woops

.dockerignore

@@ -29,3 +29,34 @@ venv/
 
 # Visual Studio
 .vscode/
+
+# Test and development files
+test-datastore/
+tests/
+*.md
+!README.md
+
+# Temporary and log files
+*.log
+*.tmp
+tmp/
+temp/
+
+# Training data and large files
+train-data/
+works-data/
+
+# Container files
+Dockerfile*
+docker-compose*.yml
+.dockerignore
+
+# Development certificates and keys
+*.pem
+*.key
+*.crt
+profile_output.prof
+
+# Large binary files that shouldn't be in container
+*.pdf
+chrome.json

.github/dependabot.yml

@@ -4,11 +4,13 @@ updates:
     directory: /
     schedule:
       interval: "weekly"
-    "caronc/apprise":
-      versioning-strategy: "increase"
-      schedule:
-        interval: "daily"
     groups:
       all:
         patterns:
         - "*"
+  - package-ecosystem: pip
+    directory: /
+    schedule:
+      interval: "daily"
+    allow:
+      - dependency-name: "apprise"

.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:3.21
+FROM ghcr.io/linuxserver/baseimage-alpine:3.22
 ENV PYTHONUNBUFFERED=1
 
 COPY requirements.txt /requirements.txt
@@ -18,17 +18,19 @@ RUN \
     libxslt-dev \
     openssl-dev \
     python3-dev \
+    file \
     zip \
     zlib-dev && \
   apk add --update --no-cache \
     libjpeg \
     libxslt \
+    file \
     nodejs \
     poppler-utils \
     python3 && \
   echo "**** pip3 install test of changedetection.io ****" && \
   python3 -m venv /lsiopy  && \
   pip install -U pip wheel setuptools && \
-  pip install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.21/ -r /requirements.txt && \
+  pip install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.22/ -r /requirements.txt && \
   apk del --purge \
     build-dependencies

.github/workflows/codeql-analysis.yml

@@ -30,7 +30,7 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@v5
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL

.github/workflows/containers.yml

@@ -39,9 +39,9 @@ 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@v4
+      - uses: actions/checkout@v5
       - name: Set up Python 3.11
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: 3.11
 
@@ -95,7 +95,7 @@ jobs:
           push: true
           tags: |
             ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
-          platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/v8
+          platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8
           cache-from: type=gha
           cache-to: type=gha,mode=max
 
@@ -103,6 +103,13 @@ jobs:
 #          provenance: false
 
       # A new tagged release is required, which builds :tag and :latest
+      - name: Debug release info
+        if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
+        run: |
+          echo "Release tag: ${{ github.event.release.tag_name }}"
+          echo "Github ref: ${{ github.ref }}"
+          echo "Github ref name: ${{ github.ref_name }}"
+          
       - name: Docker meta :tag
         if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
         uses: docker/metadata-action@v5
@@ -112,9 +119,10 @@ jobs:
                 ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io
                 ghcr.io/dgtlmoon/changedetection.io
             tags: |
-                type=semver,pattern={{version}}
-                type=semver,pattern={{major}}.{{minor}}
-                type=semver,pattern={{major}}
+                type=semver,pattern={{version}},value=${{ github.event.release.tag_name }}
+                type=semver,pattern={{major}}.{{minor}},value=${{ github.event.release.tag_name }}
+                type=semver,pattern={{major}},value=${{ github.event.release.tag_name }}
+                type=raw,value=latest
 
       - name: Build and push :tag
         id: docker_build_tag_release
@@ -125,7 +133,7 @@ jobs:
           file: ./Dockerfile
           push: true
           tags: ${{ steps.meta.outputs.tags }}
-          platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/v8
+          platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8
           cache-from: type=gha
           cache-to: type=gha,mode=max
 # Looks like this was disabled

.github/workflows/pypi-release.yml

@@ -7,9 +7,9 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v5
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v6
       with:
         python-version: "3.11"
     - name: Install pypa/build
@@ -34,12 +34,12 @@ jobs:
     - build
     steps:
     - name: Download all the dists
-      uses: actions/download-artifact@v4
+      uses: actions/download-artifact@v5
       with:
         name: python-package-distributions
         path: dist/
     - name: Set up Python 3.11
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v6
       with:
         python-version: '3.11'
     - name: Test that the basic pip built package runs without error
@@ -72,7 +72,7 @@ jobs:
 
     steps:
     - name: Download all the dists
-      uses: actions/download-artifact@v4
+      uses: actions/download-artifact@v5
       with:
         name: python-package-distributions
         path: dist/

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

@@ -23,12 +23,30 @@ on:
   # Changes to requirements.txt packages and Dockerfile may or may not always be compatible with arm etc, so worth testing
   # @todo: some kind of path filter for requirements.txt and Dockerfile
 jobs:
-  test-container-build:
+  builder:
+    name: Build ${{ matrix.platform }} (${{ matrix.dockerfile == './Dockerfile' && 'main' || 'alpine' }})
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          # Main Dockerfile platforms
+          - platform: linux/amd64
+            dockerfile: ./Dockerfile
+          - platform: linux/arm64
+            dockerfile: ./Dockerfile
+          - platform: linux/arm/v7
+            dockerfile: ./Dockerfile
+          - platform: linux/arm/v8
+            dockerfile: ./Dockerfile
+          # Alpine Dockerfile platforms (musl via alpine check)
+          - platform: linux/amd64
+            dockerfile: ./.github/test/Dockerfile-alpine
+          - platform: linux/arm64
+            dockerfile: ./.github/test/Dockerfile-alpine
     steps:
-        - uses: actions/checkout@v4
+        - uses: actions/checkout@v5
         - name: Set up Python 3.11
-          uses: actions/setup-python@v5
+          uses: actions/setup-python@v6
           with:
             python-version: 3.11
 
@@ -47,24 +65,14 @@ jobs:
             version: latest
             driver-opts: image=moby/buildkit:master
 
-        # https://github.com/dgtlmoon/changedetection.io/pull/1067
-        # Check we can still build under alpine/musl
-        - name: Test that the docker containers can build (musl via alpine check)
-          id: docker_build_musl
-          uses: docker/build-push-action@v6
-          with:
-            context: ./
-            file: ./.github/test/Dockerfile-alpine
-            platforms: linux/amd64,linux/arm64
-
-        - name: Test that the docker containers can build
+        - name: Test that the docker containers can build (${{ matrix.platform }} - ${{ matrix.dockerfile }})
           id: docker_build
           uses: docker/build-push-action@v6
           # https://github.com/docker/build-push-action#customizing
           with:
             context: ./
-            file: ./Dockerfile
-            platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/v8
-            cache-from: type=local,src=/tmp/.buildx-cache
-            cache-to: type=local,dest=/tmp/.buildx-cache
+            file: ${{ matrix.dockerfile }}
+            platforms: ${{ matrix.platform }}
+            cache-from: type=gha
+            cache-to: type=gha,mode=min
 

.github/workflows/test-only.yml

@@ -7,7 +7,7 @@ jobs:
   lint-code:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Lint with Ruff
         run: |
           pip install ruff
@@ -15,6 +15,10 @@ jobs:
           ruff check . --select E9,F63,F7,F82
           # Complete check with errors treated as warnings
           ruff check . --exit-zero
+      - name: Validate OpenAPI spec
+        run: |
+          pip install openapi-spec-validator
+          python3 -c "from openapi_spec_validator import validate_spec; import yaml; validate_spec(yaml.safe_load(open('docs/api-spec.yaml')))"
 
   test-application-3-10:
     needs: lint-code

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

@@ -20,11 +20,11 @@ jobs:
     env:
       PYTHON_VERSION: ${{ inputs.python-version }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       # Mainly just for link/flake8
       - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 
@@ -86,10 +86,10 @@ jobs:
         run: |
           # Playwright via Sockpuppetbrowser fetch
           # tests/visualselector/test_fetch_data.py will do browser steps  
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest  -vv --capture=tee-sys --showlocals --tb=long --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest  -vv --capture=tee-sys --showlocals --tb=long --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest  -vv --capture=tee-sys --showlocals --tb=long --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest  -vv --capture=tee-sys --showlocals --tb=long --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
 
 
       - name: Playwright and SocketPuppetBrowser - Headers and requests
@@ -179,6 +179,26 @@ jobs:
 
           docker kill test-changedetectionio
 
+      - name: Test HTTPS SSL mode
+        run: |
+          openssl req -x509 -newkey rsa:4096 -keyout privkey.pem -out cert.pem -days 365 -nodes -subj "/CN=localhost"
+          docker run --name test-changedetectionio-ssl --rm -e SSL_CERT_FILE=cert.pem -e SSL_PRIVKEY_FILE=privkey.pem -p 5000:5000 -v ./cert.pem:/app/cert.pem -v ./privkey.pem:/app/privkey.pem -d test-changedetectionio
+          sleep 3
+          # Should return 0 (no error) when grep finds it
+          # -k because its self-signed
+          curl --retry-connrefused --retry 6 -k https://localhost:5000 -v|grep -q checkbox-uuid
+      
+          docker kill test-changedetectionio-ssl
+
+      - name: Test IPv6 Mode
+        run: |
+          # IPv6 - :: bind to all interfaces inside container (like 0.0.0.0), ::1 would be localhost only
+          docker run --name test-changedetectionio-ipv6 --rm -p 5000:5000 -e LISTEN_HOST=:: -d test-changedetectionio
+          sleep 3
+          # Should return 0 (no error) when grep finds it on localhost
+          curl --retry-connrefused --retry 6 http://[::1]:5000 -v|grep -q checkbox-uuid
+          docker kill test-changedetectionio-ipv6
+
       - name: Test changedetection.io SIGTERM and SIGINT signal shutdown
         run: |
           

Dockerfile

@@ -5,7 +5,6 @@ ARG PYTHON_VERSION=3.11
 FROM python:${PYTHON_VERSION}-slim-bookworm AS builder
 
 # See `cryptography` pin comment in requirements.txt
-ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     g++ \
@@ -16,6 +15,8 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     libssl-dev \
     libxslt-dev \
     make \
+    patch \
+    pkg-config \
     zlib1g-dev
 
 RUN mkdir /install
@@ -23,13 +24,32 @@ WORKDIR /install
 
 COPY requirements.txt /requirements.txt
 
-# --extra-index-url https://www.piwheels.org/simple  is for cryptography module to be prebuilt (or rustc etc needs to be installed)
-RUN pip install --extra-index-url https://www.piwheels.org/simple  --target=/dependencies -r /requirements.txt
+# Use cache mounts and multiple wheel sources for faster ARM builds
+ENV PIP_CACHE_DIR=/tmp/pip-cache
+# Help Rust find OpenSSL for cryptography package compilation on ARM
+ENV PKG_CONFIG_PATH="/usr/lib/pkgconfig:/usr/lib/arm-linux-gnueabihf/pkgconfig:/usr/lib/aarch64-linux-gnu/pkgconfig"
+ENV PKG_CONFIG_ALLOW_SYSTEM_CFLAGS=1
+ENV OPENSSL_DIR="/usr"
+ENV OPENSSL_LIB_DIR="/usr/lib/arm-linux-gnueabihf"
+ENV OPENSSL_INCLUDE_DIR="/usr/include/openssl"
+# Additional environment variables for cryptography Rust build
+ENV CRYPTOGRAPHY_DONT_BUILD_RUST=1
+RUN --mount=type=cache,target=/tmp/pip-cache \
+    pip install \
+    --extra-index-url https://www.piwheels.org/simple \
+    --extra-index-url https://pypi.anaconda.org/ARM-software/simple \
+    --cache-dir=/tmp/pip-cache \
+    --target=/dependencies \
+    -r /requirements.txt
 
 # Playwright is an alternative to Selenium
 # Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
 # https://github.com/dgtlmoon/changedetection.io/pull/1067 also musl/alpine (not supported)
-RUN pip install --target=/dependencies playwright~=1.48.0 \
+RUN --mount=type=cache,target=/tmp/pip-cache \
+    pip install \
+    --cache-dir=/tmp/pip-cache \
+    --target=/dependencies \
+    playwright~=1.48.0 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
@@ -42,6 +62,8 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     locales \
     # For pdftohtml
     poppler-utils \
+    # favicon type detection and other uses
+    file \
     zlib1g \
     && apt-get clean && rm -rf /var/lib/apt/lists/*
 
@@ -62,6 +84,11 @@ EXPOSE 5000
 
 # The actual flask app module
 COPY changedetectionio /app/changedetectionio
+
+# Also for OpenAPI validation wrapper - needs the YML
+RUN [ ! -d "/app/docs" ] && mkdir /app/docs
+COPY docs/api-spec.yaml /app/docs/api-spec.yaml
+
 # Starting wrapper
 COPY changedetection.py /app/changedetection.py
 
@@ -70,6 +97,9 @@ COPY changedetection.py /app/changedetection.py
 ARG LOGGER_LEVEL=''
 ENV LOGGER_LEVEL="$LOGGER_LEVEL"
 
+# Default
+ENV LC_ALL=en_US.UTF-8
+
 WORKDIR /app
 CMD ["python", "./changedetection.py", "-d", "/datastore"]
 

LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright [yyyy] [name of copyright owner]
+   Copyright 2025 Web Technologies s.r.o.
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

MANIFEST.in

@@ -1,7 +1,7 @@
 recursive-include changedetectionio/api *
 recursive-include changedetectionio/blueprint *
-recursive-include changedetectionio/content_fetchers *
 recursive-include changedetectionio/conditions *
+recursive-include changedetectionio/content_fetchers *
 recursive-include changedetectionio/model *
 recursive-include changedetectionio/notification *
 recursive-include changedetectionio/processors *
@@ -9,6 +9,7 @@ recursive-include changedetectionio/realtime *
 recursive-include changedetectionio/static *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/tests *
+recursive-include changedetectionio/widgets *
 prune changedetectionio/static/package-lock.json
 prune changedetectionio/static/styles/node_modules
 prune changedetectionio/static/styles/package-lock.json

README-pip.md

@@ -1,11 +1,21 @@
-## Web Site Change Detection, Monitoring and Notification.
+# Monitor website changes
 
-Live your data-life pro-actively, track website content changes and receive notifications via Discord, Email, Slack, Telegram and 70+ more
+Detect WebPage Changes Automatically — Monitor Web Page Changes in Real Time
+
+Monitor websites for updates — get notified via Discord, Email, Slack, Telegram, Webhook and many more.
+
+Detect web page content changes and get instant alerts.
+
+
+[Changedetection.io is the best tool to monitor web-pages for changes](https://changedetection.io) Track website content changes and receive notifications via Discord, Email, Slack, Telegram and 90+ more
+
+Ideal for monitoring price changes, content edits, conditional changes and more.
 
 [<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring, list of websites with changes"  title="Self-hosted web page change monitoring, list of websites with changes"  />](https://changedetection.io)
 
 
-[**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://changedetection.io) 
+[**Don't have time? Try our extremely affordable subscription use our proxies and support!**](https://changedetection.io) 
+
 
 
 ### Target specific parts of the webpage using the Visual Selector tool.

README.md

@@ -1,11 +1,13 @@
-## Web Site Change Detection, Restock monitoring and notifications.
+# Detect Website Changes Automatically — Monitor Web Page Changes in Real Time
 
-**_Detect website content changes and perform meaningful actions - trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._**
+Monitor websites for updates — get notified via Discord, Email, Slack, Telegram, Webhook and many more.
 
-_Live your data-life pro-actively._ 
+**Detect web page content changes and get instant alerts.**  
+
+Ideal for monitoring price changes, content edits, conditional changes and more.
 
 
-[<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)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Web site page change monitoring"  title="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)
 
@@ -13,6 +15,7 @@ _Live your data-life pro-actively._
 
 [**Get started with website page change monitoring straight away. Don't have time? Try our $8.99/month subscription, use our proxies and support!**](https://changedetection.io) , _half the price of other website change monitoring services!_
 
+
 - Chrome browser included.
 - Nothing to install, access via browser login after signup.
 - Super fast, no registration needed setup.
@@ -99,9 +102,7 @@ _Need an actual Chrome runner with Javascript support? We support fetching via W
 - 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. 
+We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) global proxy services, Bright Data will match any first deposit up to $150 using our signup link.
 
 Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
 
@@ -279,7 +280,10 @@ Excel import is recommended - that way you can better organise tags/groups of we
 
 ## API Support
 
-Supports managing the website watch list [via our API](https://changedetection.io/docs/api_v1/index.html)
+Full REST API for programmatic management of watches, tags, notifications and more. 
+
+- **[Interactive API Documentation](https://changedetection.io/docs/api_v1/index.html)** - Complete API reference with live testing
+- **[OpenAPI Specification](docs/api-spec.yaml)** - Generate SDKs for any programming language
 
 ## Support us
 

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.49.18'
+__version__ = '0.50.16'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError
@@ -10,10 +10,11 @@ import os
 import getopt
 import platform
 import signal
-import socket
-import sys
-from werkzeug.serving import run_simple
 
+import sys
+
+# Eventlet completely removed - using threading mode for SocketIO
+# This provides better Python 3.12+ compatibility and eliminates eventlet/asyncio conflicts
 from changedetectionio import store
 from changedetectionio.flask_app import changedetection_app
 from loguru import logger
@@ -28,22 +29,43 @@ def get_version():
 # Parent wrapper or OS sends us a SIGTERM/SIGINT, do everything required for a clean shutdown
 def sigshutdown_handler(_signo, _stack_frame):
     name = signal.Signals(_signo).name
-    logger.critical(f'Shutdown: Got Signal - {name} ({_signo}), Saving DB to disk and calling shutdown')
-    datastore.sync_to_json()
-    logger.success('Sync JSON to disk complete.')
+    logger.critical(f'Shutdown: Got Signal - {name} ({_signo}), Fast shutdown initiated')
     
-    # Shutdown socketio server if available
+    # Set exit flag immediately to stop all loops
+    app.config.exit.set()
+    datastore.stop_thread = True
+    
+    # Shutdown workers and queues immediately
+    try:
+        from changedetectionio import worker_handler
+        worker_handler.shutdown_workers()
+    except Exception as e:
+        logger.error(f"Error shutting down workers: {str(e)}")
+    
+    # Close janus queues properly
+    try:
+        from changedetectionio.flask_app import update_q, notification_q
+        update_q.close()
+        notification_q.close()
+        logger.debug("Janus queues closed successfully")
+    except Exception as e:
+        logger.critical(f"CRITICAL: Failed to close janus queues: {e}")
+    
+    # Shutdown socketio server fast
     from changedetectionio.flask_app import socketio_server
     if socketio_server and hasattr(socketio_server, 'shutdown'):
         try:
-            logger.info("Shutting down Socket.IO server...")
             socketio_server.shutdown()
         except Exception as e:
             logger.error(f"Error shutting down Socket.IO server: {str(e)}")
     
-    # Set flags for clean shutdown
-    datastore.stop_thread = True
-    app.config.exit.set()
+    # Save data quickly
+    try:
+        datastore.sync_to_json()
+        logger.success('Fast sync to disk complete.')
+    except Exception as e:
+        logger.error(f"Error syncing to disk: {str(e)}")
+    
     sys.exit()
 
 def main():
@@ -52,9 +74,8 @@ def main():
 
     datastore_path = None
     do_cleanup = False
-    host = ''
-    ipv6_enabled = False
-    port = os.environ.get('PORT') or 5000
+    host = os.environ.get("LISTEN_HOST", "0.0.0.0").strip()
+    port = int(os.environ.get('PORT', 5000))
     ssl_mode = False
 
     # On Windows, create and use a default path.
@@ -95,10 +116,6 @@ def main():
         if opt == '-d':
             datastore_path = arg
 
-        if opt == '-6':
-            logger.success("Enabling IPv6 listen support")
-            ipv6_enabled = True
-
         # Cleanup (remove text files that arent in the index)
         if opt == '-c':
             do_cleanup = True
@@ -110,6 +127,20 @@ def main():
         if opt == '-l':
             logger_level = int(arg) if arg.isdigit() else arg.upper()
 
+
+    logger.success(f"changedetection.io version {get_version()} starting.")
+    # Launch using SocketIO run method for proper integration (if enabled)
+    ssl_cert_file = os.getenv("SSL_CERT_FILE", 'cert.pem')
+    ssl_privkey_file = os.getenv("SSL_PRIVKEY_FILE", 'privkey.pem')
+    if os.getenv("SSL_CERT_FILE") and os.getenv("SSL_PRIVKEY_FILE"):
+        ssl_mode = True
+
+    # SSL mode could have been set by -s too, therefor fallback to default values
+    if ssl_mode:
+        if not os.path.isfile(ssl_cert_file) or not os.path.isfile(ssl_privkey_file):
+            logger.critical(f"Cannot start SSL/HTTPS mode, Please be sure that {ssl_cert_file}' and '{ssl_privkey_file}' exist in in {os.getcwd()}")
+            os._exit(2)
+
     # Without this, a logger will be duplicated
     logger.remove()
     try:
@@ -150,6 +181,11 @@ def main():
 
     app = changedetection_app(app_config, datastore)
 
+    # Get the SocketIO instance from the Flask app (created in flask_app.py)
+    from changedetectionio.flask_app import socketio_server
+    global socketio
+    socketio = socketio_server
+
     signal.signal(signal.SIGTERM, sigshutdown_handler)
     signal.signal(signal.SIGINT, sigshutdown_handler)
     
@@ -174,10 +210,11 @@ def main():
 
 
     @app.context_processor
-    def inject_version():
+    def inject_template_globals():
         return dict(right_sticky="v{}".format(datastore.data['version_tag']),
                     new_version_available=app.config['NEW_VERSION_AVAILABLE'],
-                    has_password=datastore.data['settings']['application']['password'] != False
+                    has_password=datastore.data['settings']['application']['password'] != False,
+                    socket_io_enabled=datastore.data['settings']['application']['ui'].get('socket_io_enabled', True)
                     )
 
     # Monitored websites will not receive a Referer header when a user clicks on an outgoing link.
@@ -201,87 +238,21 @@ def main():
         from werkzeug.middleware.proxy_fix import ProxyFix
         app.wsgi_app = ProxyFix(app.wsgi_app, x_prefix=1, x_host=1)
 
-    s_type = socket.AF_INET6 if ipv6_enabled else socket.AF_INET
 
-    # Get socketio_server from flask_app
-    from changedetectionio.flask_app import socketio_server
-
-    if socketio_server and datastore.data['settings']['application']['ui'].get('open_diff_in_new_tab'):
-        logger.info("Starting server with Socket.IO support (using threading)...")
-
-        # Use Flask-SocketIO's run method with error handling for Werkzeug warning
-        # This is the cleanest approach that works with all Flask-SocketIO versions
-        # Use '0.0.0.0' as the default host if none is specified
-        # This will listen on all available interfaces
-        listen_host = '0.0.0.0' if host == '' else host
-        logger.info(f"Using host: {listen_host} and port: {port}")
-
-        try:
-            # First try with the allow_unsafe_werkzeug parameter (newer versions)
-            if ssl_mode:
-                socketio_server.run(
-                    app,
-                    host=listen_host,
-                    port=int(port),
-                    certfile='cert.pem',
-                    keyfile='privkey.pem',
-                    debug=False,
-                    use_reloader=False,
-                    allow_unsafe_werkzeug=True  # Only in newer versions
-                )
-            else:
-                socketio_server.run(
-                    app,
-                    host=listen_host,
-                    port=int(port),
-                    debug=False,
-                    use_reloader=False,
-                    allow_unsafe_werkzeug=True  # Only in newer versions
-                )
-        except TypeError:
-            # If allow_unsafe_werkzeug is not a valid parameter, try without it
-            logger.info("Falling back to basic run method without allow_unsafe_werkzeug")
-            # Override the werkzeug safety check by setting an environment variable
-            os.environ['WERKZEUG_RUN_MAIN'] = 'true'
-            if ssl_mode:
-                socketio_server.run(
-                    app,
-                    host=listen_host,
-                    port=int(port),
-                    certfile='cert.pem',
-                    keyfile='privkey.pem',
-                    debug=False,
-                    use_reloader=False
-                )
-            else:
-                socketio_server.run(
-                    app,
-                    host=listen_host,
-                    port=int(port),
-                    debug=False,
-                    use_reloader=False
-                )
-    else:
-        logger.warning("Socket.IO server not initialized, falling back to standard WSGI server")
-        # Fallback to standard WSGI server if socketio_server is not available
-        listen_host = '0.0.0.0' if host == '' else host
+    # SocketIO instance is already initialized in flask_app.py
+    if socketio_server:
         if ssl_mode:
-            # Use Werkzeug's run_simple with SSL support
-            run_simple(
-                hostname=listen_host,
-                port=int(port),
-                application=app,
-                use_reloader=False,
-                use_debugger=False,
-                ssl_context=('cert.pem', 'privkey.pem')
-            )
+            logger.success(f"SSL mode enabled, attempting to start with '{ssl_cert_file}' and '{ssl_privkey_file}' in {os.getcwd()}")
+            socketio.run(app, host=host, port=int(port), debug=False,
+                         ssl_context=(ssl_cert_file, ssl_privkey_file), allow_unsafe_werkzeug=True)
         else:
-            # Use Werkzeug's run_simple for standard HTTP
-            run_simple(
-                hostname=listen_host,
-                port=int(port),
-                application=app,
-                use_reloader=False,
-                use_debugger=False
-            )
-
+            socketio.run(app, host=host, port=int(port), debug=False, allow_unsafe_werkzeug=True)
+    else:
+        # Run Flask app without Socket.IO if disabled
+        logger.info("Starting Flask app without Socket.IO server")
+        if ssl_mode:
+            logger.success(f"SSL mode enabled, attempting to start with '{ssl_cert_file}' and '{ssl_privkey_file}' in {os.getcwd()}")
+            app.run(host=host, port=int(port), debug=False,
+                    ssl_context=(ssl_cert_file, ssl_privkey_file))
+        else:
+            app.run(host=host, port=int(port), debug=False)

changedetectionio/api/Import.py

@@ -3,7 +3,7 @@ from changedetectionio.strtobool import strtobool
 from flask_restful import abort, Resource
 from flask import request
 import validators
-from . import auth
+from . import auth, validate_openapi_request
 
 
 class Import(Resource):
@@ -12,17 +12,9 @@ class Import(Resource):
         self.datastore = kwargs['datastore']
 
     @auth.check_token
+    @validate_openapi_request('importWatches')
     def post(self):
-        """
-        @api {post} /api/v1/import Import a list of watched URLs
-        @apiDescription Accepts a line-feed separated list of URLs to import, additionally with ?tag_uuids=(tag  id), ?tag=(name), ?proxy={key}, ?dedupe=true (default true) one URL per line.
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/import --data-binary @list-of-sites.txt -H"x-api-key:8a111a21bc2f8f1dd9b9353bbd46049a"
-        @apiName Import
-        @apiGroup Watch
-        @apiSuccess (200) {List} OK List of watch UUIDs added
-        @apiSuccess (500) {String} ERR Some other error
-        """
+        """Import a list of watched URLs."""
 
         extras = {}
 

changedetectionio/api/Notifications.py

@@ -1,9 +1,7 @@
 from flask_expects_json import expects_json
-from flask_restful import Resource
-from . import auth
-from flask_restful import abort, Resource
+from flask_restful import Resource, abort
 from flask import request
-from . import auth
+from . import auth, validate_openapi_request
 from . import schema_create_notification_urls, schema_delete_notification_urls
 
 class Notifications(Resource):
@@ -12,19 +10,9 @@ class Notifications(Resource):
         self.datastore = kwargs['datastore']
 
     @auth.check_token
+    @validate_openapi_request('getNotifications')
     def get(self):
-        """
-        @api {get} /api/v1/notifications Return Notification URL List
-        @apiDescription Return the Notification URL List from the configuration
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/notifications -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            HTTP/1.0 200
-            {
-                'notification_urls': ["notification-urls-list"]
-            }
-        @apiName Get
-        @apiGroup Notifications
-        """
+        """Return Notification URL List."""
 
         notification_urls = self.datastore.data.get('settings', {}).get('application', {}).get('notification_urls', [])        
 
@@ -33,18 +21,10 @@ class Notifications(Resource):
                }, 200
     
     @auth.check_token
+    @validate_openapi_request('addNotifications')
     @expects_json(schema_create_notification_urls)
     def post(self):
-        """
-        @api {post} /api/v1/notifications Create Notification URLs
-        @apiDescription Add one or more notification URLs from the configuration
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/notifications/batch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"notification_urls": ["url1", "url2"]}'
-        @apiName CreateBatch
-        @apiGroup Notifications
-        @apiSuccess (201) {Object[]} notification_urls List of added notification URLs
-        @apiError (400) {String} Invalid input
-        """
+        """Create Notification URLs."""
 
         json_data = request.get_json()
         notification_urls = json_data.get("notification_urls", [])
@@ -69,18 +49,10 @@ class Notifications(Resource):
         return {'notification_urls': added_urls}, 201
     
     @auth.check_token
+    @validate_openapi_request('replaceNotifications')
     @expects_json(schema_create_notification_urls)
     def put(self):
-        """
-        @api {put} /api/v1/notifications Replace Notification URLs
-        @apiDescription Replace all notification URLs with the provided list (can be empty)
-        @apiExample {curl} Example usage:
-            curl -X PUT http://localhost:5000/api/v1/notifications -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"notification_urls": ["url1", "url2"]}'
-        @apiName Replace
-        @apiGroup Notifications
-        @apiSuccess (200) {Object[]} notification_urls List of current notification URLs
-        @apiError (400) {String} Invalid input
-        """
+        """Replace Notification URLs."""
         json_data = request.get_json()
         notification_urls = json_data.get("notification_urls", [])
 
@@ -100,19 +72,10 @@ class Notifications(Resource):
         return {'notification_urls': clean_urls}, 200
         
     @auth.check_token
+    @validate_openapi_request('deleteNotifications')
     @expects_json(schema_delete_notification_urls)
     def delete(self):
-        """
-        @api {delete} /api/v1/notifications Delete Notification URLs
-        @apiDescription Deletes one or more notification URLs from the configuration
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/notifications -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"notification_urls": ["url1", "url2"]}'
-        @apiParam {String[]} notification_urls The notification URLs to delete.
-        @apiName Delete
-        @apiGroup Notifications
-        @apiSuccess (204) {String} OK Deleted
-        @apiError (400) {String} No matching notification URLs found.
-        """
+        """Delete Notification URLs."""
 
         json_data = request.get_json()
         urls_to_delete = json_data.get("notification_urls", [])

changedetectionio/api/Search.py

@@ -1,6 +1,6 @@
 from flask_restful import Resource, abort
 from flask import request
-from . import auth
+from . import auth, validate_openapi_request
 
 class Search(Resource):
     def __init__(self, **kwargs):
@@ -8,21 +8,9 @@ class Search(Resource):
         self.datastore = kwargs['datastore']
 
     @auth.check_token
+    @validate_openapi_request('searchWatches')
     def get(self):
-        """
-        @api {get} /api/v1/search Search for watches
-        @apiDescription Search watches by URL or title text
-        @apiExample {curl} Example usage:
-            curl "http://localhost:5000/api/v1/search?q=https://example.com/page1" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/search?q=https://example.com/page1?tag=Favourites" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/search?q=https://example.com?partial=true" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiName Search
-        @apiGroup Watch Management
-        @apiQuery {String} q Search query to match against watch URLs and titles
-        @apiQuery {String} [tag] Optional name of tag to limit results (name not UUID)
-        @apiQuery {String} [partial] Allow partial matching of URL query
-        @apiSuccess (200) {Object} JSON Object containing matched watches
-        """
+        """Search for watches by URL or title text."""
         query = request.args.get('q', '').strip()
         tag_limit = request.args.get('tag', '').strip()
         from changedetectionio.strtobool import strtobool

changedetectionio/api/SystemInfo.py

@@ -1,5 +1,5 @@
 from flask_restful import Resource
-from . import auth
+from . import auth, validate_openapi_request
 
 
 class SystemInfo(Resource):
@@ -9,23 +9,9 @@ class SystemInfo(Resource):
         self.update_q = kwargs['update_q']
 
     @auth.check_token
+    @validate_openapi_request('getSystemInfo')
     def get(self):
-        """
-        @api {get} /api/v1/systeminfo Return system info
-        @apiDescription Return some info about the current system state
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/systeminfo -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            HTTP/1.0 200
-            {
-                'queue_size': 10 ,
-                'overdue_watches': ["watch-uuid-list"],
-                'uptime': 38344.55,
-                'watch_count': 800,
-                'version': "0.40.1"
-            }
-        @apiName Get Info
-        @apiGroup System Information
-        """
+        """Return system info."""
         import time
         overdue_watches = []
 

changedetectionio/api/Tags.py

@@ -1,39 +1,46 @@
+from changedetectionio import queuedWatchMetaData
+from changedetectionio import worker_handler
 from flask_expects_json import expects_json
 from flask_restful import abort, Resource
+
 from flask import request
 from . import auth
 
 # Import schemas from __init__.py
-from . import schema_tag, schema_create_tag, schema_update_tag
+from . import schema_tag, schema_create_tag, schema_update_tag, validate_openapi_request
 
 
 class Tag(Resource):
     def __init__(self, **kwargs):
         # datastore is a black box dependency
         self.datastore = kwargs['datastore']
+        self.update_q = kwargs['update_q']
 
     # Get information about a single tag
     # curl http://localhost:5000/api/v1/tag/<string:uuid>
     @auth.check_token
+    @validate_openapi_request('getTag')
     def get(self, uuid):
-        """
-        @api {get} /api/v1/tag/:uuid Single tag - get data or toggle notification muting.
-        @apiDescription Retrieve tag information and set notification_muted status
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/tag/cc0cfffa-f449-477b-83ea-0caafd1dc091 -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/tag/cc0cfffa-f449-477b-83ea-0caafd1dc091?muted=muted" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiName Tag
-        @apiGroup Tag
-        @apiParam {uuid} uuid Tag unique ID.
-        @apiQuery {String} [muted] =`muted` or =`unmuted` , Sets the MUTE NOTIFICATIONS state
-        @apiSuccess (200) {String} OK When muted operation OR full JSON object of the tag
-        @apiSuccess (200) {JSON} TagJSON JSON Full JSON object of the tag
-        """
+        """Get data for a single tag/group, toggle notification muting, or recheck all."""
         from copy import deepcopy
         tag = deepcopy(self.datastore.data['settings']['application']['tags'].get(uuid))
         if not tag:
             abort(404, message=f'No tag exists with the UUID of {uuid}')
 
+        if request.args.get('recheck'):
+            # Recheck all, including muted
+            # Get most overdue first
+            i=0
+            for k in sorted(self.datastore.data['watching'].items(), key=lambda item: item[1].get('last_checked', 0)):
+                watch_uuid = k[0]
+                watch = k[1]
+                if not watch['paused'] and tag['uuid'] not in watch['tags']:
+                    continue
+                worker_handler.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
+                i+=1
+
+            return f"OK, {i} watches queued", 200
+
         if request.args.get('muted', '') == 'muted':
             self.datastore.data['settings']['application']['tags'][uuid]['notification_muted'] = True
             return "OK", 200
@@ -44,16 +51,9 @@ class Tag(Resource):
         return tag
 
     @auth.check_token
+    @validate_openapi_request('deleteTag')
     def delete(self, uuid):
-        """
-        @api {delete} /api/v1/tag/:uuid Delete a tag and remove it from all watches
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/tag/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiParam {uuid} uuid Tag unique ID.
-        @apiName DeleteTag
-        @apiGroup Tag
-        @apiSuccess (200) {String} OK Was deleted
-        """
+        """Delete a tag/group and remove it from all watches."""
         if not self.datastore.data['settings']['application']['tags'].get(uuid):
             abort(400, message='No tag exists with the UUID of {}'.format(uuid))
 
@@ -68,21 +68,10 @@ class Tag(Resource):
         return 'OK', 204
 
     @auth.check_token
+    @validate_openapi_request('updateTag')
     @expects_json(schema_update_tag)
     def put(self, uuid):
-        """
-        @api {put} /api/v1/tag/:uuid Update tag information
-        @apiExample {curl} Example usage:
-            Update (PUT)
-            curl http://localhost:5000/api/v1/tag/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X PUT -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"title": "New Tag Title"}'
-
-        @apiDescription Updates an existing tag using JSON
-        @apiParam {uuid} uuid Tag unique ID.
-        @apiName UpdateTag
-        @apiGroup Tag
-        @apiSuccess (200) {String} OK Was updated
-        @apiSuccess (500) {String} ERR Some other error
-        """
+        """Update tag information."""
         tag = self.datastore.data['settings']['application']['tags'].get(uuid)
         if not tag:
             abort(404, message='No tag exists with the UUID of {}'.format(uuid))
@@ -94,17 +83,10 @@ class Tag(Resource):
 
 
     @auth.check_token
+    @validate_openapi_request('createTag')
     # Only cares for {'title': 'xxxx'}
     def post(self):
-        """
-        @api {post} /api/v1/watch Create a single tag
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"name": "Work related"}'
-        @apiName Create
-        @apiGroup Tag
-        @apiSuccess (200) {String} OK Was created
-        @apiSuccess (500) {String} ERR Some other error
-        """
+        """Create a single tag/group."""
 
         json_data = request.get_json()
         title = json_data.get("title",'').strip()
@@ -122,28 +104,9 @@ class Tags(Resource):
         self.datastore = kwargs['datastore']
 
     @auth.check_token
+    @validate_openapi_request('listTags')
     def get(self):
-        """
-        @api {get} /api/v1/tags List tags
-        @apiDescription Return list of available tags
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/tags -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            {
-                "cc0cfffa-f449-477b-83ea-0caafd1dc091": {
-                    "title": "Tech News",
-                    "notification_muted": false,
-                    "date_created": 1677103794
-                },
-                "e6f5fd5c-dbfe-468b-b8f3-f9d6ff5ad69b": {
-                    "title": "Shopping",
-                    "notification_muted": true,
-                    "date_created": 1676662819
-                }
-            }
-        @apiName ListTags
-        @apiGroup Tag Management
-        @apiSuccess (200) {String} OK JSON dict
-        """
+        """List tags/groups."""
         result = {}
         for uuid, tag in self.datastore.data['settings']['application']['tags'].items():
             result[uuid] = {

changedetectionio/api/Watch.py

@@ -3,14 +3,48 @@ from changedetectionio.strtobool import strtobool
 
 from flask_expects_json import expects_json
 from changedetectionio import queuedWatchMetaData
+from changedetectionio import worker_handler
 from flask_restful import abort, Resource
-from flask import request, make_response
+from flask import request, make_response, send_from_directory
 import validators
 from . import auth
 import copy
 
 # Import schemas from __init__.py
-from . import schema, schema_create_watch, schema_update_watch
+from . import schema, schema_create_watch, schema_update_watch, validate_openapi_request
+
+
+def validate_time_between_check_required(json_data):
+    """
+    Validate that at least one time interval is specified when not using default settings.
+    Returns None if valid, or error message string if invalid.
+    Defaults to using global settings if time_between_check_use_default is not provided.
+    """
+    # Default to using global settings if not specified
+    use_default = json_data.get('time_between_check_use_default', True)
+
+    # If using default settings, no validation needed
+    if use_default:
+        return None
+
+    # If not using defaults, check if time_between_check exists and has at least one non-zero value
+    time_check = json_data.get('time_between_check')
+    if not time_check:
+        # No time_between_check provided and not using defaults - this is an error
+        return "At least one time interval (weeks, days, hours, minutes, or seconds) must be specified when not using global settings."
+
+    # time_between_check exists, check if it has at least one non-zero value
+    if any([
+        (time_check.get('weeks') or 0) > 0,
+        (time_check.get('days') or 0) > 0,
+        (time_check.get('hours') or 0) > 0,
+        (time_check.get('minutes') or 0) > 0,
+        (time_check.get('seconds') or 0) > 0
+    ]):
+        return None
+
+    # time_between_check exists but all values are 0 or empty - this is an error
+    return "At least one time interval (weeks, days, hours, minutes, or seconds) must be specified when not using global settings."
 
 
 class Watch(Resource):
@@ -24,30 +58,16 @@ class Watch(Resource):
     # @todo - version2 - ?muted and ?paused should be able to be called together, return the watch struct not "OK"
     # ?recheck=true
     @auth.check_token
+    @validate_openapi_request('getWatch')
     def get(self, uuid):
-        """
-        @api {get} /api/v1/watch/:uuid Single watch - get data, recheck, pause, mute.
-        @apiDescription Retrieve watch information and set muted/paused status
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?muted=unmuted"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?paused=unpaused"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiName Watch
-        @apiGroup Watch
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiQuery {Boolean} [recheck] Recheck this watch `recheck=1`
-        @apiQuery {String} [paused] =`paused` or =`unpaused` , Sets the PAUSED state
-        @apiQuery {String} [muted] =`muted` or =`unmuted` , Sets the MUTE NOTIFICATIONS state
-        @apiSuccess (200) {String} OK When paused/muted/recheck operation OR full JSON object of the watch
-        @apiSuccess (200) {JSON} WatchJSON JSON Full JSON object of the watch
-        """
+        """Get information about a single watch, recheck, pause, or mute."""
         from copy import deepcopy
         watch = deepcopy(self.datastore.data['watching'].get(uuid))
         if not watch:
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
 
         if request.args.get('recheck'):
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+            worker_handler.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             return "OK", 200
         if request.args.get('paused', '') == 'paused':
             self.datastore.data['watching'].get(uuid).pause()
@@ -68,19 +88,14 @@ class Watch(Resource):
         # attr .last_changed will check for the last written text snapshot on change
         watch['last_changed'] = watch.last_changed
         watch['viewed'] = watch.viewed
+        watch['link'] = watch.link,
+
         return watch
 
     @auth.check_token
+    @validate_openapi_request('deleteWatch')
     def delete(self, uuid):
-        """
-        @api {delete} /api/v1/watch/:uuid Delete a watch and related history
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiName Delete
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was deleted
-        """
+        """Delete a watch and related history."""
         if not self.datastore.data['watching'].get(uuid):
             abort(400, message='No watch exists with the UUID of {}'.format(uuid))
 
@@ -88,21 +103,10 @@ class Watch(Resource):
         return 'OK', 204
 
     @auth.check_token
+    @validate_openapi_request('updateWatch')
     @expects_json(schema_update_watch)
     def put(self, uuid):
-        """
-        @api {put} /api/v1/watch/:uuid Update watch information
-        @apiExample {curl} Example usage:
-            Update (PUT)
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X PUT -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "new list"}'
-
-        @apiDescription Updates an existing watch using JSON, accepts the same structure as returned in <a href="#api-Watch-Watch">get single watch information</a>
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiName Update a watch
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was updated
-        @apiSuccess (500) {String} ERR Some other error
-        """
+        """Update watch information."""
         watch = self.datastore.data['watching'].get(uuid)
         if not watch:
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
@@ -112,6 +116,11 @@ class Watch(Resource):
             if not request.json.get('proxy') in plist:
                 return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
 
+        # Validate time_between_check when not using defaults
+        validation_error = validate_time_between_check_required(request.json)
+        if validation_error:
+            return validation_error, 400
+
         watch.update(request.json)
 
         return "OK", 200
@@ -125,22 +134,9 @@ class WatchHistory(Resource):
     # Get a list of available history for a watch by UUID
     # curl http://localhost:5000/api/v1/watch/<string:uuid>/history
     @auth.check_token
+    @validate_openapi_request('getWatchHistory')
     def get(self, uuid):
-        """
-        @api {get} /api/v1/watch/<string:uuid>/history Get a list of all historical snapshots available for a watch
-        @apiDescription Requires `uuid`, returns list
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
-            {
-                "1676649279": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/cb7e9be8258368262246910e6a2a4c30.txt",
-                "1677092785": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/e20db368d6fc633e34f559ff67bb4044.txt",
-                "1677103794": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/02efdd37dacdae96554a8cc85dc9c945.txt"
-            }
-        @apiName Get list of available stored snapshots for watch
-        @apiGroup Watch History
-        @apiSuccess (200) {String} OK
-        @apiSuccess (404) {String} ERR Not found
-        """
+        """Get a list of all historical snapshots available for a watch."""
         watch = self.datastore.data['watching'].get(uuid)
         if not watch:
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
@@ -153,18 +149,9 @@ class WatchSingleHistory(Resource):
         self.datastore = kwargs['datastore']
 
