improve pdf tests

.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

@@ -2,7 +2,7 @@
 # Test that we can still build on Alpine (musl modified libc https://musl.libc.org/)
 # Some packages wont install via pypi because they dont have a wheel available under this architecture.
 
-FROM ghcr.io/linuxserver/baseimage-alpine:3.16
+FROM ghcr.io/linuxserver/baseimage-alpine:3.18
 ENV PYTHONUNBUFFERED=1
 
 COPY requirements.txt /requirements.txt
@@ -26,6 +26,6 @@ RUN \
     py3-pip && \
   echo "**** pip3 install test of changedetection.io ****" && \
   pip3 install -U pip wheel setuptools && \
-  pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.16/ -r /requirements.txt && \
+  pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.18/ -r /requirements.txt && \
   apk del --purge \
     build-dependencies

.github/workflows/codeql-analysis.yml

@@ -30,11 +30,11 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v2
+      uses: actions/checkout@v4
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v1
+      uses: github/codeql-action/init@v2
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -45,7 +45,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v1
+      uses: github/codeql-action/autobuild@v2
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -59,4 +59,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v1
+      uses: github/codeql-action/analyze@v2

.github/workflows/containers.yml

@@ -39,11 +39,11 @@ jobs:
     # Or if we are in a tagged release scenario.
     if: ${{ github.event.workflow_run.conclusion == 'success' }} || ${{ github.event.release.tag_name }} != ''
     steps:
-      - uses: actions/checkout@v2
-      - name: Set up Python 3.9
-        uses: actions/setup-python@v2
+      - uses: actions/checkout@v4
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v4
         with:
-          python-version: 3.9
+          python-version: 3.11
 
       - name: Install dependencies
         run: |
@@ -58,27 +58,27 @@ jobs:
           echo ${{ github.ref }} > changedetectionio/tag.txt
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
+        uses: docker/setup-qemu-action@v3
         with:
           image: tonistiigi/binfmt:latest
           platforms: all
 
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@v1
+        uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Login to Docker Hub Container Registry
-        uses: docker/login-action@v1
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_HUB_USERNAME }}
           password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }}
 
       - name: Set up Docker Buildx
         id: buildx
-        uses: docker/setup-buildx-action@v1
+        uses: docker/setup-buildx-action@v3
         with:
           install: true
           version: latest
@@ -88,16 +88,17 @@ jobs:
       - name: Build and push :dev
         id: docker_build
         if: ${{ github.ref }} == "refs/heads/master"
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v5
         with:
           context: ./
           file: ./Dockerfile
           push: true
           tags: |
             ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
-          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
-          cache-from: type=local,src=/tmp/.buildx-cache
-          cache-to: type=local,dest=/tmp/.buildx-cache
+          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
 # Looks like this was disabled
 #          provenance: false
 
@@ -105,7 +106,7 @@ jobs:
       - name: Build and push :tag
         id: docker_build_tag_release
         if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v5
         with:
           context: ./
           file: ./Dockerfile
@@ -115,19 +116,12 @@ jobs:
             ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
             ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest
             ghcr.io/dgtlmoon/changedetection.io:latest
-          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
-          cache-from: type=local,src=/tmp/.buildx-cache
-          cache-to: type=local,dest=/tmp/.buildx-cache
+          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
 # Looks like this was disabled
 #          provenance: false
 
       - name: Image digest
         run: echo step SHA ${{ steps.vars.outputs.sha_short }} tag ${{steps.vars.outputs.tag}} branch ${{steps.vars.outputs.branch}} digest ${{ steps.docker_build.outputs.digest }}
 
-      - name: Cache Docker layers
-        uses: actions/cache@v2
-        with:
-          path: /tmp/.buildx-cache
-          key: ${{ runner.os }}-buildx-${{ github.sha }}
-          restore-keys: |
-            ${{ runner.os }}-buildx-

.github/workflows/pypi.yml

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

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

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

.github/workflows/test-only.yml

@@ -7,13 +7,13 @@ jobs:
   test-application:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
 
       # Mainly just for link/flake8
-      - name: Set up Python 3.10
-        uses: actions/setup-python@v2
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v4
         with:
-          python-version: '3.10'
+          python-version: '3.11'
 
       - name: Lint with flake8
         run: |
@@ -29,19 +29,29 @@ jobs:
           docker network create changedet-network
 
           # Selenium+browserless
-          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome-debug:3.141.59
-          docker run --network changedet-network -d --hostname browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
+          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome:4
+          docker run --network changedet-network -d --name browserless --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:1.60-chrome-stable
+          
+          # For accessing custom browser tests
+          docker run --network changedet-network -d --name browserless-custom-url --hostname browserless-custom-url -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm --shm-size="2g"  browserless/chrome:1.60-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: |
+          # 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'
+          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_watch_model'
           
           # All tests
           docker run --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio && ./run_basic_tests.sh'
@@ -55,13 +65,35 @@ jobs:
           # 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
+          # And again with PLAYWRIGHT_DRIVER_URL=..
+          cd ..
+
+      - name: Test custom browser URL
+        run: |
+          cd changedetectionio
+          ./run_custom_browser_url_tests.sh
           cd ..
 
       - name: Test changedetection.io container starts+runs basically without error
@@ -77,4 +109,4 @@ jobs:
 
 #export WEBDRIVER_URL=http://localhost:4444/wd/hub
 #pytest tests/fetchers/test_content.py
-#pytest tests/test_errorhandling.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@v4
+
+        - name: Set up Python 3.11
+          uses: actions/setup-python@v4
+          with:
+            python-version: 3.11
+
+
+        - name: Test that the basic pip built package runs without error
+          run: |
+            set -e
+            mkdir dist
+            pip3 install wheel
+            python3 setup.py bdist_wheel            
+            pip3 install -r requirements.txt
+            rm ./changedetection.py
+            rm -rf changedetectio
+            
+            pip3 install dist/changedetection.io*.whl
+            changedetection.io -d /tmp -p 10000 &
+            sleep 3
+            curl http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
+            killall -9 changedetection.io

Dockerfile

@@ -1,5 +1,5 @@
 # pip dependencies install stage
-FROM python:3.10-slim as builder
+FROM python:3.11-slim-bookworm as builder
 
 # See `cryptography` pin comment in requirements.txt
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
@@ -25,14 +25,13 @@ RUN pip install --target=/dependencies -r /requirements.txt
 # Playwright is an alternative to Selenium
 # Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
 # https://github.com/dgtlmoon/changedetection.io/pull/1067 also musl/alpine (not supported)
-RUN pip install --target=/dependencies playwright~=1.27.1 \
+RUN pip install --target=/dependencies playwright~=1.39 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
-FROM python:3.10-slim
+FROM python:3.11-slim-bookworm
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    libssl1.1 \
     libxslt1.1 \
     # For pdftohtml
     poppler-utils \

MANIFEST.in

@@ -13,3 +13,7 @@ include changedetection.py
 global-exclude *.pyc
 global-exclude node_modules
 global-exclude venv
+
+global-exclude test-datastore
+global-exclude changedetection.io*dist-info
+global-exclude changedetectionio/tests/proxy_socks5/test-datastore

README-pip.md

@@ -2,19 +2,44 @@
 
 Live your data-life pro-actively, track website content changes and receive notifications via Discord, Email, Slack, Telegram and 70+ more
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=pip)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring, list of websites with changes"  title="Self-hosted web page change monitoring, list of websites with changes"  />](https://changedetection.io)
 
 
-[**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://lemonade.changedetection.io/start) 
+[**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://changedetection.io) 
 
 
-#### Example use cases
+### Target specific parts of the webpage using the Visual Selector tool.
+
+Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
+
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Select parts and elements of a web page to monitor for changes"  title="Select parts and elements of a web page to monitor for changes" />](https://changedetection.io?src=pip)
+
+### Easily see what changed, examine by word, line, or individual character.
+
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://changedetection.io?src=pip)
+
+
+### Perform interactive browser steps
+
+Fill in text boxes, click buttons and more, setup your changedetection scenario. 
+
+Using the **Browser Steps** configuration, add basic steps before performing change detection, such as logging into websites, adding a product to a cart, accept cookie logins, entering dates and refining searches.
+
+[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more"  title="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more" />](https://changedetection.io?src=pip)
+
+After **Browser Steps** have been run, then visit the **Visual Selector** tab to refine the content you're interested in.
+Requires Playwright to be enabled.
+
+
+### Example use cases
 
 - Products and services have a change in pricing
 - _Out of stock notification_ and _Back In stock notification_
+- Monitor and track PDF file changes, know when a PDF file has text changes.
 - Governmental department updates (changes are often only on their websites)
 - New software releases, security advisories when you're not on their mailing list.
 - Festivals with changes
+- Discogs restock alerts and monitoring
 - Realestate listing changes
 - Know when your favourite whiskey is on sale, or other special deals are announced before anyone else
 - COVID related news from government websites
@@ -27,18 +52,34 @@ Live your data-life pro-actively, track website content changes and receive noti
 - Create RSS feeds based on changes in web content
 - Monitor HTML source code for unexpected changes, strengthen your PCI compliance
 - You have a very sensitive list of URLs to watch and you do _not_ want to use the paid alternatives. (Remember, _you_ are the product)
+- Get notified when certain keywords appear in Twitter search results
+- Proactively search for jobs, get notified when companies update their careers page, search job portals for keywords.
+- Get alerts when new job positions are open on Bamboo HR and other job platforms
+- Website defacement monitoring
+- Pokémon Card Restock Tracker / Pokémon TCG Tracker
+- RegTech - stay ahead of regulatory changes, regulatory compliance
 
