revert accidential change

.dockerignore

@@ -33,7 +33,6 @@ venv/
 # Test and development files
 test-datastore/
 tests/
-docs/
 *.md
 !README.md
 

.github/dependabot.yml

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

.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

@@ -30,11 +30,11 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@v5
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@v4
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -45,7 +45,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v3
+      uses: github/codeql-action/autobuild@v4
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -59,4 +59,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@v4

.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
 
@@ -133,7 +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
@@ -28,32 +28,53 @@ jobs:
 
 
   test-pypi-package:
-    name: Test the built 📦 package works basically.
+    name: Test the built package works basically.
     runs-on: ubuntu-latest
     needs:
     - 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
       run: |
         set -ex
         ls -alR 
         
-        # Find and install the first .whl file
-        find dist -type f -name "*.whl" -exec pip3 install {} \; -quit
+        # Install the first wheel found in dist/
+        WHEEL=$(find dist -type f -name "*.whl" -print -quit)
+        echo Installing $WHEEL
+        python3 -m pip install --upgrade pip
+        python3 -m pip install "$WHEEL"
         changedetection.io -d /tmp -p 10000 &
         
         sleep 3
         curl --retry-connrefused --retry 6 http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
         curl --retry-connrefused --retry 6 http://127.0.0.1:10000/ >/dev/null
+        
+        # --- API test ---
+        # This also means that the docs/api-spec.yml was shipped and could be read
+        test -f /tmp/url-watches.json
+        API_KEY=$(jq -r '.. | .api_access_token? // empty' /tmp/url-watches.json)
+        echo Test API KEY is $API_KEY
+        curl -X POST "http://127.0.0.1:10000/api/v1/watch" \
+          -H "x-api-key: ${API_KEY}" \
+          -H "Content-Type: application/json" \
+          --show-error --fail \
+          --retry 6 --retry-delay 1 --retry-connrefused \
+          -d '{
+            "url": "https://example.com",
+            "title": "Example Site Monitor",
+            "time_between_check": { "hours": 1 }
+          }'
+          
         killall changedetection.io
 
 
@@ -72,7 +93,7 @@ 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

@@ -38,17 +38,15 @@ jobs:
             dockerfile: ./Dockerfile
           - platform: linux/arm/v8
             dockerfile: ./Dockerfile
-          - platform: linux/arm64/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
 
@@ -76,5 +74,5 @@ jobs:
             file: ${{ matrix.dockerfile }}
             platforms: ${{ matrix.platform }}
             cache-from: type=gha
-            cache-to: type=gha,mode=max
+            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 }}
 
@@ -54,7 +54,10 @@ jobs:
 
       - name: Spin up ancillary SMTP+Echo message test server
         run: |
-          # Debug SMTP server/echo message back server
+          # Debug SMTP server/echo message back server, telnet 11080 to it should immediately bounce back the most recent message that tried to send (then you can see if cdio tried to send, the format, etc)
+          # 11025 is the SMTP port for testing
+          # apprise example would be 'mailto://changedetection@localhost:11025/?to=fff@home.com  (it will also echo to STDOUT)
+          # telnet localhost 11080
           docker run --network changedet-network -d -p 11025:11025 -p 11080:11080  --hostname mailserver test-changedetectionio  bash -c 'pip3 install aiosmtpd && python changedetectionio/tests/smtp/smtp-test-server.py'
           docker ps
 
@@ -253,6 +256,30 @@ jobs:
           docker logs test-cdio-basic-tests > output-logs/test-cdio-basic-tests-stdout-${{ env.PYTHON_VERSION }}.txt
           docker logs test-cdio-basic-tests 2> output-logs/test-cdio-basic-tests-stderr-${{ env.PYTHON_VERSION }}.txt
 
+      - name: Extract and display memory test report
+        if: always()
+        run: |
+          # Extract test-memory.log from the container
+          echo "Extracting test-memory.log from container..."
+          docker cp test-cdio-basic-tests:/app/changedetectionio/test-memory.log output-logs/test-memory-${{ env.PYTHON_VERSION }}.log || echo "test-memory.log not found in container"
+
+          # Display the memory log contents for immediate visibility in workflow output
+          echo "=== Top 10 Highest Peak Memory Tests ==="
+          if [ -f output-logs/test-memory-${{ env.PYTHON_VERSION }}.log ]; then
+            # Sort by peak memory value (extract number before MB and sort numerically, reverse order)
+            grep "Peak memory:" output-logs/test-memory-${{ env.PYTHON_VERSION }}.log | \
+              sed 's/.*Peak memory: //' | \
+              paste -d'|' - <(grep "Peak memory:" output-logs/test-memory-${{ env.PYTHON_VERSION }}.log) | \
+              sort -t'|' -k1 -nr | \
+              cut -d'|' -f2 | \
+              head -10
+            echo ""
+            echo "=== Full Memory Test Report ==="
+            cat output-logs/test-memory-${{ env.PYTHON_VERSION }}.log
+          else
+            echo "No memory log available"
+          fi
+
       - name: Store everything including test-datastore
         if: always()
         uses: actions/upload-artifact@v4

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
@@ -25,6 +26,14 @@ COPY requirements.txt /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 \
@@ -53,6 +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/*
 
@@ -73,6 +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
 
@@ -81,6 +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 +1,9 @@
 recursive-include changedetectionio/api *
+include docs/api-spec.yaml
 recursive-include changedetectionio/blueprint *
-recursive-include changedetectionio/content_fetchers *
 recursive-include changedetectionio/conditions *
+recursive-include changedetectionio/content_fetchers *
+recursive-include changedetectionio/jinja2_custom *
 recursive-include changedetectionio/model *
 recursive-include changedetectionio/notification *
 recursive-include changedetectionio/processors *
@@ -9,6 +11,7 @@ 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__ = '0.50.3'
+__version__ = '0.50.28'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError
@@ -35,13 +35,22 @@ def sigshutdown_handler(_signo, _stack_frame):
     app.config.exit.set()
     datastore.stop_thread = True
     
-    # Shutdown workers immediately
+    # 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'):

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

@@ -5,13 +5,46 @@ 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):
@@ -25,23 +58,9 @@ 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:
@@ -69,19 +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))
 
@@ -89,21 +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))
@@ -113,6 +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
@@ -126,22 +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))
@@ -154,18 +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}")
@@ -191,6 +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):
@@ -199,18 +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()
@@ -225,6 +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)
@@ -243,35 +259,9 @@ class CreateWatch(Resource):
             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()
@@ -285,6 +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

changedetectionio/api/__init__.py

@@ -1,4 +1,7 @@
 import copy
+import functools
+from flask import request, abort
+from loguru import logger
 from . import api_schema
 from ..model import watch_base
 
@@ -8,6 +11,7 @@ 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 +29,58 @@ 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():
+    """Lazy load OpenAPI spec and dependencies only when validation is needed."""
+    import os
+    import yaml  # Lazy import - only loaded when API validation is actually used
+    from openapi_core import OpenAPI  # Lazy import - saves ~10.7 MB on startup
+
+    spec_path = os.path.join(os.path.dirname(__file__), '../../docs/api-spec.yaml')
+    if not os.path.exists(spec_path):
+        # Possibly for pip3 packages
+        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':
+                    # Lazy import - only loaded when actually validating a request
+                    from openapi_core.contrib.flask import FlaskOpenAPIRequest
+
+                    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

@@ -7,6 +7,7 @@ from changedetectionio.flask_app import watch_check_update
 import asyncio
 import importlib
 import os
+import queue
 import time
 
 from loguru import logger
@@ -37,13 +38,23 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore):
         watch = None
 
         try:
-            # Use asyncio wait_for to make queue.get() cancellable
-            queued_item_data = await asyncio.wait_for(q.get(), timeout=1.0)
+            # 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.error(f"Worker {worker_id} error getting queue item: {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
         
@@ -299,15 +310,6 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore):
                     continue
 
                 if process_changedetection_results:
-                    # Extract title if needed
-                    if datastore.data['settings']['application'].get('extract_title_as_title') or watch['extract_title_as_title']:
-                        if not watch['title'] or not len(watch['title']):
-                            try:
-                                update_obj['title'] = html_tools.extract_element(find='title', html_content=update_handler.fetcher.content)
-                                logger.info(f"UUID: {uuid} Extract <title> updated title to '{update_obj['title']}")
-                            except Exception as e:
-                                logger.warning(f"UUID: {uuid} Extract <title> as watch title was enabled, but couldn't find a <title>.")
-
                     try:
                         datastore.update_watch(uuid=uuid, update_obj=update_obj)
 
@@ -332,6 +334,10 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore):
                             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))
 
+                            # Explicitly delete large content variables to free memory IMMEDIATELY after saving
+                            # These are no longer needed after being saved to history
+                            del contents
+
                             # Send notifications on second+ check
                             if watch.history_n >= 2:
                                 logger.info(f"Change detected in UUID {uuid} - {watch['url']}")
@@ -346,6 +352,14 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore):
                 # 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]
@@ -353,9 +367,21 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore):
                 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})
 
+                # NOW clear fetcher content - after all processing is complete
+                # This is the last point where we need the fetcher data
+                if update_handler and hasattr(update_handler, 'fetcher') and update_handler.fetcher:
+                    update_handler.fetcher.clear_content()
+                    logger.debug(f"Cleared fetcher content for UUID {uuid}")
+
         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)
@@ -376,7 +402,28 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore):
                         #logger.info(f"Worker {worker_id} sending completion signal for UUID {watch['uuid']}")
                         watch_check_update.send(watch_uuid=watch['uuid'])
 
-                    update_handler = None
+                    # Explicitly clean up update_handler and all its references
+                    if update_handler:
+                        # Clear fetcher content using the proper method
+                        if hasattr(update_handler, 'fetcher') and update_handler.fetcher:
+                            update_handler.fetcher.clear_content()
+
+                        # Clear processor references
+                        if hasattr(update_handler, 'content_processor'):
+                            update_handler.content_processor = None
+
+                        update_handler = None
+
+                    # Clear local contents variable if it still exists
+                    if 'contents' in locals():
+                        del contents
+
+                    # Note: We don't set watch = None here because:
+                    # 1. watch is just a local reference to datastore.data['watching'][uuid]
+                    # 2. Setting it to None doesn't affect the datastore
+                    # 3. GC can't collect the object anyway (still referenced by datastore)
+                    # 4. It would just cause confusion
+
                     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}")

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -6,7 +6,7 @@ from loguru import logger
 
 from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT
 from changedetectionio.content_fetchers.base import manage_user_agent
-from changedetectionio.safe_jinja import render as jinja_render
+from changedetectionio.jinja2_custom import render as jinja_render
 
 
 

changedetectionio/blueprint/check_proxies/__init__.py

@@ -33,7 +33,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def long_task(uuid, preferred_proxy):
         import time
         from changedetectionio.content_fetchers import exceptions as content_fetcher_exceptions
-        from changedetectionio.safe_jinja import render as jinja_render
+        from changedetectionio.jinja2_custom import render as jinja_render
 
         status = {'status': '', 'length': 0, 'text': ''}
 

changedetectionio/blueprint/rss/blueprint.py

@@ -1,5 +1,5 @@
 
-from changedetectionio.safe_jinja import render as jinja_render
+from changedetectionio.jinja2_custom import render as jinja_render
 from changedetectionio.store import ChangeDetectionStore
 from feedgen.feed import FeedGenerator
 from flask import Blueprint, make_response, request, url_for, redirect
@@ -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

@@ -119,7 +119,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                                 hide_remove_pass=os.getenv("SALTED_PASS", False),
                                 min_system_recheck_seconds=int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3)),
                                 settings_application=datastore.data['settings']['application'],
-                                timezone_default_config=datastore.data['settings']['application'].get('timezone'),
+                                timezone_default_config=datastore.data['settings']['application'].get('scheduler_timezone_default'),
                                 utc_time=utc_time,
                                 )
 

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, render_fieldlist_with_inline_errors %}
 {% 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")}}";
@@ -72,33 +72,23 @@
                         <span class="pure-form-message-inline">Allow access to view watch diff page when password is enabled (Good for sharing the diff page)
                         </span>
                     </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.application.form.rss_hide_muted_watches) }}
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.application.form.pager_size) }}
-                        <span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.application.form.rss_content_format) }}
-                        <span class="pure-form-message-inline">Love RSS? Does your reader support HTML? Set it here</span>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.application.form.extract_title_as_title) }}
-                        <span class="pure-form-message-inline">Note: This will automatically apply to all existing watches.</span>
-                    </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.empty_pages_are_a_change) }}
                         <span class="pure-form-message-inline">When a request returns no content, or the HTML does not contain any text, is this considered a change?</span>
                     </div>
-                {% if form.requests.proxy %}
-                    <div class="pure-control-group inline-radio">
-                        {{ render_field(form.requests.form.proxy, class="fetch-backend-proxy") }}
-                        <span class="pure-form-message-inline">
-                        Choose a default proxy for all watches
-                        </span>
+                    <div class="grey-form-border">
+                        <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.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.rss_reader_mode) }}
+                            <span class="pure-form-message-inline">Transforms RSS/RDF feed watches into beautiful text only</span>
+                        </div>
                     </div>
-                {% endif %}
                 </fieldset>
             </div>
 
@@ -141,6 +131,10 @@
                     <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">
+                    {{ render_field(form.requests.form.timeout) }}
+                    <span class="pure-form-message-inline">For regular plain requests (not chrome based), maximum number of seconds until timeout, 1-999.<br>
+                </div>
                 <div class="pure-control-group inline-radio">
                     {{ render_field(form.requests.form.default_ua) }}
                     <span class="pure-form-message-inline">
@@ -199,11 +193,17 @@ 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) }}
@@ -238,7 +238,7 @@ nav
                     <p><strong>UTC Time &amp Date from Server:</strong> <span id="utc-time" >{{ utc_time }}</span></p>
                     <p><strong>Local Time &amp Date in Browser:</strong> <span class="local-time" data-utc="{{ utc_time }}"></span></p>
                     <p>
-                       {{ render_field(form.application.form.timezone) }}
+                       {{ render_field(form.application.form.scheduler_timezone_default) }}
                         <datalist id="timezones" style="display: none;">
                             {% for tz_name in available_timezones %}
                                 <option value="{{ tz_name }}">{{ tz_name }}</option>
@@ -256,6 +256,18 @@ nav
                     {{ 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>
             <div class="tab-pane-inner" id="proxies">
                 <div id="recommended-proxy">
@@ -304,23 +316,33 @@ nav
                <p><strong>Tip</strong>: "Residential" and "Mobile" proxy type can be more successfull than "Data Center" for blocked websites.
 