     @auth.check_token
+    @validate_openapi_request('getWatchSnapshot')
     def get(self, uuid, timestamp):
-        """
-        @api {get} /api/v1/watch/<string:uuid>/history/<int:timestamp> Get single snapshot from watch
-        @apiDescription Requires watch `uuid` and `timestamp`. `timestamp` of "`latest`" for latest available snapshot, or <a href="#api-Watch_History-Get_list_of_available_stored_snapshots_for_watch">use the list returned here</a>
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history/1677092977 -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
-        @apiName Get single snapshot content
-        @apiGroup Watch History
-        @apiParam {String} [html]       Optional Set to =1 to return the last HTML (only stores last 2 snapshots, use `latest` as timestamp)
-        @apiSuccess (200) {String} OK
-        @apiSuccess (404) {String} ERR Not found
-        """
+        """Get single snapshot from watch."""
         watch = self.datastore.data['watching'].get(uuid)
         if not watch:
             abort(404, message=f"No watch exists with the UUID of {uuid}")
@@ -190,6 +177,39 @@ class WatchSingleHistory(Resource):
 
         return response
 
+class WatchFavicon(Resource):
+    def __init__(self, **kwargs):
+        # datastore is a black box dependency
+        self.datastore = kwargs['datastore']
+
+    @auth.check_token
+    @validate_openapi_request('getWatchFavicon')
+    def get(self, uuid):
+        """Get favicon for a watch."""
+        watch = self.datastore.data['watching'].get(uuid)
+        if not watch:
+            abort(404, message=f"No watch exists with the UUID of {uuid}")
+
+        favicon_filename = watch.get_favicon_filename()
+        if favicon_filename:
+            try:
+                import magic
+                mime = magic.from_file(
+                    os.path.join(watch.watch_data_dir, favicon_filename),
+                    mime=True
+                )
+            except ImportError:
+                # Fallback, no python-magic
+                import mimetypes
+                mime, encoding = mimetypes.guess_type(favicon_filename)
+
+            response = make_response(send_from_directory(watch.watch_data_dir, favicon_filename))
+            response.headers['Content-type'] = mime
+            response.headers['Cache-Control'] = 'max-age=300, must-revalidate'  # Cache for 5 minutes, then revalidate
+            return response
+
+        abort(404, message=f'No Favicon available for {uuid}')
+
 
 class CreateWatch(Resource):
     def __init__(self, **kwargs):
@@ -198,18 +218,10 @@ class CreateWatch(Resource):
         self.update_q = kwargs['update_q']
 
     @auth.check_token
+    @validate_openapi_request('createWatch')
     @expects_json(schema_create_watch)
     def post(self):
-        """
-        @api {post} /api/v1/watch Create a single watch
-        @apiDescription Requires atleast `url` set, can accept the same structure as <a href="#api-Watch-Watch">get single watch information</a> to create.
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "nice list"}'
-        @apiName Create
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was created
-        @apiSuccess (500) {String} ERR Some other error
-        """
+        """Create a single watch."""
 
         json_data = request.get_json()
         url = json_data['url'].strip()
@@ -224,6 +236,11 @@ class CreateWatch(Resource):
             if not json_data.get('proxy') in plist:
                 return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
 
+        # Validate time_between_check when not using defaults
+        validation_error = validate_time_between_check_required(json_data)
+        if validation_error:
+            return validation_error, 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)
@@ -236,41 +253,15 @@ class CreateWatch(Resource):
 
         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}))
+            worker_handler.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
             return {'uuid': new_uuid}, 201
         else:
             return "Invalid or unsupported URL", 400
 
     @auth.check_token
+    @validate_openapi_request('listWatches')
     def get(self):
-        """
-        @api {get} /api/v1/watch List watches
-        @apiDescription Return concise list of available watches and some very basic info
-        @apiExample {curl} Example usage:
-            curl http://localhost:5000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            {
-                "6a4b7d5c-fee4-4616-9f43-4ac97046b595": {
-                    "last_changed": 1677103794,
-                    "last_checked": 1677103794,
-                    "last_error": false,
-                    "title": "",
-                    "url": "http://www.quotationspage.com/random.php"
-                },
-                "e6f5fd5c-dbfe-468b-b8f3-f9d6ff5ad69b": {
-                    "last_changed": 0,
-                    "last_checked": 1676662819,
-                    "last_error": false,
-                    "title": "QuickLook",
-                    "url": "https://github.com/QL-Win/QuickLook/tags"
-                }
-            }
-
-        @apiParam {String} [recheck_all]       Optional Set to =1 to force recheck of all watches
-        @apiParam {String} [tag]               Optional name of tag to limit results
-        @apiName ListWatches
-        @apiGroup Watch Management
-        @apiSuccess (200) {String} OK JSON dict
-        """
+        """List watches."""
         list = {}
 
         tag_limit = request.args.get('tag', '').lower()
@@ -284,6 +275,8 @@ class CreateWatch(Resource):
                 'last_changed': watch.last_changed,
                 'last_checked': watch['last_checked'],
                 'last_error': watch['last_error'],
+                'link': watch.link,
+                'page_title': watch['page_title'],
                 'title': watch['title'],
                 'url': watch['url'],
                 'viewed': watch.viewed
@@ -291,7 +284,7 @@ class CreateWatch(Resource):
 
         if request.args.get('recheck_all'):
             for uuid in self.datastore.data['watching'].keys():
-                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                worker_handler.queue_item_async_safe(self.update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             return {'status': "OK"}, 200
 
         return list, 200

changedetectionio/api/__init__.py

@@ -1,4 +1,10 @@
 import copy
+import yaml
+import functools
+from flask import request, abort
+from loguru import logger
+from openapi_core import OpenAPI
+from openapi_core.contrib.flask import FlaskOpenAPIRequest
 from . import api_schema
 from ..model import watch_base
 
@@ -8,6 +14,7 @@ schema = api_schema.build_watch_json_schema(watch_base_config)
 
 schema_create_watch = copy.deepcopy(schema)
 schema_create_watch['required'] = ['url']
+del schema_create_watch['properties']['last_viewed']
 
 schema_update_watch = copy.deepcopy(schema)
 schema_update_watch['additionalProperties'] = False
@@ -25,9 +32,47 @@ schema_create_notification_urls['required'] = ['notification_urls']
 schema_delete_notification_urls = copy.deepcopy(schema_notification_urls)
 schema_delete_notification_urls['required'] = ['notification_urls']
 
+@functools.cache
+def get_openapi_spec():
+    import os
+    spec_path = os.path.join(os.path.dirname(__file__), '../../docs/api-spec.yaml')
+    with open(spec_path, 'r') as f:
+        spec_dict = yaml.safe_load(f)
+    _openapi_spec = OpenAPI.from_dict(spec_dict)
+    return _openapi_spec
+
+def validate_openapi_request(operation_id):
+    """Decorator to validate incoming requests against OpenAPI spec."""
+    def decorator(f):
+        @functools.wraps(f)
+        def wrapper(*args, **kwargs):
+            try:
+                # Skip OpenAPI validation for GET requests since they don't have request bodies
+                if request.method.upper() != 'GET':
+                    spec = get_openapi_spec()
+                    openapi_request = FlaskOpenAPIRequest(request)
+                    result = spec.unmarshal_request(openapi_request)
+                    if result.errors:
+                        from werkzeug.exceptions import BadRequest
+                        error_details = []
+                        for error in result.errors:
+                            error_details.append(str(error))
+                        raise BadRequest(f"OpenAPI validation failed: {error_details}")
+            except BadRequest:
+                # Re-raise BadRequest exceptions (validation failures)
+                raise
+            except Exception as e:
+                # If OpenAPI spec loading fails, log but don't break existing functionality
+                logger.critical(f"OpenAPI validation warning for {operation_id}: {e}")
+                abort(500)
+            return f(*args, **kwargs)
+        return wrapper
+    return decorator
+
 # Import all API resources
-from .Watch import Watch, WatchHistory, WatchSingleHistory, CreateWatch
+from .Watch import Watch, WatchHistory, WatchSingleHistory, CreateWatch, WatchFavicon
 from .Tags import Tags, Tag
 from .Import import Import
 from .SystemInfo import SystemInfo
 from .Notifications import Notifications
+

changedetectionio/api/api_schema.py

@@ -78,6 +78,13 @@ def build_watch_json_schema(d):
               ]:
         schema['properties'][v]['anyOf'].append({'type': 'string', "maxLength": 5000})
 
+    for v in ['last_viewed']:
+        schema['properties'][v] = {
+            "type": "integer",
+            "description": "Unix timestamp in seconds of the last time the watch was viewed.",
+            "minimum": 0
+        }
+
     # None or Boolean
     schema['properties']['track_ldjson_price_data']['anyOf'].append({'type': 'boolean'})
 
@@ -112,6 +119,12 @@ def build_watch_json_schema(d):
 
     schema['properties']['time_between_check'] = build_time_between_check_json_schema()
 
+    schema['properties']['time_between_check_use_default'] = {
+        "type": "boolean",
+        "default": True,
+        "description": "Whether to use global settings for time between checks - defaults to true if not set"
+    }
+
     schema['properties']['browser_steps'] = {
         "anyOf": [
             {

changedetectionio/async_update_worker.py

@@ -0,0 +1,465 @@
+from .processors.exceptions import ProcessorException
+import changedetectionio.content_fetchers.exceptions as content_fetchers_exceptions
+from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
+from changedetectionio import html_tools
+from changedetectionio.flask_app import watch_check_update
+
+import asyncio
+import importlib
+import os
+import queue
+import time
+
+from loguru import logger
+
+# Async version of update_worker
+# Processes jobs from AsyncSignalPriorityQueue instead of threaded queue
+
+async def async_update_worker(worker_id, q, notification_q, app, datastore):
+    """
+    Async worker function that processes watch check jobs from the queue.
+    
+    Args:
+        worker_id: Unique identifier for this worker
+        q: AsyncSignalPriorityQueue containing jobs to process
+        notification_q: Standard queue for notifications
+        app: Flask application instance
+        datastore: Application datastore
+    """
+    # Set a descriptive name for this task
+    task = asyncio.current_task()
+    if task:
+        task.set_name(f"async-worker-{worker_id}")
+    
+    logger.info(f"Starting async worker {worker_id}")
+    
+    while not app.config.exit.is_set():
+        update_handler = None
+        watch = None
+
+        try:
+            # Use native janus async interface - no threads needed!
+            queued_item_data = await asyncio.wait_for(q.async_get(), timeout=1.0)
+            
+        except asyncio.TimeoutError:
+            # No jobs available, continue loop
+            continue
+        except Exception as e:
+            logger.critical(f"CRITICAL: Worker {worker_id} failed to get queue item: {type(e).__name__}: {e}")
+            
+            # Log queue health for debugging
+            try:
+                queue_size = q.qsize()
+                is_empty = q.empty()
+                logger.critical(f"CRITICAL: Worker {worker_id} queue health - size: {queue_size}, empty: {is_empty}")
+            except Exception as health_e:
+                logger.critical(f"CRITICAL: Worker {worker_id} queue health check failed: {health_e}")
+            
+            await asyncio.sleep(0.1)
+            continue
+        
+        uuid = queued_item_data.item.get('uuid')
+        fetch_start_time = round(time.time())
+        
+        # Mark this UUID as being processed
+        from changedetectionio import worker_handler
+        worker_handler.set_uuid_processing(uuid, processing=True)
+        
+        try:
+            if uuid in list(datastore.data['watching'].keys()) and datastore.data['watching'][uuid].get('url'):
+                changed_detected = False
+                contents = b''
+                process_changedetection_results = True
+                update_obj = {}
+
+                # Clear last errors
+                datastore.data['watching'][uuid]['browser_steps_last_error_step'] = None
+                datastore.data['watching'][uuid]['last_checked'] = fetch_start_time
+
+                watch = datastore.data['watching'].get(uuid)
+
+                logger.info(f"Worker {worker_id} processing watch UUID {uuid} Priority {queued_item_data.priority} URL {watch['url']}")
+
+                try:
+                    watch_check_update.send(watch_uuid=uuid)
+
+                    # Processor is what we are using for detecting the "Change"
+                    processor = watch.get('processor', 'text_json_diff')
+
+                    # Init a new 'difference_detection_processor'
+                    processor_module_name = f"changedetectionio.processors.{processor}.processor"
+                    try:
+                        processor_module = importlib.import_module(processor_module_name)
+                    except ModuleNotFoundError as e:
+                        print(f"Processor module '{processor}' not found.")
+                        raise e
+
+                    update_handler = processor_module.perform_site_check(datastore=datastore,
+                                                                         watch_uuid=uuid)
+
+                    # All fetchers are now async, so call directly
+                    await update_handler.call_browser()
+
+                    # Run change detection (this is synchronous)
+                    changed_detected, update_obj, contents = update_handler.run_changedetection(watch=watch)
+
+                except PermissionError as e:
+                    logger.critical(f"File permission error updating file, watch: {uuid}")
+                    logger.critical(str(e))
+                    process_changedetection_results = False
+
+                except ProcessorException as e:
+                    if e.screenshot:
+                        watch.save_screenshot(screenshot=e.screenshot)
+                    if e.xpath_data:
+                        watch.save_xpath_data(data=e.xpath_data)
+                    datastore.update_watch(uuid=uuid, update_obj={'last_error': e.message})
+                    process_changedetection_results = False
+
+                except content_fetchers_exceptions.ReplyWithContentButNoText as e:
+                    extra_help = ""
+                    if e.has_filters:
+                        has_img = html_tools.include_filters(include_filters='img',
+                                                             html_content=e.html_content)
+                        if has_img:
+                            extra_help = ", it's possible that the filters you have give an empty result or contain only an image."
+                        else:
+                            extra_help = ", it's possible that the filters were found, but contained no usable text."
+
+                    datastore.update_watch(uuid=uuid, update_obj={
+                        'last_error': f"Got HTML content but no text found (With {e.status_code} reply code){extra_help}"
+                    })
+
+                    if e.screenshot:
+                        watch.save_screenshot(screenshot=e.screenshot, as_error=True)
+
+                    if e.xpath_data:
+                        watch.save_xpath_data(data=e.xpath_data)
+                        
+                    process_changedetection_results = False
+
+                except content_fetchers_exceptions.Non200ErrorCodeReceived as e:
+                    if e.status_code == 403:
+                        err_text = "Error - 403 (Access denied) received"
+                    elif e.status_code == 404:
+                        err_text = "Error - 404 (Page not found) received"
+                    elif e.status_code == 407:
+                        err_text = "Error - 407 (Proxy authentication required) received, did you need a username and password for the proxy?"
+                    elif e.status_code == 500:
+                        err_text = "Error - 500 (Internal server error) received from the web site"
+                    else:
+                        extra = ' (Access denied or blocked)' if str(e.status_code).startswith('4') else ''
+                        err_text = f"Error - Request returned a HTTP error code {e.status_code}{extra}"
+
+                    if e.screenshot:
+                        watch.save_screenshot(screenshot=e.screenshot, as_error=True)
+                    if e.xpath_data:
+                        watch.save_xpath_data(data=e.xpath_data, as_error=True)
+                    if e.page_text:
+                        watch.save_error_text(contents=e.page_text)
+
+                    datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
+                    process_changedetection_results = False
+
+                except FilterNotFoundInResponse as e:
+                    if not datastore.data['watching'].get(uuid):
+                        continue
+
+                    err_text = "Warning, no filters were found, no change detection ran - Did the page change layout? update your Visual Filter if necessary."
+                    datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
+
+                    # Filter wasnt found, but we should still update the visual selector so that they can have a chance to set it up again
+                    if e.screenshot:
+                        watch.save_screenshot(screenshot=e.screenshot)
+
+                    if e.xpath_data:
+                        watch.save_xpath_data(data=e.xpath_data)
+
+                    # Only when enabled, send the notification
+                    if watch.get('filter_failure_notification_send', False):
+                        c = watch.get('consecutive_filter_failures', 0)
+                        c += 1
+                        # Send notification if we reached the threshold?
+                        threshold = datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts', 0)
+                        logger.debug(f"Filter for {uuid} not found, consecutive_filter_failures: {c} of threshold {threshold}")
+                        if c >= threshold:
+                            if not watch.get('notification_muted'):
+                                logger.debug(f"Sending filter failed notification for {uuid}")
+                                await send_filter_failure_notification(uuid, notification_q, datastore)
+                            c = 0
+                            logger.debug(f"Reset filter failure count back to zero")
+
+                        datastore.update_watch(uuid=uuid, update_obj={'consecutive_filter_failures': c})
+                    else:
+                        logger.trace(f"{uuid} - filter_failure_notification_send not enabled, skipping")
+
+                    process_changedetection_results = False
+
+                except content_fetchers_exceptions.checksumFromPreviousCheckWasTheSame as e:
+                    # Yes fine, so nothing todo, don't continue to process.
+                    process_changedetection_results = False
+                    changed_detected = False
+                    
+                except content_fetchers_exceptions.BrowserConnectError as e:
+                    datastore.update_watch(uuid=uuid,
+                                         update_obj={'last_error': e.msg})
+                    process_changedetection_results = False
+                    
+                except content_fetchers_exceptions.BrowserFetchTimedOut as e:
+                    datastore.update_watch(uuid=uuid,
+                                         update_obj={'last_error': e.msg})
+                    process_changedetection_results = False
+                    
+                except content_fetchers_exceptions.BrowserStepsStepException as e:
+                    if not datastore.data['watching'].get(uuid):
+                        continue
+
+                    error_step = e.step_n + 1
+                    from playwright._impl._errors import TimeoutError, Error
+
+                    # Generally enough info for TimeoutError (couldnt locate the element after default seconds)
+                    err_text = f"Browser step at position {error_step} could not run, check the watch, add a delay if necessary, view Browser Steps to see screenshot at that step."
+
+                    if e.original_e.name == "TimeoutError":
+                        # Just the first line is enough, the rest is the stack trace
+                        err_text += " Could not find the target."
+                    else:
+                        # Other Error, more info is good.
+                        err_text += " " + str(e.original_e).splitlines()[0]
+
+                    logger.debug(f"BrowserSteps exception at step {error_step} {str(e.original_e)}")
+
+                    datastore.update_watch(uuid=uuid,
+                                         update_obj={'last_error': err_text,
+                                                   'browser_steps_last_error_step': error_step})
+
+                    if watch.get('filter_failure_notification_send', False):
+                        c = watch.get('consecutive_filter_failures', 0)
+                        c += 1
+                        # Send notification if we reached the threshold?
+                        threshold = datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts', 0)
+                        logger.error(f"Step for {uuid} not found, consecutive_filter_failures: {c}")
+                        if threshold > 0 and c >= threshold:
+                            if not watch.get('notification_muted'):
+                                await send_step_failure_notification(watch_uuid=uuid, step_n=e.step_n, notification_q=notification_q, datastore=datastore)
+                            c = 0
+
+                        datastore.update_watch(uuid=uuid, update_obj={'consecutive_filter_failures': c})
+
+                    process_changedetection_results = False
+
+                except content_fetchers_exceptions.EmptyReply as e:
+                    # Some kind of custom to-str handler in the exception handler that does this?
+                    err_text = "EmptyReply - try increasing 'Wait seconds before extracting text', Status Code {}".format(e.status_code)
+                    datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                                                                'last_check_status': e.status_code})
+                    process_changedetection_results = False
+                    
+                except content_fetchers_exceptions.ScreenshotUnavailable as e:
+                    err_text = "Screenshot unavailable, page did not render fully in the expected time or page was too long - try increasing 'Wait seconds before extracting text'"
+                    datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                                                                'last_check_status': e.status_code})
+                    process_changedetection_results = False
+                    
+                except content_fetchers_exceptions.JSActionExceptions as e:
+                    err_text = "Error running JS Actions - Page request - "+e.message
+                    if e.screenshot:
+                        watch.save_screenshot(screenshot=e.screenshot, as_error=True)
+                    datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                                                                'last_check_status': e.status_code})
+                    process_changedetection_results = False
+                    
+                except content_fetchers_exceptions.PageUnloadable as e:
+                    err_text = "Page request from server didnt respond correctly"
+                    if e.message:
+                        err_text = "{} - {}".format(err_text, e.message)
+
+                    if e.screenshot:
+                        watch.save_screenshot(screenshot=e.screenshot, as_error=True)
+
+                    datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                                                                'last_check_status': e.status_code,
+                                                                'has_ldjson_price_data': None})
+                    process_changedetection_results = False
+                    
+                except content_fetchers_exceptions.BrowserStepsInUnsupportedFetcher as e:
+                    err_text = "This watch has Browser Steps configured and so it cannot run with the 'Basic fast Plaintext/HTTP Client', either remove the Browser Steps or select a Chrome fetcher."
+                    datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
+                    process_changedetection_results = False
+                    logger.error(f"Exception (BrowserStepsInUnsupportedFetcher) reached processing watch UUID: {uuid}")
+
+                except Exception as e:
+                    logger.error(f"Worker {worker_id} exception processing watch UUID: {uuid}")
+                    logger.error(str(e))
+                    datastore.update_watch(uuid=uuid, update_obj={'last_error': "Exception: " + str(e)})
+                    process_changedetection_results = False
+
+                else:
+                    if not datastore.data['watching'].get(uuid):
+                        continue
+
+                    update_obj['content-type'] = update_handler.fetcher.get_all_headers().get('content-type', '').lower()
+
+                    if not watch.get('ignore_status_codes'):
+                        update_obj['consecutive_filter_failures'] = 0
+
+                    update_obj['last_error'] = False
+                    cleanup_error_artifacts(uuid, datastore)
+
+                if not datastore.data['watching'].get(uuid):
+                    continue
+
+                if process_changedetection_results:
+                    try:
+                        datastore.update_watch(uuid=uuid, update_obj=update_obj)
+
+                        if changed_detected or not watch.history_n:
+                            if update_handler.screenshot:
+                                watch.save_screenshot(screenshot=update_handler.screenshot)
+
+                            if update_handler.xpath_data:
+                                watch.save_xpath_data(data=update_handler.xpath_data)
+
+                            # Ensure unique timestamp for history
+                            if watch.newest_history_key and int(fetch_start_time) == int(watch.newest_history_key):
+                                logger.warning(f"Timestamp {fetch_start_time} already exists, waiting 1 seconds")
+                                fetch_start_time += 1
+                                await asyncio.sleep(1)
+
+                            watch.save_history_text(contents=contents,
+                                                    timestamp=int(fetch_start_time),
+                                                    snapshot_id=update_obj.get('previous_md5', 'none'))
+
+                            empty_pages_are_a_change = datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
+                            if update_handler.fetcher.content or (not update_handler.fetcher.content and empty_pages_are_a_change):
+                                watch.save_last_fetched_html(contents=update_handler.fetcher.content, timestamp=int(fetch_start_time))
+
+                            # Send notifications on second+ check
+                            if watch.history_n >= 2:
+                                logger.info(f"Change detected in UUID {uuid} - {watch['url']}")
+                                if not watch.get('notification_muted'):
+                                    await send_content_changed_notification(uuid, notification_q, datastore)
+
+                    except Exception as e:
+                        logger.critical(f"Worker {worker_id} exception in process_changedetection_results")
+                        logger.critical(str(e))
+                        datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
+
+                # Always record attempt count
+                count = watch.get('check_count', 0) + 1
+
+                # Always record page title (used in notifications, and can change even when the content is the same)
+                try:
+                    page_title = html_tools.extract_title(data=update_handler.fetcher.content)
+                    logger.debug(f"UUID: {uuid} Page <title> is '{page_title}'")
+                    datastore.update_watch(uuid=uuid, update_obj={'page_title': page_title})
+                except Exception as e:
+                    logger.warning(f"UUID: {uuid} Exception when extracting <title> - {str(e)}")
+
+                # Record server header
+                try:
+                    server_header = update_handler.fetcher.headers.get('server', '').strip().lower()[:255]
+                    datastore.update_watch(uuid=uuid, update_obj={'remote_server_reply': server_header})
+                except Exception as e:
+                    pass
+
+                # Store favicon if necessary
+                if update_handler.fetcher.favicon_blob and update_handler.fetcher.favicon_blob.get('base64'):
+                    watch.bump_favicon(url=update_handler.fetcher.favicon_blob.get('url'),
+                                       favicon_base_64=update_handler.fetcher.favicon_blob.get('base64')
+                                       )
+
+                datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - fetch_start_time, 3),
+                                                               'check_count': count})
+
+        except Exception as e:
+            logger.error(f"Worker {worker_id} unexpected error processing {uuid}: {e}")
+            logger.error(f"Worker {worker_id} traceback:", exc_info=True)
+            
+            # Also update the watch with error information
+            if datastore and uuid in datastore.data['watching']:
+                datastore.update_watch(uuid=uuid, update_obj={'last_error': f"Worker error: {str(e)}"})
+        
+        finally:
+            # Always cleanup - this runs whether there was an exception or not
+            if uuid:
+                try:
+                    # Mark UUID as no longer being processed
+                    worker_handler.set_uuid_processing(uuid, processing=False)
+                    
+                    # Send completion signal
+                    if watch:
+                        #logger.info(f"Worker {worker_id} sending completion signal for UUID {watch['uuid']}")
+                        watch_check_update.send(watch_uuid=watch['uuid'])
+
+                    update_handler = None
+                    logger.debug(f"Worker {worker_id} completed watch {uuid} in {time.time()-fetch_start_time:.2f}s")
+                except Exception as cleanup_error:
+                    logger.error(f"Worker {worker_id} error during cleanup: {cleanup_error}")
+            
+            # Brief pause before continuing to avoid tight error loops (only on error)
+            if 'e' in locals():
+                await asyncio.sleep(1.0)
+            else:
+                # Small yield for normal completion
+                await asyncio.sleep(0.01)
+
+        # Check if we should exit
+        if app.config.exit.is_set():
+            break
+
+    # Check if we're in pytest environment - if so, be more gentle with logging
+    import sys
+    in_pytest = "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ
+    
+    if not in_pytest:
+        logger.info(f"Worker {worker_id} shutting down")
+
+
+def cleanup_error_artifacts(uuid, datastore):
+    """Helper function to clean up error artifacts"""
+    cleanup_files = ["last-error-screenshot.png", "last-error.txt"]
+    for f in cleanup_files:
+        full_path = os.path.join(datastore.datastore_path, uuid, f)
+        if os.path.isfile(full_path):
+            os.unlink(full_path)
+
+
+
+async def send_content_changed_notification(watch_uuid, notification_q, datastore):
+    """Helper function to queue notifications using the new notification service"""
+    try:
+        from changedetectionio.notification_service import create_notification_service
+        
+        # Create notification service instance
+        notification_service = create_notification_service(datastore, notification_q)
+        
+        notification_service.send_content_changed_notification(watch_uuid)
+    except Exception as e:
+        logger.error(f"Error sending notification for {watch_uuid}: {e}")
+
+
+async def send_filter_failure_notification(watch_uuid, notification_q, datastore):
+    """Helper function to send filter failure notifications using the new notification service"""
+    try:
+        from changedetectionio.notification_service import create_notification_service
+        
+        # Create notification service instance
+        notification_service = create_notification_service(datastore, notification_q)
+        
+        notification_service.send_filter_failure_notification(watch_uuid)
+    except Exception as e:
+        logger.error(f"Error sending filter failure notification for {watch_uuid}: {e}")
+
+
+async def send_step_failure_notification(watch_uuid, step_n, notification_q, datastore):
+    """Helper function to send step failure notifications using the new notification service"""
+    try:
+        from changedetectionio.notification_service import create_notification_service
+        
+        # Create notification service instance
+        notification_service = create_notification_service(datastore, notification_q)
+        
+        notification_service.send_step_failure_notification(watch_uuid, step_n)
+    except Exception as e:
+        logger.error(f"Error sending step failure notification for {watch_uuid}: {e}")

changedetectionio/blueprint/browser_steps/__init__.py

@@ -25,35 +25,53 @@ io_interface_context = None
 import json
 import hashlib
 from flask import Response
+import asyncio
+import threading
+
+def run_async_in_browser_loop(coro):
+    """Run async coroutine using the existing async worker event loop"""
+    from changedetectionio import worker_handler
+    
+    # Use the existing async worker event loop instead of creating a new one
+    if worker_handler.USE_ASYNC_WORKERS and worker_handler.async_loop and not worker_handler.async_loop.is_closed():
+        logger.debug("Browser steps using existing async worker event loop")
+        future = asyncio.run_coroutine_threadsafe(coro, worker_handler.async_loop)
+        return future.result()
+    else:
+        # Fallback: create a new event loop (for sync workers or if async loop not available)
+        logger.debug("Browser steps creating temporary event loop")
+        loop = asyncio.new_event_loop()
+        asyncio.set_event_loop(loop)
+        try:
+            return loop.run_until_complete(coro)
+        finally:
+            loop.close()
 
 def construct_blueprint(datastore: ChangeDetectionStore):
     browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
 
-    def start_browsersteps_session(watch_uuid):
-        from . import nonContext
+    async def start_browsersteps_session(watch_uuid):
         from . import browser_steps
         import time
-        global io_interface_context
+        from playwright.async_api import async_playwright
 
         # 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()
+        # Create a new async playwright instance for browser steps
+        playwright_instance = async_playwright()
+        playwright_context = await playwright_instance.start()
 
         keepalive_ms = ((keepalive_seconds + 3) * 1000)
         base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '').strip('"')
         a = "?" if not '?' in base_url else '&'
         base_url += a + f"timeout={keepalive_ms}"
 
-        browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(base_url)
+        browser = await playwright_context.chromium.connect_over_cdp(base_url, timeout=keepalive_ms)
+        browsersteps_start_session['browser'] = browser
+        browsersteps_start_session['playwright_context'] = playwright_context
 
         proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
         proxy = None
@@ -75,15 +93,20 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 logger.debug(f"Browser Steps: UUID {watch_uuid} selected proxy {proxy_url}")
 
         # Tell Playwright to connect to Chrome and setup a new session via our stepper interface
-        browsersteps_start_session['browserstepper'] = browser_steps.browsersteps_live_ui(
-            playwright_browser=browsersteps_start_session['browser'],
+        browserstepper = browser_steps.browsersteps_live_ui(
+            playwright_browser=browser,
             proxy=proxy,
             start_url=datastore.data['watching'][watch_uuid].link,
             headers=datastore.data['watching'][watch_uuid].get('headers')
         )
+        
+        # Initialize the async connection
+        await browserstepper.connect(proxy=proxy)
+        
+        browsersteps_start_session['browserstepper'] = browserstepper
 
         # For test
-        #browsersteps_start_session['browserstepper'].action_goto_url(value="http://example.com?time="+str(time.time()))
+        #await browsersteps_start_session['browserstepper'].action_goto_url(value="http://example.com?time="+str(time.time()))
 
         return browsersteps_start_session
 
@@ -92,7 +115,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @browser_steps_blueprint.route("/browsersteps_start_session", methods=['GET'])
     def browsersteps_start_session():
         # A new session was requested, return sessionID
-
+        import asyncio
         import uuid
         browsersteps_session_id = str(uuid.uuid4())
         watch_uuid = request.args.get('uuid')
@@ -104,7 +127,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         logger.debug("browser_steps.py connecting")
 
         try:
-            browsersteps_sessions[browsersteps_session_id] = start_browsersteps_session(watch_uuid)
+            # Run the async function in the dedicated browser steps event loop
+            browsersteps_sessions[browsersteps_session_id] = run_async_in_browser_loop(
+                start_browsersteps_session(watch_uuid)
+            )
         except Exception as e:
             if 'ECONNREFUSED' in str(e):
                 return make_response('Unable to start the Playwright Browser session, is sockpuppetbrowser running? Network configuration is OK?', 401)
@@ -169,9 +195,14 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             is_last_step = strtobool(request.form.get('is_last_step'))
 
             try:
-                browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(action_name=step_operation,
-                                         selector=step_selector,
-                                         optional_value=step_optional_value)
+                # Run the async call_action method in the dedicated browser steps event loop
+                run_async_in_browser_loop(
+                    browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(
+                        action_name=step_operation,
+                        selector=step_selector,
+                        optional_value=step_optional_value
+                    )
+                )
 
             except Exception as e:
                 logger.error(f"Exception when calling step operation {step_operation} {str(e)}")
@@ -185,7 +216,11 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         # Screenshots and other info only needed on requesting a step (POST)
         try:
-            (screenshot, xpath_data) = browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
+            # Run the async get_current_state method in the dedicated browser steps event loop
+            (screenshot, xpath_data) = run_async_in_browser_loop(
+                browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
+            )
+                
             if is_last_step:
                 watch = datastore.data['watching'].get(uuid)
                 u = browsersteps_sessions[browsersteps_session_id]['browserstepper'].page.url
@@ -193,13 +228,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                     watch.save_screenshot(screenshot=screenshot)
                     watch.save_xpath_data(data=xpath_data)
 
-        except playwright._impl._api_types.Error as e:
-            return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
         except Exception as e:
-            return make_response("Error fetching screenshot and element data - " + str(e), 401)
+            return make_response(f"Error fetching screenshot and element data - {str(e)}", 401)
 
         # SEND THIS BACK TO THE BROWSER
-
         output = {
             "screenshot": f"data:image/jpeg;base64,{base64.b64encode(screenshot).decode('ascii')}",
             "xpath_data": xpath_data,

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -1,8 +1,6 @@
 import os
 import time
 import re
-import sys
-import traceback
 from random import randint
 from loguru import logger
 
@@ -63,7 +61,7 @@ class steppable_browser_interface():
         self.start_url = start_url
 
     # Convert and perform "Click Button" for example
-    def call_action(self, action_name, selector=None, optional_value=None):
+    async def call_action(self, action_name, selector=None, optional_value=None):
         if self.page is None:
             logger.warning("Cannot call action on None page object")
             return
@@ -92,74 +90,99 @@ class steppable_browser_interface():
         if optional_value and ('{%' in optional_value or '{{' in optional_value):
             optional_value = jinja_render(template_str=optional_value)
 
+        # Trigger click and cautiously handle potential navigation
+        # This means the page redirects/reloads/changes JS etc etc
+        if call_action_name.startswith('click_'):
+            try:
+                # Set up navigation expectation before the click (like sync version)
+                async with self.page.expect_event("framenavigated", timeout=3000) as navigation_info:
+                    await action_handler(selector, optional_value)
+                
+                # Check if navigation actually occurred
+                try:
+                    await navigation_info.value  # This waits for the navigation promise
+                    logger.debug(f"Navigation occurred on {call_action_name}.")
+                except Exception:
+                    logger.debug(f"No navigation occurred within timeout when calling {call_action_name}, that's OK, continuing.")
+                    
+            except Exception as e:
+                # If expect_event itself times out, that means no navigation occurred - that's OK
+                if "framenavigated" in str(e) and "exceeded" in str(e):
+                    logger.debug(f"No navigation occurred within timeout when calling {call_action_name}, that's OK, continuing.")
+                else:
+                    raise e
+        else:
+            # Some other action that probably a navigation is not expected
+            await action_handler(selector, optional_value)
+
 
-        action_handler(selector, optional_value)
         # Safely wait for timeout
-        self.page.wait_for_timeout(1.5 * 1000)
+        await self.page.wait_for_timeout(1.5 * 1000)
         logger.debug(f"Call action done in {time.time()-now:.2f}s")
 
-    def action_goto_url(self, selector=None, value=None):
+    async def action_goto_url(self, selector=None, value=None):
         if not value:
             logger.warning("No URL provided for goto_url action")
             return None
             
         now = time.time()
-        response = self.page.goto(value, timeout=0, wait_until='load')
+        response = await self.page.goto(value, timeout=0, wait_until='load')
         logger.debug(f"Time to goto URL {time.time()-now:.2f}s")
         return response
 
     # Incase they request to go back to the start
-    def action_goto_site(self, selector=None, value=None):
-        return self.action_goto_url(value=self.start_url)
+    async def action_goto_site(self, selector=None, value=None):
+        return await self.action_goto_url(value=re.sub(r'^source:', '', self.start_url, flags=re.IGNORECASE))
 
-    def action_click_element_containing_text(self, selector=None, value=''):
+    async def action_click_element_containing_text(self, selector=None, value=''):
         logger.debug("Clicking element containing text")
         if not value or not len(value.strip()):
             return
             
         elem = self.page.get_by_text(value)
-        if elem.count():
-            elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
+        if await elem.count():
+            await elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
 
 
-    def action_click_element_containing_text_if_exists(self, selector=None, value=''):
+    async def action_click_element_containing_text_if_exists(self, selector=None, value=''):
         logger.debug("Clicking element containing text if exists")
         if not value or not len(value.strip()):
             return
             
         elem = self.page.get_by_text(value)
-        logger.debug(f"Clicking element containing text - {elem.count()} elements found")
-        if elem.count():
-            elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
+        count = await elem.count()
+        logger.debug(f"Clicking element containing text - {count} elements found")
+        if count:
+            await elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
                 
 
-    def action_enter_text_in_field(self, selector, value):
+    async def action_enter_text_in_field(self, selector, value):
         if not selector or not len(selector.strip()):
             return
 
-        self.page.fill(selector, value, timeout=self.action_timeout)
+        await self.page.fill(selector, value, timeout=self.action_timeout)
 
-    def action_execute_js(self, selector, value):
+    async def action_execute_js(self, selector, value):
         if not value:
             return None
             
-        return self.page.evaluate(value)
+        return await self.page.evaluate(value)
 
-    def action_click_element(self, selector, value):
+    async def action_click_element(self, selector, value):
         logger.debug("Clicking element")
         if not selector or not len(selector.strip()):
             return
 
-        self.page.click(selector=selector, timeout=self.action_timeout + 20 * 1000, delay=randint(200, 500))
+        await self.page.click(selector=selector, timeout=self.action_timeout + 20 * 1000, delay=randint(200, 500))
 
-    def action_click_element_if_exists(self, selector, value):
+    async def action_click_element_if_exists(self, selector, value):
         import playwright._impl._errors as _api_types
         logger.debug("Clicking element if exists")
         if not selector or not len(selector.strip()):
             return
             
         try:
-            self.page.click(selector, timeout=self.action_timeout, delay=randint(200, 500))
+            await self.page.click(selector, timeout=self.action_timeout, delay=randint(200, 500))
         except _api_types.TimeoutError:
             return
         except _api_types.Error:
@@ -167,7 +190,7 @@ class steppable_browser_interface():
             return
                 
 
-    def action_click_x_y(self, selector, value):
+    async def action_click_x_y(self, selector, value):
         if not value or not re.match(r'^\s?\d+\s?,\s?\d+\s?$', value):
             logger.warning("'Click X,Y' step should be in the format of '100 , 90'")
             return
@@ -177,42 +200,42 @@ class steppable_browser_interface():
             x = int(float(x.strip()))
             y = int(float(y.strip()))
             
-            self.page.mouse.click(x=x, y=y, delay=randint(200, 500))
+            await self.page.mouse.click(x=x, y=y, delay=randint(200, 500))
                 
         except Exception as e:
             logger.error(f"Error parsing x,y coordinates: {str(e)}")
 
-    def action__select_by_option_text(self, selector, value):
+    async def action__select_by_option_text(self, selector, value):
         if not selector or not len(selector.strip()):
             return
 
-        self.page.select_option(selector, label=value, timeout=self.action_timeout)
+        await self.page.select_option(selector, label=value, timeout=self.action_timeout)
 
-    def action_scroll_down(self, selector, value):
+    async def action_scroll_down(self, selector, value):
         # Some sites this doesnt work on for some reason
-        self.page.mouse.wheel(0, 600)
-        self.page.wait_for_timeout(1000)
+        await self.page.mouse.wheel(0, 600)
+        await self.page.wait_for_timeout(1000)
 
-    def action_wait_for_seconds(self, selector, value):
+    async def action_wait_for_seconds(self, selector, value):
         try:
             seconds = float(value.strip()) if value else 1.0
-            self.page.wait_for_timeout(seconds * 1000)
+            await self.page.wait_for_timeout(seconds * 1000)
         except (ValueError, TypeError) as e:
             logger.error(f"Invalid value for wait_for_seconds: {str(e)}")
 
-    def action_wait_for_text(self, selector, value):
+    async def action_wait_for_text(self, selector, value):
         if not value:
             return
             
         import json
         v = json.dumps(value)
-        self.page.wait_for_function(
+        await self.page.wait_for_function(
             f'document.querySelector("body").innerText.includes({v});',
             timeout=30000
         )
             
 
-    def action_wait_for_text_in_element(self, selector, value):
+    async def action_wait_for_text_in_element(self, selector, value):
         if not selector or not value:
             return
             
@@ -220,49 +243,49 @@ class steppable_browser_interface():
         s = json.dumps(selector)
         v = json.dumps(value)
         
-        self.page.wait_for_function(
+        await self.page.wait_for_function(
             f'document.querySelector({s}).innerText.includes({v});',
             timeout=30000
         )
 
     # @todo - in the future make some popout interface to capture what needs to be set
     # https://playwright.dev/python/docs/api/class-keyboard
-    def action_press_enter(self, selector, value):
-        self.page.keyboard.press("Enter", delay=randint(200, 500))
+    async def action_press_enter(self, selector, value):
+        await self.page.keyboard.press("Enter", delay=randint(200, 500))
             
 
-    def action_press_page_up(self, selector, value):
-        self.page.keyboard.press("PageUp", delay=randint(200, 500))
+    async def action_press_page_up(self, selector, value):
+        await self.page.keyboard.press("PageUp", delay=randint(200, 500))
 
-    def action_press_page_down(self, selector, value):
-        self.page.keyboard.press("PageDown", delay=randint(200, 500))
+    async def action_press_page_down(self, selector, value):
+        await self.page.keyboard.press("PageDown", delay=randint(200, 500))
 
-    def action_check_checkbox(self, selector, value):
+    async def action_check_checkbox(self, selector, value):
         if not selector:
             return
 
-        self.page.locator(selector).check(timeout=self.action_timeout)
+        await self.page.locator(selector).check(timeout=self.action_timeout)
 
-    def action_uncheck_checkbox(self, selector, value):
+    async def action_uncheck_checkbox(self, selector, value):
         if not selector:
             return
             
-        self.page.locator(selector).uncheck(timeout=self.action_timeout)
+        await self.page.locator(selector).uncheck(timeout=self.action_timeout)
             
 
-    def action_remove_elements(self, selector, value):
+    async def action_remove_elements(self, selector, value):
         """Removes all elements matching the given selector from the DOM."""
         if not selector:
             return
             
-        self.page.locator(selector).evaluate_all("els => els.forEach(el => el.remove())")
+        await self.page.locator(selector).evaluate_all("els => els.forEach(el => el.remove())")
 
-    def action_make_all_child_elements_visible(self, selector, value):
+    async def action_make_all_child_elements_visible(self, selector, value):
         """Recursively makes all child elements inside the given selector fully visible."""
         if not selector:
             return
             
-        self.page.locator(selector).locator("*").evaluate_all("""
+        await self.page.locator(selector).locator("*").evaluate_all("""
             els => els.forEach(el => {
                 el.style.display = 'block';   // Forces it to be displayed
                 el.style.visibility = 'visible';   // Ensures it's not hidden
@@ -307,21 +330,22 @@ class browsersteps_live_ui(steppable_browser_interface):
         self.playwright_browser = playwright_browser
         self.start_url = start_url
         self._is_cleaned_up = False
-        if self.context is None:
-            self.connect(proxy=proxy)
+        self.proxy = proxy
+        # Note: connect() is now async and must be called separately
 
     def __del__(self):
         # Ensure cleanup happens if object is garbage collected
-        self.cleanup()
+        # Note: cleanup is now async, so we can only mark as cleaned up here
+        self._is_cleaned_up = True
 
     # Connect and setup a new context
-    def connect(self, proxy=None):
+    async def connect(self, proxy=None):
         # Should only get called once - test that
         keep_open = 1000 * 60 * 5
         now = time.time()
 
         # @todo handle multiple contexts, bind a unique id from the browser on each req?
-        self.context = self.playwright_browser.new_context(
+        self.context = await self.playwright_browser.new_context(
             accept_downloads=False,  # Should never be needed
             bypass_csp=True,  # This is needed to enable JavaScript execution on GitHub and others
             extra_http_headers=self.headers,
@@ -332,7 +356,7 @@ class browsersteps_live_ui(steppable_browser_interface):
             user_agent=manage_user_agent(headers=self.headers),
         )
 
-        self.page = self.context.new_page()
+        self.page = await self.context.new_page()
 
         # self.page.set_default_navigation_timeout(keep_open)
         self.page.set_default_timeout(keep_open)
@@ -342,13 +366,15 @@ class browsersteps_live_ui(steppable_browser_interface):
         self.page.on("console", lambda msg: print(f"Browser steps console - {msg.type}: {msg.text} {msg.args}"))
 
         logger.debug(f"Time to browser setup {time.time()-now:.2f}s")
-        self.page.wait_for_timeout(1 * 1000)
+        await self.page.wait_for_timeout(1 * 1000)
 
     def mark_as_closed(self):
         logger.debug("Page closed, cleaning up..")
-        self.cleanup()
+        # Note: This is called from a sync context (event handler)
+        # so we'll just mark as cleaned up and let __del__ handle the rest
+        self._is_cleaned_up = True
 
-    def cleanup(self):
+    async def cleanup(self):
         """Properly clean up all resources to prevent memory leaks"""
         if self._is_cleaned_up:
             return
@@ -359,7 +385,7 @@ class browsersteps_live_ui(steppable_browser_interface):
         if hasattr(self, 'page') and self.page is not None:
             try:
                 # Force garbage collection before closing
-                self.page.request_gc()
+                await self.page.request_gc()
             except Exception as e:
                 logger.debug(f"Error during page garbage collection: {str(e)}")
                 
@@ -370,7 +396,7 @@ class browsersteps_live_ui(steppable_browser_interface):
                 logger.debug(f"Error removing event listeners: {str(e)}")
                 
             try:
-                self.page.close()
+                await self.page.close()
             except Exception as e:
                 logger.debug(f"Error closing page: {str(e)}")
             
@@ -379,7 +405,7 @@ class browsersteps_live_ui(steppable_browser_interface):
         # Clean up context
         if hasattr(self, 'context') and self.context is not None:
             try:
-                self.context.close()
+                await self.context.close()
             except Exception as e:
                 logger.debug(f"Error closing context: {str(e)}")
             