 _Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
 
 #### Key Features
 
 - Lots of trigger filters, such as "Trigger on text", "Remove text by selector", "Ignore text", "Extract text", also using regular-expressions!
-- Target elements with xPath and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
+- Target elements with xPath(1.0) and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
 - Switch between fast non-JS and Chrome JS based "fetchers"
+- Track changes in PDF files (Monitor text changed in the PDF, Also monitor PDF filesize and checksums)
 - Easily specify how often a site should be checked
 - Execute JS before extracting text (Good for logging in, see examples in the UI!)
 - Override Request Headers, Specify `POST` or `GET` and other methods
 - Use the "Visual Selector" to help target specific elements
+- Configurable [proxy per watch](https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration)
+- Send a screenshot with the notification when a change is detected in the web page
+
+We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) global proxy services, Bright Data will match any first deposit up to $100 using our signup link.
+
+[Oxylabs](https://oxylabs.go2cloud.org/SH2d) is also an excellent proxy provider and well worth using, they offer Residental, ISP, Rotating and many other proxy types to suit your project. 
+
+Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
+
 
 
 ```bash
@@ -54,5 +95,5 @@ $ changedetection.io -d /path/to/empty/data/dir -p 5000
 
 Then visit http://127.0.0.1:5000 , You should now be able to access the UI.
 
-See https://github.com/dgtlmoon/changedetection.io for more information.
+See https://changedetection.io for more information.
 

README.md

@@ -5,13 +5,13 @@
 _Live your data-life pro-actively._ 
 
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=github)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web site page change monitoring"  title="Self-hosted web site page change monitoring"  />](https://changedetection.io?src=github)
 
 [![Release Version][release-shield]][release-link] [![Docker Pulls][docker-pulls]][docker-link] [![License][license-shield]](LICENSE.md)
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
-[**Don't have time? Let us host it for you! try our $8.99/month subscription - use our proxies and support!**](https://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
+[**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.
@@ -22,11 +22,11 @@ _Live your data-life pro-actively._
 
 Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://lemonade.changedetection.io/start?src=github)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Select parts and elements of a web page to monitor for changes"  title="Select parts and elements of a web page to monitor for changes" />](https://changedetection.io?src=github)
 
 ### Easily see what changed, examine by word, line, or individual character.
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://lemonade.changedetection.io/start?src=github)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://changedetection.io?src=github)
 
 
 ### Perform interactive browser steps
@@ -35,7 +35,7 @@ Fill in text boxes, click buttons and more, setup your changedetection scenario.
 
 Using the **Browser Steps** configuration, add basic steps before performing change detection, such as logging into websites, adding a product to a cart, accept cookie logins, entering dates and refining searches.
 
-[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Website change detection with interactive browser steps, login, cookies etc" />](https://lemonade.changedetection.io/start?src=github)
+[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more"  title="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more" />](https://changedetection.io?src=github)
 
 After **Browser Steps** have been run, then visit the **Visual Selector** tab to refine the content you're interested in.
 Requires Playwright to be enabled.
@@ -65,13 +65,16 @@ Requires Playwright to be enabled.
 - Get notified when certain keywords appear in Twitter search results
 - Proactively search for jobs, get notified when companies update their careers page, search job portals for keywords.
 - Get alerts when new job positions are open on Bamboo HR and other job platforms
+- Website defacement monitoring
+- Pokémon Card Restock Tracker / Pokémon TCG Tracker
+- RegTech - stay ahead of regulatory changes, regulatory compliance
 
 _Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
 
 #### Key Features
 
 - Lots of trigger filters, such as "Trigger on text", "Remove text by selector", "Ignore text", "Extract text", also using regular-expressions!
-- Target elements with xPath and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
+- Target elements with xPath(1.0) and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
 - Switch between fast non-JS and Chrome JS based "fetchers"
 - Track changes in PDF files (Monitor text changed in the PDF, Also monitor PDF filesize and checksums)
 - Easily specify how often a site should be checked
@@ -83,6 +86,8 @@ _Need an actual Chrome runner with Javascript support? We support fetching via W
 
 We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) global proxy services, Bright Data will match any first deposit up to $100 using our signup link.
 
+[Oxylabs](https://oxylabs.go2cloud.org/SH2d) is also an excellent proxy provider and well worth using, they offer Residental, ISP, Rotating and many other proxy types to suit your project. 
+
 Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
 
 ## Installation
@@ -142,8 +147,8 @@ See the wiki for more information https://github.com/dgtlmoon/changedetection.io
 
 ## Filters
 
-XPath, JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools. 
-(We support LXML `re:test`, `re:math` and `re:replace`.)
+XPath(1.0), JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools. 
+(We support LXML `re:test`, `re:match` and `re:replace`.)
 
 ## Notifications
 
@@ -181,7 +186,7 @@ This will re-parse the JSON and apply formatting to the text, making it super ea
 
 ### JSONPath or jq?
 
-For more complex parsing, filtering, and modifying of JSON data, jq is recommended due to the built-in operators and functions. Refer to the [documentation](https://stedolan.github.io/jq/manual/) for more specifc information on jq.
+For more complex parsing, filtering, and modifying of JSON data, jq is recommended due to the built-in operators and functions. Refer to the [documentation](https://stedolan.github.io/jq/manual/) for more specific information on jq.
 
 One big advantage of `jq` is that you can use logic in your JSON filter, such as filters to only show items that have a value greater than/less than etc.
 
@@ -221,12 +226,19 @@ The application also supports notifying you that it can follow this information
 
 ## Proxy Configuration
 
-See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [BrightData proxy services where possible]( https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support)
+See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [Bright Data proxy services where possible](https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support) and [Oxylabs](https://oxylabs.go2cloud.org/SH2d) proxy services.
 
 ## Raspberry Pi support?
 
 Raspberry Pi and linux/arm/v6 linux/arm/v7 arm64 devices are supported! See the wiki for [details](https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver)
 
+## Import support
+
+Easily [import your list of websites to watch for changes in Excel .xslx file format](https://changedetection.io/tutorial/how-import-your-website-change-detection-lists-excel), or paste in lists of website URLs as plaintext. 
+
+Excel import is recommended - that way you can better organise tags/groups of websites and other features.
+
+
 ## API Support
 
 Supports managing the website watch list [via our API](https://changedetection.io/docs/api_v1/index.html)
@@ -236,7 +248,7 @@ Supports managing the website watch list [via our API](https://changedetection.i
 Do you use changedetection.io to make money? does it save you time or money? Does it make your life easier? less stressful? Remember, we write this software when we should be doing actual paid work, we have to buy food and pay rent just like you.
 
 
-Firstly, consider taking out a [change detection monthly subscription - unlimited checks and watches](https://lemonade.changedetection.io/start) , even if you don't use it, you still get the warm fuzzy feeling of helping out the project. (And who knows, you might just use it!)
+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)
 
@@ -256,3 +268,7 @@ I offer commercial support, this software is depended on by network security, ae
 [license-shield]: https://img.shields.io/github/license/dgtlmoon/changedetection.io.svg?style=for-the-badge
 [release-link]: https://github.com/dgtlmoon/changedetection.io/releases
 [docker-link]: https://hub.docker.com/r/dgtlmoon/changedetection.io
+
+## Third-party licenses
+
+changedetectionio.html_tools.elementpath_tostring: Copyright (c), 2018-2021, SISSA (Scuola Internazionale Superiore di Studi Avanzati), Licensed under [MIT license](https://github.com/sissaschool/elementpath/blob/master/LICENSE)

changedetectionio/__init__.py

@@ -33,10 +33,14 @@ from flask import (
     url_for,
 )
 
+from flask_paginate import Pagination, get_page_parameter
+
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.41.1'
+__version__ = '0.45.7.3'
+
+from changedetectionio.store import BASE_URL_NOT_SET_TEXT
 
 datastore = None
 
@@ -101,6 +105,10 @@ def get_darkmode_state():
     css_dark_mode = request.cookies.get('css_dark_mode', 'false')
     return 'true' if css_dark_mode and strtobool(css_dark_mode) else 'false'
 
+@app.template_global()
+def get_css_version():
+    return __version__
+
 # We use the whole watch object from the store/JSON so we can see if there's some related status in terms of a thread
 # running or something similar.
 @app.template_filter('format_last_checked_time')
@@ -122,6 +130,15 @@ def _jinja2_filter_datetimestamp(timestamp, format="%Y-%m-%d %H:%M:%S"):
 
     return timeago.format(timestamp, time.time())
 
+
+@app.template_filter('pagination_slice')
+def _jinja2_filter_pagination_slice(arr, skip):
+    per_page = datastore.data['settings']['application'].get('pager_size', 50)
+    if per_page:
+        return arr[skip:skip + per_page]
+
+    return arr
+
 @app.template_filter('format_seconds_ago')
 def _jinja2_filter_seconds_precise(timestamp):
     if timestamp == False:
@@ -173,7 +190,6 @@ class User(flask_login.UserMixin):
 
     pass
 
-
 def login_optionally_required(func):
     @wraps(func)
     def decorated_view(*args, **kwargs):
@@ -186,7 +202,6 @@ def login_optionally_required(func):
         # Permitted
         elif request.endpoint == 'diff_history_page' and datastore.data['settings']['application'].get('shared_diff_access'):
             return func(*args, **kwargs)
-
         elif request.method in flask_login.config.EXEMPT_METHODS:
             return func(*args, **kwargs)
         elif app.config.get('LOGIN_DISABLED'):
@@ -306,25 +321,21 @@ def changedetection_app(config=None, datastore_o=None):
             return "Access denied, bad token", 403
 
         from . import diff
-        limit_tag = request.args.get('tag')
+        limit_tag = request.args.get('tag', '').lower().strip()
+        # Be sure limit_tag is a uuid
+        for uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
+            if limit_tag == tag.get('title', '').lower().strip():
+                limit_tag = uuid
 
         # Sort by last_changed and add the uuid which is usually the key..
         sorted_watches = []
 
         # @todo needs a .itemsWithTag() or something - then we can use that in Jinaj2 and throw this away
         for uuid, watch in datastore.data['watching'].items():
-
-            if limit_tag != None:
-                # Support for comma separated list of tags.
-                for tag_in_watch in watch['tag'].split(','):
-                    tag_in_watch = tag_in_watch.strip()
-                    if tag_in_watch == limit_tag:
-                        watch['uuid'] = uuid
-                        sorted_watches.append(watch)
-
-            else:
-                watch['uuid'] = uuid
-                sorted_watches.append(watch)
+            if limit_tag and not limit_tag in watch['tags']:
+                    continue
+            watch['uuid'] = uuid
+            sorted_watches.append(watch)
 
         sorted_watches.sort(key=lambda x: x.last_changed, reverse=False)
 
@@ -348,11 +359,11 @@ def changedetection_app(config=None, datastore_o=None):
 
                 # Include a link to the diff page, they will have to login here to see if password protection is enabled.
                 # Description is the page you watch, link takes you to the diff JS UI page
-                base_url = datastore.data['settings']['application']['base_url']
-                if base_url == '':
-                    base_url = "<base-url-env-var-not-set>"
+                # Dict val base_url will get overriden with the env var if it is set.
+                ext_base_url = datastore.data['settings']['application'].get('active_base_url')
 
-                diff_link = {'href': "{}{}".format(base_url, url_for('diff_history_page', uuid=watch['uuid']))}
+                # Because we are called via whatever web server, flask should figure out the right path (
+                diff_link = {'href': url_for('diff_history_page', uuid=watch['uuid'], _external=True)}
 
                 fe.link(link=diff_link)
 
@@ -381,9 +392,17 @@ def changedetection_app(config=None, datastore_o=None):
     @app.route("/", methods=['GET'])
     @login_optionally_required
     def index():
+        global datastore
         from changedetectionio import forms
 
-        limit_tag = request.args.get('tag')
+        limit_tag = request.args.get('tag', '').lower().strip()
+
+        # Be sure limit_tag is a uuid
+        for uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
+            if limit_tag == tag.get('title', '').lower().strip():
+                limit_tag = uuid
+
+
         # Redirect for the old rss path which used the /?rss=true
         if request.args.get('rss'):
             return redirect(url_for('rss', tag=limit_tag))
@@ -401,44 +420,68 @@ def changedetection_app(config=None, datastore_o=None):
 
         # Sort by last_changed and add the uuid which is usually the key..
         sorted_watches = []
+        with_errors = request.args.get('with_errors') == "1"
+        errored_count = 0
+        search_q = request.args.get('q').strip().lower() if request.args.get('q') else False
         for uuid, watch in datastore.data['watching'].items():
+            if with_errors and not watch.get('last_error'):
+                continue
 
-            if limit_tag != None:
-                # Support for comma separated list of tags.
-                if watch['tag'] is None:
+            if limit_tag and not limit_tag in watch['tags']:
                     continue
-                for tag_in_watch in watch['tag'].split(','):
-                    tag_in_watch = tag_in_watch.strip()
-                    if tag_in_watch == limit_tag:
-                        watch['uuid'] = uuid
-                        sorted_watches.append(watch)
-
+            if watch.get('last_error'):
+                errored_count += 1
+                
+            if search_q:
+                if (watch.get('title') and search_q in watch.get('title').lower()) or search_q in watch.get('url', '').lower():
+                    sorted_watches.append(watch)
             else:
-                watch['uuid'] = uuid
                 sorted_watches.append(watch)
 
-        existing_tags = datastore.get_all_tags()
         form = forms.quickWatchForm(request.form)
+        page = request.args.get(get_page_parameter(), type=int, default=1)
+        total_count = len(sorted_watches)
+
+        pagination = Pagination(page=page,
+                                total=total_count,
+                                per_page=datastore.data['settings']['application'].get('pager_size', 50), css_framework="semantic")
+
+
         output = render_template(
             "watch-overview.html",
                                  # Don't link to hosting when we're on the hosting environment
                                  active_tag=limit_tag,
                                  app_rss_token=datastore.data['settings']['application']['rss_access_token'],
+                                 datastore=datastore,
+                                 errored_count=errored_count,
                                  form=form,
                                  guid=datastore.data['app_guid'],
                                  has_proxies=datastore.proxy_list,
                                  has_unviewed=datastore.has_unviewed,
                                  hosted_sticky=os.getenv("SALTED_PASS", False) == False,
+                                 pagination=pagination,
                                  queued_uuids=[q_uuid.item['uuid'] for q_uuid in update_q.queue],
+                                 search_q=request.args.get('q','').strip(),
+                                 sort_attribute=request.args.get('sort') if request.args.get('sort') else request.cookies.get('sort'),
+                                 sort_order=request.args.get('order') if request.args.get('order') else request.cookies.get('order'),
                                  system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),
-                                 tags=existing_tags,
+                                 tags=datastore.data['settings']['application'].get('tags'),
                                  watches=sorted_watches
                                  )
 
-
         if session.get('share-link'):
             del(session['share-link'])
-        return output
+
+        resp = make_response(output)
+
+        # The template can run on cookie or url query info
+        if request.args.get('sort'):
+            resp.set_cookie('sort', request.args.get('sort'))
+        if request.args.get('order'):
+            resp.set_cookie('order', request.args.get('order'))
+
+        return resp
+
 
 
     # AJAX endpoint for sending a test
@@ -463,11 +506,19 @@ def changedetection_app(config=None, datastore_o=None):
 
         try:
             n_object = {'watch_url': request.form['window_url'],
-                        'notification_urls': request.form['notification_urls'].splitlines(),
-                        'notification_title': request.form['notification_title'].strip(),
-                        'notification_body': request.form['notification_body'].strip(),
-                        'notification_format': request.form['notification_format'].strip()
+                        'notification_urls': request.form['notification_urls'].splitlines()
                         }
+
+            # Only use if present, if not set in n_object it should use the default system value
+            if 'notification_format' in request.form and request.form['notification_format'].strip():
+                n_object['notification_format'] = request.form.get('notification_format', '').strip()
+
+            if 'notification_title' in request.form and request.form['notification_title'].strip():
+                n_object['notification_title'] = request.form.get('notification_title', '').strip()
+
+            if 'notification_body' in request.form and request.form['notification_body'].strip():
+                n_object['notification_body'] = request.form.get('notification_body', '').strip()
+
             notification_q.put(n_object)
         except Exception as e:
             return make_response({'error': str(e)}, 400)
@@ -557,9 +608,15 @@ def changedetection_app(config=None, datastore_o=None):
 
         # proxy_override set to the json/text list of the items
         form = forms.watchForm(formdata=request.form if request.method == 'POST' else None,
-                               data=default,
+                               data=default
                                )
 
+        # For the form widget tag uuid lookup
+        form.tags.datastore = datastore # in _value
+
+        for p in datastore.extra_browsers:
+            form.fetch_backend.choices.append(p)
+
         form.fetch_backend.choices.append(("system", 'System settings default'))
 
         # form.browser_steps[0] can be assumed that we 'goto url' first
@@ -579,7 +636,6 @@ def changedetection_app(config=None, datastore_o=None):
 
             if request.args.get('unpause_on_save'):
                 extra_update_obj['paused'] = False
-
             # Re #110, if they submit the same as the default value, set it to None, so we continue to follow the default
             # Assume we use the default value, unless something relevant is different, then use the form value
             # values could be None, 0 etc.
@@ -610,6 +666,16 @@ def changedetection_app(config=None, datastore_o=None):
                 extra_update_obj['filter_text_replaced'] = True
                 extra_update_obj['filter_text_removed'] = True
 
+            # Because wtforms doesn't support accessing other data in process_ , but we convert the CSV list of tags back to a list of UUIDs
+            tag_uuids = []
+            if form.data.get('tags'):
+                # Sometimes in testing this can be list, dont know why
+                if type(form.data.get('tags')) == list:
+                    extra_update_obj['tags'] = form.data.get('tags')
+                else:
+                    for t in form.data.get('tags').split(','):
+                        tag_uuids.append(datastore.add_tag(name=t))
+                    extra_update_obj['tags'] = tag_uuids
 
             datastore.data['watching'][uuid].update(form.data)
             datastore.data['watching'][uuid].update(extra_update_obj)
@@ -650,20 +716,20 @@ def changedetection_app(config=None, datastore_o=None):
             system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
 
             is_html_webdriver = False
-            if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
+            if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
                 is_html_webdriver = True
 
             # Only works reliably with Playwright
             visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and is_html_webdriver
-
             output = render_template("edit.html",
                                      available_processors=processors.available_processors(),
                                      browser_steps_config=browser_step_ui_config,
-                                     current_base_url=datastore.data['settings']['application']['base_url'],
                                      emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
+                                     extra_title=f" - Edit - {watch.label}",
                                      form=form,
                                      has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
                                      has_empty_checktime=using_default_check_time,
+                                     has_extra_headers_file=len(datastore.get_all_headers_in_textfile_for_watch(uuid=uuid)) > 0,
                                      is_html_webdriver=is_html_webdriver,
                                      jq_support=jq_support,
                                      playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False),
@@ -748,7 +814,6 @@ def changedetection_app(config=None, datastore_o=None):
 
         output = render_template("settings.html",
                                  form=form,
-                                 current_base_url = datastore.data['settings']['application']['base_url'],
                                  hide_remove_pass=os.getenv("SALTED_PASS", False),
                                  api_key=datastore.data['settings']['application'].get('api_access_token'),
                                  emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
@@ -756,6 +821,16 @@ def changedetection_app(config=None, datastore_o=None):
 
         return output
 
+    @app.route("/settings/reset-api-key", methods=['GET'])
+    @login_optionally_required
+    def settings_reset_api_key():
+        import secrets
+        secret = secrets.token_hex(16)
+        datastore.data['settings']['application']['api_access_token'] = secret
+        datastore.needs_write_urgent = True
+        flash("API Key was regenerated.")
+        return redirect(url_for('settings_page')+'#api')
+
     @app.route("/import", methods=['GET', "POST"])
     @login_optionally_required
     def import_page():
@@ -763,6 +838,7 @@ def changedetection_app(config=None, datastore_o=None):
         from . import forms
 
         if request.method == 'POST':
+
             from .importer import import_url_list, import_distill_io_json
 
             # URL List import
@@ -786,11 +862,32 @@ def changedetection_app(config=None, datastore_o=None):
                 for uuid in d_importer.new_uuids:
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
 
+            # XLSX importer
+            if request.files and request.files.get('xlsx_file'):
+                file = request.files['xlsx_file']
+                from .importer import import_xlsx_wachete, import_xlsx_custom
+
+                if request.values.get('file_mapping') == 'wachete':
+                    w_importer = import_xlsx_wachete()
+                    w_importer.run(data=file, flash=flash, datastore=datastore)
+                else:
+                    w_importer = import_xlsx_custom()
+                    # Building mapping of col # to col # type
+                    map = {}
+                    for i in range(10):
+                        c = request.values.get(f"custom_xlsx[col_{i}]")
+                        v = request.values.get(f"custom_xlsx[col_type_{i}]")
+                        if c and v:
+                            map[int(c)] = v
+
+                    w_importer.import_profile = map
+                    w_importer.run(data=file, flash=flash, datastore=datastore)
+
+                for uuid in w_importer.new_uuids:
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
 
-        form = forms.importForm(formdata=request.form if request.method == 'POST' else None,
-#                               data=default,
-                               )
         # Could be some remaining, or we could be on GET
+        form = forms.importForm(formdata=request.form if request.method == 'POST' else None)
         output = render_template("import.html",
                                  form=form,
                                  import_url_list_remaining="\n".join(remaining_urls),
@@ -804,7 +901,10 @@ def changedetection_app(config=None, datastore_o=None):
     def mark_all_viewed():
 
         # Save the current newest history as the most recently viewed
+        with_errors = request.args.get('with_errors') == "1"
         for watch_uuid, watch in datastore.data['watching'].items():
+            if with_errors and not watch.get('last_error'):
+                continue
             datastore.set_last_viewed(watch_uuid, int(time.time()))
 
         return redirect(url_for('index'))
@@ -860,28 +960,36 @@ def changedetection_app(config=None, datastore_o=None):
 
         # Read as binary and force decode as UTF-8
         # Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
-        try:
-            newest_version_file_contents = watch.get_history_snapshot(dates[-1])
-        except Exception as e:
-            newest_version_file_contents = "Unable to read {}.\n".format(dates[-1])
-
-        previous_version = request.args.get('previous_version')
-        previous_timestamp = dates[-2]
-        if previous_version:
-            previous_timestamp = previous_version
+        from_version = request.args.get('from_version')
+        from_version_index = -2  # second newest
+        if from_version and from_version in dates:
+            from_version_index = dates.index(from_version)
+        else:
+            from_version = dates[from_version_index]
 
         try:
-            previous_version_file_contents = watch.get_history_snapshot(previous_timestamp)
+            from_version_file_contents = watch.get_history_snapshot(dates[from_version_index])
         except Exception as e:
-            previous_version_file_contents = "Unable to read {}.\n".format(previous_timestamp)
+            from_version_file_contents = f"Unable to read to-version at index {dates[from_version_index]}.\n"
 
+        to_version = request.args.get('to_version')
+        to_version_index = -1
+        if to_version and to_version in dates:
+            to_version_index = dates.index(to_version)
+        else:
+            to_version = dates[to_version_index]
+
+        try:
+            to_version_file_contents = watch.get_history_snapshot(dates[to_version_index])
+        except Exception as e:
+            to_version_file_contents = "Unable to read to-version at index{}.\n".format(dates[to_version_index])
 
         screenshot_url = watch.get_screenshot()
 
         system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
 
         is_html_webdriver = False
-        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
+        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
             is_html_webdriver = True
 
         password_enabled_and_share_is_off = False
@@ -890,22 +998,24 @@ def changedetection_app(config=None, datastore_o=None):
 
         output = render_template("diff.html",
                                  current_diff_url=watch['url'],
-                                 current_previous_version=str(previous_version),
+                                 from_version=str(from_version),
+                                 to_version=str(to_version),
                                  extra_stylesheets=extra_stylesheets,
-                                 extra_title=" - Diff - {}".format(watch['title'] if watch['title'] else watch['url']),
+                                 extra_title=f" - Diff - {watch.label}",
                                  extract_form=extract_form,
                                  is_html_webdriver=is_html_webdriver,
                                  last_error=watch['last_error'],
                                  last_error_screenshot=watch.get_error_snapshot(),
                                  last_error_text=watch.get_error_text(),
                                  left_sticky=True,
-                                 newest=newest_version_file_contents,
+                                 newest=to_version_file_contents,
                                  newest_version_timestamp=dates[-1],
                                  password_enabled_and_share_is_off=password_enabled_and_share_is_off,
-                                 previous=previous_version_file_contents,
+                                 from_version_file_contents=from_version_file_contents,
+                                 to_version_file_contents=to_version_file_contents,
                                  screenshot=screenshot_url,
                                  uuid=uuid,
-                                 versions=dates[:-1], # All except current/last
+                                 versions=dates, # All except current/last
                                  watch_a=watch
                                  )
 
@@ -933,7 +1043,7 @@ def changedetection_app(config=None, datastore_o=None):
 
 
         is_html_webdriver = False
-        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
+        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
             is_html_webdriver = True
 
         # Never requested successfully, but we detected a fetch error
@@ -1060,8 +1170,8 @@ def changedetection_app(config=None, datastore_o=None):
                 os.path.join(datastore_o.datastore_path, list_with_tags_file), "w"
             ) as f:
                 for uuid in datastore.data["watching"]:
-                    url = datastore.data["watching"][uuid]["url"]
-                    tag = datastore.data["watching"][uuid]["tag"]
+                    url = datastore.data["watching"][uuid].get('url')
+                    tag = datastore.data["watching"][uuid].get('tags', {})
                     f.write("{} {}\r\n".format(url, tag))
 
             # Add it to the Zip
@@ -1114,8 +1224,7 @@ def changedetection_app(config=None, datastore_o=None):
             # These files should be in our subdirectory
             try:
                 # set nocache, set content-type
-                watch_dir = datastore_o.datastore_path + "/" + filename
-                response = make_response(send_from_directory(filename="elements.json", directory=watch_dir, path=watch_dir + "/elements.json"))
+                response = make_response(send_from_directory(os.path.join(datastore_o.datastore_path, filename), "elements.json"))
                 response.headers['Content-type'] = 'application/json'
                 response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
                 response.headers['Pragma'] = 'no-cache'
@@ -1149,7 +1258,7 @@ def changedetection_app(config=None, datastore_o=None):
 
         add_paused = request.form.get('edit_and_watch_submit_button') != None
         processor = request.form.get('processor', 'text_json_diff')
-        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tag').strip(), extras={'paused': add_paused, 'processor': processor})
+        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tags').strip(), extras={'paused': add_paused, 'processor': processor})
 
         if new_uuid:
             if add_paused:
@@ -1203,6 +1312,8 @@ def changedetection_app(config=None, datastore_o=None):
         # Forced recheck will skip the 'skip if content is the same' rule (, 'reprocess_existing_data': True})))
         tag = request.args.get('tag')
         uuid = request.args.get('uuid')
+        with_errors = request.args.get('with_errors') == "1"
+
         i = 0
 
         running_uuids = []
@@ -1214,20 +1325,27 @@ def changedetection_app(config=None, datastore_o=None):
                 update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
             i = 1
 
-        elif tag != None:
+        elif tag:
             # Items that have this current tag
             for watch_uuid, watch in datastore.data['watching'].items():
-                if (tag != None and tag in watch['tag']):
+                if tag in watch.get('tags', {}):
+                    if with_errors and not watch.get('last_error'):
+                        continue
                     if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
-                        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False}))
+                        update_q.put(
+                            queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False})
+                        )
                         i += 1
 
         else:
             # No tag, no uuid, add everything.
             for watch_uuid, watch in datastore.data['watching'].items():
                 if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
+                    if with_errors and not watch.get('last_error'):
+                        continue
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False}))
                     i += 1
+
         flash("{} watches queued for rechecking.".format(i))
         return redirect(url_for('index', tag=tag))
 
@@ -1258,6 +1376,13 @@ def changedetection_app(config=None, datastore_o=None):
                     datastore.data['watching'][uuid.strip()]['paused'] = False
             flash("{} watches unpaused".format(len(uuids)))
 
+        elif (op == 'mark-viewed'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.set_last_viewed(uuid, int(time.time()))
+            flash("{} watches updated".format(len(uuids)))
+
         elif (op == 'mute'):
             for uuid in uuids:
                 uuid = uuid.strip()
@@ -1280,6 +1405,13 @@ def changedetection_app(config=None, datastore_o=None):
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
             flash("{} watches queued for rechecking".format(len(uuids)))
 
+        elif (op == 'clear-history'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.clear_watch_history(uuid)
+            flash("{} watches cleared/reset.".format(len(uuids)))
+
         elif (op == 'notification-default'):
             from changedetectionio.notification import (
                 default_notification_format_for_watch
@@ -1293,6 +1425,18 @@ def changedetection_app(config=None, datastore_o=None):
                     datastore.data['watching'][uuid.strip()]['notification_format'] = default_notification_format_for_watch
             flash("{} watches set to use default notification settings".format(len(uuids)))
 
+        elif (op == 'assign-tag'):
+            op_extradata = request.form.get('op_extradata', '').strip()
+            if op_extradata:
+                tag_uuid = datastore.add_tag(name=op_extradata)
+                if op_extradata and tag_uuid:
+                    for uuid in uuids:
+                        uuid = uuid.strip()
+                        if datastore.data['watching'].get(uuid):
+                            datastore.data['watching'][uuid]['tags'].append(tag_uuid)
+
+            flash("{} watches assigned tag".format(len(uuids)))
+
         return redirect(url_for('index'))
 
     @app.route("/api/share-url", methods=['GET'])
@@ -1302,7 +1446,6 @@ def changedetection_app(config=None, datastore_o=None):
            the share-link can be imported/added"""
         import requests
         import json
-        tag = request.args.get('tag')
         uuid = request.args.get('uuid')
 
         # more for testing
@@ -1349,12 +1492,40 @@ def changedetection_app(config=None, datastore_o=None):
         # paste in etc
         return redirect(url_for('index'))
 
+    @app.route("/highlight_submit_ignore_url", methods=['POST'])
+    @login_optionally_required
+    def highlight_submit_ignore_url():
+        import re
+        mode = request.form.get('mode')
+        selection = request.form.get('selection')
+
+        uuid = request.args.get('uuid','')
+        if datastore.data["watching"].get(uuid):
+            if mode == 'exact':
+                for l in selection.splitlines():
+                    datastore.data["watching"][uuid]['ignore_text'].append(l.strip())
+            elif mode == 'digit-regex':
+                for l in selection.splitlines():
+                    # Replace any series of numbers with a regex
+                    s = re.escape(l.strip())
+                    s = re.sub(r'[0-9]+', r'\\d+', s)
+                    datastore.data["watching"][uuid]['ignore_text'].append('/' + s + '/')
+
+        return f"<a href={url_for('preview_page', uuid=uuid)}>Click to preview</a>"
+
+
     import changedetectionio.blueprint.browser_steps as browser_steps
     app.register_blueprint(browser_steps.construct_blueprint(datastore), url_prefix='/browser-steps')
 
     import changedetectionio.blueprint.price_data_follower as price_data_follower
     app.register_blueprint(price_data_follower.construct_blueprint(datastore, update_q), url_prefix='/price_data_follower')
 
+    import changedetectionio.blueprint.tags as tags
+    app.register_blueprint(tags.construct_blueprint(datastore), url_prefix='/tags')
+
+    import changedetectionio.blueprint.check_proxies as check_proxies
+    app.register_blueprint(check_proxies.construct_blueprint(datastore=datastore), url_prefix='/check_proxy')
+
 
     # @todo handle ctrl break
     ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks).start()
@@ -1394,6 +1565,7 @@ def check_for_new_version():
         # Check daily
         app.config.exit.wait(86400)
 
+
 def notification_runner():
     global notification_debug_log
     from datetime import datetime

changedetectionio/api/api_v1.py

@@ -1,3 +1,6 @@
+import os
+from distutils.util import strtobool
+
 from flask_expects_json import expects_json
 from changedetectionio import queuedWatchMetaData
 from flask_restful import abort, Resource
@@ -33,7 +36,7 @@ class Watch(Resource):
     @auth.check_token
     def get(self, uuid):
         """
-        @api {get} /api/v1/watch/:uuid Get a single watch data
+        @api {get} /api/v1/watch/:uuid Single watch - get data, recheck, pause, mute.
         @apiDescription Retrieve watch information and set muted/paused status
         @apiExample {curl} Example usage:
             curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
@@ -209,7 +212,9 @@ class CreateWatch(Resource):
         json_data = request.get_json()
         url = json_data['url'].strip()
 
-        if not validators.url(json_data['url'].strip()):
+        # If hosts that only contain alphanumerics are allowed ("localhost" for example)
+        allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
+        if not validators.url(url, simple_host=allow_simplehost):
             return "Invalid or unsupported URL", 400
 
         if json_data.get('proxy'):
@@ -218,9 +223,16 @@ class CreateWatch(Resource):
                 return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
 
         extras = copy.deepcopy(json_data)
+
+        # Because we renamed 'tag' to 'tags' but don't want to change the API (can do this in v2 of the API)
+        tags = None
+        if extras.get('tag'):
+            tags = extras.get('tag')
+            del extras['tag']
+
         del extras['url']
 
-        new_uuid = self.datastore.add_watch(url=url, extras=extras)
+        new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags)
         if new_uuid:
             self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
             return {'uuid': new_uuid}, 201
@@ -259,13 +271,16 @@ class CreateWatch(Resource):
         """
         list = {}
 
-        tag_limit = request.args.get('tag', None)
-        for k, watch in self.datastore.data['watching'].items():
-            if tag_limit:
-                if not tag_limit.lower() in watch.all_tags:
-                    continue
+        tag_limit = request.args.get('tag', '').lower()
 
-            list[k] = {'url': watch['url'],
+
+        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,

changedetectionio/blueprint/browser_steps/__init__.py

@@ -23,62 +23,139 @@
 
 from distutils.util import strtobool
 from flask import Blueprint, request, make_response
-import os
 import logging
+import os
+import re
+
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio import login_optionally_required
-browsersteps_live_ui_o = {}
-browsersteps_playwright_browser_interface = None
-browsersteps_playwright_browser_interface_browser = None
-browsersteps_playwright_browser_interface_context = None
-browsersteps_playwright_browser_interface_end_time = None
-browsersteps_playwright_browser_interface_start_time = None
 
-def cleanup_playwright_session():
+browsersteps_sessions = {}
+io_interface_context = None
 
-    global browsersteps_live_ui_o
-    global browsersteps_playwright_browser_interface
-    global browsersteps_playwright_browser_interface_browser
-    global browsersteps_playwright_browser_interface_context
-    global browsersteps_playwright_browser_interface_end_time
-    global browsersteps_playwright_browser_interface_start_time
-
-    browsersteps_live_ui_o = {}
-    browsersteps_playwright_browser_interface = None
-    browsersteps_playwright_browser_interface_browser = None
-    browsersteps_playwright_browser_interface_end_time = None
-    browsersteps_playwright_browser_interface_start_time = None
-
-    print("Cleaning up old playwright session because time was up, calling .goodbye()")
-    try:
-        browsersteps_playwright_browser_interface_context.goodbye()
-    except Exception as e:
-        print ("Got exception in shutdown, probably OK")
-        print (str(e))
-
-    browsersteps_playwright_browser_interface_context = None
-
-    print ("Cleaning up old playwright session because time was up - done")
 
 def construct_blueprint(datastore: ChangeDetectionStore):
-
     browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
 
+    def start_browsersteps_session(watch_uuid):
+        from . import nonContext
+        from . import browser_steps
+        import time
+        global browsersteps_sessions
+        global io_interface_context
+
+
+        # We keep the playwright session open for many minutes
+        keepalive_seconds = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
+
+        browsersteps_start_session = {'start_time': time.time()}
+
+        # You can only have one of these running
+        # This should be very fine to leave running for the life of the application
+        # @idea - Make it global so the pool of watch fetchers can use it also
+        if not io_interface_context:
+            io_interface_context = nonContext.c_sync_playwright()
+            # Start the Playwright context, which is actually a nodejs sub-process and communicates over STDIN/STDOUT pipes
+            io_interface_context = io_interface_context.start()
+
+        keepalive_ms = ((keepalive_seconds + 3) * 1000)
+        base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '')
+        a = "?" if not '?' in base_url else '&'
+        base_url += a + f"timeout={keepalive_ms}"
+
+        try:
+            browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(base_url)
+        except Exception as e:
+            if 'ECONNREFUSED' in str(e):
+                return make_response('Unable to start the Playwright Browser session, is it running?', 401)
+            else:
+                # Other errors, bad URL syntax, bad reply etc
+                return make_response(str(e), 401)
+
+        proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
+        proxy = None
+        if proxy_id:
+            proxy_url = datastore.proxy_list.get(proxy_id).get('url')
+            if proxy_url:
+
+                # Playwright needs separate username and password values
+                from urllib.parse import urlparse
+                parsed = urlparse(proxy_url)
+                proxy = {'server': proxy_url}
+
+                if parsed.username:
+                    proxy['username'] = parsed.username
+
+                if parsed.password:
+                    proxy['password'] = parsed.password
+
+                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_update", methods=['GET', 'POST'])
+    @browser_steps_blueprint.route("/browsersteps_start_session", methods=['GET'])
+    def browsersteps_start_session():
+        # A new session was requested, return sessionID
+
+        import uuid
+        global browsersteps_sessions
+
+        browsersteps_session_id = str(uuid.uuid4())
+        watch_uuid = request.args.get('uuid')
+
+        if not watch_uuid:
+            return make_response('No Watch UUID specified', 500)
+
+        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}
+
+    @login_optionally_required
+    @browser_steps_blueprint.route("/browsersteps_image", methods=['GET'])
+    def browser_steps_fetch_screenshot_image():
+        from flask import (
+            make_response,
+            request,
+            send_from_directory,
+        )
+        uuid = request.args.get('uuid')
+        step_n = int(request.args.get('step_n'))
+
+        watch = datastore.data['watching'].get(uuid)
+        filename = f"step_before-{step_n}.jpeg" if request.args.get('type', '') == 'before' else f"step_{step_n}.jpeg"
+
+        if step_n and watch and os.path.isfile(os.path.join(watch.watch_data_dir, filename)):
+            response = make_response(send_from_directory(directory=watch.watch_data_dir, path=filename))
+            response.headers['Content-type'] = 'image/jpeg'
+            response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+            response.headers['Pragma'] = 'no-cache'
+            response.headers['Expires'] = 0
+            return response
+
+        else:
+            return make_response('Unable to fetch image, is the URL correct? does the watch exist? does the step_type-n.jpeg exist?', 401)
+
+    # A request for an action was received
+    @login_optionally_required
+    @browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
     def browsersteps_ui_update():
         import base64
         import playwright._impl._api_types
-        import time
-
+        global browsersteps_sessions
         from changedetectionio.blueprint.browser_steps import browser_steps
 
-        global browsersteps_live_ui_o, browsersteps_playwright_browser_interface_end_time
-        global browsersteps_playwright_browser_interface_browser
-        global browsersteps_playwright_browser_interface
-        global browsersteps_playwright_browser_interface_start_time
-
-        step_n = None
         remaining =0
         uuid = request.args.get('uuid')
 
@@ -87,13 +164,9 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         if not browsersteps_session_id:
             return make_response('No browsersteps_session_id specified', 500)
 
-        # Because we don't "really" run in a context manager ( we make the playwright interface global/long-living )
-        # We need to manage the shutdown when the time is up
-        if browsersteps_playwright_browser_interface_end_time:
-            remaining = browsersteps_playwright_browser_interface_end_time-time.time()
-            if browsersteps_playwright_browser_interface_end_time and remaining <= 0:
-                cleanup_playwright_session()
-                return make_response('Browser session expired, please reload the Browser Steps interface', 401)
+        if not browsersteps_sessions.get(browsersteps_session_id):
+            return make_response('No session exists under that ID', 500)
+
 
         # Actions - step/apply/etc, do the thing and return state
         if request.method == 'POST':
@@ -112,12 +185,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             # @todo try.. accept.. nice errors not popups..
             try:
 
-                this_session = browsersteps_live_ui_o.get(browsersteps_session_id)
-                if not this_session:
-                    print("Browser exited")
-                    return make_response('Browser session ran out of time :( Please reload this page.', 401)
-
-                this_session.call_action(action_name=step_operation,
+                browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(action_name=step_operation,
                                          selector=step_selector,
                                          optional_value=step_optional_value)
 
@@ -129,99 +197,43 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             # Get visual selector ready/update its data (also use the current filter info from the page?)
             # When the last 'apply' button was pressed
             # @todo this adds overhead because the xpath selection is happening twice
-            u = this_session.page.url
+            u = browsersteps_sessions[browsersteps_session_id]['browserstepper'].page.url
             if is_last_step and u:
-                (screenshot, xpath_data) = this_session.request_visualselector_data()
+                (screenshot, xpath_data) = browsersteps_sessions[browsersteps_session_id]['browserstepper'].request_visualselector_data()
                 datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
                 datastore.save_xpath_data(watch_uuid=uuid, data=xpath_data)
 
-        # Setup interface
-        if request.method == 'GET':
+#        if not this_session.page:
+#            cleanup_playwright_session()
+#            return make_response('Browser session ran out of time :( Please reload this page.', 401)
 
-            if not browsersteps_playwright_browser_interface:
-                print("Starting connection with playwright")
-                logging.debug("browser_steps.py connecting")
+        # Screenshots and other info only needed on requesting a step (POST)
+        try:
+            state = browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
+        except playwright._impl._api_types.Error as e:
+            return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
 
-                global browsersteps_playwright_browser_interface_context
-                from . import nonContext
-                browsersteps_playwright_browser_interface_context = nonContext.c_sync_playwright()
-                browsersteps_playwright_browser_interface = browsersteps_playwright_browser_interface_context.start()
+        # Use send_file() which is way faster than read/write loop on bytes
+        import json
+        from tempfile import mkstemp
+        from flask import send_file
+        tmp_fd, tmp_file = mkstemp(text=True, suffix=".json", prefix="changedetectionio-")
 
-                time.sleep(1)
-                # At 20 minutes, some other variable is closing it
-                # @todo find out what it is and set it
-                seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
+        output = json.dumps({'screenshot': "data:image/jpeg;base64,{}".format(
+            base64.b64encode(state[0]).decode('ascii')),
+            'xpath_data': state[1],
+            'session_age_start': browsersteps_sessions[browsersteps_session_id]['browserstepper'].age_start,
+            'browser_time_remaining': round(remaining)
+        })
 
-                # keep it alive for 10 seconds more than we advertise, sometimes it helps to keep it shutting down cleanly
-                keepalive = "&timeout={}".format(((seconds_keepalive+3) * 1000))
-                try:
-                    browsersteps_playwright_browser_interface_browser = browsersteps_playwright_browser_interface.chromium.connect_over_cdp(
-                        os.getenv('PLAYWRIGHT_DRIVER_URL', '') + keepalive)
-                except Exception as e:
-                    if 'ECONNREFUSED' in str(e):
-                        return make_response('Unable to start the Playwright session properly, is it running?', 401)
+        with os.fdopen(tmp_fd, 'w') as f:
+            f.write(output)
 
-                browsersteps_playwright_browser_interface_end_time = time.time() + (seconds_keepalive-3)
-                print("Starting connection with playwright - done")
-
-            if not browsersteps_live_ui_o.get(browsersteps_session_id):
-                # Boot up a new session
-                proxy_id = datastore.get_preferred_proxy_for_watch(uuid=uuid)
-                proxy = None
-                if proxy_id:
-                    proxy_url = datastore.proxy_list.get(proxy_id).get('url')
-                    if proxy_url:
-                        proxy = {'server': proxy_url}
-                        print("Browser Steps: UUID {} Using proxy {}".format(uuid, proxy_url))
-
-                # Begin the new "Playwright Context" that re-uses the playwright interface
-                # Each session is a "Playwright Context" as a list, that uses the playwright interface
-                browsersteps_live_ui_o[browsersteps_session_id] = browser_steps.browsersteps_live_ui(
-                    playwright_browser=browsersteps_playwright_browser_interface_browser,
-                    proxy=proxy)
-                this_session = browsersteps_live_ui_o[browsersteps_session_id]
-
-        if not this_session.page:
-            cleanup_playwright_session()
-            return make_response('Browser session ran out of time :( Please reload this page.', 401)
-
-        response = None
-
-        if request.method == 'POST':
-            # Screenshots and other info only needed on requesting a step (POST)
-            try:
-                state = this_session.get_current_state()
-            except playwright._impl._api_types.Error as e:
-                return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
-
-            # Use send_file() which is way faster than read/write loop on bytes
-            import json
-            from tempfile import mkstemp
-            from flask import send_file
-            tmp_fd, tmp_file = mkstemp(text=True, suffix=".json", prefix="changedetectionio-")
-
-            output = json.dumps({'screenshot': "data:image/jpeg;base64,{}".format(
-                base64.b64encode(state[0]).decode('ascii')),
-                'xpath_data': state[1],
-                'session_age_start': this_session.age_start,
-                'browser_time_remaining': round(remaining)
-            })
-
-            with os.fdopen(tmp_fd, 'w') as f:
-                f.write(output)
-
-            response = make_response(send_file(path_or_file=tmp_file,
-                                               mimetype='application/json; charset=UTF-8',
-                                               etag=True))
-            # No longer needed
-            os.unlink(tmp_file)
-
-        elif request.method == 'GET':
-            # Just enough to get the session rolling, it will call for goto-site via POST next
-            response = make_response({
-                'session_age_start': this_session.age_start,
-                'browser_time_remaining': round(remaining)
-            })
+        response = make_response(send_file(path_or_file=tmp_file,
+                                           mimetype='application/json; charset=UTF-8',
+                                           etag=True))
+        # No longer needed
+        os.unlink(tmp_file)
 
         return response
 

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -71,19 +71,19 @@ class steppable_browser_interface():
             optional_value = str(jinja2_env.from_string(optional_value).render())
 
         action_handler(selector, optional_value)
-        self.page.wait_for_timeout(3 * 1000)
+        self.page.wait_for_timeout(1.5 * 1000)
         print("Call action done in", time.time() - now)
 
-    def action_goto_url(self, selector, value):
+    def action_goto_url(self, selector=None, value=None):
         # self.page.set_viewport_size({"width": 1280, "height": 5000})
         now = time.time()
-        response = self.page.goto(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'
+        response = self.page.goto(value, timeout=0, wait_until='load')
+        # Should be the same as the puppeteer_fetch.js methods, means, load with no timeout set (skip timeout)
+        #and also wait for seconds ?
+        #await page.waitForTimeout(1000);
+        #await page.waitForTimeout(extra_wait_ms);
         print("Time to goto URL ", time.time() - now)
+        return response
 
     def action_click_element_containing_text(self, selector=None, value=''):
         if not len(value.strip()):
@@ -99,13 +99,15 @@ class steppable_browser_interface():
         self.page.fill(selector, value, timeout=10 * 1000)
 
     def action_execute_js(self, selector, value):
-        self.page.evaluate(value)
+        response = self.page.evaluate(value)
+        return response
 
     def action_click_element(self, selector, value):
         print("Clicking element")
         if not len(selector.strip()):
             return
-        self.page.click(selector, timeout=10 * 1000, delay=randint(200, 500))
+
+        self.page.click(selector=selector, timeout=30 * 1000, delay=randint(200, 500))
 
     def action_click_element_if_exists(self, selector, value):
         import playwright._impl._api_types as _api_types
@@ -132,7 +134,7 @@ class steppable_browser_interface():
         self.page.wait_for_timeout(1000)
 
     def action_wait_for_seconds(self, selector, value):
-        self.page.wait_for_timeout(int(value) * 1000)
+        self.page.wait_for_timeout(float(value.strip()) * 1000)
 
     def action_wait_for_text(self, selector, value):
         import json

changedetectionio/blueprint/check_proxies/__init__.py

@@ -0,0 +1,118 @@
+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, watch_uuid=uuid)
+            update_handler.call_browser()
+        # 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 content_fetcher.ReplyWithContentButNoText as e:
+            txt = f"Got reply but with no content - Status code {e.status_code} - It's possible that the filters were found, but contained no usable text (or contained only an image)."
+            status.update({'status': 'ERROR', 'text': txt})
+        except Exception as e:
+            status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': 'Error: '+type(e).__name__+str(e)})
+        else:
+            status.update({'status': 'OK', 'length': len(contents), 'text': ''})
+
+        if status.get('text'):
+            status['text'] = Environment(loader=BaseLoader()).from_string('{{text|e}}').render({'text': status['text']})
+
+        status['time'] = "{:.2f}s".format(time.time() - now)
+
+        return status
+
+    def _recalc_check_status(uuid):
+
+        results = {}
+        for k, v in checks_in_progress.get(uuid, {}).items():
+            try:
+                r_1 = v.result(timeout=0.05)
+            except Exception as e:
+                # If timeout error?
+                results[k] = {'status': 'RUNNING'}
+
+            else:
+                results[k] = r_1
+
+        return results
+
+    @login_required
+    @check_proxies_blueprint.route("/<string:uuid>/status", methods=['GET'])
+    def get_recheck_status(uuid):
+        results = _recalc_check_status(uuid=uuid)
+        return results
+
+    @login_required
+    @check_proxies_blueprint.route("/<string:uuid>/start", methods=['GET'])
+    def start_check(uuid):
+
+        if not datastore.proxy_list:
+            return
+
+        if checks_in_progress.get(uuid):
+            state = _recalc_check_status(uuid=uuid)
+            for proxy_key, v in state.items():
+                if v.get('status') == 'RUNNING':
+                    return state
+        else:
+            checks_in_progress[uuid] = {}
+
+        for k, v in datastore.proxy_list.items():
+            if not checks_in_progress[uuid].get(k):
+                checks_in_progress[uuid][k] = long_task(uuid=uuid, preferred_proxy=k)
+
+        results = _recalc_check_status(uuid=uuid)
+        return results
+
+    return check_proxies_blueprint

changedetectionio/blueprint/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 +1,136 @@
+{% 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>
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
+</script>
+
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script>
+
+/*{% if emailprefix %}*/
+    /*const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');*/
+/*{% endif %}*/
+
+
+</script>
+
+<script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
+<!--<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>-->
+<script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
+
+<div class="edit-form monospaced-textarea">
+
+    <div class="tabs collapsable">
+        <ul>
+            <li class="tab" id=""><a href="#general">General</a></li>
+            <li class="tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
+            <li class="tab"><a href="#notifications">Notifications</a></li>
+        </ul>
+    </div>
+
+    <div class="box-wrap inner">
+        <form class="pure-form pure-form-stacked"
+              action="{{ url_for('tags.form_tag_edit', uuid=data.uuid) }}" method="POST">
+             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
+
+            <div class="tab-pane-inner" id="general">
+                <fieldset>
+                    <div class="pure-control-group">
+                        {{ render_field(form.title, placeholder="https://...", required=true, class="m-d") }}
+                    </div>
+                </fieldset>
+            </div>
+
+            <div class="tab-pane-inner" id="filters-and-triggers">
+                    <div class="pure-control-group">
+                        {% set field = render_field(form.include_filters,
+                            rows=5,
+                            placeholder="#example
+xpath://body/div/span[contains(@class, 'example-class')]",
+                            class="m-d")
+                        %}
+                        {{ field }}
+                        {% if '/text()' in  field %}
+                          <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br>
+                        {% endif %}
+                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br>
+
+                    <ul>
+                        <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
+                        <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
+                            <ul>
+                                <li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required,  <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
+                                {% if jq_support %}
+                                <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>.</li>
+                                {% else %}
+                                <li>jq support not installed</li>
+                                {% endif %}
+                            </ul>
+                        </li>
+                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash. To specify XPath to be used explicitly or the XPath rule starts with an XPath function: Prefix with <code>xpath:</code>
+                            <ul>
+                                <li>Example:  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath:count(//*[contains(@class, 'sametext')])</code>, <a
+                                href="http://xpather.com/" target="new">test your XPath here</a></li>
+                                <li>Example: Get all titles from an RSS feed <code>//title/text()</code></li>
+                                <li>To use XPath1.0: Prefix with <code>xpath1:</code></li>
+                            </ul>
+                            </li>
+                    </ul>
+                    Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
+                                href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
+                </span>
+                    </div>
+                <fieldset class="pure-control-group">
+                    {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
+footer
+nav
+.stockticker") }}
+                    <span class="pure-form-message-inline">
+                        <ul>
+                          <li> Remove HTML element(s) by CSS selector before text conversion. </li>
+                          <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
+                        </ul>
+                      </span>
+                </fieldset>
+
+            </div>
+
+            <div class="tab-pane-inner" id="notifications">
+                <fieldset>
+                    <div  class="pure-control-group inline-radio">
+                      {{ render_checkbox_field(form.notification_muted) }}
+                    </div>
+                    {% if is_html_webdriver %}
+                    <div class="pure-control-group inline-radio">
+                      {{ render_checkbox_field(form.notification_screenshot) }}
+                        <span class="pure-form-message-inline">
+                            <strong>Use with caution!</strong> This will easily fill up your email storage quota or flood other storages.
+                        </span>
+                    </div>
+                    {% endif %}
+                    <div class="field-group" id="notification-field-group">
+                        {% if has_default_notification_urls %}
+                        <div class="inline-warning">
+                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!" >
+                            There are <a href="{{ url_for('settings_page')}}#notifications">system-wide notification URLs enabled</a>, this form will override notification settings for this watch only &dash; an empty Notification URL list here will still send notifications.
+                        </div>
+                        {% endif %}
+                        <a href="#notifications" id="notification-setting-reset-to-default" class="pure-button button-xsmall" style="right: 20px; top: 20px; position: absolute; background-color: #5f42dd; border-radius: 4px; font-size: 70%; color: #fff">Use system defaults</a>
+
+                        {{ render_common_settings_form(form, emailprefix, settings_application) }}
+                    </div>
+                </fieldset>
+            </div>
+
+            <div id="actions">
+                <div class="pure-control-group">
+                    {{ render_button(form.save_button) }}
+                </div>
+            </div>
+        </form>
+    </div>
+</div>
+
+{% endblock %}

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

@@ -0,0 +1,60 @@
+{% 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/content_fetcher.py

@@ -1,15 +1,19 @@
-import hashlib
 from abc import abstractmethod
+from distutils.util import strtobool
+from urllib.parse import urlparse
 import chardet
+import hashlib
 import json
 import logging
 import os
 import requests
 import sys
 import time
+import urllib.parse
 
 visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4, header, footer, section, article, aside, details, main, nav, section, summary'
 
+
 class Non200ErrorCodeReceived(Exception):
     def __init__(self, status_code, url, screenshot=None, xpath_data=None, page_html=None):
         # Set this so we can use it in other parts of the app
@@ -24,10 +28,12 @@ class Non200ErrorCodeReceived(Exception):
             self.page_text = html_tools.html_to_text(page_html)
         return
 
+
 class checksumFromPreviousCheckWasTheSame(Exception):
     def __init__(self):
         return
 
+
 class JSActionExceptions(Exception):
     def __init__(self, status_code, url, screenshot, message=''):
         self.status_code = status_code
@@ -36,6 +42,7 @@ class JSActionExceptions(Exception):
         self.message = message
         return
 
+
 class BrowserStepsStepTimout(Exception):
     def __init__(self, step_n):
         self.step_n = step_n
@@ -51,6 +58,7 @@ 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
@@ -59,6 +67,7 @@ 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
@@ -69,21 +78,26 @@ class ScreenshotUnavailable(Exception):
             self.page_text = html_to_text(page_html)
         return
 
+
 class ReplyWithContentButNoText(Exception):
-    def __init__(self, status_code, url, screenshot=None):
+    def __init__(self, status_code, url, screenshot=None, has_filters=False, html_content=''):
         # Set this so we can use it in other parts of the app
         self.status_code = status_code
         self.url = url
         self.screenshot = screenshot
+        self.has_filters = has_filters
+        self.html_content = html_content
         return
 
+
 class Fetcher():
     browser_steps = None
     browser_steps_screenshot_path = None
     content = None
     error = None
     fetcher_description = "No description"
-    headers = None
+    browser_connection_url = None
+    headers = {}
     status_code = None
     webdriver_js_execute_code = None
     xpath_data = None
@@ -105,7 +119,6 @@ class Fetcher():
         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
@@ -140,6 +153,23 @@ class Fetcher():
     def is_ready(self):
         return True
 
+    def get_all_headers(self):
+        """
+        Get all headers but ensure all keys are lowercase
+        :return:
+        """
+        return {k.lower(): v for k, v in self.headers.items()}
+
+    def browser_steps_get_valid_steps(self):
+        if self.browser_steps is not None and len(self.browser_steps):
+            valid_steps = filter(
+                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+                self.browser_steps)
+
+            return valid_steps
+
+        return None
+
     def iterate_browser_steps(self):
         from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
         from playwright._impl._api_types import TimeoutError
@@ -151,14 +181,13 @@ class Fetcher():
         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)
+            valid_steps = self.browser_steps_get_valid_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))
+                self.screenshot_step("before-" + str(step_n))
+                self.save_step_html("before-" + str(step_n))
                 try:
                     optional_value = step['optional_value']
                     selector = step['selector']
@@ -173,12 +202,11 @@ class Fetcher():
                                                       optional_value=optional_value)
                     self.screenshot_step(step_n)
                     self.save_step_html(step_n)
-                except TimeoutError:
+                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
@@ -186,7 +214,9 @@ class Fetcher():
             dest = os.path.join(self.browser_steps_screenshot_path, 'step_*.jpeg')
             files = glob.glob(dest)
             for f in files:
-                os.unlink(f)
+                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)
@@ -205,6 +235,7 @@ def available_fetchers():
 
     return p
 
+
 class base_html_playwright(Fetcher):
     fetcher_description = "Playwright {}/Javascript".format(
         os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
@@ -221,14 +252,16 @@ class base_html_playwright(Fetcher):
 
     proxy = None
 
-    def __init__(self, proxy_override=None):
+    def __init__(self, proxy_override=None, browser_connection_url=None):
         super().__init__()
-        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+
         self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
-        self.command_executor = os.getenv(
-            "PLAYWRIGHT_DRIVER_URL",
-            'ws://playwright-chrome:3000'
-        ).strip('"')
+
+        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+        if not browser_connection_url:
+            self.browser_connection_url = os.getenv("PLAYWRIGHT_DRIVER_URL", 'ws://playwright-chrome:3000').strip('"')
+        else:
+            self.browser_connection_url = browser_connection_url
 
         # If any proxy settings are enabled, then we should setup the proxy object
         proxy_args = {}
@@ -246,7 +279,6 @@ class base_html_playwright(Fetcher):
 
         if self.proxy:
             # Playwright needs separate username and password values
-            from urllib.parse import urlparse
             parsed = urlparse(self.proxy.get('server'))
             if parsed.username:
                 self.proxy['username'] = parsed.username
@@ -268,6 +300,117 @@ class base_html_playwright(Fetcher):
         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:
+            # 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}"
+
+        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': {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None),
+                        'proxy_username': self.proxy.get('username', '') if self.proxy else False,
+                        'proxy_password': self.proxy.get('password', '') if self.proxy and self.proxy.get('username') 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,
@@ -278,23 +421,41 @@ class base_html_playwright(Fetcher):
             current_include_filters=None,
             is_binary=False):
 
+        # For now, USE_EXPERIMENTAL_PUPPETEER_FETCH is not supported by watches with BrowserSteps (for now!)
+        if not self.browser_steps and os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
+            if strtobool(os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH')):
+                # Temporary backup solution until we rewrite the playwright code
+                return self.run_fetch_browserless_puppeteer(
+                    url,
+                    timeout,
+                    request_headers,
+                    request_body,
+                    request_method,
+                    ignore_status_codes,
+                    current_include_filters,
+                    is_binary)
+
         from playwright.sync_api import sync_playwright
         import playwright._impl._api_types
 
         self.delete_browser_steps_screenshots()
         response = None
+
         with sync_playwright() as p:
             browser_type = getattr(p, self.browser_type)
 
             # Seemed to cause a connection Exception even tho I can see it connect
             # self.browser = browser_type.connect(self.command_executor, timeout=timeout*1000)
             # 60,000 connection timeout only
-            browser = browser_type.connect_over_cdp(self.command_executor, timeout=60000)
+            browser = browser_type.connect_over_cdp(self.browser_connection_url, timeout=60000)
+
+            # SOCKS5 with authentication is not supported (yet)
+            # https://github.com/microsoft/playwright/issues/10567
 
             # Set user agent to prevent Cloudflare from blocking the browser
             # Use the default one configured in the App.py model that's passed from fetch_site_status.py
             context = browser.new_context(
-                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
+                user_agent={k.lower(): v for k, v in request_headers.items()}.get('user-agent', None),
                 proxy=self.proxy,
                 # This is needed to enable JavaScript execution on GitHub and others
                 bypass_csp=True,
@@ -308,73 +469,61 @@ class base_html_playwright(Fetcher):
             if len(request_headers):
                 context.set_extra_http_headers(request_headers)
 
-                self.page.set_default_navigation_timeout(90000)
-                self.page.set_default_timeout(90000)
+            # Listen for all console events and handle errors
+            self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
 
-                # Listen for all console events and handle errors
-                self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
+            # Re-use as much code from browser steps as possible so its the same
+            from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+            browsersteps_interface = steppable_browser_interface()
+            browsersteps_interface.page = self.page
 
-            # 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')
+            response = browsersteps_interface.action_goto_url(value=url)
+            self.headers = response.all_headers()
 
-            except Exception as e:
-                print ("Content Fetcher > Other exception when page.goto", str(e))
+            if response is None:
                 context.close()
                 browser.close()
-                raise PageUnloadable(url=url, status_code=None, message=str(e))
+                print("Content Fetcher > Response object was none")
+                raise EmptyReply(url=url, status_code=None)
 
-            # 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)
-
+                    browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
             except playwright._impl._api_types.TimeoutError as e:
                 context.close()
                 browser.close()
                 # This can be ok, we will try to grab what we could retrieve
                 pass
             except Exception as e:
-                print ("Content Fetcher > Other exception when executing custom JS code", str(e))
+                print("Content Fetcher > Other exception when executing custom JS code", str(e))
                 context.close()
                 browser.close()
                 raise PageUnloadable(url=url, status_code=None, message=str(e))
 
-            if response is None:
-                context.close()
-                browser.close()
-                print ("Content Fetcher > Response object was none")
-                raise EmptyReply(url=url, status_code=None)
-
-            # Run Browser Steps here
-            self.iterate_browser_steps()
-
             extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-            time.sleep(extra_wait)
+            self.page.wait_for_timeout(extra_wait * 1000)
+
 
-            self.content = self.page.content()
             self.status_code = response.status
+
+            if self.status_code != 200 and not ignore_status_codes:
+
+                screenshot=self.page.screenshot(type='jpeg', full_page=True,
+                                     quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+
+                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
+
             if len(self.page.content().strip()) == 0:
                 context.close()
                 browser.close()
-                print ("Content Fetcher > Content was empty")
+                print("Content Fetcher > Content was empty")
                 raise EmptyReply(url=url, status_code=response.status)
 
-            self.status_code = response.status
-            self.headers = response.all_headers()
+            # Run Browser Steps here
+            if self.browser_steps_get_valid_steps():
+                self.iterate_browser_steps()
+                
+            self.page.wait_for_timeout(extra_wait * 1000)
 
             # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
             if current_include_filters is not None:
@@ -382,9 +531,11 @@ class base_html_playwright(Fetcher):
             else:
                 self.page.evaluate("var include_filters=''")
 
-            self.xpath_data = self.page.evaluate("async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
+            self.xpath_data = self.page.evaluate(
+                "async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
             self.instock_data = self.page.evaluate("async () => {" + self.instock_data_js + "}")
 
+            self.content = self.page.content()
             # Bug 3 in Playwright screenshot handling
             # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
             # JPEG is better here because the screenshots can be very very large
@@ -394,23 +545,23 @@ class base_html_playwright(Fetcher):
             # acceptable screenshot quality here
             try:
                 # The actual screenshot
-                self.screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+                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)
+                raise ScreenshotUnavailable(url=url, status_code=response.status_code)
 
             context.close()
             browser.close()
 
+
 class base_html_webdriver(Fetcher):
     if os.getenv("WEBDRIVER_URL"):
         fetcher_description = "WebDriver Chrome/Javascript via '{}'".format(os.getenv("WEBDRIVER_URL"))
     else:
         fetcher_description = "WebDriver Chrome/Javascript"
 
-    command_executor = ''
-
     # Configs for Proxy setup
     # In the ENV vars, is prefixed with "webdriver_", so it is for example "webdriver_sslProxy"
     selenium_proxy_settings_mappings = ['proxyType', 'ftpProxy', 'httpProxy', 'noProxy',
@@ -418,12 +569,15 @@ class base_html_webdriver(Fetcher):
                                         'socksProxy', 'socksVersion', 'socksUsername', 'socksPassword']
     proxy = None
 
-    def __init__(self, proxy_override=None):
+    def __init__(self, proxy_override=None, browser_connection_url=None):
         super().__init__()
         from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
 
         # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
-        self.command_executor = os.getenv("WEBDRIVER_URL", 'http://browser-chrome:4444/wd/hub').strip('"')
+        if not browser_connection_url:
+            self.browser_connection_url = os.getenv("WEBDRIVER_URL", 'http://browser-chrome:4444/wd/hub').strip('"')
+        else:
+            self.browser_connection_url = browser_connection_url
 
         # If any proxy settings are enabled, then we should setup the proxy object
         proxy_args = {}
@@ -456,15 +610,17 @@ class base_html_webdriver(Fetcher):
             is_binary=False):
 
         from selenium import webdriver
-        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+        from selenium.webdriver.chrome.options import Options as ChromeOptions
         from selenium.common.exceptions import WebDriverException
         # request_body, request_method unused for now, until some magic in the future happens.
 
-        # check env for WEBDRIVER_URL
+        options = ChromeOptions()
+        if self.proxy:
+            options.proxy = self.proxy
+
         self.driver = webdriver.Remote(
-            command_executor=self.command_executor,
-            desired_capabilities=DesiredCapabilities.CHROME,
-            proxy=self.proxy)
+            command_executor=self.browser_connection_url,
+            options=options)
 
         try:
             self.driver.get(url)
@@ -496,11 +652,11 @@ class base_html_webdriver(Fetcher):
     # Does the connection to the webdriver work? run a test connection.
     def is_ready(self):
         from selenium import webdriver
-        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+        from selenium.webdriver.chrome.options import Options as ChromeOptions
 
         self.driver = webdriver.Remote(
             command_executor=self.command_executor,
-            desired_capabilities=DesiredCapabilities.CHROME)
+            options=ChromeOptions())
 
         # driver.quit() seems to cause better exceptions
         self.quit()
@@ -518,8 +674,10 @@ class base_html_webdriver(Fetcher):
 class html_requests(Fetcher):
     fetcher_description = "Basic fast Plaintext/HTTP Client"
 
-    def __init__(self, proxy_override=None):
+    def __init__(self, proxy_override=None, browser_connection_url=None):
+        super().__init__()
         self.proxy_override = proxy_override
+        # browser_connection_url is none because its always 'launched locally'
 
     def run(self,
             url,
@@ -532,13 +690,17 @@ class html_requests(Fetcher):
             is_binary=False):
 
         # Make requests use a more modern looking user-agent
-        if not 'User-Agent' in request_headers:
+        if not {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None):
             request_headers['User-Agent'] = os.getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT",
                                                       'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36')
 
         proxies = {}
 
         # Allows override the proxy on a per-request basis
+
+        # https://requests.readthedocs.io/en/latest/user/advanced/#socks
+        # Should also work with `socks5://user:pass@host:port` type syntax.
+
         if self.proxy_override:
             proxies = {'http': self.proxy_override, 'https': self.proxy_override, 'ftp': self.proxy_override}
         else:

changedetectionio/diff.py

@@ -35,15 +35,19 @@ def customSequenceMatcher(before, after, include_equal=False, include_removed=Tr
 
 # only_differences - only return info about the differences, no context
 # line_feed_sep could be "<br>" or "<li>" or "\n" etc
-def render_diff(previous_version_file_contents, newest_version_file_contents, include_equal=False, include_removed=True, include_added=True, include_replaced=True, line_feed_sep="\n", include_change_type_prefix=True):
+def render_diff(previous_version_file_contents, newest_version_file_contents, include_equal=False, include_removed=True, include_added=True, include_replaced=True, line_feed_sep="\n", include_change_type_prefix=True, patch_format=False):
 
     newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
 
     if previous_version_file_contents:
-            previous_version_file_contents = [line.rstrip() for line in previous_version_file_contents.splitlines()]
+        previous_version_file_contents = [line.rstrip() for line in previous_version_file_contents.splitlines()]
     else:
         previous_version_file_contents = ""
 
+    if patch_format:
+        patch = difflib.unified_diff(previous_version_file_contents, newest_version_file_contents)
+        return line_feed_sep.join(patch)
+
     rendered_diff = customSequenceMatcher(before=previous_version_file_contents,
                                           after=newest_version_file_contents,
                                           include_equal=include_equal,
@@ -54,4 +58,5 @@ def render_diff(previous_version_file_contents, newest_version_file_contents, in
 
     # Recursively join lists
     f = lambda L: line_feed_sep.join([f(x) if type(x) is list else x for x in L])
-    return f(rendered_diff)
+    p= f(rendered_diff)
+    return p

changedetectionio/forms.py

@@ -1,5 +1,6 @@
 import os
 import re
+from distutils.util import strtobool
 
 from wtforms import (
     BooleanField,
@@ -14,20 +15,28 @@ from wtforms import (
     validators,
     widgets
 )
+from flask_wtf.file import FileField, FileAllowed
 from wtforms.fields import FieldList
+
 from wtforms.validators import ValidationError
 
+from validators.url import url as url_validator
+
+
 # default
 # each select <option data-enabled="enabled-0-0"
 from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
 
-from changedetectionio import content_fetcher
+from changedetectionio import content_fetcher, html_tools
+
 from changedetectionio.notification import (
     valid_notification_formats,
 )
 
 from wtforms.fields import FormField
 
+dictfilt = lambda x, y: dict([ (i,x[i]) for i in x if i in set(y) ])
+
 valid_method = {
     'GET',
     'POST',
@@ -37,7 +46,7 @@ valid_method = {
 }
 
 default_method = 'GET'
-
+allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
 
 class StringListField(StringField):
     widget = widgets.TextArea()
@@ -90,6 +99,29 @@ 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")])
@@ -136,7 +168,9 @@ class ValidateContentFetcherIsReady(object):
     def __call__(self, form, field):
         import urllib3.exceptions
         from changedetectionio import content_fetcher
+        return
 
+# AttributeError: module 'changedetectionio.content_fetcher' has no attribute 'extra_browser_unlocked<>ASDF213r123r'
         # Better would be a radiohandler that keeps a reference to each class
         if field.data is not None and field.data != 'system':
             klass = getattr(content_fetcher, field.data)
@@ -203,16 +237,19 @@ class ValidateJinja2Template(object):
     def __call__(self, form, field):
         from changedetectionio import notification
 
-        from jinja2 import Environment, BaseLoader, TemplateSyntaxError
+        from jinja2 import Environment, BaseLoader, TemplateSyntaxError, UndefinedError
         from jinja2.meta import find_undeclared_variables
 
 
         try:
             jinja2_env = Environment(loader=BaseLoader)
             jinja2_env.globals.update(notification.valid_tokens)
+
             rendered = jinja2_env.from_string(field.data).render()
         except TemplateSyntaxError as e:
             raise ValidationError(f"This is not a valid Jinja2 template: {e}") from e
+        except UndefinedError as e:
+            raise ValidationError(f"A variable or function is not defined: {e}") from e
 
         ast = jinja2_env.parse(field.data)
         undefined = ", ".join(find_undeclared_variables(ast))
@@ -231,18 +268,23 @@ class validateURL(object):
         self.message = message
 
     def __call__(self, form, field):
-        import validators
+        # This should raise a ValidationError() or not
+        validate_url(field.data)
 
-        try:
-            validators.url(field.data.strip())
-        except validators.ValidationFailure:
-            message = field.gettext('\'%s\' is not a valid URL.' % (field.data.strip()))
-            raise ValidationError(message)
-
-        from .model.Watch import is_safe_url
-        if not is_safe_url(field.data):
-            raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX')