                 <div class="pure-control-group" id="extra-proxies-setting">
-                {{ render_field(form.requests.form.extra_proxies) }}
+                {{ render_fieldlist_with_inline_errors(form.requests.form.extra_proxies) }}
                 <span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span><br>
                 <span class="pure-form-message-inline">SOCKS5 proxies with authentication are only supported with 'plain requests' fetcher, for other fetchers you should whitelist the IP access instead</span>
+                {% if form.requests.proxy %}
+                <div>
+                <br>
+                    <div class="inline-radio">
+                        {{ render_field(form.requests.form.proxy, class="fetch-backend-proxy") }}
+                        <span class="pure-form-message-inline">Choose a default proxy for all watches</span>
+                    </div>
+                </div>
+                {% endif %}
                 </div>
                 <div class="pure-control-group" id="extra-browsers-setting">
                     <p>
                     <span class="pure-form-message-inline"><i>Extra Browsers</i> can be attached to further defeat CAPTCHA's on websites that are particularly hard to scrape.</span><br>
                     <span class="pure-form-message-inline">Simply paste the connection address into the box, <a href="https://changedetection.io/tutorial/using-bright-datas-scraping-browser-pass-captchas-and-other-protection-when-monitoring">More instructions and examples here</a> </span>
                     </p>
-                    {{ render_field(form.requests.form.extra_browsers) }}
+                    {{ render_fieldlist_with_inline_errors(form.requests.form.extra_browsers) }}
                 </div>
+            
             </div>
             <div id="actions">
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}
-                    <a href="{{url_for('watchlist.index')}}" class="pure-button button-small button-cancel">Back</a>
-                    <a href="{{url_for('ui.clear_all_history')}}" class="pure-button button-small button-error">Clear Snapshot History</a>
+                    <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/ui/edit.py

@@ -187,7 +187,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
             tz_name = time_schedule_limit.get('timezone')
             if not tz_name:
-                tz_name = datastore.data['settings']['application'].get('timezone', 'UTC')
+                tz_name = datastore.data['settings']['application'].get('scheduler_timezone_default', os.getenv('TZ', 'UTC').strip())
 
             if time_schedule_limit and time_schedule_limit.get('enabled'):
                 try:
@@ -242,6 +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}",
@@ -256,7 +257,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                 'system_has_webdriver_configured': os.getenv('WEBDRIVER_URL'),
                 'ui_edit_stats_extras': collect_ui_edit_stats_extras(watch),
                 'visual_selector_data_ready': datastore.visualselector_data_is_ready(watch_uuid=uuid),
-                'timezone_default_config': datastore.data['settings']['application'].get('timezone'),
+                'timezone_default_config': datastore.data['settings']['application'].get('scheduler_timezone_default'),
                 'using_global_webdriver_wait': not default['webdriver_delay'],
                 'uuid': uuid,
                 'watch': watch,

changedetectionio/blueprint/ui/notification.py

@@ -2,6 +2,7 @@ from flask import Blueprint, request, make_response
 import random
 from loguru import logger
 
+from changedetectionio.notification_service import NotificationContextData
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
 
@@ -19,6 +20,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         import apprise
         from changedetectionio.notification.handler import process_notification
         from changedetectionio.notification.apprise_plugin.assets import apprise_asset
+        from changedetectionio.jinja2_custom import render as jinja_render
 
         from changedetectionio.notification.apprise_plugin.custom_handlers import apprise_http_custom_handler
 
@@ -61,16 +63,20 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             return 'Error: No Notification URLs set/found'
 
         for n_url in notification_urls:
+            # We are ONLY validating the apprise:// part here, convert all tags to something so as not to break apprise URLs
+            generic_notification_context_data = NotificationContextData()
+            generic_notification_context_data.set_random_for_validation()
+            n_url = jinja_render(template_str=n_url, **generic_notification_context_data).strip()
             if len(n_url.strip()):
                 if not apobj.add(n_url):
                     return f'Error:  {n_url} is not a valid AppRise URL.'
 
         try:
             # use the same as when it is triggered, but then override it with the form test values
-            n_object = {
+            n_object = NotificationContextData({
                 'watch_url': request.form.get('window_url', "https://changedetection.io"),
                 'notification_urls': notification_urls
-            }
+            })
 
             # Only use if present, if not set in n_object it should use the default system value
             if 'notification_format' in request.form and request.form['notification_format'].strip():

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

@@ -1,8 +1,7 @@
 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
@@ -78,9 +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
@@ -94,62 +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()
 
@@ -163,7 +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),
@@ -186,7 +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

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'):
@@ -83,7 +87,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
             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,
@@ -93,6 +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

@@ -4,6 +4,7 @@
 <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 favicon_baseURL="{{ url_for('static_content', group='favicon', filename="PLACEHOLDER")}}";</script>
 <script>
 // Initialize Feather icons after the page loads
 document.addEventListener('DOMContentLoaded', function() {
@@ -80,16 +81,26 @@ document.addEventListener('DOMContentLoaded', function() {
     {%- 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 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 = "" -%}
                 <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 -%}
                 <th>Restock &amp; Price</th>
@@ -105,10 +116,13 @@ document.addEventListener('DOMContentLoaded', function() {
                 <td colspan="{{ cols_required }}" style="text-wrap: wrap;">No website watches configured, please add a URL in the box above, or <a href="{{ url_for('imports.import_page')}}" >import a list</a>.</td>
             </tr>
             {%- endif -%}
+
             {%- for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))|pagination_slice(skip=pagination.skip) -%}
                 {%- set checking_now = is_checking_now(watch) -%}
                 {%- set history_n = watch.history_n -%}
-                {#  Mirror in changedetectionio/static/js/realtime.js for the frontend #}
+                {%- 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'],
@@ -116,49 +130,69 @@ document.addEventListener('DOMContentLoaded', function() {
                     '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 ''
+                    '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" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span>{{ loop.index+pagination.skip }}</span></td>
+                <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:','') }}">&nbsp;</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>
 {%- if any_has_restock_price_processor -%}
                 <td class="restock-and-price">
@@ -195,23 +229,25 @@ document.addEventListener('DOMContentLoaded', function() {
                     Not yet
                     {%- 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>
                     <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 -%}
             </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 -%}
@@ -219,6 +255,9 @@ document.addEventListener('DOMContentLoaded', function() {
                 <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>

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
@@ -63,21 +64,36 @@ class Fetcher():
     # Time ONTOP of the system defined env minimum time
     render_extract_delay = 0
 
+    def clear_content(self):
+        """
+        Explicitly clear all content from memory to free up heap space.
+        Call this after content has been saved to disk.
+        """
+        self.content = None
+        if hasattr(self, 'raw_content'):
+            self.raw_content = None
+        self.screenshot = None
+        self.xpath_data = None
+        # Keep headers and status_code as they're small
+        logger.trace("Fetcher content cleared from memory")
+
     @abstractmethod
     def get_error(self):
         return self.error
 
     @abstractmethod
     async 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):
+                  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
 
@@ -125,7 +141,7 @@ class Fetcher():
     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
+        from changedetectionio.jinja2_custom import render as jinja_render
         step_n = 0
 
         if self.browser_steps is not None and len(self.browser_steps):

changedetectionio/content_fetchers/playwright.py

@@ -5,7 +5,7 @@ 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
 
@@ -143,15 +143,17 @@ class fetcher(Fetcher):
             f.write(content)
 
     async 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):
+                  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.async_api import async_playwright
         import playwright._impl._errors
@@ -234,6 +236,13 @@ 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)
+                    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 = await capture_full_page_async(self.page)
                 raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
@@ -274,6 +283,7 @@ class fetcher(Fetcher):
             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

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
@@ -145,15 +145,16 @@ 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()
@@ -179,10 +180,11 @@ class fetcher(Fetcher):
         except Exception as 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
@@ -292,6 +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)
 
@@ -343,8 +351,18 @@ class fetcher(Fetcher):
     async def main(self, **kwargs):
         await self.fetch_page(**kwargs)
 
-    async 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 = int(os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180))
@@ -352,16 +370,17 @@ class fetcher(Fetcher):
         # Now we run this properly in async context since we're called from async worker
         try:
             await asyncio.wait_for(self.main(
-                url=url,
-                timeout=timeout,
-                request_headers=request_headers,
-                request_body=request_body,
-                request_method=request_method,
-                ignore_status_codes=ignore_status_codes,
                 current_include_filters=current_include_filters,
+                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

@@ -51,6 +51,7 @@ class fetcher(Fetcher):
 
         session = requests.Session()
 
+
         if strtobool(os.getenv('ALLOW_FILE_URI', 'false')) and url.startswith('file://'):
             from requests_file import FileAdapter
             session.mount('file://', FileAdapter())
@@ -104,15 +105,17 @@ class fetcher(Fetcher):
         self.raw_content = r.content
 
     async 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):
+                  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()

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

@@ -17,6 +17,7 @@ async () => {
             'back in stock soon',
             'back-order or out of stock',
             'backordered',
+            'backorder',
             'benachrichtigt mich', // notify me
             'binnenkort leverbaar', // coming soon
             'brak na stanie',
@@ -39,12 +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',

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):
@@ -46,20 +46,21 @@ class fetcher(Fetcher):
                 continue
             self.proxy_url = k.strip()
 
-
     async 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):
+                  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,
+                  ):
 
         import asyncio
-        
+
         # Wrap the entire selenium operation in a thread executor
         def _run_sync():
             from selenium.webdriver.chrome.options import Options as ChromeOptions
@@ -140,4 +141,3 @@ class fetcher(Fetcher):
         # 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/flask_app.py

@@ -12,19 +12,17 @@ from blinker import signal
 
 from changedetectionio.strtobool import strtobool
 from threading import Event
-from changedetectionio.custom_queue import SignalPriorityQueue, AsyncSignalPriorityQueue, NotificationQueue
+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
@@ -40,7 +38,7 @@ 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
 
@@ -50,8 +48,8 @@ datastore = None
 ticker_thread = None
 extra_stylesheets = []
 
-# Use async queue by default, keep sync for backward compatibility  
-update_q = AsyncSignalPriorityQueue() if worker_handler.USE_ASYNC_WORKERS else SignalPriorityQueue()
+# Use bulletproof janus-based queues for sync/async reliability  
+update_q = RecheckPriorityQueue()
 notification_q = NotificationQueue()
 MAX_QUEUE_SIZE = 2000
 
@@ -307,7 +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})
@@ -329,7 +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})
@@ -427,6 +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
@@ -769,7 +795,7 @@ def ticker_thread_check_time_launch_checks():
             else:
                 time_schedule_limit = watch.get('time_schedule_limit')
                 logger.trace(f"{uuid} Time scheduler - Using watch settings (not global settings)")
-            tz_name = datastore.data['settings']['application'].get('timezone', 'UTC')
+            tz_name = datastore.data['settings']['application'].get('scheduler_timezone_default', os.getenv('TZ', 'UTC').strip())
 
             if time_schedule_limit and time_schedule_limit.get('enabled'):
                 try:
@@ -818,16 +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
-                    worker_handler.queue_item_async_safe(update_q, 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

@@ -5,6 +5,7 @@ from wtforms.widgets.core import TimeInput
 
 from changedetectionio.blueprint.rss import RSS_FORMAT_TYPES
 from changedetectionio.conditions.form import ConditionFormRow
+from changedetectionio.notification_service import NotificationContextData
 from changedetectionio.strtobool import strtobool
 
 from wtforms import (
@@ -23,11 +24,14 @@ 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 +58,8 @@ 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 +216,35 @@ 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 +253,123 @@ 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()
@@ -318,11 +470,16 @@ class ValidateAppRiseServers(object):
         import apprise
         from .notification.apprise_plugin.assets import apprise_asset
         from .notification.apprise_plugin.custom_handlers import apprise_http_custom_handler  # noqa: F401
+        from changedetectionio.jinja2_custom import render as jinja_render
 
         apobj = apprise.Apprise(asset=apprise_asset)
 
         for server_url in field.data:
-            url = server_url.strip()
+            generic_notification_context_data = NotificationContextData()
+            # Make sure something is atleast in all those regular token fields
+            generic_notification_context_data.set_random_for_validation()
+
+            url = jinja_render(template_str=server_url.strip(), **generic_notification_context_data).strip()
             if url.startswith("#"):
                 continue
 
@@ -336,9 +493,8 @@ class ValidateJinja2Template(object):
     """
     def __call__(self, form, field):
         from changedetectionio import notification
-
+        from changedetectionio.jinja2_custom import create_jinja_env
         from jinja2 import BaseLoader, TemplateSyntaxError, UndefinedError
-        from jinja2.sandbox import ImmutableSandboxedEnvironment
         from jinja2.meta import find_undeclared_variables
         import jinja2.exceptions
 
@@ -346,9 +502,11 @@ 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.globals.update(notification.valid_tokens)
-            # Extra validation tokens provided on the form_class(... extra_tokens={}) setup
+            # Use the shared helper to create a properly configured environment
+            jinja2_env = create_jinja_env(loader=BaseLoader)
+
+            # Add notification tokens for validation
+            jinja2_env.globals.update(NotificationContextData())
             if hasattr(field, 'extra_notification_tokens'):
                 jinja2_env.globals.update(field.extra_notification_tokens)
 
@@ -360,6 +518,7 @@ class ValidateJinja2Template(object):
         except jinja2.exceptions.SecurityError as e:
             raise ValidationError(f"This is not a valid Jinja2 template: {e}") from e
 
+        # Check for undeclared variables
         ast = jinja2_env.parse(joined_data)
         undefined = ", ".join(find_undeclared_variables(ast))
         if undefined:
@@ -396,6 +555,19 @@ 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 +586,7 @@ class ValidateListRegex(object):
                     message = field.gettext('RegEx \'%s\' is not a valid regular expression.')
                     raise ValidationError(message % (line))
 
+
 class ValidateCSSJSONXPATHInput(object):
     """
     Filter validation
@@ -513,6 +686,51 @@ class ValidateCSSJSONXPATHInput(object):
                 except:
                     raise ValidationError("A system-error occurred when validating your jq expression")
 
+class ValidateSimpleURL:
+    """Validate that the value can be parsed by urllib.parse.urlparse() and has a scheme/netloc."""
+    def __init__(self, message=None):
+        self.message = message or "Invalid URL."
+
+    def __call__(self, form, field):
+        data = (field.data or "").strip()
+        if not data:
+            return  # empty is OK — pair with validators.Optional()
+        from urllib.parse import urlparse
+
+        parsed = urlparse(data)
+        if not parsed.scheme or not parsed.netloc:
+            raise ValidationError(self.message)
+
+class ValidateStartsWithRegex(object):
+    def __init__(self, regex, *, flags=0, message=None, allow_empty=True, split_lines=True):
+        # compile with given flags (we’ll pass re.IGNORECASE below)
+        self.pattern = re.compile(regex, flags) if isinstance(regex, str) else regex
+        self.message = message
+        self.allow_empty = allow_empty
+        self.split_lines = split_lines
+
+    def __call__(self, form, field):
+        data = field.data
+        if not data:
+            return
+
+        # normalize into list of lines
+        if isinstance(data, str) and self.split_lines:
+            lines = data.splitlines()
+        elif isinstance(data, (list, tuple)):
+            lines = data
+        else:
+            lines = [data]
+
+        for line in lines:
+            stripped = line.strip()
+            if not stripped:
+                if self.allow_empty:
+                    continue
+                raise ValidationError(self.message or "Empty value not allowed.")
+            if not self.pattern.match(stripped):
+                raise ValidationError(self.message or "Invalid value.")
+
 class quickWatchForm(Form):
     from . import processors
 
@@ -534,14 +752,13 @@ 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())
     notification_title = StringField('Notification Title', default='ChangeDetection.io Notification - {{ watch_url }}', validators=[validators.Optional(), ValidateJinja2Template()])
     notification_urls = StringListField('Notification URL List', validators=[validators.Optional(), ValidateAppRiseServers(), ValidateJinja2Template()])
     processor = RadioField( label=u"Processor - What do you want to achieve?", choices=processors.available_processors(), default="text_json_diff")
-    timezone = StringField("Timezone for watch schedule", render_kw={"list": "timezones"}, validators=[validateTimeZoneName()])
+    scheduler_timezone_default = StringField("Default timezone for watch check scheduler", render_kw={"list": "timezones"}, validators=[validateTimeZoneName()])
     webdriver_delay = IntegerField('Wait seconds before extracting text', validators=[validators.Optional(), validators.NumberRange(min=1, message="Should contain one or more seconds")])
 
 
@@ -568,11 +785,16 @@ 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 +812,7 @@ 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 +825,18 @@ 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
@@ -625,7 +848,7 @@ class processor_text_json_diff_form(commonSettingsForm):
         if not super().validate():
             return False
 
-        from changedetectionio.safe_jinja import render as jinja_render
+        from changedetectionio.jinja2_custom import render as jinja_render
         result = True
 
         # Fail form validation when a body is set for a GET
@@ -688,23 +911,36 @@ class processor_text_json_diff_form(commonSettingsForm):
     ):
         super().__init__(formdata, obj, prefix, data, meta, **kwargs)
         if kwargs and kwargs.get('default_system_settings'):
-            default_tz = kwargs.get('default_system_settings').get('application', {}).get('timezone')
+            default_tz = kwargs.get('default_system_settings').get('application', {}).get('scheduler_timezone_default')
             if default_tz:
                 self.time_schedule_limit.form.timezone.render_kw['placeholder'] = default_tz
 
 
 
 class SingleExtraProxy(Form):
-
     # maybe better to set some <script>var..
     proxy_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
-    proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "socks5:// or regular proxy http://user:pass@...:3128", "size":50})
-    # @todo do the validation here instead
+    proxy_url = StringField('Proxy URL', [
+        validators.Optional(),
+        ValidateStartsWithRegex(
+            regex=r'^(https?|socks5)://',  # ✅ main pattern
+            flags=re.IGNORECASE,  # ✅ makes it case-insensitive
+            message='Proxy URLs must start with http://, https:// or socks5://',
+        ),
+        ValidateSimpleURL()
+    ], render_kw={"placeholder": "socks5:// or regular proxy http://user:pass@...:3128", "size":50})
 
 class SingleExtraBrowser(Form):
     browser_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
-    browser_connection_url = StringField('Browser connection URL', [validators.Optional()], render_kw={"placeholder": "wss://brightdata... wss://oxylabs etc", "size":50})
-    # @todo do the validation here instead
+    browser_connection_url = StringField('Browser connection URL', [
+        validators.Optional(),
+        ValidateStartsWithRegex(
+            regex=r'^(wss?|ws)://',
+            flags=re.IGNORECASE,
+            message='Browser URLs must start with wss:// or ws://'
+        ),
+        ValidateSimpleURL()
+    ], render_kw={"placeholder": "wss://brightdata... wss://oxylabs etc", "size":50})
 
 class DefaultUAInputForm(Form):
     html_requests = StringField('Plaintext requests', validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
@@ -713,9 +949,9 @@ 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')
+    proxy = RadioField('Default 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")])
@@ -724,7 +960,12 @@ class globalSettingsRequestForm(Form):
                           render_kw={"style": "width: 5em;"},
                           validators=[validators.NumberRange(min=1, max=50,
                                                              message="Should be between 1 and 50")])
-    
+
+    timeout = IntegerField('Requests timeout in seconds',
+                           render_kw={"style": "width: 5em;"},
+                           validators=[validators.NumberRange(min=1, max=999,
+                                                              message="Should be between 1 and 999")])
+
     extra_proxies = FieldList(FormField(SingleExtraProxy), min_entries=5)
     extra_browsers = FieldList(FormField(SingleExtraBrowser), min_entries=5)
 
