initial WIP

.dockerignore

@@ -1,18 +1,31 @@
-.git
-.github
-changedetectionio/processors/__pycache__
-changedetectionio/api/__pycache__
-changedetectionio/model/__pycache__
-changedetectionio/blueprint/price_data_follower/__pycache__
-changedetectionio/blueprint/tags/__pycache__
-changedetectionio/blueprint/__pycache__
-changedetectionio/blueprint/browser_steps/__pycache__
-changedetectionio/fetchers/__pycache__
-changedetectionio/tests/visualselector/__pycache__
-changedetectionio/tests/restock/__pycache__
-changedetectionio/tests/__pycache__
-changedetectionio/tests/fetchers/__pycache__
-changedetectionio/tests/unit/__pycache__
-changedetectionio/tests/proxy_list/__pycache__
-changedetectionio/__pycache__
+# Git
+.git/
+.gitignore
 
+# GitHub
+.github/
+
+# Byte-compiled / optimized / DLL files
+**/__pycache__
+**/*.py[cod]
+
+# Caches
+.mypy_cache/
+.pytest_cache/
+.ruff_cache/
+
+# Distribution / packaging
+build/
+dist/
+*.egg-info*
+
+# Virtual environment
+.env
+.venv/
+venv/
+
+# IntelliJ IDEA
+.idea/
+
+# Visual Studio
+.vscode/

.github/ISSUE_TEMPLATE/bug_report.md

@@ -27,6 +27,10 @@ A clear and concise description of what the bug is.
 **Version**
 *Exact version* in the top right area: 0....
 
+**How did you install?**
+
+Docker, Pip, from source directly etc
+
 **To Reproduce**
 
 Steps to reproduce the behavior:

.github/workflows/build-deb-package.yml

@@ -0,0 +1,53 @@
+name: Build Debian Package
+# Check status: systemctl status changedetection.io.service
+# Get logs: journalctl -u changedetection.io.service
+on: [push, pull_request]
+
+jobs:
+  build-deb:
+    runs-on: ubuntu-latest
+    name: Build and Package changedetection.io
+    env:
+      PACKAGE_VERSION: 0.48.5  # or load from somewhere else
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+        with:
+          path: changedetection.io-${{ env.PACKAGE_VERSION }}
+
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.11'
+
+      - name: Install Build Dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y \
+            build-essential \
+            devscripts \
+            dh-virtualenv \
+            dh-python \
+            python3-all \
+            python3-all-dev \
+            python3.10 \
+            python3.10-venv \
+            python3.10-dev \
+            debhelper-compat
+
+      - name: Build the Debian Package
+        # Build it the same as the pypi way, then use the same package tar
+        run: |
+          mkdir /tmp/changedetection.io
+          python3 -m build
+          mv dist/*gz .
+          debuild -us -uc
+
+      - name: Upload Debian Package Artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: changedetection.io-deb-package
+          path: ../*.deb
+
+#@todo install and test that some basic content appears