@@ -401,12 +427,12 @@ class browsersteps_live_ui(steppable_browser_interface):
             
         return False
 
-    def get_current_state(self):
+    async def get_current_state(self):
         """Return the screenshot and interactive elements mapping, generally always called after action_()"""
         import importlib.resources
         import json
         # because we for now only run browser steps in playwright mode (not puppeteer mode)
-        from changedetectionio.content_fetchers.playwright import capture_full_page
+        from changedetectionio.content_fetchers.playwright import capture_full_page_async
 
         # Safety check - don't proceed if resources are cleaned up
         if self._is_cleaned_up or self.page is None:
@@ -416,29 +442,32 @@ class browsersteps_live_ui(steppable_browser_interface):
         xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text()
 
         now = time.time()
-        self.page.wait_for_timeout(1 * 1000)
+        await self.page.wait_for_timeout(1 * 1000)
 
         screenshot = None
         xpath_data = None
         
         try:
             # Get screenshot first
-            screenshot = capture_full_page(page=self.page)
+            screenshot = await capture_full_page_async(page=self.page)
+            if not screenshot:
+                logger.error("No screenshot was retrieved :((")
+
             logger.debug(f"Time to get screenshot from browser {time.time() - now:.2f}s")
 
             # Then get interactive elements
             now = time.time()
-            self.page.evaluate("var include_filters=''")
-            self.page.request_gc()
+            await self.page.evaluate("var include_filters=''")
+            await self.page.request_gc()
 
             scan_elements = 'a,button,input,select,textarea,i,th,td,p,li,h1,h2,h3,h4,div,span'
 
             MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
-            xpath_data = json.loads(self.page.evaluate(xpath_element_js, {
+            xpath_data = json.loads(await self.page.evaluate(xpath_element_js, {
                 "visualselector_xpath_selectors": scan_elements,
                 "max_height": MAX_TOTAL_HEIGHT
             }))
-            self.page.request_gc()
+            await self.page.request_gc()
 
             # Sort elements by size
             xpath_data['size_pos'] = sorted(xpath_data['size_pos'], key=lambda k: k['width'] * k['height'], reverse=True)
@@ -446,15 +475,21 @@ class browsersteps_live_ui(steppable_browser_interface):
             
         except Exception as e:
             logger.error(f"Error getting current state: {str(e)}")
+            # If the page has navigated (common with logins) then the context is destroyed on navigation, continue
+            # I'm not sure that this is required anymore because we have the "expect navigation wrapper" at the top
+            if "Execution context was destroyed" in str(e):
+                logger.debug("Execution context was destroyed, most likely because of navigation, continuing...")
+            pass
+
             # Attempt recovery - force garbage collection
             try:
-                self.page.request_gc()
+                await self.page.request_gc()
             except:
                 pass
         
         # Request garbage collection one final time
         try:
-            self.page.request_gc()
+            await self.page.request_gc()
         except:
             pass
             

changedetectionio/blueprint/browser_steps/nonContext.py

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

changedetectionio/blueprint/imports/__init__.py

@@ -1,6 +1,7 @@
 from flask import Blueprint, request, redirect, url_for, flash, render_template
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
+from changedetectionio import worker_handler
 from changedetectionio.blueprint.imports.importer import (
     import_url_list, 
     import_distill_io_json, 
@@ -24,7 +25,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                 importer_handler = import_url_list()
                 importer_handler.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', 'text_json_diff'))
                 for uuid in importer_handler.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                    worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
                 if len(importer_handler.remaining_data) == 0:
                     return redirect(url_for('watchlist.index'))
@@ -37,7 +38,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                 d_importer = import_distill_io_json()
                 d_importer.run(data=request.values.get('distill-io'), flash=flash, datastore=datastore)
                 for uuid in d_importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                    worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
             # XLSX importer
             if request.files and request.files.get('xlsx_file'):
@@ -60,7 +61,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                     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}))
+                    worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
         # Could be some remaining, or we could be on GET
         form = forms.importForm(formdata=request.form if request.method == 'POST' else None)

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -4,6 +4,7 @@ from flask import Blueprint, flash, redirect, url_for
 from flask_login import login_required
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio import queuedWatchMetaData
+from changedetectionio import worker_handler
 from queue import PriorityQueue
 
 PRICE_DATA_TRACK_ACCEPT = 'accepted'
@@ -19,7 +20,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
         datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_ACCEPT
         datastore.data['watching'][uuid]['processor'] = 'restock_diff'
         datastore.data['watching'][uuid].clear_watch()
-        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+        worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
         return redirect(url_for("watchlist.index"))
 
     @login_required

changedetectionio/blueprint/rss/blueprint.py

@@ -108,10 +108,13 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
                 fe.link(link=diff_link)
 
-                # @todo watch should be a getter - watch.get('title') (internally if URL else..)
+                # Same logic as watch-overview.html
+                if datastore.data['settings']['application']['ui'].get('use_page_title_in_list') or watch.get('use_page_title_in_list'):
+                    watch_label = watch.label
+                else:
+                    watch_label = watch.get('url')
 
-                watch_title = watch.get('title') if watch.get('title') else watch.get('url')
-                fe.title(title=watch_title)
+                fe.title(title=watch_label)
                 try:
 
                     html_diff = diff.render_diff(previous_version_file_contents=watch.get_history_snapshot(dates[-2]),
@@ -127,7 +130,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 # @todo User could decide if <link> goes to the diff page, or to the watch link
                 rss_template = "<html><body>\n<h4><a href=\"{{watch_url}}\">{{watch_title}}</a></h4>\n<p>{{html_diff}}</p>\n</body></html>\n"
 
-                content = jinja_render(template_str=rss_template, watch_title=watch_title, html_diff=html_diff, watch_url=watch.link)
+                content = jinja_render(template_str=rss_template, watch_title=watch_label, html_diff=html_diff, watch_url=watch.link)
 
                 # Out of range chars could also break feedgen
                 if scan_invalid_chars_in_rss(content):

changedetectionio/blueprint/settings/__init__.py

@@ -67,7 +67,32 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                     del (app_update['password'])
 
                 datastore.data['settings']['application'].update(app_update)
+                
+                # Handle dynamic worker count adjustment
+                old_worker_count = datastore.data['settings']['requests'].get('workers', 1)
+                new_worker_count = form.data['requests'].get('workers', 1)
+                
                 datastore.data['settings']['requests'].update(form.data['requests'])
+                
+                # Adjust worker count if it changed
+                if new_worker_count != old_worker_count:
+                    from changedetectionio import worker_handler
+                    from changedetectionio.flask_app import update_q, notification_q, app, datastore as ds
+                    
+                    result = worker_handler.adjust_async_worker_count(
+                        new_count=new_worker_count,
+                        update_q=update_q,
+                        notification_q=notification_q,
+                        app=app,
+                        datastore=ds
+                    )
+                    
+                    if result['status'] == 'success':
+                        flash(f"Worker count adjusted: {result['message']}", 'notice')
+                    elif result['status'] == 'not_supported':
+                        flash("Dynamic worker adjustment not supported for sync workers", 'warning')
+                    elif result['status'] == 'error':
+                        flash(f"Error adjusting workers: {result['message']}", 'error')
 
                 if not os.getenv("SALTED_PASS", False) and len(form.application.form.password.encrypted_password):
                     datastore.data['settings']['application']['password'] = form.application.form.password.encrypted_password

changedetectionio/blueprint/settings/templates/settings.html

@@ -1,7 +1,7 @@
 {% extends 'base.html' %}
 
 {% block content %}
-{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_time_schedule_form %}
+{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_time_schedule_form, render_ternary_field %}
 {% from '_common_fields.html' import render_common_settings_form %}
 <script>
     const notification_base_url="{{url_for('ui.ui_notification.ajax_callback_send_notification_test', mode="global-settings")}}";
@@ -75,18 +75,10 @@
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.rss_hide_muted_watches) }}
                     </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.application.form.pager_size) }}
-                        <span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
-                    </div>
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.rss_content_format) }}
                         <span class="pure-form-message-inline">Love RSS? Does your reader support HTML? Set it here</span>
                     </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.application.form.extract_title_as_title) }}
-                        <span class="pure-form-message-inline">Note: This will automatically apply to all existing watches.</span>
-                    </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.empty_pages_are_a_change) }}
                         <span class="pure-form-message-inline">When a request returns no content, or the HTML does not contain any text, is this considered a change?</span>
@@ -135,6 +127,12 @@
                         {{ render_field(form.application.form.webdriver_delay) }}
                     </div>
                 </fieldset>
+                <div class="pure-control-group">
+                    {{ render_field(form.requests.form.workers) }}
+                    {% set worker_info = get_worker_status_info() %}
+                    <span class="pure-form-message-inline">Number of concurrent workers to process watches. More workers = faster processing but higher memory usage.<br>
+                    Currently running: <strong>{{ worker_info.count }}</strong> operational {{ worker_info.type }} workers{% if worker_info.active_workers > 0 %} ({{ worker_info.active_workers }} actively processing){% endif %}.</span>
+                </div>
                 <div class="pure-control-group inline-radio">
                     {{ render_field(form.requests.form.default_ua) }}
                     <span class="pure-form-message-inline">
@@ -193,11 +191,17 @@ nav
                         </ul>
                      </span>
                     </fieldset>
+                    <fieldset class="pure-group">
+                        {{ render_checkbox_field(form.application.form.strip_ignored_lines) }}
+                        <span class="pure-form-message-inline">Remove any text that appears in the "Ignore text" from the output (otherwise its just ignored for change-detection)<br>
+                        <i>Note:</i> Changing this will change the status of your existing watches, possibly trigger alerts etc.
+                        </span>
+                    </fieldset>
            </div>
 
             <div class="tab-pane-inner" id="api">
                 <h4>API Access</h4>
-                <p>Drive your changedetection.io via API, More about <a href="https://github.com/dgtlmoon/changedetection.io/wiki/API-Reference">API access here</a></p>
+                <p>Drive your changedetection.io via API, More about <a href="https://changedetection.io/docs/api_v1/index.html">API access and examples here</a>.</p>
 
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.api_access_token_enabled) }}
@@ -247,7 +251,19 @@ nav
                     <span class="pure-form-message-inline">Enable this setting to open the diff page in a new tab. If disabled, the diff page will open in the current tab.</span>
                 </div>
                 <div class="pure-control-group">
-                    <span class="pure-form-message-inline">Enable realtime updates in the UI</span>
+                    {{ render_checkbox_field(form.application.form.ui.form.socket_io_enabled, class="socket_io_enabled") }}
+                    <span class="pure-form-message-inline">Realtime UI Updates Enabled - (Restart required if this is changed)</span>
+                </div>
+                <div class="pure-control-group">
+                    {{ render_checkbox_field(form.application.form.ui.form.favicons_enabled, class="") }}
+                    <span class="pure-form-message-inline">Enable or Disable Favicons next to the watch list</span>
+                </div>
+                <div class="pure-control-group">
+                    {{ render_checkbox_field(form.application.form.ui.use_page_title_in_list) }}
+                </div>
+                <div class="pure-control-group">
+                    {{ render_field(form.application.form.pager_size) }}
+                    <span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
                 </div>
 
             </div>
@@ -313,8 +329,8 @@ nav
             <div id="actions">
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}
-                    <a href="{{url_for('watchlist.index')}}" class="pure-button button-small button-cancel">Back</a>
-                    <a href="{{url_for('ui.clear_all_history')}}" class="pure-button button-small button-error">Clear Snapshot History</a>
+                    <a href="{{url_for('watchlist.index')}}" class="pure-button button-cancel">Back</a>
+                    <a href="{{url_for('ui.clear_all_history')}}" class="pure-button button-error">Clear Snapshot History</a>
                 </div>
             </div>
         </form>

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

@@ -1,6 +1,6 @@
 {% extends 'base.html' %}
 {% block content %}
-{% from '_helpers.html' import render_field, render_checkbox_field, render_button %}
+{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_ternary_field %}
 {% from '_common_fields.html' import render_common_settings_form %}
 <script>
     const notification_base_url="{{url_for('ui.ui_notification.ajax_callback_send_notification_test', mode="group-settings")}}";
@@ -64,7 +64,7 @@
             <div class="tab-pane-inner" id="notifications">
                 <fieldset>
                     <div  class="pure-control-group inline-radio">
-                      {{ render_checkbox_field(form.notification_muted) }}
+                      {{ render_ternary_field(form.notification_muted, BooleanField=True) }}
                     </div>
                     {% if 1 %}
                     <div class="pure-control-group inline-radio">

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

@@ -10,7 +10,7 @@
             <legend>Add a new organisational tag</legend>
             <div id="watch-add-wrapper-zone">
                 <div>
-                    {{ render_simple_field(form.name, placeholder="watch label / tag") }}
+                    {{ render_simple_field(form.name, placeholder="Watch group / tag") }}
                 </div>
                 <div>
                     {{ render_simple_field(form.save_button, title="Save" ) }}

changedetectionio/blueprint/ui/__init__.py

@@ -1,15 +1,112 @@
 import time
 from flask import Blueprint, request, redirect, url_for, flash, render_template, session
 from loguru import logger
-from functools import wraps
 
-from changedetectionio.blueprint.ui.ajax import constuct_ui_ajax_blueprint
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.blueprint.ui.edit import construct_blueprint as construct_edit_blueprint
 from changedetectionio.blueprint.ui.notification import construct_blueprint as construct_notification_blueprint
 from changedetectionio.blueprint.ui.views import construct_blueprint as construct_views_blueprint
 
-def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_update_threads, queuedWatchMetaData, watch_check_update):
+def _handle_operations(op, uuids, datastore, worker_handler, update_q, queuedWatchMetaData, watch_check_update, extra_data=None, emit_flash=True):
+    from flask import request, flash
+
+    if op == 'delete':
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.delete(uuid)
+        if emit_flash:
+            flash(f"{len(uuids)} watches deleted")
+
+    elif op == 'pause':
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.data['watching'][uuid]['paused'] = True
+        if emit_flash:
+            flash(f"{len(uuids)} watches paused")
+
+    elif op == 'unpause':
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.data['watching'][uuid.strip()]['paused'] = False
+        if emit_flash:
+            flash(f"{len(uuids)} watches unpaused")
+
+    elif (op == 'mark-viewed'):
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.set_last_viewed(uuid, int(time.time()))
+        if emit_flash:
+            flash(f"{len(uuids)} watches updated")
+
+    elif (op == 'mute'):
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.data['watching'][uuid]['notification_muted'] = True
+        if emit_flash:
+            flash(f"{len(uuids)} watches muted")
+
+    elif (op == 'unmute'):
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.data['watching'][uuid]['notification_muted'] = False
+        if emit_flash:
+            flash(f"{len(uuids)} watches un-muted")
+
+    elif (op == 'recheck'):
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                # Recheck and require a full reprocessing
+                worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+        if emit_flash:
+            flash(f"{len(uuids)} watches queued for rechecking")
+
+    elif (op == 'clear-errors'):
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.data['watching'][uuid]["last_error"] = False
+        if emit_flash:
+            flash(f"{len(uuids)} watches errors cleared")
+
+    elif (op == 'clear-history'):
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.clear_watch_history(uuid)
+        if emit_flash:
+            flash(f"{len(uuids)} watches cleared/reset.")
+
+    elif (op == 'notification-default'):
+        from changedetectionio.notification import (
+            default_notification_format_for_watch
+        )
+        for uuid in uuids:
+            if datastore.data['watching'].get(uuid):
+                datastore.data['watching'][uuid]['notification_title'] = None
+                datastore.data['watching'][uuid]['notification_body'] = None
+                datastore.data['watching'][uuid]['notification_urls'] = []
+                datastore.data['watching'][uuid]['notification_format'] = default_notification_format_for_watch
+        if emit_flash:
+            flash(f"{len(uuids)} watches set to use default notification settings")
+
+    elif (op == 'assign-tag'):
+        op_extradata = extra_data
+        if op_extradata:
+            tag_uuid = datastore.add_tag(title=op_extradata)
+            if op_extradata and tag_uuid:
+                for uuid in uuids:
+                    if datastore.data['watching'].get(uuid):
+                        # Bug in old versions caused by bad edit page/tag handler
+                        if isinstance(datastore.data['watching'][uuid]['tags'], str):
+                            datastore.data['watching'][uuid]['tags'] = []
+
+                        datastore.data['watching'][uuid]['tags'].append(tag_uuid)
+        if emit_flash:
+            flash(f"{len(uuids)} watches were tagged")
+
+    if uuids:
+        for uuid in uuids:
+            watch_check_update.send(watch_uuid=uuid)
+
+def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_handler, queuedWatchMetaData, watch_check_update):
     ui_blueprint = Blueprint('ui', __name__, template_folder="templates")
     
     # Register the edit blueprint
@@ -24,9 +121,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
     views_blueprint = construct_views_blueprint(datastore, update_q, queuedWatchMetaData, watch_check_update)
     ui_blueprint.register_blueprint(views_blueprint)
 
-    ui_ajax_blueprint = constuct_ui_ajax_blueprint(datastore, update_q, running_update_threads, queuedWatchMetaData, watch_check_update)
-    ui_blueprint.register_blueprint(ui_ajax_blueprint)
-
     # Import the login decorator
     from changedetectionio.auth_decorator import login_optionally_required
 
@@ -65,12 +159,20 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
     def mark_all_viewed():
         # Save the current newest history as the most recently viewed
         with_errors = request.args.get('with_errors') == "1"
+        tag_limit = request.args.get('tag')
+        logger.debug(f"Limiting to tag {tag_limit}")
+        now = int(time.time())
         for watch_uuid, watch in datastore.data['watching'].items():
             if with_errors and not watch.get('last_error'):
                 continue
-            datastore.set_last_viewed(watch_uuid, int(time.time()))
 
-        return redirect(url_for('watchlist.index'))
+            if tag_limit and ( not watch.get('tags') or tag_limit not in watch['tags'] ):
+                logger.debug(f"Skipping watch {watch_uuid}")
+                continue
+
+            datastore.set_last_viewed(watch_uuid, now)
+
+        return redirect(url_for('watchlist.index', tag=tag_limit))
 
     @ui_blueprint.route("/delete", methods=['GET'])
     @login_optionally_required
@@ -100,7 +202,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
         new_uuid = datastore.clone(uuid)
 
         if not datastore.data['watching'].get(uuid).get('paused'):
-            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
+            worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
 
         flash('Cloned, you are editing the new watch.')
 
@@ -116,13 +218,11 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
 
         i = 0
 
-        running_uuids = []
-        for t in running_update_threads:
-            running_uuids.append(t.current_uuid)
+        running_uuids = worker_handler.get_running_uuids()
 
         if uuid:
             if uuid not in running_uuids:
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
                 i += 1
 
         else:
@@ -139,7 +239,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
                         if tag != None and tag not in watch['tags']:
                             continue
 
-                        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
+                        worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
                         i += 1
 
         if i == 1:
@@ -156,93 +256,17 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
     def form_watch_list_checkbox_operations():
         op = request.form['op']
         uuids = [u.strip() for u in request.form.getlist('uuids') if u]
-
-        if (op == 'delete'):
-            for uuid in uuids:
-                if datastore.data['watching'].get(uuid):
-                    datastore.delete(uuid)
-            flash("{} watches deleted".format(len(uuids)))
-
-        elif (op == 'pause'):
-            for uuid in uuids:
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid]['paused'] = True
-            flash("{} watches paused".format(len(uuids)))
-
-        elif (op == 'unpause'):
-            for uuid in uuids:
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid.strip()]['paused'] = False
-            flash("{} watches unpaused".format(len(uuids)))
-
-        elif (op == 'mark-viewed'):
-            for uuid in uuids:
-                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:
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid]['notification_muted'] = True
-            flash("{} watches muted".format(len(uuids)))
-
-        elif (op == 'unmute'):
-            for uuid in uuids:
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid]['notification_muted'] = False
-            flash("{} watches un-muted".format(len(uuids)))
-
-        elif (op == 'recheck'):
-            for uuid in uuids:
-                if datastore.data['watching'].get(uuid):
-                    # Recheck and require a full reprocessing
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-            flash("{} watches queued for rechecking".format(len(uuids)))
-
-        elif (op == 'clear-errors'):
-            for uuid in uuids:
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid]["last_error"] = False
-            flash(f"{len(uuids)} watches errors cleared")
-
-        elif (op == 'clear-history'):
-            for uuid in uuids:
-                if datastore.data['watching'].get(uuid):
-                    datastore.clear_watch_history(uuid)
-            flash("{} watches cleared/reset.".format(len(uuids)))
-
-        elif (op == 'notification-default'):
-            from changedetectionio.notification import (
-                default_notification_format_for_watch
-            )
-            for uuid in uuids:
-                if datastore.data['watching'].get(uuid):
-                    datastore.data['watching'][uuid]['notification_title'] = None
-                    datastore.data['watching'][uuid]['notification_body'] = None
-                    datastore.data['watching'][uuid]['notification_urls'] = []
-                    datastore.data['watching'][uuid]['notification_format'] = default_notification_format_for_watch
-            flash("{} watches set to use default notification settings".format(len(uuids)))
-
-        elif (op == 'assign-tag'):
-            op_extradata = request.form.get('op_extradata', '').strip()
-            if op_extradata:
-                tag_uuid = datastore.add_tag(title=op_extradata)
-                if op_extradata and tag_uuid:
-                    for uuid in uuids:
-                        if datastore.data['watching'].get(uuid):
-                            # Bug in old versions caused by bad edit page/tag handler
-                            if isinstance(datastore.data['watching'][uuid]['tags'], str):
-                                datastore.data['watching'][uuid]['tags'] = []
-
-                            datastore.data['watching'][uuid]['tags'].append(tag_uuid)
-
-            flash(f"{len(uuids)} watches were tagged")
-
-        if uuids:
-            for uuid in uuids:
-#                with app.app_context():
-                watch_check_update.send(watch_uuid=uuid)
+        extra_data = request.form.get('op_extradata', '').strip()
+        _handle_operations(
+            datastore=datastore,
+            extra_data=extra_data,
+            queuedWatchMetaData=queuedWatchMetaData,
+            uuids=uuids,
+            worker_handler=worker_handler,
+            update_q=update_q,
+            watch_check_update=watch_check_update,
+            op=op,
+        )
 
         return redirect(url_for('watchlist.index'))
 

changedetectionio/blueprint/ui/ajax.py

@@ -1,35 +0,0 @@
-import time
-
-from blinker import signal
-from flask import Blueprint, request, redirect, url_for, flash, render_template, session
-
-
-from changedetectionio.store import ChangeDetectionStore
-
-def constuct_ui_ajax_blueprint(datastore: ChangeDetectionStore, update_q, running_update_threads, queuedWatchMetaData, watch_check_update):
-    ui_ajax_blueprint = Blueprint('ajax', __name__, template_folder="templates", url_prefix='/ajax')
-
-    # Import the login decorator
-    from changedetectionio.auth_decorator import login_optionally_required
-
-    @ui_ajax_blueprint.route("/toggle", methods=['POST'])
-    @login_optionally_required
-    def ajax_toggler():
-        op = request.values.get('op')
-        uuid = request.values.get('uuid')
-        if op and datastore.data['watching'].get(uuid):
-            if op == 'pause':
-                datastore.data['watching'][uuid].toggle_pause()
-            elif op == 'mute':
-                datastore.data['watching'][uuid].toggle_mute()
-            elif op == 'recheck':
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
-
-            watch_check_update = signal('watch_check_update')
-            if watch_check_update:
-                watch_check_update.send(watch_uuid=uuid)
-
-        return 'OK'
-
-
-    return ui_ajax_blueprint

changedetectionio/blueprint/ui/edit.py

@@ -9,6 +9,7 @@ from jinja2 import Environment, FileSystemLoader
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
 from changedetectionio.time_handler import is_within_schedule
+from changedetectionio import worker_handler
 
 def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
     edit_blueprint = Blueprint('ui_edit', __name__, template_folder="../ui/templates")
@@ -201,7 +202,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             #############################
             if not datastore.data['watching'][uuid].get('paused') and is_in_schedule:
                 # Queue the watch for immediate recheck, with a higher priority
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
             # Diff page [edit] link should go back to diff page
             if request.args.get("next") and request.args.get("next") == 'diff':
@@ -241,6 +242,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                 'available_timezones': sorted(available_timezones()),
                 'browser_steps_config': browser_step_ui_config,
                 'emailprefix': os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
+                'extra_classes': 'checking-now' if worker_handler.is_watch_running(uuid) else '',
                 'extra_notification_token_placeholder_info': datastore.get_unique_notification_token_placeholders_available(),
                 'extra_processor_config': form.extra_tab_content(),
                 'extra_title': f" - Edit - {watch.label}",

changedetectionio/blueprint/ui/templates/edit.html

@@ -1,6 +1,6 @@
 {% extends 'base.html' %}
 {% block content %}
-{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_time_schedule_form, playwright_warning, only_playwright_type_watches_warning, render_conditions_fieldlist_of_formfields_as_table %}
+{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_time_schedule_form, playwright_warning, only_playwright_type_watches_warning, render_conditions_fieldlist_of_formfields_as_table, render_ternary_field %}
 {% from '_common_fields.html' import render_common_settings_form %}
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='vis.js')}}" defer></script>
@@ -72,15 +72,16 @@
                         <div class="pure-form-message">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></div>
                         <div class="pure-form-message">Variables are supported in the URL (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
                     </div>
+                    <div class="pure-control-group">
+                        {{ 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 inline-radio">
                         {{ render_field(form.processor) }}
                     </div>
                     <div class="pure-control-group">
-                        {{ render_field(form.title, class="m-d") }}
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.tags) }}
-                        <span class="pure-form-message-inline">Organisational tag/group name used in the main listing page</span>
+                        {{ render_field(form.title, class="m-d", placeholder=watch.label) }}
+                        <span class="pure-form-message-inline">Automatically uses the page title if found, you can also use your own title/description here</span>
                     </div>
                     <div class="pure-control-group time-between-check border-fieldset">
 
@@ -101,15 +102,16 @@
                         </div>
 <br>
               </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.extract_title_as_title) }}
-                    </div>
+
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.filter_failure_notification_send) }}
                         <span class="pure-form-message-inline">
                          Sends a notification when the filter can no longer be seen on the page, good for knowing when the page changed and your filter will not work anymore.
                         </span>
                     </div>
+                    <div class="pure-control-group">
+                        {{ render_ternary_field(form.use_page_title_in_list) }}
+                    </div>
                 </fieldset>
             </div>
 
@@ -262,7 +264,7 @@ Math: {{ 1 + 1 }}") }}
             <div class="tab-pane-inner" id="notifications">
                 <fieldset>
                     <div  class="pure-control-group inline-radio">
-                      {{ render_checkbox_field(form.notification_muted) }}
+                      {{ render_ternary_field(form.notification_muted, BooleanField=true) }}
                     </div>
                     {% if watch_needs_selenium_or_playwright %}
                     <div class="pure-control-group inline-radio">
@@ -469,11 +471,11 @@ Math: {{ 1 + 1 }}") }}
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}
                     <a href="{{url_for('ui.form_delete', uuid=uuid)}}"
-                       class="pure-button button-small button-error ">Delete</a>
+                       class="pure-button button-error ">Delete</a>
                     {% if watch.history_n %}<a href="{{url_for('ui.clear_watch_history', uuid=uuid)}}"
-                       class="pure-button button-small button-error ">Clear History</a>{% endif %}
+                       class="pure-button button-error">Clear History</a>{% endif %}
                     <a href="{{url_for('ui.form_clone', uuid=uuid)}}"
-                       class="pure-button button-small ">Clone &amp; Edit</a>
+                       class="pure-button">Clone &amp; Edit</a>
                 </div>
             </div>
         </form>

changedetectionio/blueprint/ui/views.py

@@ -1,12 +1,12 @@
 from flask import Blueprint, request, redirect, url_for, flash, render_template, make_response, send_from_directory, abort
-from flask_login import current_user
 import os
 import time
-from copy import deepcopy
+from loguru import logger
 
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
 from changedetectionio import html_tools
+from changedetectionio import worker_handler
 
 def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData, watch_check_update):
     views_blueprint = Blueprint('ui_views', __name__, template_folder="../ui/templates")
@@ -77,9 +77,46 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
         return output
 
-    @views_blueprint.route("/diff/<string:uuid>", methods=['GET', 'POST'])
+    @views_blueprint.route("/diff/<string:uuid>", methods=['POST'])
     @login_optionally_required
-    def diff_history_page(uuid):
+    def diff_history_page_build_report(uuid):
+        from changedetectionio import forms
+
+        # More for testing, possible to return the first/only
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+
+        try:
+            watch = datastore.data['watching'][uuid]
+        except KeyError:
+            flash("No history found for the specified link, bad link?", "error")
+            return redirect(url_for('watchlist.index'))
+
+        # For submission of requesting an extract
+        extract_form = forms.extractDataForm(formdata=request.form,
+                                             data={'extract_regex': request.form.get('extract_regex', '')}
+                                             )
+        if not extract_form.validate():
+            flash("An error occurred, please see below.", "error")
+            return _render_diff_template(uuid, extract_form)
+
+        else:
+            extract_regex = request.form.get('extract_regex', '').strip()
+            output = watch.extract_regex_from_all_history(extract_regex)
+            if output:
+                watch_dir = os.path.join(datastore.datastore_path, uuid)
+                response = make_response(send_from_directory(directory=watch_dir, path=output, as_attachment=True))
+                response.headers['Content-type'] = 'text/csv'
+                response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+                response.headers['Pragma'] = 'no-cache'
+                response.headers['Expires'] = "0"
+                return response
+
+            flash('No matches found while scanning all of the watch history for that RegEx.', 'error')
+        return redirect(url_for('ui.ui_views.diff_history_page', uuid=uuid) + '#extract')
+
+    def _render_diff_template(uuid, extract_form=None):
+        """Helper function to render the diff template with all required data"""
         from changedetectionio import forms
 
         # More for testing, possible to return the first/only
@@ -93,62 +130,36 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             flash("No history found for the specified link, bad link?", "error")
             return redirect(url_for('watchlist.index'))
 
-        # For submission of requesting an extract
-        extract_form = forms.extractDataForm(request.form)
-        if request.method == 'POST':
-            if not extract_form.validate():
-                flash("An error occurred, please see below.", "error")
-
-            else:
-                extract_regex = request.form.get('extract_regex').strip()
-                output = watch.extract_regex_from_all_history(extract_regex)
-                if output:
-                    watch_dir = os.path.join(datastore.datastore_path, uuid)
-                    response = make_response(send_from_directory(directory=watch_dir, path=output, as_attachment=True))
-                    response.headers['Content-type'] = 'text/csv'
-                    response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
-                    response.headers['Pragma'] = 'no-cache'
-                    response.headers['Expires'] = 0
-                    return response
-
-                flash('Nothing matches that RegEx', 'error')
-                redirect(url_for('ui_views.diff_history_page', uuid=uuid)+'#extract')
+        # Use provided form or create a new one
+        if extract_form is None:
+            extract_form = forms.extractDataForm(formdata=request.form,
+                                                 data={'extract_regex': request.form.get('extract_regex', '')}
+                                                 )
 
         history = watch.history
         dates = list(history.keys())
 
-        if len(dates) < 2:
-            flash("Not enough saved change detection snapshots to produce a report.", "error")
-            return redirect(url_for('watchlist.index'))
+        # If a "from_version" was requested, then find it (or the closest one)
+        # Also set "from version" to be the closest version to the one that was last viewed.
 
-        # Save the current newest history as the most recently viewed
-        datastore.set_last_viewed(uuid, time.time())
+        best_last_viewed_timestamp = watch.get_from_version_based_on_last_viewed
+        from_version_timestamp = best_last_viewed_timestamp if best_last_viewed_timestamp else dates[-2]
+        from_version = request.args.get('from_version', from_version_timestamp )
 
-        # Read as binary and force decode as UTF-8
-        # Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
-        from_version = request.args.get('from_version')
-        from_version_index = -2  # second newest
-        if from_version and from_version in dates:
-            from_version_index = dates.index(from_version)
-        else:
-            from_version = dates[from_version_index]
+        # Use the current one if nothing was specified
+        to_version = request.args.get('to_version', str(dates[-1]))
 
         try:
-            from_version_file_contents = watch.get_history_snapshot(dates[from_version_index])
+            to_version_file_contents = watch.get_history_snapshot(timestamp=to_version)
         except Exception as e:
-            from_version_file_contents = f"Unable to read to-version at index {dates[from_version_index]}.\n"
-
-        to_version = request.args.get('to_version')
-        to_version_index = -1
-        if to_version and to_version in dates:
-            to_version_index = dates.index(to_version)
-        else:
-            to_version = dates[to_version_index]
+            logger.error(f"Unable to read watch history to-version for version {to_version}: {str(e)}")
+            to_version_file_contents = f"Unable to read to-version at {to_version}.\n"
 
         try:
-            to_version_file_contents = watch.get_history_snapshot(dates[to_version_index])
+            from_version_file_contents = watch.get_history_snapshot(timestamp=from_version)
         except Exception as e:
-            to_version_file_contents = "Unable to read to-version at index{}.\n".format(dates[to_version_index])
+            logger.error(f"Unable to read watch history from-version for version {from_version}: {str(e)}")
+            from_version_file_contents = f"Unable to read to-version {from_version}.\n"
 
         screenshot_url = watch.get_screenshot()
 
@@ -162,7 +173,9 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
         if datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False):
             password_enabled_and_share_is_off = not datastore.data['settings']['application'].get('shared_diff_access')
 
-        output = render_template("diff.html",
+        datastore.set_last_viewed(uuid, time.time())
+
+        return render_template("diff.html",
                                  current_diff_url=watch['url'],
                                  from_version=str(from_version),
                                  to_version=str(to_version),
@@ -185,7 +198,10 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                                  watch_a=watch
                                  )
 
-        return output
+    @views_blueprint.route("/diff/<string:uuid>", methods=['GET'])
+    @login_optionally_required
+    def diff_history_page(uuid):
+        return _render_diff_template(uuid)
 
     @views_blueprint.route("/form/add/quickwatch", methods=['POST'])
     @login_optionally_required
@@ -212,7 +228,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                 return redirect(url_for('ui.ui_edit.edit_page', uuid=new_uuid, unpause_on_save=1, tag=request.args.get('tag')))
             else:
                 # Straight into the queue.
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
+                worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
                 flash("Watch added.")
 
         return redirect(url_for('watchlist.index', tag=request.args.get('tag','')))

changedetectionio/blueprint/watchlist/__init__.py

@@ -44,12 +44,16 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
         # Sort by last_changed and add the uuid which is usually the key..
         sorted_watches = []
         with_errors = request.args.get('with_errors') == "1"
+        unread_only = request.args.get('unread') == "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 unread_only and (watch.viewed or watch.last_changed == 0) :
+                continue
+
             if active_tag_uuid and not active_tag_uuid in watch['tags']:
                     continue
             if watch.get('last_error'):
@@ -78,13 +82,11 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             active_tag=active_tag,
             active_tag_uuid=active_tag_uuid,
             app_rss_token=datastore.data['settings']['application'].get('rss_access_token'),
-            ajax_toggle_url=url_for('ui.ajax.ajax_toggler'),
             datastore=datastore,
             errored_count=errored_count,
             form=form,
             guid=datastore.data['app_guid'],
             has_proxies=datastore.proxy_list,
-            has_unviewed=datastore.has_unviewed,
             hosted_sticky=os.getenv("SALTED_PASS", False) == False,
             now_time_server=round(time.time()),
             pagination=pagination,
@@ -94,6 +96,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             sort_order=request.args.get('order') if request.args.get('order') else request.cookies.get('order'),
             system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),
             tags=sorted_tags,
+            unread_changes_count=datastore.unread_changes_count,
             watches=sorted_watches
         )
 

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

@@ -1,11 +1,16 @@
-{% extends 'base.html' %}
-{% block content %}
-{% from '_helpers.html' import render_simple_field, render_field, render_nolabel_field, sort_by_title %}
+{%- extends 'base.html' -%}
+{%- block content -%}
+{%- from '_helpers.html' import render_simple_field, render_field, render_nolabel_field, sort_by_title -%}
 <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
 <script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
 <script>let nowtimeserver={{ now_time_server }};</script>
-<script>let ajax_toggle_url="{{ ajax_toggle_url }}";</script>
-
+<script>let favicon_baseURL="{{ url_for('static_content', group='favicon', filename="PLACEHOLDER")}}";</script>
+<script>
+// Initialize Feather icons after the page loads
+document.addEventListener('DOMContentLoaded', function() {
+    feather.replace();
+});
+</script>
 <style>
 .checking-now .last-checked {
     background-image: linear-gradient(to bottom, transparent 0%, rgba(0,0,0,0.05) 40%, rgba(0,0,0,0.1) 100%);
@@ -14,19 +19,20 @@
     transition: background-size 0.9s ease
 }
 </style>
-<div class="box">
+<div class="box" id="form-quick-watch-add">
 
     <form class="pure-form" action="{{ url_for('ui.ui_views.form_quick_watch_add', tag=active_tag_uuid) }}" method="POST" id="new-watch-form">
         <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
         <fieldset>
-            <legend>Add a new change detection watch</legend>
+            <legend>Add a new web page change detection watch</legend>
             <div id="watch-add-wrapper-zone">
-
                     {{ render_nolabel_field(form.url, placeholder="https://...", required=true) }}
-                    {{ render_nolabel_field(form.tags, value=active_tag.title if active_tag_uuid else '', placeholder="watch label / tag") }}
                     {{ render_nolabel_field(form.watch_submit_button, title="Watch this URL!" ) }}
                     {{ render_nolabel_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
             </div>
+            <div id="watch-group-tag">
+               {{ render_field(form.tags, value=active_tag.title if active_tag_uuid else '', placeholder="Watch group / tag", class="transparent-field") }}
+            </div>
             <div id="quick-watch-processor-type">
                 {{ render_simple_field(form.processor) }}
             </div>
@@ -34,144 +40,182 @@
         </fieldset>
         <span style="color:#eee; font-size: 80%;"><img alt="Create a shareable link" style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" > Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></span>
     </form>
-
+</div>
+<div class="box">
     <form class="pure-form" action="{{ url_for('ui.form_watch_list_checkbox_operations') }}" method="POST" id="watch-list-form">
     <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
     <input type="hidden" id="op_extradata" name="op_extradata" value="" >
     <div id="checkbox-operations">
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="pause">Pause</button>
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="unpause">UnPause</button>
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="mute">Mute</button>
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="unmute">UnMute</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="recheck">Recheck</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="assign-tag" id="checkbox-assign-tag">Tag</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="mark-viewed">Mark viewed</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default">Use default notification</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="clear-errors">Clear errors</button>
-        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="clear-history">Clear/reset history</button>
-        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="delete">Delete</button>
+        <button class="pure-button button-secondary button-xsmall"  name="op" value="pause"><i data-feather="pause" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>Pause</button>
+        <button class="pure-button button-secondary button-xsmall"  name="op" value="unpause"><i data-feather="play" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>UnPause</button>
+        <button class="pure-button button-secondary button-xsmall"  name="op" value="mute"><i data-feather="volume-x" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>Mute</button>
+        <button class="pure-button button-secondary button-xsmall"  name="op" value="unmute"><i data-feather="volume-2" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>UnMute</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="recheck"><i data-feather="refresh-cw" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>Recheck</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="assign-tag" id="checkbox-assign-tag"><i data-feather="tag" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>Tag</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="mark-viewed"><i data-feather="eye" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>Mark viewed</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default"><i data-feather="bell" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>Use default notification</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="clear-errors"><i data-feather="x-circle" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>Clear errors</button>
+        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="clear-history"><i data-feather="trash-2" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>Clear/reset history</button>
+        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="delete"><i data-feather="trash" style="width: 14px; height: 14px; stroke: white; margin-right: 4px;"></i>Delete</button>
     </div>
-    {% if watches|length >= pagination.per_page %}
+    {%- 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 %}
+    {%- endif -%}
+    {%- if search_q -%}<div id="search-result-info">Searching "<strong><i>{{search_q}}</i></strong>"</div>{%- endif -%}
     <div>
         <a href="{{url_for('watchlist.index')}}" class="pure-button button-tag {{'active' if not active_tag_uuid }}">All</a>
 
     <!-- tag list -->
-    {% for uuid, tag in tags %}
-        {% if tag != "" %}
+    {%- for uuid, tag in tags -%}
+        {%- if tag != "" -%}
             <a href="{{url_for('watchlist.index', tag=uuid) }}" class="pure-button button-tag {{'active' if active_tag_uuid == uuid }}">{{ tag.title }}</a>
-        {% endif %}
-    {% endfor %}
+        {%- endif -%}
+    {%- endfor -%}
     </div>
 
-    {% set sort_order = sort_order or 'asc' %}
-    {% set sort_attribute = sort_attribute or 'last_changed'  %}
-    {% set pagination_page = request.args.get('page', 0) %}
-    {% set cols_required = 6 %}
-    {% set any_has_restock_price_processor = datastore.any_watches_have_processor_by_name("restock_diff") %}
-    {% if any_has_restock_price_processor %}
-        {% set cols_required = cols_required + 1 %}
-    {% endif %}
-
-    <div id="watch-table-wrapper">
-
-        <table class="pure-table pure-table-striped watch-table">
+    {%- set sort_order = sort_order or 'asc' -%}
+    {%- set sort_attribute = sort_attribute or 'last_changed'  -%}
+    {%- set pagination_page = request.args.get('page', 0) -%}
+    {%- set cols_required = 6 -%}
+    {%- set any_has_restock_price_processor = datastore.any_watches_have_processor_by_name("restock_diff") -%}
+    {%- if any_has_restock_price_processor -%}
+        {%- set cols_required = cols_required + 1 -%}
+    {%- endif -%}
+    {%- set ui_settings = datastore.data['settings']['application']['ui'] -%}
+    {%- set wrapper_classes = [
+        'has-unread-changes' if unread_changes_count else '',
+        'has-error' if errored_count else '',
+    ] -%}
+    <div id="watch-table-wrapper" class="{{ wrapper_classes | reject('equalto', '') | join(' ') }}">
+        {%- set table_classes = [
+            'favicon-enabled' if 'favicons_enabled' not in ui_settings or ui_settings['favicons_enabled'] else 'favicon-not-enabled',
+        ] -%}
+        <table class="pure-table pure-table-striped watch-table {{ table_classes | reject('equalto', '') | join(' ') }}">
             <thead>
             <tr>
-                {% set link_order = "desc" if sort_order  == 'asc' else "asc" %}
-                {% set arrow_span = "" %}
+                {%- set link_order = "desc" if sort_order  == 'asc' else "asc" -%}
+                {%- set arrow_span = "" -%}
                 <th><input style="vertical-align: middle" type="checkbox" id="check-all" > <a class="{{ 'active '+link_order if sort_attribute == 'date_created' else 'inactive' }}"  href="{{url_for('watchlist.index', sort='date_created', order=link_order, tag=active_tag_uuid)}}"># <span class='arrow {{link_order}}'></span></a></th>
-                <th class="empty-cell"></th>
+                <th>
+                    <a class="{{ 'active '+link_order if sort_attribute == 'paused' else 'inactive' }}" href="{{url_for('watchlist.index', sort='paused', order=link_order, tag=active_tag_uuid)}}"><i data-feather="pause" style="vertical-align: bottom; width: 14px; height: 14px;  margin-right: 4px;"></i><span class='arrow {{link_order}}'></span></a>
+                    &nbsp;
+                    <a class="{{ 'active '+link_order if sort_attribute == 'notification_muted' else 'inactive' }}" href="{{url_for('watchlist.index', sort='notification_muted', order=link_order, tag=active_tag_uuid)}}"><i data-feather="volume-2" style="vertical-align: bottom; width: 14px; height: 14px;  margin-right: 4px;"></i><span class='arrow {{link_order}}'></span></a>
+                </th>
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('watchlist.index', sort='label', order=link_order, tag=active_tag_uuid)}}">Website <span class='arrow {{link_order}}'></span></a></th>
-             {% if any_has_restock_price_processor %}
+             {%- if any_has_restock_price_processor -%}
                 <th>Restock &amp; Price</th>
-             {% endif %}
+             {%- endif -%}
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('watchlist.index', sort='last_checked', order=link_order, tag=active_tag_uuid)}}"><span class="hide-on-mobile">Last</span> Checked <span class='arrow {{link_order}}'></span></a></th>
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('watchlist.index', sort='last_changed', order=link_order, tag=active_tag_uuid)}}"><span class="hide-on-mobile">Last</span> Changed <span class='arrow {{link_order}}'></span></a></th>
                 <th class="empty-cell"></th>
             </tr>
             </thead>
             <tbody>
-            {% if not watches|length %}
+            {%- if not watches|length -%}
             <tr>
                 <td colspan="{{ cols_required }}" style="text-wrap: wrap;">No website watches configured, please add a URL in the box above, or <a href="{{ url_for('imports.import_page')}}" >import a list</a>.</td>
             </tr>
-            {% endif %}
-            {% for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))|pagination_slice(skip=pagination.skip) %}
+            {%- endif -%}
 