+def validate_url(test_url):
+    # If hosts that only contain alphanumerics are allowed ("localhost" for example)
+    try:
+        url_validator(test_url, simple_host=allow_simplehost)
+    except validators.ValidationError:
+        #@todo check for xss
+        message = f"'{test_url}' is not a valid URL."
+        # This should be wtforms.validators.
+        raise ValidationError(message)
 
+    from .model.Watch import is_safe_url
+    if not is_safe_url(test_url):
+        # This should be wtforms.validators.
+        raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX or incorrect URL format')
 
 class ValidateListRegex(object):
     """
@@ -254,11 +296,10 @@ class ValidateListRegex(object):
     def __call__(self, form, field):
 
         for line in field.data:
-            if line[0] == '/' and line[-1] == '/':
-                # Because internally we dont wrap in /
-                line = line.strip('/')
+            if re.search(html_tools.PERL_STYLE_REGEX, line, re.IGNORECASE):
                 try:
-                    re.compile(line)
+                    regex = html_tools.perl_style_slash_enclosed_regex_to_options(line)
+                    re.compile(regex)
                 except re.error:
                     message = field.gettext('RegEx \'%s\' is not a valid regular expression.')
                     raise ValidationError(message % (line))
@@ -287,11 +328,30 @@ class ValidateCSSJSONXPATHInput(object):
                 return
 
             # Does it look like XPath?
-            if line.strip()[0] == '/':
+            if line.strip()[0] == '/' or line.strip().startswith('xpath:'):
+                if not self.allow_xpath:
+                    raise ValidationError("XPath not permitted in this field!")
+                from lxml import etree, html
+                import elementpath
+                # xpath 2.0-3.1
+                from elementpath.xpath3 import XPath3Parser
+                tree = html.fromstring("<html></html>")
+                line = line.replace('xpath:', '')
+
+                try:
+                    elementpath.select(tree, line.strip(), parser=XPath3Parser)
+                except elementpath.ElementPathError as e:
+                    message = field.gettext('\'%s\' is not a valid XPath expression. (%s)')
+                    raise ValidationError(message % (line, str(e)))
+                except:
+                    raise ValidationError("A system-error occurred when validating your XPath expression")
+
+            if line.strip().startswith('xpath1:'):
                 if not self.allow_xpath:
                     raise ValidationError("XPath not permitted in this field!")
                 from lxml import etree, html
                 tree = html.fromstring("<html></html>")
+                line = re.sub(r'^xpath1:', '', line)
 
                 try:
                     tree.xpath(line.strip())
@@ -347,7 +407,7 @@ 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"})
@@ -355,6 +415,7 @@ class quickWatchForm(Form):
 
 # 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', 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()])
@@ -367,6 +428,9 @@ class importForm(Form):
     from . import processors
     processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
     urls = TextAreaField('URLs')
+    xlsx_file = FileField('Upload .xlsx file', validators=[FileAllowed(['xlsx'], 'Must be .xlsx file!')])
+    file_mapping = SelectField('File mapping', [validators.DataRequired()], choices={('wachete', 'Wachete mapping'), ('custom','Custom mapping')})
+
 
 class SingleBrowserStep(Form):
 
@@ -382,7 +446,7 @@ class SingleBrowserStep(Form):
 class watchForm(commonSettingsForm):
 
     url = fields.URLField('URL', validators=[validateURL()])
-    tag = StringField('Group tag', [validators.Optional()], default='')
+    tags = StringTagUUID('Group tag', [validators.Optional()], default='')
 
     time_between_check = FormField(TimeBetweenCheckForm)
 
@@ -450,9 +514,15 @@ class SingleExtraProxy(Form):
 
     # maybe better to set some <script>var..
     proxy_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
-    proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "http://user:pass@...:3128", "size":50})
+    proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "socks5:// or regular proxy http://user:pass@...:3128", "size":50})
     # @todo do the validation here instead
 
+class SingleExtraBrowser(Form):
+    browser_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
+    browser_connection_url = StringField('Browser connection URL', [validators.Optional()], render_kw={"placeholder": "wss://brightdata... wss://oxylabs etc", "size":50})
+    # @todo do the validation here instead
+
+
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
     time_between_check = FormField(TimeBetweenCheckForm)
@@ -461,6 +531,7 @@ class globalSettingsRequestForm(Form):
                                   render_kw={"style": "width: 5em;"},
                                   validators=[validators.NumberRange(min=0, message="Should contain zero or more seconds")])
     extra_proxies = FieldList(FormField(SingleExtraProxy), min_entries=5)
+    extra_browsers = FieldList(FormField(SingleExtraBrowser), min_entries=5)
 
     def validate_extra_proxies(self, extra_validators=None):
         for e in self.data['extra_proxies']:
@@ -474,13 +545,20 @@ class globalSettingsRequestForm(Form):
 class globalSettingsApplicationForm(commonSettingsForm):
 
     api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
-    base_url = StringField('Base URL', validators=[validators.Optional()])
+    base_url = StringField('Notification base URL override',
+                           validators=[validators.Optional()],
+                           render_kw={"placeholder": os.getenv('BASE_URL', 'Not set')}
+                           )
     empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
     fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     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()])

changedetectionio/html_tools.py

@@ -1,23 +1,44 @@
 
 from bs4 import BeautifulSoup
 from inscriptis import get_text
-from inscriptis.model.config import ParserConfig
 from jsonpath_ng.ext import parse
 from typing import List
+from inscriptis.css_profiles import CSS_PROFILES, HtmlElement
+from inscriptis.html_properties import Display
+from inscriptis.model.config import ParserConfig
+from xml.sax.saxutils import escape as xml_escape
 import json
 import re
 
+
 # HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
 TEXT_FILTER_LIST_LINE_SUFFIX = "<br>"
 
+PERL_STYLE_REGEX = r'^/(.*?)/([a-z]*)?$'
 # 'price' , 'lowPrice', 'highPrice' are usually under here
-# all of those may or may not appear on different websites
-LD_JSON_PRODUCT_OFFER_SELECTOR = "json:$..offers"
+# All of those may or may not appear on different websites - I didnt find a way todo case-insensitive searching here
+LD_JSON_PRODUCT_OFFER_SELECTORS = ["json:$..offers", "json:$..Offers"]
 
 class JSONNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
-        
+
+
+# Doesn't look like python supports forward slash auto enclosure in re.findall
+# So convert it to inline flag "(?i)foobar" type configuration
+def perl_style_slash_enclosed_regex_to_options(regex):
+
+    res = re.search(PERL_STYLE_REGEX, regex, re.IGNORECASE)
+
+    if res:
+        flags = res.group(2) if res.group(2) else 'i'
+        regex = f"(?{flags}){res.group(1)}"
+    else:
+        # Fall back to just ignorecase as an option
+        regex = f"(?i){regex}"
+
+    return regex
+
 # Given a CSS Rule, and a blob of HTML, return the blob of HTML that matches
 def include_filters(include_filters, html_content, append_pretty_line_formatting=False):
     soup = BeautifulSoup(html_content, "html.parser")
@@ -48,12 +69,96 @@ def element_removal(selectors: List[str], html_content):
     selector = ",".join(selectors)
     return subtractive_css_selector(selector, html_content)
 
+def elementpath_tostring(obj):
+    """
+    change elementpath.select results to string type
+    # The MIT License (MIT), Copyright (c), 2018-2021, SISSA (Scuola Internazionale Superiore di Studi Avanzati)
+    # https://github.com/sissaschool/elementpath/blob/dfcc2fd3d6011b16e02bf30459a7924f547b47d0/elementpath/xpath_tokens.py#L1038
+    """
+
+    import elementpath
+    from decimal import Decimal
+    import math
+
+    if obj is None:
+        return ''
+    # https://elementpath.readthedocs.io/en/latest/xpath_api.html#elementpath.select
+    elif isinstance(obj, elementpath.XPathNode):
+        return obj.string_value
+    elif isinstance(obj, bool):
+        return 'true' if obj else 'false'
+    elif isinstance(obj, Decimal):
+        value = format(obj, 'f')
+        if '.' in value:
+            return value.rstrip('0').rstrip('.')
+        return value
+
+    elif isinstance(obj, float):
+        if math.isnan(obj):
+            return 'NaN'
+        elif math.isinf(obj):
+            return str(obj).upper()
+
+        value = str(obj)
+        if '.' in value:
+            value = value.rstrip('0').rstrip('.')
+        if '+' in value:
+            value = value.replace('+', '')
+        if 'e' in value:
+            return value.upper()
+        return value
+
+    return str(obj)
 
 # Return str Utf-8 of matched rules
-def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False):
+def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_rss=False):
+    from lxml import etree, html
+    import elementpath
+    # xpath 2.0-3.1
+    from elementpath.xpath3 import XPath3Parser
+
+    parser = etree.HTMLParser()
+    if is_rss:
+        # So that we can keep CDATA for cdata_in_document_to_text() to process
+        parser = etree.XMLParser(strip_cdata=False)
+
+    tree = html.fromstring(bytes(html_content, encoding='utf-8'), parser=parser)
+    html_block = ""
+
+    r = elementpath.select(tree, xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'}, parser=XPath3Parser)
+    #@note: //title/text() wont work where <title>CDATA..
+
+    if type(r) != list:
+        r = [r]
+
+    for element in r:
+        # When there's more than 1 match, then add the suffix to separate each line
+        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
+        # (This way each 'match' reliably has a new-line in the diff)
+        # Divs are converted to 4 whitespaces by inscriptis
+        if append_pretty_line_formatting and len(html_block) and (not hasattr( element, 'tag' ) or not element.tag in (['br', 'hr', 'div', 'p'])):
+            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
+
+        if type(element) == str:
+            html_block += element
+        elif issubclass(type(element), etree._Element) or issubclass(type(element), etree._ElementTree):
+            html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
+        else:
+            html_block += elementpath_tostring(element)
+
+    return html_block
+
+# Return str Utf-8 of matched rules
+# 'xpath1:'
+def xpath1_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_rss=False):
     from lxml import etree, html
 
-    tree = html.fromstring(bytes(html_content, encoding='utf-8'))
+    parser = None
+    if is_rss:
+        # So that we can keep CDATA for cdata_in_document_to_text() to process
+        parser = etree.XMLParser(strip_cdata=False)
+
+    tree = html.fromstring(bytes(html_content, encoding='utf-8'), parser=parser)
     html_block = ""
 
     r = tree.xpath(xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'})
@@ -76,7 +181,6 @@ def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False
 
     return html_block
 
-
 # Extract/find element
 def extract_element(find='title', html_content=''):
 
@@ -137,45 +241,58 @@ def _get_stripped_text_from_json_match(match):
 def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None):
     stripped_text_from_html = False
 
-    # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded <script type=ldjson>
+    # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded within HTML tags
     try:
         stripped_text_from_html = _parse_json(json.loads(content), json_filter)
     except json.JSONDecodeError:
 
         # Foreach <script json></script> blob.. just return the first that matches json_filter
-        s = []
+        # As a last resort, try to parse the whole <body>
         soup = BeautifulSoup(content, 'html.parser')
 
         if ensure_is_ldjson_info_type:
             bs_result = soup.findAll('script', {"type": "application/ld+json"})
         else:
             bs_result = soup.findAll('script')
+        bs_result += soup.findAll('body')
 
-
-        if not bs_result:
-            raise JSONNotFound("No parsable JSON found in this document")
-
+        bs_jsons = []
         for result in bs_result:
             # Skip empty tags, and things that dont even look like JSON
-            if not result.string or not '{' in result.string:
+            if not result.text or '{' not in result.text:
                 continue
-                
             try:
-                json_data = json.loads(result.string)
+                json_data = json.loads(result.text)
+                bs_jsons.append(json_data)
             except json.JSONDecodeError:
-                # Just skip it
+                # Skip objects which cannot be parsed
                 continue
-            else:
-                stripped_text_from_html = _parse_json(json_data, json_filter)
-                if ensure_is_ldjson_info_type:
-                    # Could sometimes be list, string or something else random
-                    if isinstance(json_data, dict):
-                        # If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
-                        # (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
-                        if json_data.get('@type', False) and json_data.get('@type','').lower() == ensure_is_ldjson_info_type.lower() and stripped_text_from_html:
-                            break
-                elif stripped_text_from_html:
-                    break
+
+        if not bs_jsons:
+            raise JSONNotFound("No parsable JSON found in this document")
+        
+        for json_data in bs_jsons:
+            stripped_text_from_html = _parse_json(json_data, json_filter)
+
+            if ensure_is_ldjson_info_type:
+                # Could sometimes be list, string or something else random
+                if isinstance(json_data, dict):
+                    # If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
+                    # (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
+                    # @type could also be a list (Product, SubType)
+                    # LD_JSON auto-extract also requires some content PLUS the ldjson to be present
+                    # 1833 - could be either str or dict, should not be anything else
+                    if json_data.get('@type') and stripped_text_from_html:
+                        try:
+                            if json_data.get('@type') == str or json_data.get('@type') == dict:
+                                types = [json_data.get('@type')] if isinstance(json_data.get('@type'), str) else json_data.get('@type')
+                                if ensure_is_ldjson_info_type.lower() in [x.lower().strip() for x in types]:
+                                    break
+                        except:
+                            continue
+
+            elif stripped_text_from_html:
+                break
 
     if not stripped_text_from_html:
         # Re 265 - Just return an empty string when filter not found
@@ -188,50 +305,56 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
 #
 # wordlist - list of regex's (str) or words (str)
 def strip_ignore_text(content, wordlist, mode="content"):
-    ignore = []
-    ignore_regex = []
-
-    # @todo check this runs case insensitive
-    for k in wordlist:
-
-        # Is it a regex?
-        if k[0] == '/':
-            ignore_regex.append(k.strip(" /"))
-        else:
-            ignore.append(k)
-
     i = 0
     output = []
+    ignore_text = []
+    ignore_regex = []
     ignored_line_numbers = []
+
+    for k in wordlist:
+        # Is it a regex?
+        res = re.search(PERL_STYLE_REGEX, k, re.IGNORECASE)
+        if res:
+            ignore_regex.append(re.compile(perl_style_slash_enclosed_regex_to_options(k)))
+        else:
+            ignore_text.append(k.strip())
+
     for line in content.splitlines():
         i += 1
         # Always ignore blank lines in this mode. (when this function gets called)
+        got_match = False
         if len(line.strip()):
-            regex_matches = False
+            for l in ignore_text:
+                if l.lower() in line.lower():
+                    got_match = True
 
-            # if any of these match, skip
-            for regex in ignore_regex:
-                try:
-                    if re.search(regex, line, re.IGNORECASE):
-                        regex_matches = True
-                except Exception as e:
-                    continue
+            if not got_match:
+                for r in ignore_regex:
+                    if r.search(line):
+                        got_match = True
 
-            if not regex_matches and not any(skip_text.lower() in line.lower() for skip_text in ignore):
+            if not got_match:
+                # Not ignored
                 output.append(line.encode('utf8'))
             else:
                 ignored_line_numbers.append(i)
 
 
-
     # Used for finding out what to highlight
     if mode == "line numbers":
         return ignored_line_numbers
 
     return "\n".encode('utf8').join(output)
 
+def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False) -> str:
+    pattern = '<!\[CDATA\[(\s*(?:.(?<!\]\]>)\s*)*)\]\]>'
+    def repl(m):
+        text = m.group(1)
+        return xml_escape(html_to_text(html_content=text)).strip()
 
-def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
+    return re.sub(pattern, repl, html_content)
+
+def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=False) -> str:
     """Converts html string to a string with just the text. If ignoring
     rendering anchor tag content is enable, anchor tag content are also
     included in the text
@@ -247,16 +370,21 @@ def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
     #  if anchor tag content flag is set to True define a config for
     #  extracting this content
     if render_anchor_tag_content:
-
         parser_config = ParserConfig(
-            annotation_rules={"a": ["hyperlink"]}, display_links=True
+            annotation_rules={"a": ["hyperlink"]},
+            display_links=True
         )
-
-    # otherwise set config to None
+    # otherwise set config to None/default
     else:
         parser_config = None
 
-    # get text and annotations via inscriptis
+    # RSS Mode - Inscriptis will treat `title` as something else.
+    # Make it as a regular block display element (//item/title)
+    # This is a bit of a hack - the real way it to use XSLT to convert it to HTML #1874
+    if is_rss:
+        html_content = re.sub(r'<title([\s>])', r'<h1\1', html_content)
+        html_content = re.sub(r'</title>', r'</h1>', html_content)
+
     text_content = get_text(html_content, config=parser_config)
 
     return text_content
@@ -264,9 +392,18 @@ def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
 
 # Does LD+JSON exist with a @type=='product' and a .price set anywhere?
 def has_ldjson_product_info(content):
+    pricing_data = ''
+
     try:
-        pricing_data = extract_json_as_string(content=content, json_filter=LD_JSON_PRODUCT_OFFER_SELECTOR, ensure_is_ldjson_info_type="product")
-    except JSONNotFound as e:
+        if not 'application/ld+json' in content:
+            return False
+
+        for filter in LD_JSON_PRODUCT_OFFER_SELECTORS:
+            pricing_data += extract_json_as_string(content=content,
+                                                  json_filter=filter,
+                                                  ensure_is_ldjson_info_type="product")
+
+    except Exception as e:
         # Totally fine
         return False
     x=bool(pricing_data)

changedetectionio/importer.py

@@ -1,6 +1,9 @@
 from abc import ABC, abstractmethod
 import time
 import validators
+from wtforms import ValidationError
+
+from changedetectionio.forms import validate_url
 
 
 class Importer():
@@ -12,6 +15,7 @@ class Importer():
         self.new_uuids = []
         self.good = 0
         self.remaining_data = []
+        self.import_profile = None
 
     @abstractmethod
     def run(self,
@@ -52,7 +56,8 @@ 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:
+            # @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}
@@ -84,7 +89,8 @@ 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:
@@ -119,11 +125,8 @@ class import_distill_io_json(Importer):
                 except IndexError:
                     pass
 
-
-                if d.get('tags', False):
-                    extras['tag'] = ", ".join(d['tags'])
-
                 new_uuid = datastore.add_watch(url=d['uri'].strip(),
+                                               tag=",".join(d.get('tags', [])),
                                                extras=extras,
                                                write_to_disk_now=False)
 
@@ -133,3 +136,167 @@ class import_distill_io_json(Importer):
                     good += 1
 
         flash("{} Imported from Distill.io in {:.2f}s, {} Skipped.".format(len(self.new_uuids), time.time() - now, len(self.remaining_data)))
+
+
+class import_xlsx_wachete(Importer):
+
+    def run(self,
+            data,
+            flash,
+            datastore,
+            ):
+
+        good = 0
+        now = time.time()
+        self.new_uuids = []
+
+        from openpyxl import load_workbook
+
+        try:
+            wb = load_workbook(data)
+        except Exception as e:
+            # @todo correct except
+            flash("Unable to read export XLSX file, something wrong with the file?", 'error')
+            return
+
+        row_id = 2
+        for row in wb.active.iter_rows(min_row=row_id):
+            try:
+                extras = {}
+                data = {}
+                for cell in row:
+                    if not cell.value:
+                        continue
+                    column_title = wb.active.cell(row=1, column=cell.column).value.strip().lower()
+                    data[column_title] = cell.value
+
+                # Forced switch to webdriver/playwright/etc
+                dynamic_wachet = str(data.get('dynamic wachet', '')).strip().lower()  # Convert bool to str to cover all cases
+                # libreoffice and others can have it as =FALSE() =TRUE(), or bool(true)
+                if 'true' in dynamic_wachet or dynamic_wachet == '1':
+                    extras['fetch_backend'] = 'html_webdriver'
+                elif 'false' in dynamic_wachet or dynamic_wachet == '0':
+                    extras['fetch_backend'] = 'html_requests'
+
+                if data.get('xpath'):
+                    # @todo split by || ?
+                    extras['include_filters'] = [data.get('xpath')]
+                if data.get('name'):
+                    extras['title'] = data.get('name').strip()
+                if data.get('interval (min)'):
+                    minutes = int(data.get('interval (min)'))
+                    hours, minutes = divmod(minutes, 60)
+                    days, hours = divmod(hours, 24)
+                    weeks, days = divmod(days, 7)
+                    extras['time_between_check'] = {'weeks': weeks, 'days': days, 'hours': hours, 'minutes': minutes, 'seconds': 0}
+
+                # At minimum a URL is required.
+                if data.get('url'):
+                    try:
+                        validate_url(data.get('url'))
+                    except ValidationError as e:
+                        print(">> import URL error", data.get('url'), str(e))
+                        flash(f"Error processing row number {row_id}, URL value was incorrect, row was skipped.", 'error')
+                        # Don't bother processing anything else on this row
+                        continue
+
+                    new_uuid = datastore.add_watch(url=data['url'].strip(),
+                                                   extras=extras,
+                                                   tag=data.get('folder'),
+                                                   write_to_disk_now=False)
+                    if new_uuid:
+                        # Straight into the queue.
+                        self.new_uuids.append(new_uuid)
+                        good += 1
+            except Exception as e:
+                print(e)
+                flash(f"Error processing row number {row_id}, check all cell data types are correct, row was skipped.", 'error')
+            else:
+                row_id += 1
+
+        flash(
+            "{} imported from Wachete .xlsx in {:.2f}s".format(len(self.new_uuids), time.time() - now))
+
+
+class import_xlsx_custom(Importer):
+
+    def run(self,
+            data,
+            flash,
+            datastore,
+            ):
+
+        good = 0
+        now = time.time()
+        self.new_uuids = []
+
+        from openpyxl import load_workbook
+
+        try:
+            wb = load_workbook(data)
+        except Exception as e:
+            # @todo correct except
+            flash("Unable to read export XLSX file, something wrong with the file?", 'error')
+            return
+
+        # @todo cehck atleast 2 rows, same in other method
+        from .forms import validate_url
+        row_i = 1
+
+        try:
+            for row in wb.active.iter_rows():
+                url = None
+                tags = None
+                extras = {}
+
+                for cell in row:
+                    if not self.import_profile.get(cell.col_idx):
+                        continue
+                    if not cell.value:
+                        continue
+
+                    cell_map = self.import_profile.get(cell.col_idx)
+
+                    cell_val = str(cell.value).strip()  # could be bool
+
+                    if cell_map == 'url':
+                        url = cell.value.strip()
+                        try:
+                            validate_url(url)
+                        except ValidationError as e:
+                            print(">> Import URL error", url, str(e))
+                            flash(f"Error processing row number {row_i}, URL value was incorrect, row was skipped.", 'error')
+                            # Don't bother processing anything else on this row
+                            url = None
+                            break
+                    elif cell_map == 'tag':
+                        tags = cell.value.strip()
+                    elif cell_map == 'include_filters':
+                        # @todo validate?
+                        extras['include_filters'] = [cell.value.strip()]
+                    elif cell_map == 'interval_minutes':
+                        hours, minutes = divmod(int(cell_val), 60)
+                        days, hours = divmod(hours, 24)
+                        weeks, days = divmod(days, 7)
+                        extras['time_between_check'] = {'weeks': weeks, 'days': days, 'hours': hours, 'minutes': minutes, 'seconds': 0}
+                    else:
+                        extras[cell_map] = cell_val
+
+                # At minimum a URL is required.
+                if url:
+                    new_uuid = datastore.add_watch(url=url,
+                                                   extras=extras,
+                                                   tag=tags,
+                                                   write_to_disk_now=False)
+                    if new_uuid:
+                        # Straight into the queue.
+                        self.new_uuids.append(new_uuid)
+                        good += 1
+        except Exception as e:
+            print(e)
+            flash(f"Error processing row number {row_i}, check all cell data types are correct, row was skipped.", 'error')
+        else:
+            row_i += 1
+
+        flash(
+            "{} imported from custom .xlsx in {:.2f}s".format(len(self.new_uuids), time.time() - now))

changedetectionio/model/App.py

@@ -16,6 +16,7 @@ class model(dict):
                 },
                 'requests': {
                     'extra_proxies': [], # Configurable extra proxies via the UI
+                    'extra_browsers': [],  # Configurable extra proxies via the UI
                     'jitter_seconds': 0,
                     'proxy': None, # Preferred proxy connection
                     'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
@@ -23,25 +24,27 @@ class model(dict):
                     'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "10")),  # Number of threads, lower is better for slow connections
                 },
                 '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,
                     'shared_diff_access': False,
-                    'webdriver_delay': None  # Extra delay in seconds before extracting text
+                    'webdriver_delay': None , # Extra delay in seconds before extracting text
+                    'tags': {} #@todo use Tag.model initialisers
                 }
             }
         }
@@ -49,3 +52,15 @@ 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

@@ -4,6 +4,7 @@ import os
 import re
 import time
 import uuid
+from pathlib import Path
 
 # Allowable protocols, protects against javascript: etc
 # file:// is further checked by ALLOW_FILE_URI
@@ -18,12 +19,16 @@ from changedetectionio.notification import (
 
 base_config = {
     'body': None,
+    'browser_steps': [],
+    'browser_steps_last_error_step': None,
     'check_unique_lines': False,  # On change-detected, compare against all history if its something new
     'check_count': 0,
+    'date_created': None,
     'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
     'extract_text': [],  # Extract text by regex after filters
     'extract_title_as_title': False,
     'fetch_backend': 'system', # plaintext, playwright etc
+    'fetch_time': 0.0,
     'processor': 'text_json_diff', # could be restock_diff or others from .processors
     'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
     'filter_text_added': True,
@@ -51,7 +56,8 @@ base_config = {
     'previous_md5_before_filters': False,  # Used for skipping changedetection entirely
     'proxy': None,  # Preferred proxy connection
     'subtractive_selectors': [],
-    'tag': None,
+    'tag': '', # Old system of text name for a tag, to be removed
+    'tags': [], # list of UUIDs to App.Tags
     'text_should_not_be_present': [],  # Text that should not present
     # Re #110, so then if this is set to None, we know to use the default value instead
     # Requires setting to None on submit if it's the same as the default
@@ -140,8 +146,14 @@ class model(dict):
                 flash(message, 'error')
                 return ''
 
+        if ready_url.startswith('source:'):
+            ready_url=ready_url.replace('source:', '')
         return ready_url
 
+    @property
+    def is_source_type_url(self):
+        return self.get('url', '').startswith('source:')
+
     @property
     def get_fetch_backend(self):
         """
@@ -165,9 +177,7 @@ class model(dict):
     @property
     def label(self):
         # Used for sorting
-        if self['title']:
-            return self['title']
-        return self['url']
+        return self.get('title') if self.get('title') else self.get('url')
 
     @property
     def last_changed(self):
@@ -231,6 +241,14 @@ class model(dict):
         fname = os.path.join(self.watch_data_dir, "history.txt")
         return os.path.isfile(fname)
 
+    @property
+    def has_browser_steps(self):
+        has_browser_steps = self.get('browser_steps') and list(filter(
+                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+                self.get('browser_steps')))
+
+        return  has_browser_steps
+
     # Returns the newest key, but if theres only 1 record, then it's counted as not being new, so return 0.
     @property
     def newest_history_key(self):
@@ -244,6 +262,38 @@ class model(dict):
         bump = self.history
         return self.__newest_history_key
 
+    # Given an arbitrary timestamp, find the closest next key
+    # For example, last_viewed = 1000 so it should return the next 1001 timestamp
+    #
+    # used for the [diff] button so it can preset a smarter from_version
+    @property
+    def get_next_snapshot_key_to_last_viewed(self):
+
+        """Unfortunately for now timestamp is stored as string key"""
+        keys = list(self.history.keys())
+        if not keys:
+            return None
+
+        last_viewed = int(self.get('last_viewed'))
+        prev_k = keys[0]
+        sorted_keys = sorted(keys, key=lambda x: int(x))
+        sorted_keys.reverse()
+
+        # When the 'last viewed' timestamp is greater than the newest snapshot, return second last
+        if last_viewed > int(sorted_keys[0]):
+            return sorted_keys[1]
+
+        for k in sorted_keys:
+            if int(k) < last_viewed:
+                if prev_k == sorted_keys[0]:
+                    # Return the second last one so we dont recommend the same version compares itself
+                    return sorted_keys[1]
+
+                return prev_k
+            prev_k = k
+
+        return keys[0]
+
     def get_history_snapshot(self, timestamp):
         import brotli
         filepath = self.history[timestamp]
@@ -454,10 +504,6 @@ class model(dict):
 
         return csv_output_filename
 
-    @property
-    # Return list of tags, stripped and lowercase, used for searching
-    def all_tags(self):
-        return [s.strip().lower() for s in self.get('tag','').split(',')]
 
     def has_special_diff_filter_options_set(self):
 
@@ -493,3 +539,13 @@ class model(dict):
         filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
         with open(filepath, 'wb') as f:
             f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
+
+    @property
+    def get_browsersteps_available_screenshots(self):
+        "For knowing which screenshots are available to show the user in BrowserSteps UI"
+        available = []
+        for f in Path(self.watch_data_dir).glob('step_before-*.jpeg'):
+            step_n=re.search(r'step_before-(\d+)', f.name)
+            if step_n:
+                available.append(step_n.group(1))
+        return available

changedetectionio/notification.py

@@ -9,6 +9,7 @@ valid_tokens = {
     'diff': '',
     'diff_added': '',
     'diff_full': '',
+    'diff_patch': '',
     'diff_removed': '',
     'diff_url': '',
     'preview_url': '',
@@ -89,10 +90,16 @@ def process_notification(n_object, datastore):
     n_body = jinja2_env.from_string(n_object.get('notification_body', default_notification_body)).render(**notification_parameters)
     n_title = jinja2_env.from_string(n_object.get('notification_title', default_notification_title)).render(**notification_parameters)
     n_format = valid_notification_formats.get(
-        n_object['notification_format'],
+        n_object.get('notification_format', default_notification_format),
         valid_notification_formats[default_notification_format],
     )
-    
+
+    # If we arrived with 'System default' then look it up
+    if n_format == default_notification_format_for_watch and datastore.data['settings']['application'].get('notification_format') != default_notification_format_for_watch:
+        # Initially text or whatever
+        n_format = datastore.data['settings']['application'].get('notification_format', valid_notification_formats[default_notification_format])
+
+
     # 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
@@ -145,9 +152,12 @@ 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)
 
@@ -168,7 +178,7 @@ def process_notification(n_object, datastore):
                 log_value = logs.getvalue()
                 if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
                     raise Exception(log_value)
-                
+
                 sent_objs.append({'title': n_title,
                                   'body': n_body,
                                   'url' : url,
@@ -186,22 +196,23 @@ 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 = ''
 
     # Create URLs to customise the notification with
-    base_url = datastore.data['settings']['application']['base_url']
+    # active_base_url - set in store.py data property
+    base_url = datastore.data['settings']['application'].get('active_base_url')
 
     watch_url = n_object['watch_url']
 
-    # Re #148 - Some people have just {{ base_url }} in the body or title, but this may break some notification services
-    #           like 'Join', so it's always best to atleast set something obvious so that they are not broken.
-    if base_url == '':
-        base_url = "<base-url-env-var-not-set>"
-
     diff_url = "{}/diff/{}".format(base_url, uuid)
     preview_url = "{}/preview/{}".format(base_url, uuid)
 
@@ -211,11 +222,12 @@ def create_notification_parameters(n_object, datastore):
     # Valid_tokens also used as a field validator
     tokens.update(
         {
-            'base_url': base_url if base_url is not None else '',
+            'base_url': base_url,
             '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_patch': n_object.get('diff_patch', ''),  # Null default in the case we use a test
             'diff_removed': n_object.get('diff_removed', ''),  # Null default in the case we use a test
             'diff_url': diff_url,
             'preview_url': preview_url,

changedetectionio/processors/__init__.py

@@ -1,15 +1,122 @@
 from abc import abstractmethod
+import os
 import hashlib
-
+import re
+from changedetectionio import content_fetcher
+from copy import deepcopy
+from distutils.util import strtobool
 
 class difference_detection_processor():
 
+    browser_steps = None
+    datastore = None
+    fetcher = None
+    screenshot = None
+    watch = None
+    xpath_data = None
 
-    def __init__(self, *args, **kwargs):
+    def __init__(self, *args, datastore, watch_uuid, **kwargs):
         super().__init__(*args, **kwargs)
+        self.datastore = datastore
+        self.watch = deepcopy(self.datastore.data['watching'].get(watch_uuid))
+
+    def call_browser(self):
+
+        # Protect against file:// access
+        if re.search(r'^file://', self.watch.get('url', '').strip(), re.IGNORECASE):
+            if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
+                raise Exception(
+                    "file:// type access is denied for security reasons."
+                )
+
+        url = self.watch.link
+
+        # Requests, playwright, other browser via wss:// etc, fetch_extra_something
+        prefer_fetch_backend = self.watch.get('fetch_backend', 'system')
+
+        # Proxy ID "key"
+        preferred_proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=self.watch.get('uuid'))
+
+        # Pluggable content self.fetcher
+        if not prefer_fetch_backend or prefer_fetch_backend == 'system':
+            prefer_fetch_backend = self.datastore.data['settings']['application'].get('fetch_backend')
+
+        # In the case that the preferred fetcher was a browser config with custom connection URL..
+        # @todo - on save watch, if its extra_browser_ then it should be obvious it will use playwright (like if its requests now..)
+        browser_connection_url = None
+        if prefer_fetch_backend.startswith('extra_browser_'):
+            (t, key) = prefer_fetch_backend.split('extra_browser_')
+            connection = list(
+                filter(lambda s: (s['browser_name'] == key), self.datastore.data['settings']['requests'].get('extra_browsers', [])))
+            if connection:
+                prefer_fetch_backend = 'base_html_playwright'
+                browser_connection_url = connection[0].get('browser_connection_url')
+
+
+        # Grab the right kind of 'fetcher', (playwright, requests, etc)
+        if hasattr(content_fetcher, prefer_fetch_backend):
+            fetcher_obj = getattr(content_fetcher, prefer_fetch_backend)
+        else:
+            # If the klass doesnt exist, just use a default
+            fetcher_obj = getattr(content_fetcher, "html_requests")
+
+
+        proxy_url = None
+        if preferred_proxy_id:
+            proxy_url = self.datastore.proxy_list.get(preferred_proxy_id).get('url')
+            print(f"Using proxy Key: {preferred_proxy_id} as Proxy URL {proxy_url}")
+
+        # Now call the fetcher (playwright/requests/etc) with arguments that only a fetcher would need.
+        # When browser_connection_url is None, it method should default to working out whats the best defaults (os env vars etc)
+        self.fetcher = fetcher_obj(proxy_override=proxy_url,
+                                   browser_connection_url=browser_connection_url
+                                   )
+
+        if self.watch.has_browser_steps:
+            self.fetcher.browser_steps = self.watch.get('browser_steps', [])
+            self.fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, self.watch.get('uuid'))
+
+        # Tweak the base config with the per-watch ones
+        request_headers = self.watch.get('headers', [])
+        request_headers.update(self.datastore.get_all_base_headers())
+        request_headers.update(self.datastore.get_all_headers_in_textfile_for_watch(uuid=self.watch.get('uuid')))
+
+        # https://github.com/psf/requests/issues/4525
+        # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
+        # do this by accident.
+        if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
+            request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
+
+        timeout = self.datastore.data['settings']['requests'].get('timeout')
+
+        request_body = self.watch.get('body')
+        request_method = self.watch.get('method')
+        ignore_status_codes = self.watch.get('ignore_status_codes', False)
+
+        # Configurable per-watch or global extra delay before extracting text (for webDriver types)
+        system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
+        if self.watch.get('webdriver_delay'):
+            self.fetcher.render_extract_delay = self.watch.get('webdriver_delay')
+        elif system_webdriver_delay is not None:
+            self.fetcher.render_extract_delay = system_webdriver_delay
+
+        if self.watch.get('webdriver_js_execute_code') is not None and self.watch.get('webdriver_js_execute_code').strip():
+            self.fetcher.webdriver_js_execute_code = self.watch.get('webdriver_js_execute_code')
+
+        # Requests for PDF's, images etc should be passwd the is_binary flag
+        is_binary = self.watch.is_pdf
+
+        # And here we go! call the right browser with browser-specific settings
+        self.fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, self.watch.get('include_filters'),
+                    is_binary=is_binary)
+
+        #@todo .quit here could go on close object, so we can run JS if change-detected
+        self.fetcher.quit()
+
+        # After init, call run_changedetection() which will do the actual change-detection
 
     @abstractmethod
-    def run(self, uuid, skip_when_checksum_same=True):
+    def run_changedetection(self, uuid, skip_when_checksum_same=True):
         update_obj = {'last_notification_error': False, 'last_error': False}
         some_data = 'xxxxx'
         update_obj["previous_md5"] = hashlib.md5(some_data.encode('utf-8')).hexdigest()

changedetectionio/processors/restock_diff.py

@@ -1,10 +1,7 @@
 
 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)
@@ -12,15 +9,17 @@ 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):
+    def run_changedetection(self, uuid, skip_when_checksum_same=True):
 
         # DeepCopy so we can be sure we don't accidently change anything by reference
         watch = deepcopy(self.datastore.data['watching'].get(uuid))
@@ -28,84 +27,24 @@ class perform_site_check(difference_detection_processor):
         if not watch:
             raise Exception("Watch no longer exists.")
 
-        # Protect against file:// access
-        if re.search(r'^file', watch.get('url', ''), re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
-            raise Exception(
-                "file:// type access is denied for security reasons."
-            )
-
         # Unset any existing notification error
         update_obj = {'last_notification_error': False, 'last_error': False}
-        extra_headers = watch.get('headers', [])
 
-        # Tweak the base config with the per-watch ones
-        request_headers = deepcopy(self.datastore.data['settings']['headers'])
-        request_headers.update(extra_headers)
-
-        # https://github.com/psf/requests/issues/4525
-        # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
-        # do this by accident.
-        if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
-            request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
-
-        timeout = self.datastore.data['settings']['requests'].get('timeout')
-
-        url = watch.link
-
-        request_body = self.datastore.data['watching'][uuid].get('body')
-        request_method = self.datastore.data['watching'][uuid].get('method')
-        ignore_status_codes = self.datastore.data['watching'][uuid].get('ignore_status_codes', False)
-
-        # Pluggable content fetcher
-        prefer_backend = watch.get_fetch_backend
-        if not prefer_backend or prefer_backend == 'system':
-            prefer_backend = self.datastore.data['settings']['application']['fetch_backend']
-
-        if hasattr(content_fetcher, prefer_backend):