.github/workflows/build-deb.yml

@@ -0,0 +1,165 @@
+name: Build Debian Package
+
+on:
+  push:
+    branches: [ master ]
+    tags:
+      - '*'
+  pull_request:
+    branches: [ master ]
+  workflow_dispatch:
+
+jobs:
+  build-deb:
+    runs-on: ubuntu-latest
+    container:
+      image: debian:bookworm
+
+    steps:
+    - name: Install git and dependencies
+      run: |
+        apt-get update
+        apt-get install -y git
+
+    - name: Checkout code
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+
+    - name: Install build dependencies
+      run: |
+        apt-get install -y \
+          dpkg-dev \
+          debhelper \
+          dh-python \
+          python3-all \
+          python3-setuptools \
+          python3-pip \
+          python3-venv \
+          build-essential \
+          fakeroot
+
+    - name: Build Debian package
+      run: |
+        # Build the package
+        dpkg-buildpackage -us -uc -b
+
+        # Move built package to workspace for artifact upload
+        mkdir -p deb-packages
+        mv ../*.deb deb-packages/ || true
+        mv ../*.buildinfo deb-packages/ || true
+        mv ../*.changes deb-packages/ || true
+
+        # List what was built
+        ls -lh deb-packages/
+
+    - name: Upload .deb package
+      uses: actions/upload-artifact@v4
+      with:
+        name: changedetection-deb-package
+        path: deb-packages/*.deb
+        retention-days: 30
+
+    - name: Upload build artifacts
+      uses: actions/upload-artifact@v4
+      with:
+        name: changedetection-build-info
+        path: |
+          deb-packages/*.buildinfo
+          deb-packages/*.changes
+        retention-days: 30
+
+  test-install:
+    needs: build-deb
+    runs-on: ubuntu-latest
+    container:
+      image: debian:bookworm
+
+    steps:
+    - name: Download .deb package
+      uses: actions/download-artifact@v4
+      with:
+        name: changedetection-deb-package
+        path: ./deb-packages
+
+    - name: Install systemd and dependencies
+      run: |
+        apt-get update
+        apt-get install -y systemd systemctl
+
+    - name: Install package
+      run: |
+        ls -lh deb-packages/
+        apt-get install -y ./deb-packages/*.deb
+
+    - name: Verify installation
+      run: |
+        echo "Checking if _changedetection user exists..."
+        id _changedetection
+
+        echo "Checking if data directory exists..."
+        test -d /var/lib/changedetection
+        ls -ld /var/lib/changedetection
+
+        echo "Checking if service file exists..."
+        test -f /lib/systemd/system/changedetection.io.service
+
+        echo "Checking if binary wrapper exists..."
+        test -x /usr/bin/changedetection.io
+
+        echo "Checking if venv exists..."
+        test -d /opt/changedetection
+        test -x /opt/changedetection/bin/python3
+
+        echo "Testing binary execution..."
+        /usr/bin/changedetection.io --help || echo "Help command returned: $?"
+
+        echo ""
+        echo "✓ Installation verification passed!"
+
+    - name: Test service start and HTTP endpoint
+      run: |
+        apt-get install -y curl procps
+
+        echo "Starting changedetection.io service manually..."
+        # Start service in background as _changedetection user
+        su - _changedetection -s /bin/sh -c 'cd /var/lib/changedetection && /opt/changedetection/bin/changedetection.io -h 127.0.0.1 -p 5000 -d /var/lib/changedetection' &
+
+        echo "Waiting 5 seconds for service to start..."
+        sleep 5
+
+        echo "Checking if process is running..."
+        ps aux | grep changedetection || true
+
+        echo "Testing HTTP endpoint on localhost:5000..."
+        if curl -f -s http://127.0.0.1:5000/ | grep -i "changedetection" > /dev/null; then
+          echo "✓ Service is responding on port 5000!"
+          echo "✓ HTML content received successfully!"
+        else
+          echo "✗ Service did not respond correctly"
+          exit 1
+        fi
+
+  # Optional: Publish to GitHub Releases on tag push
+  publish-release:
+    if: startsWith(github.ref, 'refs/tags/')
+    needs: [build-deb, test-install]
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+
+    steps:
+    - name: Download .deb package
+      uses: actions/download-artifact@v4
+      with:
+        name: changedetection-deb-package
+        path: ./deb-packages
+
+    - name: Create Release
+      uses: softprops/action-gh-release@v1
+      with:
+        files: deb-packages/*.deb
+        draft: false
+        prerelease: false
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/test-only.yml

@@ -37,3 +37,10 @@ jobs:
       python-version: '3.12'
       skip-pypuppeteer: true
 
+  test-application-3-13:
+    needs: lint-code
+    uses: ./.github/workflows/test-stack-reusable-workflow.yml
+    with:
+      python-version: '3.13'
+      skip-pypuppeteer: true
+      

.gitignore

@@ -1,14 +1,29 @@
-__pycache__
-.idea
-*.pyc
-datastore/url-watches.json
-datastore/*
-__pycache__
-.pytest_cache
-build
-dist
-venv
-test-datastore/*
-test-datastore
+# Byte-compiled / optimized / DLL files
+**/__pycache__
+**/*.py[cod]
+
+# Caches
+.mypy_cache/
+.pytest_cache/
+.ruff_cache/
+
+# Distribution / packaging
+build/
+dist/
 *.egg-info*
+
+# Virtual environment
+.env
+.venv/
+venv/
+
+# IDEs
+.idea
 .vscode/settings.json
+
+# Datastore files
+datastore/
+test-datastore/
+
+# Memory consumption log
+test-memory.log

COMMERCIAL_LICENCE.md

@@ -4,7 +4,7 @@ In any commercial activity involving 'Hosting' (as defined herein), whether in p
 