-                {% set checking_now = is_checking_now(watch) %}
-            <tr id="{{ watch.uuid }}" data-watch-uuid="{{ watch.uuid }}"
-                class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }} processor-{{ watch['processor'] }}
-                {# realtime.js also sets these vars on the row for update #}
-                {% if watch.compile_error_texts()|length >2 %}has-error{% endif %}
-                {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
-                {% if watch.has_unviewed %}unviewed{% endif %}
-                {% if watch.has_restock_info %} has-restock-info {% if watch['restock']['in_stock'] %}in-stock{% else %}not-in-stock{% endif %} {% else %}no-restock-info{% endif %}
-                {% if watch.uuid in queued_uuids %}queued{% endif %}
-                {% if checking_now %}checking-now{% endif %}
-                {% if watch.notification_muted %}notification_muted{% endif %}
-                ">
-                <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span>{{ loop.index+pagination.skip }}</span></td>
+            {%- for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))|pagination_slice(skip=pagination.skip) -%}
+                {%- set checking_now = is_checking_now(watch) -%}
+                {%- set history_n = watch.history_n -%}
+                {%- set favicon = watch.get_favicon_filename() -%}
+                {%- set system_use_url_watchlist = datastore.data['settings']['application']['ui'].get('use_page_title_in_list')  -%}
+                {#  Class settings mirrored in changedetectionio/static/js/realtime.js for the frontend #}
+                {%- set row_classes = [
+                    loop.cycle('pure-table-odd', 'pure-table-even'),
+                    'processor-' ~ watch['processor'],
+                    'has-error' if watch.compile_error_texts()|length > 2 else '',
+                    'paused' if watch.paused is defined and watch.paused != False else '',
+                    'unviewed' if watch.has_unviewed else '',
+                    'has-restock-info' if watch.has_restock_info else 'no-restock-info',
+                    'has-favicon' if favicon else '',
+                    'in-stock' if watch.has_restock_info and watch['restock']['in_stock'] else '',
+                    'not-in-stock' if watch.has_restock_info and not watch['restock']['in_stock'] else '',
+                    'queued' if watch.uuid in queued_uuids else '',
+                    'checking-now' if checking_now else '',
+                    'notification_muted' if watch.notification_muted else '',
+                    'single-history' if history_n == 1 else '',
+                    'multiple-history' if history_n >= 2 else '',
+                    'use-html-title' if system_use_url_watchlist else 'no-html-title',
+                ] -%}
+            <tr id="{{ watch.uuid }}" data-watch-uuid="{{ watch.uuid }}" class="{{ row_classes | reject('equalto', '') | join(' ') }}">
+                <td class="inline checkbox-uuid" ><div><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span class="counter-i">{{ loop.index+pagination.skip }}</span></div></td>
                 <td class="inline watch-controls">
+                    <div>
                     <a class="ajax-op state-off pause-toggle" data-op="pause" href="{{url_for('watchlist.index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause" ></a>
                     <a class="ajax-op state-on pause-toggle"  data-op="pause" style="display: none" href="{{url_for('watchlist.index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause" ></a>
-
                     <a class="ajax-op state-off mute-toggle" data-op="mute" href="{{url_for('watchlist.index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notification" title="Mute notification" class="icon icon-mute" ></a>
                     <a class="ajax-op state-on mute-toggle" data-op="mute"  style="display: none" href="{{url_for('watchlist.index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="UnMute notification" title="UnMute notification" class="icon icon-mute" ></a>
+                    </div>
                 </td>
-                <td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
-                    <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
-                    <a class="link-spread" href="{{url_for('ui.form_share_put_watch', uuid=watch.uuid)}}"><img src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" ></a>
 
-                    {% if watch.get_fetch_backend == "html_webdriver"
-                         or ( watch.get_fetch_backend == "system" and system_default_fetcher == 'html_webdriver'  )
-                         or "extra_browser_" in watch.get_fetch_backend
-                    %}
-                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='google-chrome-icon.png')}}" alt="Using a Chrome browser" title="Using a Chrome browser" >
-                    {% endif %}
+                <td class="title-col inline">
+                    <div class="flex-wrapper">
+                    {% if 'favicons_enabled' not in ui_settings or ui_settings['favicons_enabled'] %}
+                        <div>{# A page might have hundreds of these images, set IMG options for lazy loading, don't set SRC if we dont have it so it doesnt fetch the placeholder'  #}
+                            <img alt="Favicon thumbnail" class="favicon" loading="lazy" decoding="async" fetchpriority="low" {% if favicon %} src="{{url_for('static_content', group='favicon', filename=watch.uuid)}}" {% else %} src='data:image/svg+xml;utf8,%3Csvg xmlns="http://www.w3.org/2000/svg" width="7.087" height="7.087" viewBox="0 0 7.087 7.087"%3E%3Ccircle cx="3.543" cy="3.543" r="3.279" stroke="%23e1e1e1" stroke-width="0.45" fill="none" opacity="0.74"/%3E%3C/svg%3E' {%  endif %} />
+                        </div>
+                    {%  endif %}
+                        <div>
+                        <span class="watch-title">
+                            {% if system_use_url_watchlist or watch.get('use_page_title_in_list') %}
+                                {{ watch.label }}
+                            {% else %}
+                                {{ watch.get('title') or watch.link }}
+                            {% endif %}
+                           <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}">&nbsp;</a>
+                        </span>
+                            <div class="error-text" style="display:none;">{{ watch.compile_error_texts(has_proxies=datastore.proxy_list) }}</div>
+                            {%- if watch['processor'] == 'text_json_diff'  -%}
+                                {%- if watch['has_ldjson_price_data'] and not watch['track_ldjson_price_data']  -%}
+                                <div class="ldjson-price-track-offer">Switch to Restock & Price watch mode? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
+                                {%- endif -%}
+                            {%- endif -%}
+                            {%- if watch['processor'] == 'restock_diff' -%}
+                                <span class="tracking-ldjson-price-data" title="Automatically following embedded price information"><img src="{{url_for('static_content', group='images', filename='price-tag-icon.svg')}}"  class="status-icon price-follow-tag-icon" > Price</span>
+                            {%- endif -%}
+                            {%- for watch_tag_uuid, watch_tag in datastore.get_all_tags_for_watch(watch['uuid']).items() -%}
+                              <span class="watch-tag-list">{{ watch_tag.title }}</span>
+                            {%- endfor -%}
+                        </div>
+                    <div class="status-icons">
+                            <a class="link-spread" href="{{url_for('ui.form_share_put_watch', uuid=watch.uuid)}}"><img src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" ></a>
+                            {%- if watch.get_fetch_backend == "html_webdriver"
+                                 or ( watch.get_fetch_backend == "system" and system_default_fetcher == 'html_webdriver'  )
+                                 or "extra_browser_" in watch.get_fetch_backend
+                            -%}
+                            <img class="status-icon" src="{{url_for('static_content', group='images', filename='google-chrome-icon.png')}}" alt="Using a Chrome browser" title="Using a Chrome browser" >
+                            {%- endif -%}
+                            {%- if watch.is_pdf  -%}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" alt="Converting PDF to text" >{%- endif -%}
+                            {%- if watch.has_browser_steps -%}<img class="status-icon status-browsersteps" src="{{url_for('static_content', group='images', filename='steps.svg')}}" alt="Browser Steps is enabled" >{%- endif -%}
 
-                    {% if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" alt="Converting PDF to text" >{% endif %}
-                    {% if watch.has_browser_steps %}<img class="status-icon status-browsersteps" src="{{url_for('static_content', group='images', filename='steps.svg')}}" alt="Browser Steps is enabled" >{% endif %}
-
-                    <div class="error-text" style="display:none;">{{ watch.compile_error_texts(has_proxies=datastore.proxy_list)|safe }}</div>
-
-                    {% if watch['processor'] == 'text_json_diff'  %}
-                        {% if watch['has_ldjson_price_data'] and not watch['track_ldjson_price_data']  %}
-                        <div class="ldjson-price-track-offer">Switch to Restock & Price watch mode? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
-                        {% endif %}
-                    {% endif %}
-                    {% if watch['processor'] == 'restock_diff' %}
-                        <span class="tracking-ldjson-price-data" title="Automatically following embedded price information"><img src="{{url_for('static_content', group='images', filename='price-tag-icon.svg')}}"  class="status-icon price-follow-tag-icon" > Price</span>
-                    {% endif %}
-                    {% for watch_tag_uuid, watch_tag in datastore.get_all_tags_for_watch(watch['uuid']).items() %}
-                      <span class="watch-tag-list">{{ watch_tag.title }}</span>
-                    {% endfor %}
+                    </div>
+                    </div>
                 </td>
-            <!-- @todo make it so any watch handler obj can expose this --->
-{% if any_has_restock_price_processor %}
+{%- if any_has_restock_price_processor -%}
                 <td class="restock-and-price">
-                    {% if watch['processor'] == 'restock_diff'  %}
-                        {% if watch.has_restock_info %}
+                    {%- if watch['processor'] == 'restock_diff'  -%}
+                        {%- if watch.has_restock_info -%}
                             <span class="restock-label {{'in-stock' if watch['restock']['in_stock'] else 'not-in-stock' }}" title="Detecting restock and price">
                                 <!-- maybe some object watch['processor'][restock_diff] or.. -->
-                                 {% if watch['restock']['in_stock'] %} In stock {% else %} Not in stock {% endif %}
+                                 {%- if watch['restock']['in_stock']-%}  In stock {%- else-%}  Not in stock {%- endif -%}
                             </span>
-                        {% endif %}
+                        {%- endif -%}
 
-                        {% if watch.get('restock') and watch['restock']['price'] != None %}
-                            {% if watch['restock']['price'] != None %}
+                        {%- if watch.get('restock') and watch['restock']['price'] != None -%}
+                            {%- if watch['restock']['price'] != None -%}
                                 <span class="restock-label price" title="Price">
                                 {{ watch['restock']['price']|format_number_locale }} {{ watch['restock']['currency'] }}
                                 </span>
-                            {% endif %}
-                        {% elif not watch.has_restock_info %}
+                            {%- endif -%}
+                        {%- elif not watch.has_restock_info -%}
                             <span class="restock-label error">No information</span>
-                        {% endif %}
-                    {% endif %}
+                        {%- endif -%}
+                    {%- endif -%}
                 </td>
-{% endif %}
+{%- endif -%}
             {#last_checked becomes fetch-start-time#}
                 <td class="last-checked" data-timestamp="{{ watch.last_checked }}" data-fetchduration={{ watch.fetch_time }} data-eta_complete="{{ watch.last_checked+watch.fetch_time }}" >
                     <div class="spinner-wrapper" style="display:none;" >
@@ -179,51 +223,44 @@
                     </div>
                     <span class="innertext">{{watch|format_last_checked_time|safe}}</span>
                 </td>
-
-
-                <td class="last-changed" data-timestamp="{{ watch.last_changed }}">{% if watch.history_n >=2 and watch.last_changed >0 %}
+                <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 %}
+                    {%- else -%}
                     Not yet
-                    {% endif %}
+                    {%- endif -%}
                 </td>
-                <td>
+                <td class="buttons">
+                    <div>
+                    {%- set target_attr = ' target="' ~ watch.uuid ~ '"' if datastore.data['settings']['application']['ui'].get('open_diff_in_new_tab') else '' -%}
                     <a href="" class="already-in-queue-button recheck pure-button pure-button-primary" style="display: none;" disabled="disabled">Queued</a>
-
                     <a href="{{ url_for('ui.form_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}" data-op='recheck' class="ajax-op recheck pure-button pure-button-primary">Recheck</a>
                     <a href="{{ url_for('ui.ui_edit.edit_page', uuid=watch.uuid, tag=active_tag_uuid)}}#general" class="pure-button pure-button-primary">Edit</a>
-
-                    {% if watch.history_n >= 2 %}
-
-                        {% set open_diff_in_new_tab = datastore.data['settings']['application']['ui'].get('open_diff_in_new_tab') %}
-                        {% set target_attr = ' target="' ~ watch.uuid ~ '"' if open_diff_in_new_tab else '' %}
-
-                        {% if watch.has_unviewed %}
-                           <a href="{{ url_for('ui.ui_views.diff_history_page', uuid=watch.uuid, from_version=watch.get_from_version_based_on_last_viewed) }}" {{target_attr}} class="pure-button pure-button-primary diff-link">History</a>
-                        {% else %}
-                           <a href="{{ url_for('ui.ui_views.diff_history_page', uuid=watch.uuid)}}" {{target_attr}} class="pure-button pure-button-primary diff-link">History</a>
-                        {% endif %}
-
-                    {% else %}
-                        {% if watch.history_n == 1 or (watch.history_n ==0 and watch.error_text_ctime )%}
-                            <a href="{{ url_for('ui.ui_views.preview_page', uuid=watch.uuid)}}" {{target_attr}} class="pure-button pure-button-primary">Preview</a>
-                        {% endif %}
-                    {% endif %}
+                    <a href="{{ url_for('ui.ui_views.diff_history_page', uuid=watch.uuid)}}" {{target_attr}} class="pure-button pure-button-primary history-link" style="display: none;">History</a>
+                    <a href="{{ url_for('ui.ui_views.preview_page', uuid=watch.uuid)}}" {{target_attr}} class="pure-button pure-button-primary preview-link" style="display: none;">Preview</a>
+                    </div>
                 </td>
             </tr>
-            {% endfor %}
+            {%- endfor -%}
             </tbody>
         </table>
         <ul id="post-list-buttons">
-            <li id="post-list-with-errors" class="{% if errored_count %}has-error{% endif %}" style="display: none;" >
+            <li id="post-list-with-errors" style="display: none;" >
                 <a href="{{url_for('watchlist.index', with_errors=1, tag=request.args.get('tag')) }}" class="pure-button button-tag button-error">With errors ({{ errored_count }})</a>
             </li>
-            <li id="post-list-mark-views" class="{% if has_unviewed %}has-unviewed{% endif %}" style="display: none;" >
+            <li id="post-list-mark-views" style="display: none;" >
                 <a href="{{url_for('ui.mark_all_viewed',with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag " id="mark-all-viewed">Mark all viewed</a>
             </li>
+        {%-  if active_tag_uuid -%}
+            <li id="post-list-mark-views-tag">
+                <a href="{{url_for('ui.mark_all_viewed', tag=active_tag_uuid) }}" class="pure-button button-tag " id="mark-all-viewed">Mark all viewed in '{{active_tag.title}}'</a>
+            </li>
+        {%-  endif -%}
+            <li id="post-list-unread" style="display: none;" >
+                <a href="{{url_for('watchlist.index', unread=1, tag=request.args.get('tag')) }}" class="pure-button button-tag">Unread (<span id="unread-tab-counter">{{ unread_changes_count }}</span>)</a>
+            </li>
             <li>
                <a href="{{ url_for('ui.form_watch_checknow', tag=active_tag_uuid, with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag" id="recheck-all">Recheck
-                all {% if active_tag_uuid %} in "{{active_tag.title}}"{%endif%}</a>
+                all {% if active_tag_uuid %}  in '{{active_tag.title}}'{%endif%}</a>
             </li>
             <li>
                 <a href="{{ url_for('rss.feed', tag=active_tag_uuid, token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='generic_feed-icon.svg')}}" height="15"></a>
@@ -233,4 +270,4 @@
     </div>
     </form>
 </div>
-{% endblock %}
+{%- endblock -%}

changedetectionio/conditions/__init__.py

@@ -1,5 +1,3 @@
-from flask import Blueprint
-
 from json_logic.builtins import BUILTINS
 
 from .exceptions import EmptyConditionRuleRowNotUsable
@@ -16,7 +14,6 @@ operator_choices = [
     ("==", "Equals"),
     ("!=", "Not Equals"),
     ("in", "Contains"),
-    ("!in", "Does Not Contain"),
 ]
 
 # Fields available in the rules

changedetectionio/conditions/default_plugin.py

@@ -21,17 +21,21 @@ def register_operators():
     def length_max(_, text, strlen):
         return len(text) <= int(strlen)
 
-    # ✅ Custom function for case-insensitive regex matching
+    # Custom function for case-insensitive regex matching
     def contains_regex(_, text, pattern):
         """Returns True if `text` contains `pattern` (case-insensitive regex match)."""
         return bool(re.search(pattern, str(text), re.IGNORECASE))
 
-    # ✅ Custom function for NOT matching case-insensitive regex
+    # Custom function for NOT matching case-insensitive regex
     def not_contains_regex(_, text, pattern):
         """Returns True if `text` does NOT contain `pattern` (case-insensitive regex match)."""
         return not bool(re.search(pattern, str(text), re.IGNORECASE))
 
+    def not_contains(_, text, pattern):
+        return not pattern in text
+
     return {
+        "!in": not_contains,
         "!contains_regex": not_contains_regex,
         "contains_regex": contains_regex,
         "ends_with": ends_with,
@@ -43,6 +47,7 @@ def register_operators():
 @hookimpl
 def register_operator_choices():
     return [
+        ("!in", "Does NOT Contain"),
         ("starts_with", "Text Starts With"),
         ("ends_with", "Text Ends With"),
         ("length_min", "Length minimum"),

changedetectionio/conditions/plugins/levenshtein_plugin.py

@@ -1,6 +1,8 @@
 import pluggy
 from loguru import logger
 
+LEVENSHTEIN_MAX_LEN_FOR_EDIT_STATS=100000
+
 # Support both plugin systems
 conditions_hookimpl = pluggy.HookimplMarker("changedetectionio_conditions")
 global_hookimpl = pluggy.HookimplMarker("changedetectionio")
@@ -72,7 +74,17 @@ def ui_edit_stats_extras(watch):
     """Generate the HTML for Levenshtein stats - shared by both plugin systems"""
     if len(watch.history.keys()) < 2:
         return "<p>Not enough history to calculate Levenshtein metrics</p>"
-    
+
+
+    # Protection against the algorithm getting stuck on huge documents
+    k = list(watch.history.keys())
+    if any(
+            len(watch.get_history_snapshot(timestamp=k[idx])) > LEVENSHTEIN_MAX_LEN_FOR_EDIT_STATS
+            for idx in (-1, -2)
+            if len(k) >= abs(idx)
+    ):
+        return "<p>Snapshot too large for edit statistics, skipping.</p>"
+
     try:
         lev_data = levenshtein_ratio_recent_history(watch)
         if not lev_data or not isinstance(lev_data, dict):

changedetectionio/content_fetchers/__init__.py

@@ -28,6 +28,7 @@ from changedetectionio.content_fetchers.requests import fetcher as html_requests
 import importlib.resources
 XPATH_ELEMENT_JS = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text(encoding='utf-8')
 INSTOCK_DATA_JS = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text(encoding='utf-8')
+FAVICON_FETCHER_JS = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('favicon-fetcher.js').read_text(encoding='utf-8')
 
 
 def available_fetchers():

changedetectionio/content_fetchers/base.py

@@ -48,6 +48,7 @@ class Fetcher():
     error = None
     fetcher_description = "No description"
     headers = {}
+    favicon_blob = None
     instock_data = None
     instock_data_js = ""
     status_code = None
@@ -68,16 +69,18 @@ class Fetcher():
         return self.error
 
     @abstractmethod
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False,
-            empty_pages_are_a_change=False):
+    async def run(self,
+                  fetch_favicon=True,
+                  current_include_filters=None,
+                  empty_pages_are_a_change=False,
+                  ignore_status_codes=False,
+                  is_binary=False,
+                  request_body=None,
+                  request_headers=None,
+                  request_method=None,
+                  timeout=None,
+                  url=None,
+                  ):
         # Should set self.error, self.status_code and self.content
         pass
 
@@ -122,7 +125,7 @@ class Fetcher():
 
         return None
 
-    def iterate_browser_steps(self, start_url=None):
+    async def iterate_browser_steps(self, start_url=None):
         from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
         from playwright._impl._errors import TimeoutError, Error
         from changedetectionio.safe_jinja import render as jinja_render
@@ -136,8 +139,8 @@ class Fetcher():
             for step in valid_steps:
                 step_n += 1
                 logger.debug(f">> Iterating check - browser Step n {step_n} - {step['operation']}...")
-                self.screenshot_step("before-" + str(step_n))
-                self.save_step_html("before-" + str(step_n))
+                await self.screenshot_step("before-" + str(step_n))
+                await self.save_step_html("before-" + str(step_n))
 
                 try:
                     optional_value = step['optional_value']
@@ -148,11 +151,11 @@ class Fetcher():
                     if '{%' in step['selector'] or '{{' in step['selector']:
                         selector = jinja_render(template_str=step['selector'])
 
-                    getattr(interface, "call_action")(action_name=step['operation'],
+                    await getattr(interface, "call_action")(action_name=step['operation'],
                                                       selector=selector,
                                                       optional_value=optional_value)
-                    self.screenshot_step(step_n)
-                    self.save_step_html(step_n)
+                    await self.screenshot_step(step_n)
+                    await self.save_step_html(step_n)
                 except (Error, TimeoutError) as e:
                     logger.debug(str(e))
                     # Stop processing here

changedetectionio/content_fetchers/playwright.py

@@ -5,19 +5,19 @@ from urllib.parse import urlparse
 from loguru import logger
 
 from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT, visualselector_xpath_selectors, \
-    SCREENSHOT_SIZE_STITCH_THRESHOLD, SCREENSHOT_MAX_TOTAL_HEIGHT, XPATH_ELEMENT_JS, INSTOCK_DATA_JS
+    SCREENSHOT_SIZE_STITCH_THRESHOLD, SCREENSHOT_MAX_TOTAL_HEIGHT, XPATH_ELEMENT_JS, INSTOCK_DATA_JS, FAVICON_FETCHER_JS
 from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
 from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, ScreenshotUnavailable
 
-def capture_full_page(page):
+async def capture_full_page_async(page):
     import os
     import time
     from multiprocessing import Process, Pipe
 
     start = time.time()
 
-    page_height = page.evaluate("document.documentElement.scrollHeight")
-    page_width = page.evaluate("document.documentElement.scrollWidth")
+    page_height = await page.evaluate("document.documentElement.scrollHeight")
+    page_width = await page.evaluate("document.documentElement.scrollWidth")
     original_viewport = page.viewport_size
 
     logger.debug(f"Playwright viewport size {page.viewport_size} page height {page_height} page width {page_width}")
@@ -32,23 +32,23 @@ def capture_full_page(page):
             step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
         logger.debug(f"Setting bigger viewport to step through large page width W{page.viewport_size['width']}xH{step_size} because page_height > viewport_size")
         # Set viewport to a larger size to capture more content at once
-        page.set_viewport_size({'width': page.viewport_size['width'], 'height': step_size})
+        await page.set_viewport_size({'width': page.viewport_size['width'], 'height': step_size})
 
     # Capture screenshots in chunks up to the max total height
     while y < min(page_height, SCREENSHOT_MAX_TOTAL_HEIGHT):
-        page.request_gc()
-        page.evaluate(f"window.scrollTo(0, {y})")
-        page.request_gc()
-        screenshot_chunks.append(page.screenshot(
+        await page.request_gc()
+        await page.evaluate(f"window.scrollTo(0, {y})")
+        await page.request_gc()
+        screenshot_chunks.append(await page.screenshot(
             type="jpeg",
             full_page=False,
             quality=int(os.getenv("SCREENSHOT_QUALITY", 72))
         ))
         y += step_size
-        page.request_gc()
+        await page.request_gc()
 
     # Restore original viewport size
-    page.set_viewport_size({'width': original_viewport['width'], 'height': original_viewport['height']})
+    await page.set_viewport_size({'width': original_viewport['width'], 'height': original_viewport['height']})
 
     # If we have multiple chunks, stitch them together
     if len(screenshot_chunks) > 1:
@@ -73,7 +73,6 @@ def capture_full_page(page):
 
     return screenshot_chunks[0]
 
-
 class fetcher(Fetcher):
     fetcher_description = "Playwright {}/Javascript".format(
         os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
@@ -124,9 +123,9 @@ class fetcher(Fetcher):
                 self.proxy['username'] = parsed.username
                 self.proxy['password'] = parsed.password
 
-    def screenshot_step(self, step_n=''):
+    async def screenshot_step(self, step_n=''):
         super().screenshot_step(step_n=step_n)
-        screenshot = capture_full_page(page=self.page)
+        screenshot = await capture_full_page_async(page=self.page)
 
 
         if self.browser_steps_screenshot_path is not None:
@@ -135,45 +134,47 @@ class fetcher(Fetcher):
             with open(destination, 'wb') as f:
                 f.write(screenshot)
 
-    def save_step_html(self, step_n):
+    async def save_step_html(self, step_n):
         super().save_step_html(step_n=step_n)
-        content = self.page.content()
+        content = await self.page.content()
         destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.html'.format(step_n))
         logger.debug(f"Saving step HTML to {destination}")
         with open(destination, 'w') as f:
             f.write(content)
 
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False,
-            empty_pages_are_a_change=False):
+    async def run(self,
+                  fetch_favicon=True,
+                  current_include_filters=None,
+                  empty_pages_are_a_change=False,
+                  ignore_status_codes=False,
+                  is_binary=False,
+                  request_body=None,
+                  request_headers=None,
+                  request_method=None,
+                  timeout=None,
+                  url=None,
+                  ):
 
-        from playwright.sync_api import sync_playwright
+        from playwright.async_api import async_playwright
         import playwright._impl._errors
         import time
         self.delete_browser_steps_screenshots()
         response = None
 
-        with sync_playwright() as p:
+        async with async_playwright() as p:
             browser_type = getattr(p, self.browser_type)
 
             # Seemed to cause a connection Exception even tho I can see it connect
             # self.browser = browser_type.connect(self.command_executor, timeout=timeout*1000)
             # 60,000 connection timeout only
-            browser = browser_type.connect_over_cdp(self.browser_connection_url, timeout=60000)
+            browser = await 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(
+            context = await browser.new_context(
                 accept_downloads=False,  # Should never be needed
                 bypass_csp=True,  # This is needed to enable JavaScript execution on GitHub and others
                 extra_http_headers=request_headers,
@@ -183,7 +184,7 @@ class fetcher(Fetcher):
                 user_agent=manage_user_agent(headers=request_headers),
             )
 
-            self.page = context.new_page()
+            self.page = await context.new_page()
 
             # Listen for all console events and handle errors
             self.page.on("console", lambda msg: logger.debug(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
@@ -193,32 +194,37 @@ class fetcher(Fetcher):
             browsersteps_interface = steppable_browser_interface(start_url=url)
             browsersteps_interface.page = self.page
 
-            response = browsersteps_interface.action_goto_url(value=url)
+            response = await browsersteps_interface.action_goto_url(value=url)
 
             if response is None:
-                context.close()
-                browser.close()
+                await context.close()
+                await browser.close()
                 logger.debug("Content Fetcher > Response object from the browser communication was none")
                 raise EmptyReply(url=url, status_code=None)
 
-            self.headers = response.all_headers()
+            # In async_playwright, all_headers() returns a coroutine
+            try:
+                self.headers = await response.all_headers()
+            except TypeError:
+                # Fallback for sync version
+                self.headers = response.all_headers()
 
             try:
                 if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
-                    browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
+                    await browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
             except playwright._impl._errors.TimeoutError as e:
-                context.close()
-                browser.close()
+                await context.close()
+                await browser.close()
                 # This can be ok, we will try to grab what we could retrieve
                 pass
             except Exception as e:
                 logger.debug(f"Content Fetcher > Other exception when executing custom JS code {str(e)}")
-                context.close()
-                browser.close()
+                await context.close()
+                await browser.close()
                 raise PageUnloadable(url=url, status_code=None, message=str(e))
 
             extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-            self.page.wait_for_timeout(extra_wait * 1000)
+            await self.page.wait_for_timeout(extra_wait * 1000)
 
             try:
                 self.status_code = response.status
@@ -226,50 +232,58 @@ class fetcher(Fetcher):
                 # https://github.com/dgtlmoon/changedetection.io/discussions/2122#discussioncomment-8241962
                 logger.critical(f"Response from the browser/Playwright did not have a status_code! Response follows.")
                 logger.critical(response)
-                context.close()
-                browser.close()
+                await context.close()
+                await browser.close()
                 raise PageUnloadable(url=url, status_code=None, message=str(e))
 
+            if fetch_favicon:
+                try:
+                    self.favicon_blob = await self.page.evaluate(FAVICON_FETCHER_JS)
+                    await self.page.request_gc()
+                except Exception as e:
+                    logger.error(f"Error fetching FavIcon info {str(e)}, continuing.")
+
             if self.status_code != 200 and not ignore_status_codes:
-                screenshot = capture_full_page(self.page)
+                screenshot = await capture_full_page_async(self.page)
                 raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
 
-            if not empty_pages_are_a_change and len(self.page.content().strip()) == 0:
+            if not empty_pages_are_a_change and len((await self.page.content()).strip()) == 0:
                 logger.debug("Content Fetcher > Content was empty, empty_pages_are_a_change = False")
-                context.close()
-                browser.close()
+                await context.close()
+                await browser.close()
                 raise EmptyReply(url=url, status_code=response.status)
 
             # Run Browser Steps here
             if self.browser_steps_get_valid_steps():
-                self.iterate_browser_steps(start_url=url)
+                await self.iterate_browser_steps(start_url=url)
 
-            self.page.wait_for_timeout(extra_wait * 1000)
+            await self.page.wait_for_timeout(extra_wait * 1000)
 
             now = time.time()
             # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
             if current_include_filters is not None:
-                self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
+                await self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
             else:
-                self.page.evaluate("var include_filters=''")
-            self.page.request_gc()
+                await self.page.evaluate("var include_filters=''")
+            await self.page.request_gc()
 
             # request_gc before and after evaluate to free up memory
             # @todo browsersteps etc
             MAX_TOTAL_HEIGHT = int(os.getenv("SCREENSHOT_MAX_HEIGHT", SCREENSHOT_MAX_HEIGHT_DEFAULT))
-            self.xpath_data = self.page.evaluate(XPATH_ELEMENT_JS, {
+            self.xpath_data = await self.page.evaluate(XPATH_ELEMENT_JS, {
                 "visualselector_xpath_selectors": visualselector_xpath_selectors,
                 "max_height": MAX_TOTAL_HEIGHT
             })
-            self.page.request_gc()
+            await self.page.request_gc()
 
-            self.instock_data = self.page.evaluate(INSTOCK_DATA_JS)
-            self.page.request_gc()
+            self.instock_data = await self.page.evaluate(INSTOCK_DATA_JS)
+            await self.page.request_gc()
 
-            self.content = self.page.content()
-            self.page.request_gc()
+            self.content = await self.page.content()
+            await self.page.request_gc()
             logger.debug(f"Scrape xPath element data in browser done in {time.time() - now:.2f}s")
 
+
             # Bug 3 in Playwright screenshot handling
             # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
             # JPEG is better here because the screenshots can be very very large
@@ -279,7 +293,7 @@ class fetcher(Fetcher):
             # acceptable screenshot quality here
             try:
                 # The actual screenshot - this always base64 and needs decoding! horrible! huge CPU usage
-                self.screenshot = capture_full_page(page=self.page)
+                self.screenshot = await capture_full_page_async(page=self.page)
 
             except Exception as e:
                 # It's likely the screenshot was too long/big and something crashed
@@ -287,30 +301,30 @@ class fetcher(Fetcher):
             finally:
                 # Request garbage collection one more time before closing
                 try:
-                    self.page.request_gc()
+                    await self.page.request_gc()
                 except:
                     pass
                 
                 # Clean up resources properly
                 try:
-                    self.page.request_gc()
+                    await self.page.request_gc()
                 except:
                     pass
 
                 try:
-                    self.page.close()
+                    await self.page.close()
                 except:
                     pass
                 self.page = None
 
                 try:
-                    context.close()
+                    await context.close()
                 except:
                     pass
                 context = None
 
                 try:
-                    browser.close()
+                    await browser.close()
                 except:
                     pass
                 browser = None

changedetectionio/content_fetchers/puppeteer.py

@@ -8,7 +8,7 @@ from loguru import logger
 
 from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT, visualselector_xpath_selectors, \
     SCREENSHOT_SIZE_STITCH_THRESHOLD, SCREENSHOT_DEFAULT_QUALITY, XPATH_ELEMENT_JS, INSTOCK_DATA_JS, \
-    SCREENSHOT_MAX_TOTAL_HEIGHT
+    SCREENSHOT_MAX_TOTAL_HEIGHT, FAVICON_FETCHER_JS
 from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
 from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, BrowserFetchTimedOut, \
     BrowserConnectError
@@ -51,7 +51,15 @@ async def capture_full_page(page):
         await page.setViewport({'width': page.viewport['width'], 'height': step_size})
 
     while y < min(page_height, SCREENSHOT_MAX_TOTAL_HEIGHT):
-        await page.evaluate(f"window.scrollTo(0, {y})")
+        # better than scrollTo incase they override it in the page
+        await page.evaluate(
+            """(y) => {
+                document.documentElement.scrollTop = y;
+                document.body.scrollTop = y;
+            }""",
+            y
+        )
+
         screenshot_chunks.append(await page.screenshot(type_='jpeg',
                                                        fullPage=False,
                                                        quality=int(os.getenv("SCREENSHOT_QUALITY", 72))))
@@ -137,19 +145,24 @@ class fetcher(Fetcher):
     #         f.write(content)
 
     async def fetch_page(self,
-                         url,
-                         timeout,
-                         request_headers,
-                         request_body,
-                         request_method,
-                         ignore_status_codes,
                          current_include_filters,
+                         empty_pages_are_a_change,
+                         fetch_favicon,
+                         ignore_status_codes,
                          is_binary,
-                         empty_pages_are_a_change
+                         request_body,
+                         request_headers,
+                         request_method,
+                         timeout,
+                         url,
                          ):
         import re
         self.delete_browser_steps_screenshots()
-        extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+
+        n = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+        extra_wait = min(n, 15)
+
+        logger.debug(f"Extra wait set to {extra_wait}s, requested was {n}s.")
 
         from pyppeteer import Pyppeteer
         pyppeteer_instance = Pyppeteer()
@@ -165,12 +178,13 @@ class fetcher(Fetcher):
         except websockets.exceptions.InvalidURI:
             raise BrowserConnectError(msg=f"Error connecting to the browser, check your browser connection address (should be ws:// or wss://")
         except Exception as e:
-            raise BrowserConnectError(msg=f"Error connecting to the browser {str(e)}")
+            raise BrowserConnectError(msg=f"Error connecting to the browser - Exception '{str(e)}'")
 
-        # Better is to launch chrome with the URL as arg
-        # non-headless - newPage() will launch an extra tab/window, .browser should already contain 1 page/tab
-        # headless - ask a new page
-        self.page = (pages := await browser.pages) and len(pages) or await browser.newPage()
+        # more reliable is to just request a new page
+        self.page = await browser.newPage()
+        
+        # Add console handler to capture console.log from favicon fetcher
+        #self.page.on('console', lambda msg: logger.debug(f"Browser console [{msg.type}]: {msg.text}"))
 
         if '--window-size' in self.browser_connection_url:
             # Be sure the viewport is always the window-size, this is often not the same thing
@@ -227,13 +241,35 @@ class fetcher(Fetcher):
         #            browsersteps_interface = steppable_browser_interface()
         #            browsersteps_interface.page = self.page
 
-        response = await self.page.goto(url, waitUntil="load")
+        async def handle_frame_navigation(event):
+            logger.debug(f"Frame navigated: {event}")
+            w = extra_wait - 2 if extra_wait > 4 else 2
+            logger.debug(f"Waiting {w} seconds before calling Page.stopLoading...")
+            await asyncio.sleep(w)
+            logger.debug("Issuing stopLoading command...")
+            await self.page._client.send('Page.stopLoading')
+            logger.debug("stopLoading command sent!")
 
-        if response is None:
-            await self.page.close()
-            await browser.close()
-            logger.warning("Content Fetcher > Response object was none (as in, the response from the browser was empty, not just the content)")
-            raise EmptyReply(url=url, status_code=None)
+        self.page._client.on('Page.frameStartedNavigating', lambda event: asyncio.create_task(handle_frame_navigation(event)))
+        self.page._client.on('Page.frameStartedLoading', lambda event: asyncio.create_task(handle_frame_navigation(event)))
+        self.page._client.on('Page.frameStoppedLoading', lambda event: logger.debug(f"Frame stopped loading: {event}"))
+
+        response = None
+        attempt=0
+        while not response:
+            logger.debug(f"Attempting page fetch {url} attempt {attempt}")
+            response = await self.page.goto(url)
+            await asyncio.sleep(1 + extra_wait)
+            if response:
+                break
+            if not response:
+                logger.warning("Page did not fetch! trying again!")
+            if response is None and attempt>=2:
+                await self.page.close()
+                await browser.close()
+                logger.warning(f"Content Fetcher > Response object was none (as in, the response from the browser was empty, not just the content) exiting attmpt {attempt}")
+                raise EmptyReply(url=url, status_code=None)
+            attempt+=1
 
         self.headers = response.headers
 
@@ -258,6 +294,12 @@ class fetcher(Fetcher):
             await browser.close()
             raise PageUnloadable(url=url, status_code=None, message=str(e))
 
+        if fetch_favicon:
+            try:
+                self.favicon_blob = await self.page.evaluate(FAVICON_FETCHER_JS)
+            except Exception as e:
+                logger.error(f"Error fetching FavIcon info {str(e)}, continuing.")
+
         if self.status_code != 200 and not ignore_status_codes:
             screenshot = await capture_full_page(page=self.page)
 
@@ -276,7 +318,6 @@ class fetcher(Fetcher):
         #            if self.browser_steps_get_valid_steps():
         #                self.iterate_browser_steps()
 
-        await asyncio.sleep(1 + extra_wait)
 
         # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
         # Setup the xPath/VisualSelector scraper
@@ -310,25 +351,36 @@ class fetcher(Fetcher):
     async def main(self, **kwargs):
         await self.fetch_page(**kwargs)
 
-    def run(self, url, timeout, request_headers, request_body, request_method, ignore_status_codes=False,
-            current_include_filters=None, is_binary=False, empty_pages_are_a_change=False):
+    async def run(self,
+                  fetch_favicon=True,
+                  current_include_filters=None,
+                  empty_pages_are_a_change=False,
+                  ignore_status_codes=False,
+                  is_binary=False,
+                  request_body=None,
+                  request_headers=None,
+                  request_method=None,
+                  timeout=None,
+                  url=None,
+                  ):
 
         #@todo make update_worker async which could run any of these content_fetchers within memory and time constraints
-        max_time = os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180)
+        max_time = int(os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180))
 
-        # This will work in 3.10 but not >= 3.11 because 3.11 wants tasks only
+        # Now we run this properly in async context since we're called from async worker
         try:
-            asyncio.run(asyncio.wait_for(self.main(
-                url=url,
-                timeout=timeout,
-                request_headers=request_headers,
-                request_body=request_body,
-                request_method=request_method,
-                ignore_status_codes=ignore_status_codes,
+            await asyncio.wait_for(self.main(
                 current_include_filters=current_include_filters,
+                empty_pages_are_a_change=empty_pages_are_a_change,
+                fetch_favicon=fetch_favicon,
+                ignore_status_codes=ignore_status_codes,
                 is_binary=is_binary,
-                empty_pages_are_a_change=empty_pages_are_a_change
-            ), timeout=max_time))
+                request_body=request_body,
+                request_headers=request_headers,
+                request_method=request_method,
+                timeout=timeout,
+                url=url,
+            ), timeout=max_time
+            )
         except asyncio.TimeoutError:
-            raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))
-
+            raise (BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))

changedetectionio/content_fetchers/requests.py

@@ -1,6 +1,7 @@
 from loguru import logger
 import hashlib
 import os
+import asyncio
 from changedetectionio import strtobool
 from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
 from changedetectionio.content_fetchers.base import Fetcher
@@ -15,7 +16,7 @@ class fetcher(Fetcher):
         self.proxy_override = proxy_override
         # browser_connection_url is none because its always 'launched locally'
 
-    def run(self,
+    def _run_sync(self,
             url,
             timeout,
             request_headers,
@@ -25,6 +26,7 @@ class fetcher(Fetcher):
             current_include_filters=None,
             is_binary=False,
             empty_pages_are_a_change=False):
+        """Synchronous version of run - the original requests implementation"""
 
         import chardet
         import requests
@@ -36,7 +38,6 @@ class fetcher(Fetcher):
         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.
 
@@ -100,9 +101,40 @@ class fetcher(Fetcher):
         else:
             self.content = r.text
 
-
         self.raw_content = r.content
 
+    async def run(self,
+                  fetch_favicon=True,
+                  current_include_filters=None,
+                  empty_pages_are_a_change=False,
+                  ignore_status_codes=False,
+                  is_binary=False,
+                  request_body=None,
+                  request_headers=None,
+                  request_method=None,
+                  timeout=None,
+                  url=None,
+                  ):
+        """Async wrapper that runs the synchronous requests code in a thread pool"""
+        
+        loop = asyncio.get_event_loop()
+        
+        # Run the synchronous _run_sync in a thread pool to avoid blocking the event loop
+        await loop.run_in_executor(
+            None,  # Use default ThreadPoolExecutor
+            lambda: self._run_sync(
+                url=url,
+                timeout=timeout,
+                request_headers=request_headers,
+                request_body=request_body,
+                request_method=request_method,
+                ignore_status_codes=ignore_status_codes,
+                current_include_filters=current_include_filters,
+                is_binary=is_binary,
+                empty_pages_are_a_change=empty_pages_are_a_change
+            )
+        )
+
     def quit(self, watch=None):
 
         # In case they switched to `requests` fetcher from something else

changedetectionio/content_fetchers/res/favicon-fetcher.js

@@ -0,0 +1,101 @@
+(async () => {
+  // Define the function inside the IIFE for console testing
+  window.getFaviconAsBlob = async function() {
+    const links = Array.from(document.querySelectorAll(
+      'link[rel~="apple-touch-icon"], link[rel~="icon"]'
+    ));
+
+    const icons = links.map(link => {
+      const sizesStr = link.getAttribute('sizes');
+      let size = 0;
+      if (sizesStr) {
+        const [w] = sizesStr.split('x').map(Number);
+        if (!isNaN(w)) size = w;
+      } else {
+        size = 16;
+      }
+      return {
+        size,
+        rel: link.getAttribute('rel'),
+        href: link.href,
+        hasSizes: !!sizesStr
+      };
+    });
+
+    // If no icons found, add fallback favicon.ico
+    if (icons.length === 0) {
+      icons.push({
+        size: 16,
+        rel: 'icon',
+        href: '/favicon.ico',
+        hasSizes: false
+      });
+    }
+
+    // sort preference: highest resolution first, then apple-touch-icon, then regular icons
+    icons.sort((a, b) => {
+      // First priority: actual size (highest first)
+      if (a.size !== b.size) {
+        return b.size - a.size;
+      }
+      
+      // Second priority: apple-touch-icon over regular icon
+      const isAppleA = /apple-touch-icon/.test(a.rel);
+      const isAppleB = /apple-touch-icon/.test(b.rel);
+      if (isAppleA && !isAppleB) return -1;
+      if (!isAppleA && isAppleB) return 1;
+      
+      // Third priority: icons with no size attribute (fallback icons) last
+      const hasNoSizeA = !a.hasSizes;
+      const hasNoSizeB = !b.hasSizes;
+      if (hasNoSizeA && !hasNoSizeB) return 1;
+      if (!hasNoSizeA && hasNoSizeB) return -1;
+      
+      return 0;
+    });
+
+    const timeoutMs = 2000;
+
+    for (const icon of icons) {
+      try {
+        const controller = new AbortController();
+        const timeout = setTimeout(() => controller.abort(), timeoutMs);
+
+        const resp = await fetch(icon.href, {
+          signal: controller.signal,
+          redirect: 'follow'
+        });
+
+        clearTimeout(timeout);
+
+        if (!resp.ok) {
+          continue;
+        }
+
+        const blob = await resp.blob();
+
+        // Convert blob to base64
+        const reader = new FileReader();
+        return await new Promise(resolve => {
+          reader.onloadend = () => {
+            resolve({
+              url: icon.href,
+              base64: reader.result.split(",")[1]
+            });
+          };
+          reader.readAsDataURL(blob);
+        });
+
+      } catch (e) {
+        continue;
+      }
+    }
+
+    // nothing found
+    return null;
+  };
+
+  // Auto-execute and return result for page.evaluate()
+  return await window.getFaviconAsBlob();
+})();
+

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

@@ -17,7 +17,9 @@ async () => {
             'back in stock soon',
             'back-order or out of stock',
             'backordered',
+            'backorder',
             'benachrichtigt mich', // notify me
+            'binnenkort leverbaar', // coming soon
             'brak na stanie',
             'brak w magazynie',
             'coming soon',
@@ -38,12 +40,14 @@ async () => {
             'mail me when available',
             'message if back in stock',
             'mevcut değil',
+            'more on order',
             'nachricht bei',
             'nicht auf lager',
             'nicht lagernd',
             'nicht lieferbar',
             'nicht verfügbar',
             'nicht vorrätig',
+            'nicht mehr lieferbar',
             'nicht zur verfügung',
             'nie znaleziono produktów',
             'niet beschikbaar',
@@ -85,6 +89,7 @@ async () => {
             'tidak tersedia',
             'tijdelijk uitverkocht',
             'tiket tidak tersedia',
+            'to subscribe to back in stock',
             'tükendi',
             'unavailable nearby',
             'unavailable tickets',
@@ -119,8 +124,7 @@ async () => {
             return text.toLowerCase().trim();
         }
 
-        const negateOutOfStockRegex = new RegExp('^([0-9] in stock|add to cart|in stock)', 'ig');
-
+        const negateOutOfStockRegex = new RegExp('^([0-9] in stock|add to cart|in stock|arrives approximately)', 'ig');
         // The out-of-stock or in-stock-text is generally always above-the-fold
         // and often below-the-fold is a list of related products that may or may not contain trigger text
         // so it's good to filter to just the 'above the fold' elements

changedetectionio/content_fetchers/webdriver_selenium.py

@@ -4,9 +4,10 @@ import time
 from loguru import logger
 from changedetectionio.content_fetchers.base import Fetcher
 
+
 class fetcher(Fetcher):
     if os.getenv("WEBDRIVER_URL"):
-        fetcher_description = "WebDriver Chrome/Javascript via '{}'".format(os.getenv("WEBDRIVER_URL"))
+        fetcher_description = f"WebDriver Chrome/Javascript via \"{os.getenv('WEBDRIVER_URL', '')}\""
     else:
         fetcher_description = "WebDriver Chrome/Javascript"
 
@@ -25,7 +26,6 @@ class fetcher(Fetcher):
             self.browser_connection_is_custom = True
             self.browser_connection_url = custom_browser_connection_url
 
-
         ##### PROXY SETUP #####
 
         proxy_sources = [
@@ -38,7 +38,7 @@ class fetcher(Fetcher):
             os.getenv('webdriver_proxyHttps'),
             os.getenv('webdriver_httpsProxy'),
             os.getenv('webdriver_sslProxy'),
-            proxy_override, # last one should override
+            proxy_override,  # last one should override
         ]
         # The built in selenium proxy handling is super unreliable!!! so we just grab which ever proxy setting we can find and throw it in --proxy-server=
         for k in filter(None, proxy_sources):
@@ -46,89 +46,98 @@ class fetcher(Fetcher):
                 continue
             self.proxy_url = k.strip()
 
+    async def run(self,
+                  fetch_favicon=True,
+                  current_include_filters=None,
+                  empty_pages_are_a_change=False,
+                  ignore_status_codes=False,
+                  is_binary=False,
+                  request_body=None,
+                  request_headers=None,
+                  request_method=None,
+                  timeout=None,
+                  url=None,
+                  ):
 
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False,
-            empty_pages_are_a_change=False):
+        import asyncio
 
-        from selenium.webdriver.chrome.options import Options as ChromeOptions
-        # request_body, request_method unused for now, until some magic in the future happens.
+        # Wrap the entire selenium operation in a thread executor
+        def _run_sync():
+            from selenium.webdriver.chrome.options import Options as ChromeOptions
+            # request_body, request_method unused for now, until some magic in the future happens.
 
