_requests")
+
+        if preferred_proxy:
+            proxy_id = preferred_proxy
+        else:
+            proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=uuid)
+
+        proxy_url = None
+        if proxy_id:
+            proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
+            print("UUID {} Using proxy {}".format(uuid, proxy_url))
+
+        fetcher = klass(proxy_override=proxy_url)
+
+        # Configurable per-watch or global extra delay before extracting text (for webDriver types)
+        system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
+        if watch['webdriver_delay'] is not None:
+            fetcher.render_extract_delay = watch.get('webdriver_delay')
+        elif system_webdriver_delay is not None:
+            fetcher.render_extract_delay = system_webdriver_delay
+
+        # Possible conflict
+        if prefer_backend == 'html_webdriver':
+            fetcher.browser_steps = watch.get('browser_steps', None)
+            fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, uuid)
+
+        if watch.get('webdriver_js_execute_code') is not None and watch.get('webdriver_js_execute_code').strip():
+            fetcher.webdriver_js_execute_code = watch.get('webdriver_js_execute_code')
+
+        # requests for PDF's, images etc should be passwd the is_binary flag
+        is_binary = watch.is_pdf
+
+        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'), is_binary=is_binary)
+        fetcher.quit()
+
+        self.screenshot = fetcher.screenshot
+        self.xpath_data = fetcher.xpath_data
+
+        # Track the content type
+        update_obj['content_type'] = fetcher.get_all_headers().get('content-type', '').lower()
+
+        # Watches added automatically in the queue manager will skip if its the same checksum as the previous run
+        # Saves a lot of CPU
+        update_obj['previous_md5_before_filters'] = hashlib.md5(fetcher.content.encode('utf-8')).hexdigest()
+        if skip_when_checksum_same:
+            if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
+                raise content_fetcher.checksumFromPreviousCheckWasTheSame()
+
+
+        # Fetching complete, now filters
+        # @todo move to class / maybe inside of fetcher abstract base?
+
+        # @note: I feel like the following should be in a more obvious chain system
+        #  - Check filter text
+        #  - Is the checksum different?
+        #  - Do we convert to JSON?
+        # https://stackoverflow.com/questions/41817578/basic-method-chaining ?
+        # return content().textfilter().jsonextract().checksumcompare() ?
+
+        is_json = 'application/json' in fetcher.get_all_headers().get('content-type', '').lower()
+        is_html = not is_json
+
+        # source: support, basically treat it as plaintext
+        if is_source:
+            is_html = False
+            is_json = False
+
+        if watch.is_pdf or 'application/pdf' in fetcher.get_all_headers().get('content-type', '').lower():
+            from shutil import which
+            tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
+            if not which(tool):
+                raise PDFToHTMLToolNotFound("Command-line `{}` tool was not found in system PATH, was it installed?".format(tool))
+
+            import subprocess
+            proc = subprocess.Popen(
+                [tool, '-stdout', '-', '-s', 'out.pdf', '-i'],
+                stdout=subprocess.PIPE,
+                stdin=subprocess.PIPE)
+            proc.stdin.write(fetcher.raw_content)
+            proc.stdin.close()
+            fetcher.content = proc.stdout.read().decode('utf-8')
+            proc.wait(timeout=60)
+
+            # Add a little metadata so we know if the file changes (like if an image changes, but the text is the same
+            # @todo may cause problems with non-UTF8?
+            metadata = "<p>Added by changedetection.io: Document checksum - {} Filesize - {} bytes</p>".format(
+                hashlib.md5(fetcher.raw_content).hexdigest().upper(),
+                len(fetcher.content))
+
+            fetcher.content = fetcher.content.replace('</body>', metadata + '</body>')
+
+        # Better would be if Watch.model could access the global data also
+        # and then use getattr https://docs.python.org/3/reference/datamodel.html#object.__getitem__
+        # https://realpython.com/inherit-python-dict/ instead of doing it procedurely
+        include_filters_from_tags = self.datastore.get_tag_overrides_for_watch(uuid=uuid, attr='include_filters')
+        include_filters_rule = [*watch.get('include_filters', []), *include_filters_from_tags]
+
+        subtractive_selectors = [*self.datastore.get_tag_overrides_for_watch(uuid=uuid, attr='subtractive_selectors'),
+                                 *watch.get("subtractive_selectors", []),
+                                 *self.datastore.data["settings"]["application"].get("global_subtractive_selectors", [])
+                                 ]
+
+        # Inject a virtual LD+JSON price tracker rule
+        if watch.get('track_ldjson_price_data', '') == PRICE_DATA_TRACK_ACCEPT:
+            include_filters_rule.append(html_tools.LD_JSON_PRODUCT_OFFER_SELECTOR)
+
+        has_filter_rule = len(include_filters_rule) and len(include_filters_rule[0].strip())
+        has_subtractive_selectors = len(subtractive_selectors) and len(subtractive_selectors[0].strip())
+
+        if is_json and not has_filter_rule:
+            include_filters_rule.append("json:$")
+            has_filter_rule = True
+
+        if is_json:
+            # Sort the JSON so we dont get false alerts when the content is just re-ordered
+            try:
+                fetcher.content = json.dumps(json.loads(fetcher.content), sort_keys=True)
+            except Exception as e:
+                # Might have just been a snippet, or otherwise bad JSON, continue
+                pass
+
+        if has_filter_rule:
+            json_filter_prefixes = ['json:', 'jq:']
+            for filter in include_filters_rule:
+                if any(prefix in filter for prefix in json_filter_prefixes):
+                    stripped_text_from_html += html_tools.extract_json_as_string(content=fetcher.content, json_filter=filter)
+                    is_html = False
+
+
+
+        if is_html or is_source:
+
+            # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
+            fetcher.content = html_tools.workarounds_for_obfuscations(fetcher.content)
+            html_content = fetcher.content
+
+            # If not JSON,  and if it's not text/plain..
+            if 'text/plain' in fetcher.get_all_headers().get('content-type', '').lower():
+                # Don't run get_text or xpath/css filters on plaintext
+                stripped_text_from_html = html_content
+            else:
+                # Does it have some ld+json price data? used for easier monitoring
+                update_obj['has_ldjson_price_data'] = html_tools.has_ldjson_product_info(fetcher.content)
+
+                # Then we assume HTML
+                if has_filter_rule:
+                    html_content = ""
+
+                    for filter_rule in include_filters_rule:
+                        # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
+                        if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
+                            html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
+                                                                    html_content=fetcher.content,
+                                                                    append_pretty_line_formatting=not is_source)
+                        else:
+                            # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
+                            html_content += html_tools.include_filters(include_filters=filter_rule,
+                                                                       html_content=fetcher.content,
+                                                                       append_pretty_line_formatting=not is_source)
+
+                    if not html_content.strip():
+                        raise FilterNotFoundInResponse(include_filters_rule)
+
+                if has_subtractive_selectors:
+                    html_content = html_tools.element_removal(subtractive_selectors, html_content)
+
+                if is_source:
+                    stripped_text_from_html = html_content
+                else:
+                    # extract text
+                    do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
+                    stripped_text_from_html = \
+                        html_tools.html_to_text(
+                            html_content,
+                            render_anchor_tag_content=do_anchor
+                        )
+
+        # Re #340 - return the content before the 'ignore text' was applied
+        text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
+
+
+        # @todo whitespace coming from missing rtrim()?
+        # stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
+        # Rewrite's the processing text based on only what diff result they want to see
+        if watch.has_special_diff_filter_options_set() and len(watch.history.keys()):
+            # Now the content comes from the diff-parser and not the returned HTTP traffic, so could be some differences
+            from .. import diff
+            # needs to not include (added) etc or it may get used twice
+            # Replace the processed text with the preferred result
+            rendered_diff = diff.render_diff(previous_version_file_contents=watch.get_last_fetched_before_filters(),
+                                                       newest_version_file_contents=stripped_text_from_html,
+                                                       include_equal=False,  # not the same lines
+                                                       include_added=watch.get('filter_text_added', True),
+                                                       include_removed=watch.get('filter_text_removed', True),
+                                                       include_replaced=watch.get('filter_text_replaced', True),
+                                                       line_feed_sep="\n",
+                                                       include_change_type_prefix=False)
+
+            watch.save_last_fetched_before_filters(text_content_before_ignored_filter)
+
+            if not rendered_diff and stripped_text_from_html:
+                # We had some content, but no differences were found
+                # Store our new file as the MD5 so it will trigger in the future
+                c = hashlib.md5(text_content_before_ignored_filter.translate(None, b'\r\n\t ')).hexdigest()
+                return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8')
+            else:
+                stripped_text_from_html = rendered_diff
+
+        # Treat pages with no renderable text content as a change? No by default
+        empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
+        if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
+            raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot)
+
+        # We rely on the actual text in the html output.. many sites have random script vars etc,
+        # in the future we'll implement other mechanisms.
+
+        update_obj["last_check_status"] = fetcher.get_last_status_code()
+
+        # If there's text to skip
+        # @todo we could abstract out the get_text() to handle this cleaner
+        text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
+        if len(text_to_ignore):
+            stripped_text_from_html = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
+        else:
+            stripped_text_from_html = stripped_text_from_html.encode('utf8')
+
+        # 615 Extract text by regex
+        extract_text = watch.get('extract_text', [])
+        if len(extract_text) > 0:
+            regex_matched_output = []
+            for s_re in extract_text:
+                # incase they specified something in '/.../x'
+                regex = self.forward_slash_enclosed_regex_to_options(s_re)
+                result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
+
+                for l in result:
+                    if type(l) is tuple:
+                        # @todo - some formatter option default (between groups)
+                        regex_matched_output += list(l) + [b'\n']
+                    else:
+                        # @todo - some formatter option default (between each ungrouped result)
+                        regex_matched_output += [l] + [b'\n']
+
+            # Now we will only show what the regex matched
+            stripped_text_from_html = b''
+            text_content_before_ignored_filter = b''
+            if regex_matched_output:
+                # @todo some formatter for presentation?
+                stripped_text_from_html = b''.join(regex_matched_output)
+                text_content_before_ignored_filter = stripped_text_from_html
+
+        # Re #133 - if we should strip whitespaces from triggering the change detected comparison
+        if self.datastore.data['settings']['application'].get('ignore_whitespace', False):
+            fetched_md5 = hashlib.md5(stripped_text_from_html.translate(None, b'\r\n\t ')).hexdigest()
+        else:
+            fetched_md5 = hashlib.md5(stripped_text_from_html).hexdigest()
+
+        ############ Blocking rules, after checksum #################
+        blocked = False
+
+        trigger_text = watch.get('trigger_text', [])
+        if len(trigger_text):
+            # Assume blocked
+            blocked = True
+            # Filter and trigger works the same, so reuse it
+            # It should return the line numbers that match
+            # Unblock flow if the trigger was found (some text remained after stripped what didnt match)
+            result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
+                                                  wordlist=trigger_text,
+                                                  mode="line numbers")
+            # Unblock if the trigger was found
+            if result:
+                blocked = False
+
+        text_should_not_be_present = watch.get('text_should_not_be_present', [])
+        if len(text_should_not_be_present):
+            # If anything matched, then we should block a change from happening
+            result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
+                                                  wordlist=text_should_not_be_present,
+                                                  mode="line numbers")
+            if result:
+                blocked = True
+
+        # The main thing that all this at the moment comes down to :)
+        if watch.get('previous_md5') != fetched_md5:
+            changed_detected = True
+
+        # Looks like something changed, but did it match all the rules?
+        if blocked:
+            changed_detected = False
+
+        # Extract title as title
+        if is_html:
+            if self.datastore.data['settings']['application'].get('extract_title_as_title') or watch['extract_title_as_title']:
+                if not watch['title'] or not len(watch['title']):
+                    update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
+
+        if changed_detected:
+            if watch.get('check_unique_lines', False):
+                has_unique_lines = watch.lines_contain_something_unique_compared_to_history(lines=stripped_text_from_html.splitlines())
+                # One or more lines? unsure?
+                if not has_unique_lines:
+                    logging.debug("check_unique_lines: UUID {} didnt have anything new setting change_detected=False".format(uuid))
+                    changed_detected = False
+                else:
+                    logging.debug("check_unique_lines: UUID {} had unique content".format(uuid))
+
+        # Always record the new checksum
+        update_obj["previous_md5"] = fetched_md5
+
+        # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
+        if not watch.get('previous_md5'):
+            watch['previous_md5'] = fetched_md5
+
+        return changed_detected, update_obj, text_content_before_ignored_filter

changedetectionio/queuedWatchMetaData.py

@@ -0,0 +1,10 @@
+from dataclasses import dataclass, field
+from typing import Any
+
+# So that we can queue some metadata in `item`
+# https://docs.python.org/3/library/queue.html#queue.PriorityQueue
+#
+@dataclass(order=True)
+class PrioritizedItem:
+    priority: int
+    item: Any=field(compare=False)

changedetectionio/res/puppeteer_fetch.js

@@ -0,0 +1,183 @@
+module.exports = async ({page, context}) => {
+
+    var {
+        url,
+        execute_js,
+        user_agent,
+        extra_wait_ms,
+        req_headers,
+        include_filters,
+        xpath_element_js,
+        screenshot_quality,
+        proxy_username,
+        proxy_password,
+        disk_cache_dir,
+        no_cache_list,
+        block_url_list,
+    } = context;
+
+    await page.setBypassCSP(true)
+    await page.setExtraHTTPHeaders(req_headers);
+    await page.setUserAgent(user_agent);
+    // https://ourcodeworld.com/articles/read/1106/how-to-solve-puppeteer-timeouterror-navigation-timeout-of-30000-ms-exceeded
+
+    await page.setDefaultNavigationTimeout(0);
+
+    if (proxy_username) {
+        await page.authenticate({
+            username: proxy_username,
+            password: proxy_password
+        });
+    }
+
+    await page.setViewport({
+        width: 1024,
+        height: 768,
+        deviceScaleFactor: 1,
+    });
+
+    await page.setRequestInterception(true);
+    if (disk_cache_dir) {
+        console.log(">>>>>>>>>>>>>>> LOCAL DISK CACHE ENABLED <<<<<<<<<<<<<<<<<<<<<");
+    }
+    const fs = require('fs');
+    const crypto = require('crypto');
+
+    function file_is_expired(file_path) {
+        if (!fs.existsSync(file_path)) {
+            return true;
+        }
+        var stats = fs.statSync(file_path);
+        const now_date = new Date();
+        const expire_seconds = 300;
+        if ((now_date / 1000) - (stats.mtime.getTime() / 1000) > expire_seconds) {
+            console.log("CACHE EXPIRED: " + file_path);
+            return true;
+        }
+        return false;
+
+    }
+
+    page.on('request', async (request) => {
+        // General blocking of requests that waste traffic
+        if (block_url_list.some(substring => request.url().toLowerCase().includes(substring))) return request.abort();
+
+        if (disk_cache_dir) {
+            const url = request.url();
+            const key = crypto.createHash('md5').update(url).digest("hex");
+            const dir_path = disk_cache_dir + key.slice(0, 1) + '/' + key.slice(1, 2) + '/' + key.slice(2, 3) + '/';
+
+            // https://stackoverflow.com/questions/4482686/check-synchronously-if-file-directory-exists-in-node-js
+
+            if (fs.existsSync(dir_path + key)) {
+                console.log("* CACHE HIT , using - " + dir_path + key + " - " + url);
+                const cached_data = fs.readFileSync(dir_path + key);
+                // @todo headers can come from dir_path+key+".meta" json file
+                request.respond({
+                    status: 200,
+                    //contentType: 'text/html', //@todo
+                    body: cached_data
+                });
+                return;
+            }
+        }
+        request.continue();
+    });
+
+
+    if (disk_cache_dir) {
+        page.on('response', async (response) => {
+            const url = response.url();
+            // Basic filtering for sane responses
+            if (response.request().method() != 'GET' || response.request().resourceType() == 'xhr' || response.request().resourceType() == 'document' || response.status() != 200) {
+                console.log("Skipping (not useful) - Status:" + response.status() + " Method:" + response.request().method() + " ResourceType:" + response.request().resourceType() + " " + url);
+                return;
+            }
+            if (no_cache_list.some(substring => url.toLowerCase().includes(substring))) {
+                console.log("Skipping (no_cache_list) - " + url);
+                return;
+            }
+            if (url.toLowerCase().includes('data:')) {
+                console.log("Skipping (embedded-data) - " + url);
+                return;
+            }
+            response.buffer().then(buffer => {
+                if (buffer.length > 100) {
+                    console.log("Cache - Saving " + response.request().method() + " - " + url + " - " + response.request().resourceType());
+
+                    const key = crypto.createHash('md5').update(url).digest("hex");
+                    const dir_path = disk_cache_dir + key.slice(0, 1) + '/' + key.slice(1, 2) + '/' + key.slice(2, 3) + '/';
+
+                    if (!fs.existsSync(dir_path)) {
+                        fs.mkdirSync(dir_path, {recursive: true})
+                    }
+
+                    if (fs.existsSync(dir_path + key)) {
+                        if (file_is_expired(dir_path + key)) {
+                            fs.writeFileSync(dir_path + key, buffer);
+                        }
+                    } else {
+                        fs.writeFileSync(dir_path + key, buffer);
+                    }
+                }
+            });
+        });
+    }
+
+    const r = await page.goto(url, {
+        waitUntil: 'load'
+    });
+
+    await page.waitForTimeout(1000);
+    await page.waitForTimeout(extra_wait_ms);
+
+    if (execute_js) {
+        await page.evaluate(execute_js);
+        await page.waitForTimeout(200);
+    }
+
+    var xpath_data;
+    var instock_data;
+    try {
+        // Not sure the best way here, in the future this should be a new package added to npm then run in browserless
+        // (Once the old playwright is removed)
+        xpath_data = await page.evaluate((include_filters) => {%xpath_scrape_code%}, include_filters);
+        instock_data = await page.evaluate(() => {%instock_scrape_code%});
+    } catch (e) {
+        console.log(e);
+    }
+
+    // Protocol error (Page.captureScreenshot): Cannot take screenshot with 0 width can come from a proxy auth failure
+    // Wrap it here (for now)
+
+    var b64s = false;
+    try {
+        b64s = await page.screenshot({encoding: "base64", fullPage: true, quality: screenshot_quality, type: 'jpeg'});
+    } catch (e) {
+        console.log(e);
+    }
+
+    // May fail on very large pages with 'WARNING: tile memory limits exceeded, some content may not draw'
+    if (!b64s) {
+        // @todo after text extract, we can place some overlay text with red background to say 'croppped'
+        console.error('ERROR: content-fetcher page was maybe too large for a screenshot, reverting to viewport only screenshot');
+        try {
+            b64s = await page.screenshot({encoding: "base64", quality: screenshot_quality, type: 'jpeg'});
+        } catch (e) {
+            console.log(e);
+        }
+    }
+
+    var html = await page.content();
+    return {
+        data: {
+            'content': html,
+            'headers': r.headers(),
+            'instock_data': instock_data,
+            'screenshot': b64s,
+            'status_code': r.status(),
+            'xpath_data': xpath_data
+        },
+        type: 'application/json',
+    };
+};