@@ -740,6 +981,8 @@ class globalSettingsRequestForm(Form):
 class globalSettingsApplicationUIForm(Form):
     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):
@@ -764,9 +1007,14 @@ 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()])
+
+    rss_reader_mode = BooleanField('RSS reader mode ', default=False,
+                                      validators=[validators.Optional()])
+
     filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',
                                                                   render_kw={"style": "width: 5em;"},
                                                                   validators=[validators.NumberRange(min=0,
@@ -786,9 +1034,9 @@ 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 +1,6 @@
 from loguru import logger
-from lxml import etree
 from typing import List
+import html
 import json
 import re
 
@@ -9,6 +9,11 @@ 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"]
@@ -52,13 +57,17 @@ def include_filters(include_filters, html_content, append_pretty_line_formatting
 
     return html_block
 
-def subtractive_css_selector(css_selector, html_content):
+def subtractive_css_selector(css_selector, content):
     from bs4 import BeautifulSoup
-    soup = BeautifulSoup(html_content, "html.parser")
+    soup = BeautifulSoup(content, "html.parser")
 
     # So that the elements dont shift their index, build a list of elements here which will be pointers to their place in the DOM
     elements_to_remove = soup.select(css_selector)
 
+    if not elements_to_remove:
+        # Better to return the original that rebuild with BeautifulSoup
+        return content
+
     # Then, remove them in a separate loop
     for item in elements_to_remove:
         item.decompose()
@@ -66,6 +75,7 @@ def subtractive_css_selector(css_selector, html_content):
     return str(soup)
 
 def subtractive_xpath_selector(selectors: List[str], html_content: str) -> str:
+    from lxml import etree
     # Parse the HTML content using lxml
     html_tree = etree.HTML(html_content)
 
@@ -77,6 +87,10 @@ def subtractive_xpath_selector(selectors: List[str], html_content: str) -> str:
         # Collect elements for each selector
         elements_to_remove.extend(html_tree.xpath(selector))
 
+    # If no elements were found, return the original HTML content
+    if not elements_to_remove:
+        return html_content
+
     # Then, remove them in a separate loop
     for element in elements_to_remove:
         if element.getparent() is not None:  # Ensure the element has a parent before removing
@@ -94,7 +108,7 @@ def element_removal(selectors: List[str], html_content):
     xpath_selectors = []
 
     for selector in selectors:
-        if selector.startswith(('xpath:', 'xpath1:', '//')):
+        if selector.strip().startswith(('xpath:', 'xpath1:', '//')):
             # Handle XPath selectors separately
             xpath_selector = selector.removeprefix('xpath:').removeprefix('xpath1:')
             xpath_selectors.append(xpath_selector)
@@ -289,70 +303,92 @@ def _get_stripped_text_from_json_match(match):
 
     return stripped_text_from_html
 
+def extract_json_blob_from_html(content, ensure_is_ldjson_info_type, json_filter):
+    from bs4 import BeautifulSoup
+    stripped_text_from_html = ''
+
+    # Foreach <script json></script> blob.. just return the first that matches json_filter
+    # As a last resort, try to parse the whole <body>
+    soup = BeautifulSoup(content, 'html.parser')
+
+    if ensure_is_ldjson_info_type:
+        bs_result = soup.find_all('script', {"type": "application/ld+json"})
+    else:
+        bs_result = soup.find_all('script')
+    bs_result += soup.find_all('body')
+
+    bs_jsons = []
+
+    for result in bs_result:
+        # result.text is how bs4 magically strips JSON from the body
+        content_start = result.text.lstrip("\ufeff").strip()[:100] if result.text else ''
+        # Skip empty tags, and things that dont even look like JSON
+        if not result.text or not (content_start[0] == '{' or content_start[0] == '['):
+            continue
+        try:
+            json_data = json.loads(result.text)
+            bs_jsons.append(json_data)
+        except json.JSONDecodeError:
+            # Skip objects which cannot be parsed
+            continue
+
+    if not bs_jsons:
+        raise JSONNotFound("No parsable JSON found in this document")
+
+    for json_data in bs_jsons:
+        stripped_text_from_html = _parse_json(json_data, json_filter)
+
+        if ensure_is_ldjson_info_type:
+            # Could sometimes be list, string or something else random
+            if isinstance(json_data, dict):
+                # If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
+                # (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
+                # @type could also be a list although non-standard ("@type": ["Product", "SubType"],)
+                # LD_JSON auto-extract also requires some content PLUS the ldjson to be present
+                # 1833 - could be either str or dict, should not be anything else
+
+                t = json_data.get('@type')
+                if t and stripped_text_from_html:
+
+                    if isinstance(t, str) and t.lower() == ensure_is_ldjson_info_type.lower():
+                        break
+                    # The non-standard part, some have a list
+                    elif isinstance(t, list):
+                        if ensure_is_ldjson_info_type.lower() in [x.lower().strip() for x in t]:
+                            break
+
+        elif stripped_text_from_html:
+            break
+
+    return stripped_text_from_html
+
 # content - json
 # json_filter - ie json:$..price
 # ensure_is_ldjson_info_type - str "product", optional, "@type == product" (I dont know how to do that as a json selector)
 def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None):
-    from bs4 import BeautifulSoup
 
     stripped_text_from_html = False
 # https://github.com/dgtlmoon/changedetection.io/pull/2041#issuecomment-1848397161w
     # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded within HTML tags
-    try:
-        # .lstrip("\ufeff") strings ByteOrderMark from UTF8 and still lets the UTF work
-        stripped_text_from_html = _parse_json(json.loads(content.lstrip("\ufeff") ), json_filter)
-    except json.JSONDecodeError as e:
-        logger.warning(str(e))
 
-        # Foreach <script json></script> blob.. just return the first that matches json_filter
-        # As a last resort, try to parse the whole <body>
-        soup = BeautifulSoup(content, 'html.parser')
+    # Looks like clean JSON, dont bother extracting from HTML
 
-        if ensure_is_ldjson_info_type:
-            bs_result = soup.find_all('script', {"type": "application/ld+json"})
-        else:
-            bs_result = soup.find_all('script')
-        bs_result += soup.find_all('body')
+    content_start = content.lstrip("\ufeff").strip()[:100]
 
-        bs_jsons = []
-        for result in bs_result:
-            # Skip empty tags, and things that dont even look like JSON
-            if not result.text or '{' not in result.text:
-                continue
-            try:
-                json_data = json.loads(result.text)
-                bs_jsons.append(json_data)
-            except json.JSONDecodeError:
-                # Skip objects which cannot be parsed
-                continue
-
-        if not bs_jsons:
-            raise JSONNotFound("No parsable JSON found in this document")
-        
-        for json_data in bs_jsons:
-            stripped_text_from_html = _parse_json(json_data, json_filter)
-
-            if ensure_is_ldjson_info_type:
-                # Could sometimes be list, string or something else random
-                if isinstance(json_data, dict):
-                    # If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
-                    # (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
-                    # @type could also be a list although non-standard ("@type": ["Product", "SubType"],)
-                    # LD_JSON auto-extract also requires some content PLUS the ldjson to be present
-                    # 1833 - could be either str or dict, should not be anything else
-
-                    t = json_data.get('@type')
-                    if t and stripped_text_from_html:
-
-                        if isinstance(t, str) and t.lower() == ensure_is_ldjson_info_type.lower():
-                            break
-                        # The non-standard part, some have a list
-                        elif isinstance(t, list):
-                            if ensure_is_ldjson_info_type.lower() in [x.lower().strip() for x in t]:
-                                break
-
-            elif stripped_text_from_html:
-                break
+    if content_start[0] == '{' or content_start[0] == '[':
+        try:
+            # .lstrip("\ufeff") strings ByteOrderMark from UTF8 and still lets the UTF work
+            stripped_text_from_html = _parse_json(json.loads(content.lstrip("\ufeff")), json_filter)
+        except json.JSONDecodeError as e:
+            logger.warning(f"Error processing JSON {content[:20]}...{str(e)})")
+    else:
+        # Probably something else, go fish inside for it
+        try:
+            stripped_text_from_html = extract_json_blob_from_html(content=content,
+                                                                  ensure_is_ldjson_info_type=ensure_is_ldjson_info_type,
+                                                                  json_filter=json_filter                                                                  )
+        except json.JSONDecodeError as e:
+            logger.warning(f"Error processing JSON while extracting JSON from HTML blob {content[:20]}...{str(e)})")
 
     if not stripped_text_from_html:
         # Re 265 - Just return an empty string when filter not found
@@ -372,6 +408,9 @@ def strip_ignore_text(content, wordlist, mode="content"):
     ignored_lines = []
 
     for k in wordlist:
+        # Skip empty strings to avoid matching everything
+        if not k or not k.strip():
+            continue
         # Is it a regex?
         res = re.search(PERL_STYLE_REGEX, k, re.IGNORECASE)
         if res:
@@ -510,3 +549,43 @@ 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/jinja2_custom/__init__.py

@@ -0,0 +1,20 @@
+"""
+Jinja2 custom extensions and safe rendering utilities.
+"""
+from .extensions.TimeExtension import TimeExtension
+from .safe_jinja import (
+    render,
+    render_fully_escaped,
+    create_jinja_env,
+    JINJA2_MAX_RETURN_PAYLOAD_SIZE,
+    DEFAULT_JINJA2_EXTENSIONS,
+)
+
+__all__ = [
+    'TimeExtension',
+    'render',
+    'render_fully_escaped',
+    'create_jinja_env',
+    'JINJA2_MAX_RETURN_PAYLOAD_SIZE',
+    'DEFAULT_JINJA2_EXTENSIONS',
+]

changedetectionio/jinja2_custom/extensions/TimeExtension.py

@@ -0,0 +1,221 @@
+"""
+Jinja2 TimeExtension - Custom date/time handling for templates.
+
+This extension provides the {% now %} tag for Jinja2 templates, offering timezone-aware
+date/time formatting with support for time offsets.
+
+Why This Extension Exists:
+    The Arrow library has a now() function (arrow.now()), but Jinja2 templates cannot
+    directly call Python functions - they need extensions or filters to expose functionality.
+
+    This TimeExtension serves as a Jinja2-to-Arrow bridge that:
+
+    1. Makes Arrow accessible in templates - Jinja2 requires registering functions/tags
+       through extensions. You cannot use arrow.now() directly in a template.
+
+    2. Provides template-friendly syntax - Instead of complex Python code, you get clean tags:
+       {% now 'UTC' %}
+       {% now 'UTC' + 'hours=2' %}
+       {% now 'Europe/London', '%Y-%m-%d' %}
+
+    3. Adds convenience features on top of Arrow:
+       - Default timezone from environment variable (TZ) or config
+       - Default datetime format configuration
+       - Offset syntax parsing: 'hours=2,minutes=30' → shift(hours=2, minutes=30)
+       - Empty string timezone support to use configured defaults
+
+    4. Maintains security - Works within Jinja2's sandboxed environment so users
+       cannot access arbitrary Python code or objects.
+
+    Essentially, this is a Jinja2 wrapper around arrow.now() and arrow.shift() that
+    provides user-friendly template syntax while maintaining security.
+
+Basic Usage:
+    {% now 'UTC' %}
+    # Output: Wed, 09 Dec 2015 23:33:01
+
+Custom Format:
+    {% now 'UTC', '%Y-%m-%d %H:%M:%S' %}
+    # Output: 2015-12-09 23:33:01
+
+Timezone Support:
+    {% now 'America/New_York' %}
+    {% now 'Europe/London' %}
+    {% now '' %}  # Uses default timezone from environment.default_timezone
+
+Time Offsets (Addition):
+    {% now 'UTC' + 'hours=2' %}
+    {% now 'UTC' + 'hours=2,minutes=30' %}
+    {% now 'UTC' + 'days=1,hours=2,minutes=15,seconds=10' %}
+
+Time Offsets (Subtraction):
+    {% now 'UTC' - 'minutes=11' %}
+    {% now 'UTC' - 'days=2,minutes=33,seconds=1' %}
+
+Time Offsets with Custom Format:
+    {% now 'UTC' + 'hours=2', '%Y-%m-%d %H:%M:%S' %}
+    # Output: 2015-12-10 01:33:01
+
+Weekday Support (for finding next/previous weekday):
+    {% now 'UTC' + 'weekday=0' %}  # Next Monday (0=Monday, 6=Sunday)
+    {% now 'UTC' + 'weekday=4' %}  # Next Friday
+
+Configuration:
+    - Default timezone: Set via TZ environment variable or override environment.default_timezone
+    - Default format: '%a, %d %b %Y %H:%M:%S' (can be overridden via environment.datetime_format)
+
+Environment Customization:
+    from changedetectionio.jinja2_custom import create_jinja_env
+
+    jinja2_env = create_jinja_env()
+    jinja2_env.default_timezone = 'America/New_York'  # Override default timezone
+    jinja2_env.datetime_format = '%Y-%m-%d %H:%M'      # Override default format
+
+Supported Offset Parameters:
+    - years, months, weeks, days
+    - hours, minutes, seconds, microseconds
+    - weekday (0=Monday through 6=Sunday, must be integer)
+
+Note:
+    This extension uses the Arrow library for timezone-aware datetime handling.
+    All timezone names should be valid IANA timezone identifiers (e.g., 'America/New_York').
+"""
+import arrow
+
+from jinja2 import nodes
+from jinja2.ext import Extension
+import os
+
+class TimeExtension(Extension):
+    """
+    Jinja2 Extension providing the {% now %} tag for timezone-aware date/time rendering.
+
+    This extension adds two attributes to the Jinja2 environment:
+    - datetime_format: Default strftime format string (default: '%a, %d %b %Y %H:%M:%S')
+    - default_timezone: Default timezone for rendering (default: TZ env var or 'UTC')
+
+    Both can be overridden after environment creation by setting the attributes directly.
+    """
+
+    tags = {'now'}
+
+    def __init__(self, environment):
+        """Jinja2 Extension constructor."""
+        super().__init__(environment)
+
+        environment.extend(
+            datetime_format='%a, %d %b %Y %H:%M:%S',
+            default_timezone=os.getenv('TZ', 'UTC').strip()
+        )
+
+    def _datetime(self, timezone, operator, offset, datetime_format):
+        """
+        Get current datetime with time offset applied.
+
+        Args:
+            timezone: IANA timezone identifier (e.g., 'UTC', 'America/New_York') or empty string for default
+            operator: '+' for addition or '-' for subtraction
+            offset: Comma-separated offset parameters (e.g., 'hours=2,minutes=30')
+            datetime_format: strftime format string or None to use environment default
+
+        Returns:
+            Formatted datetime string with offset applied
+
+        Example:
+            _datetime('UTC', '+', 'hours=2,minutes=30', '%Y-%m-%d %H:%M:%S')
+            # Returns current time + 2.5 hours
+        """
+        # Use default timezone if none specified
+        if not timezone or timezone == '':
+            timezone = self.environment.default_timezone
+
+        d = arrow.now(timezone)
+
+        # parse shift params from offset and include operator
+        shift_params = {}
+        for param in offset.split(','):
+            interval, value = param.split('=')
+            shift_params[interval.strip()] = float(operator + value.strip())
+
+        # Fix weekday parameter can not be float
+        if 'weekday' in shift_params:
+            shift_params['weekday'] = int(shift_params['weekday'])
+
+        d = d.shift(**shift_params)
+
+        if datetime_format is None:
+            datetime_format = self.environment.datetime_format
+        return d.strftime(datetime_format)
+
+    def _now(self, timezone, datetime_format):
+        """
+        Get current datetime without any offset.
+
+        Args:
+            timezone: IANA timezone identifier (e.g., 'UTC', 'America/New_York') or empty string for default
+            datetime_format: strftime format string or None to use environment default
+
+        Returns:
+            Formatted datetime string for current time
+
+        Example:
+            _now('America/New_York', '%Y-%m-%d %H:%M:%S')
+            # Returns current time in New York timezone
+        """
+        # Use default timezone if none specified
+        if not timezone or timezone == '':
+            timezone = self.environment.default_timezone
+
+        if datetime_format is None:
+            datetime_format = self.environment.datetime_format
+        return arrow.now(timezone).strftime(datetime_format)
+
+    def parse(self, parser):
+        """
+        Parse the {% now %} tag and generate appropriate AST nodes.
+
+        This method is called by Jinja2 when it encounters a {% now %} tag.
+        It parses the tag syntax and determines whether to call _now() or _datetime()
+        based on whether offset operations (+ or -) are present.
+
+        Supported syntax:
+            {% now 'timezone' %}                              -> calls _now()
+            {% now 'timezone', 'format' %}                    -> calls _now()
+            {% now 'timezone' + 'offset' %}                   -> calls _datetime()
+            {% now 'timezone' + 'offset', 'format' %}         -> calls _datetime()
+            {% now 'timezone' - 'offset', 'format' %}         -> calls _datetime()
+
+        Args:
+            parser: Jinja2 parser instance
+
+        Returns:
+            nodes.Output: AST output node containing the formatted datetime string
+        """
+        lineno = next(parser.stream).lineno
+
+        node = parser.parse_expression()
+
+        if parser.stream.skip_if('comma'):
+            datetime_format = parser.parse_expression()
+        else:
+            datetime_format = nodes.Const(None)
+
+        if isinstance(node, nodes.Add):
+            call_method = self.call_method(
+                '_datetime',
+                [node.left, nodes.Const('+'), node.right, datetime_format],
+                lineno=lineno,
+            )
+        elif isinstance(node, nodes.Sub):
+            call_method = self.call_method(
+                '_datetime',
+                [node.left, nodes.Const('-'), node.right, datetime_format],
+                lineno=lineno,
+            )
+        else:
+            call_method = self.call_method(
+                '_now',
+                [node, datetime_format],
+                lineno=lineno,
+            )
+        return nodes.Output([call_method], lineno=lineno)