-            klass = getattr(content_fetcher, prefer_backend)
-        else:
-            # If the klass doesnt exist, just use a default
-            klass = getattr(content_fetcher, "html_requests")
-
-        proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=uuid)
-        proxy_url = None
-        if proxy_id:
-            proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
-            print("UUID {} Using proxy {}".format(uuid, proxy_url))
-
-        fetcher = klass(proxy_override=proxy_url)
-
-        # Configurable per-watch or global extra delay before extracting text (for webDriver types)
-        system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
-        if watch['webdriver_delay'] is not None:
-            fetcher.render_extract_delay = watch.get('webdriver_delay')
-        elif system_webdriver_delay is not None:
-            fetcher.render_extract_delay = system_webdriver_delay
-
-        # Could be removed if requests/plaintext could also return some info?
-        if prefer_backend != 'html_webdriver':
-            raise Exception("Re-stock detection requires Chrome or compatible webdriver/playwright fetcher to work")
-
-        if watch.get('webdriver_js_execute_code') is not None and watch.get('webdriver_js_execute_code').strip():
-            fetcher.webdriver_js_execute_code = watch.get('webdriver_js_execute_code')
-
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'))
-        fetcher.quit()
-
-        self.screenshot = fetcher.screenshot
-        self.xpath_data = fetcher.xpath_data
+        self.screenshot = self.fetcher.screenshot
+        self.xpath_data = self.fetcher.xpath_data
 
         # Track the content type
-        update_obj['content_type'] = fetcher.headers.get('Content-Type', '')
-        update_obj["last_check_status"] = fetcher.get_last_status_code()
+        update_obj['content_type'] = self.fetcher.headers.get('Content-Type', '')
+        update_obj["last_check_status"] = self.fetcher.get_last_status_code()
 
         # Main detection method
         fetched_md5 = None
-        if fetcher.instock_data:
-            fetched_md5 = hashlib.md5(fetcher.instock_data.encode('utf-8')).hexdigest()
+        if self.fetcher.instock_data:
+            fetched_md5 = hashlib.md5(self.fetcher.instock_data.encode('utf-8')).hexdigest()
             # 'Possibly in stock' comes from stock-not-in-stock.js when no string found above the fold.
-            update_obj["in_stock"] = True if fetcher.instock_data == 'Possibly in stock' else False
-
+            update_obj["in_stock"] = True if self.fetcher.instock_data == 'Possibly in stock' else False
+        else:
+            raise UnableToExtractRestockData(status_code=self.fetcher.status_code)
 
         # The main thing that all this at the moment comes down to :)
         changed_detected = False
@@ -122,4 +61,4 @@ class perform_site_check(difference_detection_processor):
         # Always record the new checksum
         update_obj["previous_md5"] = fetched_md5
 
-        return changed_detected, update_obj, fetcher.instock_data.encode('utf-8')
+        return changed_detected, update_obj, self.fetcher.instock_data.encode('utf-8')

changedetectionio/processors/text_json_diff.py

@@ -1,4 +1,4 @@
-# HTML to TEXT/JSON DIFFERENCE FETCHER
+# HTML to TEXT/JSON DIFFERENCE self.fetcher
 
 import hashlib
 import json
@@ -11,17 +11,19 @@ from changedetectionio import content_fetcher, html_tools
 from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
 from copy import deepcopy
 from . import difference_detection_processor
+from ..html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
-
-name =  'Webpage Text/HTML, JSON and PDF changes'
+name = 'Webpage Text/HTML, JSON and PDF changes'
 description = 'Detects all text changes where possible'
+json_filter_prefixes = ['json:', 'jq:']
 
 class FilterNotFoundInResponse(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
 
+
 class PDFToHTMLToolNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
@@ -30,128 +32,37 @@ class PDFToHTMLToolNotFound(ValueError):
 # Some common stuff here that can be moved to a base class
 # (set_proxy_from_list)
 class perform_site_check(difference_detection_processor):
-    screenshot = None
-    xpath_data = None
 
-    def __init__(self, *args, datastore, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.datastore = datastore
-
-    # Doesn't look like python supports forward slash auto enclosure in re.findall
-    # So convert it to inline flag "foobar(?i)" type configuration
-    def forward_slash_enclosed_regex_to_options(self, regex):
-        res = re.search(r'^/(.*?)/(\w+)$', regex, re.IGNORECASE)
-
-        if res:
-            regex = res.group(1)
-            regex += '(?{})'.format(res.group(2))
-        else:
-            regex += '(?{})'.format('i')
-
-        return regex
-
-    def run(self, uuid, skip_when_checksum_same=True):
+    def run_changedetection(self, uuid, skip_when_checksum_same=True):
         changed_detected = False
+        html_content = ""
         screenshot = False  # as bytes
         stripped_text_from_html = ""
 
         # 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}
 
-        extra_headers = watch.get('headers', [])
-
-        # Tweak the base config with the per-watch ones
-        request_headers = deepcopy(self.datastore.data['settings']['headers'])
-        request_headers.update(extra_headers)
-
-        # https://github.com/psf/requests/issues/4525
-        # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
-        # do this by accident.
-        if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
-            request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
-
-        timeout = self.datastore.data['settings']['requests'].get('timeout')
-
         url = watch.link
 
-        request_body = self.datastore.data['watching'][uuid].get('body')
-        request_method = self.datastore.data['watching'][uuid].get('method')
-        ignore_status_codes = self.datastore.data['watching'][uuid].get('ignore_status_codes', False)
-
-        # source: support
-        is_source = False
-        if url.startswith('source:'):
-            url = url.replace('source:', '')
-            is_source = True
-
-        # Pluggable content fetcher
-        prefer_backend = watch.get_fetch_backend
-        if not prefer_backend or prefer_backend == 'system':
-            prefer_backend = self.datastore.data['settings']['application']['fetch_backend']
-
-        if hasattr(content_fetcher, prefer_backend):
-            klass = getattr(content_fetcher, prefer_backend)
-        else:
-            # If the klass doesnt exist, just use a default
-            klass = getattr(content_fetcher, "html_requests")
-
-        proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=uuid)
-        proxy_url = None
-        if proxy_id:
-            proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
-            print("UUID {} Using proxy {}".format(uuid, proxy_url))
-
-        fetcher = klass(proxy_override=proxy_url)
-
-        # Configurable per-watch or global extra delay before extracting text (for webDriver types)
-        system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
-        if watch['webdriver_delay'] is not None:
-            fetcher.render_extract_delay = watch.get('webdriver_delay')
-        elif system_webdriver_delay is not None:
-            fetcher.render_extract_delay = system_webdriver_delay
-
-        # Possible conflict
-        if prefer_backend == 'html_webdriver':
-            fetcher.browser_steps = watch.get('browser_steps', None)
-            fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, uuid)
-
-        if watch.get('webdriver_js_execute_code') is not None and watch.get('webdriver_js_execute_code').strip():
-            fetcher.webdriver_js_execute_code = watch.get('webdriver_js_execute_code')
-
-        # requests for PDF's, images etc should be passwd the is_binary flag
-        is_binary = watch.is_pdf
-
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'), is_binary=is_binary)
-        fetcher.quit()
-
-        self.screenshot = fetcher.screenshot
-        self.xpath_data = fetcher.xpath_data
+        self.screenshot = self.fetcher.screenshot
+        self.xpath_data = self.fetcher.xpath_data
 
         # Track the content type
-        update_obj['content_type'] = fetcher.headers.get('Content-Type', '')
+        update_obj['content_type'] = self.fetcher.get_all_headers().get('content-type', '').lower()
 
         # Watches added automatically in the queue manager will skip if its the same checksum as the previous run
         # Saves a lot of CPU
-        update_obj['previous_md5_before_filters'] = hashlib.md5(fetcher.content.encode('utf-8')).hexdigest()
+        update_obj['previous_md5_before_filters'] = hashlib.md5(self.fetcher.content.encode('utf-8')).hexdigest()
         if skip_when_checksum_same:
             if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
                 raise content_fetcher.checksumFromPreviousCheckWasTheSame()
 
-
         # 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
@@ -160,15 +71,24 @@ class perform_site_check(difference_detection_processor):
         # https://stackoverflow.com/questions/41817578/basic-method-chaining ?
         # return content().textfilter().jsonextract().checksumcompare() ?
 
-        is_json = 'application/json' in fetcher.headers.get('Content-Type', '')
+        is_json = 'application/json' in self.fetcher.get_all_headers().get('content-type', '').lower()
         is_html = not is_json
+        is_rss = False
+
+        ctype_header = self.fetcher.get_all_headers().get('content-type', '').lower()
+        # Go into RSS preprocess for converting CDATA/comment to usable text
+        if any(substring in ctype_header for substring in ['application/xml', 'application/rss', 'text/xml']):
+            if '<rss' in self.fetcher.content[:100].lower():
+                self.fetcher.content = cdata_in_document_to_text(html_content=self.fetcher.content)
+                is_rss = True
 
         # source: support, basically treat it as plaintext
-        if is_source:
+        if watch.is_source_type_url:
             is_html = False
             is_json = False
 
-        if watch.is_pdf or 'application/pdf' in fetcher.headers.get('Content-Type', '').lower():
+        inline_pdf = self.fetcher.get_all_headers().get('content-disposition', '') and '%PDF-1' in self.fetcher.content[:10]
+        if watch.is_pdf or 'application/pdf' in self.fetcher.get_all_headers().get('content-type', '').lower() or inline_pdf:
             from shutil import which
             tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
             if not which(tool):
@@ -179,34 +99,36 @@ class perform_site_check(difference_detection_processor):
                 [tool, '-stdout', '-', '-s', 'out.pdf', '-i'],
                 stdout=subprocess.PIPE,
                 stdin=subprocess.PIPE)
-            proc.stdin.write(fetcher.raw_content)
+            proc.stdin.write(self.fetcher.raw_content)
             proc.stdin.close()
-            fetcher.content = proc.stdout.read().decode('utf-8')
+            self.fetcher.content = proc.stdout.read().decode('utf-8')
             proc.wait(timeout=60)
 
             # Add a little metadata so we know if the file changes (like if an image changes, but the text is the same
             # @todo may cause problems with non-UTF8?
             metadata = "<p>Added by changedetection.io: Document checksum - {} Filesize - {} bytes</p>".format(
-                hashlib.md5(fetcher.raw_content).hexdigest().upper(),
-                len(fetcher.content))
+                hashlib.md5(self.fetcher.raw_content).hexdigest().upper(),
+                len(self.fetcher.content))
 
-            fetcher.content = fetcher.content.replace('</body>', metadata + '</body>')
+            self.fetcher.content = self.fetcher.content.replace('</body>', metadata + '</body>')
 
+        # Better would be if Watch.model could access the global data also
+        # and then use getattr https://docs.python.org/3/reference/datamodel.html#object.__getitem__
+        # https://realpython.com/inherit-python-dict/ instead of doing it procedurely
+        include_filters_from_tags = self.datastore.get_tag_overrides_for_watch(uuid=uuid, attr='include_filters')
+        include_filters_rule = [*watch.get('include_filters', []), *include_filters_from_tags]
 
-        include_filters_rule = deepcopy(watch.get('include_filters', []))
-        # include_filters_rule = watch['include_filters']
-        subtractive_selectors = watch.get(
-            "subtractive_selectors", []
-        ) + self.datastore.data["settings"]["application"].get(
-            "global_subtractive_selectors", []
-        )
+        subtractive_selectors = [*self.datastore.get_tag_overrides_for_watch(uuid=uuid, attr='subtractive_selectors'),
+                                 *watch.get("subtractive_selectors", []),
+                                 *self.datastore.data["settings"]["application"].get("global_subtractive_selectors", [])
+                                 ]
 
         # Inject a virtual LD+JSON price tracker rule
         if watch.get('track_ldjson_price_data', '') == PRICE_DATA_TRACK_ACCEPT:
-            include_filters_rule.append(html_tools.LD_JSON_PRODUCT_OFFER_SELECTOR)
+            include_filters_rule += html_tools.LD_JSON_PRODUCT_OFFER_SELECTORS
 
-        has_filter_rule = include_filters_rule and len("".join(include_filters_rule).strip())
-        has_subtractive_selectors = subtractive_selectors and len(subtractive_selectors[0].strip())
+        has_filter_rule = len(include_filters_rule) and len(include_filters_rule[0].strip())
+        has_subtractive_selectors = len(subtractive_selectors) and len(subtractive_selectors[0].strip())
 
         if is_json and not has_filter_rule:
             include_filters_rule.append("json:$")
@@ -215,33 +137,30 @@ class perform_site_check(difference_detection_processor):
         if is_json:
             # Sort the JSON so we dont get false alerts when the content is just re-ordered
             try:
-                fetcher.content = json.dumps(json.loads(fetcher.content), sort_keys=True)
+                self.fetcher.content = json.dumps(json.loads(self.fetcher.content), sort_keys=True)
             except Exception as e:
                 # Might have just been a snippet, or otherwise bad JSON, continue
                 pass
 
         if has_filter_rule:
-            json_filter_prefixes = ['json:', 'jq:']
             for filter in include_filters_rule:
                 if any(prefix in filter for prefix in json_filter_prefixes):
-                    stripped_text_from_html += html_tools.extract_json_as_string(content=fetcher.content, json_filter=filter)
+                    stripped_text_from_html += html_tools.extract_json_as_string(content=self.fetcher.content, json_filter=filter)
                     is_html = False
 
-
-
-        if is_html or is_source:
+        if is_html or watch.is_source_type_url:
 
             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-            fetcher.content = html_tools.workarounds_for_obfuscations(fetcher.content)
-            html_content = fetcher.content
+            self.fetcher.content = html_tools.workarounds_for_obfuscations(self.fetcher.content)
+            html_content = self.fetcher.content
 
             # If not JSON,  and if it's not text/plain..
-            if 'text/plain' in fetcher.headers.get('Content-Type', '').lower():
+            if 'text/plain' in self.fetcher.get_all_headers().get('content-type', '').lower():
                 # Don't run get_text or xpath/css filters on plaintext
                 stripped_text_from_html = html_content
             else:
                 # Does it have some ld+json price data? used for easier monitoring
-                update_obj['has_ldjson_price_data'] = html_tools.has_ldjson_product_info(fetcher.content)
+                update_obj['has_ldjson_price_data'] = html_tools.has_ldjson_product_info(self.fetcher.content)
 
                 # Then we assume HTML
                 if has_filter_rule:
@@ -251,13 +170,19 @@ class perform_site_check(difference_detection_processor):
                         # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
                         if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
                             html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
-                                                                    html_content=fetcher.content,
-                                                                    append_pretty_line_formatting=not is_source)
+                                                                    html_content=self.fetcher.content,
+                                                                    append_pretty_line_formatting=not watch.is_source_type_url,
+                                                                    is_rss=is_rss)
+                        elif filter_rule.startswith('xpath1:'):
+                            html_content += html_tools.xpath1_filter(xpath_filter=filter_rule.replace('xpath1:', ''),
+                                                                    html_content=self.fetcher.content,
+                                                                    append_pretty_line_formatting=not watch.is_source_type_url,
+                                                                    is_rss=is_rss)
                         else:
                             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
                             html_content += html_tools.include_filters(include_filters=filter_rule,
-                                                                       html_content=fetcher.content,
-                                                                       append_pretty_line_formatting=not is_source)
+                                                                       html_content=self.fetcher.content,
+                                                                       append_pretty_line_formatting=not watch.is_source_type_url)
 
                     if not html_content.strip():
                         raise FilterNotFoundInResponse(include_filters_rule)
@@ -265,21 +190,21 @@ class perform_site_check(difference_detection_processor):
                 if has_subtractive_selectors:
                     html_content = html_tools.element_removal(subtractive_selectors, html_content)
 
-                if is_source:
+                if watch.is_source_type_url:
                     stripped_text_from_html = html_content
                 else:
                     # extract text
                     do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
                     stripped_text_from_html = \
                         html_tools.html_to_text(
-                            html_content,
-                            render_anchor_tag_content=do_anchor
+                            html_content=html_content,
+                            render_anchor_tag_content=do_anchor,
+                            is_rss=is_rss # #1874 activate the <title workaround hack
                         )
 
         # Re #340 - return the content before the 'ignore text' was applied
         text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
-
         # @todo whitespace coming from missing rtrim()?
         # stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
         # Rewrite's the processing text based on only what diff result they want to see
@@ -289,13 +214,13 @@ class perform_site_check(difference_detection_processor):
             # needs to not include (added) etc or it may get used twice
             # Replace the processed text with the preferred result
             rendered_diff = diff.render_diff(previous_version_file_contents=watch.get_last_fetched_before_filters(),
-                                                       newest_version_file_contents=stripped_text_from_html,
-                                                       include_equal=False,  # not the same lines
-                                                       include_added=watch.get('filter_text_added', True),
-                                                       include_removed=watch.get('filter_text_removed', True),
-                                                       include_replaced=watch.get('filter_text_replaced', True),
-                                                       line_feed_sep="\n",
-                                                       include_change_type_prefix=False)
+                                             newest_version_file_contents=stripped_text_from_html,
+                                             include_equal=False,  # not the same lines
+                                             include_added=watch.get('filter_text_added', True),
+                                             include_removed=watch.get('filter_text_removed', True),
+                                             include_replaced=watch.get('filter_text_replaced', True),
+                                             line_feed_sep="\n",
+                                             include_change_type_prefix=False)
 
             watch.save_last_fetched_before_filters(text_content_before_ignored_filter)
 
@@ -310,12 +235,17 @@ class perform_site_check(difference_detection_processor):
         # Treat pages with no renderable text content as a change? No by default
         empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
         if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
-            raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot)
+            raise content_fetcher.ReplyWithContentButNoText(url=url,
+                                                            status_code=self.fetcher.get_last_status_code(),
+                                                            screenshot=screenshot,
+                                                            has_filters=has_filter_rule,
+                                                            html_content=html_content
+                                                            )
 
         # We rely on the actual text in the html output.. many sites have random script vars etc,
         # in the future we'll implement other mechanisms.
 
-        update_obj["last_check_status"] = fetcher.get_last_status_code()
+        update_obj["last_check_status"] = self.fetcher.get_last_status_code()
 
         # If there's text to skip
         # @todo we could abstract out the get_text() to handle this cleaner
@@ -331,16 +261,25 @@ class perform_site_check(difference_detection_processor):
             regex_matched_output = []
             for s_re in extract_text:
                 # incase they specified something in '/.../x'
-                regex = self.forward_slash_enclosed_regex_to_options(s_re)
-                result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
+                if re.search(PERL_STYLE_REGEX, s_re, re.IGNORECASE):
+                    regex = html_tools.perl_style_slash_enclosed_regex_to_options(s_re)
+                    result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
 
-                for l in result:
-                    if type(l) is tuple:
-                        # @todo - some formatter option default (between groups)
-                        regex_matched_output += list(l) + [b'\n']
-                    else:
-                        # @todo - some formatter option default (between each ungrouped result)
-                        regex_matched_output += [l] + [b'\n']
+                    for l in result:
+                        if type(l) is tuple:
+                            # @todo - some formatter option default (between groups)
+                            regex_matched_output += list(l) + [b'\n']
+                        else:
+                            # @todo - some formatter option default (between each ungrouped result)
+                            regex_matched_output += [l] + [b'\n']
+                else:
+                    # Doesnt look like regex, just hunt for plaintext and return that which matches
+                    # `stripped_text_from_html` will be bytes, so we must encode s_re also to bytes
+                    r = re.compile(re.escape(s_re.encode('utf-8')), re.IGNORECASE)
+                    res = r.findall(stripped_text_from_html)
+                    if res:
+                        for match in res:
+                            regex_matched_output += [match] + [b'\n']
 
             # Now we will only show what the regex matched
             stripped_text_from_html = b''
@@ -394,7 +333,7 @@ class perform_site_check(difference_detection_processor):
         if is_html:
             if self.datastore.data['settings']['application'].get('extract_title_as_title') or watch['extract_title_as_title']:
                 if not watch['title'] or not len(watch['title']):
-                    update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
+                    update_obj['title'] = html_tools.extract_element(find='title', html_content=self.fetcher.content)
 
         if changed_detected:
             if watch.get('check_unique_lines', False):

changedetectionio/res/puppeteer_fetch.js

@@ -0,0 +1,190 @@
+module.exports = async ({page, context}) => {
+
+    var {
+        url,
+        execute_js,
+        user_agent,
+        extra_wait_ms,
+        req_headers,
+        include_filters,
+        xpath_element_js,
+        screenshot_quality,
+        proxy_username,
+        proxy_password,
+        disk_cache_dir,
+        no_cache_list,
+        block_url_list,
+    } = context;
+
+    await page.setBypassCSP(true)
+    await page.setExtraHTTPHeaders(req_headers);
+
+    if (user_agent) {
+        await page.setUserAgent(user_agent);
+    }
+    // https://ourcodeworld.com/articles/read/1106/how-to-solve-puppeteer-timeouterror-navigation-timeout-of-30000-ms-exceeded
+
+    await page.setDefaultNavigationTimeout(0);
+
+    if (proxy_username) {
+        // Setting Proxy-Authentication header is deprecated, and doing so can trigger header change errors from Puppeteer
+        // https://github.com/puppeteer/puppeteer/issues/676 ?
+        // https://help.brightdata.com/hc/en-us/articles/12632549957649-Proxy-Manager-How-to-Guides#h_01HAKWR4Q0AFS8RZTNYWRDFJC2
+        // https://cri.dev/posts/2020-03-30-How-to-solve-Puppeteer-Chrome-Error-ERR_INVALID_ARGUMENT/
+        await page.authenticate({
+            username: proxy_username,
+            password: proxy_password
+        });
+    }
+
+    await page.setViewport({
+        width: 1024,
+        height: 768,
+        deviceScaleFactor: 1,
+    });
+
+    await page.setRequestInterception(true);
+    if (disk_cache_dir) {
+        console.log(">>>>>>>>>>>>>>> LOCAL DISK CACHE ENABLED <<<<<<<<<<<<<<<<<<<<<");
+    }
+    const fs = require('fs');
+    const crypto = require('crypto');
+
+    function file_is_expired(file_path) {
+        if (!fs.existsSync(file_path)) {
+            return true;
+        }
+        var stats = fs.statSync(file_path);
+        const now_date = new Date();
+        const expire_seconds = 300;
+        if ((now_date / 1000) - (stats.mtime.getTime() / 1000) > expire_seconds) {
+            console.log("CACHE EXPIRED: " + file_path);
+            return true;
+        }
+        return false;
+
+    }
+
+    page.on('request', async (request) => {
+        // General blocking of requests that waste traffic
+        if (block_url_list.some(substring => request.url().toLowerCase().includes(substring))) return request.abort();
+
+        if (disk_cache_dir) {
+            const url = request.url();
+            const key = crypto.createHash('md5').update(url).digest("hex");
+            const dir_path = disk_cache_dir + key.slice(0, 1) + '/' + key.slice(1, 2) + '/' + key.slice(2, 3) + '/';
+
+            // https://stackoverflow.com/questions/4482686/check-synchronously-if-file-directory-exists-in-node-js
+
+            if (fs.existsSync(dir_path + key)) {
+                console.log("* CACHE HIT , using - " + dir_path + key + " - " + url);
+                const cached_data = fs.readFileSync(dir_path + key);
+                // @todo headers can come from dir_path+key+".meta" json file
+                request.respond({
+                    status: 200,
+                    //contentType: 'text/html', //@todo
+                    body: cached_data
+                });
+                return;
+            }
+        }
+        request.continue();
+    });
+
+
+    if (disk_cache_dir) {
+        page.on('response', async (response) => {
+            const url = response.url();
+            // Basic filtering for sane responses
+            if (response.request().method() != 'GET' || response.request().resourceType() == 'xhr' || response.request().resourceType() == 'document' || response.status() != 200) {
+                console.log("Skipping (not useful) - Status:" + response.status() + " Method:" + response.request().method() + " ResourceType:" + response.request().resourceType() + " " + url);
+                return;
+            }
+            if (no_cache_list.some(substring => url.toLowerCase().includes(substring))) {
+                console.log("Skipping (no_cache_list) - " + url);
+                return;
+            }
+            if (url.toLowerCase().includes('data:')) {
+                console.log("Skipping (embedded-data) - " + url);
+                return;
+            }
+            response.buffer().then(buffer => {
+                if (buffer.length > 100) {
+                    console.log("Cache - Saving " + response.request().method() + " - " + url + " - " + response.request().resourceType());
+
+                    const key = crypto.createHash('md5').update(url).digest("hex");
+                    const dir_path = disk_cache_dir + key.slice(0, 1) + '/' + key.slice(1, 2) + '/' + key.slice(2, 3) + '/';
+
+                    if (!fs.existsSync(dir_path)) {
+                        fs.mkdirSync(dir_path, {recursive: true})
+                    }
+
+                    if (fs.existsSync(dir_path + key)) {
+                        if (file_is_expired(dir_path + key)) {
+                            fs.writeFileSync(dir_path + key, buffer);
+                        }
+                    } else {
+                        fs.writeFileSync(dir_path + key, buffer);
+                    }
+                }
+            });
+        });
+    }
+
+    const r = await page.goto(url, {
+        waitUntil: 'load'
+    });
+
+    await page.waitForTimeout(1000);
+    await page.waitForTimeout(extra_wait_ms);
+
+    if (execute_js) {
+        await page.evaluate(execute_js);
+        await page.waitForTimeout(200);
+    }
+
+    var xpath_data;
+    var instock_data;
+    try {
+        // Not sure the best way here, in the future this should be a new package added to npm then run in 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

@@ -4,35 +4,60 @@ function isItemInStock() {
     '0 in stock',
     'agotado',
     'artikel zurzeit vergriffen',
-    'available for back order',
-    'backordered',
-    'brak w magazynie',
-    'brak na stanie',
-    'coming soon',
-    'currently unavailable',
-    'en rupture de stock',
     'as soon as stock is available',
+    'ausverkauft', // sold out
+    'available for back order',
+    'back-order or out of stock',
+    'backordered',
+    'benachrichtigt mich', // notify me
+    'brak na stanie',
+    'brak w magazynie',
+    'coming soon',
+    'currently have any tickets for this',
+    'currently unavailable',
+    'dostępne wkrótce',
+    'en rupture de stock',
+    'ist derzeit nicht auf lager',
+    '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',
-    'não estamos a aceitar encomendas',
     'produkt niedostępny',
-    'no longer in stock',
     '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',
+    '已售完',
   ];
 
+
+  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) {
@@ -43,13 +68,39 @@ function isItemInStock() {
         elementText = element.textContent.toLowerCase();
       }
 
-      for (const outOfStockText of outOfStockTexts) {
-        if (elementText.includes(outOfStockText)) {
-          return elementText; // item is out of stock
+      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.
 }
 

changedetectionio/res/xpath_element_scraper.js

@@ -8,8 +8,14 @@
 // Some pages like https://www.londonstockexchange.com/stock/NCCL/ncondezi-energy-limited/analysis
 // will automatically force a scroll somewhere, so include the position offset
 // Lets hope the position doesnt change while we iterate the bbox's, but this is better than nothing
+var scroll_y = 0;
+try {
+    scroll_y = +document.documentElement.scrollTop || document.body.scrollTop
+} catch (e) {
+    console.log(e);
+}
+
 
-var scroll_y=+document.documentElement.scrollTop || document.body.scrollTop
 
 // Include the getXpath script directly, easier than fetching
 function getxpath(e) {
@@ -38,15 +44,15 @@ const findUpTag = (el) => {
     if (el.name !== undefined && el.name.length) {
         var proposed = el.tagName + "[name=" + el.name + "]";
         var proposed_element = window.document.querySelectorAll(proposed);
-        if(proposed_element.length) {
+        if (proposed_element.length) {
             if (proposed_element.length === 1) {
                 return proposed;
             } else {
                 // Some sites change ID but name= stays the same, we can hit it if we know the index
                 // Find all the elements that match and work out the input[n]
-                var n=Array.from(proposed_element).indexOf(el);
+                var n = Array.from(proposed_element).indexOf(el);
                 // Return a Playwright selector for nthinput[name=zipcode]
-                return proposed+" >> nth="+n;
+                return proposed + " >> nth=" + n;
             }
         }
     }
@@ -164,9 +170,12 @@ if (include_filters.length) {
 
         try {
             // is it xpath?
-            if (f.startsWith('/') || f.startsWith('xpath:')) {
-                q = document.evaluate(f.replace('xpath:', ''), document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
+            if (f.startsWith('/') || f.startsWith('xpath')) {
+                var qry_f = f.replace(/xpath(:|\d:)/, '')
+                console.log("[xpath] Scanning for included filter " + qry_f)
+                q = document.evaluate(qry_f, document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
             } else {
+                console.log("[css] Scanning for included filter " + f)
                 q = document.querySelector(f);
             }
         } catch (e) {
@@ -176,8 +185,18 @@ if (include_filters.length) {
         }
 
         if (q) {
+            // Try to resolve //something/text() back to its /something so we can atleast get the bounding box
+            try {
+                if (typeof q.nodeName == 'string' && q.nodeName === '#text') {
+                    q = q.parentElement
+                }
+            } catch (e) {
+                console.log(e)
+                console.log("xpath_element_scraper: #text resolver")
+            }
+
             // #1231 - IN the case XPath attribute filter is applied, we will have to traverse up and find the element.
-            if (q.hasOwnProperty('getBoundingClientRect')) {
+            if (typeof q.getBoundingClientRect == 'function') {
                 bbox = q.getBoundingClientRect();
                 console.log("xpath_element_scraper: Got filter element, scroll from top was " + scroll_y)
             } else {
@@ -186,7 +205,8 @@ if (include_filters.length) {
                     bbox = q.ownerElement.getBoundingClientRect();
                     console.log("xpath_element_scraper: Got filter by ownerElement element, scroll from top was " + scroll_y)
                 } catch (e) {
-                    console.log("xpath_element_scraper: error looking up ownerElement")
+                    console.log(e)
+                    console.log("xpath_element_scraper: error looking up q.ownerElement")
                 }
             }
         }

changedetectionio/run_custom_browser_url_tests.sh

@@ -0,0 +1,44 @@
+#!/bin/bash
+
+# run some tests and look if the 'custom-browser-search-string=1' connect string appeared in the correct containers
+
+# enable debug
+set -x
+
+# A extra browser is configured, but we never chose to use it, so it should NOT show in the logs
+docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/custom_browser_url/test_custom_browser_url.py::test_request_not_via_custom_browser_url'
+docker logs browserless-custom-url &>log.txt
+grep 'custom-browser-search-string=1' log.txt
+if [ $? -ne 1 ]
+then
+  echo "Saw a request in 'browserless-custom-url' container with 'custom-browser-search-string=1' when I should not"
+  exit 1
+fi
+
+docker logs browserless &>log.txt
+grep 'custom-browser-search-string=1' log.txt
+if [ $? -ne 1 ]
+then
+  echo "Saw a request in 'browser' container with 'custom-browser-search-string=1' when I should not"
+  exit 1
+fi
+
+# Special connect string should appear in the custom-url container, but not in the 'default' one
+docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/custom_browser_url/test_custom_browser_url.py::test_request_via_custom_browser_url'
+docker logs browserless-custom-url &>log.txt
+grep 'custom-browser-search-string=1' log.txt
+if [ $? -ne 0 ]
+then
+  echo "Did not see request in 'browserless-custom-url' container with 'custom-browser-search-string=1' when I should"
+  exit 1
+fi
+
+docker logs browserless &>log.txt
+grep 'custom-browser-search-string=1' log.txt
+if [ $? -ne 1 ]
+then
+  echo "Saw a request in 'browser' container with 'custom-browser-search-string=1' when I should not"
+  exit 1
+fi
+
+

changedetectionio/run_proxy_tests.sh

@@ -2,12 +2,48 @@
 
 # exit when any command fails
 set -e
+# enable debug
+set -x
 
 # Test proxy list handling, starting two squids on different ports
 # Each squid adds a different header to the response, which is the main thing we test for.
 docker run --network changedet-network -d --name squid-one --hostname squid-one --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
 docker run --network changedet-network -d --name squid-two --hostname squid-two --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
 
+# SOCKS5 related - start simple Socks5 proxy server
+# SOCKSTEST=xyz should show in the logs of this service to confirm it fetched
+docker run --network changedet-network -d --hostname socks5proxy --name socks5proxy -p 1080:1080 -e PROXY_USER=proxy_user123 -e PROXY_PASSWORD=proxy_pass123 serjs/go-socks5-proxy
+docker run --network changedet-network -d --hostname socks5proxy-noauth -p 1081:1080 --name socks5proxy-noauth  serjs/go-socks5-proxy
+
+echo "---------------------------------- SOCKS5 -------------------"
+# SOCKS5 related - test from proxies.json
+docker run --network changedet-network \
+  -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
+  --rm \
+  -e "SOCKSTEST=proxiesjson" \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+
+# SOCKS5 related - by manually entering in UI
+docker run --network changedet-network \
+  --rm \
+  -e "SOCKSTEST=manual" \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy.py'
+
+# SOCKS5 related - test from proxies.json via playwright - NOTE- PLAYWRIGHT DOESNT SUPPORT AUTHENTICATING PROXY
+docker run --network changedet-network \
+  -e "SOCKSTEST=manual-playwright" \
+  -v `pwd`/tests/proxy_socks5/proxies.json-example-noauth:/app/changedetectionio/test-datastore/proxies.json \
+  -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" \
+  --rm \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+
+echo "socks5 server logs"
+docker logs socks5proxy
+echo "----------------------------------"
+
 # Used for configuring a custom proxy URL via the UI
 docker run --network changedet-network -d \
   --name squid-custom \
@@ -19,7 +55,6 @@ docker run --network changedet-network -d \
 
 
 ## 2nd test actually choose the preferred proxy from proxies.json
-
 docker run --network changedet-network \
   -v `pwd`/tests/proxy_list/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
   test-changedetectionio \
@@ -44,7 +79,6 @@ 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'
@@ -58,4 +92,25 @@ then
   exit 1
 fi
 
+# Test "no-proxy" option
+docker run --network changedet-network \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_list/test_noproxy.py'
+
+# We need to handle grep returning 1
+set +e
+# Check request was never seen in any container
+for c in $(echo "squid-one squid-two squid-custom"); do
+  echo Checking $c
+  docker logs $c &> $c.txt
+  grep noproxy $c.txt
+  if [ $? -ne 1 ]
+  then
+    echo "Saw request for noproxy in $c container"
+    cat $c.txt
+    exit 1
+  fi
+done
+
+
 docker kill squid-one squid-two squid-custom

changedetectionio/static/images/brightdata.svg

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

changedetectionio/static/images/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/js/browser-steps.js

@@ -114,11 +114,11 @@ $(document).ready(function () {
             e.preventDefault()
         });
 
+        // When the mouse moves we know which element it should be above
+        // mousedown will link that to the UI (select the right action, highlight etc)
         $('#browsersteps-selector-canvas').bind('mousedown', function (e) {
             // https://developer.mozilla.org/en-US/docs/Web/API/MouseEvent
             e.preventDefault()
-            console.log(e);
-            console.log("current xpath in index is " + current_selected_i);
             last_click_xy = {'x': parseInt((1 / x_scale) * e.offsetX), 'y': parseInt((1 / y_scale) * e.offsetY)}
             process_selected(current_selected_i);
             current_selected_i = false;
@@ -132,6 +132,7 @@ $(document).ready(function () {
             }
         });
 
+        // Debounce and find the current most 'interesting' element we are hovering above
         $('#browsersteps-selector-canvas').bind('mousemove', function (e) {
             if (!xpath_data) {
                 return;
@@ -151,41 +152,40 @@ $(document).ready(function () {
             current_selected_i = false;
             // Reverse order - the most specific one should be deeper/"laster"
             // Basically, find the most 'deepest'
-            //$('#browsersteps-selector-canvas').css('cursor', 'pointer');
-            for (var i = xpath_data['size_pos'].length; i !== 0; i--) {
-                // draw all of them? let them choose somehow?
-                var sel = xpath_data['size_pos'][i - 1];
+            var possible_elements = [];
+            xpath_data['size_pos'].forEach(function (item, index) {
                 // If we are in a bounding-box
-                if (e.offsetY > sel.top * y_scale && e.offsetY < sel.top * y_scale + sel.height * y_scale
+                if (e.offsetY > item.top * y_scale && e.offsetY < item.top * y_scale + item.height * y_scale
                     &&
-                    e.offsetX > sel.left * y_scale && e.offsetX < sel.left * y_scale + sel.width * y_scale
+                    e.offsetX > item.left * y_scale && e.offsetX < item.left * y_scale + item.width * y_scale
 
                 ) {
-                    // Only highlight these interesting types
-                    if (1) {
-                        ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                        ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                        current_selected_i = i - 1;
-                        break;
-
-                        // find the smallest one at this x,y
-                        // does it mean sort the xpath list by size (w*h) i think so!
-                    } else {
-
-                        if (include_text_elements[0].checked === true) {
-                            // blue one with background instead?
-                            ctx.fillStyle = 'rgba(0,0,255, 0.1)';
-                            ctx.strokeStyle = 'rgba(0,0,200, 0.7)';
-                            $('#browsersteps-selector-canvas').css('cursor', 'grab');
-                            ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                            ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                            current_selected_i = i - 1;
-                            break;
-                        }
+                    // There could be many elements here, record them all and then we'll find out which is the most 'useful'
+                    // (input, textarea, button, A etc)
+                    if (item.width < xpath_data['browser_width']) {
+                        possible_elements.push(item);
                     }
                 }
+            });
+
+            // Find the best one
+            if (possible_elements.length) {
+                possible_elements.forEach(function (item, index) {
+                  if (["a", "input", "textarea", "button"].includes(item['tagName'])) {
+                      current_selected_i = item;
+                  }
+                });
+
+                if (!current_selected_i) {
+                    current_selected_i = possible_elements[0];
+                }
+
+                sel = xpath_data['size_pos'][current_selected_i];
+                ctx.strokeRect(current_selected_i.left * x_scale, current_selected_i.top * y_scale, current_selected_i.width * x_scale, current_selected_i.height * y_scale);
+                ctx.fillRect(current_selected_i.left * x_scale, current_selected_i.top * y_scale, current_selected_i.width * x_scale, current_selected_i.height * y_scale);
             }
 
+
         }.debounce(10));
     });
 
@@ -195,45 +195,37 @@ $(document).ready(function () {
 
 
     // callback for clicking on an xpath on the canvas