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

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

changedetectionio/res/xpath_element_scraper.js

@@ -0,0 +1,221 @@
+// Copyright (C) 2021 Leigh Morresi (dgtlmoon@gmail.com)
+// All rights reserved.
+
+// @file Scrape the page looking for elements of concern (%ELEMENTS%)
+// http://matatk.agrip.org.uk/tests/position-and-width/
+// https://stackoverflow.com/questions/26813480/when-is-element-getboundingclientrect-guaranteed-to-be-updated-accurate
+//
+// Some pages like https://www.londonstockexchange.com/stock/NCCL/ncondezi-energy-limited/analysis
+// will automatically force a scroll somewhere, so include the position offset
+// Lets hope the position doesnt change while we iterate the bbox's, but this is better than nothing
+var scroll_y = 0;
+try {
+    scroll_y = +document.documentElement.scrollTop || document.body.scrollTop
+} catch (e) {
+    console.log(e);
+}
+
+
+
+// Include the getXpath script directly, easier than fetching
+function getxpath(e) {
+        var n = e;
+        if (n && n.id) return '//*[@id="' + n.id + '"]';
+        for (var o = []; n && Node.ELEMENT_NODE === n.nodeType;) {
+            for (var i = 0, r = !1, d = n.previousSibling; d;) d.nodeType !== Node.DOCUMENT_TYPE_NODE && d.nodeName === n.nodeName && i++, d = d.previousSibling;
+            for (d = n.nextSibling; d;) {
+                if (d.nodeName === n.nodeName) {
+                    r = !0;
+                    break
+                }
+                d = d.nextSibling
+            }
+            o.push((n.prefix ? n.prefix + ":" : "") + n.localName + (i || r ? "[" + (i + 1) + "]" : "")), n = n.parentNode
+        }
+        return o.length ? "/" + o.reverse().join("/") : ""
+    }
+
+const findUpTag = (el) => {
+    let r = el
+    chained_css = [];
+    depth = 0;
+
+    //  Strategy 1: If it's an input, with name, and there's only one, prefer that
+    if (el.name !== undefined && el.name.length) {
+        var proposed = el.tagName + "[name=" + el.name + "]";
+        var proposed_element = window.document.querySelectorAll(proposed);
+        if (proposed_element.length) {
+            if (proposed_element.length === 1) {
+                return proposed;
+            } else {
+                // Some sites change ID but name= stays the same, we can hit it if we know the index
+                // Find all the elements that match and work out the input[n]
+                var n = Array.from(proposed_element).indexOf(el);
+                // Return a Playwright selector for nthinput[name=zipcode]
+                return proposed + " >> nth=" + n;
+            }
+        }
+    }
+
+    // Strategy 2: Keep going up until we hit an ID tag, imagine it's like  #list-widget div h4
+    while (r.parentNode) {
+        if (depth == 5) {
+            break;
+        }
+        if ('' !== r.id) {
+            chained_css.unshift("#" + CSS.escape(r.id));
+            final_selector = chained_css.join(' > ');
+            // Be sure theres only one, some sites have multiples of the same ID tag :-(
+            if (window.document.querySelectorAll(final_selector).length == 1) {
+                return final_selector;
+            }
+            return null;
+        } else {
+            chained_css.unshift(r.tagName.toLowerCase());
+        }
+        r = r.parentNode;
+        depth += 1;
+    }
+    return null;
+}
+
+
+// @todo - if it's SVG or IMG, go into image diff mode
+// %ELEMENTS% replaced at injection time because different interfaces use it with different settings
+var elements = window.document.querySelectorAll("%ELEMENTS%");
+var size_pos = [];
+// after page fetch, inject this JS
+// build a map of all elements and their positions (maybe that only include text?)
+var bbox;
+for (var i = 0; i < elements.length; i++) {
+    bbox = elements[i].getBoundingClientRect();
+
+    // Exclude items that are not interactable or visible
+    if(elements[i].style.opacity === "0") {
+        continue
+    }
+    if(elements[i].style.display === "none" || elements[i].style.pointerEvents === "none" ) {
+        continue
+    }
+
+    // Skip really small ones, and where width or height ==0
+    if (bbox['width'] * bbox['height'] < 100) {
+        continue;
+    }
+
+    // Don't include elements that are offset from canvas
+    if (bbox['top']+scroll_y < 0 || bbox['left'] < 0) {
+        continue;
+    }
+
+    // @todo the getXpath kind of sucks, it doesnt know when there is for example just one ID sometimes
+    // it should not traverse when we know we can anchor off just an ID one level up etc..
+    // maybe, get current class or id, keep traversing up looking for only class or id until there is just one match
+
+    // 1st primitive - if it has class, try joining it all and select, if theres only one.. well thats us.
+    xpath_result = false;
+
+    try {
+        var d = findUpTag(elements[i]);
+        if (d) {
+            xpath_result = d;
+        }
+    } catch (e) {
+        console.log(e);
+    }
+
+    // You could swap it and default to getXpath and then try the smarter one
+    // default back to the less intelligent one
+    if (!xpath_result) {
+        try {
+            // I've seen on FB and eBay that this doesnt work
+            // ReferenceError: getXPath is not defined at eval (eval at evaluate (:152:29), <anonymous>:67:20) at UtilityScript.evaluate (<anonymous>:159:18) at UtilityScript.<anonymous> (<anonymous>:1:44)
+            xpath_result = getxpath(elements[i]);
+        } catch (e) {
+            console.log(e);
+            continue;
+        }
+    }
+
+    if (window.getComputedStyle(elements[i]).visibility === "hidden") {
+        continue;
+    }
+
+    // @todo Possible to ONLY list where it's clickable to save JSON xfer size
+    size_pos.push({
+        xpath: xpath_result,
+        width: Math.round(bbox['width']),
+        height: Math.round(bbox['height']),
+        left: Math.floor(bbox['left']),
+        top: Math.floor(bbox['top'])+scroll_y,
+        tagName: (elements[i].tagName) ? elements[i].tagName.toLowerCase() : '',
+        tagtype: (elements[i].tagName == 'INPUT' && elements[i].type) ? elements[i].type.toLowerCase() : '',
+        isClickable: (elements[i].onclick) || window.getComputedStyle(elements[i]).cursor == "pointer"
+    });
+
+}
+
+// Inject the current one set in the include_filters, which may be a CSS rule
+// used for displaying the current one in VisualSelector, where its not one we generated.
+if (include_filters.length) {
+    // Foreach filter, go and find it on the page and add it to the results so we can visualise it again
+    for (const f of include_filters) {
+        bbox = false;
+        q = false;
+
+        if (!f.length) {
+            console.log("xpath_element_scraper: Empty filter, skipping");
+            continue;
+        }
+
+        try {
+            // is it xpath?
+            if (f.startsWith('/') || f.startsWith('xpath:')) {
+                q = document.evaluate(f.replace('xpath:', ''), document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
+            } else {
+                q = document.querySelector(f);
+            }
+        } catch (e) {
+            // Maybe catch DOMException and alert?
+            console.log("xpath_element_scraper: Exception selecting element from filter "+f);
+            console.log(e);
+        }
+
+        if (q) {
+            // #1231 - IN the case XPath attribute filter is applied, we will have to traverse up and find the element.
+            if (q.hasOwnProperty('getBoundingClientRect')) {
+                bbox = q.getBoundingClientRect();
+                console.log("xpath_element_scraper: Got filter element, scroll from top was " + scroll_y)
+            } else {
+                try {
+                    // Try and see we can find its ownerElement
+                    bbox = q.ownerElement.getBoundingClientRect();
+                    console.log("xpath_element_scraper: Got filter by ownerElement element, scroll from top was " + scroll_y)
+                } catch (e) {
+                    console.log("xpath_element_scraper: error looking up ownerElement")
+                }
+            }
+        }
+        
+        if(!q) {
+            console.log("xpath_element_scraper: filter element " + f + " was not found");
+        }
+
+        if (bbox && bbox['width'] > 0 && bbox['height'] > 0) {
+            size_pos.push({
+                xpath: f,
+                width: parseInt(bbox['width']),
+                height: parseInt(bbox['height']),
+                left: parseInt(bbox['left']),
+                top: parseInt(bbox['top'])+scroll_y
+            });
+        }
+    }
+}
+
+// Sort the elements so we find the smallest one first, in other words, we find the smallest one matching in that area
+// so that we dont select the wrapping element by mistake and be unable to select what we want
+size_pos.sort((a, b) => (a.width*a.height > b.width*b.height) ? 1 : -1)
+
+// Window.width required for proper scaling in the frontend
+return {'size_pos': size_pos, 'browser_width': window.innerWidth};

changedetectionio/run_all_tests.sh

@@ -1,106 +0,0 @@
-#!/bin/bash
-
-
-# live_server will throw errors even with live_server_scope=function if I have the live_server setup in different functions
-# and I like to restart the server for each test (and have the test cleanup after each test)
-# merge request welcome :)
-
-
-# exit when any command fails
-set -e
-
-SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
-
-find tests/test_*py -type f|while read test_name
-do
-  echo "TEST RUNNING $test_name"
-  pytest $test_name
-done
-
-echo "RUNNING WITH BASE_URL SET"
-
-# Now re-run some tests with BASE_URL enabled
-# Re #65 - Ability to include a link back to the installation, in the notification.
-export BASE_URL="https://really-unique-domain.io"
-pytest tests/test_notification.py
-
-
-## JQ + JSON: filter test
-# jq is not available on windows and we should just test it when the package is installed
-# this will re-test with jq support
-pip3 install jq~=1.3
-pytest tests/test_jsonpath_jq_selector.py
-
-
-# Now for the selenium and playwright/browserless fetchers
-# Note - this is not UI functional tests - just checking that each one can fetch the content
-
-echo "TESTING WEBDRIVER FETCH > SELENIUM/WEBDRIVER..."
-docker run -d --name $$-test_selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome-debug:3.141.59
-# takes a while to spin up
-sleep 5
-export WEBDRIVER_URL=http://localhost:4444/wd/hub
-pytest tests/fetchers/test_content.py
-pytest tests/test_errorhandling.py
-unset WEBDRIVER_URL
-docker kill $$-test_selenium
-
-echo "TESTING WEBDRIVER FETCH > PLAYWRIGHT/BROWSERLESS..."
-# Not all platforms support playwright (not ARM/rPI), so it's not packaged in requirements.txt
-PLAYWRIGHT_VERSION=$(grep -i -E "RUN pip install.+" "$SCRIPT_DIR/../Dockerfile" | grep --only-matching -i -E "playwright[=><~+]+[0-9\.]+")
-echo "using $PLAYWRIGHT_VERSION"
-pip3 install "$PLAYWRIGHT_VERSION"
-docker run -d --name $$-test_browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
-# takes a while to spin up
-sleep 5
-export PLAYWRIGHT_DRIVER_URL=ws://127.0.0.1:3000
-pytest tests/fetchers/test_content.py
-pytest tests/test_errorhandling.py
-pytest tests/visualselector/test_fetch_data.py
-
-unset PLAYWRIGHT_DRIVER_URL
-docker kill $$-test_browserless
-
-# Test proxy list handling, starting two squids on different ports
-# Each squid adds a different header to the response, which is the main thing we test for.
-docker run -d --name $$-squid-one --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf -p 3128:3128 ubuntu/squid:4.13-21.10_edge
-docker run -d --name $$-squid-two --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf -p 3129:3128 ubuntu/squid:4.13-21.10_edge
-
-
-# So, basic HTTP as env var test
-export HTTP_PROXY=http://localhost:3128
-export HTTPS_PROXY=http://localhost:3128
-pytest tests/proxy_list/test_proxy.py
-docker logs $$-squid-one 2>/dev/null|grep one.changedetection.io
-if [ $? -ne 0 ]
-then
-  echo "Did not see a request to one.changedetection.io in the squid logs (while checking env vars HTTP_PROXY/HTTPS_PROXY)"
-fi
-unset HTTP_PROXY
-unset HTTPS_PROXY
-
-
-# 2nd test actually choose the preferred proxy from proxies.json
-cp tests/proxy_list/proxies.json-example ./test-datastore/proxies.json
-# Makes a watch use a preferred proxy
-pytest tests/proxy_list/test_multiple_proxy.py
-
-# Should be a request in the default "first" squid
-docker logs $$-squid-one 2>/dev/null|grep chosen.changedetection.io
-if [ $? -ne 0 ]
-then
-  echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy)"
-fi
-
-# And one in the 'second' squid (user selects this as preferred)
-docker logs $$-squid-two 2>/dev/null|grep chosen.changedetection.io
-if [ $? -ne 0 ]
-then
-  echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy)"
-fi
-
-# @todo - test system override proxy selection and watch defaults, setup a 3rd squid?
-docker kill $$-squid-one
-docker kill $$-squid-two
-
-

changedetectionio/run_basic_tests.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+
+
+# live_server will throw errors even with live_server_scope=function if I have the live_server setup in different functions
+# and I like to restart the server for each test (and have the test cleanup after each test)
+# merge request welcome :)
+
+
+# exit when any command fails
+set -e
+
+SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+
+find tests/test_*py -type f|while read test_name
+do
+  echo "TEST RUNNING $test_name"
+  pytest $test_name
+done
+
+echo "RUNNING WITH BASE_URL SET"
+
+# Now re-run some tests with BASE_URL enabled
+# Re #65 - Ability to include a link back to the installation, in the notification.
+export BASE_URL="https://really-unique-domain.io"
+pytest tests/test_notification.py
+
+
+# Re-run with HIDE_REFERER set - could affect login
+export HIDE_REFERER=True
+pytest tests/test_access_control.py
+
+# Re-run a few tests that will trigger brotli based storage
+export SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD=5
+pytest tests/test_access_control.py
+pytest tests/test_notification.py
+pytest tests/test_backend.py
+pytest tests/test_rss.py
+pytest tests/test_unique_lines.py

changedetectionio/run_proxy_tests.sh

@@ -0,0 +1,61 @@
+#!/bin/bash
+
+# exit when any command fails
+set -e
+
+# Test proxy list handling, starting two squids on different ports
+# Each squid adds a different header to the response, which is the main thing we test for.
+docker run --network changedet-network -d --name squid-one --hostname squid-one --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
+docker run --network changedet-network -d --name squid-two --hostname squid-two --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
+
+# Used for configuring a custom proxy URL via the UI
+docker run --network changedet-network -d \
+  --name squid-custom \
+  --hostname squid-custom \
+  --rm \
+  -v `pwd`/tests/proxy_list/squid-auth.conf:/etc/squid/conf.d/debian.conf \
+  -v `pwd`/tests/proxy_list/squid-passwords.txt:/etc/squid3/passwords \
+  ubuntu/squid:4.13-21.10_edge
+
+
+## 2nd test actually choose the preferred proxy from proxies.json
+
+docker run --network changedet-network \
+  -v `pwd`/tests/proxy_list/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_list/test_multiple_proxy.py'
+
+
+## Should be a request in the default "first" squid
+docker logs squid-one 2>/dev/null|grep chosen.changedetection.io
+if [ $? -ne 0 ]
+then
+  echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy - squid one)"
+  exit 1
+fi
+
+# And one in the 'second' squid (user selects this as preferred)
+docker logs squid-two 2>/dev/null|grep chosen.changedetection.io
+if [ $? -ne 0 ]
+then
+  echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy - squid two)"
+  exit 1
+fi
+
+
+# Test the UI configurable proxies
+
+docker run --network changedet-network \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_list/test_select_custom_proxy.py'
+
+
+# Should see a request for one.changedetection.io in there
+docker logs squid-custom 2>/dev/null|grep "TCP_TUNNEL.200.*changedetection.io"
+if [ $? -ne 0 ]
+then
+  echo "Did not see a valid request to changedetection.io in the squid logs (while checking preferred proxy - squid two)"
+  exit 1
+fi
+
+docker kill squid-one squid-two squid-custom

changedetectionio/static/favicons/browserconfig.xml

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="utf-8"?>
+<browserconfig>
+    <msapplication>
+        <tile>
+            <square150x150logo src="favicons/mstile-150x150.png"/>
+            <TileColor>#da532c</TileColor>
+        </tile>
+    </msapplication>
+</browserconfig>

changedetectionio/static/favicons/safari-pinned-tab.svg

@@ -0,0 +1,35 @@
+<?xml version="1.0" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 20010904//EN"
+ "http://www.w3.org/TR/2001/REC-SVG-20010904/DTD/svg10.dtd">
+<svg version="1.0" xmlns="http://www.w3.org/2000/svg"
+ width="256.000000pt" height="256.000000pt" viewBox="0 0 256.000000 256.000000"
+ preserveAspectRatio="xMidYMid meet">
+<metadata>
+Created by potrace 1.14, written by Peter Selinger 2001-2017
+</metadata>
+<g transform="translate(0.000000,256.000000) scale(0.100000,-0.100000)"
+fill="#000000" stroke="none">
+<path d="M0 1280 l0 -1280 1280 0 1280 0 0 1280 0 1280 -1280 0 -1280 0 0
+-1280z m1555 936 c387 -112 675 -426 741 -810 24 -138 15 -352 -20 -470 -106
+-353 -360 -606 -713 -712 -75 -22 -113 -27 -253 -31 -144 -5 -176 -2 -252 16
+-316 75 -564 271 -707 557 -67 136 -92 237 -98 401 -7 164 5 253 47 378 106
+315 349 556 665 659 114 37 180 45 350 41 125 -2 165 -7 240 -29z"/>
+<path d="M1091 2165 c-364 -82 -629 -328 -738 -682 -24 -80 -27 -103 -27 -258
+-1 -146 2 -182 21 -251 74 -271 259 -497 508 -621 477 -238 1061 -35 1294 450
+61 126 83 220 88 379 7 194 -15 307 -93 461 -126 251 -340 428 -614 507 -99
+29 -343 37 -439 15z m829 -473 c55 -54 100 -106 100 -116 0 -21 -184 -213
+-212 -222 -24 -7 -48 12 -48 38 0 11 26 47 58 80 l57 60 -151 -3 c-145 -4
+-152 -5 -190 -31 -22 -15 -78 -73 -124 -128 l-85 -99 -32 31 -32 31 30 38 c17
+22 70 79 117 128 66 67 97 92 127 100 22 6 106 11 188 11 81 0 147 3 147 8 0
+4 -25 31 -55 61 -55 55 -65 77 -43 99 25 25 50 10 148 -86z m-1002 -101 c46
+-24 141 -121 312 -321 203 -236 290 -330 322 -346 22 -11 60 -14 169 -12 l141
+3 -51 58 c-28 32 -51 64 -51 71 0 18 21 36 43 36 24 0 217 -193 217 -217 0
+-19 -185 -210 -212 -219 -24 -7 -48 12 -48 38 0 10 23 43 50 72 l50 53 -52 7
+c-29 3 -93 6 -142 6 -104 0 -152 12 -200 52 -19 15 -135 144 -258 286 -274
+316 -305 347 -354 361 -22 6 -94 11 -161 11 -67 0 -128 3 -137 6 -22 9 -21 61
+2 67 9 3 86 5 170 6 133 1 158 -2 190 -18z m227 -468 c23 -34 17 -43 -103
+-172 -119 -128 -131 -133 -343 -129 l-154 3 0 35 c0 34 1 35 50 42 28 3 96 7
+153 7 64 1 115 6 136 15 20 8 71 56 127 120 52 58 99 106 105 106 7 0 20 -12
+29 -27z"/>
+</g>
+</svg>

changedetectionio/static/favicons/site.webmanifest

@@ -0,0 +1,19 @@
+{
+    "name": "",
+    "short_name": "",
+    "icons": [
+        {
+            "src": "android-chrome-192x192.png",
+            "sizes": "192x192",
+            "type": "image/png"
+        },
+        {
+            "src": "android-chrome-256x256.png",
+            "sizes": "256x256",
+            "type": "image/png"
+        }
+    ],
+    "theme_color": "#ffffff",
+    "background_color": "#ffffff",
+    "display": "standalone"
+}