changedetectionio/jinja2_custom/safe_jinja.py

@@ -0,0 +1,55 @@
+"""
+Safe Jinja2 render with max payload sizes
+
+See https://jinja.palletsprojects.com/en/3.1.x/sandbox/#security-considerations
+"""
+
+import jinja2.sandbox
+import typing as t
+import os
+from .extensions.TimeExtension import TimeExtension
+
+JINJA2_MAX_RETURN_PAYLOAD_SIZE = 1024 * int(os.getenv("JINJA2_MAX_RETURN_PAYLOAD_SIZE_KB", 1024 * 10))
+
+# Default extensions - can be overridden in create_jinja_env()
+DEFAULT_JINJA2_EXTENSIONS = [TimeExtension]
+
+
+def create_jinja_env(extensions=None, **kwargs) -> jinja2.sandbox.ImmutableSandboxedEnvironment:
+    """
+    Create a sandboxed Jinja2 environment with our custom extensions and default timezone.
+
+    Args:
+        extensions: List of extension classes to use (defaults to DEFAULT_JINJA2_EXTENSIONS)
+        **kwargs: Additional arguments to pass to ImmutableSandboxedEnvironment
+
+    Returns:
+        Configured Jinja2 environment
+    """
+    if extensions is None:
+        extensions = DEFAULT_JINJA2_EXTENSIONS
+
+    jinja2_env = jinja2.sandbox.ImmutableSandboxedEnvironment(
+        extensions=extensions,
+        **kwargs
+    )
+
+    # Get default timezone from environment variable
+    default_timezone = os.getenv('TZ', 'UTC').strip()
+    jinja2_env.default_timezone = default_timezone
+
+    return jinja2_env
+
+
+# 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 = create_jinja_env()
+    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/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,
@@ -55,14 +55,18 @@ class model(dict):
                     'rss_access_token': None,
                     'rss_content_format': RSS_FORMAT_TYPES[0][0],
                     'rss_hide_muted_watches': True,
+                    'rss_reader_mode': False,
+                    'scheduler_timezone_default': None,  # Default IANA timezone name
                     '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
+                        'socket_io_enabled': True,
+                        'favicons_enabled': True
                     },
                 }
             }

changedetectionio/model/Watch.py

@@ -1,18 +1,21 @@
 from blinker import signal
 
 from changedetectionio.strtobool import strtobool
-from changedetectionio.safe_jinja import render as jinja_render
+from changedetectionio.jinja2_custom import render as jinja_render
 from . import watch_base
 import os
 import re
 from pathlib import Path
 from loguru import logger
 
+from .. import jinja2_custom as 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}
@@ -86,9 +89,8 @@ class model(watch_base):
                 ready_url = jinja_render(template_str=url)
             except Exception as e:
                 logger.critical(f"Invalid URL template for: '{url}' - {str(e)}")
-                from flask import (
-                    flash, Markup, url_for
-                )
+                from flask import flash, url_for
+                from markupsafe import Markup
                 message = Markup('<a href="{}#general">The URL {} is invalid and cannot be used, click to edit</a>'.format(
                     url_for('ui.ui_edit.edit_page', uuid=self.get('uuid')), self.get('url', '')))
                 flash(message, 'error')
@@ -102,6 +104,13 @@ 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 +168,8 @@ 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 +421,154 @@ 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 +662,7 @@ 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']
@@ -691,11 +848,11 @@ 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/__init__.py

@@ -1,6 +1,5 @@
 from changedetectionio.model import default_notification_format_for_watch
 
-ult_notification_format_for_watch = 'System default'
 default_notification_format = 'HTML Color'
 default_notification_body = '{{watch_url}} had a change.\n---\n{{diff}}\n---\n'
 default_notification_title = 'ChangeDetection.io Notification - {{watch_url}}'
@@ -8,28 +7,11 @@ default_notification_title = 'ChangeDetection.io Notification - {{watch_url}}'
 # The values (markdown etc) are from apprise NotifyFormat,
 # But to avoid importing the whole heavy module just use the same strings here.
 valid_notification_formats = {
-    'Text': 'text',
-    'Markdown': 'markdown',
+    'Plain Text': 'text',
     'HTML': 'html',
     'HTML Color': 'htmlcolor',
+    'Markdown to HTML': 'markdown',
     # Used only for editing a watch (not for global)
     default_notification_format_for_watch: default_notification_format_for_watch
 }
 
-
-valid_tokens = {
-    'base_url': '',
-    'current_snapshot': '',
-    'diff': '',
-    'diff_added': '',
-    'diff_full': '',
-    'diff_patch': '',
-    'diff_removed': '',
-    'diff_url': '',
-    'preview_url': '',
-    'triggered_text': '',
-    'watch_tag': '',
-    'watch_title': '',
-    'watch_url': '',
-    'watch_uuid': '',
-}

changedetectionio/notification/apprise_plugin/custom_handlers.py

@@ -70,6 +70,7 @@ def apprise_http_custom_handler(
     title: str,
     notify_type: str,
     meta: dict,
+    body_format: str = None,
     *args,
     **kwargs,
 ) -> bool:

changedetectionio/notification/handler.py

@@ -1,33 +1,163 @@
 
 import time
 import apprise
+from apprise import NotifyFormat
 from loguru import logger
+from urllib.parse import urlparse
 from .apprise_plugin.assets import apprise_asset, APPRISE_AVATAR_URL
+from .apprise_plugin.custom_handlers import SUPPORTED_HTTP_METHODS
+from ..notification_service import NotificationContextData
 
-def process_notification(n_object, datastore):
-    from changedetectionio.safe_jinja import render as jinja_render
+
+def markup_text_links_to_html(body):
+    """
+    Convert plaintext to HTML with clickable links.
+    Uses Jinja2's escape and Markup for XSS safety.
+    """
+    from linkify_it import LinkifyIt
+    from markupsafe import Markup, escape
+
+    linkify = LinkifyIt()
+
+    # Match URLs in the ORIGINAL text (before escaping)
+    matches = linkify.match(body)
+
+    if not matches:
+        # No URLs, just escape everything
+        return Markup(escape(body))
+
+    result = []
+    last_index = 0
+
+    # Process each URL match
+    for match in matches:
+        # Add escaped text before the URL
+        if match.index > last_index:
+            text_part = body[last_index:match.index]
+            result.append(escape(text_part))
+
+        # Add the link with escaped URL (both in href and display)
+        url = match.url
+        result.append(Markup(f'<a href="{escape(url)}">{escape(url)}</a>'))
+
+        last_index = match.last_index
+
+    # Add remaining escaped text
+    if last_index < len(body):
+        result.append(escape(body[last_index:]))
+
+    # Join all parts
+    return str(Markup(''.join(str(part) for part in result)))
+
+def notification_format_align_with_apprise(n_format : str):
+    """
+    Correctly align changedetection's formats with apprise's formats
+    Probably these are the same - but good to be sure.
+    These set the expected OUTPUT format type
+    :param n_format:
+    :return:
+    """
+
+    if n_format.lower().startswith('html'):
+        # Apprise only knows 'html' not 'htmlcolor' etc, which shouldnt matter here
+        n_format = NotifyFormat.HTML.value
+    elif n_format.lower().startswith('markdown'):
+        # probably the same but just to be safe
+        n_format = NotifyFormat.MARKDOWN.value
+    elif n_format.lower().startswith('text'):
+        # probably the same but just to be safe
+        n_format = NotifyFormat.TEXT.value
+    else:
+        n_format = NotifyFormat.TEXT.value
+
+    return n_format
+
+
+def apply_service_tweaks(url, n_body, n_title):
+    # Re 323 - Limit discord length to their 2000 char limit total or it wont send.
+    # Because different notifications may require different pre-processing, run each sequentially :(
+    # 2000 bytes minus -
+    #     200 bytes for the overhead of the _entire_ json payload, 200 bytes for {tts, wait, content} etc headers
+    #     Length of URL - Incase they specify a longer custom avatar_url
+
+    # So if no avatar_url is specified, add one so it can be correctly calculated into the total payload
+    parsed = urlparse(url)
+    k = '?' if not parsed.query else '&'
+    if not 'avatar_url' in url \
+            and not url.startswith('mail') \
+            and not url.startswith('post') \
+            and not url.startswith('get') \
+            and not url.startswith('delete') \
+            and not url.startswith('put'):
+        url += k + f"avatar_url={APPRISE_AVATAR_URL}"
+
+    if url.startswith('tgram://'):
+        # Telegram only supports a limit subset of HTML, remove the '<br>' we place in.
+        # re https://github.com/dgtlmoon/changedetection.io/issues/555
+        # @todo re-use an existing library we have already imported to strip all non-allowed tags
+        n_body = n_body.replace('<br>', '\n')
+        n_body = n_body.replace('</br>', '\n')
+        # real limit is 4096, but minus some for extra metadata
+        payload_max_size = 3600
+        body_limit = max(0, payload_max_size - len(n_title))
+        n_title = n_title[0:payload_max_size]
+        n_body = n_body[0:body_limit]
+
+    elif url.startswith('discord://') or url.startswith('https://discordapp.com/api/webhooks') or url.startswith(
+            'https://discord.com/api'):
+        # real limit is 2000, but minus some for extra metadata
+        payload_max_size = 1700
+        body_limit = max(0, payload_max_size - len(n_title))
+        n_title = n_title[0:payload_max_size]
+        n_body = n_body[0:body_limit]
+
+    return url, n_body, n_title
+
+
+def process_notification(n_object: NotificationContextData, datastore):
+    from changedetectionio.jinja2_custom import render as jinja_render
     from . import default_notification_format_for_watch, default_notification_format, valid_notification_formats
     # be sure its registered
     from .apprise_plugin.custom_handlers import apprise_http_custom_handler
 
+    # Create list of custom handler protocols (both http and https versions)
+    custom_handler_protocols = [f"{method}://" for method in SUPPORTED_HTTP_METHODS]
+    custom_handler_protocols += [f"{method}s://" for method in SUPPORTED_HTTP_METHODS]
+
+    has_custom_handler = any(
+        url.startswith(tuple(custom_handler_protocols))
+        for url in n_object['notification_urls']
+    )
+
+    if not isinstance(n_object, NotificationContextData):
+        raise TypeError(f"Expected NotificationContextData, got {type(n_object)}")
+
     now = time.time()
     if n_object.get('notification_timestamp'):
         logger.trace(f"Time since queued {now-n_object['notification_timestamp']:.3f}s")
+
     # Insert variables into the notification content
     notification_parameters = create_notification_parameters(n_object, datastore)
 
-    n_format = valid_notification_formats.get(
+    requested_output_format = valid_notification_formats.get(
         n_object.get('notification_format', default_notification_format),
         valid_notification_formats[default_notification_format],
     )
 
     # If we arrived with 'System default' then look it up
-    if n_format == default_notification_format_for_watch and datastore.data['settings']['application'].get('notification_format') != default_notification_format_for_watch:
+    if requested_output_format == default_notification_format_for_watch and datastore.data['settings']['application'].get('notification_format') != default_notification_format_for_watch:
         # Initially text or whatever
-        n_format = datastore.data['settings']['application'].get('notification_format', valid_notification_formats[default_notification_format])
+        requested_output_format = datastore.data['settings']['application'].get('notification_format', valid_notification_formats[default_notification_format]).lower()
+
+    requested_output_format = notification_format_align_with_apprise(n_format=requested_output_format)
 
     logger.trace(f"Complete notification body including Jinja and placeholders calculated in  {time.time() - now:.2f}s")
 
+    # If we have custom handlers, use invalid format to prevent conversion
+    # Otherwise use the proper format
+    if has_custom_handler:
+        input_format = 'raw-no-convert'
+
     # https://github.com/caronc/apprise/wiki/Development_LogCapture
     # Anything higher than or equal to WARNING (which covers things like Connection errors)
     # raise it as an exception
@@ -44,11 +174,41 @@ def process_notification(n_object, datastore):
 
     with apprise.LogCapture(level=apprise.logging.DEBUG) as logs:
         for url in n_object['notification_urls']:
+            parsed_url = urlparse(url)
+            prefix_add_to_url = '?' if not parsed_url.query else '&'
 
             # Get the notification body from datastore
             n_body = jinja_render(template_str=n_object.get('notification_body', ''), **notification_parameters)
-            if n_object.get('notification_format', '').startswith('HTML'):
+
+            if n_object.get('markup_text_to_html'):
+                n_body = markup_text_links_to_html(body=n_body)
+
+            # This actually means we request "Markdown to HTML"
+            if requested_output_format == NotifyFormat.MARKDOWN.value:
+                output_format = NotifyFormat.HTML.value
+                input_format = NotifyFormat.MARKDOWN.value
+                if not 'format=' in url.lower():
+                    url = f"{url}{prefix_add_to_url}format={output_format}"
+
+            # Deviation from apprise.
+            # No conversion, its like they want to send raw HTML but we add linebreaks
+            elif requested_output_format == NotifyFormat.HTML.value:
+                # same in and out means apprise wont try to convert
+                input_format = output_format = NotifyFormat.HTML.value
                 n_body = n_body.replace("\n", '<br>')
+                if not 'format=' in url.lower():
+                    url = f"{url}{prefix_add_to_url}format={output_format}"
+
+            else:
+                # Nothing to be done, leave it as plaintext
+                # `body_format` Tell apprise what format the INPUT is in
+                # &format= in URL Tell apprise what format the OUTPUT should be in (it can convert between)
+                input_format = output_format = NotifyFormat.TEXT.value
+                if not 'format=' in url.lower():
+                    url = f"{url}{prefix_add_to_url}format={output_format}"
+
+            if has_custom_handler:
+                input_format='raw-no-convert'
 
             n_title = jinja_render(template_str=n_object.get('notification_title', ''), **notification_parameters)
 
@@ -64,74 +224,28 @@ def process_notification(n_object, datastore):
             logger.info(f">> Process Notification: AppRise notifying {url}")
             url = jinja_render(template_str=url, **notification_parameters)
 
-            # Re 323 - Limit discord length to their 2000 char limit total or it wont send.
-            # Because different notifications may require different pre-processing, run each sequentially :(
-            # 2000 bytes minus -
-            #     200 bytes for the overhead of the _entire_ json payload, 200 bytes for {tts, wait, content} etc headers
-            #     Length of URL - Incase they specify a longer custom avatar_url
-
-            # So if no avatar_url is specified, add one so it can be correctly calculated into the total payload
-            k = '?' if not '?' in url else '&'
-            if not 'avatar_url' in url \
-                    and not url.startswith('mail') \
-                    and not url.startswith('post') \
-                    and not url.startswith('get') \
-                    and not url.startswith('delete') \
-                    and not url.startswith('put'):
-                url += k + f"avatar_url={APPRISE_AVATAR_URL}"
-
-            if url.startswith('tgram://'):
-                # Telegram only supports a limit subset of HTML, remove the '<br>' we place in.
-                # re https://github.com/dgtlmoon/changedetection.io/issues/555
-                # @todo re-use an existing library we have already imported to strip all non-allowed tags
-                n_body = n_body.replace('<br>', '\n')
-                n_body = n_body.replace('</br>', '\n')
-                # real limit is 4096, but minus some for extra metadata
-                payload_max_size = 3600
-                body_limit = max(0, payload_max_size - len(n_title))
-                n_title = n_title[0:payload_max_size]
-                n_body = n_body[0:body_limit]
-
-            elif url.startswith('discord://') or url.startswith('https://discordapp.com/api/webhooks') or url.startswith(
-                    'https://discord.com/api'):
-                # real limit is 2000, but minus some for extra metadata
-                payload_max_size = 1700
-                body_limit = max(0, payload_max_size - len(n_title))
-                n_title = n_title[0:payload_max_size]
-                n_body = n_body[0:body_limit]
-
-            elif url.startswith('mailto'):
-                # Apprise will default to HTML, so we need to override it
-                # So that whats' generated in n_body is in line with what is going to be sent.
-                # https://github.com/caronc/apprise/issues/633#issuecomment-1191449321
-                if not 'format=' in url and (n_format == 'Text' or n_format == 'Markdown'):
-                    prefix = '?' if not '?' in url else '&'
-                    # Apprise format is lowercase text https://github.com/caronc/apprise/issues/633
-                    n_format = n_format.lower()
-                    url = f"{url}{prefix}format={n_format}"
-                # If n_format == HTML, then apprise email should default to text/html and we should be sending HTML only
+            (url, n_body, n_title) = apply_service_tweaks(url=url, n_body=n_body, n_title=n_title)
 
             apobj.add(url)
 
             sent_objs.append({'title': n_title,
                               'body': n_body,
-                              'url': url,
-                              'body_format': n_format})
+                              'url': url})
 