 # Commercial License Agreement
 
-This Commercial License Agreement ("Agreement") is entered into by and between Mr Morresi (the original creator of this software) here-in ("Licensor") and (your company or personal name) _____________ ("Licensee"). This Agreement sets forth the terms and conditions under which Licensor provides its software ("Software") and services to Licensee for the purpose of reselling the software either in part or full, as part of any commercial activity where the activity involves a third party.
+This Commercial License Agreement ("Agreement") is entered into by and between Web Technologies s.r.o. here-in ("Licensor") and (your company or personal name) _____________ ("Licensee"). This Agreement sets forth the terms and conditions under which Licensor provides its software ("Software") and services to Licensee for the purpose of reselling the software either in part or full, as part of any commercial activity where the activity involves a third party.
 
 ### Definition of Hosting
 

Dockerfile

@@ -32,7 +32,7 @@ RUN pip install --extra-index-url https://www.piwheels.org/simple  --target=/dep
 # Playwright is an alternative to Selenium
 # Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
 # https://github.com/dgtlmoon/changedetection.io/pull/1067 also musl/alpine (not supported)
-RUN pip install --target=/dependencies playwright~=1.41.2 \
+RUN pip install --target=/dependencies playwright~=1.48.0 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage

MANIFEST.in

@@ -10,6 +10,8 @@ recursive-include changedetectionio/tests *
 prune changedetectionio/static/package-lock.json
 prune changedetectionio/static/styles/node_modules
 prune changedetectionio/static/styles/package-lock.json
+prune changedetectionio/tests/test-datastore
+
 include changedetection.py
 include requirements.txt
 include README-pip.md
@@ -18,5 +20,6 @@ global-exclude node_modules
 global-exclude venv
 
 global-exclude test-datastore
+global-exclude changedetectionio/tests/test-datastore
 global-exclude changedetection.io*dist-info
 global-exclude changedetectionio/tests/proxy_socks5/test-datastore

README.md

@@ -105,6 +105,15 @@ We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) glob
 
 Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
 
+### Schedule web page watches in any timezone, limit by day of week and time.
+
+Easily set a re-check schedule, for example you could limit the web page change detection to only operate during business hours.
+Or perhaps based on a foreign timezone (for example, you want to check for the latest news-headlines in a foreign country at 0900 AM),
+
+<img src="./docs/scheduler.png" style="max-width:80%;" alt="How to monitor web page changes according to a schedule"  title="How to monitor web page changes according to a schedule"  />
+
+Includes quick short-cut buttons to setup a schedule for **business hours only**, or **weekends**.
+
 ### We have a Chrome extension!
 
 Easily add the current web page to your changedetection.io tool, simply install the extension and click "Sync" to connect it to your existing changedetection.io install.

build-deb.sh

@@ -0,0 +1,40 @@
+#!/bin/bash
+set -e
+
+echo "========================================"
+echo "Building changedetection.io Debian package"
+echo "========================================"
+
+# Check if running on Debian-based system
+if ! command -v dpkg-buildpackage &> /dev/null; then
+    echo "Error: dpkg-buildpackage not found. Install with:"
+    echo "  sudo apt-get install dpkg-dev debhelper dh-python python3-all python3-setuptools"
+    exit 1
+fi
+
+# Clean previous builds
+echo "Cleaning previous builds..."
+rm -rf debian/.debhelper debian/changedetection.io debian/files debian/*.debhelper* debian/*.substvars
+rm -f ../changedetection.io_*.deb ../changedetection.io_*.buildinfo ../changedetection.io_*.changes
+
+# Build the package
+echo "Building package..."
+dpkg-buildpackage -us -uc -b
+
+echo ""
+echo "========================================"
+echo "Build complete!"
+echo "========================================"
+echo ""
+echo "Package created at:"
+ls -lh ../changedetection.io_*.deb
+echo ""
+echo "To install locally:"
+echo "  sudo dpkg -i ../changedetection.io_*.deb"
+echo "  sudo apt-get install -f  # If there are dependency issues"
+echo ""
+echo "To test in a clean environment:"
+echo "  docker run --rm -it -v \$(pwd)/..:/build debian:bookworm bash"
+echo "  # Inside container:"
+echo "  apt-get update && apt-get install -y /build/changedetection.io_*.deb"
+echo "  systemctl status changedetection.io"

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.47.03'
+__version__ = '0.48.05'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError
@@ -160,11 +160,10 @@ def main():
                     )
 