changedetectionio/static/images/bell-off.svg

@@ -1,42 +1,4 @@
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<svg
-   width="15"
-   height="16.363636"
-   viewBox="0 0 15 16.363636"
-   version="1.1"
-   id="svg4"
-   sodipodi:docname="bell-off.svg"
-   inkscape:version="1.1.1 (1:1.1+202109281949+c3084ef5ed)"
-   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
-   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
-   xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg">
-  <sodipodi:namedview
-     id="namedview5"
-     pagecolor="#ffffff"
-     bordercolor="#666666"
-     borderopacity="1.0"
-     inkscape:pageshadow="2"
-     inkscape:pageopacity="0.0"
-     inkscape:pagecheckerboard="0"
-     showgrid="false"
-     fit-margin-top="0"
-     fit-margin-left="0"
-     fit-margin-right="0"
-     fit-margin-bottom="0"
-     inkscape:zoom="28.416667"
-     inkscape:cx="-0.59824046"
-     inkscape:cy="12"
-     inkscape:window-width="1554"
-     inkscape:window-height="896"
-     inkscape:window-x="2095"
-     inkscape:window-y="107"
-     inkscape:window-maximized="0"
-     inkscape:current-layer="svg4" />
-  <defs
-     id="defs8" />
-  <path
-     d="m 14.318182,11.762045 v 1.1925 H 5.4102273 L 11.849318,7.1140909 C 12.234545,9.1561364 12.54,11.181818 14.318182,11.762045 Z m -6.7984093,4.601591 c 1.0759091,0 2.0256823,-0.955909 2.0256823,-2.045454 H 5.4545455 c 0,1.089545 0.9879545,2.045454 2.0652272,2.045454 z M 15,2.8622727 0.9177273,15.636136 0,14.627045 l 1.8443182,-1.6725 h -1.1625 v -1.1925 C 4.0070455,10.677273 2.1784091,4.5388636 5.3611364,2.6897727 5.8009091,2.4347727 6.0709091,1.9609091 6.0702273,1.4488636 v -0.00205 C 6.0702273,0.64772727 6.7104545,0 7.5,0 8.2895455,0 8.9297727,0.64772727 8.9297727,1.4468182 v 0.00205 C 8.9290909,1.9602319 9.199773,2.4354591 9.638864,2.6897773 10.364318,3.111141 10.827273,3.7568228 11.1525,4.5129591 L 14.085682,1.8531818 Z M 6.8181818,1.3636364 C 6.8181818,1.74 7.1236364,2.0454545 7.5,2.0454545 7.8763636,2.0454545 8.1818182,1.74 8.1818182,1.3636364 8.1818182,0.98795455 7.8763636,0.68181818 7.5,0.68181818 c -0.3763636,0 -0.6818182,0.30613637 -0.6818182,0.68181822 z"
-     id="path2"
-     style="fill:#f8321b;stroke-width:0.681818;fill-opacity:1" />
+<svg width="15" height="16.363636" viewBox="0 0 15 16.363636" xmlns="http://www.w3.org/2000/svg" xmlns:svg="http://www.w3.org/2000/svg">
+  <path d="m 14.318182,11.762045 v 1.1925 H 5.4102273 L 11.849318,7.1140909 C 12.234545,9.1561364 12.54,11.181818 14.318182,11.762045 Z m -6.7984093,4.601591 c 1.0759091,0 2.0256823,-0.955909 2.0256823,-2.045454 H 5.4545455 c 0,1.089545 0.9879545,2.045454 2.0652272,2.045454 z M 15,2.8622727 0.9177273,15.636136 0,14.627045 l 1.8443182,-1.6725 h -1.1625 v -1.1925 C 4.0070455,10.677273 2.1784091,4.5388636 5.3611364,2.6897727 5.8009091,2.4347727 6.0709091,1.9609091 6.0702273,1.4488636 v -0.00205 C 6.0702273,0.64772727 6.7104545,0 7.5,0 8.2895455,0 8.9297727,0.64772727 8.9297727,1.4468182 v 0.00205 C 8.9290909,1.9602319 9.199773,2.4354591 9.638864,2.6897773 10.364318,3.111141 10.827273,3.7568228 11.1525,4.5129591 L 14.085682,1.8531818 Z M 6.8181818,1.3636364 C 6.8181818,1.74 7.1236364,2.0454545 7.5,2.0454545 7.8763636,2.0454545 8.1818182,1.74 8.1818182,1.3636364 8.1818182,0.98795455 7.8763636,0.68181818 7.5,0.68181818 c -0.3763636,0 -0.6818182,0.30613637 -0.6818182,0.68181822 z" id="path2" style="fill:#f8321b;stroke-width:0.681818;fill-opacity:1"/>
 </svg>

changedetectionio/static/images/email.svg

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

changedetectionio/static/images/generic-icon.svg

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

changedetectionio/static/images/pdf-icon.svg

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg xmlns="http://www.w3.org/2000/svg" width="75.320129mm" height="92.604164mm" viewBox="0 0 75.320129 92.604164">
+  <g transform="translate(53.548057 -183.975276) scale(1.4843)">
+    <path fill="#ff2116" d="M-29.632812 123.94727c-3.551967 0-6.44336 2.89347-6.44336 6.44531v49.49804c0 3.55185 2.891393 6.44532 6.44336 6.44532H8.2167969c3.5519661 0 6.4433591-2.89335 6.4433591-6.44532v-40.70117s.101353-1.19181-.416015-2.35156c-.484969-1.08711-1.275391-1.84375-1.275391-1.84375a1.0584391 1.0584391 0 0 0-.0059-.008l-9.3906254-9.21094a1.0584391 1.0584391 0 0 0-.015625-.0156s-.8017392-.76344-1.9902344-1.27344c-1.39939552-.6005-2.8417968-.53711-2.8417968-.53711l.021484-.002z" color="#000" font-family="sans-serif" overflow="visible" paint-order="markers fill stroke" style="line-height:normal;font-variant-ligatures:normal;font-variant-position:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-alternates:normal;font-feature-settings:normal;text-indent:0;text-align:start;text-decoration-line:none;text-decoration-style:solid;text-decoration-color:#000000;text-transform:none;text-orientation:mixed;white-space:normal;shape-padding:0;isolation:auto;mix-blend-mode:normal;solid-color:#000000;solid-opacity:1"/>
+    <path fill="#f5f5f5" d="M-29.632812 126.06445h28.3789058a1.0584391 1.0584391 0 0 0 .021484 0s1.13480448.011 1.96484378.36719c.79889772.34282 1.36536982.86176 1.36914062.86524.0000125.00001.00391.004.00391.004l9.3671868 9.18945s.564354.59582.837891 1.20899c.220779.49491.234375 1.40039.234375 1.40039a1.0584391 1.0584391 0 0 0-.002.0449v40.74609c0 2.41592-1.910258 4.32813-4.3261717 4.32813H-29.632812c-2.415914 0-4.326172-1.91209-4.326172-4.32813v-49.49804c0-2.41603 1.910258-4.32813 4.326172-4.32813z" color="#000" font-family="sans-serif" overflow="visible" paint-order="markers fill stroke" style="line-height:normal;font-variant-ligatures:normal;font-variant-position:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-alternates:normal;font-feature-settings:normal;text-indent:0;text-align:start;text-decoration-line:none;text-decoration-style:solid;text-decoration-color:#000000;text-transform:none;text-orientation:mixed;white-space:normal;shape-padding:0;isolation:auto;mix-blend-mode:normal;solid-color:#000000;solid-opacity:1"/>
+    <path fill="#ff2116" d="M-23.40766 161.09299c-1.45669-1.45669.11934-3.45839 4.39648-5.58397l2.69124-1.33743 1.04845-2.29399c.57665-1.26169 1.43729-3.32036 1.91254-4.5748l.8641-2.28082-.59546-1.68793c-.73217-2.07547-.99326-5.19438-.52872-6.31588.62923-1.51909 2.69029-1.36323 3.50626.26515.63727 1.27176.57212 3.57488-.18329 6.47946l-.6193 2.38125.5455.92604c.30003.50932 1.1764 1.71867 1.9475 2.68743l1.44924 1.80272 1.8033728-.23533c5.72900399-.74758 7.6912472.523 7.6912472 2.34476 0 2.29921-4.4984914 2.48899-8.2760865-.16423-.8499666-.59698-1.4336605-1.19001-1.4336605-1.19001s-2.3665326.48178-3.531704.79583c-1.202707.32417-1.80274.52719-3.564509 1.12186 0 0-.61814.89767-1.02094 1.55026-1.49858 2.4279-3.24833 4.43998-4.49793 5.1723-1.3991.81993-2.86584.87582-3.60433.13733zm2.28605-.81668c.81883-.50607 2.47616-2.46625 3.62341-4.28553l.46449-.73658-2.11497 1.06339c-3.26655 1.64239-4.76093 3.19033-3.98386 4.12664.43653.52598.95874.48237 2.01093-.16792zm21.21809-5.95578c.80089-.56097.68463-1.69142-.22082-2.1472-.70466-.35471-1.2726074-.42759-3.1031574-.40057-1.1249.0767-2.9337647.3034-3.2403347.37237 0 0 .993716.68678 1.434896.93922.58731.33544 2.0145161.95811 3.0565161 1.27706 1.02785.31461 1.6224.28144 2.0729-.0409zm-8.53152-3.54594c-.4847-.50952-1.30889-1.57296-1.83152-2.3632-.68353-.89643-1.02629-1.52887-1.02629-1.52887s-.4996 1.60694-.90948 2.57394l-1.27876 3.16076-.37075.71695s1.971043-.64627 2.97389-.90822c1.0621668-.27744 3.21787-.70134 3.21787-.70134zm-2.74938-11.02573c.12363-1.0375.1761-2.07346-.15724-2.59587-.9246-1.01077-2.04057-.16787-1.85154 2.23517.0636.8084.26443 2.19033.53292 3.04209l.48817 1.54863.34358-1.16638c.18897-.64151.47882-2.02015.64411-3.06364z"/>
+    <path fill="#2c2c2c" d="M-20.930423 167.83862h2.364986q1.133514 0 1.840213.2169.706698.20991 1.189489.9446.482795.72769.482795 1.75625 0 .94459-.391832 1.6233-.391833.67871-1.056548.97958-.65772.30087-2.02913.30087h-.818651v3.72941h-1.581322zm1.581322 1.22447v3.33058h.783664q1.049552 0 1.44838-.39184.405826-.39183.405826-1.27345 0-.65772-.265887-1.06355-.265884-.41282-.587747-.50378-.314866-.098-1.000572-.098zm5.50664-1.22447h2.148082q1.560333 0 2.4909318.55276.9375993.55276 1.4133973 1.6443.482791 1.09153.482791 2.42096 0 1.3994-.4338151 2.49793-.4268149 1.09153-1.3154348 1.76324-.8816233.67172-2.5189212.67172h-2.267031zm1.581326 1.26645v7.018h.657715q1.378411 0 2.001144-.9516.6227329-.95858.6227329-2.5539 0-3.5125-2.6238769-3.5125zm6.4722254-1.26645h5.30372941v1.26645H-4.2075842v2.85478h2.9807225v1.26646h-2.9807225v4.16322h-1.5813254z" font-family="Franklin Gothic Medium Cond" letter-spacing="0" style="line-height:125%;-inkscape-font-specification:'Franklin Gothic Medium Cond'" word-spacing="4.26000023"/>
+  </g>
+</svg>

changedetectionio/static/images/price-tag-icon.svg

@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg width="83.39" height="89.648" enable-background="new 0 0 122.406 122.881" version="1.1" viewBox="0 0 83.39 89.648" xml:space="preserve" xmlns="http://www.w3.org/2000/svg"><g transform="translate(5e-4 -33.234)"><path d="m44.239 42.946-39.111 39.896 34.908 34.91 39.09-39.876-1.149-34.931zm-0.91791 42.273c0.979-0.979 1.507-1.99 1.577-3.027 0.077-1.043-0.248-2.424-0.967-4.135-0.725-1.717-1.348-3.346-1.87-4.885s-0.814-3.014-0.897-4.432c-0.07-1.42 0.134-2.768 0.624-4.045 0.477-1.279 1.348-2.545 2.607-3.804 2.099-2.099 4.535-3.123 7.314-3.065 2.773 0.063 5.457 1.158 8.04 3.294l2.881 3.034c1.946 2.607 2.799 5.33 2.557 8.166-0.235 2.83-1.532 5.426-3.893 7.785l-6.296-6.297c1.291-1.291 2.035-2.531 2.238-3.727 0.191-1.197-0.165-2.252-1.081-3.168-0.821-0.82-1.717-1.195-2.69-1.139-0.967 0.064-1.908 0.547-2.817 1.457-0.922 0.922-1.393 1.914-1.412 2.977s0.306 2.416 0.973 4.064c0.661 1.652 1.24 3.25 1.736 4.801 0.496 1.553 0.782 3.035 0.858 4.445 0.076 1.426-0.127 2.787-0.591 4.104-0.477 1.316-1.336 2.596-2.588 3.848-2.125 2.125-4.522 3.186-7.212 3.18s-5.311-1.063-7.855-3.16l-3.747 3.746-2.964-2.965 3.766-3.764c-2.423-2.996-3.568-5.998-3.447-9.02 0.127-3.014 1.476-5.813 4.045-8.383l6.278 6.277c-1.412 1.412-2.175 2.799-2.277 4.16-0.108 1.367 0.414 2.627 1.571 3.783 0.839 0.84 1.755 1.26 2.741 1.242 0.985-0.017 1.92-0.47 2.798-1.347zm21.127-46.435h17.457c-0.0269 2.2368 0.69936 16.025 0.69936 16.025l0.785 23.858c0.019 0.609-0.221 1.164-0.619 1.564l5e-3 4e-3 -41.236 42.022c-0.82213 0.8378-2.175 0.83-3.004 0l-37.913-37.91c-0.83-0.83-0.83-2.176 0-3.006l41.236-42.021c0.39287-0.42671 1.502-0.53568 1.502-0.53568zm18.011 11.59c-59.392-29.687-29.696-14.843 0 0z"/></g></svg>

changedetectionio/static/images/spread.svg

@@ -1,46 +1,5 @@
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<svg
-   width="18"
-   height="19.92"
-   viewBox="0 0 18 19.92"
-   version="1.1"
-   id="svg6"
-   sodipodi:docname="spread.svg"
-   inkscape:version="1.1.1 (1:1.1+202109281949+c3084ef5ed)"
-   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
-   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
-   xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg">
-  <defs
-     id="defs10" />
-  <sodipodi:namedview
-     id="namedview8"
-     pagecolor="#ffffff"
-     bordercolor="#666666"
-     borderopacity="1.0"
-     inkscape:pageshadow="2"
-     inkscape:pageopacity="0.0"
-     inkscape:pagecheckerboard="0"
-     showgrid="false"
-     fit-margin-top="0"
-     fit-margin-left="0"
-     fit-margin-right="0"
-     fit-margin-bottom="0"
-     inkscape:zoom="28.416667"
-     inkscape:cx="9.0087975"
-     inkscape:cy="9.9941348"
-     inkscape:window-width="1920"
-     inkscape:window-height="1056"
-     inkscape:window-x="1920"
-     inkscape:window-y="0"
-     inkscape:window-maximized="1"
-     inkscape:current-layer="svg6" />
-  <path
-     d="M -3,-2 H 21 V 22 H -3 Z"
-     fill="none"
-     id="path2" />
-  <path
-     d="m 15,14.08 c -0.76,0 -1.44,0.3 -1.96,0.77 L 5.91,10.7 C 5.96,10.47 6,10.24 6,10 6,9.76 5.96,9.53 5.91,9.3 L 12.96,5.19 C 13.5,5.69 14.21,6 15,6 16.66,6 18,4.66 18,3 18,1.34 16.66,0 15,0 c -1.66,0 -3,1.34 -3,3 0,0.24 0.04,0.47 0.09,0.7 L 5.04,7.81 C 4.5,7.31 3.79,7 3,7 1.34,7 0,8.34 0,10 c 0,1.66 1.34,3 3,3 0.79,0 1.5,-0.31 2.04,-0.81 l 7.12,4.16 c -0.05,0.21 -0.08,0.43 -0.08,0.65 0,1.61 1.31,2.92 2.92,2.92 1.61,0 2.92,-1.31 2.92,-2.92 0,-1.61 -1.31,-2.92 -2.92,-2.92 z"
-     id="path4"
-     style="fill:#0078e7;fill-opacity:1" />
+<svg width="18" height="19.92" viewBox="0 0 18 19.92" xmlns="http://www.w3.org/2000/svg" xmlns:svg="http://www.w3.org/2000/svg">
+  <path d="M -3,-2 H 21 V 22 H -3 Z" fill="none" id="path2"/>
+  <path d="m 15,14.08 c -0.76,0 -1.44,0.3 -1.96,0.77 L 5.91,10.7 C 5.96,10.47 6,10.24 6,10 6,9.76 5.96,9.53 5.91,9.3 L 12.96,5.19 C 13.5,5.69 14.21,6 15,6 16.66,6 18,4.66 18,3 18,1.34 16.66,0 15,0 c -1.66,0 -3,1.34 -3,3 0,0.24 0.04,0.47 0.09,0.7 L 5.04,7.81 C 4.5,7.31 3.79,7 3,7 1.34,7 0,8.34 0,10 c 0,1.66 1.34,3 3,3 0.79,0 1.5,-0.31 2.04,-0.81 l 7.12,4.16 c -0.05,0.21 -0.08,0.43 -0.08,0.65 0,1.61 1.31,2.92 2.92,2.92 1.61,0 2.92,-1.31 2.92,-2.92 0,-1.61 -1.31,-2.92 -2.92,-2.92 z" id="path4" style="fill:#0078e7;fill-opacity:1"/>
 </svg>