-        # Blast off the notifications tht are set in .add()
         apobj.notify(
             title=n_title,
             body=n_body,
-            body_format=n_format,
+            # `body_format` Tell apprise what format the INPUT is in
+            # &format= in URL Tell apprise what format the OUTPUT should be in (it can convert between)
+            body_format=input_format,
             # False is not an option for AppRise, must be type None
             attach=n_object.get('screenshot', None)
         )
 
-
         # Returns empty string if nothing found, multi-line string otherwise
         log_value = logs.getvalue()
 
-        if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
+        if log_value and ('WARNING' in log_value or 'ERROR' in log_value):
             logger.critical(log_value)
             raise Exception(log_value)
 
@@ -141,17 +255,15 @@ def process_notification(n_object, datastore):
 
 # Notification title + body content parameters get created here.
 # ( Where we prepare the tokens in the notification to be replaced with actual values )
-def create_notification_parameters(n_object, datastore):
-    from copy import deepcopy
-    from . import valid_tokens
+def create_notification_parameters(n_object: NotificationContextData, datastore):
+    if not isinstance(n_object, NotificationContextData):
+        raise TypeError(f"Expected NotificationContextData, got {type(n_object)}")
 
-    # in the case we send a test notification from the main settings, there is no UUID.
-    uuid = n_object['uuid'] if 'uuid' in n_object else ''
-
-    if uuid:
-        watch_title = datastore.data['watching'][uuid].get('title', '')
+    watch = datastore.data['watching'].get(n_object['uuid'])
+    if watch:
+        watch_title = datastore.data['watching'][n_object['uuid']].label
         tag_list = []
-        tags = datastore.get_all_tags_for_watch(uuid)
+        tags = datastore.get_all_tags_for_watch(n_object['uuid'])
         if tags:
             for tag_uuid, tag in tags.items():
                 tag_list.append(tag.get('title'))
@@ -166,14 +278,10 @@ def create_notification_parameters(n_object, datastore):
 
     watch_url = n_object['watch_url']
 
-    diff_url = "{}/diff/{}".format(base_url, uuid)
-    preview_url = "{}/preview/{}".format(base_url, uuid)
+    diff_url = "{}/diff/{}".format(base_url, n_object['uuid'])
+    preview_url = "{}/preview/{}".format(base_url, n_object['uuid'])
 
-    # Not sure deepcopy is needed here, but why not
-    tokens = deepcopy(valid_tokens)
-
-    # Valid_tokens also used as a field validator
-    tokens.update(
+    n_object.update(
         {
             'base_url': base_url,
             'diff_url': diff_url,
@@ -181,13 +289,10 @@ def create_notification_parameters(n_object, datastore):
             'watch_tag': watch_tag if watch_tag is not None else '',
             'watch_title': watch_title if watch_title is not None else '',
             'watch_url': watch_url,
-            'watch_uuid': uuid,
+            'watch_uuid': n_object['uuid'],
         })
 
-    # n_object will contain diff, diff_added etc etc
-    tokens.update(n_object)
+    if watch:
+        n_object.update(datastore.data['watching'].get(n_object['uuid']).extra_notification_token_values())
 
-    if uuid:
-        tokens.update(datastore.data['watching'].get(uuid).extra_notification_token_values())
-
-    return tokens
+    return n_object

changedetectionio/notification_service.py

@@ -6,9 +6,51 @@ Extracted from update_worker.py to provide standalone notification functionality
 for both sync and async workers
 """
 
-import time
 from loguru import logger
+import time
 
+from changedetectionio.notification import default_notification_format
+
+# What is passed around as notification context, also used as the complete list of valid {{ tokens }}
+class NotificationContextData(dict):
+    def __init__(self, initial_data=None, **kwargs):
+        super().__init__({
+            'current_snapshot': None,
+            'diff': None,
+            'diff_added': None,
+            'diff_full': None,
+            'diff_patch': None,
+            'diff_removed': None,
+            'notification_timestamp': time.time(),
+            'screenshot': None,
+            'triggered_text': None,
+            'uuid': 'XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX',  # Converted to 'watch_uuid' in create_notification_parameters
+            'watch_url': 'https://WATCH-PLACE-HOLDER/',
+            'base_url': None,
+            'diff_url': None,
+            'preview_url': None,
+            'watch_tag': None,
+            'watch_title': None,
+            'markup_text_to_html': False, # If automatic conversion of plaintext to HTML should happen
+        })
+
+        # Apply any initial data passed in
+        self.update({'watch_uuid': self.get('uuid')})
+        if initial_data:
+            self.update(initial_data)
+
+        # Apply any keyword arguments
+        if kwargs:
+            self.update(kwargs)
+
+    def set_random_for_validation(self):
+        import random, string
+        """Randomly fills all dict keys with random strings (for validation/testing)."""
+        for key in self.keys():
+            if key in ['uuid', 'time', 'watch_uuid']:
+                continue
+            rand_str = 'RANDOM-PLACEHOLDER-'+''.join(random.choices(string.ascii_letters + string.digits, k=12))
+            self[key] = rand_str
 
 class NotificationService:
     """
@@ -20,13 +62,16 @@ class NotificationService:
         self.datastore = datastore
         self.notification_q = notification_q
     
-    def queue_notification_for_watch(self, n_object, watch):
+    def queue_notification_for_watch(self, n_object: NotificationContextData, 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
 
+        if not isinstance(n_object, NotificationContextData):
+            raise TypeError(f"Expected NotificationContextData, got {type(n_object)}")
+
         dates = []
         trigger_text = ''
 
@@ -79,15 +124,15 @@ class NotificationService:
         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_added': diff.render_diff(prev_snapshot, current_snapshot, include_removed=False, line_feed_sep=line_feed_sep, html_colour=html_colour_enable),
             '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,
+            'diff_removed': diff.render_diff(prev_snapshot, current_snapshot, include_added=False, line_feed_sep=line_feed_sep, html_colour=html_colour_enable),
             '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,
+            'watch_uuid': watch.get('uuid') if watch else None,
         })
 
         if watch:
@@ -140,7 +185,7 @@ class NotificationService:
         """
         Send notification when content changes are detected
         """
-        n_object = {}
+        n_object = NotificationContextData()
         watch = self.datastore.data['watching'].get(watch_uuid)
         if not watch:
             return
@@ -183,11 +228,26 @@ class NotificationService:
         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'}
+        n_format = self.datastore.data['settings']['application'].get('notification_format', default_notification_format)
+        filter_list = ", ".join(watch['include_filters'])
+        # @todo - This could be a markdown template on the disk, apprise will convert the markdown to HTML+Plaintext parts in the email, and then 'markup_text_to_html' is not needed
+        body = f"""Hello,
+
+Your configured CSS/xPath filters of '{filter_list}' for {{{{watch_url}}}} did not appear on the page after {threshold} attempts.
+
+It's possible the page changed layout and the filter needs updating ( Try the 'Visual Selector' tab )
+
+Edit link: {{{{base_url}}}}/edit/{{{{watch_uuid}}}}
+
+Thanks - Your omniscient changedetection.io installation.
+"""
+
+        n_object = NotificationContextData({
+            'notification_title': 'Changedetection.io - Alert - CSS/xPath filter was not present in the page',
+            'notification_body': body,
+            'notification_format': n_format,
+            'markup_text_to_html': n_format.lower().startswith('html')
+        })
 
         if len(watch['notification_urls']):
             n_object['notification_urls'] = watch['notification_urls']
@@ -215,12 +275,28 @@ class NotificationService:
         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'}
+        n_format = self.datastore.data['settings']['application'].get('notification_format', default_notification_format).lower()
+        step = step_n + 1
+        # @todo - This could be a markdown template on the disk, apprise will convert the markdown to HTML+Plaintext parts in the email, and then 'markup_text_to_html' is not needed
+
+        # {{{{ }}}} because this will be Jinja2 {{ }} tokens
+        body = f"""Hello,
+        
+Your configured browser step at position {step} for the web page watch {{{{watch_url}}}} did not appear on the page after {threshold} attempts, did the page change layout?
+
+The element may have moved and needs editing, or does it need a delay added?
+
+Edit link: {{{{base_url}}}}/edit/{{{{watch_uuid}}}}
+
+Thanks - Your omniscient changedetection.io installation.
+"""
+
+        n_object = NotificationContextData({
+            'notification_title': f"Changedetection.io - Alert - Browser step at position {step} could not be run",
+            'notification_body': body,
+            'notification_format': n_format,
+            'markup_text_to_html': n_format.lower().startswith('html')
+        })
 
         if len(watch['notification_urls']):
             n_object['notification_urls'] = watch['notification_urls']

changedetectionio/processors/__init__.py

@@ -102,7 +102,7 @@ class difference_detection_processor():
             self.fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, self.watch.get('uuid'))
 
         # Tweak the base config with the per-watch ones
-        from changedetectionio.safe_jinja import render as jinja_render
+        from changedetectionio.jinja2_custom import render as jinja_render
         request_headers = CaseInsensitiveDict()
 
         ua = self.datastore.data['settings']['requests'].get('default_ua')
@@ -146,18 +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)
-
         # All fetchers are now async
-        await 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
-                               )
+        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 +1,133 @@
+"""
+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",
+    "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",
+]
+
+
+# Generic XML Content-types (non-RSS/Atom)
+XML_CONTENT_TYPES = [
+    "text/xml",
+    "application/xml",
+]
+
+HTML_PATTERNS = ['<!doctype html', '<html', '<head', '<body', '<script', '<iframe', '<div']
+
+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):
+        import re
+        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)
+
+        # Use puremagic for lightweight MIME detection (saves ~14MB vs python-magic)
+        magic_result = None
+        try:
+            import puremagic
+
+            # puremagic needs bytes, so encode if we have a string
+            content_bytes = content[:200].encode('utf-8') if isinstance(content, str) else content[:200]
+
+            # puremagic returns a list of PureMagic objects with confidence scores
+            detections = puremagic.magic_string(content_bytes)
+            if detections:
+                # Get the highest confidence detection
+                mime = detections[0].mime_type
+                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
+                    if mime in ['application/octet-stream', 'application/x-empty', 'binary']:
+                        logger.debug(f"Ignoring generic mime type '{mime}' from puremagic library")
+                    # Trust puremagic 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 'puremagic' 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 'text/plain' in http_content_header:
+            self.is_plaintext = True
+        if any(s in http_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):
+            self.is_json = 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
+        elif any(s in magic_content_header for s in JSON_CONTENT_TYPES):
+            self.is_json = True
+        # magic will call a rss document 'xml'
+        # Rarely do endpoints give the right header, usually just text/xml, so we check also for <rss
+        # This also triggers the automatic CDATA text parser so the RSS goes back a nice content list
+        elif '<rss' in test_content_normalized or '<feed' in test_content_normalized or any(s in magic_content_header for s in RSS_XML_CONTENT_TYPES) or '<rdf:' in test_content_normalized:
+            self.is_rss = True
+        elif any(s in http_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 test_content_normalized.startswith('<?xml') or any(s in magic_content_header for s in XML_CONTENT_TYPES):
+            # 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
+        elif http_content_header.startswith('text/'):
+            self.is_plaintext = True
+        # Only trust magic for 'text' if no other patterns matched
+        elif 'text' in magic_content_header:
+            self.is_plaintext = 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)")
+

changedetectionio/processors/text_json_diff/processor.py

@@ -13,12 +13,17 @@ 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'
 description = 'Detects all text changes where possible'
 
-json_filter_prefixes = ['json:', 'jq:', 'jqraw:']
+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):
@@ -32,356 +37,560 @@ class PDFToHTMLToolNotFound(ValueError):
         ValueError.__init__(self, msg)
 