-        options = ChromeOptions()
+            options = ChromeOptions()
 
-        # Load Chrome options from env
-        CHROME_OPTIONS = [
-            line.strip()
-            for line in os.getenv("CHROME_OPTIONS", "").strip().splitlines()
-            if line.strip()
-        ]
+            # Load Chrome options from env
+            CHROME_OPTIONS = [
+                line.strip()
+                for line in os.getenv("CHROME_OPTIONS", "").strip().splitlines()
+                if line.strip()
+            ]
 
-        for opt in CHROME_OPTIONS:
-            options.add_argument(opt)
+            for opt in CHROME_OPTIONS:
+                options.add_argument(opt)
 
-        # 1. proxy_config /Proxy(proxy_config) selenium object is REALLY unreliable
-        # 2. selenium-wire cant be used because the websocket version conflicts with pypeteer-ng
-        # 3. selenium only allows ONE runner at a time by default!
-        # 4. driver must use quit() or it will continue to block/hold the selenium process!!
+            # 1. proxy_config /Proxy(proxy_config) selenium object is REALLY unreliable
+            # 2. selenium-wire cant be used because the websocket version conflicts with pypeteer-ng
+            # 3. selenium only allows ONE runner at a time by default!
+            # 4. driver must use quit() or it will continue to block/hold the selenium process!!
 
-        if self.proxy_url:
-            options.add_argument(f'--proxy-server={self.proxy_url}')
+            if self.proxy_url:
+                options.add_argument(f'--proxy-server={self.proxy_url}')
 
-        from selenium.webdriver.remote.remote_connection import RemoteConnection
-        from selenium.webdriver.remote.webdriver import WebDriver as RemoteWebDriver
-        driver = None
-        try:
-            # Create the RemoteConnection and set timeout (e.g., 30 seconds)
-            remote_connection = RemoteConnection(
-                self.browser_connection_url,
-            )
-            remote_connection.set_timeout(30)  # seconds
+            from selenium.webdriver.remote.remote_connection import RemoteConnection
+            from selenium.webdriver.remote.webdriver import WebDriver as RemoteWebDriver
+            driver = None
+            try:
+                # Create the RemoteConnection and set timeout (e.g., 30 seconds)
+                remote_connection = RemoteConnection(
+                    self.browser_connection_url,
+                )
+                remote_connection.set_timeout(30)  # seconds
 
-            # Now create the driver with the RemoteConnection
-            driver = RemoteWebDriver(
-                command_executor=remote_connection,
-                options=options
-            )
+                # Now create the driver with the RemoteConnection
+                driver = RemoteWebDriver(
+                    command_executor=remote_connection,
+                    options=options
+                )
 
-            driver.set_page_load_timeout(int(os.getenv("WEBDRIVER_PAGELOAD_TIMEOUT", 45)))
-        except Exception as e:
-            if driver:
-                driver.quit()
-            raise e
+                driver.set_page_load_timeout(int(os.getenv("WEBDRIVER_PAGELOAD_TIMEOUT", 45)))
+            except Exception as e:
+                if driver:
+                    driver.quit()
+                raise e
 
-        try:
-            driver.get(url)
+            try:
+                driver.get(url)
 
-            if not "--window-size" in os.getenv("CHROME_OPTIONS", ""):
-                driver.set_window_size(1280, 1024)
+                if not "--window-size" in os.getenv("CHROME_OPTIONS", ""):
+                    driver.set_window_size(1280, 1024)
 
-            driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
-
-            if self.webdriver_js_execute_code is not None:
-                driver.execute_script(self.webdriver_js_execute_code)
-                # Selenium doesn't automatically wait for actions as good as Playwright, so wait again
                 driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
 
-            # @todo - how to check this? is it possible?
-            self.status_code = 200
-            # @todo somehow we should try to get this working for WebDriver
-            # raise EmptyReply(url=url, status_code=r.status_code)
+                if self.webdriver_js_execute_code is not None:
+                    driver.execute_script(self.webdriver_js_execute_code)
+                    # Selenium doesn't automatically wait for actions as good as Playwright, so wait again
+                    driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+
+                # @todo - how to check this? is it possible?
+                self.status_code = 200
+                # @todo somehow we should try to get this working for WebDriver
+                # raise EmptyReply(url=url, status_code=r.status_code)
+
+                # @todo - dom wait loaded?
+                import time
+                time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay)
+                self.content = driver.page_source
+                self.headers = {}
+                self.screenshot = driver.get_screenshot_as_png()
+            except Exception as e:
+                driver.quit()
+                raise e
 
-            # @todo - dom wait loaded?
-            time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay)
-            self.content = driver.page_source
-            self.headers = {}
-            self.screenshot = driver.get_screenshot_as_png()
-        except Exception as e:
             driver.quit()
-            raise e
-
-        driver.quit()
 
+        # Run the selenium operations in a thread pool to avoid blocking the event loop
+        loop = asyncio.get_event_loop()
+        await loop.run_in_executor(None, _run_sync)

changedetectionio/custom_queue.py

@@ -1,7 +1,43 @@
 import queue
+import asyncio
 from blinker import signal
 from loguru import logger
 
+
+class NotificationQueue(queue.Queue):
+    """
+    Extended Queue that sends a 'notification_event' signal when notifications are added.
+    
+    This class extends the standard Queue and adds a signal emission after a notification
+    is put into the queue. The signal includes the watch UUID if available.
+    """
+    
+    def __init__(self, maxsize=0):
+        super().__init__(maxsize)
+        try:
+            self.notification_event_signal = signal('notification_event')
+        except Exception as e:
+            logger.critical(f"Exception creating notification_event signal: {e}")
+
+    def put(self, item, block=True, timeout=None):
+        # Call the parent's put method first
+        super().put(item, block, timeout)
+        
+        # After putting the notification in the queue, emit signal with watch UUID
+        try:
+            if self.notification_event_signal and isinstance(item, dict):
+                watch_uuid = item.get('uuid')
+                if watch_uuid:
+                    # Send the notification_event signal with the watch UUID
+                    self.notification_event_signal.send(watch_uuid=watch_uuid)
+                    logger.trace(f"NotificationQueue: Emitted notification_event signal for watch UUID {watch_uuid}")
+                else:
+                    # Send signal without UUID for system notifications
+                    self.notification_event_signal.send()
+                    logger.trace("NotificationQueue: Emitted notification_event signal for system notification")
+        except Exception as e:
+            logger.error(f"Exception emitting notification_event signal: {e}")
+
 class SignalPriorityQueue(queue.PriorityQueue):
     """
     Extended PriorityQueue that sends a signal when items with a UUID are added.
@@ -50,3 +86,450 @@ class SignalPriorityQueue(queue.PriorityQueue):
         except Exception as e:
             logger.critical(f"Exception: {e}")
         return item
+    
+    def get_uuid_position(self, target_uuid):
+        """
+        Find the position of a watch UUID in the priority queue.
+        Optimized for large queues - O(n) complexity instead of O(n log n).
+        
+        Args:
+            target_uuid: The UUID to search for
+            
+        Returns:
+            dict: Contains position info or None if not found
+                - position: 0-based position in queue (0 = next to be processed)
+                - total_items: total number of items in queue
+                - priority: the priority value of the found item
+        """
+        with self.mutex:
+            queue_list = list(self.queue)
+            total_items = len(queue_list)
+            
+            if total_items == 0:
+                return {
+                    'position': None,
+                    'total_items': 0,
+                    'priority': None,
+                    'found': False
+                }
+            
+            # Find the target item and its priority first - O(n)
+            target_item = None
+            target_priority = None
+            
+            for item in queue_list:
+                if (hasattr(item, 'item') and 
+                    isinstance(item.item, dict) and 
+                    item.item.get('uuid') == target_uuid):
+                    target_item = item
+                    target_priority = item.priority
+                    break
+            
+            if target_item is None:
+                return {
+                    'position': None,
+                    'total_items': total_items,
+                    'priority': None,
+                    'found': False
+                }
+            
+            # Count how many items have higher priority (lower numbers) - O(n)
+            position = 0
+            for item in queue_list:
+                # Items with lower priority numbers are processed first
+                if item.priority < target_priority:
+                    position += 1
+                elif item.priority == target_priority and item != target_item:
+                    # For same priority, count items that come before this one
+                    # (Note: this is approximate since heap order isn't guaranteed for equal priorities)
+                    position += 1
+            
+            return {
+                'position': position,
+                'total_items': total_items,
+                'priority': target_priority,
+                'found': True
+            }
+    
+    def get_all_queued_uuids(self, limit=None, offset=0):
+        """
+        Get UUIDs currently in the queue with their positions.
+        For large queues, use limit/offset for pagination.
+        
+        Args:
+            limit: Maximum number of items to return (None = all)
+            offset: Number of items to skip (for pagination)
+        
+        Returns:
+            dict: Contains items and metadata
+                - items: List of dicts with uuid, position, and priority
+                - total_items: Total number of items in queue
+                - returned_items: Number of items returned
+                - has_more: Whether there are more items after this page
+        """
+        with self.mutex:
+            queue_list = list(self.queue)
+            total_items = len(queue_list)
+            
+            if total_items == 0:
+                return {
+                    'items': [],
+                    'total_items': 0,
+                    'returned_items': 0,
+                    'has_more': False
+                }
+            
+            # For very large queues, warn about performance
+            if total_items > 1000 and limit is None:
+                logger.warning(f"Getting all {total_items} queued items without limit - this may be slow")
+            
+            # Sort only if we need exact positions (expensive for large queues)
+            if limit is not None and limit <= 100:
+                # For small requests, we can afford to sort
+                queue_items = sorted(queue_list)
+                end_idx = min(offset + limit, len(queue_items)) if limit else len(queue_items)
+                items_to_process = queue_items[offset:end_idx]
+                
+                result = []
+                for position, item in enumerate(items_to_process, start=offset):
+                    if (hasattr(item, 'item') and 
+                        isinstance(item.item, dict) and 
+                        'uuid' in item.item):
+                        
+                        result.append({
+                            'uuid': item.item['uuid'],
+                            'position': position,
+                            'priority': item.priority
+                        })
+                
+                return {
+                    'items': result,
+                    'total_items': total_items,
+                    'returned_items': len(result),
+                    'has_more': (offset + len(result)) < total_items
+                }
+            else:
+                # For large requests, return items with approximate positions
+                # This is much faster O(n) instead of O(n log n)
+                result = []
+                processed = 0
+                skipped = 0
+                
+                for item in queue_list:
+                    if (hasattr(item, 'item') and 
+                        isinstance(item.item, dict) and 
+                        'uuid' in item.item):
+                        
+                        if skipped < offset:
+                            skipped += 1
+                            continue
+                        
+                        if limit and processed >= limit:
+                            break
+                        
+                        # Approximate position based on priority comparison
+                        approx_position = sum(1 for other in queue_list if other.priority < item.priority)
+                        
+                        result.append({
+                            'uuid': item.item['uuid'],
+                            'position': approx_position,  # Approximate
+                            'priority': item.priority
+                        })
+                        processed += 1
+                
+                return {
+                    'items': result,
+                    'total_items': total_items,
+                    'returned_items': len(result),
+                    'has_more': (offset + len(result)) < total_items,
+                    'note': 'Positions are approximate for performance with large queues'
+                }
+    
+    def get_queue_summary(self):
+        """
+        Get a quick summary of queue state without expensive operations.
+        O(n) complexity - fast even for large queues.
+        
+        Returns:
+            dict: Queue summary statistics
+        """
+        with self.mutex:
+            queue_list = list(self.queue)
+            total_items = len(queue_list)
+            
+            if total_items == 0:
+                return {
+                    'total_items': 0,
+                    'priority_breakdown': {},
+                    'immediate_items': 0,
+                    'clone_items': 0,
+                    'scheduled_items': 0
+                }
+            
+            # Count items by priority type - O(n)
+            immediate_items = 0  # priority 1
+            clone_items = 0      # priority 5  
+            scheduled_items = 0  # priority > 100 (timestamps)
+            priority_counts = {}
+            
+            for item in queue_list:
+                priority = item.priority
+                priority_counts[priority] = priority_counts.get(priority, 0) + 1
+                
+                if priority == 1:
+                    immediate_items += 1
+                elif priority == 5:
+                    clone_items += 1
+                elif priority > 100:
+                    scheduled_items += 1
+            
+            return {
+                'total_items': total_items,
+                'priority_breakdown': priority_counts,
+                'immediate_items': immediate_items,
+                'clone_items': clone_items,
+                'scheduled_items': scheduled_items,
+                'min_priority': min(priority_counts.keys()) if priority_counts else None,
+                'max_priority': max(priority_counts.keys()) if priority_counts else None
+            }
+
+
+class AsyncSignalPriorityQueue(asyncio.PriorityQueue):
+    """
+    Async version of SignalPriorityQueue that sends signals when items are added/removed.
+    
+    This class extends asyncio.PriorityQueue and maintains the same signal behavior
+    as the synchronous version for real-time UI updates.
+    """
+    
+    def __init__(self, maxsize=0):
+        super().__init__(maxsize)
+        try:
+            self.queue_length_signal = signal('queue_length')
+        except Exception as e:
+            logger.critical(f"Exception: {e}")
+
+    async def put(self, item):
+        # Call the parent's put method first
+        await super().put(item)
+        
+        # After putting the item in the queue, check if it has a UUID and emit signal
+        if hasattr(item, 'item') and isinstance(item.item, dict) and 'uuid' in item.item:
+            uuid = item.item['uuid']
+            # Get the signal and send it if it exists
+            watch_check_update = signal('watch_check_update')
+            if watch_check_update:
+                # Send the watch_uuid parameter
+                watch_check_update.send(watch_uuid=uuid)
+        
+        # Send queue_length signal with current queue size
+        try:
+            if self.queue_length_signal:
+                self.queue_length_signal.send(length=self.qsize())
+        except Exception as e:
+            logger.critical(f"Exception: {e}")
+
+    async def get(self):
+        # Call the parent's get method first
+        item = await super().get()
+        
+        # Send queue_length signal with current queue size
+        try:
+            if self.queue_length_signal:
+                self.queue_length_signal.send(length=self.qsize())
+        except Exception as e:
+            logger.critical(f"Exception: {e}")
+        return item
+    
+    @property
+    def queue(self):
+        """
+        Provide compatibility with sync PriorityQueue.queue access
+        Returns the internal queue for template access
+        """
+        return self._queue if hasattr(self, '_queue') else []
+    
+    def get_uuid_position(self, target_uuid):
+        """
+        Find the position of a watch UUID in the async priority queue.
+        Optimized for large queues - O(n) complexity instead of O(n log n).
+        
+        Args:
+            target_uuid: The UUID to search for
+            
+        Returns:
+            dict: Contains position info or None if not found
+                - position: 0-based position in queue (0 = next to be processed)
+                - total_items: total number of items in queue
+                - priority: the priority value of the found item
+        """
+        queue_list = list(self._queue)
+        total_items = len(queue_list)
+        
+        if total_items == 0:
+            return {
+                'position': None,
+                'total_items': 0,
+                'priority': None,
+                'found': False
+            }
+        
+        # Find the target item and its priority first - O(n)
+        target_item = None
+        target_priority = None
+        
+        for item in queue_list:
+            if (hasattr(item, 'item') and 
+                isinstance(item.item, dict) and 
+                item.item.get('uuid') == target_uuid):
+                target_item = item
+                target_priority = item.priority
+                break
+        
+        if target_item is None:
+            return {
+                'position': None,
+                'total_items': total_items,
+                'priority': None,
+                'found': False
+            }
+        
+        # Count how many items have higher priority (lower numbers) - O(n)
+        position = 0
+        for item in queue_list:
+            if item.priority < target_priority:
+                position += 1
+            elif item.priority == target_priority and item != target_item:
+                position += 1
+        
+        return {
+            'position': position,
+            'total_items': total_items,
+            'priority': target_priority,
+            'found': True
+        }
+    
+    def get_all_queued_uuids(self, limit=None, offset=0):
+        """
+        Get UUIDs currently in the async queue with their positions.
+        For large queues, use limit/offset for pagination.
+        
+        Args:
+            limit: Maximum number of items to return (None = all)
+            offset: Number of items to skip (for pagination)
+        
+        Returns:
+            dict: Contains items and metadata (same structure as sync version)
+        """
+        queue_list = list(self._queue)
+        total_items = len(queue_list)
+        
+        if total_items == 0:
+            return {
+                'items': [],
+                'total_items': 0,
+                'returned_items': 0,
+                'has_more': False
+            }
+        
+        # Same logic as sync version but without mutex
+        if limit is not None and limit <= 100:
+            queue_items = sorted(queue_list)
+            end_idx = min(offset + limit, len(queue_items)) if limit else len(queue_items)
+            items_to_process = queue_items[offset:end_idx]
+            
+            result = []
+            for position, item in enumerate(items_to_process, start=offset):
+                if (hasattr(item, 'item') and 
+                    isinstance(item.item, dict) and 
+                    'uuid' in item.item):
+                    
+                    result.append({
+                        'uuid': item.item['uuid'],
+                        'position': position,
+                        'priority': item.priority
+                    })
+            
+            return {
+                'items': result,
+                'total_items': total_items,
+                'returned_items': len(result),
+                'has_more': (offset + len(result)) < total_items
+            }
+        else:
+            # Fast approximate positions for large queues
+            result = []
+            processed = 0
+            skipped = 0
+            
+            for item in queue_list:
+                if (hasattr(item, 'item') and 
+                    isinstance(item.item, dict) and 
+                    'uuid' in item.item):
+                    
+                    if skipped < offset:
+                        skipped += 1
+                        continue
+                    
+                    if limit and processed >= limit:
+                        break
+                    
+                    approx_position = sum(1 for other in queue_list if other.priority < item.priority)
+                    
+                    result.append({
+                        'uuid': item.item['uuid'],
+                        'position': approx_position,
+                        'priority': item.priority
+                    })
+                    processed += 1
+            
+            return {
+                'items': result,
+                'total_items': total_items,
+                'returned_items': len(result),
+                'has_more': (offset + len(result)) < total_items,
+                'note': 'Positions are approximate for performance with large queues'
+            }
+    
+    def get_queue_summary(self):
+        """
+        Get a quick summary of async queue state.
+        O(n) complexity - fast even for large queues.
+        """
+        queue_list = list(self._queue)
+        total_items = len(queue_list)
+        
+        if total_items == 0:
+            return {
+                'total_items': 0,
+                'priority_breakdown': {},
+                'immediate_items': 0,
+                'clone_items': 0,
+                'scheduled_items': 0
+            }
+        
+        immediate_items = 0
+        clone_items = 0
+        scheduled_items = 0
+        priority_counts = {}
+        
+        for item in queue_list:
+            priority = item.priority
+            priority_counts[priority] = priority_counts.get(priority, 0) + 1
+            
+            if priority == 1:
+                immediate_items += 1
+            elif priority == 5:
+                clone_items += 1
+            elif priority > 100:
+                scheduled_items += 1
+        
+        return {
+            'total_items': total_items,
+            'priority_breakdown': priority_counts,
+            'immediate_items': immediate_items,
+            'clone_items': clone_items,
+            'scheduled_items': scheduled_items,
+            'min_priority': min(priority_counts.keys()) if priority_counts else None,
+            'max_priority': max(priority_counts.keys()) if priority_counts else None
+        }

changedetectionio/flask_app.py

@@ -4,6 +4,7 @@ import flask_login
 import locale
 import os
 import queue
+import sys
 import threading
 import time
 import timeago
@@ -11,18 +12,17 @@ from blinker import signal
 
 from changedetectionio.strtobool import strtobool
 from threading import Event
-from changedetectionio.custom_queue import SignalPriorityQueue
+from changedetectionio.queue_handlers import RecheckPriorityQueue, NotificationQueue
+from changedetectionio import worker_handler
 
 from flask import (
     Flask,
     abort,
     flash,
-    make_response,
     redirect,
     render_template,
     request,
     send_from_directory,
-    session,
     url_for,
 )
 from flask_compress import Compress as FlaskCompress
@@ -38,20 +38,19 @@ from loguru import logger
 
 from changedetectionio import __version__
 from changedetectionio import queuedWatchMetaData
-from changedetectionio.api import Watch, WatchHistory, WatchSingleHistory, CreateWatch, Import, SystemInfo, Tag, Tags, Notifications
+from changedetectionio.api import Watch, WatchHistory, WatchSingleHistory, CreateWatch, Import, SystemInfo, Tag, Tags, Notifications, WatchFavicon
 from changedetectionio.api.Search import Search
 from .time_handler import is_within_schedule
 
 datastore = None
 
 # Local
-running_update_threads = []
 ticker_thread = None
-
 extra_stylesheets = []
 
-update_q = SignalPriorityQueue()
-notification_q = queue.Queue()
+# Use bulletproof janus-based queues for sync/async reliability  
+update_q = RecheckPriorityQueue()
+notification_q = NotificationQueue()
 MAX_QUEUE_SIZE = 2000
 
 app = Flask(__name__,
@@ -99,7 +98,7 @@ watch_api = Api(app, decorators=[csrf.exempt])
 def init_app_secret(datastore_path):
     secret = ""
 
-    path = "{}/secret.txt".format(datastore_path)
+    path = os.path.join(datastore_path, "secret.txt")
 
     try:
         with open(path, "r") as f:
@@ -145,10 +144,32 @@ def _jinja2_filter_format_number_locale(value: float) -> str:
 
 @app.template_global('is_checking_now')
 def _watch_is_checking_now(watch_obj, format="%Y-%m-%d %H:%M:%S"):
-    # Worker thread tells us which UUID it is currently processing.
-    for t in running_update_threads:
-        if t.current_uuid == watch_obj['uuid']:
-            return True
+    return worker_handler.is_watch_running(watch_obj['uuid'])
+
+@app.template_global('get_watch_queue_position')
+def _get_watch_queue_position(watch_obj):
+    """Get the position of a watch in the queue"""
+    uuid = watch_obj['uuid']
+    return update_q.get_uuid_position(uuid)
+
+@app.template_global('get_current_worker_count')
+def _get_current_worker_count():
+    """Get the current number of operational workers"""
+    return worker_handler.get_worker_count()
+
+@app.template_global('get_worker_status_info')
+def _get_worker_status_info():
+    """Get detailed worker status information for display"""
+    status = worker_handler.get_worker_status()
+    running_uuids = worker_handler.get_running_uuids()
+    
+    return {
+        'count': status['worker_count'],
+        'type': status['worker_type'],
+        'active_workers': len(running_uuids),
+        'processing_watches': running_uuids,
+        'loop_running': status.get('async_loop_running', None)
+    }
 
 
 # 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
@@ -284,7 +305,9 @@ def changedetection_app(config=None, datastore_o=None):
     watch_api.add_resource(WatchSingleHistory,
                            '/api/v1/watch/<string:uuid>/history/<string:timestamp>',
                            resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
-
+    watch_api.add_resource(WatchFavicon,
+                           '/api/v1/watch/<string:uuid>/favicon',
+                           resource_class_kwargs={'datastore': datastore})
     watch_api.add_resource(WatchHistory,
                            '/api/v1/watch/<string:uuid>/history',
                            resource_class_kwargs={'datastore': datastore})
@@ -306,7 +329,7 @@ def changedetection_app(config=None, datastore_o=None):
                            resource_class_kwargs={'datastore': datastore})
 
     watch_api.add_resource(Tag, '/api/v1/tag', '/api/v1/tag/<string:uuid>',
-                           resource_class_kwargs={'datastore': datastore})
+                           resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
                            
     watch_api.add_resource(Search, '/api/v1/search',
                            resource_class_kwargs={'datastore': datastore})
@@ -404,6 +427,32 @@ def changedetection_app(config=None, datastore_o=None):
             except FileNotFoundError:
                 abort(404)
 
+        if group == 'favicon':
+            # Could be sensitive, follow password requirements
+            if datastore.data['settings']['application']['password'] and not flask_login.current_user.is_authenticated:
+                abort(403)
+            # Get the watch object
+            watch = datastore.data['watching'].get(filename)
+            if not watch:
+                abort(404)
+
+            favicon_filename = watch.get_favicon_filename()
+            if favicon_filename:
+                try:
+                    import magic
+                    mime = magic.from_file(
+                        os.path.join(watch.watch_data_dir, favicon_filename),
+                        mime=True
+                    )
+                except ImportError:
+                    # Fallback, no python-magic
+                    import mimetypes
+                    mime, encoding = mimetypes.guess_type(favicon_filename)
+
+                response = make_response(send_from_directory(watch.watch_data_dir, favicon_filename))
+                response.headers['Content-type'] = mime
+                response.headers['Cache-Control'] = 'max-age=300, must-revalidate'  # Cache for 5 minutes, then revalidate
+                return response
 
         if group == 'visual_selector_data':
             # Could be sensitive, follow password requirements
@@ -470,16 +519,21 @@ def changedetection_app(config=None, datastore_o=None):
 
     # watchlist UI buttons etc
     import changedetectionio.blueprint.ui as ui
-    app.register_blueprint(ui.construct_blueprint(datastore, update_q, running_update_threads, queuedWatchMetaData, watch_check_update))
+    app.register_blueprint(ui.construct_blueprint(datastore, update_q, worker_handler, queuedWatchMetaData, watch_check_update))
 
     import changedetectionio.blueprint.watchlist as watchlist
     app.register_blueprint(watchlist.construct_blueprint(datastore=datastore, update_q=update_q, queuedWatchMetaData=queuedWatchMetaData), url_prefix='')
 
-    # Initialize Socket.IO server
-    from changedetectionio.realtime.socket_server import init_socketio
-    global socketio_server
-    socketio_server = init_socketio(app, datastore)
-    logger.info("Socket.IO server initialized")
+    # Initialize Socket.IO server conditionally based on settings
+    socket_io_enabled = datastore.data['settings']['application']['ui'].get('socket_io_enabled', True)
+    if socket_io_enabled:
+        from changedetectionio.realtime.socket_server import init_socketio
+        global socketio_server
+        socketio_server = init_socketio(app, datastore)
+        logger.info("Socket.IO server initialized")
+    else:
+        logger.info("Socket.IO server disabled via settings")
+        socketio_server = None
 
     # Memory cleanup endpoint
     @app.route('/gc-cleanup', methods=['GET'])
@@ -491,12 +545,91 @@ def changedetection_app(config=None, datastore_o=None):
         result = memory_cleanup(app)
         return jsonify({"status": "success", "message": "Memory cleanup completed", "result": result})
 
+    # Worker health check endpoint
+    @app.route('/worker-health', methods=['GET'])
+    @login_optionally_required
+    def worker_health():
+        from flask import jsonify
+        
+        expected_workers = int(os.getenv("FETCH_WORKERS", datastore.data['settings']['requests']['workers']))
+        
+        # Get basic status
+        status = worker_handler.get_worker_status()
+        
+        # Perform health check
+        health_result = worker_handler.check_worker_health(
+            expected_count=expected_workers,
+            update_q=update_q,
+            notification_q=notification_q,
+            app=app,
+            datastore=datastore
+        )
+        
+        return jsonify({
+            "status": "success",
+            "worker_status": status,
+            "health_check": health_result,
+            "expected_workers": expected_workers
+        })
+
+    # Queue status endpoint
+    @app.route('/queue-status', methods=['GET'])
+    @login_optionally_required
+    def queue_status():
+        from flask import jsonify, request
+        
+        # Get specific UUID position if requested
+        target_uuid = request.args.get('uuid')
+        
+        if target_uuid:
+            position_info = update_q.get_uuid_position(target_uuid)
+            return jsonify({
+                "status": "success",
+                "uuid": target_uuid,
+                "queue_position": position_info
+            })
+        else:
+            # Get pagination parameters
+            limit = request.args.get('limit', type=int)
+            offset = request.args.get('offset', type=int, default=0)
+            summary_only = request.args.get('summary', type=bool, default=False)
+            
+            if summary_only:
+                # Fast summary for large queues
+                summary = update_q.get_queue_summary()
+                return jsonify({
+                    "status": "success",
+                    "queue_summary": summary
+                })
+            else:
+                # Get queued items with pagination support
+                if limit is None:
+                    # Default limit for large queues to prevent performance issues
+                    queue_size = update_q.qsize()
+                    if queue_size > 100:
+                        limit = 50
+                        logger.warning(f"Large queue ({queue_size} items) detected, limiting to {limit} items. Use ?limit=N for more.")
+                
+                all_queued = update_q.get_all_queued_uuids(limit=limit, offset=offset)
+                return jsonify({
+                    "status": "success",
+                    "queue_size": update_q.qsize(),
+                    "queued_data": all_queued
+                })
+
+    # Start the async workers during app initialization
+    # Can be overridden by ENV or use the default settings
+    n_workers = int(os.getenv("FETCH_WORKERS", datastore.data['settings']['requests']['workers']))
+    logger.info(f"Starting {n_workers} workers during app initialization")
+    worker_handler.start_workers(n_workers, update_q, notification_q, app, datastore)
+
     # @todo handle ctrl break
     ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks).start()
     threading.Thread(target=notification_runner).start()
 
+    in_pytest = "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ
     # Check for new release version, but not when running in test/build or pytest
-    if not os.getenv("GITHUB_REF", False) and not strtobool(os.getenv('DISABLE_VERSION_CHECK', 'no')):
+    if not os.getenv("GITHUB_REF", False) and not strtobool(os.getenv('DISABLE_VERSION_CHECK', 'no')) and not in_pytest:
         threading.Thread(target=check_for_new_version).start()
 
     # Return the Flask app - the Socket.IO will be attached to it but initialized separately
@@ -588,27 +721,35 @@ def notification_runner():
 # Threaded runner, look for new watches to feed into the Queue.
 def ticker_thread_check_time_launch_checks():
     import random
-    from changedetectionio import update_worker
     proxy_last_called_time = {}
+    last_health_check = 0
 
     recheck_time_minimum_seconds = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
     logger.debug(f"System env MINIMUM_SECONDS_RECHECK_TIME {recheck_time_minimum_seconds}")
 
-    # Spin up Workers that do the fetching
-    # Can be overriden by ENV or use the default settings
-    n_workers = int(os.getenv("FETCH_WORKERS", datastore.data['settings']['requests']['workers']))
-    for _ in range(n_workers):
-        new_worker = update_worker.update_worker(update_q, notification_q, app, datastore)
-        running_update_threads.append(new_worker)
-        new_worker.start()
+    # Workers are now started during app initialization, not here
 
     while not app.config.exit.is_set():
 
+        # Periodic worker health check (every 60 seconds)
+        now = time.time()
+        if now - last_health_check > 60:
+            expected_workers = int(os.getenv("FETCH_WORKERS", datastore.data['settings']['requests']['workers']))
+            health_result = worker_handler.check_worker_health(
+                expected_count=expected_workers,
+                update_q=update_q,
+                notification_q=notification_q,
+                app=app,
+                datastore=datastore
+            )
+            
+            if health_result['status'] != 'healthy':
+                logger.warning(f"Worker health check: {health_result['message']}")
+                
+            last_health_check = now
+
         # Get a list of watches by UUID that are currently fetching data
-        running_uuids = []
-        for t in running_update_threads:
-            if t.current_uuid:
-                running_uuids.append(t.current_uuid)
+        running_uuids = worker_handler.get_running_uuids()
 
         # Re #232 - Deepcopy the data incase it changes while we're iterating through it all
         watch_uuid_list = []
@@ -703,16 +844,22 @@ def ticker_thread_check_time_launch_checks():
 
                     # Use Epoch time as priority, so we get a "sorted" PriorityQueue, but we can still push a priority 1 into it.
                     priority = int(time.time())
-                    logger.debug(
-                        f"> Queued watch UUID {uuid} "
-                        f"last checked at {watch['last_checked']} "
-                        f"queued at {now:0.2f} priority {priority} "
-                        f"jitter {watch.jitter_seconds:0.2f}s, "
-                        f"{now - watch['last_checked']:0.2f}s since last checked")
 
                     # Into the queue with you
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=priority, item={'uuid': uuid}))
-
+                    queued_successfully = worker_handler.queue_item_async_safe(update_q,
+                                                                               queuedWatchMetaData.PrioritizedItem(priority=priority,
+                                                                                                                   item={'uuid': uuid})
+                                                                               )
+                    if queued_successfully:
+                        logger.debug(
+                            f"> Queued watch UUID {uuid} "
+                            f"last checked at {watch['last_checked']} "
+                            f"queued at {now:0.2f} priority {priority} "
+                            f"jitter {watch.jitter_seconds:0.2f}s, "
+                            f"{now - watch['last_checked']:0.2f}s since last checked")
+                    else:
+                        logger.critical(f"CRITICAL: Failed to queue watch UUID {uuid} in ticker thread!")
+                        
                     # Reset for next time
                     watch.jitter_seconds = 0
 

changedetectionio/forms.py

@@ -23,11 +23,14 @@ from wtforms import (
 )
 from flask_wtf.file import FileField, FileAllowed
 from wtforms.fields import FieldList
+from wtforms.utils import unset_value
 
 from wtforms.validators import ValidationError
 
 from validators.url import url as url_validator
 
+from changedetectionio.widgets import TernaryNoneBooleanField
+
 
 # default
 # each select <option data-enabled="enabled-0-0"
@@ -54,6 +57,8 @@ valid_method = {
 
 default_method = 'GET'
 allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
+REQUIRE_ATLEAST_ONE_TIME_PART_MESSAGE_DEFAULT='At least one time interval (weeks, days, hours, minutes, or seconds) must be specified.'
+REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT='At least one time interval (weeks, days, hours, minutes, or seconds) must be specified when not using global settings.'
 
 class StringListField(StringField):
     widget = widgets.TextArea()
@@ -210,6 +215,35 @@ class ScheduleLimitForm(Form):
         self.sunday.form.enabled.label.text = "Sunday"
 
 
+def validate_time_between_check_has_values(form):
+    """
+    Custom validation function for TimeBetweenCheckForm.
+    Returns True if at least one time interval field has a value > 0.
+    """
+    res = any([
+        form.weeks.data and int(form.weeks.data) > 0,
+        form.days.data and int(form.days.data) > 0,
+        form.hours.data and int(form.hours.data) > 0,
+        form.minutes.data and int(form.minutes.data) > 0,
+        form.seconds.data and int(form.seconds.data) > 0
+    ])
+
+    return res
+
+
+class RequiredTimeInterval(object):
+    """
+    WTForms validator that ensures at least one time interval field has a value > 0.
+    Use this with FormField(TimeBetweenCheckForm, validators=[RequiredTimeInterval()]).
+    """
+    def __init__(self, message=None):
+        self.message = message or 'At least one time interval (weeks, days, hours, minutes, or seconds) must be specified.'
+
+    def __call__(self, form, field):
+        if not validate_time_between_check_has_values(field.form):
+            raise ValidationError(self.message)
+
+
 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")])
@@ -218,6 +252,123 @@ class TimeBetweenCheckForm(Form):
     seconds = IntegerField('Seconds', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
     # @todo add total seconds minimum validatior = minimum_seconds_recheck_time
 
+    def __init__(self, formdata=None, obj=None, prefix="", data=None, meta=None, **kwargs):
+        super().__init__(formdata, obj, prefix, data, meta, **kwargs)
+        self.require_at_least_one = kwargs.get('require_at_least_one', False)
+        self.require_at_least_one_message = kwargs.get('require_at_least_one_message', REQUIRE_ATLEAST_ONE_TIME_PART_MESSAGE_DEFAULT)
+
+    def validate(self, **kwargs):
+        """Custom validation that can optionally require at least one time interval."""
+        # Run normal field validation first
+        if not super().validate(**kwargs):
+            return False
+
+        # Apply optional "at least one" validation
+        if self.require_at_least_one:
+            if not validate_time_between_check_has_values(self):
+                # Add error to the form's general errors (not field-specific)
+                if not hasattr(self, '_formdata_errors'):
+                    self._formdata_errors = []
+                self._formdata_errors.append(self.require_at_least_one_message)
+                return False
+
+        return True
+
+
+class EnhancedFormField(FormField):
+    """
+    An enhanced FormField that supports conditional validation with top-level error messages.
+    Adds a 'top_errors' property for validation errors at the FormField level.
+    """
+
+    def __init__(self, form_class, label=None, validators=None, separator="-",
+                 conditional_field=None, conditional_message=None, conditional_test_function=None, **kwargs):
+        """
+        Initialize EnhancedFormField with optional conditional validation.
+
+        :param conditional_field: Name of the field this FormField depends on (e.g. 'time_between_check_use_default')
+        :param conditional_message: Error message to show when validation fails
+        :param conditional_test_function: Custom function to test if FormField has valid values.
+                                        Should take self.form as parameter and return True if valid.
+        """
+        super().__init__(form_class, label, validators, separator, **kwargs)
+        self.top_errors = []
+        self.conditional_field = conditional_field
+        self.conditional_message = conditional_message or "At least one field must have a value when not using defaults."
+        self.conditional_test_function = conditional_test_function
+
+    def validate(self, form, extra_validators=()):
+        """
+        Custom validation that supports conditional logic and stores top-level errors.
+        """
+        self.top_errors = []
+
+        # First run the normal FormField validation
+        base_valid = super().validate(form, extra_validators)
+
+        # Apply conditional validation if configured
+        if self.conditional_field and hasattr(form, self.conditional_field):
+            conditional_field_obj = getattr(form, self.conditional_field)
+
+            # If the conditional field is False/unchecked, check if this FormField has any values
+            if not conditional_field_obj.data:
+                # Use custom test function if provided, otherwise use generic fallback
+                if self.conditional_test_function:
+                    has_any_value = self.conditional_test_function(self.form)
+                else:
+                    # Generic fallback - check if any field has truthy data
+                    has_any_value = any(field.data for field in self.form if hasattr(field, 'data') and field.data)
+
+                if not has_any_value:
+                    self.top_errors.append(self.conditional_message)
+                    base_valid = False
+
+        return base_valid
+
+
+class RequiredFormField(FormField):
+    """
+    A FormField that passes require_at_least_one=True to TimeBetweenCheckForm.
+    Use this when you want the sub-form to always require at least one value.
+    """
+
+    def __init__(self, form_class, label=None, validators=None, separator="-", **kwargs):
+        super().__init__(form_class, label, validators, separator, **kwargs)
+
+    def process(self, formdata, data=unset_value, extra_filters=None):
+        if extra_filters:
+            raise TypeError(
+                "FormField cannot take filters, as the encapsulated"
+                "data is not mutable."
+            )
+
+        if data is unset_value:
+            try:
+                data = self.default()
+            except TypeError:
+                data = self.default
+            self._obj = data
+
+        self.object_data = data
+
+        prefix = self.name + self.separator
+        # Pass require_at_least_one=True to the sub-form
+        if isinstance(data, dict):
+            self.form = self.form_class(formdata=formdata, prefix=prefix, require_at_least_one=True, **data)
+        else:
+            self.form = self.form_class(formdata=formdata, obj=data, prefix=prefix, require_at_least_one=True)
+
+    @property
+    def errors(self):
+        """Include sub-form validation errors"""
+        form_errors = self.form.errors
+        # Add any general form errors to a special 'form' key
+        if hasattr(self.form, '_formdata_errors') and self.form._formdata_errors:
+            form_errors = dict(form_errors)  # Make a copy
+            form_errors['form'] = self.form._formdata_errors
+        return form_errors
+
+
 # Separated by  key:value
 class StringDictKeyValue(StringField):
     widget = widgets.TextArea()
@@ -346,7 +497,7 @@ class ValidateJinja2Template(object):
         joined_data = ' '.join(map(str, field.data)) if isinstance(field.data, list) else f"{field.data}"
 
         try:
-            jinja2_env = ImmutableSandboxedEnvironment(loader=BaseLoader)
+            jinja2_env = ImmutableSandboxedEnvironment(loader=BaseLoader, extensions=['jinja2_time.TimeExtension'])
             jinja2_env.globals.update(notification.valid_tokens)
             # Extra validation tokens provided on the form_class(... extra_tokens={}) setup
             if hasattr(field, 'extra_notification_tokens'):
@@ -396,6 +547,19 @@ def validate_url(test_url):
         # This should be wtforms.validators.
         raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX or incorrect URL format')
 
+
+class ValidateSinglePythonRegexString(object):
+    def __init__(self, message=None):
+        self.message = message
+
+    def __call__(self, form, field):
+        try:
+            re.compile(field.data)
+        except re.error:
+            message = field.gettext('RegEx \'%s\' is not a valid regular expression.')
+            raise ValidationError(message % (field.data))
+
+
 class ValidateListRegex(object):
     """
     Validates that anything that looks like a regex passes as a regex
@@ -414,6 +578,7 @@ class ValidateListRegex(object):
                     message = field.gettext('RegEx \'%s\' is not a valid regular expression.')
                     raise ValidationError(message % (line))
 
+
 class ValidateCSSJSONXPATHInput(object):
     """
     Filter validation
@@ -534,7 +699,6 @@ class commonSettingsForm(Form):
         self.notification_title.extra_notification_tokens = kwargs.get('extra_notification_tokens', {})
         self.notification_urls.extra_notification_tokens = kwargs.get('extra_notification_tokens', {})
 
-    extract_title_as_title = BooleanField('Extract <title> from document and use as watch title', default=False)
     fetch_backend = RadioField(u'Fetch Method', choices=content_fetchers.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     notification_body = TextAreaField('Notification Body', default='{{ watch_url }} had a change.', validators=[validators.Optional(), ValidateJinja2Template()])
     notification_format = SelectField('Notification format', choices=valid_notification_formats.keys())
@@ -568,11 +732,16 @@ class processor_text_json_diff_form(commonSettingsForm):
     url = fields.URLField('URL', validators=[validateURL()])
     tags = StringTagUUID('Group tag', [validators.Optional()], default='')
 
-    time_between_check = FormField(TimeBetweenCheckForm)
+    time_between_check = EnhancedFormField(
+        TimeBetweenCheckForm,
+        conditional_field='time_between_check_use_default',
+        conditional_message=REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT,
+        conditional_test_function=validate_time_between_check_has_values
+    )
 
     time_schedule_limit = FormField(ScheduleLimitForm)
 
-    time_between_check_use_default = BooleanField('Use global settings for time between check', default=False)
+    time_between_check_use_default = BooleanField('Use global settings for time between check and scheduler.', default=False)
 
     include_filters = StringListField('CSS/JSONPath/JQ/XPath Filters', [ValidateCSSJSONXPATHInput()], default='')
 
@@ -590,6 +759,7 @@ class processor_text_json_diff_form(commonSettingsForm):
     check_unique_lines = BooleanField('Only trigger when unique lines appear in all history', default=False)
     remove_duplicate_lines = BooleanField('Remove duplicate lines of text', default=False)
     sort_text_alphabetically =  BooleanField('Sort text alphabetically', default=False)
+    strip_ignored_lines = TernaryNoneBooleanField('Strip ignored lines', default=None)
     trim_text_whitespace = BooleanField('Trim whitespace before and after text', default=False)
 
     filter_text_added = BooleanField('Added lines', default=True)
@@ -602,18 +772,18 @@ class processor_text_json_diff_form(commonSettingsForm):
     text_should_not_be_present = StringListField('Block change-detection while text matches', [validators.Optional(), ValidateListRegex()])
     webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
 