changedetectionio/static/js/browser-steps.js

@@ -0,0 +1,445 @@
+$(document).ready(function () {
+
+    // duplicate
+    var csrftoken = $('input[name=csrf_token]').val();
+    $.ajaxSetup({
+        beforeSend: function (xhr, settings) {
+            if (!/^(GET|HEAD|OPTIONS|TRACE)$/i.test(settings.type) && !this.crossDomain) {
+                xhr.setRequestHeader("X-CSRFToken", csrftoken)
+            }
+        }
+    })
+    var browsersteps_session_id;
+    var browserless_seconds_remaining = 0;
+    var apply_buttons_disabled = false;
+    var include_text_elements = $("#include_text_elements");
+    var xpath_data = false;
+    var current_selected_i;
+    var state_clicked = false;
+    var c;
+
+    // redline highlight context
+    var ctx;
+    var last_click_xy = {'x': -1, 'y': -1}
+
+    $(window).resize(function () {
+        set_scale();
+    });
+    // Should always be disabled
+    $('#browser_steps >li:first-child select').val('Goto site').attr('disabled', 'disabled');
+
+    $('#browsersteps-click-start').click(function () {
+        $("#browsersteps-click-start").fadeOut();
+        $("#browsersteps-selector-wrapper .spinner").fadeIn();
+        start();
+    });
+
+    $('a#browsersteps-tab').click(function () {
+        reset();
+    });
+
+    window.addEventListener('hashchange', function () {
+        if (window.location.hash == '#browser-steps') {
+            reset();
+        }
+    });
+
+    function reset() {
+        xpath_data = false;
+        $('#browsersteps-img').removeAttr('src');
+        $("#browsersteps-click-start").show();
+        $("#browsersteps-selector-wrapper .spinner").hide();
+        browserless_seconds_remaining = 0;
+        browsersteps_session_id = false;
+        apply_buttons_disabled = false;
+        ctx.clearRect(0, 0, c.width, c.height);
+        set_first_gotosite_disabled();
+    }
+
+    function set_first_gotosite_disabled() {
+        $('#browser_steps >li:first-child select').val('Goto site').attr('disabled', 'disabled');
+        $('#browser_steps >li:first-child').css('opacity', '0.5');
+    }
+
+    // Show seconds remaining until playwright/browserless needs to restart the session
+    // (See comment at the top of changedetectionio/blueprint/browser_steps/__init__.py )
+    setInterval(() => {
+        if (browserless_seconds_remaining >= 1) {
+            document.getElementById('browserless-seconds-remaining').innerText = browserless_seconds_remaining + " seconds remaining in session";
+            browserless_seconds_remaining -= 1;
+        }
+    }, "1000")
+
+
+    function set_scale() {
+
+        // some things to check if the scaling doesnt work
+        // - that the widths/sizes really are about the actual screen size cat elements.json |grep -o width......|sort|uniq
+        selector_image = $("img#browsersteps-img")[0];
+        selector_image_rect = selector_image.getBoundingClientRect();
+
+        // make the canvas and input steps the same size as the image
+        $('#browsersteps-selector-canvas').attr('height', selector_image_rect.height).attr('width', selector_image_rect.width);
+        //$('#browsersteps-selector-wrapper').attr('width', selector_image_rect.width);
+        $('#browser-steps-ui').attr('width', selector_image_rect.width);
+
+        x_scale = selector_image_rect.width / xpath_data['browser_width'];
+        y_scale = selector_image_rect.height / selector_image.naturalHeight;
+        ctx.strokeStyle = 'rgba(255,0,0, 0.9)';
+        ctx.fillStyle = 'rgba(255,0,0, 0.1)';
+        ctx.lineWidth = 3;
+        console.log("scaling set  x: " + x_scale + " by y:" + y_scale);
+    }
+
+    // bootstrap it, this will trigger everything else
+    $('#browsersteps-img').bind('load', function () {
+        $('body').addClass('full-width');
+        console.log("Loaded background...");
+
+        document.getElementById("browsersteps-selector-canvas");
+        c = document.getElementById("browsersteps-selector-canvas");
+        // redline highlight context
+        ctx = c.getContext("2d");
+        // @todo is click better?
+        $('#browsersteps-selector-canvas').off("mousemove mousedown click");
+        // Undo disable_browsersteps_ui
+        $("#browser-steps-ui").css('opacity', '1.0');
+
+        // init
+        set_scale();
+
+        // @todo click ? some better library?
+        $('#browsersteps-selector-canvas').bind('click', function (e) {
+            // https://developer.mozilla.org/en-US/docs/Web/API/MouseEvent
+            e.preventDefault()
+        });
+
+        // When the mouse moves we know which element it should be above
+        // mousedown will link that to the UI (select the right action, highlight etc)
+        $('#browsersteps-selector-canvas').bind('mousedown', function (e) {
+            // https://developer.mozilla.org/en-US/docs/Web/API/MouseEvent
+            e.preventDefault()
+            last_click_xy = {'x': parseInt((1 / x_scale) * e.offsetX), 'y': parseInt((1 / y_scale) * e.offsetY)}
+            process_selected(current_selected_i);
+            current_selected_i = false;
+
+            // if process selected returned false, then best we can do is offer a x,y click :(
+            if (!found_something) {
+                var first_available = $("ul#browser_steps li.empty").first();
+                $('select', first_available).val('Click X,Y').change();
+                $('input[type=text]', first_available).first().val(last_click_xy['x'] + ',' + last_click_xy['y']);
+                draw_circle_on_canvas(e.offsetX, e.offsetY);
+            }
+        });
+
+        // Debounce and find the current most 'interesting' element we are hovering above
+        $('#browsersteps-selector-canvas').bind('mousemove', function (e) {
+            if (!xpath_data) {
+                return;
+            }
+
+            // checkbox if find elements is enabled
+            ctx.clearRect(0, 0, c.width, c.height);
+            ctx.fillStyle = 'rgba(255,0,0, 0.1)';
+            ctx.strokeStyle = 'rgba(255,0,0, 0.9)';
+
+            // Add in offset
+            if ((typeof e.offsetX === "undefined" || typeof e.offsetY === "undefined") || (e.offsetX === 0 && e.offsetY === 0)) {
+                var targetOffset = $(e.target).offset();
+                e.offsetX = e.pageX - targetOffset.left;
+                e.offsetY = e.pageY - targetOffset.top;
+            }
+            current_selected_i = false;
+            // Reverse order - the most specific one should be deeper/"laster"
+            // Basically, find the most 'deepest'
+            var possible_elements = [];
+            xpath_data['size_pos'].forEach(function (item, index) {
+                // If we are in a bounding-box
+                if (e.offsetY > item.top * y_scale && e.offsetY < item.top * y_scale + item.height * y_scale
+                    &&
+                    e.offsetX > item.left * y_scale && e.offsetX < item.left * y_scale + item.width * y_scale
+
+                ) {
+                    // There could be many elements here, record them all and then we'll find out which is the most 'useful'
+                    // (input, textarea, button, A etc)
+                    if (item.width < xpath_data['browser_width']) {
+                        possible_elements.push(item);
+                    }
+                }
+            });
+
+            // Find the best one
+            if (possible_elements.length) {
+                possible_elements.forEach(function (item, index) {
+                  if (["a", "input", "textarea", "button"].includes(item['tagName'])) {
+                      current_selected_i = item;
+                  }
+                });
+
+                if (!current_selected_i) {
+                    current_selected_i = possible_elements[0];
+                }
+
+                sel = xpath_data['size_pos'][current_selected_i];
+                ctx.strokeRect(current_selected_i.left * x_scale, current_selected_i.top * y_scale, current_selected_i.width * x_scale, current_selected_i.height * y_scale);
+                ctx.fillRect(current_selected_i.left * x_scale, current_selected_i.top * y_scale, current_selected_i.width * x_scale, current_selected_i.height * y_scale);
+            }
+
+
+        }.debounce(10));
+    });
+
+//    $("#browser-steps-fieldlist").bind('mouseover', function(e) {
+//        console.log(e.xpath_data_index);
+    // });
+
+
+    // callback for clicking on an xpath on the canvas
+    function process_selected(selected_in_xpath_list) {
+        found_something = false;
+        var first_available = $("ul#browser_steps li.empty").first();
+
+
+        if (selected_in_xpath_list !== false) {
+            // Nothing focused, so fill in a new one
+            // if inpt type button or <button>
+            // from the top, find the next not used one and use it
+            var x = selected_in_xpath_list;
+            console.log(x);
+            if (x && first_available.length) {
+                // @todo will it let you click shit that has a layer ontop? probably not.
+                if (x['tagtype'] === 'text' || x['tagtype'] === 'email' || x['tagName'] === 'textarea' || x['tagtype'] === 'password' || x['tagtype'] === 'search') {
+                    $('select', first_available).val('Enter text in field').change();
+                    $('input[type=text]', first_available).first().val(x['xpath']);
+                    $('input[placeholder="Value"]', first_available).addClass('ok').click().focus();
+                    found_something = true;
+                } else {
+                    // There's no good way (that I know) to find if this
+                    // see https://stackoverflow.com/questions/446892/how-to-find-event-listeners-on-a-dom-node-in-javascript-or-in-debugging
+                    // https://codepen.io/azaslavsky/pen/DEJVWv
+
+                    // So we dont know if its really a clickable element or not :-(
+                    // Assume it is - then we dont fill the pages with unreliable "Click X,Y" selections
+                    // If you switch to "Click X,y" after an element here is setup, it will give the last co-ords anyway
+                    //if (x['isClickable'] || x['tagName'].startsWith('h') || x['tagName'] === 'a' || x['tagName'] === 'button' || x['tagtype'] === 'submit' || x['tagtype'] === 'checkbox' || x['tagtype'] === 'radio' || x['tagtype'] === 'li') {
+                        $('select', first_available).val('Click element').change();
+                        $('input[type=text]', first_available).first().val(x['xpath']);
+                        found_something = true;
+                    //}
+                }
+            }
+        }
+    }
+
+    function draw_circle_on_canvas(x, y) {
+        ctx.beginPath();
+        ctx.arc(x, y, 8, 0, 2 * Math.PI, false);
+        ctx.fillStyle = 'rgba(255,0,0, 0.6)';
+        ctx.fill();
+    }
+
+    function start() {
+        console.log("Starting browser-steps UI");
+        browsersteps_session_id = false;
+        // @todo This setting of the first one should be done at the datalayer but wtforms doesnt wanna play nice
+        $('#browser_steps >li:first-child').removeClass('empty');
+        set_first_gotosite_disabled();
+        $('#browser-steps-ui .loader .spinner').show();
+        $('.clear,.remove', $('#browser_steps >li:first-child')).hide();
+        $.ajax({
+            type: "GET",
+            url: browser_steps_start_url,
+            statusCode: {
+                400: function () {
+                    // More than likely the CSRF token was lost when the server restarted
+                    alert("There was a problem processing the request, please reload the page.");
+                }
+            }
+        }).done(function (data) {
+            $("#loading-status-text").fadeIn();
+            browsersteps_session_id = data.browsersteps_session_id;
+            // This should trigger 'Goto site'
+            console.log("Got startup response, requesting Goto-Site (first) step fake click");
+            $('#browser_steps >li:first-child .apply').click();
+            browserless_seconds_remaining = 500;
+            set_first_gotosite_disabled();
+        }).fail(function (data) {
+            console.log(data);
+            alert('There was an error communicating with the server.');
+        });
+
+    }
+
+    function disable_browsersteps_ui() {
+        set_first_gotosite_disabled();
+        $("#browser-steps-ui").css('opacity', '0.3');
+        $('#browsersteps-selector-canvas').off("mousemove mousedown click");
+    }
+
+
+    ////////////////////////// STEPS UI ////////////////////
+    $('ul#browser_steps [type="text"]').keydown(function (e) {
+        if (e.keyCode === 13) {
+            // hitting [enter] in a browser-step input should trigger the 'Apply'
+            e.preventDefault();
+            $(".apply", $(this).closest('li')).click();
+            return false;
+        }
+    });
+
+    // Look up which step was selected, and enable or disable the related extra fields
+    // So that people using it dont' get confused
+    $('ul#browser_steps select').on("change", function () {
+        var config = browser_steps_config[$(this).val()].split(' ');
+        var elem_selector = $('tr:nth-child(2) input', $(this).closest('tbody'));
+        var elem_value = $('tr:nth-child(3) input', $(this).closest('tbody'));
+
+        if (config[0] == 0) {
+            $(elem_selector).fadeOut();
+        } else {
+            $(elem_selector).fadeIn();
+        }
+        if (config[1] == 0) {
+            $(elem_value).fadeOut();
+        } else {
+            $(elem_value).fadeIn();
+        }
+
+        if ($(this).val() === 'Click X,Y' && last_click_xy['x'] > 0 && $(elem_value).val().length === 0) {
+            // @todo handle scale
+            $(elem_value).val(last_click_xy['x'] + ',' + last_click_xy['y']);
+        }
+    }).change();
+
+    function set_greyed_state() {
+        $('ul#browser_steps select').not('option:selected[value="Choose one"]').closest('li').removeClass('empty');
+        $('ul#browser_steps select option:selected[value="Choose one"]').closest('li').addClass('empty');
+    }
+
+    // Add the extra buttons to the steps
+    $('ul#browser_steps li').each(function (i) {
+            var s = '<div class="control">' + '<a data-step-index=' + i + ' class="pure-button button-secondary button-green button-xsmall apply" >Apply</a>&nbsp;';
+            if (i > 0) {
+                // The first step never gets these (Goto-site)
+                s += '<a data-step-index=' + i + ' class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;' +
+                    '<a data-step-index=' + i + ' class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>';
+            }
+            s += '</div>';
+            $(this).append(s)
+        }
+    );
+
+    $('ul#browser_steps li .control .clear').click(function (element) {
+        $("select", $(this).closest('li')).val("Choose one").change();
+        $(":text", $(this).closest('li')).val('');
+    });
+
+
+    $('ul#browser_steps li .control .remove').click(function (element) {
+        // so you wanna remove the 2nd (3rd spot 0,1,2,...)
+        var p = $("#browser_steps li").index($(this).closest('li'));
+
+        var elem_to_remove = $("#browser_steps li")[p];
+        $('.clear', elem_to_remove).click();
+        $("#browser_steps li").slice(p, 10).each(function (index) {
+            // get the next one's value from where we clicked
+            var next = $("#browser_steps li")[p + index + 1];
+            if (next) {
+                // and set THIS ones value from the next one
+                var n = $('input', next);
+                $("select", $(this)).val($('select', next).val());
+                $('input', this)[0].value = $(n)[0].value;
+                $('input', this)[1].value = $(n)[1].value;
+                // Triggers reconfiguring the field based on the system config
+                $("select", $(this)).change();
+            }
+
+        });
+
+        // Reset their hidden/empty states
+        set_greyed_state();
+    });
+
+    $('ul#browser_steps li .control .apply').click(function (event) {
+        // sequential requests @todo refactor
+        if (apply_buttons_disabled) {
+            return;
+        }
+
+        var current_data = $(event.currentTarget).closest('li');
+        $('#browser-steps-ui .loader .spinner').fadeIn();
+        apply_buttons_disabled = true;
+        $('ul#browser_steps li .control .apply').css('opacity', 0.5);
+        $("#browsersteps-img").css('opacity', 0.65);
+
+        var is_last_step = 0;
+        var step_n = $(event.currentTarget).data('step-index');
+
+        // On the last step, we should also be getting data ready for the visual selector
+        $('ul#browser_steps li select').each(function (i) {
+            if ($(this).val() !== 'Choose one') {
+                is_last_step += 1;
+            }
+        });
+
+        if (is_last_step == (step_n + 1)) {
+            is_last_step = true;
+        } else {
+            is_last_step = false;
+        }
+
+        console.log("Requesting step via POST " + $("select[id$='operation']", current_data).first().val());
+        // POST the currently clicked step form widget back and await response, redraw
+        $.ajax({
+            method: "POST",
+            url: browser_steps_sync_url + "&browsersteps_session_id=" + browsersteps_session_id,
+            data: {
+                'operation': $("select[id$='operation']", current_data).first().val(),
+                'selector': $("input[id$='selector']", current_data).first().val(),
+                'optional_value': $("input[id$='optional_value']", current_data).first().val(),
+                'step_n': step_n,
+                'is_last_step': is_last_step
+            },
+            statusCode: {
+                400: function () {
+                    // More than likely the CSRF token was lost when the server restarted
+                    alert("There was a problem processing the request, please reload the page.");
+                    $("#loading-status-text").hide();
+                    $('#browser-steps-ui .loader .spinner').fadeOut();
+                },
+                401: function (data) {
+                    // More than likely the CSRF token was lost when the server restarted
+                    alert(data.responseText);
+                    $("#loading-status-text").hide();
+                    $('#browser-steps-ui .loader .spinner').fadeOut();
+                }
+            }
+        }).done(function (data) {
+            // it should return the new state (selectors available and screenshot)
+            xpath_data = data.xpath_data;
+            $('#browsersteps-img').attr('src', data.screenshot);
+            $('#browser-steps-ui .loader .spinner').fadeOut();
+            apply_buttons_disabled = false;
+            $("#browsersteps-img").css('opacity', 1);
+            $('ul#browser_steps li .control .apply').css('opacity', 1);
+            $("#loading-status-text").hide();
+            set_first_gotosite_disabled();
+        }).fail(function (data) {
+            console.log(data);
+            if (data.responseText.includes("Browser session expired")) {
+                disable_browsersteps_ui();
+            }
+            apply_buttons_disabled = false;
+            $("#loading-status-text").hide();
+            $('ul#browser_steps li .control .apply').css('opacity', 1);
+            $("#browsersteps-img").css('opacity', 1);
+        });
+
+    });
+
+
+    $("ul#browser_steps select").change(function () {
+        set_greyed_state();
+    }).change();
+
+});

changedetectionio/static/js/diff-overview.js

@@ -1,4 +1,13 @@
 $(document).ready(function () {
+    var csrftoken = $('input[name=csrf_token]').val();
+    $.ajaxSetup({
+        beforeSend: function (xhr, settings) {
+            if (!/^(GET|HEAD|OPTIONS|TRACE)$/i.test(settings.type) && !this.crossDomain) {
+                xhr.setRequestHeader("X-CSRFToken", csrftoken)
+            }
+        }
+    })
+
     // Load it when the #screenshot tab is in use, so we dont give a slow experience when waiting for the text diff to load
     window.addEventListener('hashchange', function (e) {
         toggle(location.hash);
@@ -13,11 +22,73 @@ $(document).ready(function () {
         } else if (hash_name === '#error-screenshot') {
             $("img#error-screenshot-img").attr('src', error_screenshot_url);
             $("#settings").hide();
-        }
-
-
-        else {
+        } else if (hash_name === '#extract') {
+            $("#settings").hide();
+        } else {
             $("#settings").show();
         }
     }
+
+    const article = $('.highlightable-filter')[0];
+
+    // We could also add the  'touchend' event for touch devices, but since
+    // most iOS/Android browsers already show a dialog when you select
+    // text (often with a Share option) we'll skip that
+    article.addEventListener('mouseup', dragTextHandler, false);
+    article.addEventListener('mousedown', clean, false);
+
+    function clean(event) {
+      $("#highlightSnippet").remove();
+    }
+
+
+    function dragTextHandler(event) {
+        console.log('mouseupped');
+
+        // Check if any text was selected
+        if (window.getSelection().toString().length > 0) {
+
+            // Find out how much (if any) user has scrolled
+            var scrollTop = (window.pageYOffset !== undefined) ? window.pageYOffset : (document.documentElement || document.body.parentNode || document.body).scrollTop;
+
+            // Get cursor position
+            const posX = event.clientX;
+            const posY = event.clientY + 20 + scrollTop;
+
+            // Append HTML to the body, create the "Tweet Selection" dialog
+            document.body.insertAdjacentHTML('beforeend', '<div id="highlightSnippet" style="position: absolute; top: ' + posY + 'px; left: ' + posX + 'px;"><div class="pure-form-message-inline" style="font-size: 70%">Ignore any change on any line which contains the selected text.</div><br><a data-mode="exact" href="javascript:void(0);" class="pure-button button-secondary button-xsmall">Ignore exact text</a>&nbsp;</div>');
+
+            if (/\d/.test(window.getSelection().toString())) {
+                // Offer regex replacement
+                document.getElementById("highlightSnippet").insertAdjacentHTML('beforeend', '<a data-mode="digit-regex"  href="javascript:void(0);" class="pure-button button-secondary button-xsmall">Ignore text including number changes</a>');
+            }
+
+            $('#highlightSnippet a').bind('click', function (e) {
+                if(!window.getSelection().toString().trim().length) {
+                    alert('Oops no text selected!');
+                    return;
+                }
+
+                $.ajax({
+                    type: "POST",
+                    url: highlight_submit_ignore_url,
+                    data: {'mode': $(this).data('mode'), 'selection': window.getSelection().toString()},
+                    statusCode: {
+                        400: function () {
+                            // More than likely the CSRF token was lost when the server restarted
+                            alert("There was a problem processing the request, please reload the page.");
+                        }
+                    }
+                }).done(function (data) {
+                    $("#highlightSnippet").append(data)
+                }).fail(function (data) {
+                    console.log(data);
+                    alert('There was an error communicating with the server.');
+                });
+            });
+
+        }
+    }
+
+
 });

changedetectionio/static/js/diff-render.js

@@ -0,0 +1,110 @@
+var a = document.getElementById("a");
+var b = document.getElementById("b");
+var result = document.getElementById("result");
+
+function changed() {
+  // https://github.com/kpdecker/jsdiff/issues/389
+  // I would love to use `{ignoreWhitespace: true}` here but it breaks the formatting
+  options = {
+    ignoreWhitespace: document.getElementById("ignoreWhitespace").checked,
+  };
+
+  var diff = Diff[window.diffType](a.textContent, b.textContent, options);
+  var fragment = document.createDocumentFragment();
+  for (var i = 0; i < diff.length; i++) {
+    if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
+      var swap = diff[i];
+      diff[i] = diff[i + 1];
+      diff[i + 1] = swap;
+    }
+
+    var node;
+    if (diff[i].removed) {
+      node = document.createElement("del");
+      node.classList.add("change");
+      const wrapper = node.appendChild(document.createElement("span"));
+      wrapper.appendChild(document.createTextNode(diff[i].value));
+    } else if (diff[i].added) {
+      node = document.createElement("ins");
+      node.classList.add("change");
+      const wrapper = node.appendChild(document.createElement("span"));
+      wrapper.appendChild(document.createTextNode(diff[i].value));
+    } else {
+      node = document.createTextNode(diff[i].value);
+    }
+    fragment.appendChild(node);
+  }
+
+  result.textContent = "";
+  result.appendChild(fragment);
+
+  // Jump at start
+  inputs.current = 0;
+  next_diff();
+}
+
+window.onload = function () {
+  /* Convert what is options from UTC time.time() to local browser time */
+  var diffList = document.getElementById("diff-version");
+  if (typeof diffList != "undefined" && diffList != null) {
+    for (var option of diffList.options) {
+      var dateObject = new Date(option.value * 1000);
+      option.label = dateObject.toLocaleString();
+    }
+  }
+
+  /* Set current version date as local time in the browser also */
+  var current_v = document.getElementById("current-v-date");
+  var dateObject = new Date(newest_version_timestamp * 1000);
+  current_v.innerHTML = dateObject.toLocaleString();
+  onDiffTypeChange(
+    document.querySelector('#settings [name="diff_type"]:checked'),
+  );
+  changed();
+};
+
+a.onpaste = a.onchange = b.onpaste = b.onchange = changed;
+
+if ("oninput" in a) {
+  a.oninput = b.oninput = changed;
+} else {
+  a.onkeyup = b.onkeyup = changed;
+}
+
+function onDiffTypeChange(radio) {
+  window.diffType = radio.value;
+  // Not necessary
+  //	document.title = "Diff " + radio.value.slice(4);
+}
+
+var radio = document.getElementsByName("diff_type");
+for (var i = 0; i < radio.length; i++) {
+  radio[i].onchange = function (e) {
+    onDiffTypeChange(e.target);
+    changed();
+  };
+}
+
+document.getElementById("ignoreWhitespace").onchange = function (e) {
+  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;
+  }
+}

changedetectionio/static/js/notifications.js

@@ -26,9 +26,6 @@ $(document).ready(function() {
     data = {
         window_url : window.location.href,
         notification_urls : $('.notification-urls').val(),
-        notification_title : $('.notification-title').val(),
-        notification_body : $('.notification-body').val(),
-        notification_format : $('.notification-format').val(),
     }
     for (key in data) {
       if (!data[key].length) {

changedetectionio/static/js/recheck-proxy.js

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

changedetectionio/static/js/stepper.js

@@ -0,0 +1,34 @@
+$(document).ready(function(){
+   checkUserVal();
+   $('#fetch_backend input').on('change', checkUserVal);
+});
+
+var checkUserVal = function(){
+    if($('#fetch_backend input:checked').val()=='html_requests') {
+      $('#request-override').show();
+      $('#webdriver-stepper').hide();
+    } else {
+      $('#request-override').hide();
+      $('#webdriver-stepper').show();
+    }
+};
+
+$('a.row-options').on('click', function(){
+    var row=$(this.closest('tr'));
+    switch($(this).data("action")) {
+      case 'remove':
+        $(row).remove();
+      break;
+      case 'add':
+        var new_row=$(row).clone(true).insertAfter($(row));
+        $('input', new_new).val("");
+      break;
+      case 'add':
+        var new_row=$(row).clone(true).insertAfter($(row));
+        $('input', new_new).val("");
+      break;
+      case 'resend-step':
+
+      break;
+    }
+});

changedetectionio/static/js/tabs.js

@@ -3,7 +3,8 @@
 window.addEventListener('hashchange', function () {
     var tabs = document.getElementsByClassName('active');
     while (tabs[0]) {
-        tabs[0].classList.remove('active')
+        tabs[0].classList.remove('active');
+        document.body.classList.remove('full-width');
     }
     set_active_tab();
 }, false);
@@ -11,7 +12,7 @@ window.addEventListener('hashchange', function () {
 var has_errors = document.querySelectorAll(".messages .error");
 if (!has_errors.length) {
     if (document.location.hash == "") {
-        document.querySelector(".tabs ul li:first-child a").click();
+        location.replace(document.querySelector(".tabs ul li:first-child a").hash);
     } else {
         set_active_tab();
     }
@@ -20,6 +21,7 @@ if (!has_errors.length) {
 }
 
 function set_active_tab() {
+    document.body.classList.remove('full-width');
     var tab = document.querySelectorAll("a[href='" + location.hash + "']");
     if (tab.length) {
         tab[0].parentElement.className = "active";
@@ -45,4 +47,3 @@ function focus_error_tab() {
 