 
+class FilterConfig:
+    """Consolidates all filter and rule configurations from watch, tags, and global settings."""
+
+    def __init__(self, watch, datastore):
+        self.watch = watch
+        self.datastore = datastore
+        self.watch_uuid = watch.get('uuid')
+        # Cache computed properties to avoid repeated list operations
+        self._include_filters_cache = None
+        self._subtractive_selectors_cache = None
+
+    def _get_merged_rules(self, attr, include_global=False):
+        """Merge rules from watch, tags, and optionally global settings."""
+        watch_rules = self.watch.get(attr, [])
+        tag_rules = self.datastore.get_tag_overrides_for_watch(uuid=self.watch_uuid, attr=attr)
+        rules = list(dict.fromkeys(watch_rules + tag_rules))
+
+        if include_global:
+            global_rules = self.datastore.data['settings']['application'].get(f'global_{attr}', [])
+            rules = list(dict.fromkeys(rules + global_rules))
+
+        return rules
+
+    @property
+    def include_filters(self):
+        if self._include_filters_cache is None:
+            filters = self._get_merged_rules('include_filters')
+            # Inject LD+JSON price tracker rule if enabled
+            if self.watch.get('track_ldjson_price_data', '') == PRICE_DATA_TRACK_ACCEPT:
+                filters += html_tools.LD_JSON_PRODUCT_OFFER_SELECTORS
+            self._include_filters_cache = filters
+        return self._include_filters_cache
+
+    @property
+    def subtractive_selectors(self):
+        if self._subtractive_selectors_cache is None:
+            watch_selectors = self.watch.get("subtractive_selectors", [])
+            tag_selectors = self.datastore.get_tag_overrides_for_watch(uuid=self.watch_uuid, attr='subtractive_selectors')
+            global_selectors = self.datastore.data["settings"]["application"].get("global_subtractive_selectors", [])
+            self._subtractive_selectors_cache = [*tag_selectors, *watch_selectors, *global_selectors]
+        return self._subtractive_selectors_cache
+
+    @property
+    def extract_text(self):
+        return self._get_merged_rules('extract_text')
+
+    @property
+    def ignore_text(self):
+        return self._get_merged_rules('ignore_text', include_global=True)
+
+    @property
+    def trigger_text(self):
+        return self._get_merged_rules('trigger_text')
+
+    @property
+    def text_should_not_be_present(self):
+        return self._get_merged_rules('text_should_not_be_present')
+
+    @property
+    def has_include_filters(self):
+        return bool(self.include_filters) and bool(self.include_filters[0].strip())
+
+    @property
+    def has_include_json_filters(self):
+        return any(f.strip().startswith(prefix) for f in self.include_filters for prefix in JSON_FILTER_PREFIXES)
+
+    @property
+    def has_subtractive_selectors(self):
+        return bool(self.subtractive_selectors) and bool(self.subtractive_selectors[0].strip())
+
+
+class ContentTransformer:
+    """Handles text transformations like trimming, sorting, and deduplication."""
+
+    @staticmethod
+    def trim_whitespace(text):
+        """Remove leading/trailing whitespace from each line."""
+        # Use generator expression to avoid building intermediate list
+        return '\n'.join(line.strip() for line in text.replace("\n\n", "\n").splitlines())
+
+    @staticmethod
+    def remove_duplicate_lines(text):
+        """Remove duplicate lines while preserving order."""
+        return '\n'.join(dict.fromkeys(line for line in text.replace("\n\n", "\n").splitlines()))
+
+    @staticmethod
+    def sort_alphabetically(text):
+        """Sort lines alphabetically (case-insensitive)."""
+        # Remove double line feeds before sorting
+        text = text.replace("\n\n", "\n")
+        return '\n'.join(sorted(text.splitlines(), key=lambda x: x.lower()))
+
+    @staticmethod
+    def extract_by_regex(text, regex_patterns):
+        """Extract text matching regex patterns."""
+        # Use list of strings instead of concatenating lists repeatedly (avoids O(n²) behavior)
+        regex_matched_output = []
+
+        for s_re in regex_patterns:
+            # Check if it's perl-style regex /.../
+            if re.search(PERL_STYLE_REGEX, s_re, re.IGNORECASE):
+                regex = html_tools.perl_style_slash_enclosed_regex_to_options(s_re)
+                result = re.findall(regex, text)
+
+                for match in result:
+                    if type(match) is tuple:
+                        regex_matched_output.extend(match)
+                        regex_matched_output.append('\n')
+                    else:
+                        regex_matched_output.append(match)
+                        regex_matched_output.append('\n')
+            else:
+                # Plain text search (case-insensitive)
+                r = re.compile(re.escape(s_re), re.IGNORECASE)
+                res = r.findall(text)
+                if res:
+                    for match in res:
+                        regex_matched_output.append(match)
+                        regex_matched_output.append('\n')
+
+        return ''.join(regex_matched_output) if regex_matched_output else ''
+
+
+class RuleEngine:
+    """Evaluates blocking rules (triggers, conditions, text_should_not_be_present)."""
+
+    @staticmethod
+    def evaluate_trigger_text(content, trigger_patterns):
+        """
+        Check if trigger text is present. If trigger_text is configured,
+        content is blocked UNLESS the trigger is found.
+        Returns True if blocked, False if allowed.
+        """
+        if not trigger_patterns:
+            return False
+
+        # Assume blocked if trigger_text is configured
+        result = html_tools.strip_ignore_text(
+            content=str(content),
+            wordlist=trigger_patterns,
+            mode="line numbers"
+        )
+        # Unblock if trigger was found
+        return not bool(result)
+
+    @staticmethod
+    def evaluate_text_should_not_be_present(content, patterns):
+        """
+        Check if forbidden text is present. If found, block the change.
+        Returns True if blocked, False if allowed.
+        """
+        if not patterns:
+            return False
+
+        result = html_tools.strip_ignore_text(
+            content=str(content),
+            wordlist=patterns,
+            mode="line numbers"
+        )
+        # Block if forbidden text was found
+        return bool(result)
+
+    @staticmethod
+    def evaluate_conditions(watch, datastore, content):
+        """
+        Evaluate custom conditions ruleset.
+        Returns True if blocked, False if allowed.
+        """
+        if not watch.get('conditions') or not watch.get('conditions_match_logic'):
+            return False
+
+        conditions_result = execute_ruleset_against_all_plugins(
+            current_watch_uuid=watch.get('uuid'),
+            application_datastruct=datastore.data,
+            ephemeral_data={'text': content}
+        )
+
+        # Block if conditions not met
+        return not conditions_result.get('result')
+
+
+class ContentProcessor:
+    """Handles content preprocessing, filtering, and extraction."""
+
+    def __init__(self, fetcher, watch, filter_config, datastore):
+        self.fetcher = fetcher
+        self.watch = watch
+        self.filter_config = filter_config
+        self.datastore = datastore
+
+    def preprocess_rss(self, content):
+        """
+        Convert CDATA/comments in RSS to usable text.
+
+        Supports two RSS processing modes:
+        - 'default': Inline CDATA replacement (original behavior)
+        - 'formatted': Format RSS items with title, link, guid, pubDate, and description (CDATA unmarked)
+        """
+        from changedetectionio import rss_tools
+        rss_mode = self.datastore.data["settings"]["application"].get("rss_reader_mode")
+        if rss_mode:
+            # Format RSS items nicely with CDATA content unmarked and converted to text
+            return rss_tools.format_rss_items(content)
+        else:
+            # Default: Original inline CDATA replacement
+            return cdata_in_document_to_text(html_content=content)
+
+    def preprocess_pdf(self, raw_content):
+        """Convert PDF to HTML using external tool."""
+        from shutil import which
+        tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
+        if not which(tool):
+            raise PDFToHTMLToolNotFound(
+                f"Command-line `{tool}` tool was not found in system PATH, was it installed?"
+            )
+
+        import subprocess
+        proc = subprocess.Popen(
+            [tool, '-stdout', '-', '-s', 'out.pdf', '-i'],
+            stdout=subprocess.PIPE,
+            stdin=subprocess.PIPE
+        )
+        proc.stdin.write(raw_content)
+        proc.stdin.close()
+        html_content = proc.stdout.read().decode('utf-8')
+        proc.wait(timeout=60)
+
+        # Add metadata for change detection
+        metadata = (
+            f"<p>Added by changedetection.io: Document checksum - "
+            f"{hashlib.md5(raw_content).hexdigest().upper()} "
+            f"Original file size - {len(raw_content)} bytes</p>"
+        )
+        return html_content.replace('</body>', metadata + '</body>')
+
+    def preprocess_json(self, raw_content):
+        """Format and sort JSON content."""
+        # Then we re-format it, else it does have filters (later on) which will reformat it anyway
+        content = html_tools.extract_json_as_string(content=raw_content, json_filter="json:$")
+
+        # Sort JSON to avoid false alerts from reordering
+        try:
+            content = json.dumps(json.loads(content), sort_keys=True, indent=4)
+        except Exception:
+            # Might be malformed JSON, continue anyway
+            pass
+
+        return content
+
+    def apply_include_filters(self, content, stream_content_type):
+        """Apply CSS, XPath, or JSON filters to extract specific content."""
+        filtered_content = ""
+
+        for filter_rule in self.filter_config.include_filters:
+            # XPath filters
+            if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
+                filtered_content += html_tools.xpath_filter(
+                    xpath_filter=filter_rule.replace('xpath:', ''),
+                    html_content=content,
+                    append_pretty_line_formatting=not self.watch.is_source_type_url,
+                    is_rss=stream_content_type.is_rss
+                )
+
+            # XPath1 filters (first match only)
+            elif filter_rule.startswith('xpath1:'):
+                filtered_content += html_tools.xpath1_filter(
+                    xpath_filter=filter_rule.replace('xpath1:', ''),
+                    html_content=content,
+                    append_pretty_line_formatting=not self.watch.is_source_type_url,
+                    is_rss=stream_content_type.is_rss
+                )
+
+            # JSON filters
+            elif any(filter_rule.startswith(prefix) for prefix in JSON_FILTER_PREFIXES):
+                filtered_content += html_tools.extract_json_as_string(
+                    content=content,
+                    json_filter=filter_rule
+                )
+
+            # CSS selectors, default fallback
+            else:
+                filtered_content += html_tools.include_filters(
+                    include_filters=filter_rule,
+                    html_content=content,
+                    append_pretty_line_formatting=not self.watch.is_source_type_url
+                )
+
+        # Raise error if filter returned nothing
+        if not filtered_content.strip():
+            raise FilterNotFoundInResponse(
+                msg=self.filter_config.include_filters,
+                screenshot=self.fetcher.screenshot,
+                xpath_data=self.fetcher.xpath_data
+            )
+
+        return filtered_content
+
+    def apply_subtractive_selectors(self, content):
+        """Remove elements matching subtractive selectors."""
+        return html_tools.element_removal(self.filter_config.subtractive_selectors, content)
+
+    def extract_text_from_html(self, html_content, stream_content_type):
+        """Convert HTML to plain text."""
+        do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
+        return html_tools.html_to_text(
+            html_content=html_content,
+            render_anchor_tag_content=do_anchor,
+            is_rss=stream_content_type.is_rss
+        )
+
+
+class ChecksumCalculator:
+    """Calculates checksums with various options."""
+
+    @staticmethod
+    def calculate(text, ignore_whitespace=False):
+        """Calculate MD5 checksum of text content."""
+        if ignore_whitespace:
+            text = text.translate(TRANSLATE_WHITESPACE_TABLE)
+        return hashlib.md5(text.encode('utf-8')).hexdigest()
+
+
 # Some common stuff here that can be moved to a base class
 # (set_proxy_from_list)
 class perform_site_check(difference_detection_processor):
 
     def run_changedetection(self, watch):
         changed_detected = False
-        html_content = ""
-        screenshot = False  # as bytes
-        stripped_text_from_html = ""
 
         if not watch:
             raise Exception("Watch no longer exists.")
 
+        # Initialize components
+        filter_config = FilterConfig(watch, self.datastore)
+        content_processor = ContentProcessor(self.fetcher, watch, filter_config, self.datastore)
+        transformer = ContentTransformer()
+        rule_engine = RuleEngine()
+
+        # Get content type and stream info
+        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}
-
         url = watch.link
 
         self.screenshot = self.fetcher.screenshot
         self.xpath_data = self.fetcher.xpath_data
 
-        # Track the content type
-        update_obj['content_type'] = self.fetcher.get_all_headers().get('content-type', '').lower()
-
-        # Watches added automatically in the queue manager will skip if its the same checksum as the previous run
-        # Saves a lot of CPU
+        # Track the content type and checksum before filters
+        update_obj['content_type'] = ctype_header
         update_obj['previous_md5_before_filters'] = hashlib.md5(self.fetcher.content.encode('utf-8')).hexdigest()
 
-        # Fetching complete, now filters
+        # === CONTENT PREPROCESSING ===
+        # Avoid creating unnecessary intermediate string copies by reassigning only when needed
+        content = self.fetcher.content
 
-        # @note: I feel like the following should be in a more obvious chain system
-        #  - Check filter text
-        #  - Is the checksum different?
-        #  - Do we convert to JSON?
-        # https://stackoverflow.com/questions/41817578/basic-method-chaining ?
-        # return content().textfilter().jsonextract().checksumcompare() ?
+        # RSS preprocessing
+        if stream_content_type.is_rss:
+            content = content_processor.preprocess_rss(content)
+            if self.datastore.data["settings"]["application"].get("rss_reader_mode"):
+                # Now just becomes regular HTML that can have xpath/CSS applied (first of the set etc)
+                stream_content_type.is_rss = False
+                stream_content_type.is_html = True
+                self.fetcher.content = content
 
-        is_json = 'application/json' in self.fetcher.get_all_headers().get('content-type', '').lower()
-        is_html = not is_json
-        is_rss = False
+        # PDF preprocessing
+        if watch.is_pdf or stream_content_type.is_pdf:
+            content = content_processor.preprocess_pdf(raw_content=self.fetcher.raw_content)
+            stream_content_type.is_html = True
 
-        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
+        # JSON - Always reformat it nicely for consistency.
 
-        # source: support, basically treat it as plaintext
+        if stream_content_type.is_json:
+            if not filter_config.has_include_json_filters:
+                content = content_processor.preprocess_json(raw_content=content)
+        #else, otherwise it gets sorted/formatted in the filter stage anyway
+
+        # HTML obfuscation workarounds
+        if stream_content_type.is_html:
+            content = html_tools.workarounds_for_obfuscations(content)
+
+        # Check for LD+JSON price data (for HTML content)
+        if stream_content_type.is_html:
+            update_obj['has_ldjson_price_data'] = html_tools.has_ldjson_product_info(content)
+
+        # === FILTER APPLICATION ===
+        # Start with content reference, avoid copy until modification
+        html_content = content
+
+        # Apply include filters (CSS, XPath, JSON)
+        # Except for plaintext (incase they tried to confuse the system, it will HTML escape
+        #if not stream_content_type.is_plaintext:
+        if filter_config.has_include_filters:
+            html_content = content_processor.apply_include_filters(content, stream_content_type)
+
+        # Apply subtractive selectors
+        if filter_config.has_subtractive_selectors:
+            html_content = content_processor.apply_subtractive_selectors(html_content)
+
+        # === TEXT EXTRACTION ===
         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:
-            from shutil import which
-            tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
-            if not which(tool):
-                raise PDFToHTMLToolNotFound("Command-line `{}` tool was not found in system PATH, was it installed?".format(tool))
-
-            import subprocess
-            proc = subprocess.Popen(
-                [tool, '-stdout', '-', '-s', 'out.pdf', '-i'],
-                stdout=subprocess.PIPE,
-                stdin=subprocess.PIPE)
-            proc.stdin.write(self.fetcher.raw_content)
-            proc.stdin.close()
-            self.fetcher.content = proc.stdout.read().decode('utf-8')
-            proc.wait(timeout=60)
-
-            # Add a little metadata so we know if the file changes (like if an image changes, but the text is the same
-            # @todo may cause problems with non-UTF8?
-            metadata = "<p>Added by changedetection.io: Document checksum - {} Filesize - {} bytes</p>".format(
-                hashlib.md5(self.fetcher.raw_content).hexdigest().upper(),
-                len(self.fetcher.content))
-
-            self.fetcher.content = self.fetcher.content.replace('</body>', metadata + '</body>')
-
-        # Better would be if Watch.model could access the global data also
-        # and then use getattr https://docs.python.org/3/reference/datamodel.html#object.__getitem__
-        # https://realpython.com/inherit-python-dict/ instead of doing it procedurely
-        include_filters_from_tags = self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='include_filters')
-
-        # 1845 - remove duplicated filters in both group and watch include filter
-        include_filters_rule = list(dict.fromkeys(watch.get('include_filters', []) + include_filters_from_tags))
-
-        subtractive_selectors = [*self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='subtractive_selectors'),
-                                 *watch.get("subtractive_selectors", []),
-                                 *self.datastore.data["settings"]["application"].get("global_subtractive_selectors", [])
-                                 ]
-
-        # Inject a virtual LD+JSON price tracker rule
-        if watch.get('track_ldjson_price_data', '') == PRICE_DATA_TRACK_ACCEPT:
-            include_filters_rule += html_tools.LD_JSON_PRODUCT_OFFER_SELECTORS
-
-        has_filter_rule = len(include_filters_rule) and len(include_filters_rule[0].strip())
-        has_subtractive_selectors = len(subtractive_selectors) and len(subtractive_selectors[0].strip())
-
-        if is_json and not has_filter_rule:
-            include_filters_rule.append("json:$")
-            has_filter_rule = True
-
-        if is_json:
-            # Sort the JSON so we dont get false alerts when the content is just re-ordered
-            try:
-                self.fetcher.content = json.dumps(json.loads(self.fetcher.content), sort_keys=True)
-            except Exception as e:
-                # Might have just been a snippet, or otherwise bad JSON, continue
-                pass
-
-        if has_filter_rule:
-            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 is_html or watch.is_source_type_url:
-
-            # 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():
-                # Don't run get_text or xpath/css filters on plaintext
-                stripped_text_from_html = html_content
+            # For source URLs, keep raw content
+            stripped_text = html_content
+        elif stream_content_type.is_plaintext:
+            # For plaintext, keep as-is without HTML-to-text conversion
+            stripped_text = html_content
+        else:
+            # Extract text from HTML/RSS content (not generic XML)
+            if stream_content_type.is_html or stream_content_type.is_rss:
+                stripped_text = content_processor.extract_text_from_html(html_content, stream_content_type)
             else:
-                # Does it have some ld+json price data? used for easier monitoring
-                update_obj['has_ldjson_price_data'] = html_tools.has_ldjson_product_info(self.fetcher.content)
-
-                # Then we assume HTML
-                if has_filter_rule:
-                    html_content = ""
-
-                    for filter_rule in include_filters_rule:
-                        # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
-                        if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
-                            html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
-                                                                    html_content=self.fetcher.content,
-                                                                    append_pretty_line_formatting=not watch.is_source_type_url,
-                                                                    is_rss=is_rss)
-
-                        elif filter_rule.startswith('xpath1:'):
-                            html_content += html_tools.xpath1_filter(xpath_filter=filter_rule.replace('xpath1:', ''),
-                                                                     html_content=self.fetcher.content,
-                                                                     append_pretty_line_formatting=not watch.is_source_type_url,
-                                                                     is_rss=is_rss)
-                        else:
-                            html_content += html_tools.include_filters(include_filters=filter_rule,
-                                                                       html_content=self.fetcher.content,
-                                                                       append_pretty_line_formatting=not watch.is_source_type_url)
-
-                    if not html_content.strip():
-                        raise FilterNotFoundInResponse(msg=include_filters_rule, screenshot=self.fetcher.screenshot, xpath_data=self.fetcher.xpath_data)
-
-                if has_subtractive_selectors:
-                    html_content = html_tools.element_removal(subtractive_selectors, html_content)
-
-                if watch.is_source_type_url:
-                    stripped_text_from_html = html_content
-                else:
-                    # extract text
-                    do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
-                    stripped_text_from_html = html_tools.html_to_text(html_content=html_content,
-                                                                      render_anchor_tag_content=do_anchor,
-                                                                      is_rss=is_rss)  # 1874 activate the <title workaround hack
+                stripped_text = html_content
 
+        # === TEXT TRANSFORMATIONS ===
         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())
+            stripped_text = transformer.trim_whitespace(stripped_text)
 
-        # Re #340 - return the content before the 'ignore text' was applied
-        # Also used to calculate/show what was removed
-        text_content_before_ignored_filter = stripped_text_from_html
-
-        # @todo whitespace coming from missing rtrim()?
-        # stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
-        # Rewrite's the processing text based on only what diff result they want to see
+        # Save text before ignore filters (for diff calculation)
+        text_content_before_ignored_filter = stripped_text
 
+        # === DIFF FILTERING ===
+        # If user wants specific diff types (added/removed/replaced only)
         if watch.has_special_diff_filter_options_set() and len(watch.history.keys()):
-            # Now the content comes from the diff-parser and not the returned HTTP traffic, so could be some differences
-            from changedetectionio import diff
-            # needs to not include (added) etc or it may get used twice
-            # Replace the processed text with the preferred result
-            rendered_diff = diff.render_diff(previous_version_file_contents=watch.get_last_fetched_text_before_filters(),
-                                             newest_version_file_contents=stripped_text_from_html,
-                                             include_equal=False,  # not the same lines
-                                             include_added=watch.get('filter_text_added', True),
-                                             include_removed=watch.get('filter_text_removed', True),
-                                             include_replaced=watch.get('filter_text_replaced', True),
-                                             line_feed_sep="\n",
-                                             include_change_type_prefix=False)
+            stripped_text = self._apply_diff_filtering(watch, stripped_text, text_content_before_ignored_filter)
+            if stripped_text is None:
+                # No differences found, but content exists
+                c = ChecksumCalculator.calculate(text_content_before_ignored_filter, ignore_whitespace=True)
+                return False, {'previous_md5': c}, text_content_before_ignored_filter.encode('utf-8')
 