     # Monitored websites will not receive a Referer header when a user clicks on an outgoing link.
-    # @Note: Incompatible with password login (and maybe other features) for now, submit a PR!
     @app.after_request
     def hide_referrer(response):
         if strtobool(os.getenv("HIDE_REFERER", 'false')):
-            response.headers["Referrer-Policy"] = "no-referrer"
+            response.headers["Referrer-Policy"] = "same-origin"
 
         return response
 

changedetectionio/__main__.py

@@ -0,0 +1,4 @@
+from . import main
+
+if __name__ == '__main__':
+    main()

changedetectionio/apprise_plugin/__init__.py

@@ -13,6 +13,7 @@ from loguru import logger
 def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
     import requests
     import json
+    from urllib.parse import unquote_plus
     from apprise.utils import parse_url as apprise_parse_url
     from apprise import URLBase
 
@@ -47,7 +48,7 @@ def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
     if results:
         # Add our headers that the user can potentially over-ride if they wish
         # to to our returned result set and tidy entries by unquoting them
-        headers = {URLBase.unquote(x): URLBase.unquote(y)
+        headers = {unquote_plus(x): unquote_plus(y)
                    for x, y in results['qsd+'].items()}
 
         # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
@@ -55,14 +56,14 @@ def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
         # but here we are making straight requests, so we need todo convert this against apprise's logic
         for k, v in results['qsd'].items():
             if not k.strip('+-') in results['qsd+'].keys():
-                params[URLBase.unquote(k)] = URLBase.unquote(v)
+                params[unquote_plus(k)] = unquote_plus(v)
 
         # Determine Authentication
         auth = ''
         if results.get('user') and results.get('password'):
-            auth = (URLBase.unquote(results.get('user')), URLBase.unquote(results.get('user')))
+            auth = (unquote_plus(results.get('user')), unquote_plus(results.get('user')))
         elif results.get('user'):
-            auth = (URLBase.unquote(results.get('user')))
+            auth = (unquote_plus(results.get('user')))
 
     # Try to auto-guess if it's JSON
     h = 'application/json; charset=utf-8'

changedetectionio/blueprint/backups/__init__.py

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

changedetectionio/blueprint/backups/templates/overview.html

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

changedetectionio/blueprint/tags/__init__.py

@@ -13,6 +13,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def tags_overview_page():
         from .form import SingleTag
         add_form = SingleTag(request.form)
+
         sorted_tags = sorted(datastore.data['settings']['application'].get('tags').items(), key=lambda x: x[1]['title'])
 
         from collections import Counter
@@ -104,9 +105,11 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         default = datastore.data['settings']['application']['tags'].get(uuid)
 
-        form = group_restock_settings_form(formdata=request.form if request.method == 'POST' else None,
+        form = group_restock_settings_form(
+                                       formdata=request.form if request.method == 'POST' else None,
                                        data=default,
-                                       extra_notification_tokens=datastore.get_unique_notification_tokens_available()
+                                       extra_notification_tokens=datastore.get_unique_notification_tokens_available(),
+                                       default_system_settings = datastore.data['settings'],
                                        )
 
         template_args = {

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

@@ -30,6 +30,8 @@ function isItemInStock() {
         'dieser artikel ist bald wieder verfügbar',
         'dostępne wkrótce',
         'en rupture de stock',
+        'esgotado',
+        'indisponível',
         'isn\'t in stock right now',
         'isnt in stock right now',
         'isn’t in stock right now',
@@ -37,6 +39,7 @@ function isItemInStock() {
         'let me know when it\'s available',
         'mail me when available',
         'message if back in stock',
+        'mevcut değil',
         'nachricht bei',
         'nicht auf lager',
         'nicht lagernd',
@@ -48,7 +51,7 @@ function isItemInStock() {
         'niet beschikbaar',
         'niet leverbaar',
         'niet op voorraad',
-        'no disponible temporalmente',
+        'no disponible',
         'no longer in stock',
         'no tickets available',
         'not available',
@@ -57,6 +60,7 @@ function isItemInStock() {
         'notify me when available',
         'notify me',
         'notify when available',
+        'não disponível',
         'não estamos a aceitar encomendas',
         'out of stock',
         'out-of-stock',
@@ -64,12 +68,14 @@ function isItemInStock() {
         'produkt niedostępny',
         'sold out',
         'sold-out',
+        'stokta yok',
         'temporarily out of stock',
         'temporarily unavailable',
         'there were no search results for',
         'this item is currently unavailable',
         'tickets unavailable',
         'tijdelijk uitverkocht',
+        'tükendi',
         'unavailable nearby',
         'unavailable tickets',
         'vergriffen',