 
 
-

changedetectionio/static/js/toggle-theme.js

@@ -0,0 +1,47 @@
+/**
+ * @file
+ * Toggles theme between light and dark mode.
+ */
+$(document).ready(function () {
+  const button = document.getElementById("toggle-light-mode");
+
+  button.onclick = () => {
+    const htmlElement = document.getElementsByTagName("html");
+    const isDarkMode = htmlElement[0].dataset.darkmode === "true";
+    htmlElement[0].dataset.darkmode = !isDarkMode;
+    setCookieValue(!isDarkMode);
+  };
+
+  const setCookieValue = (value) => {
+    document.cookie = `css_dark_mode=${value};max-age=31536000;path=/`
+  }
+
+  // Search input box behaviour
+    const toggle_search = document.getElementById("toggle-search");
+  const search_q = document.getElementById("search-q");
+  window.addEventListener('keydown', function (e) {
+
+    if (e.altKey == true && e.keyCode == 83)
+      search_q.classList.toggle('expanded');
+      search_q.focus();
+  });
+
+
+  search_q.onkeydown = (e) => {
+    var key = e.keyCode || e.which;
+    if (key === 13) {
+      document.searchForm.submit();
+    }
+  };
+  toggle_search.onclick = () => {
+    // Could be that they want to search something once text is in there
+    if (search_q.value.length) {
+      document.searchForm.submit();
+    } else {
+      // If not..
+      search_q.classList.toggle('expanded');
+      search_q.focus();
+    }
+  };
+
+});

changedetectionio/static/js/visual-selector.js

@@ -1,10 +1,11 @@
-// Horrible proof of concept code :)
+// Copyright (C) 2021 Leigh Morresi (dgtlmoon@gmail.com)
+// All rights reserved.
 // yes - this is really a hack, if you are a front-ender and want to help, please get in touch!
 
-$(document).ready(function() {
+$(document).ready(function () {
 
     var current_selected_i;
-    var state_clicked=false;
+    var state_clicked = false;
 
     var c;
 
@@ -13,9 +14,9 @@ $(document).ready(function() {
     // redline highlight context
     var ctx;
 
-    var current_default_xpath;
-    var x_scale=1;
-    var y_scale=1;
+    var current_default_xpath = [];
+    var x_scale = 1;
+    var y_scale = 1;
     var selector_image;
     var selector_image_rect;
     var selector_data;
@@ -27,204 +28,224 @@ $(document).ready(function() {
         bootstrap_visualselector();
     });
 
-    $(document).on('keydown', function(event) {
+    $(document).on('keydown', function (event) {
         if ($("img#selector-background").is(":visible")) {
             if (event.key == "Escape") {
-                state_clicked=false;
+                state_clicked = false;
                 ctx.clearRect(0, 0, c.width, c.height);
             }
         }
     });
 
     // For when the page loads
-    if(!window.location.hash || window.location.hash != '#visualselector') {
-        $("img#selector-background").attr('src','');
+    if (!window.location.hash || window.location.hash != '#visualselector') {
+        $("img#selector-background").attr('src', '');
         return;
     }
 
     // Handle clearing button/link
-    $('#clear-selector').on('click', function(event) {
-        if(!state_clicked) {
+    $('#clear-selector').on('click', function (event) {
+        if (!state_clicked) {
             alert('Oops, Nothing selected!');
         }
-        state_clicked=false;
+        state_clicked = false;
         ctx.clearRect(0, 0, c.width, c.height);
         xctx.clearRect(0, 0, c.width, c.height);
-        $("#css_filter").val('');
+        $("#include_filters").val('');
     });
 
 
     bootstrap_visualselector();
 
 
-
     function bootstrap_visualselector() {
-        if ( 1 ) {
+        if (1) {
             // bootstrap it, this will trigger everything else
-            $("img#selector-background").bind('load', function () {
+            $("img#selector-background").on("error", function () {
+                $('.fetching-update-notice').html("<strong>Ooops!</strong> The VisualSelector tool needs atleast one fetched page, please unpause the watch and/or wait for the watch to complete fetching and then reload this page.");
+                $('.fetching-update-notice').css('color','#bb0000');
+                $('#selector-current-xpath').hide();
+                $('#clear-selector').hide();
+            }).bind('load', function () {
                 console.log("Loaded background...");
-               c = document.getElementById("selector-canvas");
+                c = document.getElementById("selector-canvas");
                 // greyed out fill context
-               xctx = c.getContext("2d");
+                xctx = c.getContext("2d");
                 // redline highlight context
-               ctx = c.getContext("2d");
-               current_default_xpath =$("#css_filter").val();
-               fetch_data();
-               $('#selector-canvas').off("mousemove mousedown");
-               // screenshot_url defined in the edit.html template
+                ctx = c.getContext("2d");
+                if ($("#include_filters").val().trim().length) {
+                    current_default_xpath = $("#include_filters").val().split(/\r?\n/g);
+                } else {
+                    current_default_xpath = [];
+                }
+                fetch_data();
+                $('#selector-canvas').off("mousemove mousedown");
+                // screenshot_url defined in the edit.html template
             }).attr("src", screenshot_url);
         }
+        // Tell visualSelector that the image should update
+        var s = $("img#selector-background").attr('src') + "?" + new Date().getTime();
+        $("img#selector-background").attr('src', s)
     }
 
+    // This is fired once the img src is loaded in bootstrap_visualselector()
     function fetch_data() {
-      // Image is ready
-      $('.fetching-update-notice').html("Fetching element data..");
+        // Image is ready
+        $('.fetching-update-notice').html("Fetching element data..");
 
-      $.ajax({
-        url: watch_visual_selector_data_url,
-        context: document.body
-      }).done(function (data) {
-        $('.fetching-update-notice').html("Rendering..");
-        selector_data = data;
-        console.log("Reported browser width from backend: "+data['browser_width']);
-        state_clicked=false;
-        set_scale();
-        reflow_selector();
-        $('.fetching-update-notice').fadeOut();
-      });
-    };
+        $.ajax({
+            url: watch_visual_selector_data_url,
+            context: document.body
+        }).done(function (data) {
+            $('.fetching-update-notice').html("Rendering..");
+            selector_data = data;
+            console.log("Reported browser width from backend: " + data['browser_width']);
+            state_clicked = false;
+            set_scale();
+            reflow_selector();
+            $('.fetching-update-notice').fadeOut();
+        });
 
+    }
 
 
     function set_scale() {
 
-      // some things to check if the scaling doesnt work
-      // - that the widths/sizes really are about the actual screen size cat elements.json |grep -o width......|sort|uniq
-      selector_image = $("img#selector-background")[0];
-      selector_image_rect = selector_image.getBoundingClientRect();
+        // some things to check if the scaling doesnt work
+        // - that the widths/sizes really are about the actual screen size cat elements.json |grep -o width......|sort|uniq
+        $("#selector-wrapper").show();
+        selector_image = $("img#selector-background")[0];
+        selector_image_rect = selector_image.getBoundingClientRect();
 
-      // make the canvas the same size as the image
-      $('#selector-canvas').attr('height', selector_image_rect.height);
-      $('#selector-canvas').attr('width', selector_image_rect.width);
-      $('#selector-wrapper').attr('width', selector_image_rect.width);
-      x_scale = selector_image_rect.width / selector_data['browser_width'];
-      y_scale = selector_image_rect.height / selector_image.naturalHeight;
-      ctx.strokeStyle = 'rgba(255,0,0, 0.9)';
-      ctx.fillStyle = 'rgba(255,0,0, 0.1)';
-      ctx.lineWidth = 3;
-      console.log("scaling set  x: "+x_scale+" by y:"+y_scale);
-      $("#selector-current-xpath").css('max-width', selector_image_rect.width);
+        // make the canvas the same size as the image
+        $('#selector-canvas').attr('height', selector_image_rect.height);
+        $('#selector-canvas').attr('width', selector_image_rect.width);
+        $('#selector-wrapper').attr('width', selector_image_rect.width);
+        x_scale = selector_image_rect.width / selector_data['browser_width'];
+        y_scale = selector_image_rect.height / selector_image.naturalHeight;
+        ctx.strokeStyle = 'rgba(255,0,0, 0.9)';
+        ctx.fillStyle = 'rgba(255,0,0, 0.1)';
+        ctx.lineWidth = 3;
+        console.log("scaling set  x: " + x_scale + " by y:" + y_scale);
+        $("#selector-current-xpath").css('max-width', selector_image_rect.width);
     }
 
     function reflow_selector() {
-        $(window).resize(function() {
+        $(window).resize(function () {
             set_scale();
             highlight_current_selected_i();
         });
-      var selector_currnt_xpath_text=$("#selector-current-xpath span");
+        var selector_currnt_xpath_text = $("#selector-current-xpath span");
 
-      set_scale();
+        set_scale();
 
-      console.log(selector_data['size_pos'].length + " selectors found");
+        console.log(selector_data['size_pos'].length + " selectors found");
 
-      // highlight the default one if we can find it in the xPath list
-      // or the xpath matches the default one
-      found = false;
-      if(current_default_xpath.length) {
-          for (var i = selector_data['size_pos'].length; i!==0; i--) {
-            var sel = selector_data['size_pos'][i-1];
-            if(selector_data['size_pos'][i - 1].xpath == current_default_xpath) {
-            console.log("highlighting "+current_default_xpath);
-              current_selected_i = i-1;
-              highlight_current_selected_i();
-              found = true;
-              break;
+        // highlight the default one if we can find it in the xPath list
+        // or the xpath matches the default one
+        found = false;
+        if (current_default_xpath.length) {
+            // Find the first one that matches
+            // @todo In the future paint all that match
+            for (const c of current_default_xpath) {
+                for (var i = selector_data['size_pos'].length; i !== 0; i--) {
+                    if (selector_data['size_pos'][i - 1].xpath === c) {
+                        console.log("highlighting " + c);
+                        current_selected_i = i - 1;
+                        highlight_current_selected_i();
+                        found = true;
+                        break;
+                    }
+                }
+                if (found) {
+                    break;
+                }
+            }
+            if (!found) {
+                alert("Unfortunately your existing CSS/xPath Filter was no longer found!");
             }
-          }
-        if(!found) {
-          alert("Unfortunately your existing CSS/xPath Filter was no longer found!");
-        }
-      }
-
-
-      $('#selector-canvas').bind('mousemove', function (e) {
-        if(state_clicked) {
-          return;
-        }
-        ctx.clearRect(0, 0, c.width, c.height);
-        current_selected_i=null;
-
-        // Add in offset
-        if ((typeof e.offsetX === "undefined" || typeof e.offsetY === "undefined") || (e.offsetX === 0 && e.offsetY === 0)) {
-          var targetOffset = $(e.target).offset();
-          e.offsetX = e.pageX - targetOffset.left;
-          e.offsetY = e.pageY - targetOffset.top;
         }
 
-        // Reverse order - the most specific one should be deeper/"laster"
-        // Basically, find the most 'deepest'
-        var found=0;
-        ctx.fillStyle = 'rgba(205,0,0,0.35)';
-        for (var i = selector_data['size_pos'].length; i!==0; i--) {
-          // draw all of them? let them choose somehow?
-          var sel = selector_data['size_pos'][i-1];
-          // If we are in a bounding-box
-          if (e.offsetY > sel.top * y_scale && e.offsetY < sel.top * y_scale + sel.height * y_scale
-              &&
-              e.offsetX > sel.left * y_scale && e.offsetX < sel.left * y_scale + sel.width * y_scale
 
-          ) {
+        $('#selector-canvas').bind('mousemove', function (e) {
+            if (state_clicked) {
+                return;
+            }
+            ctx.clearRect(0, 0, c.width, c.height);
+            current_selected_i = null;
 
-            // FOUND ONE
+            // Add in offset
+            if ((typeof e.offsetX === "undefined" || typeof e.offsetY === "undefined") || (e.offsetX === 0 && e.offsetY === 0)) {
+                var targetOffset = $(e.target).offset();
+                e.offsetX = e.pageX - targetOffset.left;
+                e.offsetY = e.pageY - targetOffset.top;
+            }
+
+            // Reverse order - the most specific one should be deeper/"laster"
+            // Basically, find the most 'deepest'
+            var found = 0;
+            ctx.fillStyle = 'rgba(205,0,0,0.35)';
+            // Will be sorted by smallest width*height first
+            for (var i = 0; i <= selector_data['size_pos'].length; i++) {
+                // draw all of them? let them choose somehow?
+                var sel = selector_data['size_pos'][i];
+                // If we are in a bounding-box
+                if (e.offsetY > sel.top * y_scale && e.offsetY < sel.top * y_scale + sel.height * y_scale
+                    &&
+                    e.offsetX > sel.left * y_scale && e.offsetX < sel.left * y_scale + sel.width * y_scale
+
+                ) {
+
+                    // FOUND ONE
+                    set_current_selected_text(sel.xpath);
+                    ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+                    ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+
+                    // no need to keep digging
+                    // @todo or, O to go out/up, I to go in
+                    // or double click to go up/out the selector?
+                    current_selected_i = i;
+                    found += 1;
+                    break;
+                }
+            }
+
+        }.debounce(5));
+
+        function set_current_selected_text(s) {
+            selector_currnt_xpath_text[0].innerHTML = s;
+        }
+
+        function highlight_current_selected_i() {
+            if (state_clicked) {
+                state_clicked = false;
+                xctx.clearRect(0, 0, c.width, c.height);
+                return;
+            }
+
+            var sel = selector_data['size_pos'][current_selected_i];
+            if (sel[0] == '/') {
+                // @todo - not sure just checking / is right
+                $("#include_filters").val('xpath:' + sel.xpath);
+            } else {
+                $("#include_filters").val(sel.xpath);
+            }
+            xctx.fillStyle = 'rgba(205,205,205,0.95)';
+            xctx.strokeStyle = 'rgba(225,0,0,0.9)';
+            xctx.lineWidth = 3;
+            xctx.fillRect(0, 0, c.width, c.height);
+            // Clear out what only should be seen (make a clear/clean spot)
+            xctx.clearRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+            xctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+            state_clicked = true;
             set_current_selected_text(sel.xpath);
-            ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-            ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
 
-            // no need to keep digging
-            // @todo or, O to go out/up, I to go in
-            // or double click to go up/out the selector?
-            current_selected_i=i-1;
-            found+=1;
-            break;
-          }
         }
 
-      }.debounce(5));
 
-      function set_current_selected_text(s) {
-        selector_currnt_xpath_text[0].innerHTML=s;
-      }
-
-      function highlight_current_selected_i() {
-        if(state_clicked) {
-          state_clicked=false;
-          xctx.clearRect(0,0,c.width, c.height);
-          return;
-        }
-
-        var sel = selector_data['size_pos'][current_selected_i];
-        if (sel[0] == '/') {
-        // @todo - not sure just checking / is right
-            $("#css_filter").val('xpath:'+sel.xpath);
-        } else {
-            $("#css_filter").val(sel.xpath);
-        }
-        xctx.fillStyle = 'rgba(205,205,205,0.95)';
-        xctx.strokeStyle = 'rgba(225,0,0,0.9)';
-        xctx.lineWidth = 3;
-        xctx.fillRect(0,0,c.width, c.height);
-        // Clear out what only should be seen (make a clear/clean spot)
-        xctx.clearRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-        xctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-        state_clicked=true;
-        set_current_selected_text(sel.xpath);
-
-      }
-
-
-      $('#selector-canvas').bind('mousedown', function (e) {
-        highlight_current_selected_i();
-      });
+        $('#selector-canvas').bind('mousedown', function (e) {
+            highlight_current_selected_i();
+        });
     }
 
-});
+});

changedetectionio/static/js/watch-overview.js

@@ -1,31 +1,45 @@
 $(function () {
-  // Remove unviewed status when normally clicked
-  $('.diff-link').click(function () {
-    $(this).closest('.unviewed').removeClass('unviewed');
-  });
+    // Remove unviewed status when normally clicked
+    $('.diff-link').click(function () {
+        $(this).closest('.unviewed').removeClass('unviewed');
+    });
 
+    $("#checkbox-assign-tag").click(function (e) {
+        $('#op_extradata').val(prompt("Enter a tag name"));
+    });
 
-  $('.with-share-link > *').click(function () {
-      $("#copied-clipboard").remove();
+    $('.with-share-link > *').click(function () {
+        $("#copied-clipboard").remove();
 
-      var range = document.createRange();
-      var n=$("#share-link")[0];
-      range.selectNode(n);
-      window.getSelection().removeAllRanges();
-      window.getSelection().addRange(range);
-      document.execCommand("copy");
-      window.getSelection().removeAllRanges();
+        var range = document.createRange();
+        var n = $("#share-link")[0];
+        range.selectNode(n);
+        window.getSelection().removeAllRanges();
+        window.getSelection().addRange(range);
+        document.execCommand("copy");
+        window.getSelection().removeAllRanges();
 
-      $('.with-share-link').append('<span style="font-size: 80%; color: #fff;" id="copied-clipboard">Copied to clipboard</span>');
-      $("#copied-clipboard").fadeOut(2500, function() {
-       $(this).remove();
-      });
-  });
+        $('.with-share-link').append('<span style="font-size: 80%; color: #fff;" id="copied-clipboard">Copied to clipboard</span>');
+        $("#copied-clipboard").fadeOut(2500, function () {
+            $(this).remove();
+        });
+    });
+
+    $(".watch-table tr").click(function (event) {
+        var tagName = event.target.tagName.toLowerCase();
+        if (tagName === 'tr' || tagName === 'td') {
+            var x = $('input[type=checkbox]', this);
+            if (x) {
+                $(x).click();
+            }
+        }
+    });
 
     // checkboxes - check all
     $("#check-all").click(function (e) {
         $('input[type=checkbox]').not(this).prop('checked', this.checked);
     });
+
     // checkboxes - show/hide buttons
     $("input[type=checkbox]").click(function (e) {
         if ($('input[type=checkbox]:checked').length) {

changedetectionio/static/js/watch-settings.js

@@ -1,7 +1,7 @@
-$(document).ready(function() {
+$(document).ready(function () {
     function toggle() {
         if ($('input[name="fetch_backend"]:checked').val() == 'html_webdriver') {
-            if(playwright_enabled) {
+            if (playwright_enabled) {
                 // playwright supports headers, so hide everything else
                 // See #664
                 $('#requests-override-options #request-method').hide();
@@ -14,9 +14,14 @@ $(document).ready(function() {
                 $('#requests-override-options').hide();
             }
 
-
             $('#webdriver-override-options').show();
 
+        } else if ($('input[name="fetch_backend"]:checked').val() == 'system') {
+            $('#requests-override-options #request-method').hide();
+            $('#requests-override-options #request-body').hide();
+            $('#ignore-status-codes-option').hide();
+            $('#requests-override-options').hide();
+            $('#webdriver-override-options').hide();
         } else {
 