-    save_button = SubmitField('Save', render_kw={"class": "pure-button button-small pure-button-primary"})
+    save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
 
     proxy = RadioField('Proxy')
+    # filter_failure_notification_send @todo make ternary
     filter_failure_notification_send = BooleanField(
         'Send a notification when the filter can no longer be found on the page', default=False)
-
-    notification_muted = BooleanField('Notifications Muted / Off', default=False)
+    notification_muted = TernaryNoneBooleanField('Notifications', default=None, yes_text="Muted", no_text="On")
     notification_screenshot = BooleanField('Attach screenshot to notification (where possible)', default=False)
 
     conditions_match_logic = RadioField(u'Match', choices=[('ALL', 'Match all of the following'),('ANY', 'Match any of the following')], default='ALL')
     conditions = FieldList(FormField(ConditionFormRow), min_entries=1)  # Add rule logic here
-
+    use_page_title_in_list = TernaryNoneBooleanField('Use page <title> in list', default=None)
 
     def extra_tab_content(self):
         return None
@@ -713,12 +883,18 @@ class DefaultUAInputForm(Form):
 
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
-    time_between_check = FormField(TimeBetweenCheckForm)
+    time_between_check = RequiredFormField(TimeBetweenCheckForm)
     time_schedule_limit = FormField(ScheduleLimitForm)
     proxy = RadioField('Proxy')
     jitter_seconds = IntegerField('Random jitter seconds ± check',
                                   render_kw={"style": "width: 5em;"},
                                   validators=[validators.NumberRange(min=0, message="Should contain zero or more seconds")])
+    
+    workers = IntegerField('Number of fetch workers',
+                          render_kw={"style": "width: 5em;"},
+                          validators=[validators.NumberRange(min=1, max=50,
+                                                             message="Should be between 1 and 50")])
+    
     extra_proxies = FieldList(FormField(SingleExtraProxy), min_entries=5)
     extra_browsers = FieldList(FormField(SingleExtraBrowser), min_entries=5)
 
@@ -732,7 +908,10 @@ class globalSettingsRequestForm(Form):
                     return False
 
 class globalSettingsApplicationUIForm(Form):
-    open_diff_in_new_tab = BooleanField('Open diff page in a new tab', default=True, validators=[validators.Optional()])
+    open_diff_in_new_tab = BooleanField("Open 'History' page in a new tab", default=True, validators=[validators.Optional()])
+    socket_io_enabled = BooleanField('Realtime UI Updates Enabled', default=True, validators=[validators.Optional()])
+    favicons_enabled = BooleanField('Favicons Enabled', default=True, validators=[validators.Optional()])
+    use_page_title_in_list = BooleanField('Use page <title> in watch overview list') #BooleanField=True
 
 # datastore.data['settings']['application']..
 class globalSettingsApplicationForm(commonSettingsForm):
@@ -757,7 +936,8 @@ class globalSettingsApplicationForm(commonSettingsForm):
 
     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()])
+    shared_diff_access = BooleanField('Allow anonymous access to watch history page when password is enabled', default=False, validators=[validators.Optional()])
+    strip_ignored_lines = BooleanField('Strip ignored lines')
     rss_hide_muted_watches = BooleanField('Hide muted watches from RSS feed', default=True,
                                       validators=[validators.Optional()])
     filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',
@@ -779,9 +959,9 @@ class globalSettingsForm(Form):
 
     requests = FormField(globalSettingsRequestForm)
     application = FormField(globalSettingsApplicationForm)
-    save_button = SubmitField('Save', render_kw={"class": "pure-button button-small pure-button-primary"})
+    save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
 
 
 class extractDataForm(Form):
-    extract_regex = StringField('RegEx to extract', validators=[validators.Length(min=1, message="Needs a RegEx")])
+    extract_regex = StringField('RegEx to extract', validators=[validators.DataRequired(), ValidateSinglePythonRegexString()])
     extract_submit_button = SubmitField('Extract as CSV', render_kw={"class": "pure-button pure-button-primary"})

changedetectionio/html_tools.py

@@ -1,6 +1,7 @@
 from loguru import logger
 from lxml import etree
 from typing import List
+import html
 import json
 import re
 
@@ -9,6 +10,11 @@ TEXT_FILTER_LIST_LINE_SUFFIX = "<br>"
 TRANSLATE_WHITESPACE_TABLE = str.maketrans('', '', '\r\n\t ')
 PERL_STYLE_REGEX = r'^/(.*?)/([a-z]*)?$'
 
+TITLE_RE = re.compile(r"<title[^>]*>(.*?)</title>", re.I | re.S)
+META_CS  = re.compile(r'<meta[^>]+charset=["\']?\s*([a-z0-9_\-:+.]+)', re.I)
+META_CT  = re.compile(r'<meta[^>]+http-equiv=["\']?content-type["\']?[^>]*content=["\'][^>]*charset=([a-z0-9_\-:+.]+)', re.I)
+
+
 # 'price' , 'lowPrice', 'highPrice' are usually under here
 # 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"]
@@ -510,3 +516,43 @@ def get_triggered_text(content, trigger_text):
         i += 1
 
     return triggered_text
+
+
+def extract_title(data: bytes | str, sniff_bytes: int = 2048, scan_chars: int = 8192) -> str | None:
+    try:
+        # Only decode/process the prefix we need for title extraction
+        match data:
+            case bytes() if data.startswith((b"\xff\xfe", b"\xfe\xff")):
+                prefix = data[:scan_chars * 2].decode("utf-16", errors="replace")
+            case bytes() if data.startswith((b"\xff\xfe\x00\x00", b"\x00\x00\xfe\xff")):
+                prefix = data[:scan_chars * 4].decode("utf-32", errors="replace")
+            case bytes():
+                try:
+                    prefix = data[:scan_chars].decode("utf-8")
+                except UnicodeDecodeError:
+                    try:
+                        head = data[:sniff_bytes].decode("ascii", errors="ignore")
+                        if m := (META_CS.search(head) or META_CT.search(head)):
+                            enc = m.group(1).lower()
+                        else:
+                            enc = "cp1252"
+                        prefix = data[:scan_chars * 2].decode(enc, errors="replace")
+                    except Exception as e:
+                        logger.error(f"Title extraction encoding detection failed: {e}")
+                        return None
+            case str():
+                prefix = data[:scan_chars] if len(data) > scan_chars else data
+            case _:
+                logger.error(f"Title extraction received unsupported data type: {type(data)}")
+                return None
+
+        # Search only in the prefix
+        if m := TITLE_RE.search(prefix):
+            title = html.unescape(" ".join(m.group(1).split())).strip()
+            # Some safe limit
+            return title[:2000]
+        return None
+        
+    except Exception as e:
+        logger.error(f"Title extraction failed: {e}")
+        return None

changedetectionio/model/App.py

@@ -39,12 +39,12 @@ class model(dict):
                     'api_access_token_enabled': True,
                     'base_url' : None,
                     '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,
+                    'ignore_status_codes': False, #@todo implement, as ternary.
                     'notification_body': default_notification_body,
                     'notification_format': default_notification_format,
                     'notification_title': default_notification_title,
@@ -57,11 +57,15 @@ class model(dict):
                     'rss_hide_muted_watches': True,
                     'schema_version' : 0,
                     'shared_diff_access': False,
-                    'webdriver_delay': None , # Extra delay in seconds before extracting text
+                    'strip_ignored_lines': False,
                     'tags': {}, #@todo use Tag.model initialisers
                     'timezone': None, # Default IANA timezone name
+                    'webdriver_delay': None , # Extra delay in seconds before extracting text
                     'ui': {
+                        'use_page_title_in_list': True,
                         'open_diff_in_new_tab': True,
+                        'socket_io_enabled': True,
+                        'favicons_enabled': True
                     },
                 }
             }

changedetectionio/model/Watch.py

@@ -8,11 +8,14 @@ import re
 from pathlib import Path
 from loguru import logger
 
+from .. import safe_jinja
 from ..html_tools import TRANSLATE_WHITESPACE_TABLE
 
 # Allowable protocols, protects against javascript: etc
 # file:// is further checked by ALLOW_FILE_URI
 SAFE_PROTOCOL_REGEX='^(http|https|ftp|file):'
+FAVICON_RESAVE_THRESHOLD_SECONDS=86400
+
 
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
 mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
@@ -102,6 +105,13 @@ class model(watch_base):
             return 'DISABLED'
         return ready_url
 
+    @property
+    def domain_only_from_link(self):
+        from urllib.parse import urlparse
+        parsed = urlparse(self.link)
+        domain = parsed.hostname
+        return domain
+
     def clear_watch(self):
         import pathlib
 
@@ -159,8 +169,8 @@ class model(watch_base):
 
     @property
     def label(self):
-        # Used for sorting
-        return self.get('title') if self.get('title') else self.get('url')
+        # Used for sorting, display, etc
+        return self.get('title') or self.get('page_title') or self.link
 
     @property
     def last_changed(self):
@@ -412,6 +422,154 @@ class model(watch_base):
         # False is not an option for AppRise, must be type None
         return None
 
+    def favicon_is_expired(self):
+        favicon_fname = self.get_favicon_filename()
+        import glob
+        import time
+
+        if not favicon_fname:
+            return True
+        try:
+            fname = next(iter(glob.glob(os.path.join(self.watch_data_dir, "favicon.*"))), None)
+            logger.trace(f"Favicon file maybe found at {fname}")
+            if os.path.isfile(fname):
+                file_age = int(time.time() - os.path.getmtime(fname))
+                logger.trace(f"Favicon file age is {file_age}s")
+                if file_age < FAVICON_RESAVE_THRESHOLD_SECONDS:
+                    return False
+        except Exception as e:
+            logger.critical(f"Exception checking Favicon age {str(e)}")
+            return True
+
+        # Also in the case that the file didnt exist
+        return True
+
+    def bump_favicon(self, url, favicon_base_64: str) -> None:
+        from urllib.parse import urlparse
+        import base64
+        import binascii
+        decoded = None
+
+        if url:
+            try:
+                parsed = urlparse(url)
+                filename = os.path.basename(parsed.path)
+                (base, extension) = filename.lower().strip().rsplit('.', 1)
+            except ValueError:
+                logger.error(f"UUID: {self.get('uuid')} Cant work out file extension from '{url}'")
+                return None
+        else:
+            # Assume favicon.ico
+            base = "favicon"
+            extension = "ico"
+
+        fname = os.path.join(self.watch_data_dir, f"favicon.{extension}")
+
+        try:
+            # validate=True makes sure the string only contains valid base64 chars
+            decoded = base64.b64decode(favicon_base_64, validate=True)
+        except (binascii.Error, ValueError) as e:
+            logger.warning(f"UUID: {self.get('uuid')} FavIcon save data (Base64) corrupt? {str(e)}")
+        else:
+            if decoded:
+                try:
+                    with open(fname, 'wb') as f:
+                        f.write(decoded)
+                    # A signal that could trigger the socket server to update the browser also
+                    watch_check_update = signal('watch_favicon_bump')
+                    if watch_check_update:
+                        watch_check_update.send(watch_uuid=self.get('uuid'))
+
+                except Exception as e:
+                    logger.warning(f"UUID: {self.get('uuid')} error saving FavIcon to {fname} - {str(e)}")
+
+        # @todo - Store some checksum and only write when its different
+        logger.debug(f"UUID: {self.get('uuid')} updated favicon to at {fname}")
+
+    def get_favicon_filename(self) -> str | None:
+        """
+        Find any favicon.* file in the current working directory
+        and return the contents of the newest one.
+
+        Returns:
+            bytes: Contents of the newest favicon file, or None if not found.
+        """
+        import glob
+
+        # Search for all favicon.* files
+        files = glob.glob(os.path.join(self.watch_data_dir, "favicon.*"))
+
+        if not files:
+            return None
+
+        # Find the newest by modification time
+        newest_file = max(files, key=os.path.getmtime)
+        return os.path.basename(newest_file)
+
+    def get_screenshot_as_thumbnail(self, max_age=3200):
+        """Return path to a square thumbnail of the most recent screenshot.
+
+        Creates a 150x150 pixel thumbnail from the top portion of the screenshot.
+
+        Args:
+            max_age: Maximum age in seconds before recreating thumbnail
+
+        Returns:
+            Path to thumbnail or None if no screenshot exists
+        """
+        import os
+        import time
+
+        thumbnail_path = os.path.join(self.watch_data_dir, "thumbnail.jpeg")
+        top_trim = 500  # Pixels from top of screenshot to use
+
+        screenshot_path = self.get_screenshot()
+        if not screenshot_path:
+            return None
+
+        # Reuse thumbnail if it's fresh and screenshot hasn't changed
+        if os.path.isfile(thumbnail_path):
+            thumbnail_mtime = os.path.getmtime(thumbnail_path)
+            screenshot_mtime = os.path.getmtime(screenshot_path)
+
+            if screenshot_mtime <= thumbnail_mtime and time.time() - thumbnail_mtime < max_age:
+                return thumbnail_path
+
+        try:
+            from PIL import Image
+
+            with Image.open(screenshot_path) as img:
+                # Crop top portion first (full width, top_trim height)
+                top_crop_height = min(top_trim, img.height)
+                img = img.crop((0, 0, img.width, top_crop_height))
+
+                # Create a smaller intermediate image (to reduce memory usage)
+                aspect = img.width / img.height
+                interim_width = min(top_trim, img.width)
+                interim_height = int(interim_width / aspect) if aspect > 0 else top_trim
+                img = img.resize((interim_width, interim_height), Image.NEAREST)
+
+                # Convert to RGB if needed
+                if img.mode != 'RGB':
+                    img = img.convert('RGB')
+
+                # Crop to square from top center
+                square_size = min(img.width, img.height)
+                left = (img.width - square_size) // 2
+                img = img.crop((left, 0, left + square_size, square_size))
+
+                # Final resize to exact thumbnail size with better filter
+                img = img.resize((350, 350), Image.BILINEAR)
+
+                # Save with optimized settings
+                img.save(thumbnail_path, "JPEG", quality=75, optimize=True)
+
+            return thumbnail_path
+
+        except Exception as e:
+            logger.error(f"Error creating thumbnail for {self.get('uuid')}: {str(e)}")
+            return None
+
     def __get_file_ctime(self, filename):
         fname = os.path.join(self.watch_data_dir, filename)
         if os.path.isfile(fname):
@@ -505,7 +663,7 @@ class model(watch_base):
                     if res:
                         if not csv_writer:
                             # A file on the disk can be transferred much faster via flask than a string reply
-                            csv_output_filename = 'report.csv'
+                            csv_output_filename = f"report-{self.get('uuid')}.csv"
                             f = open(os.path.join(self.watch_data_dir, csv_output_filename), 'w')
                             # @todo some headers in the future
                             #fieldnames = ['Epoch seconds', 'Date']
@@ -663,9 +821,8 @@ class model(watch_base):
     def compile_error_texts(self, has_proxies=None):
         """Compile error texts for this watch.
         Accepts has_proxies parameter to ensure it works even outside app context"""
-        from flask import (
-            Markup, url_for
-        )
+        from flask import url_for
+        from markupsafe import Markup
 
         output = []  # Initialize as list since we're using append
         last_error = self.get('last_error','')
@@ -692,11 +849,11 @@ class model(watch_base):
                 output.append(str(Markup(f"<div class=\"notification-error\"><a href=\"{url_for('settings.notification_logs')}\">{ self.get('last_notification_error') }</a></div>")))
 
         else:
-            # Lo_Fi version
+            # Lo_Fi version - no app context, cant rely on Jinja2 Markup
             if last_error:
-                output.append(str(Markup(last_error)))
+                output.append(safe_jinja.render_fully_escaped(last_error))
             if self.get('last_notification_error'):
-                output.append(str(Markup(self.get('last_notification_error'))))
+                output.append(safe_jinja.render_fully_escaped(self.get('last_notification_error')))
 
         res = "\n".join(output)
         return res

changedetectionio/model/__init__.py

@@ -3,6 +3,7 @@ import uuid
 
 from changedetectionio import strtobool
 default_notification_format_for_watch = 'System default'
+CONDITIONS_MATCH_LOGIC_DEFAULT = 'ALL'
 
 class watch_base(dict):
 
@@ -15,13 +16,14 @@ class watch_base(dict):
             'body': None,
             'browser_steps': [],
             'browser_steps_last_error_step': None,
+            'conditions' : {},
+            'conditions_match_logic': CONDITIONS_MATCH_LOGIC_DEFAULT,
             'check_count': 0,
             'check_unique_lines': False,  # On change-detected, compare against all history if its something new
             'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
             'content-type': None,
             'date_created': None,
             'extract_text': [],  # Extract text by regex after filters
-            'extract_title_as_title': False,
             'fetch_backend': 'system',  # plaintext, playwright etc
             'fetch_time': 0.0,
             'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
@@ -32,6 +34,7 @@ class watch_base(dict):
             'has_ldjson_price_data': None,
             'headers': {},  # Extra headers to send
             'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+            'ignore_status_codes': None,
             'in_stock_only': True,  # Only trigger change on going to instock from out-of-stock
             'include_filters': [],
             'last_checked': 0,
@@ -46,6 +49,7 @@ class watch_base(dict):
             'notification_screenshot': False,  # Include the latest screenshot if available and supported by the apprise URL
             'notification_title': None,
             'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
+            'page_title': None, # <title> from the page
             'paused': False,
             'previous_md5': False,
             'previous_md5_before_filters': False,  # Used for skipping changedetection entirely
@@ -54,6 +58,7 @@ class watch_base(dict):
             'proxy': None,  # Preferred proxy connection
             'remote_server_reply': None,  # From 'server' reply header
             'sort_text_alphabetically': False,
+            'strip_ignored_lines': None,
             'subtractive_selectors': [],
             'tag': '',  # Old system of text name for a tag, to be removed
             'tags': [],  # list of UUIDs to App.Tags
@@ -119,12 +124,13 @@ class watch_base(dict):
                     }
                 },
             },
-            'title': None,
+            'title': None, # An arbitrary field that overrides 'page_title'
             'track_ldjson_price_data': None,
             'trim_text_whitespace': False,
             'remove_duplicate_lines': False,
             'trigger_text': [],  # List of text or regex to wait for until a change is detected
             'url': '',
+            'use_page_title_in_list': None, # None = use system settings
             'uuid': str(uuid.uuid4()),
             'webdriver_delay': None,
             'webdriver_js_execute_code': None,  # Run before change-detection

changedetectionio/notification/handler.py

@@ -149,7 +149,7 @@ 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].get('title', '')
+        watch_title = datastore.data['watching'][uuid].label
         tag_list = []
         tags = datastore.get_all_tags_for_watch(uuid)
         if tags:

changedetectionio/notification_service.py

@@ -0,0 +1,246 @@
+#!/usr/bin/env python3
+
+"""
+Notification Service Module
+Extracted from update_worker.py to provide standalone notification functionality
+for both sync and async workers
+"""
+
+import time
+from loguru import logger
+
+
+class NotificationService:
+    """
+    Standalone notification service that handles all notification functionality
+    previously embedded in the update_worker class
+    """
+    
+    def __init__(self, datastore, notification_q):
+        self.datastore = datastore
+        self.notification_q = notification_q
+    
+    def queue_notification_for_watch(self, n_object, watch):
+        """
+        Queue a notification for a watch with full diff rendering and template variables
+        """
+        from changedetectionio import diff
+        from changedetectionio.notification import default_notification_format_for_watch
+
+        dates = []
+        trigger_text = ''
+
+        now = time.time()
+
+        if watch:
+            watch_history = watch.history
+            dates = list(watch_history.keys())
+            trigger_text = watch.get('trigger_text', [])
+
+        # Add text that was triggered
+        if len(dates):
+            snapshot_contents = watch.get_history_snapshot(dates[-1])
+        else:
+            snapshot_contents = "No snapshot/history available, the watch should fetch atleast once."
+
+        # If we ended up here with "System default"
+        if n_object.get('notification_format') == default_notification_format_for_watch:
+            n_object['notification_format'] = self.datastore.data['settings']['application'].get('notification_format')
+
+        html_colour_enable = False
+        # HTML needs linebreak, but MarkDown and Text can use a linefeed
+        if n_object.get('notification_format') == 'HTML':
+            line_feed_sep = "<br>"
+            # Snapshot will be plaintext on the disk, convert to some kind of HTML
+            snapshot_contents = snapshot_contents.replace('\n', line_feed_sep)
+        elif n_object.get('notification_format') == 'HTML Color':
+            line_feed_sep = "<br>"
+            # Snapshot will be plaintext on the disk, convert to some kind of HTML
+            snapshot_contents = snapshot_contents.replace('\n', line_feed_sep)
+            html_colour_enable = True
+        else:
+            line_feed_sep = "\n"
+
+        triggered_text = ''
+        if len(trigger_text):
+            from . import html_tools
+            triggered_text = html_tools.get_triggered_text(content=snapshot_contents, trigger_text=trigger_text)
+            if triggered_text:
+                triggered_text = line_feed_sep.join(triggered_text)
+
+        # Could be called as a 'test notification' with only 1 snapshot available
+        prev_snapshot = "Example text: example test\nExample text: change detection is cool\nExample text: some more examples\n"
+        current_snapshot = "Example text: example test\nExample text: change detection is fantastic\nExample text: even more examples\nExample text: a lot more examples"
+
+        if len(dates) > 1:
+            prev_snapshot = watch.get_history_snapshot(dates[-2])
+            current_snapshot = watch.get_history_snapshot(dates[-1])
+
+        n_object.update({
+            'current_snapshot': snapshot_contents,
+            'diff': diff.render_diff(prev_snapshot, current_snapshot, line_feed_sep=line_feed_sep, html_colour=html_colour_enable),
+            'diff_added': diff.render_diff(prev_snapshot, current_snapshot, include_removed=False, line_feed_sep=line_feed_sep),
+            'diff_full': diff.render_diff(prev_snapshot, current_snapshot, include_equal=True, line_feed_sep=line_feed_sep, html_colour=html_colour_enable),
+            'diff_patch': diff.render_diff(prev_snapshot, current_snapshot, line_feed_sep=line_feed_sep, patch_format=True),
+            'diff_removed': diff.render_diff(prev_snapshot, current_snapshot, include_added=False, line_feed_sep=line_feed_sep),
+            'notification_timestamp': now,
+            'screenshot': watch.get_screenshot() if watch and watch.get('notification_screenshot') else None,
+            'triggered_text': triggered_text,
+            'uuid': watch.get('uuid') if watch else None,
+            'watch_url': watch.get('url') if watch else None,
+        })
+
+        if watch:
+            n_object.update(watch.extra_notification_token_values())
+
+        logger.trace(f"Main rendered notification placeholders (diff_added etc) calculated in {time.time()-now:.3f}s")
+        logger.debug("Queued notification for sending")
+        self.notification_q.put(n_object)
+
+    def _check_cascading_vars(self, var_name, watch):
+        """
+        Check notification variables in cascading priority:
+        Individual watch settings > Tag settings > Global settings
+        """
+        from changedetectionio.notification import (
+            default_notification_format_for_watch,
+            default_notification_body,
+            default_notification_title
+        )
+
+        # Would be better if this was some kind of Object where Watch can reference the parent datastore etc
+        v = watch.get(var_name)
+        if v and not watch.get('notification_muted'):
+            if var_name == 'notification_format' and v == default_notification_format_for_watch:
+                return self.datastore.data['settings']['application'].get('notification_format')
+
+            return v
+
+        tags = self.datastore.get_all_tags_for_watch(uuid=watch.get('uuid'))
+        if tags:
+            for tag_uuid, tag in tags.items():
+                v = tag.get(var_name)
+                if v and not tag.get('notification_muted'):
+                    return v
+
+        if self.datastore.data['settings']['application'].get(var_name):
+            return self.datastore.data['settings']['application'].get(var_name)
+
+        # Otherwise could be defaults
+        if var_name == 'notification_format':
+            return default_notification_format_for_watch
+        if var_name == 'notification_body':
+            return default_notification_body
+        if var_name == 'notification_title':
+            return default_notification_title
+
+        return None
+
+    def send_content_changed_notification(self, watch_uuid):
+        """
+        Send notification when content changes are detected
+        """
+        n_object = {}
+        watch = self.datastore.data['watching'].get(watch_uuid)
+        if not watch:
+            return
+
+        watch_history = watch.history
+        dates = list(watch_history.keys())
+        # Theoretically it's possible that this could be just 1 long,
+        # - In the case that the timestamp key was not unique
+        if len(dates) == 1:
+            raise ValueError(
+                "History index had 2 or more, but only 1 date loaded, timestamps were not unique? maybe two of the same timestamps got written, needs more delay?"
+            )
+
+        # Should be a better parent getter in the model object
+
+        # Prefer - Individual watch settings > Tag settings >  Global settings (in that order)
+        n_object['notification_urls'] = self._check_cascading_vars('notification_urls', watch)
+        n_object['notification_title'] = self._check_cascading_vars('notification_title', watch)
+        n_object['notification_body'] = self._check_cascading_vars('notification_body', watch)
+        n_object['notification_format'] = self._check_cascading_vars('notification_format', watch)
+
+        # (Individual watch) Only prepare to notify if the rules above matched
+        queued = False
+        if n_object and n_object.get('notification_urls'):
+            queued = True
+
+            count = watch.get('notification_alert_count', 0) + 1
+            self.datastore.update_watch(uuid=watch_uuid, update_obj={'notification_alert_count': count})
+
+            self.queue_notification_for_watch(n_object=n_object, watch=watch)
+
+        return queued
+
+    def send_filter_failure_notification(self, watch_uuid):
+        """
+        Send notification when CSS/XPath filters fail consecutively
+        """
+        threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts')
+        watch = self.datastore.data['watching'].get(watch_uuid)
+        if not watch:
+            return
+
+        n_object = {'notification_title': 'Changedetection.io - Alert - CSS/xPath filter was not present in the page',
+                    'notification_body': "Your configured CSS/xPath filters of '{}' for {{{{watch_url}}}} did not appear on the page after {} attempts, did the page change layout?\n\nLink: {{{{base_url}}}}/edit/{{{{watch_uuid}}}}\n\nThanks - Your omniscient changedetection.io installation :)\n".format(
+                        ", ".join(watch['include_filters']),
+                        threshold),
+                    'notification_format': 'text'}
+
+        if len(watch['notification_urls']):
+            n_object['notification_urls'] = watch['notification_urls']
+
+        elif len(self.datastore.data['settings']['application']['notification_urls']):
+            n_object['notification_urls'] = self.datastore.data['settings']['application']['notification_urls']
+
+        # Only prepare to notify if the rules above matched
+        if 'notification_urls' in n_object:
+            n_object.update({
+                'watch_url': watch['url'],
+                'uuid': watch_uuid,
+                'screenshot': None
+            })
+            self.notification_q.put(n_object)
+            logger.debug(f"Sent filter not found notification for {watch_uuid}")
+        else:
+            logger.debug(f"NOT sending filter not found notification for {watch_uuid} - no notification URLs")
+
+    def send_step_failure_notification(self, watch_uuid, step_n):
+        """
+        Send notification when browser steps fail consecutively
+        """
+        watch = self.datastore.data['watching'].get(watch_uuid, False)
+        if not watch:
+            return
+        threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts')
+        n_object = {'notification_title': "Changedetection.io - Alert - Browser step at position {} could not be run".format(step_n+1),
+                    'notification_body': "Your configured browser step at position {} for {{{{watch_url}}}} "
+                                         "did not appear on the page after {} attempts, did the page change layout? "
+                                         "Does it need a delay added?\n\nLink: {{{{base_url}}}}/edit/{{{{watch_uuid}}}}\n\n"
+                                         "Thanks - Your omniscient changedetection.io installation :)\n".format(step_n+1, threshold),
+                    'notification_format': 'text'}
+
+        if len(watch['notification_urls']):
+            n_object['notification_urls'] = watch['notification_urls']
+
+        elif len(self.datastore.data['settings']['application']['notification_urls']):
+            n_object['notification_urls'] = self.datastore.data['settings']['application']['notification_urls']
+
+        # Only prepare to notify if the rules above matched
+        if 'notification_urls' in n_object:
+            n_object.update({
+                'watch_url': watch['url'],
+                'uuid': watch_uuid
+            })
+            self.notification_q.put(n_object)
+            logger.error(f"Sent step not found notification for {watch_uuid}")
+
+
+# Convenience functions for creating notification service instances
+def create_notification_service(datastore, notification_q):
+    """
+    Factory function to create a NotificationService instance
+    """
+    return NotificationService(datastore, notification_q)

changedetectionio/processors/__init__.py

@@ -27,7 +27,7 @@ class difference_detection_processor():
         # Generic fetcher that should be extended (requests, playwright etc)
         self.fetcher = Fetcher()
 
-    def call_browser(self, preferred_proxy_id=None):
+    async def call_browser(self, preferred_proxy_id=None):
 
         from requests.structures import CaseInsensitiveDict
 
@@ -146,17 +146,19 @@ class difference_detection_processor():
 
         # And here we go! call the right browser with browser-specific settings
         empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
-
-        self.fetcher.run(url=url,
-                         timeout=timeout,
-                         request_headers=request_headers,
-                         request_body=request_body,
-                         request_method=request_method,
-                         ignore_status_codes=ignore_status_codes,
-                         current_include_filters=self.watch.get('include_filters'),
-                         is_binary=is_binary,
-                         empty_pages_are_a_change=empty_pages_are_a_change
-                         )
+        # All fetchers are now async
+        await self.fetcher.run(
+            current_include_filters=self.watch.get('include_filters'),
+            empty_pages_are_a_change=empty_pages_are_a_change,
+            fetch_favicon=self.watch.favicon_is_expired(),
+            ignore_status_codes=ignore_status_codes,
+            is_binary=is_binary,
+            request_body=request_body,
+            request_headers=request_headers,
+            request_method=request_method,
+            timeout=timeout,
+            url=url,
+       )
 
         #@todo .quit here could go on close object, so we can run JS if change-detected
         self.fetcher.quit(watch=self.watch)

changedetectionio/processors/magic.py

@@ -0,0 +1,138 @@
+"""
+Content Type Detection and Stream Classification
+
+This module provides intelligent content-type detection for changedetection.io.
+It addresses the common problem where HTTP Content-Type headers are missing, incorrect,
+or too generic, which would otherwise cause the wrong processor to be used.
+
+The guess_stream_type class combines:
+1. HTTP Content-Type headers (when available and reliable)
+2. Python-magic library for MIME detection (analyzing actual file content)
+3. Content-based pattern matching for text formats (HTML tags, XML declarations, etc.)
+
+This multi-layered approach ensures accurate detection of RSS feeds, JSON, HTML, PDF,
+plain text, CSV, YAML, and XML formats - even when servers provide misleading headers.
+
+Used by: processors/text_json_diff/processor.py and other content processors
+"""
+
+# When to apply the 'cdata to real HTML' hack
+RSS_XML_CONTENT_TYPES = [
+    "application/rss+xml",
+    "application/rdf+xml",
+    "text/xml",
+    "application/xml",
+    "application/atom+xml",
+    "text/rss+xml",  # rare, non-standard
+    "application/x-rss+xml",  # legacy (older feed software)
+    "application/x-atom+xml",  # legacy (older Atom)
+]
+
+# JSON Content-types
+JSON_CONTENT_TYPES = [
+    "application/activity+json",
+    "application/feed+json",
+    "application/json",
+    "application/ld+json",
+    "application/vnd.api+json",
+]
+
+# CSV Content-types
+CSV_CONTENT_TYPES = [
+    "text/csv",
+    "application/csv",
+]
+
+# Generic XML Content-types (non-RSS/Atom)
+XML_CONTENT_TYPES = [
+    "text/xml",
+    "application/xml",
+]
+
+# YAML Content-types
+YAML_CONTENT_TYPES = [
+    "text/yaml",
+    "text/x-yaml",
+    "application/yaml",
+    "application/x-yaml",
+]
+
+HTML_PATTERNS = ['<!doctype html', '<html', '<head', '<body', '<script', '<iframe', '<div']
+
+import re
+import magic
+from loguru import logger
+
+
+class guess_stream_type():
+    is_pdf = False
+    is_json = False
+    is_html = False
+    is_plaintext = False
+    is_rss = False
+    is_csv = False
+    is_xml = False  # Generic XML, not RSS/Atom
+    is_yaml = False
+
+    def __init__(self, http_content_header, content):
+
+        magic_content_header = http_content_header
+        test_content = content[:200].lower().strip()
+
+        # Remove whitespace between < and tag name for robust detection (handles '< html', '<\nhtml', etc.)
+        test_content_normalized = re.sub(r'<\s+', '<', test_content)
+
+        # Magic will sometimes call text/plain as text/html!
+        magic_result = None
+        try:
+            mime = magic.from_buffer(content[:200], mime=True) # Send the original content
+            logger.debug(f"Guessing mime type, original content_type '{http_content_header}', mime type detected '{mime}'")
+            if mime and "/" in mime:
+                magic_result = mime
+                # Ignore generic/fallback mime types from magic
+                if mime in ['application/octet-stream', 'application/x-empty', 'binary']:
+                    logger.debug(f"Ignoring generic mime type '{mime}' from magic library")
+                # Trust magic for non-text types immediately
+                elif mime not in ['text/html', 'text/plain']:
+                    magic_content_header = mime
+
+        except Exception as e:
+            logger.error(f"Error getting a more precise mime type from 'magic' library ({str(e)}), using content-based detection")
+
+        # Content-based detection (most reliable for text formats)
+        # Check for HTML patterns first - if found, override magic's text/plain
+        has_html_patterns = any(p in test_content_normalized for p in HTML_PATTERNS)
+
+        # Always trust headers first
+        if any(s in http_content_header for s in RSS_XML_CONTENT_TYPES) or any(s in magic_content_header for s in RSS_XML_CONTENT_TYPES):
+            self.is_rss = True
+        elif any(s in http_content_header for s in JSON_CONTENT_TYPES) or any(s in magic_content_header for s in JSON_CONTENT_TYPES):
+            self.is_json = True
+        elif any(s in http_content_header for s in CSV_CONTENT_TYPES) or any(s in magic_content_header for s in CSV_CONTENT_TYPES):
+            self.is_csv = True
+        elif any(s in http_content_header for s in XML_CONTENT_TYPES) or any(s in magic_content_header for s in XML_CONTENT_TYPES):
+            # Only mark as generic XML if not already detected as RSS
+            if not self.is_rss:
+                self.is_xml = True
+        elif any(s in http_content_header for s in YAML_CONTENT_TYPES) or any(s in magic_content_header for s in YAML_CONTENT_TYPES):
+            self.is_yaml = True
+        elif 'pdf' in magic_content_header:
+            self.is_pdf = True
+###
+        elif has_html_patterns or http_content_header == 'text/html':
+            self.is_html = True
+        # If magic says text/plain and we found no HTML patterns, trust it
+        elif magic_result == 'text/plain':
+            self.is_plaintext = True
+            logger.debug(f"Trusting magic's text/plain result (no HTML patterns detected)")
+        elif '<rss' in test_content_normalized or '<feed' in test_content_normalized:
+            self.is_rss = True
+        elif test_content_normalized.startswith('<?xml'):
+            # Generic XML that's not RSS/Atom (RSS/Atom checked above)
+            self.is_xml = True
+        elif '%pdf-1' in test_content:
+            self.is_pdf = True
+        # Only trust magic for 'text' if no other patterns matched
+        elif 'text' in magic_content_header:
+            self.is_plaintext = True
+

changedetectionio/processors/text_json_diff/processor.py

@@ -13,6 +13,8 @@ from changedetectionio import html_tools, content_fetchers
 from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
 from loguru import logger
 
+from changedetectionio.processors.magic import guess_stream_type
+
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 name = 'Webpage Text/HTML, JSON and PDF changes'
@@ -20,6 +22,9 @@ description = 'Detects all text changes where possible'
 
 json_filter_prefixes = ['json:', 'jq:', 'jqraw:']
 
+# Assume it's this type if the server says nothing on content-type
+DEFAULT_WHEN_NO_CONTENT_TYPE_HEADER = 'text/html'
+
 class FilterNotFoundInResponse(ValueError):
     def __init__(self, msg, screenshot=None, xpath_data=None):
         self.screenshot = screenshot
@@ -45,6 +50,9 @@ class perform_site_check(difference_detection_processor):
         if not watch:
             raise Exception("Watch no longer exists.")
 
+        ctype_header = self.fetcher.get_all_headers().get('content-type', DEFAULT_WHEN_NO_CONTENT_TYPE_HEADER).lower()
+        stream_content_type = guess_stream_type(http_content_header=ctype_header, content=self.fetcher.content)
+
         # Unset any existing notification error
         update_obj = {'last_notification_error': False, 'last_error': False}
 
@@ -54,7 +62,7 @@ class perform_site_check(difference_detection_processor):
         self.xpath_data = self.fetcher.xpath_data
 
         # Track the content type
-        update_obj['content_type'] = self.fetcher.get_all_headers().get('content-type', '').lower()
+        update_obj['content_type'] = ctype_header
 
         # Watches added automatically in the queue manager will skip if its the same checksum as the previous run
         # Saves a lot of CPU
@@ -69,24 +77,12 @@ 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 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
+        if stream_content_type.is_rss:
+            self.fetcher.content = cdata_in_document_to_text(html_content=self.fetcher.content)
 
-        # source: support, basically treat it as plaintext
-        if watch.is_source_type_url:
-            is_html = False
-            is_json = False
-
-        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:
+        if watch.is_pdf or stream_content_type.is_pdf:
             from shutil import which
             tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
             if not which(tool):
@@ -130,11 +126,12 @@ class perform_site_check(difference_detection_processor):
         has_filter_rule = len(include_filters_rule) and len(include_filters_rule[0].strip())
         has_subtractive_selectors = len(subtractive_selectors) and len(subtractive_selectors[0].strip())
 
-        if is_json and not has_filter_rule:
-            include_filters_rule.append("json:$")
-            has_filter_rule = True
+        if stream_content_type.is_json:
+            if not has_filter_rule:
+                # Force a reformat
+                include_filters_rule.append("json:$")
+                has_filter_rule = True
 
-        if is_json:
             # Sort the JSON so we dont get false alerts when the content is just re-ordered
             try:
                 self.fetcher.content = json.dumps(json.loads(self.fetcher.content), sort_keys=True)
@@ -142,23 +139,28 @@ class perform_site_check(difference_detection_processor):
                 # Might have just been a snippet, or otherwise bad JSON, continue
                 pass
 
-        if has_filter_rule:
-            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=self.fetcher.content, json_filter=filter)
-                    is_html = False
+            if has_filter_rule:
+                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=self.fetcher.content, json_filter=filter)
+                        if stripped_text_from_html:
+                            stream_content_type.is_json = True
+                            stream_content_type.is_html = False
 
-        if is_html or watch.is_source_type_url:
+        # We have 'watch.is_source_type_url' because we should be able to use selectors on the raw HTML but return just that selected HTML
+        if stream_content_type.is_html or watch.is_source_type_url or stream_content_type.is_plaintext or stream_content_type.is_rss or stream_content_type.is_xml or stream_content_type.is_pdf:
 
             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
             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 self.fetcher.get_all_headers().get('content-type', '').lower():
+            # Some kind of "text" but definitely not RSS looking
+            if stream_content_type.is_plaintext:
                 # Don't run get_text or xpath/css filters on plaintext
+                # We are not HTML, we are not any kind of RSS, doesnt even look like HTML
                 stripped_text_from_html = html_content
             else:
+                # If not JSON, and if it's not text/plain..
                 # Does it have some ld+json price data? used for easier monitoring
                 update_obj['has_ldjson_price_data'] = html_tools.has_ldjson_product_info(self.fetcher.content)
 
@@ -172,13 +174,13 @@ class perform_site_check(difference_detection_processor):
                             html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
                                                                     html_content=self.fetcher.content,
                                                                     append_pretty_line_formatting=not watch.is_source_type_url,
-                                                                    is_rss=is_rss)
+                                                                    is_rss=stream_content_type.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)
+                                                                     is_rss=stream_content_type.is_rss)
                         else:
                             html_content += html_tools.include_filters(include_filters=filter_rule,
                                                                        html_content=self.fetcher.content,
@@ -197,7 +199,7 @@ class perform_site_check(difference_detection_processor):
                     do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
                     stripped_text_from_html = html_tools.html_to_text(html_content=html_content,
                                                                       render_anchor_tag_content=do_anchor,
-                                                                      is_rss=is_rss)  # 1874 activate the <title workaround hack
+                                                                      is_rss=stream_content_type.is_rss)  # 1874 activate the <title workaround hack
 
         if watch.get('trim_text_whitespace'):
             stripped_text_from_html = '\n'.join(line.strip() for line in stripped_text_from_html.replace("\n\n", "\n").splitlines())
@@ -236,7 +238,7 @@ 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:
+        if not stream_content_type.is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
             raise content_fetchers.exceptions.ReplyWithContentButNoText(url=url,
                                                             status_code=self.fetcher.get_last_status_code(),
                                                             screenshot=self.fetcher.screenshot,
@@ -251,8 +253,7 @@ class perform_site_check(difference_detection_processor):
         update_obj["last_check_status"] = self.fetcher.get_last_status_code()
 
         # 615 Extract text by regex
-        extract_text = watch.get('extract_text', [])
-        extract_text += self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='extract_text')
+        extract_text = list(dict.fromkeys(watch.get('extract_text', []) + self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='extract_text')))
         if len(extract_text) > 0:
             regex_matched_output = []
             for s_re in extract_text:
@@ -302,6 +303,11 @@ class perform_site_check(difference_detection_processor):
         text_for_checksuming = stripped_text_from_html
         if text_to_ignore:
             text_for_checksuming = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
+            # Some people prefer to also completely remove it
+            strip_ignored_lines = watch.get('strip_ignored_lines') if watch.get('strip_ignored_lines') is not None else self.datastore.data['settings']['application'].get('strip_ignored_lines')
+            if strip_ignored_lines:
+                # @todo add test in the 'preview' mode, check the widget works? compare to datastruct
+                stripped_text_from_html = text_for_checksuming
 
         # Re #133 - if we should strip whitespaces from triggering the change detected comparison
         if text_for_checksuming and self.datastore.data['settings']['application'].get('ignore_whitespace', False):
@@ -311,8 +317,7 @@ class perform_site_check(difference_detection_processor):
 
         ############ Blocking rules, after checksum #################
         blocked = False
-        trigger_text = watch.get('trigger_text', [])
-        trigger_text += self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='trigger_text')
+        trigger_text = list(dict.fromkeys(watch.get('trigger_text', []) + self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='trigger_text')))
         if len(trigger_text):
             # Assume blocked
             blocked = True
@@ -326,8 +331,7 @@ class perform_site_check(difference_detection_processor):
             if result:
                 blocked = False
 