-            watch.save_last_text_fetched_before_filters(text_content_before_ignored_filter.encode('utf-8'))
-
-            if not rendered_diff and stripped_text_from_html:
-                # We had some content, but no differences were found
-                # Store our new file as the MD5 so it will trigger in the future
-                c = hashlib.md5(stripped_text_from_html.translate(TRANSLATE_WHITESPACE_TABLE).encode('utf-8')).hexdigest()
-                return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8')
-            else:
-                stripped_text_from_html = rendered_diff
-
-        # Treat pages with no renderable text content as a change? No by default
+        # === EMPTY PAGE CHECK ===
         empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
-        if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
-            raise content_fetchers.exceptions.ReplyWithContentButNoText(url=url,
-                                                            status_code=self.fetcher.get_last_status_code(),
-                                                            screenshot=self.fetcher.screenshot,
-                                                            has_filters=has_filter_rule,
-                                                            html_content=html_content,
-                                                            xpath_data=self.fetcher.xpath_data
-                                                            )
-
-        # We rely on the actual text in the html output.. many sites have random script vars etc,
-        # in the future we'll implement other mechanisms.
+        if not stream_content_type.is_json and not empty_pages_are_a_change and len(stripped_text.strip()) == 0:
+            raise content_fetchers.exceptions.ReplyWithContentButNoText(
+                url=url,
+                status_code=self.fetcher.get_last_status_code(),
+                screenshot=self.fetcher.screenshot,
+                has_filters=filter_config.has_include_filters,
+                html_content=html_content,
+                xpath_data=self.fetcher.xpath_data
+            )
 
         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')
-        if len(extract_text) > 0:
-            regex_matched_output = []
-            for s_re in extract_text:
-                # incase they specified something in '/.../x'
-                if re.search(PERL_STYLE_REGEX, s_re, re.IGNORECASE):
-                    regex = html_tools.perl_style_slash_enclosed_regex_to_options(s_re)
-                    result = re.findall(regex, stripped_text_from_html)
-
-                    for l in result:
-                        if type(l) is tuple:
-                            # @todo - some formatter option default (between groups)
-                            regex_matched_output += list(l) + ['\n']
-                        else:
-                            # @todo - some formatter option default (between each ungrouped result)
-                            regex_matched_output += [l] + ['\n']
-                else:
-                    # Doesnt look like regex, just hunt for plaintext and return that which matches
-                    # `stripped_text_from_html` will be bytes, so we must encode s_re also to bytes
-                    r = re.compile(re.escape(s_re), re.IGNORECASE)
-                    res = r.findall(stripped_text_from_html)
-                    if res:
-                        for match in res:
-                            regex_matched_output += [match] + ['\n']
-
-            ##########################################################
-            stripped_text_from_html = ''
-
-            if regex_matched_output:
-                # @todo some formatter for presentation?
-                stripped_text_from_html = ''.join(regex_matched_output)
+        # === REGEX EXTRACTION ===
+        if filter_config.extract_text:
+            extracted = transformer.extract_by_regex(stripped_text, filter_config.extract_text)
+            stripped_text = extracted
 
+        # === MORE TEXT TRANSFORMATIONS ===
         if watch.get('remove_duplicate_lines'):
-            stripped_text_from_html = '\n'.join(dict.fromkeys(line for line in stripped_text_from_html.replace("\n\n", "\n").splitlines()))
-
+            stripped_text = transformer.remove_duplicate_lines(stripped_text)
 
         if watch.get('sort_text_alphabetically'):
-            # Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap
-            # we end up with 'Some text\n\n', sorting will add all those extra \n at the start, so we remove them here.
-            stripped_text_from_html = stripped_text_from_html.replace("\n\n", "\n")
-            stripped_text_from_html = '\n'.join(sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower()))
+            stripped_text = transformer.sort_alphabetically(stripped_text)
 
-### CALCULATE MD5
-        # If there's text to ignore
-        text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
-        text_to_ignore += self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='ignore_text')
+        # === CHECKSUM CALCULATION ===
+        text_for_checksuming = stripped_text
 
-        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)
+        # Apply ignore_text for checksum calculation
+        if filter_config.ignore_text:
+            text_for_checksuming = html_tools.strip_ignore_text(stripped_text, filter_config.ignore_text)
 
-        # 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):
-            fetched_md5 = hashlib.md5(text_for_checksuming.translate(TRANSLATE_WHITESPACE_TABLE).encode('utf-8')).hexdigest()
-        else:
-            fetched_md5 = hashlib.md5(text_for_checksuming.encode('utf-8')).hexdigest()
+            # Optionally remove ignored lines from output
+            strip_ignored_lines = watch.get('strip_ignored_lines')
+            if strip_ignored_lines is None:
+                strip_ignored_lines = self.datastore.data['settings']['application'].get('strip_ignored_lines')
+            if strip_ignored_lines:
+                stripped_text = text_for_checksuming
 
-        ############ Blocking rules, after checksum #################
+        # Calculate checksum
+        ignore_whitespace = self.datastore.data['settings']['application'].get('ignore_whitespace', False)
+        fetched_md5 = ChecksumCalculator.calculate(text_for_checksuming, ignore_whitespace=ignore_whitespace)
+
+        # === BLOCKING RULES EVALUATION ===
         blocked = False
-        trigger_text = watch.get('trigger_text', [])
-        trigger_text += self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='trigger_text')
-        if len(trigger_text):
-            # Assume blocked
+
+        # Check trigger_text
+        if rule_engine.evaluate_trigger_text(stripped_text, filter_config.trigger_text):
             blocked = True
-            # Filter and trigger works the same, so reuse it
-            # It should return the line numbers that match
-            # Unblock flow if the trigger was found (some text remained after stripped what didnt match)
-            result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
-                                                  wordlist=trigger_text,
-                                                  mode="line numbers")
-            # Unblock if the trigger was found
-            if result:
-                blocked = False
 
-        text_should_not_be_present = watch.get('text_should_not_be_present', [])
-        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),
-                                                  wordlist=text_should_not_be_present,
-                                                  mode="line numbers")
-            if result:
-                blocked = True
+        # Check text_should_not_be_present
+        if rule_engine.evaluate_text_should_not_be_present(stripped_text, filter_config.text_should_not_be_present):
+            blocked = True
 
-        # And check if 'conditions' will let this pass through
-        if watch.get('conditions') and watch.get('conditions_match_logic'):
-            conditions_result = execute_ruleset_against_all_plugins(current_watch_uuid=watch.get('uuid'),
-                                                                    application_datastruct=self.datastore.data,
-                                                                    ephemeral_data={
-                                                                        'text': stripped_text_from_html
-                                                                    }
-                                                                    )
+        # Check custom conditions
+        if rule_engine.evaluate_conditions(watch, self.datastore, stripped_text):
+            blocked = True
 
-            if not conditions_result.get('result'):
-                # Conditions say "Condition not met" so we block it.
-                blocked = True
-
-        # Looks like something changed, but did it match all the rules?
+        # === CHANGE DETECTION ===
         if blocked:
             changed_detected = False
         else:
-            # The main thing that all this at the moment comes down to :)
+            # Compare checksums
             if watch.get('previous_md5') != fetched_md5:
                 changed_detected = True
 
             # Always record the new checksum
             update_obj["previous_md5"] = fetched_md5
 
-            # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
+            # On first run, initialize previous_md5
             if not watch.get('previous_md5'):
                 watch['previous_md5'] = fetched_md5
 
         logger.debug(f"Watch UUID {watch.get('uuid')} content check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
 
-        if changed_detected:
-            if watch.get('check_unique_lines', False):
-                ignore_whitespace = self.datastore.data['settings']['application'].get('ignore_whitespace')
+        # === UNIQUE LINES CHECK ===
+        if changed_detected and watch.get('check_unique_lines', False):
+            has_unique_lines = watch.lines_contain_something_unique_compared_to_history(
+                lines=stripped_text.splitlines(),
+                ignore_whitespace=ignore_whitespace
+            )
 
-                has_unique_lines = watch.lines_contain_something_unique_compared_to_history(
-                    lines=stripped_text_from_html.splitlines(),
-                    ignore_whitespace=ignore_whitespace
-                )
+            if not has_unique_lines:
+                logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} didnt have anything new setting change_detected=False")
+                changed_detected = False
+            else:
+                logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} had unique content")
 
-                # One or more lines? unsure?
-                if not has_unique_lines:
-                    logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} didnt have anything new setting change_detected=False")
-                    changed_detected = False
-                else:
-                    logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} had unique content")
+        # Note: Explicit cleanup is only needed here because text_json_diff handles
+        # large strings (100KB-300KB for RSS/HTML). The other processors work with
+        # small strings and don't need this.
+        #
+        # Python would clean these up automatically, but explicit `del` frees memory
+        # immediately rather than waiting for function return, reducing peak memory usage.
+        del content
+        if 'html_content' in locals() and html_content is not stripped_text:
+            del html_content
+        if 'text_content_before_ignored_filter' in locals() and text_content_before_ignored_filter is not stripped_text:
+            del text_content_before_ignored_filter
+        if 'text_for_checksuming' in locals() and text_for_checksuming is not stripped_text:
+            del text_for_checksuming
 
+        return changed_detected, update_obj, stripped_text
 
-        # stripped_text_from_html - Everything after filters and NO 'ignored' content
-        return changed_detected, update_obj, stripped_text_from_html
+    def _apply_diff_filtering(self, watch, stripped_text, text_before_filter):
+        """Apply user's diff filtering preferences (show only added/removed/replaced lines)."""
+        from changedetectionio import diff
+
+        rendered_diff = diff.render_diff(
+            previous_version_file_contents=watch.get_last_fetched_text_before_filters(),
+            newest_version_file_contents=stripped_text,
+            include_equal=False,
+            include_added=watch.get('filter_text_added', True),
+            include_removed=watch.get('filter_text_removed', True),
+            include_replaced=watch.get('filter_text_replaced', True),
+            line_feed_sep="\n",
+            include_change_type_prefix=False
+        )
+
+        watch.save_last_text_fetched_before_filters(text_before_filter.encode('utf-8'))
+
+        if not rendered_diff and stripped_text:
+            # No differences found
+            return None
+
+        return rendered_diff

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/socket_server.py

@@ -29,6 +29,9 @@ class SignalHandler:
         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)
@@ -37,7 +40,7 @@ class SignalHandler:
         # 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, 
+            target=self.polling_emit_running_or_queued_watches_threaded,
             daemon=True
         )
         self.polling_emitter_thread.start()
@@ -69,6 +72,16 @@ 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:
@@ -105,39 +118,38 @@ class SignalHandler:
                 "watch_uuid": watch_uuid,
                 "event_timestamp": time.time()
             })
-            
+
             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')
-        
+
         # Track previous state to avoid unnecessary emissions
         previous_running_uuids = 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:
                 # Get current running UUIDs from async workers
                 running_uuids = set(worker_handler.get_running_uuids())
-                
+
                 # 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():
@@ -146,7 +158,7 @@ class SignalHandler:
                     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:
@@ -156,16 +168,16 @@ class SignalHandler:
                         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 threading polling: {str(e)}")
                 # Even during error recovery, check for exit quickly
@@ -173,11 +185,11 @@ class SignalHandler:
                     if exit_event.is_set():
                         break
                     time.sleep(0.5)
-        
+
         # 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)")
 
@@ -208,20 +220,20 @@ def handle_watch_update(socketio, **kwargs):
 
         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'),
-            'last_checked': watch.get('last_checked'),
-            'error_text': error_texts,
+            'has_favicon': True if watch.get_favicon_filename() else False,
             'history_n': watch.history_n,
-            '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.last_changed) > 0 else 'Not yet',
-            'queued': True if watch.get('uuid') in queue_list else False,
-            'paused': True if watch.get('paused') else False,
+            'last_checked': watch.get('last_checked'),
+            'last_checked_text': _jinja2_filter_datetime(watch),
             '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
@@ -231,14 +243,15 @@ def handle_watch_update(socketio, **kwargs):
 
         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}")
 
         # Emit to all clients (no 'broadcast' parameter needed - it's the default behavior)
-        socketio.emit("watch_update", {'watch': watch_data, 'general_stats': general_stats})
+        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']}")
@@ -251,15 +264,15 @@ def init_socketio(app, datastore):
     """Initialize SocketIO with the main Flask app"""
     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:
@@ -277,7 +290,7 @@ def init_socketio(app, datastore):
         # 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}")
 
@@ -315,7 +328,6 @@ def init_socketio(app, datastore):
             emit_flash=False
         )
 
-
     @socketio.on('connect')
     def handle_connect():
         """Handle client connection"""
@@ -393,4 +405,4 @@ def init_socketio(app, datastore):
 
     logger.info("Socket.IO initialized and attached to main Flask app")
     logger.info(f"Socket.IO: Registered event handlers: {socketio.handlers if hasattr(socketio, 'handlers') else 'No handlers found'}")
-    return socketio
+    return socketio

changedetectionio/rss_tools.py

@@ -0,0 +1,130 @@
+"""
+RSS/Atom feed processing tools for changedetection.io
+"""
+
+from loguru import logger
+import re
+
+
+def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False) -> str:
+    """
+    Process CDATA sections in HTML/XML content - inline replacement.
+
+    Args:
+        html_content: The HTML/XML content to process
+        render_anchor_tag_content: Whether to render anchor tag content
+
+    Returns:
+        Processed HTML/XML content with CDATA sections replaced inline
+    """
+    from xml.sax.saxutils import escape as xml_escape
+    from .html_tools import html_to_text
+
+    pattern = '<!\[CDATA\[(\s*(?:.(?<!\]\]>)\s*)*)\]\]>'
+
+    def repl(m):
+        text = m.group(1)
+        return xml_escape(html_to_text(html_content=text, render_anchor_tag_content=render_anchor_tag_content)).strip()
+
+    return re.sub(pattern, repl, html_content)
+
+
+def format_rss_items(rss_content: str, render_anchor_tag_content=False) -> str:
+    """
+    Format RSS/Atom feed items in a readable text format using feedparser.
+
+    Converts RSS <item> or Atom <entry> elements to formatted text with:
+    - <title> → <h1>Title</h1>
+    - <link> → Link: [url]
+    - <guid> → Guid: [id]
+    - <pubDate> → PubDate: [date]
+    - <description> or <content> → Raw HTML content (CDATA and entities automatically handled)
+
+    Args:
+        rss_content: The RSS/Atom feed content
+        render_anchor_tag_content: Whether to render anchor tag content in descriptions (unused, kept for compatibility)
+
+    Returns:
+        Formatted HTML content ready for html_to_text conversion
+    """
+    try:
+        import feedparser
+        from xml.sax.saxutils import escape as xml_escape
+
+        # Parse the feed - feedparser handles all RSS/Atom variants, CDATA, entity unescaping, etc.
+        feed = feedparser.parse(rss_content)
+
+        formatted_items = []
+
+        # Determine feed type for appropriate labels when fields are missing
+        # feedparser sets feed.version to things like 'rss20', 'atom10', etc.
+        is_atom = feed.version and 'atom' in feed.version
+
+        for entry in feed.entries:
+            item_parts = []
+
+            # Title - feedparser handles CDATA and entity unescaping automatically
+            if hasattr(entry, 'title') and entry.title:
+                item_parts.append(f'<h1>{xml_escape(entry.title)}</h1>')
+
+            # Link
+            if hasattr(entry, 'link') and entry.link:
+                item_parts.append(f'Link: {xml_escape(entry.link)}<br>')
+
+            # GUID/ID
+            if hasattr(entry, 'id') and entry.id:
+                item_parts.append(f'Guid: {xml_escape(entry.id)}<br>')
+
+            # Date - feedparser normalizes all date field names to 'published'
+            if hasattr(entry, 'published') and entry.published:
+                item_parts.append(f'PubDate: {xml_escape(entry.published)}<br>')
+
+            # Description/Content - feedparser handles CDATA and entity unescaping automatically
+            # Only add "Summary:" label for Atom <summary> tags
+            content = None
+            add_label = False
+
+            if hasattr(entry, 'content') and entry.content:
+                # Atom <content> - no label, just content
+                content = entry.content[0].value if entry.content[0].value else None
+            elif hasattr(entry, 'summary'):
+                # Could be RSS <description> or Atom <summary>
+                # feedparser maps both to entry.summary
+                content = entry.summary if entry.summary else None
+                # Only add "Summary:" label for Atom feeds (which use <summary> tag)
+                if is_atom:
+                    add_label = True
+
+            # Add content with or without label
+            if content:
+                if add_label:
+                    item_parts.append(f'Summary:<br>{content}')
+                else:
+                    item_parts.append(content)
+            else:
+                # No content - just show <none>
+                item_parts.append('&lt;none&gt;')
+
+            # Join all parts of this item
+            if item_parts:
+                formatted_items.append('\n'.join(item_parts))
+
+        # Wrap each item in a div with classes (first, last, item-N)
+        items_html = []
+        total_items = len(formatted_items)
+        for idx, item in enumerate(formatted_items):
+            classes = ['rss-item']
+            if idx == 0:
+                classes.append('first')
+            if idx == total_items - 1:
+                classes.append('last')
+            classes.append(f'item-{idx + 1}')
+
+            class_str = ' '.join(classes)
+            items_html.append(f'<div class="{class_str}">{item}</div>')
+        return '<html><body>\n'+"\n<br><br>".join(items_html)+'\n</body></html>'
+
+    except Exception as e:
+        logger.warning(f"Error formatting RSS items: {str(e)}")
+        # Fall back to original content
+        return rss_content

changedetectionio/run_basic_tests.sh

@@ -15,7 +15,7 @@ find tests/test_*py -type f|while read test_name
 do
   echo "TEST RUNNING $test_name"
   # REMOVE_REQUESTS_OLD_SCREENSHOTS disabled so that we can write a screenshot and send it in test_notifications.py without a real browser
-  REMOVE_REQUESTS_OLD_SCREENSHOTS=false pytest $test_name
+  REMOVE_REQUESTS_OLD_SCREENSHOTS=false pytest -vv -s --maxfail=1 --tb=long $test_name
 done
 
 echo "RUNNING WITH BASE_URL SET"
@@ -23,20 +23,20 @@ echo "RUNNING WITH BASE_URL SET"
 # Now re-run some tests with BASE_URL enabled
 # Re #65 - Ability to include a link back to the installation, in the notification.
 export BASE_URL="https://really-unique-domain.io"
-REMOVE_REQUESTS_OLD_SCREENSHOTS=false pytest tests/test_notification.py
+REMOVE_REQUESTS_OLD_SCREENSHOTS=false pytest -vv -s --maxfail=1 tests/test_notification.py
 