             $('#requests-override-options').show();

changedetectionio/static/styles/.dockerignore

@@ -0,0 +1,3 @@
+node_modules
+package-lock.json
+

changedetectionio/static/styles/diff.css

@@ -1,10 +1,148 @@
+/**
+ * CSS custom properties (aka variables).
+ */
+:root {
+  --color-white: #fff;
+  --color-grey-50: #111;
+  --color-grey-100: #262626;
+  --color-grey-200: #333;
+  --color-grey-300: #444;
+  --color-grey-325: #555;
+  --color-grey-350: #565d64;
+  --color-grey-400: #666;
+  --color-grey-500: #777;
+  --color-grey-600: #999;
+  --color-grey-700: #cbcbcb;
+  --color-grey-750: #ddd;
+  --color-grey-800: #e0e0e0;
+  --color-grey-850: #eee;
+  --color-grey-900: #f2f2f2;
+  --color-black: #000;
+  --color-dark-red: #a00;
+  --color-light-red: #dd0000;
+  --color-background-page: var(--color-grey-100);
+  --color-background-gradient-first: #5ad8f7;
+  --color-background-gradient-second: #2f50af;
+  --color-background-gradient-third: #9150bf;
+  --color-background: var(--color-white);
+  --color-text: var(--color-grey-200);
+  --color-link: #1b98f8;
+  --color-menu-accent: #ed5900;
+  --color-background-code: var(--color-grey-850);
+  --color-error: var(--color-dark-red);
+  --color-error-input: #ffebeb;
+  --color-error-list: var(--color-light-red);
+  --color-table-background: var(--color-background);
+  --color-table-stripe: var(--color-grey-900);
+  --color-text-tab: var(--color-white);
+  --color-background-tab: rgba(255, 255, 255, 0.2);
+  --color-background-tab-hover: rgba(255, 255, 255, 0.5);
+  --color-text-tab-active: #222;
+  --color-api-key: #0078e7;
+  --color-background-button-primary: #0078e7;
+  --color-background-button-green: #42dd53;
+  --color-background-button-red: #dd4242;
+  --color-background-button-success: rgb(28, 184, 65);
+  --color-background-button-error: rgb(202, 60, 60);
+  --color-text-button-error: var(--color-white);
+  --color-background-button-warning: rgb(202, 60, 60);
+  --color-text-button-warning: var(--color-white);
+  --color-background-button-secondary: rgb(66, 184, 221);
+  --color-background-button-cancel: rgb(200, 200, 200);
+  --color-text-button: var(--color-white);
+  --color-background-button-tag: rgb(99, 99, 99);
+  --color-background-snapshot-age: #dfdfdf;
+  --color-error-text-snapshot-age: var(--color-white);
+  --color-error-background-snapshot-age: #ff0000;
+  --color-background-button-tag-active: #9c9c9c;
+  --color-text-messages: var(--color-white);
+  --color-background-messages-message: rgba(255, 255, 255, .2);
+  --color-background-messages-error: rgba(255, 1, 1, .5);
+  --color-background-messages-notice: rgba(255, 255, 255, .5);
+  --color-border-notification: #ccc;
+  --color-background-checkbox-operations: rgba(0, 0, 0, 0.05);
+  --color-warning: #ff3300;
+  --color-border-warning: var(--color-warning);
+  --color-text-legend: var(--color-white);
+  --color-link-new-version: #e07171;
+  --color-last-checked: #bbb;
+  --color-text-footer: #444;
+  --color-border-watch-table-cell: #eee;
+  --color-text-watch-tag-list: #e70069;
+  --color-background-new-watch-form: rgba(0, 0, 0, 0.05);
+  --color-background-new-watch-input: var(--color-white);
+  --color-text-new-watch-input: var(--color-text);
+  --color-border-input: var(--color-grey-500);
+  --color-shadow-input: var(--color-grey-400);
+  --color-background-input: var(--color-white);
+  --color-text-input: var(--color-text);
+  --color-text-input-description: var(--color-grey-500);
+  --color-text-input-placeholder: var(--color-grey-600);
+  --color-background-table-thead: var(--color-grey-800);
+  --color-border-table-cell: var(--color-grey-700);
+  --color-text-menu-heading: var(--color-grey-350);
+  --color-text-menu-link: var(--color-grey-500);
+  --color-background-menu-link-hover: var(--color-grey-850);
+  --color-text-menu-link-hover: var(--color-grey-300);
+  --color-shadow-jump: var(--color-grey-500);
+  --color-icon-github: var(--color-black);
+  --color-icon-github-hover: var(--color-grey-300);
+  --color-watch-table-error: var(--color-dark-red);
+  --color-watch-table-row-text: var(--color-grey-100); }
+
+html[data-darkmode="true"] {
+  --color-link: #59bdfb;
+  --color-text: var(--color-white);
+  --color-background-gradient-first: #3f90a5;
+  --color-background-gradient-second: #1e316c;
+  --color-background-gradient-third: #4d2c64;
+  --color-background-new-watch-input: var(--color-grey-100);
+  --color-text-new-watch-input: var(--color-text);
+  --color-background-table-thead: var(--color-grey-200);
+  --color-table-background: var(--color-grey-300);
+  --color-table-stripe: var(--color-grey-325);
+  --color-background: var(--color-grey-300);
+  --color-text-menu-heading: var(--color-grey-850);
+  --color-text-menu-link: var(--color-grey-800);
+  --color-border-table-cell: var(--color-grey-400);
+  --color-text-tab-active: var(--color-text);
+  --color-border-input: var(--color-grey-400);
+  --color-shadow-input: var(--color-grey-50);
+  --color-background-input: var(--color-grey-350);
+  --color-text-input-description: var(--color-grey-600);
+  --color-text-input-placeholder: var(--color-grey-600);
+  --color-text-watch-tag-list: #fa3e92;
+  --color-background-code: var(--color-grey-200);
+  --color-background-tab: rgba(0, 0, 0, 0.2);
+  --color-background-tab-hover: rgba(0, 0, 0, 0.5);
+  --color-background-snapshot-age: var(--color-grey-200);
+  --color-shadow-jump: var(--color-grey-200);
+  --color-icon-github: var(--color-white);
+  --color-icon-github-hover: var(--color-grey-700);
+  --color-watch-table-error: var(--color-light-red);
+  --color-watch-table-row-text: var(--color-grey-800); }
+  html[data-darkmode="true"] .icon-spread {
+    filter: hue-rotate(-10deg) brightness(1.5); }
+  html[data-darkmode="true"] .watch-table .title-col a[target="_blank"]::after,
+  html[data-darkmode="true"] .watch-table .current-diff-url::after {
+    filter: invert(0.5) hue-rotate(10deg) brightness(2); }
+  html[data-darkmode="true"] .watch-table .watch-controls .state-off img {
+    opacity: 0.3; }
+  html[data-darkmode="true"] .watch-table .watch-controls .state-on img {
+    opacity: 1.0; }
+  html[data-darkmode="true"] .watch-table .unviewed {
+    color: #fff; }
+    html[data-darkmode="true"] .watch-table .unviewed.error {
+      color: var(--color-watch-table-error); }
+
 #diff-ui {
-  background: #fff;
+  background: var(--color-background);
   padding: 2em;
   margin-left: 1em;
   margin-right: 1em;
-  border-radius: 5px;
-  font-size: 11px; }
+  border-radius: 5px; }
+  #diff-ui #text {
+    font-size: 11px; }
   #diff-ui table {
     table-layout: fixed;
     width: 100%; }
@@ -45,6 +183,10 @@ ins {
     margin-left: 1em;
     display: inline-block;
     font-weight: normal; }
+  #settings del {
+    padding: 0.5em; }
+  #settings ins {
+    padding: 0.5em; }
 
 .source {
   position: absolute;
@@ -76,3 +218,10 @@ td#diff-col div {
   text-align: center; }
   .tab-pane-inner#screenshot img {
     max-width: 99%; }
+
+#highlightSnippet {
+  background: var(--color-background);
+  padding: 1em;
+  border-radius: 5px;
+  background: var(--color-background);
+  box-shadow: 1px 1px 4px var(--color-shadow-jump); }

changedetectionio/static/styles/diff.scss

@@ -1,96 +0,0 @@
-#diff-ui {
-
-    background: #fff;
-    padding: 2em;
-    margin-left: 1em;
-    margin-right: 1em;
-    border-radius: 5px;
-    font-size: 11px;
-
-    table {
-        table-layout: fixed;
-        width: 100%;
-    }
-    td {
-        padding: 3px 4px;
-        border: 1px solid transparent;
-        vertical-align: top;
-        font: 1em monospace;
-        text-align: left;
-    }
-    pre {
-            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%;
-    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 */
-	}
-}
-
-td#diff-col div {
-    text-align: justify;
-    white-space: pre-wrap;
-}
-
-.ignored {
-    background-color: #ccc;
-   /*  border: #0d91fa 1px solid; */
-    opacity: 0.7;
-}
-
-.triggered {
-    background-color: #1b98f8;
-}
-
-/* ignored and triggered? make it obvious error */
-.ignored.triggered {
-  background-color: #ff0000;
-}
-
-.tab-pane-inner#screenshot {
-  text-align: center;
-  img {
-    max-width: 99%;
-  }
-}

changedetectionio/static/styles/package.json

@@ -4,7 +4,8 @@
   "description": "",
   "main": "index.js",
   "scripts": {
-    "build": "node-sass styles.scss -o .;node-sass diff.scss -o ."
+    "watch": "node-sass -w scss -o .",
+    "build": "node-sass scss -o ."
   },
   "author": "",
   "license": "ISC",

changedetectionio/static/styles/scss/diff.scss

@@ -0,0 +1,129 @@
+@import "parts/_variables.scss";
+
+#diff-ui {
+
+  background: var(--color-background);
+  padding: 2em;
+  margin-left: 1em;
+  margin-right: 1em;
+  border-radius: 5px;
+
+  // The first tab 'text' diff
+  #text {
+    font-size: 11px;
+  }
+
+  table {
+    table-layout: fixed;
+    width: 100%;
+  }
+
+  td {
+    padding: 3px 4px;
+    border: 1px solid transparent;
+    vertical-align: top;
+    font: 1em monospace;
+    text-align: left;
+  }
+
+  pre {
+    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;
+
+  .change {
+    span {}
+  }
+}
+
+#settings {
+  background: rgba(0, 0, 0, .05);
+  padding: 1em;
+  border-radius: 10px;
+  margin-bottom: 1em;
+  color: #fff;
+  font-size: 80%;
+
+  label {
+    margin-left: 1em;
+    display: inline-block;
+    font-weight: normal;
+  }
+
+  del {
+    padding: 0.5em;
+  }
+
+  ins {
+    padding: 0.5em;
+  }
+}
+
+.source {
+  position: absolute;
+  right: 1%;
+  top: .2em;
+}
+
+@-moz-document url-prefix() {
+  body {
+    height: 99%;
+    /* Hide scroll bar in Firefox */
+  }
+}
+
+td#diff-col div {
+  text-align: justify;
+  white-space: pre-wrap;
+}
+
+.ignored {
+  background-color: #ccc;
+  /*  border: #0d91fa 1px solid; */
+  opacity: 0.7;
+}
+
+.triggered {
+  background-color: #1b98f8;
+}
+
+/* ignored and triggered? make it obvious error */
+.ignored.triggered {
+  background-color: #ff0000;
+}
+
+.tab-pane-inner#screenshot {
+  text-align: center;
+
+  img {
+    max-width: 99%;
+  }
+}
+
+#highlightSnippet {
+  background: var(--color-background);
+  padding: 1em;
+  border-radius: 5px;
+  background: var(--color-background);
+  box-shadow: 1px 1px 4px var(--color-shadow-jump);
+}

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

@@ -0,0 +1,95 @@
+
+#browser_steps {
+  /* convert rows to horizontal cells */
+  th {
+    display: none;
+  }
+
+  li {
+    &:not(:first-child) {
+      &:hover {
+        opacity: 1.0;
+      }
+    }
+    list-style: decimal;
+    padding: 5px;
+    .control {
+      padding-left: 5px;
+      padding-right: 5px;
+      a {
+        font-size: 70%;
+      }
+    }
+    &.empty {
+      padding: 0px;
+      opacity: 0.35;
+      .control {
+        display: none;
+      }
+    }
+    &:hover {
+      background: #eee;
+    }
+    > label {
+      display: none;
+    }
+  }
+}
+
+#browser-steps-fieldlist {
+  height: 100%;
+  overflow-y: scroll;
+}
+
+#browser-steps .flex-wrapper {
+  display: flex;
+  flex-flow: row;
+  height: 600px; /*@todo make this dynamic */
+}
+
+/*  this is duplicate :( */
+#browsersteps-selector-wrapper {
+  height: 100%;
+  width: 100%;
+  overflow-y: scroll;
+  position: relative;
+  //width: 100%;
+  > img {
+    position: absolute;
+    max-width: 100%;
+  }
+
+  > canvas {
+    position: relative;
+    max-width: 100%;
+
+    &:hover {
+      cursor: pointer;
+    }
+  }
+
+  .loader {
+    position: absolute;
+    left: 50%;
+    top: 50%;
+    transform: translate(-50%, -50%);
+    margin-left: -40px;
+    z-index: 100;
+    max-width: 350px;
+    text-align: center;
+  }
+
+  /* nice tall skinny one */
+  .spinner, .spinner:after {
+    width: 80px;
+    height: 80px;
+    font-size: 3px;
+  }
+
+  #browsersteps-click-start {
+    &:hover {
+      cursor: pointer;
+    }
+    color: var(--color-grey-400);
+  }
+}

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

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

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

@@ -0,0 +1,45 @@
+ul#requests-extra_proxies {
+  list-style: none;
+  /* tidy up the table to look more "inline" */
+  li {
+    > label {
+      display: none;
+    }
+
+  }
+
+  /* each proxy entry is a `table` */
+  table {
+    tr {
+      display: inline;
+    }
+  }
+}
+
+#request {
+  /* Auto proxy scan/checker */
+  label[for=proxy] {
+    display: inline-block;
+  }
+}
+
+body.proxy-check-active {
+  #request {
+    .proxy-status {
+      width: 2em;
+    }
+
+    .proxy-check-details {
+      font-size: 80%;
+      color: #555;
+      display: block;
+      padding-left: 4em;
+    }
+
+    .proxy-timing {
+      font-size: 80%;
+      padding-left: 1rem;
+      color: var(--color-link);
+    }
+  }
+}

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

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

changedetectionio/static/styles/scss/parts/_spinners.scss

@@ -0,0 +1,44 @@
+
+/* spinner */
+.spinner,
+.spinner:after {
+  border-radius: 50%;
+  width: 10px;
+  height: 10px;
+}
+.spinner {
+  margin: 0px auto;
+  font-size: 3px;
+  vertical-align: middle;
+  display: inline-block;
+  text-indent: -9999em;
+  border-top: 1.1em solid rgba(38,104,237, 0.2);
+  border-right: 1.1em solid rgba(38,104,237, 0.2);
+  border-bottom: 1.1em solid rgba(38,104,237, 0.2);
+  border-left: 1.1em solid #2668ed;
+  -webkit-transform: translateZ(0);
+  -ms-transform: translateZ(0);
+  transform: translateZ(0);
+  -webkit-animation: load8 1.1s infinite linear;
+  animation: load8 1.1s infinite linear;
+}
+@-webkit-keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg);
+  }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg);
+  }
+}
+@keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg);
+  }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg);
+  }
+}

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

@@ -0,0 +1,175 @@
+/**
+ * CSS custom properties (aka variables).
+ */
+
+:root {
+  --color-white: #fff;
+  --color-grey-50: #111;
+  --color-grey-100: #262626;
+  --color-grey-200: #333;
+  --color-grey-300: #444;
+  --color-grey-325: #555;
+  --color-grey-350: #565d64;
+  --color-grey-400: #666;
+  --color-grey-500: #777;
+  --color-grey-600: #999;
+  --color-grey-700: #cbcbcb;
+  --color-grey-750: #ddd;
+  --color-grey-800: #e0e0e0;
+  --color-grey-850: #eee;
+  --color-grey-900: #f2f2f2;
+  --color-black: #000;
+  --color-dark-red: #a00;
+  --color-light-red: #dd0000;
+
+  --color-background-page: var(--color-grey-100);
+  --color-background-gradient-first: #5ad8f7;
+  --color-background-gradient-second: #2f50af;
+  --color-background-gradient-third: #9150bf;
+  --color-background: var(--color-white);
+  --color-text: var(--color-grey-200);
+  --color-link: #1b98f8;
+  --color-menu-accent: #ed5900;
+  --color-background-code: var(--color-grey-850);
+  --color-error: var(--color-dark-red);
+  --color-error-input: #ffebeb;
+  --color-error-list: var(--color-light-red);
+  --color-table-background: var(--color-background);
+  --color-table-stripe: var(--color-grey-900);
+  --color-text-tab: var(--color-white);
+  --color-background-tab: rgba(255, 255, 255, 0.2);
+  --color-background-tab-hover: rgba(255, 255, 255, 0.5);
+  --color-text-tab-active: #222;
+  --color-api-key: #0078e7;
+
+  --color-background-button-primary: #0078e7;
+  --color-background-button-green: #42dd53;
+  --color-background-button-red: #dd4242;
+  --color-background-button-success: rgb(28, 184, 65);
+  --color-background-button-error: rgb(202, 60, 60);
+  --color-text-button-error: var(--color-white);
+  --color-background-button-warning: rgb(202, 60, 60);
+  --color-text-button-warning: var(--color-white);
+  --color-background-button-secondary: rgb(66, 184, 221);
+  --color-background-button-cancel: rgb(200, 200, 200);
+  --color-text-button: var(--color-white);
+  --color-background-button-tag: rgb(99, 99, 99);
+  --color-background-snapshot-age: #dfdfdf;
+  --color-error-text-snapshot-age: var(--color-white);
+  --color-error-background-snapshot-age: #ff0000;
+  --color-background-button-tag-active: #9c9c9c;
+
+  --color-text-messages: var(--color-white);
+  --color-background-messages-message: rgba(255, 255, 255, .2);
+  --color-background-messages-error: rgba(255, 1, 1, .5);
+  --color-background-messages-notice: rgba(255, 255, 255, .5);
+  --color-border-notification: #ccc;
+
+  --color-background-checkbox-operations: rgba(0, 0, 0, 0.05);
+  --color-warning: #ff3300;
+  --color-border-warning: var(--color-warning);
+  --color-text-legend: var(--color-white);
+
+  --color-link-new-version: #e07171;
+  --color-last-checked: #bbb;
+  --color-text-footer: #444;
+  --color-border-watch-table-cell: #eee;
+
+  --color-text-watch-tag-list: #e70069;
+  --color-background-new-watch-form: rgba(0, 0, 0, 0.05);
+  --color-background-new-watch-input: var(--color-white);
+  --color-text-new-watch-input: var(--color-text);
+
+  --color-border-input: var(--color-grey-500);
+  --color-shadow-input: var(--color-grey-400);
+  --color-background-input: var(--color-white);
+  --color-text-input: var(--color-text);
+  --color-text-input-description: var(--color-grey-500);
+  --color-text-input-placeholder: var(--color-grey-600);
+
+  --color-background-table-thead: var(--color-grey-800);
+  --color-border-table-cell: var(--color-grey-700);
+
+  --color-text-menu-heading: var(--color-grey-350);
+  --color-text-menu-link: var(--color-grey-500);
+  --color-background-menu-link-hover: var(--color-grey-850);
+  --color-text-menu-link-hover: var(--color-grey-300);
+
+  --color-shadow-jump: var(--color-grey-500);
+  --color-icon-github: var(--color-black);
+  --color-icon-github-hover: var(--color-grey-300);
+
+  --color-watch-table-error: var(--color-dark-red);
+  --color-watch-table-row-text: var(--color-grey-100);
+}
+
+html[data-darkmode="true"] {
+  --color-link: #59bdfb;
+  --color-text: var(--color-white);
+
+  --color-background-gradient-first: #3f90a5;
+  --color-background-gradient-second: #1e316c;
+  --color-background-gradient-third: #4d2c64;
+
+  --color-background-new-watch-input: var(--color-grey-100);
+  --color-text-new-watch-input: var(--color-text);
+  --color-background-table-thead: var(--color-grey-200);
+  --color-table-background: var(--color-grey-300);
+  --color-table-stripe: var(--color-grey-325);
+  --color-background: var(--color-grey-300);
+  --color-text-menu-heading: var(--color-grey-850);
+  --color-text-menu-link: var(--color-grey-800);
+  --color-border-table-cell: var(--color-grey-400);
+  --color-text-tab-active: var(--color-text);
+
+  --color-border-input: var(--color-grey-400);
+  --color-shadow-input: var(--color-grey-50);
+  --color-background-input: var(--color-grey-350);
+  --color-text-input-description: var(--color-grey-600);
+  --color-text-input-placeholder: var(--color-grey-600);
+  --color-text-watch-tag-list: #fa3e92;
+  --color-background-code: var(--color-grey-200);
+
+  --color-background-tab: rgba(0, 0, 0, 0.2);
+  --color-background-tab-hover: rgba(0, 0, 0, 0.5);
+
+  --color-background-snapshot-age: var(--color-grey-200);
+  --color-shadow-jump: var(--color-grey-200);
+  --color-icon-github: var(--color-white);
+  --color-icon-github-hover: var(--color-grey-700);
+  --color-watch-table-error: var(--color-light-red);
+  --color-watch-table-row-text: var(--color-grey-800);
+
+
+  .icon-spread {
+    filter: hue-rotate(-10deg) brightness(1.5);
+  }
+
+  .watch-table {
+
+    .title-col a[target="_blank"]::after,
+    .current-diff-url::after {
+      filter: invert(.5) hue-rotate(10deg) brightness(2);
+    }
+
+    .watch-controls {
+      .state-off {
+        img {
+          opacity: 0.3;
+        }
+      }
+      .state-on {
+        img {
+          opacity: 1.0;
+        }
+      }
+    }
+
+    .unviewed {
+      color: #fff;
+      &.error {
+        color: var(--color-watch-table-error);
+      }
+    }
+  }
+}