-    function process_selected(xpath_data_index) {
+    function process_selected(selected_in_xpath_list) {
         found_something = false;
         var first_available = $("ul#browser_steps li.empty").first();
 
 
-        if (xpath_data_index !== false) {
+        if (selected_in_xpath_list !== false) {
             // Nothing focused, so fill in a new one
             // if inpt type button or <button>
             // from the top, find the next not used one and use it
-            var x = xpath_data['size_pos'][xpath_data_index];
+            var x = selected_in_xpath_list;
             console.log(x);
             if (x && first_available.length) {
                 // @todo will it let you click shit that has a layer ontop? probably not.
-                if (x['tagtype'] === 'text' || x['tagtype'] === 'email' || x['tagName'] === 'textarea' || x['tagtype'] === 'password' || x['tagtype'] === 'search') {
+                if (x['tagtype'] === 'text' || x['tagtype'] === 'number' || x['tagtype'] === 'email' || x['tagName'] === 'textarea' || x['tagtype'] === 'password' || x['tagtype'] === 'search') {
                     $('select', first_available).val('Enter text in field').change();
                     $('input[type=text]', first_available).first().val(x['xpath']);
                     $('input[placeholder="Value"]', first_available).addClass('ok').click().focus();
                     found_something = true;
                 } else {
-                    if (x['isClickable'] || x['tagName'].startsWith('h') || x['tagName'] === 'a' || x['tagName'] === 'button' || x['tagtype'] === 'submit' || x['tagtype'] === 'checkbox' || x['tagtype'] === 'radio' || x['tagtype'] === 'li') {
+                    // There's no good way (that I know) to find if this
+                    // see https://stackoverflow.com/questions/446892/how-to-find-event-listeners-on-a-dom-node-in-javascript-or-in-debugging
+                    // https://codepen.io/azaslavsky/pen/DEJVWv
+
+                    // So we dont know if its really a clickable element or not :-(
+                    // Assume it is - then we dont fill the pages with unreliable "Click X,Y" selections
+                    // If you switch to "Click X,y" after an element here is setup, it will give the last co-ords anyway
+                    //if (x['isClickable'] || x['tagName'].startsWith('h') || x['tagName'] === 'a' || x['tagName'] === 'button' || x['tagtype'] === 'submit' || x['tagtype'] === 'checkbox' || x['tagtype'] === 'radio' || x['tagtype'] === 'li') {
                         $('select', first_available).val('Click element').change();
                         $('input[type=text]', first_available).first().val(x['xpath']);
                         found_something = true;
-                    }
-                }
-
-                first_available.xpath_data_index = xpath_data_index;
-
-                if (!found_something) {
-                    if (include_text_elements[0].checked === true) {
-                        // Suggest that we use as filter?
-                        // @todo filters should always be in the last steps, nothing non-filter after it
-                        found_something = true;
-                        ctx.strokeStyle = 'rgba(0,0,255, 0.9)';
-                        ctx.fillStyle = 'rgba(0,0,255, 0.1)';
-                        $('select', first_available).val('Extract text and use as filter').change();
-                        $('input[type=text]', first_available).first().val(x['xpath']);
-                        include_text_elements[0].checked = false;
-                    }
+                    //}
                 }
             }
         }
@@ -248,7 +240,7 @@ $(document).ready(function () {
 
     function start() {
         console.log("Starting browser-steps UI");
-        browsersteps_session_id = Date.now();
+        browsersteps_session_id = false;
         // @todo This setting of the first one should be done at the datalayer but wtforms doesnt wanna play nice
         $('#browser_steps >li:first-child').removeClass('empty');
         set_first_gotosite_disabled();
@@ -256,7 +248,7 @@ $(document).ready(function () {
         $('.clear,.remove', $('#browser_steps >li:first-child')).hide();
         $.ajax({
             type: "GET",
-            url: browser_steps_sync_url + "&browsersteps_session_id=" + browsersteps_session_id,
+            url: browser_steps_start_url,
             statusCode: {
                 400: function () {
                     // More than likely the CSRF token was lost when the server restarted
@@ -264,12 +256,12 @@ $(document).ready(function () {
                 }
             }
         }).done(function (data) {
-            xpath_data = data.xpath_data;
             $("#loading-status-text").fadeIn();
+            browsersteps_session_id = data.browsersteps_session_id;
             // This should trigger 'Goto site'
             console.log("Got startup response, requesting Goto-Site (first) step fake click");
             $('#browser_steps >li:first-child .apply').click();
-            browserless_seconds_remaining = data.browser_time_remaining;
+            browserless_seconds_remaining = 500;
             set_first_gotosite_disabled();
         }).fail(function (data) {
             console.log(data);
@@ -329,8 +321,14 @@ $(document).ready(function () {
             var s = '<div class="control">' + '<a data-step-index=' + i + ' class="pure-button button-secondary button-green button-xsmall apply" >Apply</a>&nbsp;';
             if (i > 0) {
                 // The first step never gets these (Goto-site)
-                s += '<a data-step-index=' + i + ' class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;' +
-                    '<a data-step-index=' + i + ' class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>';
+                s += `<a data-step-index="${i}" class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;` +
+                    `<a data-step-index="${i}" class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>`;
+
+                // if a screenshot is available
+                if (browser_steps_available_screenshots.includes(i.toString())) {
+                    var d = (browser_steps_last_error_step === i+1) ? 'before' : 'after';
+                    s += `&nbsp;<a data-step-index="${i}" class="pure-button button-secondary button-xsmall show-screenshot" title="Show screenshot from last run" data-type="${d}">Pic</a>&nbsp;`;
+                }
             }
             s += '</div>';
             $(this).append(s)
@@ -430,7 +428,6 @@ $(document).ready(function () {
             apply_buttons_disabled = false;
             $("#browsersteps-img").css('opacity', 1);
             $('ul#browser_steps li .control .apply').css('opacity', 1);
-            browserless_seconds_remaining = data.browser_time_remaining;
             $("#loading-status-text").hide();
             set_first_gotosite_disabled();
         }).fail(function (data) {
@@ -446,6 +443,24 @@ $(document).ready(function () {
 
     });
 
+    $('ul#browser_steps li .control .show-screenshot').click(function (element) {
+        var step_n = $(event.currentTarget).data('step-index');
+        w = window.open(this.href, "_blank", "width=640,height=480");
+        const t = $(event.currentTarget).data('type');
+
+        const url = browser_steps_fetch_screenshot_image_url + `&step_n=${step_n}&type=${t}`;
+        w.document.body.innerHTML = `<!DOCTYPE html>
+            <html lang="en">
+                <body>
+                    <img src="${url}" style="width: 100%" alt="Browser Step at step ${step_n} from last run." title="Browser Step at step ${step_n} from last run."/>
+                </body>
+        </html>`;
+        w.document.title = `Browser Step at step ${step_n} from last run.`;
+    });
+
+    if (browser_steps_last_error_step) {
+        $("ul#browser_steps>li:nth-child("+browser_steps_last_error_step+")").addClass("browser-step-with-error");
+    }
 
     $("ul#browser_steps select").change(function () {
         set_greyed_state();

changedetectionio/static/js/diff-overview.js

@@ -1,4 +1,13 @@
 $(document).ready(function () {
+    var csrftoken = $('input[name=csrf_token]').val();
+    $.ajaxSetup({
+        beforeSend: function (xhr, settings) {
+            if (!/^(GET|HEAD|OPTIONS|TRACE)$/i.test(settings.type) && !this.crossDomain) {
+                xhr.setRequestHeader("X-CSRFToken", csrftoken)
+            }
+        }
+    })
+
     // Load it when the #screenshot tab is in use, so we dont give a slow experience when waiting for the text diff to load
     window.addEventListener('hashchange', function (e) {
         toggle(location.hash);
@@ -15,11 +24,71 @@ $(document).ready(function () {
             $("#settings").hide();
         } else if (hash_name === '#extract') {
             $("#settings").hide();
-        }
-
-
-        else {
+        } else {
             $("#settings").show();
         }
     }
+
+    const article = $('.highlightable-filter')[0];
+
+    // We could also add the  'touchend' event for touch devices, but since
+    // most iOS/Android browsers already show a dialog when you select
+    // text (often with a Share option) we'll skip that
+    article.addEventListener('mouseup', dragTextHandler, false);
+    article.addEventListener('mousedown', clean, false);
+
+    function clean(event) {
+      $("#highlightSnippet").remove();
+    }
+
+
+    function dragTextHandler(event) {
+        console.log('mouseupped');
+
+        // Check if any text was selected
+        if (window.getSelection().toString().length > 0) {
+
+            // Find out how much (if any) user has scrolled
+            var scrollTop = (window.pageYOffset !== undefined) ? window.pageYOffset : (document.documentElement || document.body.parentNode || document.body).scrollTop;
+
+            // Get cursor position
+            const posX = event.clientX;
+            const posY = event.clientY + 20 + scrollTop;
+
+            // Append HTML to the body, create the "Tweet Selection" dialog
+            document.body.insertAdjacentHTML('beforeend', '<div id="highlightSnippet" style="position: absolute; top: ' + posY + 'px; left: ' + posX + 'px;"><div class="pure-form-message-inline" style="font-size: 70%">Ignore any change on any line which contains the selected text.</div><br><a data-mode="exact" href="javascript:void(0);" class="pure-button button-secondary button-xsmall">Ignore exact text</a>&nbsp;</div>');
+
+            if (/\d/.test(window.getSelection().toString())) {
+                // Offer regex replacement
+                document.getElementById("highlightSnippet").insertAdjacentHTML('beforeend', '<a data-mode="digit-regex"  href="javascript:void(0);" class="pure-button button-secondary button-xsmall">Ignore text including number changes</a>');
+            }
+
+            $('#highlightSnippet a').bind('click', function (e) {
+                if(!window.getSelection().toString().trim().length) {
+                    alert('Oops no text selected!');
+                    return;
+                }
+
+                $.ajax({
+                    type: "POST",
+                    url: highlight_submit_ignore_url,
+                    data: {'mode': $(this).data('mode'), 'selection': window.getSelection().toString()},
+                    statusCode: {
+                        400: function () {
+                            // More than likely the CSRF token was lost when the server restarted
+                            alert("There was a problem processing the request, please reload the page.");
+                        }
+                    }
+                }).done(function (data) {
+                    $("#highlightSnippet").html(data)
+                }).fail(function (data) {
+                    console.log(data);
+                    alert('There was an error communicating with the server.');
+                });
+            });
+
+        }
+    }
+
+
 });

changedetectionio/static/js/diff-render.js

@@ -1,110 +1,120 @@
-var a = document.getElementById("a");
-var b = document.getElementById("b");
-var result = document.getElementById("result");
+$(document).ready(function () {
+    var a = document.getElementById("a");
+    var b = document.getElementById("b");
+    var result = document.getElementById("result");
+    var inputs;
 
-function changed() {
-  // https://github.com/kpdecker/jsdiff/issues/389
-  // I would love to use `{ignoreWhitespace: true}` here but it breaks the formatting
-  options = {
-    ignoreWhitespace: document.getElementById("ignoreWhitespace").checked,
-  };
+    $('#jump-next-diff').click(function () {
 
-  var diff = Diff[window.diffType](a.textContent, b.textContent, options);
-  var fragment = document.createDocumentFragment();
-  for (var i = 0; i < diff.length; i++) {
-    if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
-      var swap = diff[i];
-      diff[i] = diff[i + 1];
-      diff[i + 1] = swap;
+        var element = inputs[inputs.current];
+        var headerOffset = 80;
+        var elementPosition = element.getBoundingClientRect().top;
+        var offsetPosition = elementPosition - headerOffset + window.scrollY;
+
+        window.scrollTo({
+            top: offsetPosition,
+            behavior: "smooth",
+        });
+
+        inputs.current++;
+        if (inputs.current >= inputs.length) {
+            inputs.current = 0;
+        }
+    });
+
+    function changed() {
+        // https://github.com/kpdecker/jsdiff/issues/389
+        // I would love to use `{ignoreWhitespace: true}` here but it breaks the formatting
+        options = {
+            ignoreWhitespace: document.getElementById("ignoreWhitespace").checked,
+        };
+
+        var diff = Diff[window.diffType](a.textContent, b.textContent, options);
+        var fragment = document.createDocumentFragment();
+        for (var i = 0; i < diff.length; i++) {
+            if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
+                var swap = diff[i];
+                diff[i] = diff[i + 1];
+                diff[i + 1] = swap;
+            }
+
+            var node;
+            if (diff[i].removed) {
+                node = document.createElement("del");
+                node.classList.add("change");
+                const wrapper = node.appendChild(document.createElement("span"));
+                wrapper.appendChild(document.createTextNode(diff[i].value));
+            } else if (diff[i].added) {
+                node = document.createElement("ins");
+                node.classList.add("change");
+                const wrapper = node.appendChild(document.createElement("span"));
+                wrapper.appendChild(document.createTextNode(diff[i].value));
+            } else {
+                node = document.createTextNode(diff[i].value);
+            }
+            fragment.appendChild(node);
+        }
+
+        result.textContent = "";
+        result.appendChild(fragment);
+
+        // For nice mouse-over hover/title information
+        const removed_current_option = $('#diff-version option:selected')
+        if (removed_current_option) {
+            $('del').each(function () {
+                $(this).prop('title', 'Removed '+removed_current_option[0].label);
+            });
+        }
+        const inserted_current_option = $('#current-version option:selected')
+        if (removed_current_option) {
+            $('ins').each(function () {
+                $(this).prop('title', 'Inserted '+inserted_current_option[0].label);
+            });
+        }
+        // Set the list of possible differences to jump to
+        inputs = document.querySelectorAll('#diff-ui .change')
+        // Set the "current" diff pointer
+        inputs.current = 0;
+        // Goto diff
+        $('#jump-next-diff').click();
     }
 
-    var node;
-    if (diff[i].removed) {
-      node = document.createElement("del");
-      node.classList.add("change");
-      const wrapper = node.appendChild(document.createElement("span"));
-      wrapper.appendChild(document.createTextNode(diff[i].value));
-    } else if (diff[i].added) {
-      node = document.createElement("ins");
-      node.classList.add("change");
-      const wrapper = node.appendChild(document.createElement("span"));
-      wrapper.appendChild(document.createTextNode(diff[i].value));
-    } else {
-      node = document.createTextNode(diff[i].value);
-    }
-    fragment.appendChild(node);
-  }
-
-  result.textContent = "";
-  result.appendChild(fragment);
-
-  // Jump at start
-  inputs.current = 0;
-  next_diff();
-}
-
-window.onload = function () {
-  /* Convert what is options from UTC time.time() to local browser time */
-  var diffList = document.getElementById("diff-version");
-  if (typeof diffList != "undefined" && diffList != null) {
-    for (var option of diffList.options) {
-      var dateObject = new Date(option.value * 1000);
-      option.label = dateObject.toLocaleString();
-    }
-  }
-
-  /* Set current version date as local time in the browser also */
-  var current_v = document.getElementById("current-v-date");
-  var dateObject = new Date(newest_version_timestamp * 1000);
-  current_v.innerHTML = dateObject.toLocaleString();
-  onDiffTypeChange(
-    document.querySelector('#settings [name="diff_type"]:checked'),
-  );
-  changed();
-};
-
-a.onpaste = a.onchange = b.onpaste = b.onchange = changed;
-
-if ("oninput" in a) {
-  a.oninput = b.oninput = changed;
-} else {
-  a.onkeyup = b.onkeyup = changed;
-}
-
-function onDiffTypeChange(radio) {
-  window.diffType = radio.value;
-  // Not necessary
-  //	document.title = "Diff " + radio.value.slice(4);
-}
-
-var radio = document.getElementsByName("diff_type");
-for (var i = 0; i < radio.length; i++) {
-  radio[i].onchange = function (e) {
-    onDiffTypeChange(e.target);
+    $('.needs-localtime').each(function () {
+        for (var option of this.options) {
+            var dateObject = new Date(option.value * 1000);
+            option.label = dateObject.toLocaleString(undefined, {dateStyle: "full", timeStyle: "medium"});
+        }
+    })
+    onDiffTypeChange(
+        document.querySelector('#settings [name="diff_type"]:checked'),
+    );
     changed();
-  };
-}
 
-document.getElementById("ignoreWhitespace").onchange = function (e) {
-  changed();
-};
+    a.onpaste = a.onchange = b.onpaste = b.onchange = changed;
 
-var inputs = document.getElementsByClassName("change");
-inputs.current = 0;
+    if ("oninput" in a) {
+        a.oninput = b.oninput = changed;
+    } else {
+        a.onkeyup = b.onkeyup = changed;
+    }
 
-function next_diff() {
-  var element = inputs[inputs.current];
-  var headerOffset = 80;
-  var elementPosition = element.getBoundingClientRect().top;
-  var offsetPosition = elementPosition - headerOffset + window.scrollY;
+    function onDiffTypeChange(radio) {
+        window.diffType = radio.value;
+        // Not necessary
+        //	document.title = "Diff " + radio.value.slice(4);
+    }
 
-  window.scrollTo({
-    top: offsetPosition,
-    behavior: "smooth",
-  });
+    var radio = document.getElementsByName("diff_type");
+    for (var i = 0; i < radio.length; i++) {
+        radio[i].onchange = function (e) {
+            onDiffTypeChange(e.target);
+            changed();
+        };
+    }
+
+    document.getElementById("ignoreWhitespace").onchange = function (e) {
+        changed();
+    };
+
+});
 
-  inputs.current++;
-  if (inputs.current >= inputs.length) {
-    inputs.current = 0;
-  }
-}

changedetectionio/static/js/global-settings.js

@@ -32,5 +32,10 @@ $(document).ready(function () {
         window.getSelection().removeAllRanges();
 
     });
+
+    $("#notification-token-toggle").click(function (e) {
+        e.preventDefault();
+        $('#notification-tokens-info').toggle();
+    });
 });
 

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/tabs.js

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

changedetectionio/static/js/toggle-theme.js

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

changedetectionio/static/js/visual-selector.js

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

changedetectionio/static/js/watch-overview.js

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

changedetectionio/static/js/watch-settings.js

@@ -42,4 +42,8 @@ $(document).ready(function () {
         $('#notification_urls').val('');
         e.preventDefault();
     });
+    $("#notification-token-toggle").click(function (e) {
+        e.preventDefault();
+        $('#notification-tokens-info').toggle();
+    });
 });

changedetectionio/static/styles/diff.css

@@ -187,6 +187,10 @@ ins {
     padding: 0.5em; }
   #settings ins {
     padding: 0.5em; }
+  #settings option:checked {
+    font-weight: bold; }
+  #settings [type=radio], #settings [type=checkbox] {
+    vertical-align: middle; }
 
 .source {
   position: absolute;
@@ -218,3 +222,10 @@ td#diff-col div {
   text-align: center; }
   .tab-pane-inner#screenshot img {
     max-width: 99%; }
+
+#highlightSnippet {
+  background: var(--color-background);
+  padding: 1em;
+  border-radius: 5px;
+  background: var(--color-background);
+  box-shadow: 1px 1px 4px var(--color-shadow-jump); }

changedetectionio/static/styles/scss/diff.scss

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

changedetectionio/static/styles/scss/styles.scss

@@ -5,12 +5,18 @@
 @import "parts/_arrows";
 @import "parts/_browser-steps";
 @import "parts/_extra_proxies";
+@import "parts/_extra_browsers";
+@import "parts/_pagination";
 @import "parts/_spinners";
 @import "parts/_variables";
+@import "parts/_darkmode";
+@import "parts/_menu";
+@import "parts/_love";
 
 body {
   color: var(--color-text);
   background: var(--color-background-page);
+  font-family: Helvetica Neue, Helvetica, Lucida Grande, Arial, Ubuntu, Cantarell, Fira Sans, sans-serif;
 }
 
 .visually-hidden {
@@ -53,8 +59,26 @@ a.github-link {
   }
 }
 
-button.toggle-theme {
-  width: 4rem;
+#search-q {
+  opacity: 0;
+  -webkit-transition: all .9s ease;
+  -moz-transition: all .9s ease;
+  transition: all .9s ease;
+  width: 0;
+  display: none;
+  &.expanded {
+    width: auto;
+    display: inline-block;
+
+    opacity: 1;
+  }
+}
+#search-result-info {
+  color: #fff;
+}
+
+button.toggle-button {
+  vertical-align: middle;
   background: transparent;
   border: none;
   cursor: pointer;
@@ -73,19 +97,7 @@ button.toggle-theme {
     display: block;
   }
 
-  .icon-dark {
-    display: none;
-  }
 
-  &.dark {
-    .icon-light {
-      display: none;
-    }
-
-    .icon-dark {
-      display: block;
-    }
-  }
 }
 
 .pure-menu-horizontal {
@@ -458,7 +470,11 @@ footer {
   padding: 10px;
 
   &#left-sticky {
-    left: 0px;
+    left: 0;
+    position: fixed;
+    border-top-right-radius: 5px;
+    border-bottom-right-radius: 5px;
+    box-shadow: 1px 1px 4px var(--color-shadow-jump);
   }
 
   &#right-sticky {
@@ -926,32 +942,7 @@ ul {
   }
 }
 
-#selector-wrapper {
-  height: 100%;
-  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%;
-}
+@import "parts/_visualselector";
 
 #webdriver-override-options {
   input[type="number"] {
@@ -1090,3 +1081,4 @@ ul {
   border-radius: 3px;
   white-space: nowrap;
 }
+

changedetectionio/static/styles/styles.css

@@ -26,6 +26,9 @@
   #browser_steps li {
     list-style: decimal;
     padding: 5px; }
+    #browser_steps li.browser-step-with-error {
+      background-color: #ffd6d6;
+      border-radius: 4px; }
     #browser_steps li:not(:first-child):hover {
       opacity: 1.0; }
     #browser_steps li .control {
@@ -50,8 +53,7 @@
 #browser-steps .flex-wrapper {
   display: flex;
   flex-flow: row;
-  height: 600px;
-  /*@todo make this dynamic */ }
+  height: 70vh; }
 
 /*  this is duplicate :( */
 #browsersteps-selector-wrapper {
@@ -95,6 +97,84 @@ ul#requests-extra_proxies {
   ul#requests-extra_proxies table tr {
     display: inline; }
 
+#request {
+  /* Auto proxy scan/checker */ }
+  #request label[for=proxy] {
+    display: inline-block; }
+
+body.proxy-check-active #request .proxy-status {
+  width: 2em; }
+
+body.proxy-check-active #request .proxy-check-details {
+  font-size: 80%;
+  color: #555;
+  display: block;
+  padding-left: 4em; }
+
+body.proxy-check-active #request .proxy-timing {
+  font-size: 80%;
+  padding-left: 1rem;
+  color: var(--color-link); }
+
+#recommended-proxy {
+  display: grid;
+  gap: 2rem;
+  padding-bottom: 1em; }
+  @media (min-width: 991px) {
+    #recommended-proxy {
+      grid-template-columns: repeat(2, 1fr); } }
+  #recommended-proxy > div {
+    border: 1px #aaa solid;
+    border-radius: 4px;
+    padding: 1em; }
+
+#extra-proxies-setting {
+  border: 1px solid var(--color-grey-800);
+  border-radius: 4px;
+  margin: 1em;
+  padding: 1em; }
+
+ul#requests-extra_browsers {
+  list-style: none;
+  /* tidy up the table to look more "inline" */
+  /* each proxy entry is a `table` */ }
+  ul#requests-extra_browsers li > label {
+    display: none; }
+  ul#requests-extra_browsers table tr {
+    display: inline; }
+
+#extra-browsers-setting {
+  border: 1px solid var(--color-grey-800);
+  border-radius: 4px;
+  margin: 1em;
+  padding: 1em; }
+
+.pagination-page-info {
+  color: #fff;
+  font-size: 0.85rem;
+  text-transform: capitalize; }
+
+.pagination.menu > * {
+  display: inline-block; }
+
+.pagination.menu li {
+  display: inline-block; }
+
+.pagination.menu a {
+  padding: 0.65rem;
+  margin: 3px;
+  border: none;
+  background: #444;
+  border-radius: 2px;
+  color: var(--color-text-button); }
+  .pagination.menu a.disabled {
+    display: none; }
+  .pagination.menu a.active {
+    font-weight: bold;
+    background: #888; }
+  .pagination.menu a:hover {
+    background: #999; }
+
 /* spinner */
 .spinner,
 .spinner:after {
@@ -271,9 +351,68 @@ html[data-darkmode="true"] {
     html[data-darkmode="true"] .watch-table .unviewed.error {
       color: var(--color-watch-table-error); }
 
+#toggle-light-mode {
+  /*  width: 3rem;*/
+  /* default */ }
+  #toggle-light-mode .icon-dark {
+    display: none; }
+
+html[data-darkmode="true"] #toggle-light-mode .icon-light {
+  display: none; }
+
+html[data-darkmode="true"] #toggle-light-mode .icon-dark {
+  display: block; }
+
+.pure-menu-link {
+  padding: 0.5rem 1em;
+  line-height: 1.2rem; }
+
+.pure-menu-item svg {
+  height: 1.2rem; }
+
+.pure-menu-item * {
+  vertical-align: middle; }
+
+.pure-menu-item .github-link {
+  height: 1.8rem;
+  display: block; }
+  .pure-menu-item .github-link svg {
+    height: 100%; }
+
+.pure-menu-item .bi-heart:hover {
+  cursor: pointer; }
+
+#overlay {
+  opacity: 0.95;
+  position: fixed;
+  width: 350px;
+  max-width: 100%;
+  height: 100%;
+  top: 0;
+  right: -350px;
+  background-color: var(--color-table-stripe);
+  z-index: 2;
+  transform: translateX(0);
+  transition: transform .5s ease; }
+  #overlay.visible {
+    transform: translateX(-100%); }
+  #overlay .content {
+    font-size: 0.875rem;
+    padding: 1rem;
+    margin-top: 5rem;
+    max-width: 400px;
+    color: var(--color-watch-table-row-text); }
+
+#heartpath {
+  transition: all ease 0.3s !important; }
+  #heartpath:hover {
+    fill: #ff0000 !important;
+    transition: all ease 0.3s !important; }
+
 body {
   color: var(--color-text);
-  background: var(--color-background-page); }
+  background: var(--color-background-page);
+  font-family: Helvetica Neue, Helvetica, Lucida Grande, Arial, Ubuntu, Cantarell, Fira Sans, sans-serif; }
 
 .visually-hidden {
   clip: rect(0 0 0 0);
@@ -305,23 +444,32 @@ a.github-link {
   a.github-link:hover {
     color: var(--color-icon-github-hover); }
 
-button.toggle-theme {
-  width: 4rem;
+#search-q {
+  opacity: 0;
+  -webkit-transition: all .9s ease;
+  -moz-transition: all .9s ease;
+  transition: all .9s ease;
+  width: 0;
+  display: none; }
+  #search-q.expanded {
+    width: auto;
+    display: inline-block;
+    opacity: 1; }
+
+#search-result-info {
+  color: #fff; }
+
+button.toggle-button {
+  vertical-align: middle;
   background: transparent;
   border: none;
   cursor: pointer;
   color: var(--color-icon-github); }
-  button.toggle-theme:hover {
+  button.toggle-button:hover {
     color: var(--color-icon-github-hover); }
-  button.toggle-theme svg {
+  button.toggle-button svg {
     fill: currentColor; }
-  button.toggle-theme .icon-light {
-    display: block; }
-  button.toggle-theme .icon-dark {
-    display: none; }
-  button.toggle-theme.dark .icon-light {
-    display: none; }
-  button.toggle-theme.dark .icon-dark {
+  button.toggle-button .icon-light {
     display: block; }
 
 .pure-menu-horizontal {
@@ -587,7 +735,11 @@ footer {
   background: var(--color-background);
   padding: 10px; }
   .sticky-tab#left-sticky {
-    left: 0px; }
+    left: 0;
+    position: fixed;
+    border-top-right-radius: 5px;
+    border-bottom-right-radius: 5px;
+    box-shadow: 1px 1px 4px var(--color-shadow-jump); }
   .sticky-tab#right-sticky {
     right: 0px; }
   .sticky-tab#hosted-sticky {
@@ -896,6 +1048,7 @@ ul {
 
 #selector-wrapper {
   height: 100%;
+  max-height: 70vh;
   overflow-y: scroll;
   position: relative; }
   #selector-wrapper > img {

changedetectionio/store.py

@@ -1,9 +1,11 @@
+from distutils.util import strtobool
+
 from flask import (
     flash
 )
 
 from . model import App, Watch
-from copy import deepcopy
+from copy import deepcopy, copy
 from os import path, unlink
 from threading import Lock
 import json
@@ -16,6 +18,11 @@ import threading
 import time
 import uuid as uuid_builder
 
+# Because the server will run as a daemon and wont know the URL for notification links when firing off a notification
+BASE_URL_NOT_SET_TEXT = '("Base URL" not set - see settings - notifications)'
+
+dictfilt = lambda x, y: dict([ (i,x[i]) for i in x if i in set(y) ])
+
 # Is there an existing library to ensure some data store (JSON etc) is in sync with CRUD methods?
 # Open a github issue if you know something :)
 # https://stackoverflow.com/questions/6190468/how-to-trigger-function-on-value-change
@@ -35,6 +42,7 @@ class ChangeDetectionStore:
         self.__data = App.model()
         self.datastore_path = datastore_path
         self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
+        print(">>> Datastore path is ", self.json_store_path)
         self.needs_write = False
         self.start_time = time.time()
         self.stop_thread = False
@@ -88,6 +96,14 @@ class ChangeDetectionStore:
                 self.add_watch(url='https://changedetection.io/CHANGELOG.txt',
                                tag='changedetection.io',
                                extras={'fetch_backend': 'html_requests'})
+
+            updates_available = self.get_updates_available()
+            self.__data['settings']['application']['schema_version'] = updates_available.pop()
+
+        else:
+            # Bump the update version by running updates
+            self.run_updates()
+
         self.__data['version_tag'] = version_tag
 
         # Just to test that proxies.json if it exists, doesnt throw a parsing error on startup
@@ -117,9 +133,6 @@ class ChangeDetectionStore:
             secret = secrets.token_hex(16)
             self.__data['settings']['application']['api_access_token'] = secret
 
-        # Bump the update version by running updates
-        self.run_updates()
-
         self.needs_write = True
 
         # Finally start the thread that will manage periodic data saves to JSON
@@ -171,26 +184,21 @@ class ChangeDetectionStore:
 
     @property
     def data(self):
-        # Re #152, Return env base_url if not overriden, @todo also prefer the proxy pass url
-        env_base_url = os.getenv('BASE_URL','')
-        if not self.__data['settings']['application']['base_url']:
-          self.__data['settings']['application']['base_url'] = env_base_url.strip('" ')
+        # Re #152, Return env base_url if not overriden
+        # Re #148 - Some people have just {{ base_url }} in the body or title, but this may break some notification services
+        #           like 'Join', so it's always best to atleast set something obvious so that they are not broken.
 
-        return self.__data
+        active_base_url = BASE_URL_NOT_SET_TEXT
+        if self.__data['settings']['application'].get('base_url'):
+            active_base_url = self.__data['settings']['application'].get('base_url')
+        elif os.getenv('BASE_URL'):
+            active_base_url = os.getenv('BASE_URL')
 
-    def get_all_tags(self):
-        tags = []
-        for uuid, watch in self.data['watching'].items():
-            if watch['tag'] is None:
-                continue
-            # Support for comma separated list of tags.
-            for tag in watch['tag'].split(','):
-                tag = tag.strip()
-                if tag not in tags:
-                    tags.append(tag)
-
-        tags.sort()
-        return tags
+        # I looked at various ways todo the following, but in the end just copying the dict seemed simplest/most reliable
+        # even given the memory tradeoff - if you know a better way.. maybe return d|self.__data.. or something
+        d = self.__data
+        d['settings']['application']['active_base_url'] = active_base_url.strip('" ')
+        return d
 
     # Delete a single watch by UUID
     def delete(self, uuid):
@@ -204,22 +212,22 @@ class ChangeDetectionStore:
                 # GitHub #30 also delete history records
                 for uuid in self.data['watching']:
                     path = pathlib.Path(os.path.join(self.datastore_path, uuid))
-                    shutil.rmtree(path)
-                    self.needs_write_urgent = True
+                    if os.path.exists(path):
+                        shutil.rmtree(path)
 
             else:
                 path = pathlib.Path(os.path.join(self.datastore_path, uuid))
-                shutil.rmtree(path)
+                if os.path.exists(path):
+                    shutil.rmtree(path)
                 del self.data['watching'][uuid]
 
-            self.needs_write_urgent = True
+        self.needs_write_urgent = True
 
     # Clone a watch by UUID
     def clone(self, uuid):
-        url = self.data['watching'][uuid]['url']
-        tag = self.data['watching'][uuid]['tag']
+        url = self.data['watching'][uuid].get('url')
         extras = self.data['watching'][uuid]
-        new_uuid = self.add_watch(url=url, tag=tag, extras=extras)
+        new_uuid = self.add_watch(url=url, extras=extras)
         return new_uuid
 
     def url_exists(self, url):
@@ -236,12 +244,16 @@ class ChangeDetectionStore:
         import pathlib
 
         self.__data['watching'][uuid].update({
-                'last_checked': 0,
+                'browser_steps_last_error_step' : None,
+                'check_count': 0,
+                'fetch_time' : 0.0,
                 'has_ldjson_price_data': None,
+                'last_checked': 0,
                 'last_error': False,
                 'last_notification_error': False,
                 'last_viewed': 0,
                 'previous_md5': False,
+                'previous_md5_before_filters': False,
                 'track_ldjson_price_data': None,
             })
 
@@ -254,16 +266,14 @@ 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/")):
@@ -290,6 +300,7 @@ class ChangeDetectionStore:
                     'processor',
                     'subtractive_selectors',
                     'tag',
+                    'tags',
                     'text_should_not_be_present',
                     'title',
                     'trigger_text',
@@ -312,28 +323,45 @@ class ChangeDetectionStore:
             flash('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX', 'error')
             return None
 
-        with self.lock:
-            # #Re 569
-            new_watch = Watch.model(datastore_path=self.datastore_path, default={
-                'url': url,
-                'tag': tag
-            })
+        if tag and type(tag) == str:
+            # Then it's probably a string of the actual tag by name, split and add it
+            for t in tag.split(','):
+                # for each stripped tag, add tag as UUID
+                for a_t in t.split(','):
+                    tag_uuid = self.add_tag(a_t)
+                    apply_extras['tags'].append(tag_uuid)
 
-            new_uuid = new_watch['uuid']
-            logging.debug("Added URL {} - {}".format(url, new_uuid))
+        # Or if UUIDs given directly
+        if tag_uuids:
+            apply_extras['tags'] = list(set(apply_extras['tags'] + tag_uuids))
 
-            for k in ['uuid', 'history', 'last_checked', 'last_changed', 'newest_history_key', 'previous_md5', 'viewed']:
-                if k in apply_extras:
-                    del apply_extras[k]
+        # Make any uuids unique
+        if apply_extras.get('tags'):
+            apply_extras['tags'] = list(set(apply_extras.get('tags')))
 
-            new_watch.update(apply_extras)
-            self.__data['watching'][new_uuid] = new_watch
+        new_watch = Watch.model(datastore_path=self.datastore_path, url=url)
+
+        new_uuid = new_watch.get('uuid')
+
+        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]
+
+        if not apply_extras.get('date_created'):
+            apply_extras['date_created'] = int(time.time())
+
+        new_watch.update(apply_extras)
+        new_watch.ensure_data_dir_exists()
+        self.__data['watching'][new_uuid] = new_watch
 
-        self.__data['watching'][new_uuid].ensure_data_dir_exists()
 
         if write_to_disk_now:
             self.sync_to_json()
 
+        print("added ", url)
+
         return new_uuid
 
     def visualselector_data_is_ready(self, watch_uuid):
@@ -365,19 +393,21 @@ class ChangeDetectionStore:
     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()
@@ -467,12 +497,12 @@ class ChangeDetectionStore:
                     k = "ui-" + str(i) + proxy.get('proxy_name')
                     proxy_list[k] = {'label': proxy.get('proxy_name'), 'url': proxy.get('proxy_url')}
 
+        if proxy_list and strtobool(os.getenv('ENABLE_NO_PROXY_OPTION', 'True')):
+            proxy_list["no-proxy"] = {'label': "No proxy", 'url': ''}
 
         return proxy_list if len(proxy_list) else None
 
 
-
-
     def get_preferred_proxy_for_watch(self, uuid):
         """
         Returns the preferred proxy by ID key
@@ -486,6 +516,9 @@ class ChangeDetectionStore:
         # If it's a valid one
         watch = self.data['watching'].get(uuid)
 
+        if strtobool(os.getenv('ENABLE_NO_PROXY_OPTION', 'True')) and watch.get('proxy') == "no-proxy":
+            return None
+
         if watch.get('proxy') and watch.get('proxy') in list(self.proxy_list.keys()):
             return watch.get('proxy')
 
@@ -504,14 +537,119 @@ class ChangeDetectionStore:
 
         return None
 
-    # Run all updates
-    # IMPORTANT - Each update could be run even when they have a new install and the schema is correct
-    #             So therefor - each `update_n` should be very careful about checking if it needs to actually run
-    #             Probably we should bump the current update schema version with each tag release version?
-    def run_updates(self):
-        import inspect
-        import shutil
+    @property
+    def has_extra_headers_file(self):
+        filepath = os.path.join(self.datastore_path, 'headers.txt')
+        return os.path.isfile(filepath)
 
+    def get_all_base_headers(self):
+        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 {}
+
+    @property
+    def extra_browsers(self):
+        res = []
+        p = list(filter(
+            lambda s: (s.get('browser_name') and s.get('browser_connection_url')),
+            self.__data['settings']['requests'].get('extra_browsers', [])))
+        if p:
+            for i in p:
+                res.append(("extra_browser_"+i['browser_name'], i['browser_name']))
+
+        return res
+
+    def tag_exists_by_name(self, tag_name):
+        return any(v.get('title', '').lower() == tag_name.lower() for k, v in self.__data['settings']['application']['tags'].items())
+
+    def get_updates_available(self):
+        import inspect
         updates_available = []
         for i, o in inspect.getmembers(self, predicate=inspect.ismethod):
             m = re.search(r'update_(\d+)$', i)
@@ -519,6 +657,15 @@ class ChangeDetectionStore:
                 updates_available.append(int(m.group(1)))
         updates_available.sort()
 
+        return updates_available
+
+    # Run all updates
+    # IMPORTANT - Each update could be run even when they have a new install and the schema is correct
+    #             So therefor - each `update_n` should be very careful about checking if it needs to actually run
+    #             Probably we should bump the current update schema version with each tag release version?
+    def run_updates(self):
+        import shutil
+        updates_available = self.get_updates_available()
         for update_n in updates_available:
             if update_n > self.__data['settings']['application']['schema_version']:
                 print ("Applying update_{}".format((update_n)))
@@ -679,3 +826,35 @@ class ChangeDetectionStore:
             except:
                 continue
         return
+
+    # Create tag objects and their references from existing tag text
+    def update_12(self):
+        i = 0
+        for uuid, watch in self.data['watching'].items():
+            # Split out and convert old tag string
+            tag = watch.get('tag')
+            if tag:
+                tag_uuids = []
+                for t in tag.split(','):
+                    tag_uuids.append(self.add_tag(name=t))
+
+                self.data['watching'][uuid]['tags'] = tag_uuids
+
+    # #1775 - Update 11 did not update the records correctly when adding 'date_created' values for sorting
+    def update_13(self):
+        i = 0
+        for uuid, watch in self.data['watching'].items():
+            if not watch.get('date_created'):
+                self.data['watching'][uuid]['date_created'] = i
+            i+=1
+        return
+
+    # #1774 - protect xpath1 against migration
+    def update_14(self):
+        for awatch in self.__data["watching"]:
+            if self.__data["watching"][awatch]['include_filters']:
+                for num, selector in enumerate(self.__data["watching"][awatch]['include_filters']):
+                    if selector.startswith('/'):
+                        self.__data["watching"][awatch]['include_filters'][num] = 'xpath1:' + selector
+                    if selector.startswith('xpath:'):
+                        self.__data["watching"][awatch]['include_filters'][num] = selector.replace('xpath:', 'xpath1:', 1)

changedetectionio/templates/_common_fields.jinja

@@ -13,9 +13,9 @@
                             <div class="pure-form-message-inline">
                               <ul>
                                 <li>Use <a target=_new href="https://github.com/caronc/apprise">AppRise URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.</li>
-                                <li><code>discord://</code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
-                                <li><code>tgram://</code> bots cant send messages to other bots, so you should specify chat ID of non-bot user.</li>
-                                <li><code>tgram://</code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
+                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_discord">discord://</a></code> (or <code>https://discord.com/api/webhooks...</code>)) </code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
+                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> bots can't send messages to other bots, so you should specify chat ID of non-bot user.</li>
+                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
                                 <li><code>gets://</code>, <code>posts://</code>, <code>puts://</code>, <code>deletes://</code> for direct API calls (or omit the "<code>s</code>" for non-SSL ie <code>get://</code>)</li>
                                   <li>Accepts the <code>{{ '{{token}}' }}</code> placeholders listed below</li>
                               </ul>
@@ -23,7 +23,7 @@
                             <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</a>
+                              <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>
@@ -35,18 +35,14 @@
                             </div>
                             <div class="pure-control-group">
                                 {{ render_field(form.notification_body , rows=5, class="notification-body", placeholder=settings_application['notification_body']) }}
-                                <span class="pure-form-message-inline">Body for all notifications</span>
-                            </div>
-                            <div class="pure-control-group">
-                            <!-- unsure -->
-                                {{ render_field(form.notification_format , class="notification-format") }}
-                                <span class="pure-form-message-inline">Format for all notifications</span>
+                                <span class="pure-form-message-inline">Body for all notifications &dash; You can use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> templating in the notification title, body and URL, and tokens from below.
+                                </span>
+
                             </div>
                             <div class="pure-controls">
-                            <p class="pure-form-message-inline">
-                                You can use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> templating in the notification title, body and URL.
-                            </p>
-
+                                <div id="notification-token-toggle" class="pure-button button-tag button-xsmall">Show token/placeholders</div>
+                            </div>