changedetectionio/diff.py

@@ -1,6 +1,9 @@
 import difflib
 from typing import List, Iterator, Union
 
+REMOVED_STYLE = "background-color: #fadad7; color: #b30000;"
+ADDED_STYLE = "background-color: #eaf2c2; color: #406619;"
+
 def same_slicer(lst: List[str], start: int, end: int) -> List[str]:
     """Return a slice of the list, or a single element if start == end."""
     return lst[start:end] if start != end else [lst[start]]
@@ -12,11 +15,12 @@ def customSequenceMatcher(
     include_removed: bool = True,
     include_added: bool = True,
     include_replaced: bool = True,
-    include_change_type_prefix: bool = True
+    include_change_type_prefix: bool = True,
+    html_colour: bool = False
 ) -> Iterator[List[str]]:
     """
     Compare two sequences and yield differences based on specified parameters.
-    
+
     Args:
         before (List[str]): Original sequence
         after (List[str]): Modified sequence
@@ -25,26 +29,35 @@ def customSequenceMatcher(
         include_added (bool): Include added parts
         include_replaced (bool): Include replaced parts
         include_change_type_prefix (bool): Add prefixes to indicate change types
-    
+        html_colour (bool): Use HTML background colors for differences
+
     Yields:
         List[str]: Differences between sequences
     """
     cruncher = difflib.SequenceMatcher(isjunk=lambda x: x in " \t", a=before, b=after)
-    
+
+
+
     for tag, alo, ahi, blo, bhi in cruncher.get_opcodes():
         if include_equal and tag == 'equal':
             yield before[alo:ahi]
         elif include_removed and tag == 'delete':
-            prefix = "(removed) " if include_change_type_prefix else ''
-            yield [f"{prefix}{line}" for line in same_slicer(before, alo, ahi)]
+            if html_colour:
+                yield [f'<span style="{REMOVED_STYLE}">{line}</span>' for line in same_slicer(before, alo, ahi)]
+            else:
+                yield [f"(removed) {line}" for line in same_slicer(before, alo, ahi)] if include_change_type_prefix else same_slicer(before, alo, ahi)
         elif include_replaced and tag == 'replace':
-            prefix_changed = "(changed) " if include_change_type_prefix else ''
-            prefix_into = "(into) " if include_change_type_prefix else ''
-            yield [f"{prefix_changed}{line}" for line in same_slicer(before, alo, ahi)] + \
-                  [f"{prefix_into}{line}" for line in same_slicer(after, blo, bhi)]
+            if html_colour:
+                yield [f'<span style="{REMOVED_STYLE}">{line}</span>' for line in same_slicer(before, alo, ahi)] + \
+                      [f'<span style="{ADDED_STYLE}">{line}</span>' for line in same_slicer(after, blo, bhi)]
+            else:
+                yield [f"(changed) {line}" for line in same_slicer(before, alo, ahi)] + \
+                      [f"(into) {line}" for line in same_slicer(after, blo, bhi)] if include_change_type_prefix else same_slicer(before, alo, ahi) + same_slicer(after, blo, bhi)
         elif include_added and tag == 'insert':
-            prefix = "(added) " if include_change_type_prefix else ''
-            yield [f"{prefix}{line}" for line in same_slicer(after, blo, bhi)]
+            if html_colour:
+                yield [f'<span style="{ADDED_STYLE}">{line}</span>' for line in same_slicer(after, blo, bhi)]
+            else:
+                yield [f"(added) {line}" for line in same_slicer(after, blo, bhi)] if include_change_type_prefix else same_slicer(after, blo, bhi)
 
 def render_diff(
     previous_version_file_contents: str,
@@ -55,11 +68,12 @@ def render_diff(
     include_replaced: bool = True,
     line_feed_sep: str = "\n",
     include_change_type_prefix: bool = True,
-    patch_format: bool = False
+    patch_format: bool = False,
+    html_colour: bool = False
 ) -> str:
     """
     Render the difference between two file contents.
-    
+
     Args:
         previous_version_file_contents (str): Original file contents
         newest_version_file_contents (str): Modified file contents
@@ -70,7 +84,8 @@ def render_diff(
         line_feed_sep (str): Separator for lines in output
         include_change_type_prefix (bool): Add prefixes to indicate change types
         patch_format (bool): Use patch format for output
-    
+        html_colour (bool): Use HTML background colors for differences
+
     Returns:
         str: Rendered difference
     """
@@ -88,10 +103,11 @@ def render_diff(
         include_removed=include_removed,
         include_added=include_added,
         include_replaced=include_replaced,
-        include_change_type_prefix=include_change_type_prefix
+        include_change_type_prefix=include_change_type_prefix,
+        html_colour=html_colour
     )
 
     def flatten(lst: List[Union[str, List[str]]]) -> str:
         return line_feed_sep.join(flatten(x) if isinstance(x, list) else x for x in lst)
 