changedetectionio/static/styles/styles.scss

@@ -1,806 +0,0 @@
-/*
- * -- BASE STYLES --
- * Most of these are inherited from Base, but I want to change a few.
- * nvm use v14.18.1 && npm install && npm run build
- * or npm run watch
- */
-@import "parts/_arrows.scss";
-
-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: 1em;
-  flex-direction: column;
-  display: flex;
-  align-items: center;
-  justify-content: center;
-}
-
-code {
-  background: #eee;
-}
-
-/* table related */
-.watch-table {
-  width: 100%;
-  font-size: 80%;
-
-  tr.unviewed {
-    font-weight: bold;
-  }
-
-  .error {
-    color: #a00;
-  }
-
-  td {
-    white-space: nowrap;
-  }
-
-  td.title-col {
-    word-break: break-all;
-    white-space: normal;
-  }
-
-  th {
-    white-space: nowrap;
-    a {
-      font-weight: normal;
-      &.active {
-        font-weight: bolder;
-      }
-      &.inactive {
-        .arrow {
-          display: none;
-        }
-      }
-    }
-  }
-
-  .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;
-  }
-}
-
-.watch-tag-list {
-  color: #e70069;
-  white-space: nowrap;
-}
-
-.box {
-  max-width: 80%;
-  flex-direction: column;
-  display: flex;
-  justify-content: center;
-}
-
-
-#post-list-buttons {
-  text-align: right;
-  padding: 0px;
-  margin: 0px;
-
-  li {
-    display: inline-block;
-  }
-
-  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, #5ad8f7, #2f50af 41.07%, #9150bf 84.05%);
-}
-
-body:after, body:before {
-  display: block;
-  height: 650px;
-  position: absolute;
-  top: 0;
-  left: 0;
-  width: 100%;
-  z-index: -1;
-}
-
-body::after {
-  opacity: 0.91;
-}
-
-body::before {
-  // background-image set in base.html so it works with reverse proxies etc
-  content: "";
-  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;
-}
-
-
-.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;
-
-  &.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 {
-    li {
-        list-style: none;
-        padding: 1em;
-        border-radius: 10px;
-        color: #fff;
-        font-weight: bold;
-        &.message {
-            background: rgba(255, 255, 255, .2);
-        }
-        &.error {
-            background: rgba(255, 1, 1, .5);
-        }
-        &.notice {
-            background: rgba(255, 255, 255, .5);
-        }
-    }
-    &.with-share-link {
-     > *:hover {
-       cursor:pointer;
-     }
-    }
-}
-
-#notification-customisation {
-    border: 1px solid #ccc;
-    padding: 0.5rem;
-    border-radius: 5px;
-}
-
-#notification-error-log {
-    border: 1px solid #ccc;
-    padding: 1rem;
-    border-radius: 5px;
-    overflow-wrap: break-word;
-}
-
-#token-table {
-    &.pure-table td, &.pure-table th {
-        font-size: 80%;
-    }
-}
-
-#new-watch-form {
-  background: rgba(0, 0, 0, .05);
-  padding: 1em;
-  border-radius: 10px;
-  margin-bottom: 1em;
-  input {
-    display: inline-block;
-    margin-bottom: 5px;
-  }
-  .label {
-    display: none;
-  }
-  legend {
-    color: #fff;
-    font-weight: bold;
-  }
-
-  #watch-add-wrapper-zone {
-    > div {
-      display: inline-block;
-    }
-    @media only screen and (max-width: 760px) {
-      #url {
-        width: 100%;
-      }
-    }
-  }
-}
-
-
-
-
-#diff-col {
-  padding-left: 40px;
-}
-
-#diff-jump {
-  position: fixed;
-  left: 0px;
-  top: 120px;
-  background: #fff;
-  padding: 10px;
-  border-top-right-radius: 5px;
-  border-bottom-right-radius: 5px;
-  box-shadow: 5px 0 5px -2px #888;
-     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;
-}
-
-#top-right-menu {
-// Just let flex overflow the x axis for now
-/*
-    position: absolute;
-    right: 0px;
-    background: linear-gradient(to right, #fff0, #fff 10%);
-    padding-left: 20px;
-    padding-right: 10px;
-    */
-}
-
-.sticky-tab {
-  position: absolute;
-  top: 60px;
-  font-size: 65%;
-  background: #fff;
-  padding: 10px;
-  &#left-sticky {
-    left: 0px;
-  }
-  &#right-sticky {
-    right: 0px;
-  }
-  &#hosted-sticky {
-    right: 0px;
-    top: 100px;
-    font-weight: bold;
-  }
-}
-
-#new-version-text a {
-  color: #e07171;
-}
-
-.watch-controls {
-  .state-on {
-    img {
-      opacity: 0.8;
-    }
-  }
-
-  /* default */
-  img {
-    opacity: 0.2;
-  }
-
-  img {
-    &:hover {
-      transition: opacity 0.3s;
-      opacity: 0.8;
-    }
-  }
-
-}
-
-.monospaced-textarea {
-    textarea {
-        width: 100%;
-        font-family: monospace;
-        white-space: pre;
-        overflow-wrap: normal;
-        overflow-x: scroll;
-    }
-}
-
-
-.pure-form {
-    fieldset {
-        padding-top: 0px;
-        ul {
-            padding-bottom: 0px;
-            margin-bottom: 0px;
-        }
-    }
-    .pure-control-group, .pure-group, .pure-controls {
-        padding-bottom: 1em;
-        div {
-            margin: 0px;
-        }
-        .checkbox {
-            > * {
-              display: inline;
-              vertical-align: middle;
-            }
-            > label {
-               padding-left: 5px;
-            }
-        }
-    }
-  /* The input fields with errors */
-  .error {
-    input {
-        background-color: #ffebeb;
-    }
-  }
-
-  /* The list of errors */
-  ul.errors {
-    padding: .5em .6em;
-    border: 1px solid #dd0000;
-    border-radius: 4px;
-    vertical-align: middle;
-    -webkit-box-sizing: border-box;
-    box-sizing: border-box;
-    li {
-        margin-left: 1em;
-        color: #dd0000;
-    }
-  }
-
-  label {
-    font-weight: bold;
-  }
-
-  textarea {
-    width: 100%;
-  }
-  .inline-radio {
-      ul {
-        margin: 0px;
-        list-style: none;
-        li {
-            > * {
-                display: inline-block;
-            }
-        }
-      }
-  }
-}
-
-@media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 1024px) {
-  .box {
-    max-width: 95%
-  }
-  .edit-form {
-    padding: 0.5em;
-    margin: 0;
-  }
-  #nav-menu {
-    overflow-x: scroll;
-  }
-}
-
-
-
-@media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 800px) {
-
-  div.sticky-tab#hosted-sticky {
-    top: 60px;
-    left: 0px;
-    right: auto;
-  }
-
-  section.content {
-    padding-top: 110px;
-  }
-
-  // Make the tabs easier to hit, they will be all nice and horizontal
-  div.tabs.collapsable ul li {
-    display: block;
-    border-radius: 0px;
-    margin-right: 0px;
-  }
-
-  input[type='text'] {
-    width: 100%;
-  }
-
-/*
-Max width before this PARTICULAR table gets nasty
-This query will take effect for any screen smaller than 760px
-and also iPads specifically.
-*/
-  .watch-table {
-    /* Force table to not be like tables anymore */
-    thead, tbody, th, td, tr {
-      display: block;
-    }
-
-    .last-checked {
-      > span {
-        vertical-align: middle;
-      }
-    }
-
-    .last-checked::before {
-      color: #555;
-      content: "Last Checked ";
-    }
-
-    .last-changed::before {
-      color: #555;
-      content: "Last Changed ";
-    }
-
-    /* Force table to not be like tables anymore */
-    td.inline {
-      display: inline-block;
-    }
-
-    /* Hide table headers (but not display: none;, for accessibility) */
-    thead tr {
-      position: absolute;
-      top: -9999px;
-      left: -9999px;
-    }
-
-    .pure-table td, .pure-table th {
-      border: none;
-    }
-
-    td {
-      /* Behave  like a "row" */
-      border: none;
-      border-bottom: 1px solid #eee;
-      vertical-align: middle;
-      &:before {
-        /* Top/left values mimic padding */
-        top: 6px;
-        left: 6px;
-        width: 45%;
-        padding-right: 10px;
-        white-space: nowrap;
-      }
-    }
-
-    &.pure-table-striped {
-      tr {
-        background-color: #fff;
-      }
-
-      tr:nth-child(2n-1) {
-        background-color: #eee;
-      }
-
-      tr:nth-child(2n-1) td {
-        background-color: inherit;
-      }
-    }
-
-  }
-}
-
-
-/** Desktop vs mobile input field strategy
-- We dont use 'size' with <input> because `size` is too unreliable to override, and will often push-out
-- Rely always on width in CSS
-*/
-@media only screen and (min-width: 761px) {
-/* m-d is medium-desktop */
-    .m-d {
-        min-width: 80%;
-    }
-}
-
-
-
-.tabs {
-  ul {
-    margin: 0px;
-    padding: 0px;
-    display:block;
-    li {
-      margin-right: 3px;
-      display: inline-block;
-      color: #fff;
-      border-top-left-radius: 5px;
-      border-top-right-radius: 5px;
-      background-color: rgba(255, 255, 255, 0.2);
-
-      &.active,:target {
-        background-color: #fff;
-        a {
-          color: #222;
-          font-weight: bold;
-        }
-      }
-      a {
-        display: block;
-        padding: 0.8em;
-        color: #fff;
-      }
-    }
-  }
-}
-
-$form-edge-padding: 20px;
-.pure-form-stacked {
-  >div:first-child {
-    display: block;
-  }
-}
-
-.login-form {
-  .inner {
-    background: #fff;;
-    padding: $form-edge-padding;
-    border-radius: 5px;
-  }
-}
-
-.tab-pane-inner {
-    &:not(:target) {
-        display: none;
-    }
-    &:target {
-      display: block;
-    }
-    // doesnt need padding because theres another row of buttons/activity
-    padding: 0px;
-}
-
-#beta-logo {
-    height: 50px;
-    // looks better when it's hanging off a little
-    right: -3px;
-    top: -3px;
-    position: absolute;
-}
-
-#selector-header {
-    padding-bottom: 1em;
-}
-
-.edit-form {
-  min-width: 70%;
-  /* so it cant overflow */
-  max-width: 95%;
-  .box-wrap {
-    position: relative;
-  }
-  .inner {
-    background: #fff;;
-    padding: $form-edge-padding;
-  }
-  #actions {
-    display: block;
-    background: #fff;
-  }
-
-  .pure-form-message-inline {
-    padding-left: 0;
-  }
-}
-
-ul {
-    padding-left: 1em;
-    padding-top: 0px;
-    margin-top: 4px;
-}
-
-.time-check-widget {
-    tr {
-        display: inline;
-        input[type="number"] {
-            width: 5em;
-        }
-    }
-}
-
-#selector-wrapper {
- height: 600px;
- overflow-y: scroll;
- position: relative;
-    //width: 100%;
- > img {
-    position: absolute;
-    z-index: 4;
-    max-width: 100%;
- }
- >canvas {
-    position: relative;
-    z-index: 5;
-     max-width: 100%;
-     &:hover {
-     cursor: pointer;
-     }
- }
-}
-
-#selector-current-xpath {
-  font-size: 80%;
-}
-
-#webdriver-override-options {
-        input[type="number"] {
-            width: 5em;
-        }
-}
-
-#api-key {
-  &:hover {
-    cursor: pointer;
-  }
-}
-
-#api-key-copy {
-  color: #0078e7;
-}
-
-/* spinner */
-.loader,
-.loader:after {
-  border-radius: 50%;
-  width: 10px;
-  height: 10px;
-}
-.loader {
-  margin: 0px auto;
-  font-size: 3px;
-  vertical-align: middle;
-  display: inline-block;
-  text-indent: -9999em;
-  border-top: 1.1em solid rgba(38,104,237, 0.2);
-  border-right: 1.1em solid rgba(38,104,237, 0.2);
-  border-bottom: 1.1em solid rgba(38,104,237, 0.2);
-  border-left: 1.1em solid #2668ed;
-  -webkit-transform: translateZ(0);
-  -ms-transform: translateZ(0);
-  transform: translateZ(0);
-  -webkit-animation: load8 1.1s infinite linear;
-  animation: load8 1.1s infinite linear;
-}
-@-webkit-keyframes load8 {
-  0% {
-    -webkit-transform: rotate(0deg);
-    transform: rotate(0deg);
-  }
-  100% {
-    -webkit-transform: rotate(360deg);
-    transform: rotate(360deg);
-  }
-}
-@keyframes load8 {
-  0% {
-    -webkit-transform: rotate(0deg);
-    transform: rotate(0deg);
-  }
-  100% {
-    -webkit-transform: rotate(360deg);
-    transform: rotate(360deg);
-  }
-}
-
-.snapshot-age {
-  padding: 4px;
-  background-color: #dfdfdf;
-  border-radius: 3px;
-  font-weight: bold;
-  margin-bottom: 4px;
-  &.error {
-    background-color: #ff0000;
-    color: #fff;
-  }
-}
-
-#checkbox-operations {
-  background: rgba(0, 0, 0, 0.05);
-  padding: 1em;
-  border-radius: 10px;
-  margin-bottom: 1em;
-  display: none;
-}
-.checkbox-uuid {
-  > * {
-    vertical-align: middle;
-  }
-}
-
-.inline-warning {
-  > span {
-    display: inline-block;
-    vertical-align: middle;
-  }
-
-  img.inline-warning-icon {
-    display: inline;
-    height: 26px;
-    vertical-align: middle;
-  }
-
-  border: 1px solid #ff3300;
-  padding: 0.5rem;
-  border-radius: 5px;
-  color: #ff3300;
-}

changedetectionio/store.py

@@ -1,20 +1,22 @@
 from flask import (
     flash
 )
+
+from . model import App, Watch
+from copy import deepcopy, copy
+from os import path, unlink
+from threading import Lock
 import json
 import logging
 import os
-import threading
-import time
-import uuid as uuid_builder
-from copy import deepcopy
-from os import path, unlink
-from threading import Lock
 import re
 import requests
 import secrets
+import threading
+import time
+import uuid as uuid_builder
 
-from . model import App, Watch
+dictfilt = lambda x, y: dict([ (i,x[i]) for i in x if i in set(y) ])
 
 # Is there an existing library to ensure some data store (JSON etc) is in sync with CRUD methods?
 # Open a github issue if you know something :)
@@ -27,6 +29,8 @@ class ChangeDetectionStore:
     # For when we edit, we should write to disk
     needs_write_urgent = False
 
+    __version_check = True
+
     def __init__(self, datastore_path="/datastore", include_default_watches=True, version_tag="0.0.0"):
         # Should only be active for docker
         # logging.basicConfig(filename='/dev/stdout', level=logging.INFO)
@@ -34,10 +38,8 @@ class ChangeDetectionStore:
         self.datastore_path = datastore_path
         self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
         self.needs_write = False
-        self.proxy_list = None
         self.start_time = time.time()
         self.stop_thread = False
-
         # Base definition for all watchers
         # deepcopy part of #569 - not sure why its needed exactly
         self.generic_definition = deepcopy(Watch.model(datastore_path = datastore_path, default={}))
@@ -77,15 +79,22 @@ class ChangeDetectionStore:
                     self.__data['watching'][uuid] = Watch.model(datastore_path=self.datastore_path, default=watch)
                     print("Watching:", uuid, self.__data['watching'][uuid]['url'])
 
-        # First time ran, doesnt exist.
-        except (FileNotFoundError, json.decoder.JSONDecodeError):
+        # First time ran, Create the datastore.
+        except (FileNotFoundError):
             if include_default_watches:
-                print("Creating JSON store at", self.datastore_path)
-                self.add_watch(url='https://news.ycombinator.com/', tag='Tech news')
-                self.add_watch(url='https://changedetection.io/CHANGELOG.txt', tag='changedetection.io')
+                print("No JSON DB found at {}, creating JSON store at {}".format(self.json_store_path, self.datastore_path))
+                self.add_watch(url='https://news.ycombinator.com/',
+                               tag='Tech news',
+                               extras={'fetch_backend': 'html_requests'})
 
+                self.add_watch(url='https://changedetection.io/CHANGELOG.txt',
+                               tag='changedetection.io',
+                               extras={'fetch_backend': 'html_requests'})
         self.__data['version_tag'] = version_tag
 
+        # Just to test that proxies.json if it exists, doesnt throw a parsing error on startup
+        test_list = self.proxy_list
+
         # Helper to remove password protection
         password_reset_lockfile = "{}/removepassword.lock".format(self.datastore_path)
         if path.isfile(password_reset_lockfile):
@@ -110,11 +119,6 @@ class ChangeDetectionStore:
             secret = secrets.token_hex(16)
             self.__data['settings']['application']['api_access_token'] = secret
 
-        # Proxy list support - available as a selection in settings when text file is imported
-        proxy_list_file = "{}/proxies.json".format(self.datastore_path)
-        if path.isfile(proxy_list_file):
-            self.import_proxy_list(proxy_list_file)
-
         # Bump the update version by running updates
         self.run_updates()
 
@@ -169,14 +173,6 @@ class ChangeDetectionStore:
 
     @property
     def data(self):
-        has_unviewed = False
-        for uuid, watch in self.__data['watching'].items():
-            # #106 - Be sure this is None on empty string, False, None, etc
-            # Default var for fetch_backend
-            # @todo this may not be needed anymore, or could be easily removed
-            if not self.__data['watching'][uuid]['fetch_backend']:
-                self.__data['watching'][uuid]['fetch_backend'] = self.__data['settings']['application']['fetch_backend']
-
         # Re #152, Return env base_url if not overriden, @todo also prefer the proxy pass url
         env_base_url = os.getenv('BASE_URL','')
         if not self.__data['settings']['application']['base_url']:
@@ -184,51 +180,34 @@ class ChangeDetectionStore:
 
         return self.__data
 
-    def get_all_tags(self):
-        tags = []
-        for uuid, watch in self.data['watching'].items():
-            if watch['tag'] is None:
-                continue
-            # Support for comma separated list of tags.
-            for tag in watch['tag'].split(','):
-                tag = tag.strip()
-                if tag not in tags:
-                    tags.append(tag)
-
-        tags.sort()
-        return tags
-
-    def unlink_history_file(self, path):
-        try:
-            unlink(path)
-        except (FileNotFoundError, IOError):
-            pass
-
     # Delete a single watch by UUID
     def delete(self, uuid):
+        import pathlib
+        import shutil
+
         with self.lock:
             if uuid == 'all':
                 self.__data['watching'] = {}
 
                 # GitHub #30 also delete history records
                 for uuid in self.data['watching']:
-                    for path in self.data['watching'][uuid].history.values():
-                        self.unlink_history_file(path)
+                    path = pathlib.Path(os.path.join(self.datastore_path, uuid))
+                    if os.path.exists(path):
+                        shutil.rmtree(path)
 
             else:
-                for path in self.data['watching'][uuid].history.values():
-                    self.unlink_history_file(path)
-
+                path = pathlib.Path(os.path.join(self.datastore_path, uuid))
+                if os.path.exists(path):
+                    shutil.rmtree(path)
                 del self.data['watching'][uuid]
 