+                            <div class="pure-controls" style="display: none;" id="notification-tokens-info">
                                 <table class="pure-table" id="token-table">
                                     <thead>
                                     <tr>
@@ -99,9 +95,13 @@
                                         <td><code>{{ '{{diff_full}}' }}</code></td>
                                         <td>The diff output - full difference output</td>
                                     </tr>
+                                    <tr>
+                                        <td><code>{{ '{{diff_patch}}' }}</code></td>
+                                        <td>The diff output - patch in unified format</td>
+                                    </tr>
                                     <tr>
                                         <td><code>{{ '{{current_snapshot}}' }}</code></td>
-                                        <td>The current snapshot value, useful when combined with JSON or CSS filters
+                                        <td>The current snapshot text contents value, useful when combined with JSON or CSS filters
                                         </td>
                                     </tr>
                                     <tr>
@@ -111,12 +111,15 @@
                                     </tbody>
                                 </table>
                                 <div class="pure-form-message-inline">
-                                    <br>
-                                    URLs generated by changedetection.io (such as <code>{{ '{{diff_url}}' }}</code>) require the <code>BASE_URL</code> environment variable set.<br>
-                                    Your <code>BASE_URL</code> var is currently "{{settings_application['current_base_url']}}"
-									<br>
-									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removal%7D%7D-notification-tokens">More Here</a> </br>
+                                    <p>
+									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. <br>
+                                    For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removed%7D%7D-notification-tokens">More Here</a> <br>
+                                    </p>
                                 </div>
                             </div>
+                            <div class="pure-control-group">
+                                {{ render_field(form.notification_format , class="notification-format") }}
+                                <span class="pure-form-message-inline">Format for all notifications</span>
+                            </div>
                         </div>
 {% endmacro %}

changedetectionio/templates/_helpers.jinja

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

changedetectionio/templates/_pagination.jinja

@@ -1,7 +0,0 @@
-{% macro pagination(sorted_watches, total_per_page, current_page) %}
-  {{ sorted_watches|length }}
-
-  {% for row in sorted_watches|batch(total_per_page, ' ') %}
-    {{ loop.index}}
-  {% endfor %}
-{% endmacro %}

changedetectionio/templates/base.html

@@ -2,42 +2,42 @@
 <html lang="en" data-darkmode="{{ get_darkmode_state() }}">
 
   <head>
-    <meta charset="utf-8"/>
-    <meta name="viewport" content="width=device-width, initial-scale=1.0"/>
-    <meta name="description" content="Self hosted website change detection."/>
+    <meta charset="utf-8" >
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" >
+    <meta name="description" content="Self hosted website change detection." >
     <title>Change Detection{{extra_title}}</title>
-    <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"/>
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}"/>
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}"/>
+    <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}" >
+    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}" >
+    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}?v={{ get_css_version() }}" >
     {% if extra_stylesheets %}
       {% for m in extra_stylesheets %}
-        <link rel="stylesheet" href="{{ m }}?ver=1000"/>
+        <link rel="stylesheet" href="{{ m }}?ver={{ get_css_version() }}" >
       {% endfor %}
     {% endif %}
 
-    <link rel="apple-touch-icon" sizes="180x180" href="{{url_for('static_content', group='favicons', filename='apple-touch-icon.png')}}"/>
-    <link rel="icon" type="image/png" sizes="32x32" href="{{url_for('static_content', group='favicons', filename='favicon-32x32.png')}}"/>
-    <link rel="icon" type="image/png" sizes="16x16" href="{{url_for('static_content', group='favicons', filename='favicon-16x16.png')}}"/>
-    <link rel="manifest" href="{{url_for('static_content', group='favicons', filename='site.webmanifest')}}"/>
-    <link rel="mask-icon" href="{{url_for('static_content', group='favicons', filename='safari-pinned-tab.svg')}}" color="#5bbad5"/>
-    <link rel="shortcut icon" href="{{url_for('static_content', group='favicons', filename='favicon.ico')}}"/>
-    <meta name="msapplication-TileColor" content="#da532c"/>
-    <meta name="msapplication-config" content="favicons/browserconfig.xml"/>
-    <meta name="theme-color" content="#ffffff"/>
+    <link rel="apple-touch-icon" sizes="180x180" href="{{url_for('static_content', group='favicons', filename='apple-touch-icon.png')}}">
+    <link rel="icon" type="image/png" sizes="32x32" href="{{url_for('static_content', group='favicons', filename='favicon-32x32.png')}}">
+    <link rel="icon" type="image/png" sizes="16x16" href="{{url_for('static_content', group='favicons', filename='favicon-16x16.png')}}">
+    <link rel="manifest" href="{{url_for('static_content', group='favicons', filename='site.webmanifest')}}">
+    <link rel="mask-icon" href="{{url_for('static_content', group='favicons', filename='safari-pinned-tab.svg')}}" color="#5bbad5">
+    <link rel="shortcut icon" href="{{url_for('static_content', group='favicons', filename='favicon.ico')}}">
+    <meta name="msapplication-TileColor" content="#da532c">
+    <meta name="msapplication-config" content="favicons/browserconfig.xml">
+    <meta name="theme-color" content="#ffffff">
 
     <style>
       body::before {
         background-image: url({{url_for('static_content', group='images', filename='gradient-border.png') }});
       }
     </style>
-    <script type="text/javascript" src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
+    <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
   </head>
 
   <body>
     <div class="header">
       <div class="home-menu pure-menu pure-menu-horizontal pure-menu-fixed" id="nav-menu">
         {% if has_password and not current_user.is_authenticated %}
-          <a class="pure-menu-heading" href="https://github.com/dgtlmoon/changedetection.io" rel="noopener">
+          <a class="pure-menu-heading" href="https://changedetection.io" rel="noopener">
             <strong>Change</strong>Detection.io</a>
         {% else %}
           <a class="pure-menu-heading" href="{{url_for('index')}}">
@@ -49,7 +49,7 @@
         {% else %}
           {% if new_version_available and not(has_password and not current_user.is_authenticated) %}
             <span id="new-version-text" class="pure-menu-heading">
-              <a href="https://github.com/dgtlmoon/changedetection.io">A new version is available</a>
+              <a href="https://changedetection.io">A new version is available</a>
             </span>
           {% endif %}
         {% endif %}
@@ -58,6 +58,9 @@
           {% if current_user.is_authenticated or not has_password %}
             {% if not
             current_diff_url %}
+              <li class="pure-menu-item">
+                <a href="{{ url_for('tags.tags_overview_page')}}" class="pure-menu-link">GROUPS</a>
+              </li>
               <li class="pure-menu-item">
                 <a href="{{ url_for('settings_page')}}" class="pure-menu-link">SETTINGS</a>
               </li>
@@ -74,7 +77,7 @@
             {% endif %}
           {% else %}
             <li class="pure-menu-item">
-              <a class="pure-menu-link" href="https://github.com/dgtlmoon/changedetection.io">Website Change Detection and Notification.</a>
+              <a class="pure-menu-link" href="https://changedetection.io">Website Change Detection and Notification.</a>
             </li>
           {% endif %}
           {% if current_user.is_authenticated %}
@@ -82,11 +85,20 @@
               <a href="{{url_for('logout')}}" class="pure-menu-link">LOG OUT</a>
             </li>
           {% endif %}
+          {% if current_user.is_authenticated or not has_password %}
+          <li class="pure-menu-item pure-form" id="search-menu-item">
+            <!-- We use GET here so it offers people a chance to set bookmarks etc -->
+            <form name="searchForm" action="" method="GET">
+              <input id="search-q" class="" name="q" placeholder="URL or Title {% if active_tag %}in '{{ active_tag }}'{% endif %}" required="" type="text" value="">
+              <input name="tags" type="hidden" value="{% if active_tag %}{{active_tag}}{% endif %}">
+              <button class="toggle-button " id="toggle-search" type="button" title="Search, or Use Alt+S Key" >
+                {% include "svgs/search-icon.svg" %}
+              </button>
+            </form>
+          </li>
+          {% endif %}
           <li class="pure-menu-item">
-            {% if dark_mode %}
-            {% set darkClass = 'dark' %}
-            {% endif %}
-            <button class="toggle-theme {{darkClass}}" type="button" title="Toggle Light/Dark Mode">
+            <button class="toggle-button" id ="toggle-light-mode" type="button" title="Toggle Light/Dark Mode">
               <span class="visually-hidden">Toggle light/dark mode</span>
               <span class="icon-light">
                 {% include "svgs/light-mode-toggle-icon.svg" %}
@@ -96,6 +108,20 @@
               </span>
             </button>
           </li>
+          <li class="pure-menu-item" id="heart-us">
+                <svg
+                   fill="#ff0000"
+                   class="bi bi-heart"
+                   preserveAspectRatio="xMidYMid meet"
+                   viewBox="0 0 16.9 16.1"
+                   id="svg-heart"
+                   xmlns="http://www.w3.org/2000/svg"
+                   xmlns:svg="http://www.w3.org/2000/svg">
+                  <path id="heartpath" d="M 5.338316,0.50302766 C 0.71136983,0.50647126 -3.9576371,7.2707777 8.5004254,15.503028 23.833425,5.3700277 13.220206,-2.5384409 8.6762066,1.6475589 c -0.060791,0.054322 -0.11943,0.1110064 -0.1757812,0.1699219 -0.057,-0.059 -0.1157813,-0.116875 -0.1757812,-0.171875 C 7.4724566,0.86129334 6.4060729,0.50223298 5.338316,0.50302766 Z"
+                     style="fill:var(--color-background);fill-opacity:1;stroke:#ff0000;stroke-opacity:1" />
+                </svg>
+
+          </li>
           <li class="pure-menu-item">
             <a class="github-link" href="https://github.com/dgtlmoon/changedetection.io">
               {% include "svgs/github.svg" %}
@@ -106,19 +132,57 @@
     </div>
     {% if hosted_sticky %}
       <div class="sticky-tab" id="hosted-sticky">
-        <a href="https://lemonade.changedetection.io/start?ref={{guid}}">Let us host your instance!</a>
+        <a href="https://changedetection.io/?ref={{guid}}">Let us host your instance!</a>
       </div>
     {% endif %}
     {% if left_sticky %}
       <div class="sticky-tab" id="left-sticky">
-        <a href="{{url_for('preview_page', uuid=uuid)}}">Show current snapshot</a>
+        <a href="{{url_for('preview_page', uuid=uuid)}}">Show current snapshot</a><br>
+          Visualise <strong>triggers</strong> and <strong>ignored text</strong>
       </div>
     {% endif %}
     {% if right_sticky %}
       <div class="sticky-tab" id="right-sticky">{{ right_sticky }}</div>
     {% endif %}
     <section class="content">
-      <header>
+        <div id="overlay">
+            <div class="content">
+                <strong>changedetection.io needs your support!</strong><br>
+                <p>
+                    You can help us by supporting changedetection.io on these platforms;
+                </p>
+                <p>
+                <ul>
+                    <li>
+                        <a href="https://alternativeto.net/software/changedetection-io/about/">Rate us at
+                        AlternativeTo.net</a>
+                    </li>
+                <li>
+                    <a href="https://github.com/dgtlmoon/changedetection.io">Star us on GitHub</a>
+                </li>
+                <li>
+                    <a href="https://twitter.com/change_det_io">Follow us at Twitter/X</a>
+                </li>
+                <li>
+                    <a href="https://www.linkedin.com/company/changedetection-io">Check us out on LinkedIn</a>
+                </li>
+                <li>
+                    And tell your friends and colleagues :)
+                </li>
+                </ul>
+                </p>
+                <p>
+                    The more popular changedetection.io is, the more time we can dedicate to adding amazing features!
+                </p>
+                <p>
+                    Many thanks :)<br>
+                </p>
+                <p>
+                    <i>changedetection.io team</i>
+                </p>
+            </div>
+        </div>
+        <header>
         {% block header %}{% endblock %}
       </header>
 
@@ -137,16 +201,13 @@
           <li class="message">
             Share this link:
             <span id="share-link">{{ session['share-link'] }}</span>
-            <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='copy.svg')}}"/>
+            <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='copy.svg')}}" >
           </li>
         </ul>
       {% endif %}
       {% block content %}{% endblock %}
     </section>
-    <script
-      type="text/javascript"
-      src="{{url_for('static_content', group='js', filename='toggle-theme.js')}}"
-      defer></script>
+    <script src="{{url_for('static_content', group='js', filename='toggle-theme.js')}}" defer></script>
   </body>
 
 </html>

changedetectionio/templates/clear_all_history.html

@@ -6,7 +6,7 @@
       action="{{url_for('clear_all_history')}}"
       method="POST"
     >
-      <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" />
+      <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
       <fieldset>
         <div class="pure-control-group">
           This will remove version history (snapshots) for ALL watches, but keep

changedetectionio/templates/diff.html

@@ -6,52 +6,64 @@
     {% if last_error_screenshot %}
     const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
     {% endif %}
+
+    const highlight_submit_ignore_url="{{url_for('highlight_submit_ignore_url', uuid=uuid)}}";
+
 </script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
 <div id="settings">
-    <h1>Differences</h1>
     <form class="pure-form " action="" method="GET">
         <fieldset>
-
-            <label for="diffWords" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffWords" value="diffWords"/> Words</label>
-            <label for="diffLines" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffLines" value="diffLines" checked=""/> Lines</label>
-
-            <label for="diffChars" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffChars" value="diffChars"/> Chars</label>
-            <!-- @todo - when mimetype is JSON, select this by default? -->
-            <label for="diffJson" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffJson" value="diffJson" /> JSON</label>
-
             {% if versions|length >= 1 %}
-            <label for="diff-version">Compare newest (<span id="current-v-date"></span>) with</label>
-            <select id="diff-version" name="previous_version">
-                {% for version in versions|reverse %}
-                <option value="{{version}}" {% if version== current_previous_version %} selected="" {% endif %}>
-                    {{version}}
-                </option>
-                {% endfor %}
-            </select>
-            <button type="submit" class="pure-button pure-button-primary">Go</button>
+                <strong>Compare</strong>
+                <del class="change"><span>from</span></del>
+                <select id="diff-version" name="from_version" class="needs-localtime">
+                    {% for version in versions|reverse %}
+                        <option value="{{ version }}" {% if version== from_version %} selected="" {% endif %}>
+                            {{ version }}
+                        </option>
+                    {% endfor %}
+                </select>
+                <ins class="change"><span>to</span></ins>
+                <select id="current-version" name="to_version" class="needs-localtime">
+                    {% for version in versions|reverse %}
+                        <option value="{{ version }}" {% if version== to_version %} selected="" {% endif %}>
+                            {{ version }}
+                        </option>
+                    {% endfor %}
+                </select>
+                <button type="submit" class="pure-button pure-button-primary">Go</button>
             {% endif %}
         </fieldset>
-    </form>
-    <del>Removed text</del>
-    <ins>Inserted Text</ins>
-    <span>
+        <fieldset>
+            <strong>Style</strong>
+            <label for="diffWords" class="pure-checkbox">
+                <input type="radio" name="diff_type" id="diffWords" value="diffWords"> Words</label>
+            <label for="diffLines" class="pure-checkbox">
+                <input type="radio" name="diff_type" id="diffLines" value="diffLines" checked=""> Lines</label>
+
+            <label for="diffChars" class="pure-checkbox">
+                <input type="radio" name="diff_type" id="diffChars" value="diffChars"> Chars</label>
+            <!-- @todo - when mimetype is JSON, select this by default? -->
+            <label for="diffJson" class="pure-checkbox">
+                <input type="radio" name="diff_type" id="diffJson" value="diffJson"> JSON</label>
+
+            <span>
         <!-- https://github.com/kpdecker/jsdiff/issues/389 ? -->
         <label for="ignoreWhitespace" class="pure-checkbox" id="label-diff-ignorewhitespace">
-            <input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace"/> Ignore Whitespace</label>
+            <input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace"> Ignore Whitespace</label>
     </span>
+        </fieldset>
+    </form>
+
 </div>
 
 <div id="diff-jump">
-    <a onclick="next_diff();">Jump</a>
+    <a id="jump-next-diff" title="Jump to next difference">Jump</a>
 </div>
 
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="tabs">
     <ul>
         {% if last_error_text %}<li class="tab" id="error-text-tab"><a href="#error-text">Error Text</a></li> {% endif %}
@@ -72,12 +84,10 @@
 
     <div class="tab-pane-inner" id="error-screenshot">
         <div class="snapshot-age error">{{watch_a.snapshot_error_screenshot_ctime|format_seconds_ago}} seconds ago</div>
-        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current error-ing screenshot from most recent request"/>
+        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current error-ing screenshot from most recent request" >
     </div>
 
      <div class="tab-pane-inner" id="text">
-         <div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.</div>
-
          {% if password_enabled_and_share_is_off %}
            <div class="tip">Pro-tip: You can enable <strong>"share access when password is enabled"</strong> from settings</div>
          {% endif %}
@@ -88,10 +98,10 @@
              <tbody>
              <tr>
                  <!-- just proof of concept copied straight from github.com/kpdecker/jsdiff -->
-                 <td id="a" style="display: none;">{{previous}}</td>
-                 <td id="b" style="display: none;">{{newest}}</td>
+                 <td id="a" style="display: none;">{{from_version_file_contents}}</td>
+                 <td id="b" style="display: none;">{{to_version_file_contents}}</td>
                  <td id="diff-col">
-                     <span id="result"></span>
+                     <span id="result" class="highlightable-filter"></span>
                  </td>
              </tr>
              </tbody>
@@ -105,7 +115,7 @@
          {% if is_html_webdriver %}
            {% if screenshot %}
             <div class="snapshot-age">{{watch_a.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
-            <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
+            <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request" >
            {% else %}
               No screenshot available just yet! Try rechecking the page.
            {% endif %}
@@ -117,7 +127,7 @@
         <form id="extract-data-form" class="pure-form pure-form-stacked edit-form"
               action="{{ url_for('diff_history_page', uuid=uuid) }}#extract"
               method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
 
             <p>This tool will extract text data from all of the watch history.</p>
 
@@ -149,9 +159,9 @@
 <script>
     const newest_version_timestamp = {{newest_version_timestamp}};
 </script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff.min.js')}}"></script>
+<script src="{{url_for('static_content', group='js', filename='diff.min.js')}}"></script>
 
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
+<script src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
 
 
 {% endblock %}

changedetectionio/templates/edit.html

@@ -2,29 +2,36 @@
 {% block content %}
 {% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <script>
-    const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
-    const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
-    const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
-    const playwright_enabled={% if playwright_enabled %} true {% else %} false {% endif %};
-
+    const browser_steps_available_screenshots=JSON.parse('{{ watch.get_browsersteps_available_screenshots|tojson }}');
+    const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
+    const browser_steps_fetch_screenshot_image_url="{{url_for('browser_steps.browser_steps_fetch_screenshot_image', uuid=uuid)}}";
+    const browser_steps_last_error_step={{ watch.browser_steps_last_error_step|tojson }};
+    const browser_steps_start_url="{{url_for('browser_steps.browsersteps_start_session', uuid=uuid)}}";
+    const browser_steps_sync_url="{{url_for('browser_steps.browsersteps_ui_update', uuid=uuid)}}";
 {% if emailprefix %}
     const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');
 {% endif %}
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
+    const playwright_enabled={% if playwright_enabled %} true {% else %} false {% endif %};
+    const recheck_proxy_start_url="{{url_for('check_proxies.start_check', uuid=uuid)}}";
+    const proxy_recheck_status_url="{{url_for('check_proxies.get_recheck_status', uuid=uuid)}}";
+    const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
+    const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
 
-    const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
-    const browser_steps_sync_url="{{url_for('browser_steps.browsersteps_ui_update', uuid=uuid)}}";
 </script>
 
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></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>
+<script src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
 {% if playwright_enabled %}
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='browser-steps.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='browser-steps.js')}}" defer></script>
 {% endif %}
 
+<script src="{{url_for('static_content', group='js', filename='recheck-proxy.js')}}" defer></script>
+
 <div class="edit-form monospaced-textarea">
 
     <div class="tabs collapsable">
@@ -44,13 +51,14 @@
             <li class="tab"><a href="#restock">Restock Detection</a></li>
             {% endif %}
             <li class="tab"><a href="#notifications">Notifications</a></li>
+            <li class="tab"><a href="#stats">Stats</a></li>
         </ul>
     </div>
 
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked"
               action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next'), unpause_on_save = request.args.get('unpause_on_save')) }}" method="POST">
-             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
 
             <div class="tab-pane-inner" id="general">
                 <fieldset>
@@ -73,7 +81,7 @@
                         {{ render_field(form.title, class="m-d") }}
                     </div>
                     <div class="pure-control-group">
-                        {{ render_field(form.tag) }}
+                        {{ render_field(form.tags) }}
                         <span class="pure-form-message-inline">Organisational tag/group name used in the main listing page</span>
                     </div>
                     <div class="pure-control-group">
@@ -104,12 +112,13 @@
                         <span class="pure-form-message-inline">
                             <p>Use the <strong>Basic</strong> method (default) where your watched site doesn't need Javascript to render.</p>
                             <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
-                            Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using BrightData Proxies, find out more here.</a>
+                            Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
                         </span>
                     </div>
                 {% if form.proxy %}
                     <div class="pure-control-group inline-radio">
-                        {{ render_field(form.proxy, class="fetch-backend-proxy") }}
+                          <div>{{ form.proxy.label }} <a href="" id="check-all-proxies" class="pure-button button-secondary button-xsmall" >Check/Scan all</a></div>
+                          <div>{{ form.proxy(class="fetch-backend-proxy") }}</div>
                         <span class="pure-form-message-inline">
                         Choose a proxy for this watch
                         </span>
@@ -150,6 +159,17 @@
 {{ render_field(form.headers, rows=5, placeholder="Example
 Cookie: foobar
 User-Agent: wonderbra 1.0") }}
+
+                        <div class="pure-form-message-inline">
+                            {% if has_extra_headers_file %}
+                                <strong>Alert! Extra headers file found and will be added to this watch!</strong>
+                            {% else %}
+                                Headers can be also read from a file in your data-directory <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Adding-headers-from-an-external-file">Read more here</a>
+                            {% endif %}
+                            <br>
+                            (Not supported by Selenium browser)
+                        </div>
+
                     </div>
                     <div class="pure-control-group" id="request-body">
                                         {{ render_field(form.body, rows=5, placeholder="Example
@@ -163,7 +183,7 @@ User-Agent: wonderbra 1.0") }}
             </div>
             {% if playwright_enabled %}
             <div class="tab-pane-inner" id="browser-steps">
-                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
+                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
                 <fieldset>
                     <div class="pure-control-group">
                         <!--
@@ -186,11 +206,12 @@ User-Agent: wonderbra 1.0") }}
                                     <span class="loader" >
                                         <span id="browsersteps-click-start">
                                             <h2 >Click here to Start</h2>
-                                            Please allow 10-15 seconds for the browser to connect.
+                                            <svg style="height: 3.5rem;" version="1.1" viewBox="0 0 32 32"  xml:space="preserve" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g id="Layer_1"/><g id="play_x5F_alt"><path d="M16,0C7.164,0,0,7.164,0,16s7.164,16,16,16s16-7.164,16-16S24.836,0,16,0z M10,24V8l16.008,8L10,24z" style="fill: var(--color-grey-400);"/></g></svg><br>
+                                            Please allow 10-15 seconds for the browser to connect.<br>
                                         </span>
                                         <div class="spinner"  style="display: none;"></div>
                                     </span>
-                                    <img  class="noselect" id="browsersteps-img" src="" style="max-width: 100%; width: 100%;" />
+                                    <img class="noselect" id="browsersteps-img" src="" style="max-width: 100%; width: 100%;" >
                                     <canvas  class="noselect" id="browsersteps-selector-canvas" style="max-width: 100%; width: 100%;"></canvas>
                                 </div>
                             </div>
@@ -220,7 +241,7 @@ User-Agent: wonderbra 1.0") }}
                     <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!"/>
+                            <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 %}
@@ -269,11 +290,12 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                                 {% endif %}
                             </ul>
                         </li>
-                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash,
+                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash. To specify XPath to be used explicitly or the XPath rule starts with an XPath function: Prefix with <code>xpath:</code>
                             <ul>
-                                <li>Example:  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath://*[contains(@class, 'sametext')]</code>, <a
+                                <li>Example:  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath:count(//*[contains(@class, 'sametext')])</code>, <a
                                 href="http://xpather.com/" target="new">test your XPath here</a></li>
                                 <li>Example: Get all titles from an RSS feed <code>//title/text()</code></li>
+                                <li>To use XPath1.0: Prefix with <code>xpath1:</code></li>
                             </ul>
                             </li>
                     </ul>
@@ -360,15 +382,16 @@ Unavailable") }}
                         {{ render_field(form.extract_text, rows=5, placeholder="\d+ online") }}
                         <span class="pure-form-message-inline">
                     <ul>
-                        <li>Extracts text in the final output (line by line) after other filters using regular expressions;
+                        <li>Extracts text in the final output (line by line) after other filters using regular expressions or string match;
                             <ul>
                                 <li>Regular expression &dash; example <code>/reports.+?2022/i</code></li>
+                                <li>Don't forget to consider the white-space at the start of a line <code>/.+?reports.+?2022/i</code></li>
                                 <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br></li>
                                 <li>Keyword example &dash; example <code>Out of stock</code></li>
                                 <li>Use groups to extract just that text &dash; example <code>/reports.+?(\d+)/i</code> returns a list of years only</li>
                             </ul>
                         </li>
-                        <li>One line per regular-expression/ string match</li>
+                        <li>One line per regular-expression/string match</li>
                     </ul>
                         </span>
                     </div>
@@ -390,7 +413,7 @@ Unavailable") }}
 
             {% if watch['processor'] == 'text_json_diff' %}
             <div class="tab-pane-inner visual-selector-ui" id="visualselector">
-                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
+                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
 
                 <fieldset>
                     <div class="pure-control-group">
@@ -407,7 +430,7 @@ Unavailable") }}
                                 <!-- request the screenshot and get the element offset info ready -->
                                 <!-- use img src ready load to know everything is ready to map out -->
                                 <!-- @todo: maybe something interesting like a field to select 'elements that contain text... and their parents n' -->
-                                <img id="selector-background" />
+                                <img id="selector-background" >
                                 <canvas id="selector-canvas"></canvas>
                             </div>
                             <div id="selector-current-xpath" style="overflow-x: hidden"><strong>Currently:</strong>&nbsp;<span class="text">Loading...</span></div>
@@ -422,7 +445,35 @@ Unavailable") }}
                 </fieldset>
             </div>
             {% endif %}
-
+            <div class="tab-pane-inner" id="stats">
+                <div class="pure-control-group">
+                    <style>
+                    #stats-table tr > td:first-child {
+                        font-weight: bold;
+                    }
+                    </style>
+                    <table class="pure-table" id="stats-table">
+                        <tbody>
+                        <tr>
+                            <td>Check count</td>
+                            <td>{{ "{:,}".format( watch.check_count) }}</td>
+                        </tr>
+                        <tr>
+                            <td>Consecutive filter failures</td>
+                            <td>{{ "{:,}".format( watch.consecutive_filter_failures) }}</td>
+                        </tr>
+                        <tr>
+                            <td>History length</td>
+                            <td>{{ "{:,}".format(watch.history|length) }}</td>
+                        </tr>
+                        <tr>
+                            <td>Last fetch time</td>
+                            <td>{{ watch.fetch_time }}s</td>
+                        </tr>
+                        </tbody>
+                    </table>
+                </div>
+            </div>
             <div id="actions">
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}

changedetectionio/templates/import.html

@@ -1,19 +1,20 @@
 {% extends 'base.html' %}
 {% block content %}
 {% from '_helpers.jinja' import render_field %}
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="edit-form monospaced-textarea">
 
     <div class="tabs collapsable">
         <ul>
             <li class="tab" id=""><a href="#url-list">URL List</a></li>
             <li class="tab"><a href="#distill-io">Distill.io</a></li>
+            <li class="tab"><a href="#xlsx">.XLSX &amp; Wachete</a></li>
         </ul>
     </div>
 
     <div class="box-wrap inner">
-        <form class="pure-form pure-form-aligned" action="{{url_for('import_page')}}" method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+        <form class="pure-form" action="{{url_for('import_page')}}" method="POST" enctype="multipart/form-data">
+            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
             <div class="tab-pane-inner" id="url-list">
                     <legend>
                         Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma
@@ -79,6 +80,42 @@
 " rows="25">{{ original_distill_json }}</textarea>
 
             </div>
+            <div class="tab-pane-inner" id="xlsx">
+            <fieldset>
+                <div class="pure-control-group">
+                {{ render_field(form.xlsx_file, class="processor") }}
+                </div>
+                <div class="pure-control-group">
+                    {{ render_field(form.file_mapping, class="processor") }}
+                </div>
+            </fieldset>
+                <div class="pure-control-group">
+                <span class="pure-form-message-inline">
+                    Table of custom column and data types mapping for the <strong>Custom mapping</strong> File mapping type.
+                </span>
+                    <table style="border: 1px solid #aaa; padding: 0.5rem; border-radius: 4px;">
+                        <tr>
+                            <td><strong>Column #</strong></td>
+                            {% for n in range(4) %}
+                                <td><input type="number" name="custom_xlsx[col_{{n}}]" style="width: 4rem;" min="1"></td>
+                            {%  endfor %}
+                        </tr>
+                        <tr>
+                            <td><strong>Type</strong></td>
+                            {% for n in range(4) %}
+                                <td><select name="custom_xlsx[col_type_{{n}}]">
+                                    <option value="" style="color: #aaa"> -- none --</option>
+                                    <option value="url">URL</option>
+                                    <option value="title">Title</option>
+                                    <option value="include_filter">CSS/xPath filter</option>
+                                    <option value="tag">Group / Tag name(s)</option>
+                                    <option value="interval_minutes">Recheck time (minutes)</option>
+                                </select></td>
+                            {%  endfor %}
+                        </tr>
+                    </table>
+                </div>
+            </div>
             <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">Import</button>
         </form>
 

changedetectionio/templates/login.html

@@ -4,13 +4,13 @@
 <div class="login-form">
  <div class="inner">
     <form class="pure-form pure-form-stacked" action="{{url_for('login')}}" method="POST">
-        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
         <fieldset>
             <div class="pure-control-group">
                 <label for="password">Password</label>
                 <input type="password" id="password" required="" name="password" value=""
                        size="15" autofocus />
-                <input type="hidden" id="email" name="email" value="defaultuser@changedetection.io" />
+                <input type="hidden" id="email" name="email" value="defaultuser@changedetection.io" >
             </div>
             <div class="pure-control-group">
                 <button type="submit" class="pure-button pure-button-primary">Login</button>

changedetectionio/templates/preview.html

@@ -6,10 +6,11 @@
     {% if last_error_screenshot %}
     const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
     {% endif %}
+    const highlight_submit_ignore_url="{{url_for('highlight_submit_ignore_url', uuid=uuid)}}";
 </script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="tabs">
     <ul>
         {% if last_error_text %}<li class="tab" id="error-text-tab"><a href="#error-text">Error Text</a></li> {% endif %}
@@ -20,7 +21,7 @@
         {% endif %}
     </ul>
 </div>
-
+<form><input type="hidden" name="csrf_token" value="{{ csrf_token() }}"></form>
 <div id="diff-ui">
     <div class="tab-pane-inner" id="error-text">
         <div class="snapshot-age error">{{watch.error_text_ctime|format_seconds_ago}} seconds ago</div>
@@ -31,16 +32,17 @@
 
     <div class="tab-pane-inner" id="error-screenshot">
         <div class="snapshot-age error">{{watch.snapshot_error_screenshot_ctime|format_seconds_ago}} seconds ago</div>
-        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current erroring screenshot from most recent request"/>
+        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current erroring screenshot from most recent request" >
     </div>
 
     <div class="tab-pane-inner" id="text">
         <div class="snapshot-age">{{watch.snapshot_text_ctime|format_timestamp_timeago}}</div>
-        <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span>
+        <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span> <span class="tip"><strong>Pro-tip</strong>: Highlight text to add to ignore filters</span>
+
         <table>
             <tbody>
             <tr>
-                <td id="diff-col">
+                <td id="diff-col" class="highlightable-filter">
                     {% for row in content %}
                     <div class="{{row.classes}}">{{row.line}}</div>
                     {% endfor %}
@@ -58,7 +60,7 @@
          {% if is_html_webdriver %}
            {% if screenshot %}
              <div class="snapshot-age">{{watch.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
-             <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
+             <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request" >
            {% else %}
               No screenshot available just yet! Try rechecking the page.
            {% endif %}

changedetectionio/templates/settings.html

@@ -9,10 +9,10 @@
     const email_notification_prefix=JSON.parse('{{emailprefix|tojson}}');
 {% endif %}
 </script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
 <div class="edit-form">
     <div class="tabs collapsable">
         <ul>
@@ -26,7 +26,7 @@
     </div>
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked settings" action="{{url_for('settings_page')}}" method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
             <div class="tab-pane-inner" id="general">
                 <fieldset>
                     <div class="pure-control-group">
@@ -63,12 +63,8 @@
                         </span>
                     </div>
                     <div class="pure-control-group">
-                        {{ render_field(form.application.form.base_url, placeholder="http://yoursite.com:5000/",
-                        class="m-d") }}
-                        <span class="pure-form-message-inline">
-                            Base URL used for the <code>{{ '{{ base_url }}' }}</code> token in notifications and RSS links.<br>Default value is the ENV var 'BASE_URL' (Currently "{{settings_application['current_base_url']}}"),
-                            <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">read more here</a>.
-                        </span>
+                        {{ render_field(form.application.form.pager_size) }}
+                        <span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
                     </div>
 
                     <div class="pure-control-group">
@@ -96,6 +92,13 @@
                         {{ render_common_settings_form(form.application.form, emailprefix, settings_application) }}
                     </div>
                 </fieldset>
+                <div class="pure-control-group" id="notification-base-url">
+                    {{ render_field(form.application.form.base_url, class="m-d") }}
+                    <span class="pure-form-message-inline">
+                        Base URL used for the <code>{{ '{{ base_url }}' }}</code> token in notification links.<br>
+                        Default value is the system environment variable '<code>BASE_URL</code>' - <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">read more here</a>.
+                    </span>
+                </div>
             </div>
 
             <div class="tab-pane-inner" id="fetching">
@@ -106,7 +109,7 @@
                         <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
                     </span>
                     <br>
-                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using BrightData Proxies, find out more here.</a>
+                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
                 </div>
                 <fieldset class="pure-group" id="webdriver-override-options">
                     <div class="pure-form-message-inline">
@@ -175,22 +178,66 @@ nav
                         <span style="display:none;" id="api-key-copy" >copy</span>
                     </div>
                 </div>
+                <div class="pure-control-group">
+                    <a href="{{url_for('settings_reset_api_key')}}" class="pure-button button-small button-cancel">Regenerate API key</a>
+                </div>
             </div>
             <div class="tab-pane-inner" id="proxies">
+                <div id="recommended-proxy">
+                    <div>
+                        <img style="height: 2em;" src="{{url_for('static_content', group='images', filename='brightdata.svg')}}" alt="BrightData Proxy Provider">
+                        <p>BrightData offer world-class proxy services, "Data Center" proxies are a very affordable way to proxy your requests, whilst <strong><a href="https://brightdata.grsm.io/n0r16zf7eivq">WebUnlocker</a></strong> can help solve most CAPTCHAs.</p>
+                        <p>
+                            BrightData offer many <a href="https://brightdata.com/proxy-types" target="new">many different types of proxies</a>, it is worth reading about what is best for your use-case.
+                        </p>
 
-                <p><strong>Tip</strong>: You can connect to websites using <a href="https://brightdata.grsm.io/n0r16zf7eivq">BrightData</a> proxies, their service <strong>WebUnlocker</strong> will solve most CAPTCHAs, whilst their <strong>Residential Proxies</strong> may help to avoid CAPTCHA altogether. </p>
-                <p>It may be easier to try <strong>WebUnlocker</strong> first, WebUnlocker also supports country selection.</p>
+                        <p>