 
 # Re-run with HIDE_REFERER set - could affect login
 export HIDE_REFERER=True
-pytest tests/test_access_control.py
+pytest -vv -s --maxfail=1 tests/test_access_control.py
 
 # Re-run a few tests that will trigger brotli based storage
 export SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD=5
-pytest tests/test_access_control.py
+pytest -vv -s --maxfail=1 tests/test_access_control.py
 REMOVE_REQUESTS_OLD_SCREENSHOTS=false pytest tests/test_notification.py
-pytest tests/test_backend.py
-pytest tests/test_rss.py
-pytest tests/test_unique_lines.py
+pytest -vv -s --maxfail=1 tests/test_backend.py
+pytest -vv -s --maxfail=1 tests/test_rss.py
+pytest -vv -s --maxfail=1 tests/test_unique_lines.py
 
 # Try high concurrency
 FETCH_WORKERS=130 pytest  tests/test_history_consistency.py -v -l

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

@@ -1,18 +0,0 @@
-"""
-Safe Jinja2 render with max payload sizes
-
-See https://jinja.palletsprojects.com/en/3.1.x/sandbox/#security-considerations
-"""
-
-import jinja2.sandbox
-import typing as t
-import os
-
-JINJA2_MAX_RETURN_PAYLOAD_SIZE = 1024 * int(os.getenv("JINJA2_MAX_RETURN_PAYLOAD_SIZE_KB", 1024 * 10))
-
-
-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]
-

changedetectionio/static/js/global-settings.js

@@ -29,7 +29,7 @@ $(document).ready(function () {
         $(this).text(new Date($(this).data("utc")).toLocaleString());
     })
 
-    const timezoneInput = $('#application-timezone');
+    const timezoneInput = $('#application-scheduler_timezone_default');
     if(timezoneInput.length) {
         const timezone = Intl.DateTimeFormat().resolvedOptions().timeZone;
         if (!timezoneInput.val().trim()) {

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

@@ -104,49 +104,53 @@ $(document).ready(function () {
                 });
             });
 
-            // Listen for periodically emitted watch data
-            console.log('Adding watch_update event listener');
+            // 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_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-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/_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);
   }
 
@@ -48,17 +49,17 @@
   /* 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 {
@@ -109,6 +110,7 @@
 
   tr.has-error {
     color: var(--color-watch-table-error);
+
     .error-text {
       display: block !important;
     }
@@ -119,12 +121,50 @@
       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);
@@ -184,33 +188,21 @@ code {
   @extend .inline-tag;
 }
 
+@media (min-width: 768px) {
+  .box {
+    margin: 0 1em !important;
+  }
+}
+
 .box {
   max-width: 100%;
-  margin: 0 1em;
+  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%);
@@ -352,7 +344,7 @@ label {
  }  
 }
 
-#notification-customisation {
+.grey-form-border {
   border: 1px solid var(--color-border-notification);
   padding: 0.5rem;
   border-radius: 5px;
@@ -694,114 +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 {
@@ -1056,8 +940,6 @@ ul {
   }
 }
 
-@import "parts/_visualselector";
-
 #webdriver_delay {
     width: 5em;
 }
@@ -1175,17 +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: 0.9rem;
-      > * {
-        display: inline-block;
-      }
+      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 {
@@ -1224,11 +1112,12 @@ ul {
 }
 
 #realtime-conn-error {
-  position: absolute;
+  position: fixed;
   bottom: 0;
-  left: 30px;
+  left: 0;
   background: var(--color-warning);
   padding: 10px;
   font-size: 0.8rem;
   color: #fff;
+  opacity: 0.8;
 }

changedetectionio/store.py

@@ -202,14 +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):
@@ -229,26 +228,36 @@ class ChangeDetectionStore:
         d['settings']['application']['active_base_url'] = active_base_url.strip('" ')
         return d
 
+    from pathlib import Path
+
+    def delete_path(self, path: Path):
+        import shutil
+        """Delete a file or directory tree, including the path itself."""
+        if not path.exists():
+            return
+        if path.is_file() or path.is_symlink():
+            path.unlink(missing_ok=True)  # deletes a file or symlink
+        else:
+            shutil.rmtree(path, ignore_errors=True)  # deletes dir *and* its contents
+
     # Delete a single watch by UUID
     def delete(self, uuid):
         import pathlib
-        import shutil
 
         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']:
                     path = pathlib.Path(os.path.join(self.datastore_path, uuid))
                     if os.path.exists(path):
-                        shutil.rmtree(path)
+                        self.delete(uuid)
 
             else:
                 path = pathlib.Path(os.path.join(self.datastore_path, uuid))
                 if os.path.exists(path):
-                    shutil.rmtree(path)
+                    self.delete_path(path)
+
                 del self.data['watching'][uuid]
 
         self.needs_write_urgent = True
@@ -262,11 +271,6 @@ 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):
@@ -308,7 +312,6 @@ class ChangeDetectionStore:
                     'browser_steps',
                     'css_filter',
                     'extract_text',
-                    'extract_title_as_title',
                     'headers',
                     'ignore_text',
                     'include_filters',
@@ -323,6 +326,7 @@ class ChangeDetectionStore:
                     'title',
                     'trigger_text',
                     'url',
+                    'use_page_title_in_list',
                     'webdriver_js_execute_code',
                 ]:
                     if res.get(k):
@@ -412,7 +416,7 @@ class ChangeDetectionStore:
                 with open(self.json_store_path+".tmp", 'w') as json_file:
                     # 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)
+                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)}")
 
@@ -973,6 +977,20 @@ 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 update_21(self):
+        self.data['settings']['application']['scheduler_timezone_default'] = self.data['settings']['application'].get('timezone')
+        del self.data['settings']['application']['timezone']
+
+
     def add_notification_url(self, notification_url):
         
         logger.debug(f">>> Adding new notification_url - '{notification_url}'")

changedetectionio/templates/_common_fields.html

@@ -33,7 +33,7 @@
                                 <div id="notification-test-log" style="display: none;"><span class="pure-form-message-inline">Processing..</span></div>
                             </div>
                         </div>
-                        <div id="notification-customisation" class="pure-control-group">
+                        <div class="pure-control-group grey-form-border">
                             <div class="pure-control-group">
                                 {{ render_field(form.notification_title, class="m-d notification-title", placeholder=settings_application['notification_title']) }}
                                 <span class="pure-form-message-inline">Title for all notifications</span>
@@ -70,7 +70,7 @@
                                     </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>

changedetectionio/templates/_helpers.html

@@ -1,14 +1,47 @@
 {% 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'] %}
+                    {% for error in errors %}
+                        <li>{{ error }}</li>
+                    {% endfor %}
+                {% elif field.type == 'FieldList' %}
+                    {# Handle FieldList of FormFields - errors is a list of dicts, one per entry #}
+                    {% for idx, entry_errors in field.errors|enumerate %}
+                        {% if entry_errors is mapping and entry_errors %}
+                            {# Only show entries that have actual errors #}
+                            <li><strong>Entry {{ idx + 1 }}:</strong>
+                                <ul>
+                                    {% for field_name, messages in entry_errors.items() %}
+                                        {% for message in messages %}
+                                            <li>{{ field_name }}: {{ message }}</li>
+                                        {% endfor %}
+                                    {% endfor %}
+                                </ul>
+                            </li>
+                        {% endif %}
+                    {% endfor %}
+                {% else %}
+                    {#  regular list of errors with this field #}
+                    {% for error in field.errors %}
+                        <li>{{ error }}</li>
+                    {% endfor %}
+                {% endif %}
+            </ul>
+        {% endif %}
+    </div>
 {% endmacro %}
 
 {% macro render_checkbox_field(field) %}
@@ -24,6 +57,23 @@
   </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>
@@ -61,6 +111,39 @@
   {{ field(**kwargs)|safe }}
 {% endmacro %}
 
+{% macro render_fieldlist_with_inline_errors(fieldlist) %}
+  {# Specialized macro for FieldList(FormField(...)) that renders errors inline with each field #}
+  <div {% if fieldlist.errors %} class="error" {% endif %}>{{ fieldlist.label }}</div>
+  <div {% if fieldlist.errors %} class="error" {% endif %}>
+    <ul id="{{ fieldlist.id }}">
+      {% for entry in fieldlist %}
+        <li {% if entry.errors %} class="error" {% endif %}>
+          <label for="{{ entry.id }}" {% if entry.errors %} class="error" {% endif %}>{{ fieldlist.label.text }}-{{ loop.index0 }}</label>
+          <table id="{{ entry.id }}" {% if entry.errors %} class="error" {% endif %}>
+            <tbody>
+              {% for subfield in entry %}
+                <tr {% if subfield.errors %} class="error" {% endif %}>
+                  <th {% if subfield.errors %} class="error" {% endif %}><label for="{{ subfield.id }}" {% if subfield.errors %} class="error" {% endif %}>{{ subfield.label.text }}</label></th>
+                  <td {% if subfield.errors %} class="error" {% endif %}>
+                    {{ subfield(**kwargs)|safe }}
+                    {% if subfield.errors %}
+                      <ul class="errors">
+                        {% for error in subfield.errors %}
+                          <li class="error">{{ error }}</li>
+                        {% endfor %}
+                      </ul>
+                    {% endif %}
+                  </td>
+                </tr>
+              {% endfor %}
+            </tbody>
+          </table>
+        </li>
+      {% endfor %}
+    </ul>
+  </div>
+{% endmacro %}
+
 {% macro render_conditions_fieldlist_of_formfields_as_table(fieldlist, table_id="rulesTable") %}
   <div class="fieldlist_formfields" id="{{ table_id }}">
     <div class="fieldlist-header">

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)}}" >
@@ -40,7 +41,7 @@
     {% 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">
@@ -236,7 +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">Offline</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

@@ -4,6 +4,7 @@ import time
 from threading import Thread
 
 import pytest
+import arrow
 from changedetectionio import changedetection_app
 from changedetectionio import store
 import os
@@ -29,16 +30,39 @@ def reportlog(pytestconfig):
     logger.remove(handler_id)
 
 
+@pytest.fixture
+def environment(mocker):
+    """Mock arrow.now() to return a fixed datetime for testing jinja2 time extension."""
+    # Fixed datetime: Wed, 09 Dec 2015 23:33:01 UTC
+    # This is calculated to match the test expectations when offsets are applied
+    fixed_datetime = arrow.Arrow(2015, 12, 9, 23, 33, 1, tzinfo='UTC')
+    # Patch arrow.now in the TimeExtension module where it's actually used
+    mocker.patch('changedetectionio.jinja2_custom.extensions.TimeExtension.arrow.now', return_value=fixed_datetime)
+    return fixed_datetime
+
+
+def format_memory_human(bytes_value):
+    """Format memory in human-readable units (KB, MB, GB)"""
+    if bytes_value < 1024:
+        return f"{bytes_value} B"
+    elif bytes_value < 1024 ** 2:
+        return f"{bytes_value / 1024:.2f} KB"
+    elif bytes_value < 1024 ** 3:
+        return f"{bytes_value / (1024 ** 2):.2f} MB"
+    else:
+        return f"{bytes_value / (1024 ** 3):.2f} GB"
+
 def track_memory(memory_usage, ):
     process = psutil.Process(os.getpid())
     while not memory_usage["stop"]:
         current_rss = process.memory_info().rss
         memory_usage["peak"] = max(memory_usage["peak"], current_rss)
+        memory_usage["current"] = current_rss  # Keep updating current
         time.sleep(0.01)  # Adjust the sleep time as needed
 
 @pytest.fixture(scope='function')
 def measure_memory_usage(request):
-    memory_usage = {"peak": 0, "stop": False}
+    memory_usage = {"peak": 0, "current": 0, "stop": False}
     tracker_thread = Thread(target=track_memory, args=(memory_usage,))
     tracker_thread.start()
 
@@ -47,16 +71,17 @@ def measure_memory_usage(request):
     memory_usage["stop"] = True
     tracker_thread.join()
 
-    # Note: ru_maxrss is in kilobytes on Unix-based systems
-    max_memory_used = memory_usage["peak"] / 1024  # Convert to MB
-    s = f"Peak memory used by the test {request.node.fspath} - '{request.node.name}': {max_memory_used:.2f} MB"
+    # Note: psutil returns RSS memory in bytes
+    peak_human = format_memory_human(memory_usage["peak"])
+
+    s = f"{time.time()} {request.node.fspath} - '{request.node.name}' - Peak memory: {peak_human}"
     logger.debug(s)
 
     with open("test-memory.log", 'a') as f:
         f.write(f"{s}\n")
 
     # Assert that the memory usage is less than 200MB
-#    assert max_memory_used < 150, f"Memory usage exceeded 200MB: {max_memory_used:.2f} MB"
+#    assert peak_memory_kb < 150 * 1024, f"Memory usage exceeded 150MB: {peak_human}"
 
 
 def cleanup(datastore_path):

changedetectionio/tests/custom_browser_url/test_custom_browser_url.py

@@ -29,13 +29,8 @@ def do_test(client, live_server, make_test_use_extra_browser=False):
     assert b"Settings updated." in res.data
 
     # Add our URL to the import page
-    res = client.post(
-        url_for("imports.import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-
-    assert b"1 Imported" in res.data
+    uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
+    client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
 
     if make_test_use_extra_browser:
@@ -55,7 +50,8 @@ 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
         )

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) # Setup on conftest per function
+    #  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

@@ -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

@@ -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

@@ -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
     )

changedetectionio/tests/proxy_list/test_proxy_noconnect.py

@@ -44,6 +44,7 @@ def test_proxy_noconnect_custom(client, live_server, measure_memory_usage):
         "url": test_url,
         "fetch_backend": "html_webdriver" if os.getenv('PLAYWRIGHT_DRIVER_URL') or os.getenv("WEBDRIVER_URL") else "html_requests",
         "proxy": "ui-0custom-test-proxy",
+        "time_between_check_use_default": "y",
     }
 
     res = client.post(

changedetectionio/tests/proxy_list/test_select_custom_proxy.py

@@ -49,3 +49,39 @@ def test_select_custom(client, live_server, measure_memory_usage):
     #
     # Now we should see the request in the container logs for "squid-squid-custom" because it will be the only default
 
+
+def test_custom_proxy_validation(client, live_server, measure_memory_usage):
+    #  live_server_setup(live_server) # Setup on conftest per function
+
+    # Goto settings, add our custom one
+    res = client.post(
+        url_for("settings.settings_page"),
+        data={
+            "requests-time_between_check-minutes": 180,
+            "application-ignore_whitespace": "y",
+            "application-fetch_backend": 'html_requests',
+            "requests-extra_proxies-0-proxy_name": "custom-test-proxy",
+            "requests-extra_proxies-0-proxy_url": "xxxxhtt/333??p://test:awesome@squid-custom:3128",
+        },
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." not in res.data
+    assert b'Proxy URLs must start with' in res.data
+
+
+    res = client.post(
+        url_for("settings.settings_page"),
+        data={
+            "requests-time_between_check-minutes": 180,
+            "application-ignore_whitespace": "y",
+            "application-fetch_backend": 'html_requests',
+            "requests-extra_proxies-0-proxy_name": "custom-test-proxy",
+            "requests-extra_proxies-0-proxy_url": "https://",
+        },
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." not in res.data
+    assert b"Invalid URL." in res.data
+    

changedetectionio/tests/proxy_socks5/test_socks5_proxy.py

@@ -2,7 +2,7 @@
 import json
 import os
 from flask import url_for
-from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client, delete_all_watches
 
 
 def set_response():
@@ -66,6 +66,7 @@ def test_socks5(client, live_server, measure_memory_usage):
             "proxy": "ui-0socks5proxy",
             "tags": "",
             "url": test_url,
+            "time_between_check_use_default": "y",
         },
         follow_redirects=True
     )
@@ -97,6 +98,5 @@ def test_socks5(client, live_server, measure_memory_usage):
     )
     assert b"OK" in res.data
 
-    res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
+    delete_all_watches(client)