-            self.needs_write_urgent = True
+        self.needs_write_urgent = True
 
     # Clone a watch by UUID
     def clone(self, uuid):
-        url = self.data['watching'][uuid]['url']
-        tag = self.data['watching'][uuid]['tag']
+        url = self.data['watching'][uuid].get('url')
         extras = self.data['watching'][uuid]
-        new_uuid = self.add_watch(url=url, tag=tag, extras=extras)
+        new_uuid = self.add_watch(url=url, extras=extras)
         return new_uuid
 
     def url_exists(self, url):
@@ -244,12 +223,15 @@ class ChangeDetectionStore:
     def clear_watch_history(self, uuid):
         import pathlib
 
-        self.__data['watching'][uuid].update(
-            {'last_checked': 0,
-             'last_viewed': 0,
-             'previous_md5': False,
-             'last_notification_error': False,
-             'last_error': False})
+        self.__data['watching'][uuid].update({
+                'last_checked': 0,
+                'has_ldjson_price_data': None,
+                'last_error': False,
+                'last_notification_error': False,
+                'last_viewed': 0,
+                'previous_md5': False,
+                'track_ldjson_price_data': None,
+            })
 
         # JSON Data, Screenshots, Textfiles (history index and snapshots), HTML in the future etc
         for item in pathlib.Path(os.path.join(self.datastore_path, uuid)).rglob("*.*"):
@@ -260,16 +242,14 @@ class ChangeDetectionStore:
 
         self.needs_write_urgent = True
 
-    def add_watch(self, url, tag="", extras=None, write_to_disk_now=True):
+    def add_watch(self, url, tag='', extras=None, tag_uuids=None, write_to_disk_now=True):
 
         if extras is None:
             extras = {}
-        # should always be str
-        if tag is None or not tag:
-            tag=''
 
         # Incase these are copied across, assume it's a reference and deepcopy()
         apply_extras = deepcopy(extras)
+        apply_extras['tags'] = [] if not apply_extras.get('tags') else apply_extras.get('tags')
 
         # Was it a share link? try to fetch the data
         if (url.startswith("https://changedetection.io/share/")):
@@ -281,45 +261,78 @@ class ChangeDetectionStore:
                 res = r.json()
 
                 # List of permissible attributes we accept from the wild internet
-                for k in ['url', 'tag',
-                          'paused', 'title',
-                          'previous_md5', 'headers',
-                          'body', 'method',
-                          'ignore_text', 'css_filter',
-                          'subtractive_selectors', 'trigger_text',
-                          'extract_title_as_title', 'extract_text',
-                          'text_should_not_be_present',
-                          'webdriver_js_execute_code']:
+                for k in [
+                    'body',
+                    'browser_steps',
+                    'css_filter',
+                    'extract_text',
+                    'extract_title_as_title',
+                    'headers',
+                    'ignore_text',
+                    'include_filters',
+                    'method',
+                    'paused',
+                    'previous_md5',
+                    'processor',
+                    'subtractive_selectors',
+                    'tag',
+                    'tags',
+                    'text_should_not_be_present',
+                    'title',
+                    'trigger_text',
+                    'url',
+                    'webdriver_js_execute_code',
+                ]:
                     if res.get(k):
-                        apply_extras[k] = res[k]
+                        if k != 'css_filter':
+                            apply_extras[k] = res[k]
+                        else:
+                            # We renamed the field and made it a list
+                            apply_extras['include_filters'] = [res['css_filter']]
 
             except Exception as e:
                 logging.error("Error fetching metadata for shared watch link", url, str(e))
                 flash("Error fetching metadata for {}".format(url), 'error')
                 return False
+        from .model.Watch import is_safe_url
+        if not is_safe_url(url):
+            flash('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX', 'error')
+            return None
 
-        with self.lock:
+        if tag and type(tag) == str:
+            # Then it's probably a string of the actual tag by name, split and add it
+            for t in tag.split(','):
+                # for each stripped tag, add tag as UUID
+                for a_t in t.split(','):
+                    tag_uuid = self.add_tag(a_t)
+                    apply_extras['tags'].append(tag_uuid)
 
-            # #Re 569
-            new_watch = Watch.model(datastore_path=self.datastore_path, default={
-                'url': url,
-                'tag': tag
-            })
+        # Or if UUIDs given directly
+        if tag_uuids:
+            apply_extras['tags'] = list(set(apply_extras['tags'] + tag_uuids))
 
-            new_uuid = new_watch['uuid']
-            logging.debug("Added URL {} - {}".format(url, new_uuid))
+        # Make any uuids unique
+        if apply_extras.get('tags'):
+            apply_extras['tags'] = list(set(apply_extras.get('tags')))
 
-            for k in ['uuid', 'history', 'last_checked', 'last_changed', 'newest_history_key', 'previous_md5', 'viewed']:
-                if k in apply_extras:
-                    del apply_extras[k]
+        new_watch = Watch.model(datastore_path=self.datastore_path, url=url)
 
-            new_watch.update(apply_extras)
-            self.__data['watching'][new_uuid]=new_watch
+        new_uuid = new_watch.get('uuid')
+
+        logging.debug("Added URL {} - {}".format(url, new_uuid))
+
+        for k in ['uuid', 'history', 'last_checked', 'last_changed', 'newest_history_key', 'previous_md5', 'viewed']:
+            if k in apply_extras:
+                del apply_extras[k]
+
+        new_watch.update(apply_extras)
+        new_watch.ensure_data_dir_exists()
+        self.__data['watching'][new_uuid] = new_watch
 
-        self.__data['watching'][new_uuid].ensure_data_dir_exists()
 
         if write_to_disk_now:
             self.sync_to_json()
+
         return new_uuid
 
     def visualselector_data_is_ready(self, watch_uuid):
@@ -347,22 +360,25 @@ class ChangeDetectionStore:
             f.write(screenshot)
             f.close()
 
+
     def save_error_text(self, watch_uuid, contents):
         if not self.data['watching'].get(watch_uuid):
             return
-        target_path = os.path.join(self.datastore_path, watch_uuid, "last-error.txt")
 
+        self.data['watching'][watch_uuid].ensure_data_dir_exists()
+        target_path = os.path.join(self.datastore_path, watch_uuid, "last-error.txt")
         with open(target_path, 'w') as f:
             f.write(contents)
 
     def save_xpath_data(self, watch_uuid, data, as_error=False):
+
         if not self.data['watching'].get(watch_uuid):
             return
         if as_error:
             target_path = os.path.join(self.datastore_path, watch_uuid, "elements-error.json")
         else:
             target_path = os.path.join(self.datastore_path, watch_uuid, "elements.json")
-
+        self.data['watching'][watch_uuid].ensure_data_dir_exists()
         with open(target_path, 'w') as f:
             f.write(json.dumps(data))
             f.close()
@@ -432,10 +448,28 @@ class ChangeDetectionStore:
                     print ("Removing",item)
                     unlink(item)
 
-    def import_proxy_list(self, filename):
-        with open(filename) as f:
-            self.proxy_list = json.load(f)
-            print ("Registered proxy list", list(self.proxy_list.keys()))
+    @property
+    def proxy_list(self):
+        proxy_list = {}
+        proxy_list_file = os.path.join(self.datastore_path, 'proxies.json')
+
+        # Load from external config file
+        if path.isfile(proxy_list_file):
+            with open("{}/proxies.json".format(self.datastore_path)) as f:
+                proxy_list = json.load(f)
+
+        # Mapping from UI config if available
+        extras = self.data['settings']['requests'].get('extra_proxies')
+        if extras:
+            i=0
+            for proxy in extras:
+                i += 0
+                if proxy.get('proxy_name') and proxy.get('proxy_url'):
+                    k = "ui-" + str(i) + proxy.get('proxy_name')
+                    proxy_list[k] = {'label': proxy.get('proxy_name'), 'url': proxy.get('proxy_url')}
+
+
+        return proxy_list if len(proxy_list) else None
 
 
     def get_preferred_proxy_for_watch(self, uuid):
@@ -445,11 +479,10 @@ class ChangeDetectionStore:
         :return: proxy "key" id
         """
 
-        proxy_id = None
         if self.proxy_list is None:
             return None
 
-        # If its a valid one
+        # If it's a valid one
         watch = self.data['watching'].get(uuid)
 
         if watch.get('proxy') and watch.get('proxy') in list(self.proxy_list.keys()):
@@ -462,13 +495,113 @@ class ChangeDetectionStore:
             if self.proxy_list.get(system_proxy_id):
                 return system_proxy_id
 
-        # Fallback - Did not resolve anything, use the first available
-        if system_proxy_id is None:
+
+        # Fallback - Did not resolve anything, or doesnt exist, use the first available
+        if system_proxy_id is None or not self.proxy_list.get(system_proxy_id):
             first_default = list(self.proxy_list)[0]
             return first_default
 
         return None
 
+    @property
+    def has_extra_headers_file(self):
+        filepath = os.path.join(self.datastore_path, 'headers.txt')
+        return os.path.isfile(filepath)
+
+    def get_all_base_headers(self):
+        from .model.App import parse_headers_from_text_file
+        headers = {}
+        # Global app settings
+        headers.update(self.data['settings'].get('headers', {}))
+
+        return headers
+
+    def get_all_headers_in_textfile_for_watch(self, uuid):
+        from .model.App import parse_headers_from_text_file
+        headers = {}
+
+        # Global in /datastore/headers.txt
+        filepath = os.path.join(self.datastore_path, 'headers.txt')
+        try:
+            if os.path.isfile(filepath):
+                headers.update(parse_headers_from_text_file(filepath))
+        except Exception as e:
+            print(f"ERROR reading headers.txt at {filepath}", str(e))
+
+        watch = self.data['watching'].get(uuid)
+        if watch:
+
+            # In /datastore/xyz-xyz/headers.txt
+            filepath = os.path.join(watch.watch_data_dir, 'headers.txt')
+            try:
+                if os.path.isfile(filepath):
+                    headers.update(parse_headers_from_text_file(filepath))
+            except Exception as e:
+                print(f"ERROR reading headers.txt at {filepath}", str(e))
+
+            # In /datastore/tag-name.txt
+            tags = self.get_all_tags_for_watch(uuid=uuid)
+            for tag_uuid, tag in tags.items():
+                fname = "headers-"+re.sub(r'[\W_]', '', tag.get('title')).lower().strip() + ".txt"
+                filepath = os.path.join(self.datastore_path, fname)
+                try:
+                    if os.path.isfile(filepath):
+                        headers.update(parse_headers_from_text_file(filepath))
+                except Exception as e:
+                    print(f"ERROR reading headers.txt at {filepath}", str(e))
+
+        return headers
+
+    def get_tag_overrides_for_watch(self, uuid, attr):
+        tags = self.get_all_tags_for_watch(uuid=uuid)
+        ret = []
+
+        if tags:
+            for tag_uuid, tag in tags.items():
+                if attr in tag and tag[attr]:
+                    ret=[*ret, *tag[attr]]
+
+        return ret
+
+    def add_tag(self, name):
+        # If name exists, return that
+        n = name.strip().lower()
+        print (f">>> Adding new tag - '{n}'")
+        if not n:
+            return False
+
+        for uuid, tag in self.__data['settings']['application'].get('tags', {}).items():
+            if n == tag.get('title', '').lower().strip():
+                print (f">>> Tag {name} already exists")
+                return uuid
+
+        # Eventually almost everything todo with a watch will apply as a Tag
+        # So we use the same model as a Watch
+        with self.lock:
+            new_tag = Watch.model(datastore_path=self.datastore_path, default={
+                'title': name.strip(),
+                'date_created': int(time.time())
+            })
+
+            new_uuid = new_tag.get('uuid')
+
+            self.__data['settings']['application']['tags'][new_uuid] = new_tag
+
+        return new_uuid
+
+    def get_all_tags_for_watch(self, uuid):
+        """This should be in Watch model but Watch doesn't have access to datastore, not sure how to solve that yet"""
+        watch = self.data['watching'].get(uuid)
+
+        # Should return a dict of full tag info linked by UUID
+        if watch:
+            return dictfilt(self.__data['settings']['application']['tags'], watch.get('tags', []))
+
+        return {}
+
+    def tag_exists_by_name(self, tag_name):
+        return any(v.get('title', '').lower() == tag_name.lower() for k, v in self.__data['settings']['application']['tags'].items())
+
     # Run all updates
     # IMPORTANT - Each update could be run even when they have a new install and the schema is correct
     #             So therefor - each `update_n` should be very careful about checking if it needs to actually run
@@ -583,3 +716,87 @@ class ChangeDetectionStore:
         for v in ['User-Agent', 'Accept', 'Accept-Encoding', 'Accept-Language']:
             if self.data['settings']['headers'].get(v):
                 del self.data['settings']['headers'][v]
+
+    # Convert filters to a list of filters css_filter -> include_filters
+    def update_8(self):
+        for uuid, watch in self.data['watching'].items():
+            try:
+                existing_filter = watch.get('css_filter', '')
+                if existing_filter:
+                    watch['include_filters'] = [existing_filter]
+            except:
+                continue
+        return
+
+    # Convert old static notification tokens to jinja2 tokens
+    def update_9(self):
+        # Each watch
+        import re
+        # only { } not {{ or }}
+        r = r'(?<!{){(?!{)(\w+)(?<!})}(?!})'
+        for uuid, watch in self.data['watching'].items():
+            try:
+                n_body = watch.get('notification_body', '')
+                if n_body:
+                    watch['notification_body'] = re.sub(r, r'{{\1}}', n_body)
+
+                n_title = watch.get('notification_title')
+                if n_title:
+                    watch['notification_title'] = re.sub(r, r'{{\1}}', n_title)
+
+                n_urls = watch.get('notification_urls')
+                if n_urls:
+                    for i, url in enumerate(n_urls):
+                        watch['notification_urls'][i] = re.sub(r, r'{{\1}}', url)
+
+            except:
+                continue
+
+        # System wide
+        n_body = self.data['settings']['application'].get('notification_body')
+        if n_body:
+            self.data['settings']['application']['notification_body'] = re.sub(r, r'{{\1}}', n_body)
+
+        n_title = self.data['settings']['application'].get('notification_title')
+        if n_body:
+            self.data['settings']['application']['notification_title'] = re.sub(r, r'{{\1}}', n_title)
+
+        n_urls =  self.data['settings']['application'].get('notification_urls')
+        if n_urls:
+            for i, url in enumerate(n_urls):
+                self.data['settings']['application']['notification_urls'][i] = re.sub(r, r'{{\1}}', url)
+
+        return
+
+    # Some setups may have missed the correct default, so it shows the wrong config in the UI, although it will default to system-wide
+    def update_10(self):
+        for uuid, watch in self.data['watching'].items():
+            try:
+                if not watch.get('fetch_backend', ''):
+                    watch['fetch_backend'] = 'system'
+            except:
+                continue
+        return
+
+    # We don't know when the date_created was in the past until now, so just add an index number for now.
+    def update_11(self):
+        i = 0
+        for uuid, watch in self.data['watching'].items():
+            if not watch.get('date_created'):
+                watch['date_created'] = i
+            i+=1
+        return
+
+    # Create tag objects and their references from existing tag text
+    def update_12(self):
+        i = 0
+        for uuid, watch in self.data['watching'].items():
+            # Split out and convert old tag string
+            tag = watch.get('tag')
+            if tag:
+                tag_uuids = []
+                for t in tag.split(','):
+                    tag_uuids.append(self.add_tag(name=t))
+
+                self.data['watching'][uuid]['tags'] = tag_uuids
+

changedetectionio/templates/_common_fields.jinja

@@ -16,14 +16,17 @@
                                 <li><code>discord://</code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
                                 <li><code>tgram://</code> bots cant send messages to other bots, so you should specify chat ID of non-bot user.</li>
                                 <li><code>tgram://</code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
+                                <li><code>gets://</code>, <code>posts://</code>, <code>puts://</code>, <code>deletes://</code> for direct API calls (or omit the "<code>s</code>" for non-SSL ie <code>get://</code>)</li>
+                                  <li>Accepts the <code>{{ '{{token}}' }}</code> placeholders listed below</li>
                               </ul>
                             </div>
-                            <br/>
-                            <a id="send-test-notification" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Send test notification</a>
-{% if emailprefix %}
-                            <a id="add-email-helper" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Add email</a>
-{% endif %}
-                            <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Notification debug logs</a>
+                            <div class="notifications-wrapper">
+                              <a id="send-test-notification" class="pure-button button-secondary button-xsmall" >Send test notification</a>
+                            {% if emailprefix %}
+                              <a id="add-email-helper" class="pure-button button-secondary button-xsmall" >Add email <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='email.svg')}}" alt="Add an email address"> </a>
+                            {% endif %}
+                              <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" >Notification debug logs</a>
+                            </div>
                         </div>
                         <div id="notification-customisation" class="pure-control-group">
                             <div class="pure-control-group">
@@ -40,8 +43,9 @@
                                 <span class="pure-form-message-inline">Format for all notifications</span>
                             </div>
                             <div class="pure-controls">
-                            <span class="pure-form-message-inline">
-                                These tokens can be used in the notification body and title to customise the notification text.
+                            <p class="pure-form-message-inline">
+                                You can use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> templating in the notification title, body and URL.
+                            </p>
 
                                 <table class="pure-table" id="token-table">
                                     <thead>
@@ -52,52 +56,67 @@
                                     </thead>
                                     <tbody>
                                     <tr>
-                                        <td><code>{base_url}</code></td>
+                                        <td><code>{{ '{{base_url}}' }}</code></td>
                                         <td>The URL of the changedetection.io instance you are running.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{watch_url}</code></td>
+                                        <td><code>{{ '{{watch_url}}' }}</code></td>
                                         <td>The URL being watched.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{watch_uuid}</code></td>
+                                        <td><code>{{ '{{watch_uuid}}' }}</code></td>
                                         <td>The UUID of the watch.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{watch_title}</code></td>
+                                        <td><code>{{ '{{watch_title}}' }}</code></td>
                                         <td>The title of the watch.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{watch_tag}</code></td>
-                                        <td>The tag of the watch.</td>
+                                        <td><code>{{ '{{watch_tag}}' }}</code></td>
+                                        <td>The watch label / tag</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{preview_url}</code></td>
+                                        <td><code>{{ '{{preview_url}}' }}</code></td>
                                         <td>The URL of the preview page generated by changedetection.io.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{diff}</code></td>
-                                        <td>The diff output - differences only</td>
+                                        <td><code>{{ '{{diff_url}}' }}</code></td>
+                                        <td>The URL of the diff output for the watch.</td>
+                                    </tr>
+									<tr>
+                                        <td><code>{{ '{{diff}}' }}</code></td>
+                                        <td>The diff output - only changes, additions, and removals</td>
+                                    </tr>
+									<tr>
+                                        <td><code>{{ '{{diff_added}}' }}</code></td>
+                                        <td>The diff output - only changes and additions</td>
+                                    </tr>
+									<tr>
+                                        <td><code>{{ '{{diff_removed}}' }}</code></td>
+                                        <td>The diff output - only changes and removals</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{diff_full}</code></td>
+                                        <td><code>{{ '{{diff_full}}' }}</code></td>
                                         <td>The diff output - full difference output</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{diff_url}</code></td>
-                                        <td>The URL of the diff page generated by changedetection.io.</td>
-                                    </tr>
-                                    <tr>
-                                        <td><code>{current_snapshot}</code></td>
+                                        <td><code>{{ '{{current_snapshot}}' }}</code></td>
                                         <td>The current snapshot value, useful when combined with JSON or CSS filters
                                         </td>
                                     </tr>
+                                    <tr>
+                                        <td><code>{{ '{{triggered_text}}' }}</code></td>
+                                        <td>Text that tripped the trigger from filters</td>
+                                    </tr>
                                     </tbody>
                                 </table>
-                                <br/>
-                                URLs generated by changedetection.io (such as <code>{diff_url}</code>) require the <code>BASE_URL</code> environment variable set.<br/>
-                                Your <code>BASE_URL</code> var is currently "{{settings_application['current_base_url']}}"
-                            </span>
+                                <div class="pure-form-message-inline">
+                                    <br>
+                                    URLs generated by changedetection.io (such as <code>{{ '{{diff_url}}' }}</code>) require the <code>BASE_URL</code> environment variable set.<br>
+                                    Your <code>BASE_URL</code> var is currently "{{settings_application['current_base_url']}}"
+									<br>
+									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removed%7D%7D-notification-tokens">More Here</a> <br>
+                                </div>
                             </div>
                         </div>
 {% endmacro %}