-        text_should_not_be_present = watch.get('text_should_not_be_present', [])
-        text_should_not_be_present += self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='text_should_not_be_present')
+        text_should_not_be_present = list(dict.fromkeys(watch.get('text_should_not_be_present', []) + self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='text_should_not_be_present')))
         if len(text_should_not_be_present):
             # If anything matched, then we should block a change from happening
             result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),

changedetectionio/queue_handlers.py

@@ -0,0 +1,435 @@
+from blinker import signal
+from loguru import logger
+from typing import Dict, List, Any, Optional
+import heapq
+import queue
+import threading
+
+try:
+    import janus
+except ImportError:
+    logger.critical(f"CRITICAL: janus library is required. Install with: pip install janus")
+    raise
+
+
+class RecheckPriorityQueue:
+    """
+    Ultra-reliable priority queue using janus for async/sync bridging.
+    
+    CRITICAL DESIGN NOTE: Both sync_q and async_q are required because:
+    - sync_q: Used by Flask routes, ticker threads, and other synchronous code
+    - async_q: Used by async workers (the actual fetchers/processors) and coroutines
+    
+    DO NOT REMOVE EITHER INTERFACE - they bridge different execution contexts:
+    - Synchronous code (Flask, threads) cannot use async methods without blocking
+    - Async code cannot use sync methods without blocking the event loop
+    - janus provides the only safe bridge between these two worlds
+    
+    Attempting to unify to async-only would require:
+    - Converting all Flask routes to async (major breaking change)
+    - Using asyncio.run() in sync contexts (causes deadlocks)
+    - Thread-pool wrapping (adds complexity and overhead)
+    
+    Minimal implementation focused on reliability:
+    - Pure janus for sync/async bridge
+    - Thread-safe priority ordering  
+    - Bulletproof error handling with critical logging
+    """
+    
+    def __init__(self, maxsize: int = 0):
+        try:
+            self._janus_queue = janus.Queue(maxsize=maxsize)
+            # BOTH interfaces required - see class docstring for why
+            self.sync_q = self._janus_queue.sync_q   # Flask routes, ticker thread
+            self.async_q = self._janus_queue.async_q # Async workers
+            
+            # Priority storage - thread-safe
+            self._priority_items = []
+            self._lock = threading.RLock()
+            
+            # Signals for UI updates
+            self.queue_length_signal = signal('queue_length')
+            
+            logger.debug("RecheckPriorityQueue initialized successfully")
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to initialize RecheckPriorityQueue: {str(e)}")
+            raise
+    
+    # SYNC INTERFACE (for ticker thread)
+    def put(self, item, block: bool = True, timeout: Optional[float] = None):
+        """Thread-safe sync put with priority ordering"""
+        try:
+            # Add to priority storage
+            with self._lock:
+                heapq.heappush(self._priority_items, item)
+            
+            # Notify via janus sync queue
+            self.sync_q.put(True, block=block, timeout=timeout)
+            
+            # Emit signals
+            self._emit_put_signals(item)
+            
+            logger.debug(f"Successfully queued item: {self._get_item_uuid(item)}")
+            return True
+            
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to put item {self._get_item_uuid(item)}: {str(e)}")
+            # Remove from priority storage if janus put failed
+            try:
+                with self._lock:
+                    if item in self._priority_items:
+                        self._priority_items.remove(item)
+                        heapq.heapify(self._priority_items)
+            except Exception as cleanup_e:
+                logger.critical(f"CRITICAL: Failed to cleanup after put failure: {str(e)}")
+            return False
+    
+    def get(self, block: bool = True, timeout: Optional[float] = None):
+        """Thread-safe sync get with priority ordering"""
+        try:
+            # Wait for notification
+            self.sync_q.get(block=block, timeout=timeout)
+            
+            # Get highest priority item
+            with self._lock:
+                if not self._priority_items:
+                    logger.critical(f"CRITICAL: Queue notification received but no priority items available")
+                    raise Exception("Priority queue inconsistency")
+                item = heapq.heappop(self._priority_items)
+            
+            # Emit signals
+            self._emit_get_signals()
+            
+            logger.debug(f"Successfully retrieved item: {self._get_item_uuid(item)}")
+            return item
+            
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to get item from queue: {str(e)}")
+            raise
+    
+    # ASYNC INTERFACE (for workers)
+    async def async_put(self, item):
+        """Pure async put with priority ordering"""
+        try:
+            # Add to priority storage
+            with self._lock:
+                heapq.heappush(self._priority_items, item)
+            
+            # Notify via janus async queue
+            await self.async_q.put(True)
+            
+            # Emit signals
+            self._emit_put_signals(item)
+            
+            logger.debug(f"Successfully async queued item: {self._get_item_uuid(item)}")
+            return True
+            
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to async put item {self._get_item_uuid(item)}: {str(e)}")
+            # Remove from priority storage if janus put failed
+            try:
+                with self._lock:
+                    if item in self._priority_items:
+                        self._priority_items.remove(item)
+                        heapq.heapify(self._priority_items)
+            except Exception as cleanup_e:
+                logger.critical(f"CRITICAL: Failed to cleanup after async put failure: {str(e)}")
+            return False
+    
+    async def async_get(self):
+        """Pure async get with priority ordering"""
+        try:
+            # Wait for notification
+            await self.async_q.get()
+            
+            # Get highest priority item
+            with self._lock:
+                if not self._priority_items:
+                    logger.critical(f"CRITICAL: Async queue notification received but no priority items available")
+                    raise Exception("Priority queue inconsistency")
+                item = heapq.heappop(self._priority_items)
+            
+            # Emit signals
+            self._emit_get_signals()
+            
+            logger.debug(f"Successfully async retrieved item: {self._get_item_uuid(item)}")
+            return item
+            
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to async get item from queue: {str(e)}")
+            raise
+    
+    # UTILITY METHODS
+    def qsize(self) -> int:
+        """Get current queue size"""
+        try:
+            with self._lock:
+                return len(self._priority_items)
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to get queue size: {str(e)}")
+            return 0
+    
+    def empty(self) -> bool:
+        """Check if queue is empty"""
+        return self.qsize() == 0
+    
+    def close(self):
+        """Close the janus queue"""
+        try:
+            self._janus_queue.close()
+            logger.debug("RecheckPriorityQueue closed successfully")
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to close RecheckPriorityQueue: {str(e)}")
+    
+    # COMPATIBILITY METHODS (from original implementation)
+    @property
+    def queue(self):
+        """Provide compatibility with original queue access"""
+        try:
+            with self._lock:
+                return list(self._priority_items)
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to get queue list: {str(e)}")
+            return []
+    
+    def get_uuid_position(self, target_uuid: str) -> Dict[str, Any]:
+        """Find position of UUID in queue"""
+        try:
+            with self._lock:
+                queue_list = list(self._priority_items)
+                total_items = len(queue_list)
+                
+                if total_items == 0:
+                    return {'position': None, 'total_items': 0, 'priority': None, 'found': False}
+                
+                # Find target item
+                for item in queue_list:
+                    if (hasattr(item, 'item') and isinstance(item.item, dict) and 
+                        item.item.get('uuid') == target_uuid):
+                        
+                        # Count items with higher priority
+                        position = sum(1 for other in queue_list if other.priority < item.priority)
+                        return {
+                            'position': position,
+                            'total_items': total_items, 
+                            'priority': item.priority,
+                            'found': True
+                        }
+                
+                return {'position': None, 'total_items': total_items, 'priority': None, 'found': False}
+                
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to get UUID position for {target_uuid}: {str(e)}")
+            return {'position': None, 'total_items': 0, 'priority': None, 'found': False}
+    
+    def get_all_queued_uuids(self, limit: Optional[int] = None, offset: int = 0) -> Dict[str, Any]:
+        """Get all queued UUIDs with pagination"""
+        try:
+            with self._lock:
+                queue_list = sorted(self._priority_items)  # Sort by priority
+                total_items = len(queue_list)
+                
+                if total_items == 0:
+                    return {'items': [], 'total_items': 0, 'returned_items': 0, 'has_more': False}
+                
+                # Apply pagination
+                end_idx = min(offset + limit, total_items) if limit else total_items
+                items_to_process = queue_list[offset:end_idx]
+                
+                result = []
+                for position, item in enumerate(items_to_process, start=offset):
+                    if (hasattr(item, 'item') and isinstance(item.item, dict) and 
+                        'uuid' in item.item):
+                        result.append({
+                            'uuid': item.item['uuid'],
+                            'position': position,
+                            'priority': item.priority
+                        })
+                
+                return {
+                    'items': result,
+                    'total_items': total_items,
+                    'returned_items': len(result),
+                    'has_more': (offset + len(result)) < total_items
+                }
+                
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to get all queued UUIDs: {str(e)}")
+            return {'items': [], 'total_items': 0, 'returned_items': 0, 'has_more': False}
+    
+    def get_queue_summary(self) -> Dict[str, Any]:
+        """Get queue summary statistics"""
+        try:
+            with self._lock:
+                queue_list = list(self._priority_items)
+                total_items = len(queue_list)
+                
+                if total_items == 0:
+                    return {
+                        'total_items': 0, 'priority_breakdown': {},
+                        'immediate_items': 0, 'clone_items': 0, 'scheduled_items': 0
+                    }
+                
+                immediate_items = clone_items = scheduled_items = 0
+                priority_counts = {}
+                
+                for item in queue_list:
+                    priority = item.priority
+                    priority_counts[priority] = priority_counts.get(priority, 0) + 1
+                    
+                    if priority == 1:
+                        immediate_items += 1
+                    elif priority == 5:
+                        clone_items += 1
+                    elif priority > 100:
+                        scheduled_items += 1
+                
+                return {
+                    'total_items': total_items,
+                    'priority_breakdown': priority_counts,
+                    'immediate_items': immediate_items,
+                    'clone_items': clone_items,
+                    'scheduled_items': scheduled_items,
+                    'min_priority': min(priority_counts.keys()) if priority_counts else None,
+                    'max_priority': max(priority_counts.keys()) if priority_counts else None
+                }
+                
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to get queue summary: {str(e)}")
+            return {'total_items': 0, 'priority_breakdown': {}, 'immediate_items': 0, 
+                   'clone_items': 0, 'scheduled_items': 0}
+    
+    # PRIVATE METHODS
+    def _get_item_uuid(self, item) -> str:
+        """Safely extract UUID from item for logging"""
+        try:
+            if hasattr(item, 'item') and isinstance(item.item, dict):
+                return item.item.get('uuid', 'unknown')
+        except Exception:
+            pass
+        return 'unknown'
+    
+    def _emit_put_signals(self, item):
+        """Emit signals when item is added"""
+        try:
+            # Watch update signal
+            if hasattr(item, 'item') and isinstance(item.item, dict) and 'uuid' in item.item:
+                watch_check_update = signal('watch_check_update')
+                if watch_check_update:
+                    watch_check_update.send(watch_uuid=item.item['uuid'])
+            
+            # Queue length signal
+            if self.queue_length_signal:
+                self.queue_length_signal.send(length=self.qsize())
+                
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to emit put signals: {str(e)}")
+    
+    def _emit_get_signals(self):
+        """Emit signals when item is removed"""
+        try:
+            if self.queue_length_signal:
+                self.queue_length_signal.send(length=self.qsize())
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to emit get signals: {str(e)}")
+
+
+class NotificationQueue:
+    """
+    Ultra-reliable notification queue using pure janus.
+    
+    CRITICAL DESIGN NOTE: Both sync_q and async_q are required because:
+    - sync_q: Used by Flask routes, ticker threads, and other synchronous code
+    - async_q: Used by async workers and coroutines
+    
+    DO NOT REMOVE EITHER INTERFACE - they bridge different execution contexts.
+    See RecheckPriorityQueue docstring above for detailed explanation.
+    
+    Simple wrapper around janus with bulletproof error handling.
+    """
+    
+    def __init__(self, maxsize: int = 0):
+        try:
+            self._janus_queue = janus.Queue(maxsize=maxsize)
+            # BOTH interfaces required - see class docstring for why
+            self.sync_q = self._janus_queue.sync_q   # Flask routes, threads
+            self.async_q = self._janus_queue.async_q # Async workers
+            self.notification_event_signal = signal('notification_event')
+            logger.debug("NotificationQueue initialized successfully")
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to initialize NotificationQueue: {str(e)}")
+            raise
+    
+    def put(self, item: Dict[str, Any], block: bool = True, timeout: Optional[float] = None):
+        """Thread-safe sync put with signal emission"""
+        try:
+            self.sync_q.put(item, block=block, timeout=timeout)
+            self._emit_notification_signal(item)
+            logger.debug(f"Successfully queued notification: {item.get('uuid', 'unknown')}")
+            return True
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to put notification {item.get('uuid', 'unknown')}: {str(e)}")
+            return False
+    
+    async def async_put(self, item: Dict[str, Any]):
+        """Pure async put with signal emission"""
+        try:
+            await self.async_q.put(item)
+            self._emit_notification_signal(item)
+            logger.debug(f"Successfully async queued notification: {item.get('uuid', 'unknown')}")
+            return True
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to async put notification {item.get('uuid', 'unknown')}: {str(e)}")
+            return False
+    
+    def get(self, block: bool = True, timeout: Optional[float] = None):
+        """Thread-safe sync get"""
+        try:
+            return self.sync_q.get(block=block, timeout=timeout)
+        except queue.Empty as e:
+            raise e
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to get notification: {str(e)}")
+            raise e
+    
+    async def async_get(self):
+        """Pure async get"""
+        try:
+            return await self.async_q.get()
+        except queue.Empty as e:
+            raise e
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to async get notification: {str(e)}")
+            raise e
+    
+    def qsize(self) -> int:
+        """Get current queue size"""
+        try:
+            return self.sync_q.qsize()
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to get notification queue size: {str(e)}")
+            return 0
+    
+    def empty(self) -> bool:
+        """Check if queue is empty"""
+        return self.qsize() == 0
+    
+    def close(self):
+        """Close the janus queue"""
+        try:
+            self._janus_queue.close()
+            logger.debug("NotificationQueue closed successfully")
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to close NotificationQueue: {str(e)}")
+    
+    def _emit_notification_signal(self, item: Dict[str, Any]):
+        """Emit notification signal"""
+        try:
+            if self.notification_event_signal and isinstance(item, dict):
+                watch_uuid = item.get('uuid')
+                if watch_uuid:
+                    self.notification_event_signal.send(watch_uuid=watch_uuid)
+                else:
+                    self.notification_event_signal.send()
+        except Exception as e:
+            logger.critical(f"CRITICAL: Failed to emit notification signal: {str(e)}")

changedetectionio/realtime/README.md

@@ -0,0 +1,124 @@
+# Real-time Socket.IO Implementation
+
+This directory contains the Socket.IO implementation for changedetection.io's real-time updates.
+
+## Architecture Overview
+
+The real-time system provides live updates to the web interface for:
+- Watch status changes (checking, completed, errors)
+- Queue length updates  
+- General statistics updates
+
+## Current Implementation
+
+### Socket.IO Configuration
+- **Async Mode**: `threading` (default) or `gevent` (optional via SOCKETIO_MODE env var)
+- **Server**: Flask-SocketIO with threading support
+- **Background Tasks**: Python threading with daemon threads
+
+### Async Worker Integration
+- **Workers**: Async workers using asyncio for watch processing
+- **Queue**: AsyncSignalPriorityQueue for job distribution
+- **Signals**: Blinker signals for real-time updates between workers and Socket.IO
+
+### Environment Variables
+- `SOCKETIO_MODE=threading` (default, recommended)
+- `SOCKETIO_MODE=gevent` (optional, has cross-platform limitations)
+
+## Architecture Decision: Why Threading Mode?
+
+### Previous Issues with Eventlet
+**Eventlet was completely removed** due to fundamental compatibility issues:
+
+1. **Monkey Patching Conflicts**: `eventlet.monkey_patch()` globally replaced Python's threading/socket modules, causing conflicts with:
+   - Playwright's synchronous browser automation
+   - Async worker event loops
+   - Various Python libraries expecting real threading
+
+2. **Python 3.12+ Compatibility**: Eventlet had issues with newer Python versions and asyncio integration
+
+3. **CVE-2023-29483**: Security vulnerability in eventlet's dnspython dependency
+
+### Current Solution Benefits
+✅ **Threading Mode Advantages**:
+- Full compatibility with async workers and Playwright
+- No monkey patching - uses standard Python threading
+- Better Python 3.12+ support
+- Cross-platform compatibility (Windows, macOS, Linux)
+- No external async library dependencies
+- Fast shutdown capabilities
+
+✅ **Optional Gevent Support**:
+- Available via `SOCKETIO_MODE=gevent` for high-concurrency scenarios
+- Cross-platform limitations documented in requirements.txt
+- Not recommended as default due to Windows socket limits and macOS ARM build issues
+
+## Socket.IO Mode Configuration
+
+### Threading Mode (Default)
+```python
+# Enabled automatically
+async_mode = 'threading'
+socketio = SocketIO(app, async_mode='threading')
+```
+
+### Gevent Mode (Optional)
+```bash
+# Set environment variable
+export SOCKETIO_MODE=gevent
+```
+
+## Background Tasks
+
+### Queue Polling
+- **Threading Mode**: `threading.Thread` with `threading.Event` for shutdown
+- **Signal Handling**: Blinker signals for watch state changes
+- **Real-time Updates**: Direct Socket.IO `emit()` calls to connected clients
+
+### Worker Integration
+- **Async Workers**: Run in separate asyncio event loop thread
+- **Communication**: AsyncSignalPriorityQueue bridges async workers and Socket.IO
+- **Updates**: Real-time updates sent when workers complete tasks
+
+## Files in This Directory
+
+- `socket_server.py`: Main Socket.IO initialization and event handling
+- `events.py`: Watch operation event handlers  
+- `__init__.py`: Module initialization
+
+## Production Deployment
+
+### Recommended WSGI Servers
+For production with Socket.IO threading mode:
+- **Gunicorn**: `gunicorn --worker-class eventlet changedetection:app` (if using gevent mode)
+- **uWSGI**: With threading support
+- **Docker**: Built-in Flask server works well for containerized deployments
+
+### Performance Considerations
+- Threading mode: Better memory usage, standard Python threading
+- Gevent mode: Higher concurrency but platform limitations
+- Async workers: Separate from Socket.IO, provides scalability
+
+## Environment Variables
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `SOCKETIO_MODE` | `threading` | Socket.IO async mode (`threading` or `gevent`) |
+| `FETCH_WORKERS` | `10` | Number of async workers for watch processing |
+| `CHANGEDETECTION_HOST` | `0.0.0.0` | Server bind address |
+| `CHANGEDETECTION_PORT` | `5000` | Server port |
+
+## Debugging Tips
+
+1. **Socket.IO Issues**: Check browser dev tools for WebSocket connection errors
+2. **Threading Issues**: Monitor with `ps -T` to check thread count  
+3. **Worker Issues**: Use `/worker-health` endpoint to check async worker status
+4. **Queue Issues**: Use `/queue-status` endpoint to monitor job queue
+5. **Performance**: Use `/gc-cleanup` endpoint to trigger memory cleanup
+
+## Migration Notes
+
+If upgrading from eventlet-based versions:
+- Remove any `EVENTLET_*` environment variables
+- No code changes needed - Socket.IO mode is automatically configured
+- Optional: Set `SOCKETIO_MODE=gevent` if high concurrency is required and platform supports it

changedetectionio/realtime/events.py

@@ -0,0 +1,58 @@
+from flask_socketio import emit
+from loguru import logger
+from blinker import signal
+
+
+def register_watch_operation_handlers(socketio, datastore):
+    """Register Socket.IO event handlers for watch operations"""
+    
+    @socketio.on('watch_operation')
+    def handle_watch_operation(data):
+        """Handle watch operations like pause, mute, recheck via Socket.IO"""
+        try:
+            op = data.get('op')
+            uuid = data.get('uuid')
+            
+            logger.debug(f"Socket.IO: Received watch operation '{op}' for UUID {uuid}")
+            
+            if not op or not uuid:
+                emit('operation_result', {'success': False, 'error': 'Missing operation or UUID'})
+                return
+            
+            # Check if watch exists
+            if not datastore.data['watching'].get(uuid):
+                emit('operation_result', {'success': False, 'error': 'Watch not found'})
+                return
+            
+            watch = datastore.data['watching'][uuid]
+            
+            # Perform the operation
+            if op == 'pause':
+                watch.toggle_pause()
+                logger.info(f"Socket.IO: Toggled pause for watch {uuid}")
+            elif op == 'mute':
+                watch.toggle_mute()
+                logger.info(f"Socket.IO: Toggled mute for watch {uuid}")
+            elif op == 'recheck':
+                # Import here to avoid circular imports
+                from changedetectionio.flask_app import update_q
+                from changedetectionio import queuedWatchMetaData
+                from changedetectionio import worker_handler
+                
+                worker_handler.queue_item_async_safe(update_q, queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                logger.info(f"Socket.IO: Queued recheck for watch {uuid}")
+            else:
+                emit('operation_result', {'success': False, 'error': f'Unknown operation: {op}'})
+                return
+            
+            # Send signal to update UI
+            watch_check_update = signal('watch_check_update')
+            if watch_check_update:
+                watch_check_update.send(watch_uuid=uuid)
+            
+            # Send success response to client
+            emit('operation_result', {'success': True, 'operation': op, 'uuid': uuid})
+            
+        except Exception as e:
+            logger.error(f"Socket.IO error in handle_watch_operation: {str(e)}")
+            emit('operation_result', {'success': False, 'error': str(e)})

changedetectionio/realtime/socket_server.py

@@ -8,8 +8,10 @@ from blinker import signal
 
 from changedetectionio import strtobool
 
+
 class SignalHandler:
     """A standalone class to receive signals"""
+
     def __init__(self, socketio_instance, datastore):
         self.socketio_instance = socketio_instance
         self.datastore = datastore
@@ -17,19 +19,33 @@ class SignalHandler:
         # Connect to the watch_check_update signal
         from changedetectionio.flask_app import watch_check_update as wcc
         wcc.connect(self.handle_signal, weak=False)
-        logger.info("SignalHandler: Connected to signal from direct import")
-        
+        #        logger.info("SignalHandler: Connected to signal from direct import")
+
         # Connect to the queue_length signal
         queue_length_signal = signal('queue_length')
         queue_length_signal.connect(self.handle_queue_length, weak=False)
-        logger.info("SignalHandler: Connected to queue_length signal")
+        #       logger.info("SignalHandler: Connected to queue_length signal")
 
+        watch_delete_signal = signal('watch_deleted')
+        watch_delete_signal.connect(self.handle_deleted_signal, weak=False)
+
+        watch_favicon_bumped_signal = signal('watch_favicon_bump')
+        watch_favicon_bumped_signal.connect(self.handle_watch_bumped_favicon_signal, weak=False)
+
+        # Connect to the notification_event signal
+        notification_event_signal = signal('notification_event')
+        notification_event_signal.connect(self.handle_notification_event, weak=False)
+        logger.info("SignalHandler: Connected to notification_event signal")
+
+        # Create and start the queue update thread using standard threading
+        import threading
+        self.polling_emitter_thread = threading.Thread(
+            target=self.polling_emit_running_or_queued_watches_threaded,
+            daemon=True
+        )
+        self.polling_emitter_thread.start()
+        logger.info("Started polling thread using threading (eventlet-free)")
 
-        # Create and start the queue update thread using gevent
-        import gevent
-        logger.info("Using gevent for polling thread")
-        self.polling_emitter_thread = gevent.spawn(self.polling_emit_running_or_queued_watches)
-        
         # Store the thread reference in socketio for clean shutdown
         self.socketio_instance.polling_emitter_thread = self.polling_emitter_thread
 
@@ -44,7 +60,7 @@ class SignalHandler:
             watch = self.datastore.data['watching'].get(watch_uuid)
             if watch:
                 if app_context:
-                    #note
+                    # note
                     with app_context.app_context():
                         with app_context.test_request_context():
                             # Forward to handle_watch_update with the watch parameter
@@ -56,64 +72,126 @@ class SignalHandler:
             else:
                 logger.warning(f"Watch UUID {watch_uuid} not found in datastore")
 
+    def handle_watch_bumped_favicon_signal(self, *args, **kwargs):
+        watch_uuid = kwargs.get('watch_uuid')
+        if watch_uuid:
+            # Emit the queue size to all connected clients
+            self.socketio_instance.emit("watch_bumped_favicon", {
+                "uuid": watch_uuid,
+                "event_timestamp": time.time()
+            })
+        logger.debug(f"Watch UUID {watch_uuid} got its favicon updated")
+
+    def handle_deleted_signal(self, *args, **kwargs):
+        watch_uuid = kwargs.get('watch_uuid')
+        if watch_uuid:
+            # Emit the queue size to all connected clients
+            self.socketio_instance.emit("watch_deleted", {
+                "uuid": watch_uuid,
+                "event_timestamp": time.time()
+            })
+        logger.debug(f"Watch UUID {watch_uuid} was deleted")
+
     def handle_queue_length(self, *args, **kwargs):
         """Handle queue_length signal and emit to all clients"""
         try:
             queue_length = kwargs.get('length', 0)
             logger.debug(f"SignalHandler: Queue length update received: {queue_length}")
-            
+
             # Emit the queue size to all connected clients
             self.socketio_instance.emit("queue_size", {
                 "q_length": queue_length,
                 "event_timestamp": time.time()
             })
-            
+
         except Exception as e:
             logger.error(f"Socket.IO error in handle_queue_length: {str(e)}")
 
+    def handle_notification_event(self, *args, **kwargs):
+        """Handle notification_event signal and emit to all clients"""
+        try:
+            watch_uuid = kwargs.get('watch_uuid')
+            logger.debug(f"SignalHandler: Notification event received for watch UUID: {watch_uuid}")
 
-    def polling_emit_running_or_queued_watches(self):
-        """Greenlet that periodically updates the browser/frontend with current state of who is being checked or queued
-        This is because sometimes the browser page could reload (like on clicking on a link) but the data is old
-        """
-        logger.info("Queue update greenlet started")
+            # Emit the notification event to all connected clients
+            self.socketio_instance.emit("notification_event", {
+                "watch_uuid": watch_uuid,
+                "event_timestamp": time.time()
+            })
 
-        # Import the watch_check_update signal, update_q, and running_update_threads here to avoid circular imports
-        from changedetectionio.flask_app import app, running_update_threads
+            logger.trace(f"Socket.IO: Emitted notification_event for watch UUID {watch_uuid}")
+
+        except Exception as e:
+            logger.error(f"Socket.IO error in handle_notification_event: {str(e)}")
+
+    def polling_emit_running_or_queued_watches_threaded(self):
+        """Threading version of polling for Windows compatibility"""
+        import time
+        import threading
+        logger.info("Queue update thread started (threading mode)")
+
+        # Import here to avoid circular imports
+        from changedetectionio.flask_app import app
+        from changedetectionio import worker_handler
         watch_check_update = signal('watch_check_update')
-        
-        # Use gevent sleep for non-blocking operation
-        from gevent import sleep as gevent_sleep
 
-        # Get the stop event from the socketio instance
-        stop_event = self.socketio_instance.stop_event if hasattr(self.socketio_instance, 'stop_event') else None
+        # Track previous state to avoid unnecessary emissions
+        previous_running_uuids = set()
 
-        # Run until explicitly stopped
-        while stop_event is None or not stop_event.is_set():
+        # Run until app shutdown - check exit flag more frequently for fast shutdown
+        exit_event = getattr(app.config, 'exit', threading.Event())
+
+        while not exit_event.is_set():
             try:
-                # For each item in the queue, send a signal, so we update the UI
-                for t in running_update_threads:
-                    if hasattr(t, 'current_uuid') and t.current_uuid:
-                        logger.trace(f"Sending update for {t.current_uuid}")
-                        # Send with app_context to ensure proper URL generation
-                        with app.app_context():
-                            watch_check_update.send(app_context=app, watch_uuid=t.current_uuid)
-                        # Yield control back to gevent after each send to prevent blocking
-                        gevent_sleep(0.1)  # Small sleep to yield control
-                    
-                    # Check if we need to stop in the middle of processing
-                    if stop_event is not None and stop_event.is_set():
-                        break
+                # Get current running UUIDs from async workers
+                running_uuids = set(worker_handler.get_running_uuids())
 
-                # Sleep between polling/update cycles
-                gevent_sleep(2)
+                # Only send updates for UUIDs that changed state
+                newly_running = running_uuids - previous_running_uuids
+                no_longer_running = previous_running_uuids - running_uuids
+
+                # Send updates for newly running UUIDs (but exit fast if shutdown requested)
+                for uuid in newly_running:
+                    if exit_event.is_set():
+                        break
+                    logger.trace(f"Threading polling: UUID {uuid} started processing")
+                    with app.app_context():
+                        watch_check_update.send(app_context=app, watch_uuid=uuid)
+                    time.sleep(0.01)  # Small yield
+
+                # Send updates for UUIDs that finished processing (but exit fast if shutdown requested)
+                if not exit_event.is_set():
+                    for uuid in no_longer_running:
+                        if exit_event.is_set():
+                            break
+                        logger.trace(f"Threading polling: UUID {uuid} finished processing")
+                        with app.app_context():
+                            watch_check_update.send(app_context=app, watch_uuid=uuid)
+                        time.sleep(0.01)  # Small yield
+
+                # Update tracking for next iteration
+                previous_running_uuids = running_uuids
+
+                # Sleep between polling cycles, but check exit flag every 0.5 seconds for fast shutdown
+                for _ in range(20):  # 20 * 0.5 = 10 seconds total
+                    if exit_event.is_set():
+                        break
+                    time.sleep(0.5)
 
             except Exception as e:
-                logger.error(f"Error in queue update greenlet: {str(e)}")
-                # Sleep a bit to avoid flooding logs in case of persistent error
-                gevent_sleep(0.5)
+                logger.error(f"Error in threading polling: {str(e)}")
+                # Even during error recovery, check for exit quickly
+                for _ in range(1):  # 1 * 0.5 = 0.5 seconds
+                    if exit_event.is_set():
+                        break
+                    time.sleep(0.5)
 
-        logger.info("Queue update greenlet stopped")
+        # Check if we're in pytest environment - if so, be more gentle with logging
+        import sys
+        in_pytest = "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ
+
+        if not in_pytest:
+            logger.info("Queue update thread stopped (threading mode)")
 
 
 def handle_watch_update(socketio, **kwargs):
@@ -123,14 +201,12 @@ def handle_watch_update(socketio, **kwargs):
         datastore = kwargs.get('datastore')
 
         # Emit the watch update to all connected clients
-        from changedetectionio.flask_app import running_update_threads, update_q
+        from changedetectionio.flask_app import update_q
         from changedetectionio.flask_app import _jinja2_filter_datetime
+        from changedetectionio import worker_handler
 
         # Get list of watches that are currently running
-        running_uuids = []
-        for t in running_update_threads:
-            if hasattr(t, 'current_uuid') and t.current_uuid:
-                running_uuids.append(t.current_uuid)
+        running_uuids = worker_handler.get_running_uuids()
 
         # Get list of watches in the queue
         queue_list = []
@@ -138,46 +214,47 @@ def handle_watch_update(socketio, **kwargs):
             if hasattr(q_item, 'item') and 'uuid' in q_item.item:
                 queue_list.append(q_item.item['uuid'])
 
-        error_texts = ""
         # Get the error texts from the watch
         error_texts = watch.compile_error_texts()
-
         # Create a simplified watch data object to send to clients
+
         watch_data = {
             'checking_now': True if watch.get('uuid') in running_uuids else False,
+            'error_text': error_texts,
+            'event_timestamp': time.time(),
             'fetch_time': watch.get('fetch_time'),
             'has_error': True if error_texts else False,
-            'last_changed': watch.get('last_changed'),
+            'has_favicon': True if watch.get_favicon_filename() else False,
+            'history_n': watch.history_n,
+            'last_changed_text': timeago.format(int(watch.last_changed), time.time()) if watch.history_n >= 2 and int(watch.last_changed) > 0 else 'Not yet',
             'last_checked': watch.get('last_checked'),
-            'error_text': error_texts,
             'last_checked_text': _jinja2_filter_datetime(watch),
-            'last_changed_text': timeago.format(int(watch['last_changed']), time.time()) if watch.history_n >= 2 and int(watch.get('last_changed', 0)) > 0 else 'Not yet',
-            'queued': True if watch.get('uuid') in queue_list else False,
-            'paused': True if watch.get('paused') else False,
             'notification_muted': True if watch.get('notification_muted') else False,
+            'paused': True if watch.get('paused') else False,
+            'queued': True if watch.get('uuid') in queue_list else False,
             'unviewed': watch.has_unviewed,
             'uuid': watch.get('uuid'),
-            'event_timestamp': time.time()
         }
 
-        errored_count =0
-        for uuid, watch in datastore.data['watching'].items():
-            if watch.get('last_error'):
+        errored_count = 0
+        for watch_uuid_iter, watch_iter in datastore.data['watching'].items():
+            if watch_iter.get('last_error'):
                 errored_count += 1
 
         general_stats = {
             'count_errors': errored_count,
-            'has_unviewed': datastore.has_unviewed
+            'unread_changes_count': datastore.unread_changes_count
         }
 
         # Debug what's being emitted
-        #logger.debug(f"Emitting 'watch_update' event for {watch.get('uuid')}, data: {watch_data}")
-        
+        # logger.debug(f"Emitting 'watch_update' event for {watch.get('uuid')}, data: {watch_data}")
+
         # Emit to all clients (no 'broadcast' parameter needed - it's the default behavior)
-        socketio.emit("watch_update", {'watch': watch_data, 'general_stats': general_stats})
-        
-        # Log after successful emit
-        #logger.info(f"Socket.IO: Emitted update for watch {watch.get('uuid')}, Checking now: {watch_data['checking_now']}")
+        socketio.emit("watch_update", {'watch': watch_data})
+        socketio.emit("general_stats_update", general_stats)
+
+        # Log after successful emit - use watch_data['uuid'] to avoid variable shadowing issues
+        logger.trace(f"Socket.IO: Emitted update for watch {watch_data['uuid']}, Checking now: {watch_data['checking_now']}")
 
     except Exception as e:
         logger.error(f"Socket.IO error in handle_watch_update: {str(e)}")
@@ -185,35 +262,87 @@ def handle_watch_update(socketio, **kwargs):
 
 def init_socketio(app, datastore):
     """Initialize SocketIO with the main Flask app"""
-    # Use the threading async_mode instead of eventlet
-    # This avoids the need for monkey patching eventlet,
-    # Which leads to problems with async playwright etc
-    async_mode = 'gevent'
-    logger.info(f"Using {async_mode} mode for Socket.IO")
+    import platform
+    import sys
+
+    # Platform-specific async_mode selection for better stability
+    system = platform.system().lower()
+    python_version = sys.version_info
+
+    # Check for SocketIO mode configuration via environment variable
+    # Default is 'threading' for best cross-platform compatibility
+    socketio_mode = os.getenv('SOCKETIO_MODE', 'threading').lower()
+
+    if socketio_mode == 'gevent':
+        # Use gevent mode (higher concurrency but platform limitations)
+        try:
+            import gevent
+            async_mode = 'gevent'
+            logger.info(f"SOCKETIO_MODE=gevent: Using {async_mode} mode for Socket.IO")
+        except ImportError:
+            async_mode = 'threading'
+            logger.warning(f"SOCKETIO_MODE=gevent but gevent not available, falling back to {async_mode} mode")
+    elif socketio_mode == 'threading':
+        # Use threading mode (default - best compatibility)
+        async_mode = 'threading'
+        logger.info(f"SOCKETIO_MODE=threading: Using {async_mode} mode for Socket.IO")
+    else:
+        # Invalid mode specified, use default
+        async_mode = 'threading'
+        logger.warning(f"Invalid SOCKETIO_MODE='{socketio_mode}', using default {async_mode} mode for Socket.IO")
+
+    # Log platform info for debugging
+    logger.info(f"Platform: {system}, Python: {python_version.major}.{python_version.minor}, Socket.IO mode: {async_mode}")
 
     # Restrict SocketIO CORS to same origin by default, can be overridden with env var
     cors_origins = os.environ.get('SOCKETIO_CORS_ORIGINS', None)
-    
+
     socketio = SocketIO(app,
-                      async_mode=async_mode,
-                      cors_allowed_origins=cors_origins,  # None means same-origin only
-                      logger=strtobool(os.getenv('SOCKETIO_LOGGING', 'False')),
-                      engineio_logger=strtobool(os.getenv('SOCKETIO_LOGGING', 'False')))
+                        async_mode=async_mode,
+                        cors_allowed_origins=cors_origins,  # None means same-origin only
+                        logger=strtobool(os.getenv('SOCKETIO_LOGGING', 'False')),
+                        engineio_logger=strtobool(os.getenv('SOCKETIO_LOGGING', 'False')))
 
     # Set up event handlers
+    logger.info("Socket.IO: Registering connect event handler")
+
+    @socketio.on('checkbox-operation')
+    def event_checkbox_operations(data):
+        from changedetectionio.blueprint.ui import _handle_operations
+        from changedetectionio import queuedWatchMetaData
+        from changedetectionio import worker_handler
+        from changedetectionio.flask_app import update_q, watch_check_update
+        logger.trace(f"Got checkbox operations event: {data}")
+
+        datastore = socketio.datastore
+
+        _handle_operations(
+            op=data.get('op'),
+            uuids=data.get('uuids'),
+            datastore=datastore,
+            extra_data=data.get('extra_data'),
+            worker_handler=worker_handler,
+            update_q=update_q,
+            queuedWatchMetaData=queuedWatchMetaData,
+            watch_check_update=watch_check_update,
+            emit_flash=False
+        )
+
     @socketio.on('connect')
     def handle_connect():
         """Handle client connection"""
-        from changedetectionio.auth_decorator import login_optionally_required
+        #        logger.info("Socket.IO: CONNECT HANDLER CALLED - Starting connection process")
         from flask import request
         from flask_login import current_user
         from changedetectionio.flask_app import update_q
 
         # Access datastore from socketio
         datastore = socketio.datastore
+        #        logger.info(f"Socket.IO: Current user authenticated: {current_user.is_authenticated if hasattr(current_user, 'is_authenticated') else 'No current_user'}")
 
         # Check if authentication is required and user is not authenticated
         has_password_enabled = datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False)
+        #        logger.info(f"Socket.IO: Password enabled: {has_password_enabled}")
         if has_password_enabled and not current_user.is_authenticated:
             logger.warning("Socket.IO: Rejecting unauthenticated connection")
             return False  # Reject the connection
@@ -231,6 +360,7 @@ def init_socketio(app, datastore):
 
         logger.info("Socket.IO: Client connected")
 
+    #    logger.info("Socket.IO: Registering disconnect event handler")
     @socketio.on('disconnect')
     def handle_disconnect():
         """Handle client disconnection"""
@@ -239,45 +369,40 @@ def init_socketio(app, datastore):
     # Create a dedicated signal handler that will receive signals and emit them to clients
     signal_handler = SignalHandler(socketio, datastore)
 
+    # Register watch operation event handlers
+    from .events import register_watch_operation_handlers
+    register_watch_operation_handlers(socketio, datastore)
+
     # Store the datastore reference on the socketio object for later use
     socketio.datastore = datastore
-    
-    # Create a stop event for our queue update thread using gevent Event
-    import gevent.event
-    stop_event = gevent.event.Event()
-    socketio.stop_event = stop_event
 
-    
+    # No stop event needed for threading mode - threads check app.config.exit directly
+
     # Add a shutdown method to the socketio object
     def shutdown():
-        """Shutdown the SocketIO server gracefully"""
+        """Shutdown the SocketIO server fast and aggressively"""
         try:
-            logger.info("Socket.IO: Shutting down server...")
-            
-            # Signal the queue update thread to stop
-            if hasattr(socketio, 'stop_event'):
-                socketio.stop_event.set()
-                logger.info("Socket.IO: Signaled queue update thread to stop")
-            
-            # Wait for the greenlet to exit (with timeout)
+            logger.info("Socket.IO: Fast shutdown initiated...")
+
+            # For threading mode, give the thread a very short time to exit gracefully
             if hasattr(socketio, 'polling_emitter_thread'):
-                try:
-                    # For gevent greenlets
-                    socketio.polling_emitter_thread.join(timeout=5)
-                    logger.info("Socket.IO: Queue update greenlet joined successfully")
-                except Exception as e:
-                    logger.error(f"Error joining greenlet: {str(e)}")
-                    logger.info("Socket.IO: Queue update greenlet did not exit in time")
-            
-            # Close any remaining client connections
-            #if hasattr(socketio, 'server'):
-            #    socketio.server.disconnect()
-            logger.info("Socket.IO: Server shutdown complete")
+                if socketio.polling_emitter_thread.is_alive():
+                    logger.info("Socket.IO: Waiting 1 second for polling thread to stop...")
+                    socketio.polling_emitter_thread.join(timeout=1.0)  # Only 1 second timeout
+                    if socketio.polling_emitter_thread.is_alive():
+                        logger.info("Socket.IO: Polling thread still running after timeout - continuing with shutdown")
+                    else:
+                        logger.info("Socket.IO: Polling thread stopped quickly")
+                else:
+                    logger.info("Socket.IO: Polling thread already stopped")
+
+            logger.info("Socket.IO: Fast shutdown complete")
         except Exception as e:
             logger.error(f"Socket.IO error during shutdown: {str(e)}")
-    
+
     # Attach the shutdown method to the socketio object
     socketio.shutdown = shutdown
 
     logger.info("Socket.IO initialized and attached to main Flask app")
-    return socketio
+    logger.info(f"Socket.IO: Registered event handlers: {socketio.handlers if hasattr(socketio, 'handlers') else 'No handlers found'}")
+    return socketio

changedetectionio/run_socks_proxy_tests.sh

@@ -9,7 +9,7 @@ set -x
 # SOCKS5 related - start simple Socks5 proxy server
 # SOCKSTEST=xyz should show in the logs of this service to confirm it fetched
 docker run --network changedet-network -d --hostname socks5proxy --rm  --name socks5proxy -p 1080:1080 -e PROXY_USER=proxy_user123 -e PROXY_PASSWORD=proxy_pass123 serjs/go-socks5-proxy
-docker run --network changedet-network -d --hostname socks5proxy-noauth --rm  -p 1081:1080 --name socks5proxy-noauth  serjs/go-socks5-proxy
+docker run --network changedet-network -d --hostname socks5proxy-noauth --rm -p 1081:1080 --name socks5proxy-noauth -e REQUIRE_AUTH=false serjs/go-socks5-proxy
 
 echo "---------------------------------- SOCKS5 -------------------"
 # SOCKS5 related - test from proxies.json

changedetectionio/safe_jinja.py

@@ -10,9 +10,15 @@ import os
 
 JINJA2_MAX_RETURN_PAYLOAD_SIZE = 1024 * int(os.getenv("JINJA2_MAX_RETURN_PAYLOAD_SIZE_KB", 1024 * 10))
 
-
+# This is used for notifications etc, so actually it's OK to send custom HTML such as <a href> etc, but it should limit what data is available.
+# (Which also limits available functions that could be called)
 def render(template_str, **args: t.Any) -> str:
     jinja2_env = jinja2.sandbox.ImmutableSandboxedEnvironment(extensions=['jinja2_time.TimeExtension'])
     output = jinja2_env.from_string(template_str).render(args)
     return output[:JINJA2_MAX_RETURN_PAYLOAD_SIZE]
 
+def render_fully_escaped(content):
+    env = jinja2.sandbox.ImmutableSandboxedEnvironment(autoescape=True)
+    template = env.from_string("{{ some_html|e }}")
+    return template.render(some_html=content)
+

changedetectionio/static/js/plugins.js

@@ -159,6 +159,7 @@
         // Return the current request in case it's needed
         return requests[namespace];
     };
+
 })(jQuery);
 
 

changedetectionio/static/js/realtime.js

@@ -2,22 +2,41 @@
 
 $(document).ready(function () {
 
-    function bindAjaxHandlerButtonsEvents() {
-        $('.ajax-op').on('click.ajaxHandlerNamespace', function (e) {
+    function bindSocketHandlerButtonsEvents(socket) {
+        $('.ajax-op').on('click.socketHandlerNamespace', function (e) {
             e.preventDefault();
-            $.ajax({
-                type: "POST",
-                url: ajax_toggle_url,
-                data: {'op': $(this).data('op'), 'uuid': $(this).closest('tr').data('watch-uuid')},
-                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.");
-                    }
-                }
+            const op = $(this).data('op');
+            const uuid = $(this).closest('tr').data('watch-uuid');
+            
+            console.log(`Socket.IO: Sending watch operation '${op}' for UUID ${uuid}`);
+            
+            // Emit the operation via Socket.IO
+            socket.emit('watch_operation', {
+                'op': op,
+                'uuid': uuid
             });
+            
             return false;
         });
+
+
+        $('#checkbox-operations button').on('click.socketHandlerNamespace', function (e) {
+            e.preventDefault();
+            const op = $(this).val();
+            const checkedUuids = $('input[name="uuids"]:checked').map(function () {
+                return this.value.trim();
+            }).get();
+            console.log(`Socket.IO: Sending watch operation '${op}' for UUIDs:`, checkedUuids);
+            socket.emit('checkbox-operation', {
+                op: op,
+                uuids: checkedUuids,
+                extra_data: $('#op_extradata').val() // Set by the alert() handler
+            });
+            $('input[name="uuids"]:checked').prop('checked', false);
+            $('#check-all:checked').prop('checked', false);
+            return false;
+        });
+
     }
 
 
@@ -29,16 +48,17 @@ $(document).ready(function () {
             // Connect to Socket.IO on the same host/port, with path from template
             const socket = io({
                 path: socketio_url,  // This will be the path prefix like "/app/socket.io" from the template
-                transports: ['polling', 'websocket'],  // Try WebSocket but fall back to polling
-                reconnectionDelay: 1000,
-                reconnectionAttempts: 15
+                transports: ['websocket', 'polling'],
+                reconnectionDelay: 3000,
+                reconnectionAttempts: 25
             });
 
             // Connection status logging
             socket.on('connect', function () {
+                $('#realtime-conn-error').hide();
                 console.log('Socket.IO connected with path:', socketio_url);
                 console.log('Socket transport:', socket.io.engine.transport.name);
-                bindAjaxHandlerButtonsEvents();
+                bindSocketHandlerButtonsEvents(socket);
             });
 
             socket.on('connect_error', function(error) {
@@ -55,7 +75,8 @@ $(document).ready(function () {
 
             socket.on('disconnect', function (reason) {
                 console.log('Socket.IO disconnected, reason:', reason);
-                $('.ajax-op').off('.ajaxHandlerNamespace')
+                $('.ajax-op').off('.socketHandlerNamespace');
+                $('#realtime-conn-error').show();
             });
 
             socket.on('queue_size', function (data) {
@@ -63,47 +84,73 @@ $(document).ready(function () {
                 // Update queue size display if implemented in the UI
             })
 