+                            When you have <a href="https://brightdata.grsm.io/n0r16zf7eivq">registered</a>, enabled the required services, visit the <A href="https://brightdata.com/cp/api_example?">API example page</A>, then select <strong>Python</strong>, set the country you wish to use, then copy+paste the access Proxy URL into the "Extra Proxies" boxes below.<br>
+                        </p>
+                        <p>
+                            The Proxy URL with BrightData should start with <code>http://brd-customer...</code>
+                        </p>
+                        <p>When you sign up using <a href="https://brightdata.grsm.io/n0r16zf7eivq">https://brightdata.grsm.io/n0r16zf7eivq</a> BrightData will match any first deposit up to $150</p>
+                    </div>
+                    <div>
+                        <img style="height: 2em;"
+                             src="{{url_for('static_content', group='images', filename='oxylabs.svg')}}"
+                             alt="Oxylabs Proxy Provider">
+                        <p>
+                            Collect public data at scale with industry-leading web scraping solutions and the world’s
+                            largest ethical proxy network.
+                        </p>
+                        <p>
+                            Oxylabs also provide a <a href="https://oxylabs.io/products/web-unblocker"><strong>WebUnlocker</strong></a>
+                            proxy that bypasses sophisticated anti-bot systems, so you don’t have to.<br>
+                        </p>
+                        <p>
+                            Serve over <a href="https://oxylabs.io/location-proxy">195 countries</a>, providing <a
+                                href="https://oxylabs.io/products/residential-proxy-pool">Residential</a>, <a
+                                href="https://oxylabs.io/products/mobile-proxies">Mobile</a> and <a
+                                href="https://oxylabs.io/products/rotating-isp-proxies">ISP proxies</a> and much more.
+                        </p>
+                        <p>
+                            Use the promo code <strong>boost35</strong> with this link <a href="https://oxylabs.go2cloud.org/SH2d">https://oxylabs.go2cloud.org/SH2d</a> for 35% off Residential, Mobile proxies, Web Unblocker, and Scraper APIs. Built-in proxies enable you to access data from all around the world and help overcome anti-bot solutions.
+
+                        </p>
+
+                        
+                    </div>
+                </div>
                 <p>
-                    When you have <a href="https://brightdata.grsm.io/n0r16zf7eivq">registered</a>, enabled the required services, visit the <A href="https://brightdata.com/cp/api_example?">API example page</A>, then select <strong>Python</strong>, set the country you wish to use, then copy+paste the example URL below<br>
-                    The Proxy URL with BrightData should start with <code>http://brd-customer...</code>
+                    Your proxy provider may need to whitelist our IP of <code>204.15.192.195</code>
                 </p>
+               <p><strong>Tip</strong>: "Residential" and "Mobile" proxy type can be more successfull than "Data Center" for blocked websites.
 
-                <p>When you sign up using <a href="https://brightdata.grsm.io/n0r16zf7eivq">https://brightdata.grsm.io/n0r16zf7eivq</a> BrightData will match any first deposit up to $150</p>
-
-
-                <div class="pure-control-group">
-                    {{ render_field(form.requests.form.extra_proxies) }}
-                    <span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span>
+                <div class="pure-control-group" id="extra-proxies-setting">
+                {{ render_field(form.requests.form.extra_proxies) }}
+                <span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span><br>
+                <span class="pure-form-message-inline">SOCKS5 proxies with authentication are only supported with 'plain requests' fetcher, for other fetchers you should whitelist the IP access instead</span>
+                </div>
+                <div class="pure-control-group" id="extra-browsers-setting">
+                    <span class="pure-form-message-inline"><i>Extra Browsers</i> allow changedetection.io to communicate with a different web-browser.</span><br>
+                  {{ render_field(form.requests.form.extra_browsers) }}
                 </div>
             </div>
             <div id="actions">

changedetectionio/templates/svgs/github.svg

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

changedetectionio/templates/svgs/search-icon.svg

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

changedetectionio/templates/watch-overview.html

@@ -1,20 +1,19 @@
 {% extends 'base.html' %}
 {% block content %}
 {% from '_helpers.jinja' import render_simple_field, render_field %}
-{% from '_pagination.jinja' import pagination %}
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
+<script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
 
 <div class="box">
 
     <form class="pure-form" action="{{ url_for('form_quick_watch_add') }}" method="POST" id="new-watch-form">
-        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
         <fieldset>
             <legend>Add a new change detection watch</legend>
             <div id="watch-add-wrapper-zone">
                 <div>
                     {{ render_simple_field(form.url, placeholder="https://...", required=true) }}
-                    {{ render_simple_field(form.tag, value=active_tag if active_tag else '', placeholder="watch label / tag") }}
+                    {{ render_simple_field(form.tags, value=tags[active_tag].title if active_tag else '', placeholder="watch label / tag") }}
                 </div>
                 <div>
                     {{ render_simple_field(form.watch_submit_button, title="Watch this URL!" ) }}
@@ -26,41 +25,50 @@
             </div>
 
         </fieldset>
-        <span style="color:#eee; font-size: 80%;"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" /> Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></a></span>
+        <span style="color:#eee; font-size: 80%;"><img alt="Create a shareable link" style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" > Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></span>
     </form>
 
     <form class="pure-form" action="{{ url_for('form_watch_list_checkbox_operations') }}" method="POST" id="watch-list-form">
-    <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+    <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
+    <input type="hidden" id="op_extradata" name="op_extradata" value="" >
     <div id="checkbox-operations">
         <button class="pure-button button-secondary button-xsmall"  name="op" value="pause">Pause</button>
         <button class="pure-button button-secondary button-xsmall"  name="op" value="unpause">UnPause</button>
         <button class="pure-button button-secondary button-xsmall"  name="op" value="mute">Mute</button>
         <button class="pure-button button-secondary button-xsmall"  name="op" value="unmute">UnMute</button>
         <button class="pure-button button-secondary button-xsmall" name="op" value="recheck">Recheck</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="assign-tag" id="checkbox-assign-tag">Tag</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="mark-viewed">Mark viewed</button>
         <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default">Use default notification</button>
-        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242; font-size: 70%" name="op" value="delete">Delete</button>
+        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="clear-history">Clear/reset history</button>
+        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="delete">Delete</button>
     </div>
+    {% if watches|length >= pagination.per_page %}
+        {{ pagination.info }}
+    {% endif %}
+    {% if search_q %}<div id="search-result-info">Searching "<strong><i>{{search_q}}</i></strong>"</div>{% endif %}
     <div>
         <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag }}">All</a>
-        {% for tag in tags %}
+        {% for uuid, tag in tags.items() %}
             {% if tag != "" %}
-                <a href="{{url_for('index', tag=tag) }}" class="pure-button button-tag {{'active' if active_tag == tag }}">{{ tag }}</a>
+                <a href="{{url_for('index', tag=uuid) }}" class="pure-button button-tag {{'active' if active_tag == uuid }}">{{ tag.title }}</a>
             {% endif %}
         {% endfor %}
     </div>
 
-    {% set sort_order = request.args.get('order', 'asc') == 'asc' %}
-    {% set sort_attribute = request.args.get('sort', 'last_changed')   %}
+    {% set sort_order = sort_order or 'asc' %}
+    {% set sort_attribute = sort_attribute or 'last_changed'  %}
     {% set pagination_page = request.args.get('page', 0) %}
 
     <div id="watch-table-wrapper">
+
         <table class="pure-table pure-table-striped watch-table">
             <thead>
             <tr>
-                <th><input style="vertical-align: middle" type="checkbox" id="check-all"/> #</th>
-                <th></th>
-                {% set link_order = "desc" if sort_order else "asc" %}
+                {% set link_order = "desc" if sort_order  == 'asc' else "asc" %}
                 {% set arrow_span = "" %}
+                <th><input style="vertical-align: middle" type="checkbox" id="check-all" > <a class="{{ 'active '+link_order if sort_attribute == 'date_created' else 'inactive' }}"  href="{{url_for('index', sort='date_created', order=link_order, tag=active_tag)}}"># <span class='arrow {{link_order}}'></span></a></th>
+                <th></th>
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('index', sort='label', order=link_order, tag=active_tag)}}">Website <span class='arrow {{link_order}}'></span></a></th>
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag)}}">Last Checked <span class='arrow {{link_order}}'></span></a></th>
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
@@ -68,40 +76,43 @@
             </tr>
             </thead>
             <tbody>
+            {% if not watches|length %}
+            <tr>
+                <td colspan="6">No website watches configured, please add a URL in the box above, or <a href="{{ url_for('import_page')}}" >import a list</a>.</td>
+            </tr>
+            {% endif %}
+            {% for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))|pagination_slice(skip=pagination.skip) %}
 
-            {% set sorted_watches = watches|sort(attribute=sort_attribute, reverse=sort_order) %}
-            {% for watch in sorted_watches %}
+                {% set is_unviewed =  watch.newest_history_key| int > watch.last_viewed and watch.history_n>=2 %}
 
-            {# WIP for pagination, disabled for now
-              {% if not ( loop.index >= 3 and loop.index <=4) %}{% continue %}{% endif %} -->
-             #}
             <tr id="{{ watch.uuid }}"
                 class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }} processor-{{ watch['processor'] }}
                 {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
                 {% if watch.last_notification_error is defined and watch.last_notification_error != False %}error{% endif %}
                 {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
-                {% if watch.newest_history_key| int > watch.last_viewed and watch.history_n>=2 %}unviewed{% endif %}
+                {% if is_unviewed %}unviewed{% endif %}
                 {% if watch.uuid in queued_uuids %}queued{% endif %}">
-                <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} "/> <span>{{ loop.index }}</span></td>
+                <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span>{{ loop.index+pagination.skip }}</span></td>
                 <td class="inline watch-controls">
                     {% if not watch.paused %}
-                    <a class="state-off" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause"/></a>
+                    <a class="state-off" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause" ></a>
                     {% else %}
-                    <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause"/></a>
+                    <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause" ></a>
                     {% endif %}
-                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute"/></a>
+                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag)}}"><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">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
                     <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
-                    <a class="link-spread" href="{{url_for('form_share_put_watch', uuid=watch.uuid)}}"><img class="status-icon"  src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" /></a>
+                    <a class="link-spread" href="{{url_for('form_share_put_watch', uuid=watch.uuid)}}"><img src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" ></a>
 
                     {% if watch.get_fetch_backend == "html_webdriver"
                          or (  watch.get_fetch_backend == "system" and system_default_fetcher == 'html_webdriver'  )
+                         or "extra_browser_" in watch.get_fetch_backend
                     %}
-                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a chrome browser" />
+                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a Chrome browser" >
                     {% endif %}
 
-                    {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" />{% endif %}
+                    {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" >{% endif %}
                     {% if watch.last_error is defined and watch.last_error != False %}
                     <div class="fetch-error">{{ watch.last_error }}
 
@@ -112,6 +123,9 @@
                             <a href="{{ url_for('settings_page', uuid=watch.uuid) }}#proxies">Try adding external proxies/locations</a>
                         
                         {% endif %}
+                        {% if 'empty result or contain only an image' in watch.last_error %}
+                            <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Detecting-changes-in-images">more help here</a>.
+                        {% endif %}
                     </div>
                     {% endif %}
                     {% if watch.last_notification_error is defined and watch.last_notification_error != False %}
@@ -123,7 +137,7 @@
                         <div class="ldjson-price-track-offer">Embedded price data detected, follow only price data? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
                         {% endif %}
                         {% if watch['track_ldjson_price_data'] == 'accepted' %}
-                        <span class="tracking-ldjson-price-data" title="Automatically following embedded price information"><img src="{{url_for('static_content', group='images', filename='price-tag-icon.svg')}}"  class="status-icon price-follow-tag-icon"/> Price</span>
+                        <span class="tracking-ldjson-price-data" title="Automatically following embedded price information"><img src="{{url_for('static_content', group='images', filename='price-tag-icon.svg')}}"  class="status-icon price-follow-tag-icon" > Price</span>
                         {% endif %}
                     {% endif %}
 
@@ -135,14 +149,17 @@
                         {% else %}
                             Not yet checked
                         {% endif %}
+                    </span>
                     {% endif %}
 
-                    {% if not active_tag %}
-                    <span class="watch-tag-list">{{ watch.tag}}</span>
-                    {% endif %}
+
+                    {% for watch_tag_uuid, watch_tag in datastore.get_all_tags_for_watch(watch['uuid']).items() %}
+                      <span class="watch-tag-list">{{ watch_tag.title }}</span>
+                    {% endfor %}
+
                 </td>
-                <td class="last-checked">{{watch|format_last_checked_time|safe}}</td>
-                <td class="last-changed">{% if watch.history_n >=2 and watch.last_changed >0 %}
+                <td class="last-checked" data-timestamp="{{ watch.last_checked }}">{{watch|format_last_checked_time|safe}}</td>
+                <td class="last-changed" data-timestamp="{{ watch.last_changed }}">{% if watch.history_n >=2 and watch.last_changed >0 %}
                     {{watch.last_changed|format_timestamp_timeago}}
                     {% else %}
                     Not yet
@@ -153,7 +170,13 @@
                        class="recheck pure-button pure-button-primary">{% if watch.uuid in queued_uuids %}Queued{% else %}Recheck{% endif %}</a>
                     <a href="{{ url_for('edit_page', uuid=watch.uuid)}}" class="pure-button pure-button-primary">Edit</a>
                     {% if watch.history_n >= 2 %}
-                    <a href="{{ url_for('diff_history_page', uuid=watch.uuid) }}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+
+                        {%  if is_unviewed %}
+                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid, from_version=watch.get_next_snapshot_key_to_last_viewed) }}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+                        {% else %}
+                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+                        {% endif %}
+
                     {% else %}
                         {% if watch.history_n == 1 or (watch.history_n ==0 and watch.error_text_ctime )%}
                             <a href="{{ url_for('preview_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button pure-button-primary">Preview</a>
@@ -165,23 +188,25 @@
             </tbody>
         </table>
         <ul id="post-list-buttons">
+            {% if errored_count %}
+            <li>
+                <a href="{{url_for('index', with_errors=1, tag=request.args.get('tag')) }}" class="pure-button button-tag button-error ">With errors ({{ errored_count }})</a>
+            </li>
+            {% endif %}
             {% if has_unviewed %}
             <li>
-                <a href="{{url_for('mark_all_viewed', tag=request.args.get('tag')) }}" class="pure-button button-tag ">Mark all viewed</a>
+                <a href="{{url_for('mark_all_viewed',with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Mark all viewed</a>
             </li>
             {% endif %}
             <li>
-               <a href="{{ url_for('form_watch_checknow', tag=active_tag) }}" class="pure-button button-tag ">Recheck
-                all {% if active_tag%}in "{{active_tag}}"{%endif%}</a>
+               <a href="{{ url_for('form_watch_checknow', tag=active_tag, with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Recheck
+                all {% if active_tag%} in "{{tags[active_tag].title}}"{%endif%}</a>
             </li>
             <li>
                 <a href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='Generic_Feed-icon.svg')}}" height="15"></a>
             </li>
         </ul>
-        {# WIP for pagination, disabled for now
-         {{ pagination(sorted_watches,3, pagination_page) }}
-         #}
-
+        {{ pagination.links }}
     </div>
     </form>
 </div>

changedetectionio/tests/conftest.py

@@ -14,13 +14,16 @@ global app
 
 def cleanup(datastore_path):
     # Unlink test output files
-    files = ['output.txt',
-             'url-watches.json',
-             'secret.txt',
-             'notification.txt',
-             'count.txt',
-             'endpoint-content.txt'
-                 ]
+    files = [
+        'count.txt',
+        'endpoint-content.txt'
+        'headers.txt',
+        'headers-testtag.txt',
+        'notification.txt',
+        'secret.txt',
+        'url-watches.json',
+        'output.txt',
+    ]
     for file in files:
         try:
             os.unlink("{}/{}".format(datastore_path, file))

changedetectionio/tests/custom_browser_url/__init__.py

@@ -0,0 +1 @@
+# placeholder

changedetectionio/tests/custom_browser_url/test_custom_browser_url.py

@@ -0,0 +1,89 @@
+# !/usr/bin/python3
+import os
+
+from flask import url_for
+from ..util import live_server_setup, wait_for_all_checks
+
+def do_test(client, live_server, make_test_use_extra_browser=False):
+
+    # Grep for this string in the logs?
+    test_url = f"https://changedetection.io/ci-test.html"
+    custom_browser_name = 'custom browser URL'
+
+    # needs to be set and something like 'ws://127.0.0.1:3000?stealth=1&--disable-web-security=true'
+    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
+
+    #####################
+    res = client.post(
+        url_for("settings_page"),
+        data={"application-empty_pages_are_a_change": "",
+              "requests-time_between_check-minutes": 180,
+              'application-fetch_backend': "html_webdriver",
+              # browserless-custom-url is setup in  .github/workflows/test-only.yml
+              # the test script run_custom_browser_url_test.sh will look for 'custom-browser-search-string' in the container logs
+              'requests-extra_browsers-0-browser_connection_url': 'ws://browserless-custom-url:3000?stealth=1&--disable-web-security=true&custom-browser-search-string=1',
+              'requests-extra_browsers-0-browser_name': custom_browser_name
+              },
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." in res.data
+
+    # Add our URL to the import page
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+    wait_for_all_checks(client)
+
+    if make_test_use_extra_browser:
+
+        # So the name should appear in the edit page under "Request" > "Fetch Method"
+        res = client.get(
+            url_for("edit_page", uuid="first"),
+            follow_redirects=True
+        )
+        assert b'custom browser URL' in res.data
+
+        res = client.post(
+            url_for("edit_page", uuid="first"),
+            data={
+                  "url": test_url,
+                  "tags": "",
+                  "headers": "",
+                  'fetch_backend': f"extra_browser_{custom_browser_name}",
+                  'webdriver_js_execute_code': ''
+            },
+            follow_redirects=True
+        )
+
+        assert b"Updated watch." in res.data
+        wait_for_all_checks(client)
+
+    # Force recheck
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
+
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+    assert b'cool it works' in res.data
+
+
+# Requires playwright to be installed
+def test_request_via_custom_browser_url(client, live_server):
+    live_server_setup(live_server)
+    # We do this so we can grep the logs of the custom container and see if the request actually went through that container
+    do_test(client, live_server, make_test_use_extra_browser=True)
+
+
+def test_request_not_via_custom_browser_url(client, live_server):
+    live_server_setup(live_server)
+    # We do this so we can grep the logs of the custom container and see if the request actually went through that container
+    do_test(client, live_server, make_test_use_extra_browser=False)

changedetectionio/tests/fetchers/test_content.py

@@ -28,8 +28,6 @@ def test_fetch_webdriver_content(client, live_server):
     )
 
     assert b"1 Imported" in res.data
-    time.sleep(3)
-
     wait_for_all_checks(client)
 
 

changedetectionio/tests/proxy_list/test_multiple_proxy.py

@@ -2,12 +2,11 @@
 
 import time
 from flask import url_for
-from ..util import live_server_setup
+from ..util import live_server_setup, wait_for_all_checks
+
 
 def test_preferred_proxy(client, live_server):
-    time.sleep(1)
     live_server_setup(live_server)
-    time.sleep(1)
     url = "http://chosen.changedetection.io"
 
     res = client.post(
@@ -20,7 +19,7 @@ def test_preferred_proxy(client, live_server):
 
     assert b"1 Imported" in res.data
 
-    time.sleep(2)
+    wait_for_all_checks(client)
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={
@@ -28,11 +27,11 @@ def test_preferred_proxy(client, live_server):
                 "fetch_backend": "html_requests",
                 "headers": "",
                 "proxy": "proxy-two",
-                "tag": "",
+                "tags": "",
                 "url": url,
               },
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
-    time.sleep(2)
+    wait_for_all_checks(client)
     # Now the request should appear in the second-squid logs

changedetectionio/tests/proxy_list/test_noproxy.py

@@ -0,0 +1,77 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+
+
+def test_noproxy_option(client, live_server):
+    live_server_setup(live_server)
+    # Run by run_proxy_tests.sh
+    # Call this URL then scan the containers that it never went through them
+    url = "http://noproxy.changedetection.io"
+
+    # Should only be available when a proxy is setup
+    res = client.get(
+        url_for("edit_page", uuid="first", unpause_on_save=1))
+    assert b'No proxy' not in res.data
+
+    # Setup a proxy
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "requests-time_between_check-minutes": 180,
+            "application-ignore_whitespace": "y",
+            "application-fetch_backend": "html_requests",
+            "requests-extra_proxies-0-proxy_name": "custom-one-proxy",
+            "requests-extra_proxies-0-proxy_url": "http://test:awesome@squid-one:3128",
+            "requests-extra_proxies-1-proxy_name": "custom-two-proxy",
+            "requests-extra_proxies-1-proxy_url": "http://test:awesome@squid-two:3128",
+            "requests-extra_proxies-2-proxy_name": "custom-proxy",
+            "requests-extra_proxies-2-proxy_url": "http://test:awesome@squid-custom:3128",
+        },
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." in res.data
+
+    # Should be available as an option
+    res = client.get(
+        url_for("settings_page", unpause_on_save=1))
+    assert b'No proxy' in res.data
+
+
+    # This will add it paused
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+    uuid = extract_UUID_from_client(client)
+    res = client.get(
+        url_for("edit_page", uuid=uuid, unpause_on_save=1))
+    assert b'No proxy' in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid=uuid, unpause_on_save=1),
+        data={
+                "include_filters": "",
+                "fetch_backend": "html_requests",
+                "headers": "",
+                "proxy": "no-proxy",
+                "tags": "",
+                "url": url,
+              },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+    # Now the request should NOT appear in the second-squid logs (handled by the run_test_proxies.sh script)
+
+    # Prove that it actually checked
+
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid]['last_checked'] != 0
+

changedetectionio/tests/proxy_socks5/proxies.json-example

@@ -0,0 +1,6 @@
+{
+  "socks5proxy": {
+    "label": "socks5proxy",
+    "url": "socks5://proxy_user123:proxy_pass123@socks5proxy:1080"
+  }
+}

changedetectionio/tests/proxy_socks5/proxies.json-example-noauth

@@ -0,0 +1,6 @@
+{
+  "socks5proxy": {
+    "label": "socks5proxy",
+    "url": "socks5://socks5proxy-noauth:1080"
+  }
+}

changedetectionio/tests/proxy_socks5/test_socks5_proxy.py

@@ -0,0 +1,63 @@
+#!/usr/bin/python3
+import os
+import time
+from flask import url_for
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
+
+
+def test_socks5(client, live_server):
+    live_server_setup(live_server)
+
+    # Setup a proxy
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "requests-time_between_check-minutes": 180,
+            "application-ignore_whitespace": "y",
+            "application-fetch_backend": "html_requests",
+            # set in .github/workflows/test-only.yml
+            "requests-extra_proxies-0-proxy_url": "socks5://proxy_user123:proxy_pass123@socks5proxy:1080",
+            "requests-extra_proxies-0-proxy_name": "socks5proxy",
+        },
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." in res.data
+
+    test_url = "https://changedetection.io/CHANGELOG.txt?socks-test-tag=" + os.getenv('SOCKSTEST', '')
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    res = client.get(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+    )
+    # check the proxy is offered as expected
+    assert b'ui-0socks5proxy' in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+        data={
+            "include_filters": "",
+            "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
+            "headers": "",
+            "proxy": "ui-0socks5proxy",
+            "tags": "",
+            "url": test_url,
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    # Should see the proper string
+    assert "+0200:".encode('utf-8') in res.data

changedetectionio/tests/proxy_socks5/test_socks5_proxy_sources.py

@@ -0,0 +1,52 @@
+#!/usr/bin/python3
+import os
+import time
+from flask import url_for
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
+
+
+# should be proxies.json mounted from run_proxy_tests.sh already
+# -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json
+def test_socks5_from_proxiesjson_file(client, live_server):
+    live_server_setup(live_server)
+
+    test_url = "https://changedetection.io/CHANGELOG.txt?socks-test-tag=" + os.getenv('SOCKSTEST', '')
+
+    res = client.get(url_for("settings_page"))
+    assert b'name="requests-proxy" type="radio" value="socks5proxy"' in res.data
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    res = client.get(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+    )
+    # check the proxy is offered as expected
+    assert b'name="proxy" type="radio" value="socks5proxy"' in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+        data={
+            "include_filters": "",
+            "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
+            "headers": "",
+            "proxy": "socks5proxy",
+            "tags": "",
+            "url": test_url,
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    # Should see the proper string
+    assert "+0200:".encode('utf-8') in res.data

changedetectionio/tests/restock/test_restock.py

@@ -77,7 +77,7 @@ def test_restock_detection(client, live_server):
 
     client.post(
         url_for("form_quick_watch_add"),
-        data={"url": test_url, "tag": '', 'processor': 'restock_diff'},
+        data={"url": test_url, "tags": '', 'processor': 'restock_diff'},
         follow_redirects=True
     )
 

changedetectionio/tests/smtp/smtp-test-server.py

@@ -0,0 +1,42 @@
+#!/usr/bin/python3
+import smtpd
+import asyncore
+
+# Accept a SMTP message and offer a way to retrieve the last message via TCP Socket
+
+last_received_message = b"Nothing"
+
+
+class CustomSMTPServer(smtpd.SMTPServer):
+
+    def process_message(self, peer, mailfrom, rcpttos, data, **kwargs):
+        global last_received_message
+        last_received_message = data
+        print('Receiving message from:', peer)
+        print('Message addressed from:', mailfrom)
+        print('Message addressed to  :', rcpttos)
+        print('Message length        :', len(data))
+        print(data.decode('utf8'))
+        return
+
+
+# Just print out the last message received on plain TCP socket server
+class EchoServer(asyncore.dispatcher):
+
+    def __init__(self, host, port):
+        asyncore.dispatcher.__init__(self)
+        self.create_socket()
+        self.set_reuse_addr()
+        self.bind((host, port))
+        self.listen(5)
+
+    def handle_accepted(self, sock, addr):
+        global last_received_message
+        print('Incoming connection from %s' % repr(addr))
+        sock.send(last_received_message)
+        last_received_message = b''
+
+
+server = CustomSMTPServer(('0.0.0.0', 11025), None)  # SMTP mail goes here
+server2 = EchoServer('0.0.0.0', 11080)  # Echo back last message received
+asyncore.loop()

changedetectionio/tests/smtp/test_notification_smtp.py

@@ -0,0 +1,165 @@
+import json
+import os
+import time
+import re
+from flask import url_for
+from changedetectionio.tests.util import set_original_response, set_modified_response, set_more_modified_response, live_server_setup, \
+    wait_for_all_checks, \
+    set_longer_modified_response
+from changedetectionio.tests.util import extract_UUID_from_client
+import logging
+import base64
+
+# NOTE - RELIES ON mailserver as hostname running, see github build recipes
+smtp_test_server = 'mailserver'
+
+from changedetectionio.notification import (
+    default_notification_body,
+    default_notification_format,
+    default_notification_title,
+    valid_notification_formats,
+)
+
+def test_setup(live_server):
+    live_server_setup(live_server)
+
+def get_last_message_from_smtp_server():
+    import socket
+    global smtp_test_server
+    port = 11080  # socket server port number
+
+    client_socket = socket.socket()  # instantiate
+    client_socket.connect((smtp_test_server, port))  # connect to the server
+
+    data = client_socket.recv(50024).decode()  # receive response
+    client_socket.close()  # close the connection
+    return data
+
+
+# Requires running the test SMTP server
+
+def test_check_notification_email_formats_default_HTML(client, live_server):
+    # live_server_setup(live_server)
+    set_original_response()
+
+    global smtp_test_server
+    notification_url = f'mailto://changedetection@{smtp_test_server}:11025/?to=fff@home.com'
+
+    #####################
+    # Set this up for when we remove the notification from the watch, it should fallback with these details
+    res = client.post(
+        url_for("settings_page"),
+        data={"application-notification_urls": notification_url,
+              "application-notification_title": "fallback-title " + default_notification_title,
+              "application-notification_body": "fallback-body<br> " + default_notification_body,
+              "application-notification_format": 'HTML',
+              "requests-time_between_check-minutes": 180,
+              'application-fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Settings updated." in res.data
+
+    # Add a watch and trigger a HTTP POST
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": 'nice one'},
+        follow_redirects=True
+    )
+
+    assert b"Watch added" in res.data
+
+    wait_for_all_checks(client)
+    set_longer_modified_response()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+
+    time.sleep(3)
+
+    msg = get_last_message_from_smtp_server()
+    assert len(msg) >= 1
+
+    # The email should have two bodies, and the text/html part should be <br>
+    assert 'Content-Type: text/plain' in msg
+    assert '(added) So let\'s see what happens.\n' in msg  # The plaintext part with \n
+    assert 'Content-Type: text/html' in msg
+    assert '(added) So let\'s see what happens.<br>' in msg  # the html part
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+
+def test_check_notification_email_formats_default_Text_override_HTML(client, live_server):
+    # live_server_setup(live_server)
+
+    # HTML problems? see this
+    # https://github.com/caronc/apprise/issues/633
+
+    set_original_response()
+    global smtp_test_server
+    notification_url = f'mailto://changedetection@{smtp_test_server}:11025/?to=fff@home.com'
+
+    #####################
+    # Set this up for when we remove the notification from the watch, it should fallback with these details
+    res = client.post(
+        url_for("settings_page"),
+        data={"application-notification_urls": notification_url,
+              "application-notification_title": "fallback-title " + default_notification_title,
+              "application-notification_body": default_notification_body,
+              "application-notification_format": 'Text',
+              "requests-time_between_check-minutes": 180,
+              'application-fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Settings updated." in res.data
+
+    # Add a watch and trigger a HTTP POST
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": 'nice one'},
+        follow_redirects=True
+    )
+
+    assert b"Watch added" in res.data
+
+    wait_for_all_checks(client)
+    set_longer_modified_response()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+
+    time.sleep(3)
+    msg = get_last_message_from_smtp_server()
+    assert len(msg) >= 1
+    #    with open('/tmp/m.txt', 'w') as f:
+    #        f.write(msg)
+
+    # The email should not have two bodies, should be TEXT only
+
+    assert 'Content-Type: text/plain' in msg
+    assert '(added) So let\'s see what happens.\n' in msg  # The plaintext part with \n
+
+    set_original_response()
+    # Now override as HTML format
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={
+            "url": test_url,
+            "notification_format": 'HTML',
+            'fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    wait_for_all_checks(client)
+
+    time.sleep(3)
+    msg = get_last_message_from_smtp_server()
+    assert len(msg) >= 1
+
+    # The email should have two bodies, and the text/html part should be <br>
+    assert 'Content-Type: text/plain' in msg
+    assert '(removed) So let\'s see what happens.\n' in msg  # The plaintext part with \n
+    assert 'Content-Type: text/html' in msg
+    assert '(removed) So let\'s see what happens.<br>' in msg  # the html part
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_access_control.py

@@ -1,4 +1,4 @@
-from . util import live_server_setup, extract_UUID_from_client
+from .util import live_server_setup, extract_UUID_from_client, wait_for_all_checks
 from flask import url_for
 import time
 
@@ -19,10 +19,16 @@ def test_check_access_control(app, client, live_server):
         )
 
         assert b"1 Imported" in res.data
-        time.sleep(2)
-        res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+        time.sleep(3)
+        # causes a 'Popped wrong request context.' error when client. is accessed?
+        #wait_for_all_checks(client)
+
+        res = c.get(url_for("form_watch_checknow"), follow_redirects=True)
         assert b'1 watches queued for rechecking.' in res.data
-        time.sleep(2)
+        time.sleep(3)
+        # causes a 'Popped wrong request context.' error when client. is accessed?
+        #wait_for_all_checks(client)
+
 
         # Enable password check and diff page access bypass
         res = c.post(
@@ -42,9 +48,18 @@ def test_check_access_control(app, client, live_server):
         assert b"Login" in res.data
 
         # The diff page should return something valid when logged out
-        res = client.get(url_for("diff_history_page", uuid="first"))
+        res = c.get(url_for("diff_history_page", uuid="first"))
         assert b'Random content' in res.data
 
+        # Check wrong password does not let us in
+        res = c.post(
+            url_for("login"),
+            data={"password": "WRONG PASSWORD"},
+            follow_redirects=True
+        )
+
+        assert b"LOG OUT" not in res.data
+        assert b"Incorrect password" in res.data
 
 
         # Menu should not be available yet
@@ -74,6 +89,8 @@ def test_check_access_control(app, client, live_server):
         res = c.get(url_for("logout"),
             follow_redirects=True)
 
+        assert b"Login" in res.data
+
         res = c.get(url_for("settings_page"),
             follow_redirects=True)
 
@@ -151,5 +168,5 @@ def test_check_access_control(app, client, live_server):
         assert b"Login" in res.data
 
         # The diff page should return something valid when logged out
-        res = client.get(url_for("diff_history_page", uuid="first"))
+        res = c.get(url_for("diff_history_page", uuid="first"))
         assert b'Random content' not in res.data

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -2,7 +2,7 @@
 
 import time
 from flask import url_for
-from .util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
 from changedetectionio import html_tools
 
 
@@ -39,7 +39,6 @@ def test_setup(client, live_server):
     live_server_setup(live_server)
 
 def test_check_removed_line_contains_trigger(client, live_server):
-    sleep_time_for_fetch_thread = 3
 
     # Give the endpoint time to spin up
     time.sleep(1)
@@ -54,7 +53,7 @@ def test_check_removed_line_contains_trigger(client, live_server):
     assert b"1 Imported" in res.data
 
     # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # Goto the edit page, add our ignore text
     # Add our URL to the import page
@@ -67,20 +66,20 @@ def test_check_removed_line_contains_trigger(client, live_server):
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
     set_original(excluding='Something irrelevant')
 
     # A line thats not the trigger should not trigger anything
     res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
     assert b'1 watches queued for rechecking.' in res.data
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
 
     # The trigger line is REMOVED,  this should trigger
     set_original(excluding='The golden line')
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
@@ -89,14 +88,14 @@ def test_check_removed_line_contains_trigger(client, live_server):
     client.get(url_for("mark_all_viewed"), follow_redirects=True)
     set_original(excluding=None)
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
 
     # Remove it again, and we should get a trigger
     set_original(excluding='The golden line')
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
@@ -105,8 +104,7 @@ def test_check_removed_line_contains_trigger(client, live_server):
 
 
 def test_check_add_line_contains_trigger(client, live_server):
-
-    sleep_time_for_fetch_thread = 3
+    #live_server_setup(live_server)
 
     # Give the endpoint time to spin up
     time.sleep(1)
@@ -136,8 +134,7 @@ def test_check_add_line_contains_trigger(client, live_server):
     assert b"1 Imported" in res.data
 
     # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
+    wait_for_all_checks(client)
     # Goto the edit page, add our ignore text
     # Add our URL to the import page
     res = client.post(
@@ -150,23 +147,25 @@ def test_check_add_line_contains_trigger(client, live_server):
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
     set_original(excluding='Something irrelevant')
 
     # A line thats not the trigger should not trigger anything
     res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
     assert b'1 watches queued for rechecking.' in res.data
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
 
     # The trigger line is ADDED,  this should trigger
     set_original(add_line='<p>Oh yes please</p>')
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
+    # Takes a moment for apprise to fire
+    time.sleep(3)
     with open("test-datastore/notification.txt", 'r') as f:
         response= f.read()
         assert '-Oh yes please-' in response

changedetectionio/tests/test_api.py

@@ -2,7 +2,7 @@
 
 import time
 from flask import url_for
-from .util import live_server_setup, extract_api_key_from_UI
+from .util import live_server_setup, extract_api_key_from_UI, wait_for_all_checks
 
 import json
 import uuid
@@ -57,6 +57,7 @@ def test_setup(client, live_server):
     live_server_setup(live_server)
 
 def test_api_simple(client, live_server):
+    #live_server_setup(live_server)
 
     api_key = extract_api_key_from_UI(client)
 
@@ -86,7 +87,7 @@ def test_api_simple(client, live_server):
     watch_uuid = res.json.get('uuid')
     assert res.status_code == 201
 
-    time.sleep(3)
+    wait_for_all_checks(client)
 
     # Verify its in the list and that recheck worked
     res = client.get(
@@ -107,7 +108,7 @@ def test_api_simple(client, live_server):
     )
     assert len(res.json) == 0
 
-    time.sleep(2)
+    wait_for_all_checks(client)
 
     set_modified_response()
     # Trigger recheck of all ?recheck_all=1
@@ -115,7 +116,7 @@ def test_api_simple(client, live_server):
         url_for("createwatch", recheck_all='1'),
         headers={'x-api-key': api_key},
     )
-    time.sleep(3)
+    wait_for_all_checks(client)
 
     # Did the recheck fire?
     res = client.get(
@@ -266,7 +267,7 @@ def test_api_watch_PUT_update(client, live_server):
 
     #live_server_setup(live_server)
     api_key = extract_api_key_from_UI(client)
-    time.sleep(1)
+
     # Create a watch
     set_original_response()
     test_url = url_for('test_endpoint', _external=True,
@@ -282,7 +283,6 @@ def test_api_watch_PUT_update(client, live_server):
 
     assert res.status_code == 201
 
-    time.sleep(1)
 
     # Get a listing, it will be the first one
     res = client.get(
@@ -297,6 +297,8 @@ def test_api_watch_PUT_update(client, live_server):
         url_for("edit_page", uuid=watch_uuid),
     )
     assert b"cookie: yum" in res.data, "'cookie: yum' found in 'headers' section"
+    assert b"One" in res.data, "Tag 'One' was found"
+    assert b"Two" in res.data, "Tag 'Two' was found"
 
     # HTTP PUT ( UPDATE an existing watch )
     res = client.put(
@@ -319,7 +321,8 @@ def test_api_watch_PUT_update(client, live_server):
     )
     assert b"new title" in res.data, "new title found in edit page"
     assert b"552" in res.data, "552 minutes found in edit page"
-    assert b"One, Two" in res.data, "Tag 'One, Two' was found"
+    assert b"One" in res.data, "Tag 'One' was found"
+    assert b"Two" in res.data, "Tag 'Two' was found"
     assert b"cookie: all eaten" in res.data, "'cookie: all eaten' found in 'headers' section"
 
     ######################################################

changedetectionio/tests/test_auth.py

@@ -24,7 +24,7 @@ def test_basic_auth(client, live_server):
     # Check form validation
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": "", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"include_filters": "", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data