-            // Listen for periodically emitted watch data
-            console.log('Adding watch_update event listener');
+            // Listen for operation results
+            socket.on('operation_result', function (data) {
+                if (data.success) {
+                    console.log(`Socket.IO: Operation '${data.operation}' completed successfully for UUID ${data.uuid}`);
+                } else {
+                    console.error(`Socket.IO: Operation failed: ${data.error}`);
+                    alert("There was a problem processing the request: " + data.error);
+                }
+            });
+
+            socket.on('notification_event', function (data) {
+                console.log(`Stub handler for notification_event ${data.watch_uuid}`)
+            });
+
+            socket.on('watch_deleted', function (data) {
+                $('tr[data-watch-uuid="' + data.uuid + '"] td').fadeOut(500, function () {
+                    $(this).closest('tr').remove();
+                });
+            });
+
+            // So that the favicon is only updated when the server has written the scraped favicon to disk.
+            socket.on('watch_bumped_favicon', function (watch) {
+                const $watchRow = $(`tr[data-watch-uuid="${watch.uuid}"]`);
+                if ($watchRow.length) {
+                    $watchRow.addClass('has-favicon');
+                    // Because the event could be emitted from a process that is outside the app context, url_for() might not work.
+                    // Lets use url_for at template generation time to give us a PLACEHOLDER instead
+                    let favicon_url = favicon_baseURL.replace('/PLACEHOLDER', `/${watch.uuid}?cache=${watch.event_timestamp}`);
+                    console.log(`Setting favicon for UUID - ${watch.uuid} - ${favicon_url}`);
+                    $('img.favicon', $watchRow).attr('src', favicon_url);
+                }
+            })
+
+            socket.on('general_stats_update', function (general_stats) {
+                // Tabs at bottom of list
+                $('#watch-table-wrapper').toggleClass("has-unread-changes", general_stats.unread_changes_count !==0)
+                $('#watch-table-wrapper').toggleClass("has-error", general_stats.count_errors !== 0)
+                $('#post-list-with-errors a').text(`With errors (${ new Intl.NumberFormat(navigator.language).format(general_stats.count_errors) })`);
+                $('#unread-tab-counter').text(new Intl.NumberFormat(navigator.language).format(general_stats.unread_changes_count));
+            });
 
             socket.on('watch_update', function (data) {
                 const watch = data.watch;
-                const general_stats = data.general_stats;
 
-                // Log the entire watch object for debugging
-                console.log('!!! WATCH UPDATE EVENT RECEIVED !!!');
-                console.log(`${watch.event_timestamp} - Watch update ${watch.uuid} - Checking now - ${watch.checking_now} - UUID in URL ${window.location.href.includes(watch.uuid)}`);
-                console.log('Watch data:', watch);
-                console.log('General stats:', general_stats);
-                
                 // Updating watch table rows
                 const $watchRow = $('tr[data-watch-uuid="' + watch.uuid + '"]');
                 console.log('Found watch row elements:', $watchRow.length);
-                
+
                 if ($watchRow.length) {
                     $($watchRow).toggleClass('checking-now', watch.checking_now);
                     $($watchRow).toggleClass('queued', watch.queued);
                     $($watchRow).toggleClass('unviewed', watch.unviewed);
                     $($watchRow).toggleClass('has-error', watch.has_error);
+                    $($watchRow).toggleClass('has-favicon', watch.has_favicon);
                     $($watchRow).toggleClass('notification_muted', watch.notification_muted);
                     $($watchRow).toggleClass('paused', watch.paused);
+                    $($watchRow).toggleClass('single-history', watch.history_n === 1);
+                    $($watchRow).toggleClass('multiple-history', watch.history_n >= 2);
 
                     $('td.title-col .error-text', $watchRow).html(watch.error_text)
-
-                    $('td.last-changed', $watchRow).text(watch.last_checked_text)
-
+                    $('td.last-changed', $watchRow).text(watch.last_changed_text)
                     $('td.last-checked .innertext', $watchRow).text(watch.last_checked_text)
                     $('td.last-checked', $watchRow).data('timestamp', watch.last_checked).data('fetchduration', watch.fetch_time);
                     $('td.last-checked', $watchRow).data('eta_complete', watch.last_checked + watch.fetch_time);
-                    
+
                     console.log('Updated UI for watch:', watch.uuid);
                 }
-
-                // Tabs at bottom of list
-                $('#post-list-mark-views').toggleClass("has-unviewed", general_stats.has_unviewed);
-                $('#post-list-with-errors').toggleClass("has-error", general_stats.count_errors !== 0)
-                $('#post-list-with-errors a').text(`With errors (${ general_stats.count_errors })`);
-
                 $('body').toggleClass('checking-now', watch.checking_now && window.location.href.includes(watch.uuid));
             });
 

changedetectionio/static/js/watch-overview.js

@@ -16,6 +16,12 @@ $(function () {
         $('#op_extradata').val(prompt("Enter a tag name"));
     });
 
+
+    $('.history-link').click(function (e) {
+        // Incase they click 'back' in the browser, it should be removed.
+        $(this).closest('tr').removeClass('unviewed');
+    });
+
     $('.with-share-link > *').click(function () {
         $("#copied-clipboard").remove();
 

changedetectionio/static/js/watch-settings.js

@@ -51,6 +51,7 @@ $(document).ready(function () {
         $('#notification_body').val('');
         $('#notification_format').val('System default');
         $('#notification_urls').val('');
+        $('#notification_muted_none').prop('checked', true); // in the case of a ternary field
         e.preventDefault();
     });
     $("#notification-token-toggle").click(function (e) {

changedetectionio/static/styles/package.json

@@ -3,15 +3,16 @@
   "version": "0.0.3",
   "description": "",
   "main": "index.js",
-  "scripts": {
-    "watch": "node-sass -w scss -o .",
-    "build": "node-sass scss -o ."
+  "engines": {
+    "node": ">=18.0.0"
   },
-  "author": "",
-  "license": "ISC",
+  "scripts": {
+    "watch": "sass --watch scss:. --style=compressed --no-source-map",
+    "build": "sass scss:. --style=compressed --no-source-map"
+  },
+  "author": "Leigh Morresi / Web Technologies s.r.o.",
+  "license": "Apache",
   "dependencies": {
-    "node-sass": "^7.0.0",
-    "tar": "^6.1.9",
-    "trim-newlines": "^3.0.1"
+    "sass": "^1.77.8"
   }
 }

changedetectionio/static/styles/scss/diff.scss

@@ -1,4 +1,4 @@
-@import "parts/_variables.scss";
+@use "parts/variables";
 
 #diff-ui {
 

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

@@ -64,17 +64,17 @@ body.proxy-check-active {
 #recommended-proxy {
   display: grid;
   gap: 2rem;
-    @media  (min-width: 991px) {
-      grid-template-columns: repeat(2, 1fr);
-    }
+  padding-bottom: 1em;
+  
+  @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 {

changedetectionio/static/styles/scss/parts/_lister_extra.scss

@@ -0,0 +1,92 @@
+.watch-table {
+  &.favicon-not-enabled {
+    tr {
+      .favicon {
+        display: none;
+      }
+    }
+  }
+
+  tr {
+    /* make the icons and the text inline-ish */
+    td.inline.title-col {
+      .flex-wrapper {
+        display: flex;
+        align-items: center;
+        gap: 4px;
+      }
+    }
+  }
+
+
+  td,
+  th {
+    vertical-align: middle;
+  }
+
+  tr.has-favicon {
+    &.unviewed {
+      img.favicon {
+        opacity: 1.0 !important;
+      }
+    }
+  }
+
+  .status-icons {
+    white-space: nowrap;
+    display: flex;
+    align-items: center; /* Vertical centering */
+    gap: 4px; /* Space between image and text */
+    > * {
+      vertical-align: middle;
+    }
+  }
+}
+
+.title-col {
+  /* Optional, for spacing */
+  padding: 10px;
+}
+
+.title-wrapper {
+  display: flex;
+  align-items: center; /* Vertical centering */
+  gap: 10px; /* Space between image and text */
+}
+
+/* Make sure .title-col-inner doesn't collapse or misalign */
+.title-col-inner {
+  display: inline-block;
+  vertical-align: middle;
+}
+
+/* favicon styling */
+.watch-table {
+  img.favicon {
+    vertical-align: middle;
+    max-width: 25px;
+    max-height: 25px;
+    height: 25px;
+    padding-right: 4px;
+  }
+
+    // Reserved for future use
+  /*  &.thumbnail-type-screenshot {
+      tr.has-favicon {
+        td.inline.title-col {
+          img.thumbnail {
+            background-color: #fff; !* fallback bg for SVGs without bg *!
+            border-radius: 4px; !* subtle rounded corners *!
+            border: 1px solid #ddd; !* light border for contrast *!
+            box-shadow: 0 2px 6px rgba(0, 0, 0, 0.15); !* soft shadow *!
+            filter: contrast(1.05) saturate(1.1) drop-shadow(0 0 0.5px rgba(0, 0, 0, 0.2));
+            object-fit: cover; !* crop/fill if needed *!
+            opacity: 0.8;
+            max-width: 30px;
+            max-height: 30px;
+            height: 30px;
+          }
+        }
+      }
+    }*/
+}

changedetectionio/static/styles/scss/parts/_preview_text_filter.scss

@@ -1,4 +1,4 @@
-@import "minitabs";
+@use "minitabs";
 
 body.preview-text-enabled {
 

changedetectionio/static/styles/scss/parts/_socket.scss

@@ -17,15 +17,6 @@ body.checking-now {
   position: fixed;
 }
 
-#post-list-buttons {
-  #post-list-with-errors.has-error {
-    display: inline-block !important;
-  }
-  #post-list-mark-views.has-unviewed {
-    display: inline-block !important;
-  }
-}
-
 
 
 

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

@@ -78,6 +78,7 @@
   --color-text-watch-tag-list: rgba(231, 0, 105, 0.4);
   --color-background-new-watch-form: rgba(0, 0, 0, 0.05);
   --color-background-new-watch-input: var(--color-white);
+  --color-background-new-watch-input-transparent: rgba(255, 255, 255, 0.1);
   --color-text-new-watch-input: var(--color-text);
 
   --color-border-input: var(--color-grey-500);
@@ -112,6 +113,7 @@ html[data-darkmode="true"] {
   --color-background-gradient-third: #4d2c64;
 
   --color-background-new-watch-input: var(--color-grey-100);
+  --color-background-new-watch-input-transparent: var(--color-grey-100);
   --color-text-new-watch-input: var(--color-text);
   --color-background-table-thead: var(--color-grey-200);
   --color-table-background: var(--color-grey-300);

changedetectionio/static/styles/scss/parts/_watch_table-mobile.scss

@@ -0,0 +1,178 @@
+$grid-col-checkbox: 20px;
+$grid-col-watch: 100px;
+$grid-gap: 0.5rem;
+
+
+@media (max-width: 767px) {
+
+  /*
+  Max width before this PARTICULAR table gets nasty
+  This query will take effect for any screen smaller than 760px
+  and also iPads specifically.
+  */
+  .watch-table {
+    /* make headings work on mobile */
+    thead {
+      display: block;
+
+      tr {
+        th {
+          display: inline-block;
+          // Hide the "Last" text for smaller screens
+          @media (max-width: 768px) {
+            .hide-on-mobile {
+              display: none;
+            }
+          }
+        }
+      }
+
+      .empty-cell {
+        display: none;
+      }
+    }
+
+
+    .last-checked {
+      margin-left: calc($grid-col-checkbox + $grid-gap);
+
+      > span {
+        vertical-align: middle;
+      }
+    }
+
+    .last-changed {
+      margin-left: calc($grid-col-checkbox + $grid-gap);
+    }
+
+    .last-checked::before {
+      color: var(--color-text);
+      content: "Last Checked ";
+    }
+
+    .last-changed::before {
+      color: var(--color-text);
+      content: "Last Changed ";
+    }
+
+    /* Force table to not be like tables anymore */
+    td.inline {
+      display: inline-block;
+    }
+
+    .pure-table td,
+    .pure-table th {
+      border: none;
+    }
+
+    td {
+      /* Behave  like a "row" */
+      border: none;
+      border-bottom: 1px solid var(--color-border-watch-table-cell);
+      vertical-align: middle;
+
+      &:before {
+        /* Top/left values mimic padding */
+        top: 6px;
+        left: 6px;
+        width: 45%;
+        padding-right: 10px;
+        white-space: nowrap;
+      }
+    }
+
+    &.pure-table-striped {
+      tr {
+        background-color: var(--color-table-background);
+      }
+
+      tr:nth-child(2n-1) {
+        background-color: var(--color-table-stripe);
+      }
+
+      tr:nth-child(2n-1) td {
+        background-color: inherit;
+      }
+    }
+  }
+}
+
+@media (max-width: 767px) {
+  .watch-table {
+    tbody {
+      tr {
+        padding-bottom: 10px;
+        padding-top: 10px;
+        display: grid;
+        grid-template-columns: $grid-col-checkbox 1fr $grid-col-watch;
+        grid-template-rows: auto auto auto auto;
+        gap: $grid-gap;
+
+        .counter-i {
+          display: none;
+        }
+
+        td.checkbox-uuid {
+          display: grid;
+          place-items: center;
+        }
+
+        td.inline {
+          /* display: block !important;;*/
+        }
+
+        > td {
+          border-bottom: none;
+        }
+
+        > td.title-col {
+          grid-column: 1 / -1;
+          grid-row: 1;
+          .watch-title {
+            font-size: 0.92rem;
+          }
+          .link-spread {
+            display: none;
+          }
+        }
+
+        > td.last-checked {
+          grid-column: 1 / -1;
+          grid-row: 2;
+        }
+
+        > td.last-changed {
+          grid-column: 1 / -1;
+          grid-row: 3;
+        }
+
+        > td.checkbox-uuid {
+          grid-column: 1;
+          grid-row: 4;
+        }
+
+        > td.buttons {
+          grid-column: 2;
+          grid-row: 4;
+          display: flex;
+          align-items: center;
+          justify-content: flex-start;
+        }
+
+        > td.watch-controls {
+          grid-column: 3;
+          grid-row: 4;
+          display: grid;
+          place-items: center;
+
+          a img {
+            padding: 10px;
+          }
+        }
+      }
+    }
+  }
+  .pure-table td {
+    padding: 3px !important;
+  }
+}

changedetectionio/static/styles/scss/parts/_watch_table.scss

@@ -7,6 +7,7 @@
     &.unviewed {
       font-weight: bold;
     }
+
     color: var(--color-watch-table-row-text);
   }
 
@@ -18,6 +19,12 @@
       word-break: break-all;
       white-space: normal;
     }
+
+    a.external::after {
+      content: url(data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAQElEQVR42qXKwQkAIAxDUUdxtO6/RBQkQZvSi8I/pL4BoGw/XPkh4XigPmsUgh0626AjRsgxHTkUThsG2T/sIlzdTsp52kSS1wAAAABJRU5ErkJggg==);
+      margin: 0 3px 0 5px;
+    }
+
   }
 
 
@@ -39,27 +46,20 @@
     }
   }
 
-  .title-col a[target="_blank"]::after,
-  .current-diff-url::after {
-    content: url(data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAQElEQVR42qXKwQkAIAxDUUdxtO6/RBQkQZvSi8I/pL4BoGw/XPkh4XigPmsUgh0626AjRsgxHTkUThsG2T/sIlzdTsp52kSS1wAAAABJRU5ErkJggg==);
-    margin: 0 3px 0 5px;
-  }
-
-
   /* Row with 'checking-now' */
   tr.checking-now {
     td:first-child {
-        position: relative;
+      position: relative;
     }
 
     td:first-child::before {
-        content: "";
-        position: absolute;
-        top: 0;
-        bottom: 0;
-        left: 0;
-        width: 3px;
-        background-color: #293eff;
+      content: "";
+      position: absolute;
+      top: 0;
+      bottom: 0;
+      left: 0;
+      width: 3px;
+      background-color: #293eff;
     }
 
     td.last-checked {
@@ -110,9 +110,61 @@
 
   tr.has-error {
     color: var(--color-watch-table-error);
+
     .error-text {
       display: block !important;
     }
   }
+
+  tr.single-history {
+    a.preview-link {
+      display: inline-block !important;
+    }
+  }
+
+  tr.multiple-history {
+    a.history-link {
+      display: inline-block !important;
+    }
+  }
+
+
 }
 
+#watch-table-wrapper {
+  /* general styling */
+  #post-list-buttons {
+    text-align: right;
+    padding: 0px;
+    margin: 0px;
+
+    li {
+      display: inline-block;
+    }
+
+    a {
+      border-top-left-radius: initial;
+      border-top-right-radius: initial;
+      border-bottom-left-radius: 5px;
+      border-bottom-right-radius: 5px;
+    }
+  }
+
+  /* post list dynamically on/off stuff */
+
+  &.has-error {
+    #post-list-buttons {
+      #post-list-with-errors {
+        display: inline-block !important;
+      }
+    }
+  }
+
+  &.has-unread-changes {
+    #post-list-buttons {
+      #post-list-unread, #post-list-mark-views, #post-list-unread {
+        display: inline-block !important;
+      }
+    }
+  }
+}

changedetectionio/static/styles/scss/parts/_widgets.scss

@@ -0,0 +1,114 @@
+
+// Ternary radio button group component
+.ternary-radio-group {
+  display: flex;
+  gap: 0;
+  border: 1px solid var(--color-grey-750);
+  border-radius: 4px;
+  overflow: hidden;
+  width: fit-content;
+  background: var(--color-background);
+
+  .ternary-radio-option {
+    position: relative;
+    cursor: pointer;
+    margin: 0;
+    display: flex;
+    align-items: center;
+
+    input[type="radio"] {
+      position: absolute;
+      opacity: 0;
+      width: 0;
+      height: 0;
+    }
+
+    .ternary-radio-label {
+      padding: 8px 16px;
+      background: var(--color-grey-900);
+      border: none;
+      border-right: 1px solid var(--color-grey-750);
+      font-size: 13px;
+      font-weight: 500;
+      color: var(--color-text);
+      transition: all 0.2s ease;
+      cursor: pointer;
+      display: block;
+      text-align: center;
+    }
+
+    &:last-child .ternary-radio-label {
+      border-right: none;
+    }
+
+    input:checked + .ternary-radio-label {
+      background: var(--color-link);
+      color: var(--color-text-button);
+      font-weight: 600;
+
+      &.ternary-default {
+        background: var(--color-grey-600);
+        color: var(--color-text-button);
+      }
+
+      &:hover {
+        background: #1a7bc4;
+
+        &.ternary-default {
+          background: var(--color-grey-500);
+        }
+      }
+    }
+
+    &:hover .ternary-radio-label {
+      background: var(--color-grey-800);
+    }
+  }
+
+  @media (max-width: 480px) {
+    width: 100%;
+
+    .ternary-radio-label {
+      flex: 1;
+      min-width: auto;
+    }
+  }
+}
+
+// Standard radio button styling
+input[type="radio"].pure-radio:checked + label,
+input[type="radio"].pure-radio:checked {
+  background: var(--color-link);
+  color: var(--color-text-button);
+}
+
+html[data-darkmode="true"] {
+  .ternary-radio-group {
+    .ternary-radio-option {
+      .ternary-radio-label {
+        background: var(--color-grey-350);
+      }
+
+      &:hover .ternary-radio-label {
+        background: var(--color-grey-400);
+      }
+
+      input:checked + .ternary-radio-label {
+        background: var(--color-link);
+        color: var(--color-text-button);
+
+        &.ternary-default {
+          background: var(--color-grey-600);
+        }
+
+        &:hover {
+          background: #1a7bc4;
+
+          &.ternary-default {
+            background: var(--color-grey-500);
+          }
+        }
+      }
+    }
+  }
+}

changedetectionio/static/styles/scss/styles.scss

@@ -2,21 +2,25 @@
  * -- BASE STYLES --
  */
 
-@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";
-@import "parts/preview_text_filter";
-@import "parts/_watch_table";
-@import "parts/_edit";
-@import "parts/_conditions_table";
-@import "parts/_socket";
+@use "parts/variables";
+@use "parts/arrows";
+@use "parts/browser-steps";
+@use "parts/extra_proxies";
+@use "parts/extra_browsers";
+@use "parts/pagination";
+@use "parts/spinners";
+@use "parts/darkmode";
+@use "parts/menu";
+@use "parts/love";
+@use "parts/preview_text_filter";
+@use "parts/watch_table";
+@use "parts/watch_table-mobile";
+@use "parts/edit";
+@use "parts/conditions_table";
+@use "parts/lister_extra";
+@use "parts/socket";
+@use "parts/visualselector";
+@use "parts/widgets";
 
 body {
   color: var(--color-text);
@@ -184,32 +188,21 @@ code {
   @extend .inline-tag;
 }
 
+@media (min-width: 768px) {
+  .box {
+    margin: 0 1em !important;
+  }
+}
+
 .box {
-  max-width: 80%;
+  max-width: 100%;
+  margin: 0 0.3em;
   flex-direction: column;
   display: flex;
   justify-content: center;
 }
 
 
-#post-list-buttons {
-  text-align: right;
-  padding: 0px;
-  margin: 0px;
-
-  li {
-    display: inline-block;
-  }
-
-  a {
-    border-top-left-radius: initial;
-    border-top-right-radius: initial;
-    border-bottom-left-radius: 5px;
-    border-bottom-right-radius: 5px;
-  }
-}
-
-
 body:after {
   content: "";
   background: linear-gradient(130deg, var(--color-background-gradient-first), var(--color-background-gradient-second) 41.07%, var(--color-background-gradient-third) 84.05%);
@@ -279,7 +272,7 @@ a.pure-button-selected {
   font-size: 65%;
   border-bottom-left-radius: initial;
   border-bottom-right-radius: initial;
-
+  margin-right: 4px;
   &.active {
     background: var(--color-background-button-tag-active);
     font-weight: bold;
@@ -372,11 +365,32 @@ label {
   }
 }
 
+// Some field colouring for transperant field
+.pure-form input[type=text].transparent-field {
+  background-color:  var(--color-background-new-watch-input-transparent) !important;
+  color: var(--color-white) !important;
+  border: 1px solid rgba(255, 255, 255, 0.2) !important;
+  box-shadow: none !important;
+  -webkit-box-shadow: none !important;
+  &::placeholder {
+    opacity: 0.5;
+    color: rgba(255, 255, 255, 0.7);
+    font-weight: lighter;
+  }
+}
+
 #new-watch-form {
   background: var(--color-background-new-watch-form);
   padding: 1em;
   border-radius: 10px;
   margin-bottom: 1em;
+  max-width: 100%;
+
+  #url {
+    &::placeholder {
+      font-weight: bold;
+    }
+  }
 
   input {
     display: inline-block;
@@ -397,12 +411,13 @@ label {
     font-weight: bold;
   }
 
-  #watch-add-wrapper-zone {
 
+  #watch-add-wrapper-zone {
     @media only screen and (min-width: 760px) {
       display: flex;
       gap: 0.3rem;
       flex-direction: row;
+      min-width: 70vw;
     }
     /* URL field grows always, other stay static in width */
     > span {
@@ -424,6 +439,22 @@ label {
       }
     }
   }
+
+  #watch-group-tag {
+    font-size: 0.9rem;
+    padding: 0.3rem;
+    display: flex;
+    align-items: center;
+    gap: 0.5rem;
+    color: var(--color-white);
+    label, input {
+      margin: 0;
+    }
+
+    input {
+      flex: 1;
+    }
+  }
 }
 
 
@@ -620,10 +651,6 @@ footer {
 
 @media only screen and (max-width: 760px),
 (min-device-width: 768px) and (max-device-width: 1024px) {
-  .box {
-    max-width: 95%
-  }
-
   .edit-form {
     padding: 0.5em;
     margin: 0;
@@ -659,114 +686,6 @@ footer {
     width: 100%;
   }
 
-  /*
-  Max width before this PARTICULAR table gets nasty
-  This query will take effect for any screen smaller than 760px
-  and also iPads specifically.
-  */
-  .watch-table {
-    /* make headings work on mobile */
-    thead {
-      display: block;
-      tr {
-        th {
-          display: inline-block;
-          // Hide the "Last" text for smaller screens
-          @media (max-width: 768px) {
-            .hide-on-mobile {
-              display: none; 
-            }
-          }
-        }
-      }
-      .empty-cell {
-        display: none;
-      }
-    }
-
-    /* Force table to not be like tables anymore */
-    tbody {
-      td,
-      tr {
-        display: block;
-      }
-    }
-
-    tbody {
-      tr {
-        display: flex;
-        flex-wrap: wrap;
-
-        // The third child of each row will take up the remaining space
-        // This is useful for the URL column, which should expand to fill the remaining space
-        :nth-child(3) {
-          flex-grow: 1;
-        }
-        // The last three children (from the end) of each row will take up the full width
-        // This is useful for the "Last Checked", "Last Changed", and the action buttons columns, which should each take up the full width
-        :nth-last-child(-n+3) {
-          flex-basis: 100%;
-        }
-      }
-    }
-
-    .last-checked {
-      >span {
-        vertical-align: middle;
-      }
-    }
-
-    .last-checked::before {
-      color: var(--color-last-checked);
-      content: "Last Checked ";
-    }
-
-    .last-changed::before {
-      color: var(--color-last-checked);
-      content: "Last Changed ";
-    }
-
-    /* Force table to not be like tables anymore */
-    td.inline {
-      display: inline-block;
-    }
-
-    .pure-table td,
-    .pure-table th {
-      border: none;
-    }
-
-    td {
-      /* Behave  like a "row" */
-      border: none;
-      border-bottom: 1px solid var(--color-border-watch-table-cell);
-      vertical-align: middle;
-
-      &:before {
-        /* Top/left values mimic padding */
-        top: 6px;
-        left: 6px;
-        width: 45%;
-        padding-right: 10px;
-        white-space: nowrap;
-      }
-    }
-
-    &.pure-table-striped {
-      tr {
-        background-color: var(--color-table-background);
-      }
-
-      tr:nth-child(2n-1) {
-        background-color: var(--color-table-stripe);
-      }
-
-      tr:nth-child(2n-1) td {
-        background-color: inherit;
-      }
-    }
-
-  }
 }
 
 .pure-table {
@@ -1021,8 +940,6 @@ ul {
   }
 }
 
-@import "parts/_visualselector";
-
 #webdriver_delay {
     width: 5em;
 }
@@ -1083,6 +1000,9 @@ ul {
     /* some space if they wrap the page */
     margin-bottom: 3px;
     margin-top: 3px;
+    /* vertically center icon and text */
+    display: inline-flex;
+    align-items: center;
   }
 }
 
@@ -1137,19 +1057,23 @@ ul {
 
 
 #quick-watch-processor-type {
-  color: #fff;
-  ul {
-    padding: 0.3rem;
-
+  ul#processor {
+    color: #fff;
+    padding-left: 0px;
     li {
       list-style: none;
-      font-size: 0.8rem;
-      > * {
-        display: inline-block;
-      }
+      font-size: 0.9rem;
+      display: grid;
+      grid-template-columns: auto 1fr;
+      align-items: center;
+      gap: 0.5rem;
+      margin-bottom: 0.5rem;
     }
   }
-
+  label, input {
+    padding: 0;
+    margin: 0;
+  }
 }
 
 .restock-label {
@@ -1187,3 +1111,13 @@ ul {
   vertical-align: middle;
 }
 
+#realtime-conn-error {
+  position: fixed;
+  bottom: 0;
+  left: 0;
+  background: var(--color-warning);
+  padding: 10px;
+  font-size: 0.8rem;
+  color: #fff;
+  opacity: 0.8;
+}

changedetectionio/store.py

@@ -13,6 +13,7 @@ import json
 import os
 import re
 import secrets
+import sys
 import threading
 import time
 import uuid as uuid_builder
@@ -45,7 +46,7 @@ class ChangeDetectionStore:
         # logging.basicConfig(filename='/dev/stdout', level=logging.INFO)
         self.__data = App.model()
         self.datastore_path = datastore_path
-        self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
+        self.json_store_path = os.path.join(self.datastore_path, "url-watches.json")
         logger.info(f"Datastore path is '{self.json_store_path}'")
         self.needs_write = False
         self.start_time = time.time()
@@ -118,14 +119,12 @@ class ChangeDetectionStore:
         test_list = self.proxy_list
 
         # Helper to remove password protection
-        password_reset_lockfile = "{}/removepassword.lock".format(self.datastore_path)
+        password_reset_lockfile = os.path.join(self.datastore_path, "removepassword.lock")
         if path.isfile(password_reset_lockfile):
             self.__data['settings']['application']['password'] = False
             unlink(password_reset_lockfile)
 
         if not 'app_guid' in self.__data:
-            import os
-            import sys
             if "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ:
                 self.__data['app_guid'] = "test-" + str(uuid_builder.uuid4())
             else:
@@ -203,14 +202,13 @@ class ChangeDetectionStore:
         return seconds
 
     @property
-    def has_unviewed(self):
-        if not self.__data.get('watching'):
-            return None
-
+    def unread_changes_count(self):
+        unread_changes_count = 0
         for uuid, watch in self.__data['watching'].items():
             if watch.history_n >= 2 and watch.viewed == False:
-                return True
-        return False
+                unread_changes_count += 1
+
+        return unread_changes_count
 
     @property
     def data(self):
@@ -238,6 +236,7 @@ class ChangeDetectionStore:
         with self.lock:
             if uuid == 'all':
                 self.__data['watching'] = {}
+                time.sleep(1) # Mainly used for testing to allow all items to flush before running next test
 
                 # GitHub #30 also delete history records
                 for uuid in self.data['watching']:
@@ -252,6 +251,9 @@ class ChangeDetectionStore:
                 del self.data['watching'][uuid]
 
         self.needs_write_urgent = True
+        watch_delete_signal = signal('watch_deleted')
+        if watch_delete_signal:
+            watch_delete_signal.send(watch_uuid=uuid)
 
     # Clone a watch by UUID
     def clone(self, uuid):
@@ -259,11 +261,6 @@ class ChangeDetectionStore:
         extras = deepcopy(self.data['watching'][uuid])
         new_uuid = self.add_watch(url=url, extras=extras)
         watch = self.data['watching'][new_uuid]
-
-        if self.data['settings']['application'].get('extract_title_as_title') or watch['extract_title_as_title']:
-            # Because it will be recalculated on the next fetch
-            self.data['watching'][new_uuid]['title'] = None
-
         return new_uuid
 
     def url_exists(self, url):
@@ -305,7 +302,6 @@ class ChangeDetectionStore:
                     'browser_steps',
                     'css_filter',
                     'extract_text',
-                    'extract_title_as_title',
                     'headers',
                     'ignore_text',
                     'include_filters',
@@ -320,6 +316,7 @@ class ChangeDetectionStore:
                     'title',
                     'trigger_text',
                     'url',
+                    'use_page_title_in_list',
                     'webdriver_js_execute_code',
                 ]:
                     if res.get(k):
@@ -382,9 +379,9 @@ class ChangeDetectionStore:
         return new_uuid
 
     def visualselector_data_is_ready(self, watch_uuid):
-        output_path = "{}/{}".format(self.datastore_path, watch_uuid)
-        screenshot_filename = "{}/last-screenshot.png".format(output_path)
-        elements_index_filename = "{}/elements.deflate".format(output_path)
+        output_path = os.path.join(self.datastore_path, watch_uuid)
+        screenshot_filename = os.path.join(output_path, "last-screenshot.png")
+        elements_index_filename = os.path.join(output_path, "elements.deflate")
         if path.isfile(screenshot_filename) and  path.isfile(elements_index_filename) :
             return True
 
@@ -407,7 +404,8 @@ class ChangeDetectionStore:
                 # This is a fairly basic strategy to deal with the case that the file is corrupted,
                 # system was out of memory, out of RAM etc
                 with open(self.json_store_path+".tmp", 'w') as json_file:
-                    json.dump(data, json_file, indent=4)
+                    # Use compact JSON in production for better performance
+                    json.dump(data, json_file, indent=2)
                 os.replace(self.json_store_path+".tmp", self.json_store_path)
             except Exception as e:
                 logger.error(f"Error writing JSON!! (Main JSON file save was skipped) : {str(e)}")
@@ -469,7 +467,7 @@ class ChangeDetectionStore:
 
         # Load from external config file
         if path.isfile(proxy_list_file):
-            with open("{}/proxies.json".format(self.datastore_path)) as f:
+            with open(os.path.join(self.datastore_path, "proxies.json")) as f:
                 proxy_list = json.load(f)
 
         # Mapping from UI config if available
@@ -727,10 +725,10 @@ class ChangeDetectionStore:
                 logger.critical(f"Applying update_{update_n}")
                 # Wont exist on fresh installs
                 if os.path.exists(self.json_store_path):
-                    shutil.copyfile(self.json_store_path, self.datastore_path+"/url-watches-before-{}.json".format(update_n))
+                    shutil.copyfile(self.json_store_path, os.path.join(self.datastore_path, f"url-watches-before-{update_n}.json"))
 
                 try:
-                    update_method = getattr(self, "update_{}".format(update_n))()
+                    update_method = getattr(self, f"update_{update_n}")()
                 except Exception as e:
                     logger.error(f"Error while trying update_{update_n}")
                     logger.error(e)
@@ -969,6 +967,16 @@ class ChangeDetectionStore:
                         f_d.write(zlib.compress(f_j.read()))
                         os.unlink(json_path)
 
+    def update_20(self):
+        for uuid, watch in self.data['watching'].items():
+            if self.data['watching'][uuid].get('extract_title_as_title'):
+                self.data['watching'][uuid]['use_page_title_in_list'] = self.data['watching'][uuid].get('extract_title_as_title')
+                del self.data['watching'][uuid]['extract_title_as_title']
+
+        if self.data['settings']['application'].get('extract_title_as_title'):
+            self.data['settings']['application']['ui']['use_page_title_in_list'] = self.data['settings']['application'].get('extract_title_as_title')
+
+
     def add_notification_url(self, notification_url):
         
         logger.debug(f">>> Adding new notification_url - '{notification_url}'")

changedetectionio/templates/_common_fields.html

@@ -70,11 +70,11 @@
                                     </tr>
                                     <tr>
                                         <td><code>{{ '{{watch_title}}' }}</code></td>
-                                        <td>The title of the watch.</td>
+                                        <td>The page title of the watch, uses &lt;title&gt; if not set, falls back to URL</td>
                                     </tr>
                                     <tr>
                                         <td><code>{{ '{{watch_tag}}' }}</code></td>
-                                        <td>The watch label / tag</td>
+                                        <td>The watch group / tag</td>
                                     </tr>
                                     <tr>
                                         <td><code>{{ '{{preview_url}}' }}</code></td>

changedetectionio/templates/_helpers.html

@@ -1,14 +1,29 @@
 {% 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>
+    <div {% if field.errors or field.top_errors %} class="error" {% endif %}>{{ field.label }}</div>
+    <div {% if field.errors or field.top_errors %} class="error" {% endif %}>{{ field(**kwargs)|safe }}
+        {% if field.top_errors %}
+            top
+            <ul class="errors top-errors">
+                {% for error in field.top_errors %}
+                    <li>{{ error }}</li>
+                {% endfor %}
+            </ul>
+        {% endif %}
+        {% if field.errors %}
+            <ul class=errors>
+                {% if field.errors is mapping and 'form' in field.errors %}
+                    {#  and subfield form errors, such as used in RequiredFormField() for TimeBetweenCheckForm sub form #}
+                    {% set errors = field.errors['form'] %}
+                {% else %}
+                    {#  regular list of errors with this field #}
+                    {% set errors = field.errors %}
+                {% endif %}
+                {% for error in errors %}
+                    <li>{{ error }}</li>
+                {% endfor %}
+            </ul>
+        {% endif %}
+    </div>
 {% endmacro %}
 
 {% macro render_checkbox_field(field) %}
@@ -24,6 +39,23 @@
   </div>
 {% endmacro %}
 
+{% macro render_ternary_field(field, BooleanField=false) %}
+  {% if BooleanField %}
+    {% set _ = field.__setattr__('boolean_mode', true) %}
+  {% endif %}
+  <div class="ternary-field {% if field.errors %} error {% endif %}">
+    <div class="ternary-field-label">{{ field.label }}</div>
+    <div class="ternary-field-widget">{{ field(**kwargs)|safe }}</div>
+    {% 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/base.html

@@ -5,6 +5,7 @@
     <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 name="robots" content="noindex">
     <title>Change Detection{{extra_title}}</title>
     {% if app_rss_token %}
       <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag_uuid %}- {{active_tag.title}}{% endif %}" href="{{ url_for('rss.feed', tag=active_tag_uuid , token=app_rss_token)}}" >
@@ -33,12 +34,14 @@
     </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='csrf.js')}}" defer></script>
-    <script src="{{url_for('static_content', group='js', filename='socket.io.min.js')}}" integrity="sha384-c79GN5VsunZvi+Q/WObgk2in0CbZsHnjEqvFxC5DxHn9lTfNce2WW6h2pH6u/kF+" crossorigin="anonymous"></script>
+    <script src="{{url_for('static_content', group='js', filename='feather-icons.min.js')}}" defer></script>
+    {% if socket_io_enabled %}
+    <script src="{{url_for('static_content', group='js', filename='socket.io.min.js')}}"></script>
     <script src="{{url_for('static_content', group='js', filename='realtime.js')}}" defer></script>
-    <script src="{{url_for('static_content', group='js', filename='timeago-init.js')}}" defer></script>
+    {% endif %}
   </head>
 
-  <body class="">
+  <body class="{{extra_classes}}">
     <div class="header">
     <div class="pure-menu-fixed" style="width: 100%;">
       <div class="home-menu pure-menu pure-menu-horizontal" id="nav-menu">
@@ -234,6 +237,7 @@
     <script src="{{url_for('static_content', group='js', filename='toggle-theme.js')}}" defer></script>
 
     <div id="checking-now-fixed-tab" style="display: none;"><span class="spinner"></span><span>&nbsp;Checking now</span></div>
+    <div id="realtime-conn-error" style="display:none">Real-time updates offline</div>
   </body>
 
 </html>

changedetectionio/templates/edit/text-options.html

@@ -26,7 +26,10 @@
                             <li>Changing this will affect the comparison checksum which may trigger an alert</li>
                         </ul>
                 </span>
-
+                <br><br>
+                    <div class="pure-control-group">
+                      {{ render_ternary_field(form.strip_ignored_lines) }}
+                    </div>
                 </fieldset>
 
                 <fieldset>

changedetectionio/tests/conftest.py

@@ -10,6 +10,8 @@ import os
 import sys
 from loguru import logger
 
+from changedetectionio.tests.util import live_server_setup, new_live_server_setup
+
 # https://github.com/pallets/flask/blob/1.1.2/examples/tutorial/tests/test_auth.py
 # Much better boilerplate than the docs
 # https://www.python-boilerplate.com/py3+flask+pytest/
@@ -70,6 +72,22 @@ def cleanup(datastore_path):
             if os.path.isfile(f):
                 os.unlink(f)
 
+@pytest.fixture(scope='function', autouse=True)
+def prepare_test_function(live_server):
+
+    routes = [rule.rule for rule in live_server.app.url_map.iter_rules()]
+    if '/test-random-content-endpoint' not in routes:
+        logger.debug("Setting up test URL routes")
+        new_live_server_setup(live_server)
+
+
+    yield
+    # Then cleanup/shutdown
+    live_server.app.config['DATASTORE'].data['watching']={}
+    time.sleep(0.3)
+    live_server.app.config['DATASTORE'].data['watching']={}
+
+
 @pytest.fixture(scope='session')
 def app(request):
     """Create application for the tests."""
@@ -106,8 +124,33 @@ def app(request):
     app.config['STOP_THREADS'] = True
 
     def teardown():
+        # Stop all threads and services
         datastore.stop_thread = True
         app.config.exit.set()
+        
+        # Shutdown workers gracefully before loguru cleanup
+        try:
+            from changedetectionio import worker_handler
+            worker_handler.shutdown_workers()
+        except Exception:
+            pass
+            
+        # Stop socket server threads
+        try:
+            from changedetectionio.flask_app import socketio_server
+            if socketio_server and hasattr(socketio_server, 'shutdown'):
+                socketio_server.shutdown()
+        except Exception:
+            pass
+        
+        # Give threads a moment to finish their shutdown
+        import time
+        time.sleep(0.1)
+        
+        # Remove all loguru handlers to prevent "closed file" errors
+        logger.remove()
+        
+        # Cleanup files
         cleanup(app_config['datastore_path'])
 
        

changedetectionio/tests/custom_browser_url/test_custom_browser_url.py

@@ -55,7 +55,8 @@ def do_test(client, live_server, make_test_use_extra_browser=False):
                   "tags": "",
                   "headers": "",
                   'fetch_backend': f"extra_browser_{custom_browser_name}",
-                  'webdriver_js_execute_code': ''
+                  'webdriver_js_execute_code': '',
+                  "time_between_check_use_default": "y"
             },
             follow_redirects=True
         )
@@ -78,12 +79,12 @@ def do_test(client, live_server, make_test_use_extra_browser=False):
 
 # Requires playwright to be installed
 def test_request_via_custom_browser_url(client, live_server, measure_memory_usage):
-    live_server_setup(live_server)
+   #  live_server_setup(live_server) # Setup on conftest per function
     # 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, measure_memory_usage):
-    live_server_setup(live_server)
+   #  live_server_setup(live_server) # Setup on conftest per function
     # 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

@@ -2,19 +2,24 @@
 
 import time
 from flask import url_for
+import os
 from ..util import live_server_setup, wait_for_all_checks
 import logging
 
+
 # Requires playwright to be installed
 def test_fetch_webdriver_content(client, live_server, measure_memory_usage):
-    live_server_setup(live_server)
+    #  live_server_setup(live_server) # Setup on conftest per function
 
     #####################
     res = client.post(
         url_for("settings.settings_page"),
-        data={"application-empty_pages_are_a_change": "",
-              "requests-time_between_check-minutes": 180,
-              'application-fetch_backend': "html_webdriver"},
+        data={
+            "application-empty_pages_are_a_change": "",
+            "requests-time_between_check-minutes": 180,
+            'application-fetch_backend': "html_webdriver",
+            'application-ui-favicons_enabled': "y",
+        },
         follow_redirects=True
     )
 
@@ -30,11 +35,51 @@ def test_fetch_webdriver_content(client, live_server, measure_memory_usage):
     assert b"1 Imported" in res.data
     wait_for_all_checks(client)
 
-
     res = client.get(
         url_for("ui.ui_views.preview_page", uuid="first"),
         follow_redirects=True
     )
     logging.getLogger().info("Looking for correct fetched HTML (text) from server")
-
     assert b'cool it works' in res.data
+
+    # Favicon scraper check, favicon only so far is fetched when in browser mode (not requests mode)
+    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
+        uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
+        res = client.get(
+            url_for("watchlist.index"),
+        )
+        # The UI can access it here
+        assert f'src="/static/favicon/{uuid}'.encode('utf8') in res.data
+
+        # Attempt to fetch it, make sure that works
+        res = client.get(url_for('static_content', group='favicon', filename=uuid))
+        assert res.status_code == 200
+        assert len(res.data) > 10
+
+        # Check the API also returns it
+        api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
+        res = client.get(
+            url_for("watchfavicon", uuid=uuid),
+            headers={'x-api-key': api_key}
+        )
+        assert res.status_code == 200
+        assert len(res.data) > 10
+
+    ##################### disable favicons check
+    res = client.post(
+        url_for("settings.settings_page"),
+        data={
+            "requests-time_between_check-minutes": 180,
+            'application-ui-favicons_enabled': "",
+            "application-empty_pages_are_a_change": "",
+        },
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." in res.data
+
+    res = client.get(
+        url_for("watchlist.index"),
+    )
+    # The UI can access it here
+    assert f'src="/static/favicon'.encode('utf8') not in res.data

changedetectionio/tests/fetchers/test_custom_js_before_content.py

@@ -5,7 +5,7 @@ from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_cli
 
 def test_execute_custom_js(client, live_server, measure_memory_usage):
 
-    live_server_setup(live_server)
+   #  live_server_setup(live_server) # Setup on conftest per function
     assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
 
     test_url = url_for('test_interactive_html_endpoint', _external=True)
@@ -28,6 +28,7 @@ def test_execute_custom_js(client, live_server, measure_memory_usage):
             'fetch_backend': "html_webdriver",
             'webdriver_js_execute_code': 'document.querySelector("button[name=test-button]").click();',
             'headers': "testheader: yes\buser-agent: MyCustomAgent",
+            "time_between_check_use_default": "y",
         },
         follow_redirects=True
     )

changedetectionio/tests/proxy_list/test_multiple_proxy.py

@@ -6,7 +6,7 @@ from ..util import live_server_setup, wait_for_all_checks
 
 
 def test_preferred_proxy(client, live_server, measure_memory_usage):
-    live_server_setup(live_server)
+   #  live_server_setup(live_server) # Setup on conftest per function
     url = "http://chosen.changedetection.io"
 
 
@@ -27,6 +27,7 @@ def test_preferred_proxy(client, live_server, measure_memory_usage):
                 "proxy": "proxy-two",
                 "tags": "",
                 "url": url,
+                "time_between_check_use_default": "y",
               },
         follow_redirects=True
     )

changedetectionio/tests/proxy_list/test_noproxy.py

@@ -6,7 +6,7 @@ from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_cli
 
 
 def test_noproxy_option(client, live_server, measure_memory_usage):
-    live_server_setup(live_server)
+   #  live_server_setup(live_server) # Setup on conftest per function
     # Run by run_proxy_tests.sh
     # Call this URL then scan the containers that it never went through them
     url = "http://noproxy.changedetection.io"
@@ -62,6 +62,7 @@ def test_noproxy_option(client, live_server, measure_memory_usage):
                 "proxy": "no-proxy",
                 "tags": "",
                 "url": url,
+                "time_between_check_use_default": "y",
               },
         follow_redirects=True
     )