-    return flatten(rendered_diff)
+    return flatten(rendered_diff)

changedetectionio/flask_app.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 
 import datetime
+from zoneinfo import ZoneInfo
 
 import flask_login
 import locale
@@ -42,6 +43,7 @@ from loguru import logger
 from changedetectionio import html_tools, __version__
 from changedetectionio import queuedWatchMetaData
 from changedetectionio.api import api_v1
+from .time_handler import is_within_schedule
 
 datastore = None
 
@@ -53,6 +55,7 @@ extra_stylesheets = []
 
 update_q = queue.PriorityQueue()
 notification_q = queue.Queue()
+MAX_QUEUE_SIZE = 2000
 
 app = Flask(__name__,
             static_url_path="",
@@ -83,7 +86,7 @@ csrf = CSRFProtect()
 csrf.init_app(app)
 notification_debug_log=[]
 
-# get locale ready
+# Locale for correct presentation of prices etc
 default_locale = locale.getdefaultlocale()
 logger.info(f"System locale default is {default_locale}")
 try:
@@ -715,7 +718,8 @@ def changedetection_app(config=None, datastore_o=None):
 
         form = form_class(formdata=request.form if request.method == 'POST' else None,
                           data=default,
-                          extra_notification_tokens=default.extra_notification_token_values()
+                          extra_notification_tokens=default.extra_notification_token_values(),
+                          default_system_settings=datastore.data['settings']
                           )
 
         # For the form widget tag UUID back to "string name" for the field
@@ -803,14 +807,41 @@ def changedetection_app(config=None, datastore_o=None):
             # But in the case something is added we should save straight away
             datastore.needs_write_urgent = True
 
-            # Queue the watch for immediate recheck, with a higher priority
-            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+            # Do not queue on edit if its not within the time range
+
+            # @todo maybe it should never queue anyway on edit...
+            is_in_schedule = True
+            watch = datastore.data['watching'].get(uuid)
+
+            if watch.get('time_between_check_use_default'):
+                time_schedule_limit = datastore.data['settings']['requests'].get('time_schedule_limit', {})
+            else:
+                time_schedule_limit = watch.get('time_schedule_limit')
+
+            tz_name = time_schedule_limit.get('timezone')
+            if not tz_name:
+                tz_name =  datastore.data['settings']['application'].get('timezone', 'UTC')
+
+            if time_schedule_limit and time_schedule_limit.get('enabled'):
+                try:
+                    is_in_schedule = is_within_schedule(time_schedule_limit=time_schedule_limit,
+                                                        default_tz=tz_name
+                                                        )
+                except Exception as e:
+                    logger.error(
+                        f"{uuid} - Recheck scheduler, error handling timezone, check skipped - TZ name '{tz_name}' - {str(e)}")
+                    return False
+
+            #############################
+            if not datastore.data['watching'][uuid].get('paused') and is_in_schedule:
+                # Queue the watch for immediate recheck, with a higher priority
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
             # Diff page [edit] link should go back to diff page
             if request.args.get("next") and request.args.get("next") == 'diff':
                 return redirect(url_for('diff_history_page', uuid=uuid))
 
-            return redirect(url_for('index'))
+            return redirect(url_for('index', tag=request.args.get("tag",'')))
 
         else:
             if request.method == 'POST' and not form.validate():
@@ -834,15 +865,18 @@ def changedetection_app(config=None, datastore_o=None):
             if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
                 is_html_webdriver = True
 
+            from zoneinfo import available_timezones
+
             # Only works reliably with Playwright
             visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and is_html_webdriver
             template_args = {
                 'available_processors': processors.available_processors(),
+                'available_timezones': sorted(available_timezones()),
                 'browser_steps_config': browser_step_ui_config,
                 'emailprefix': os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
-                'extra_title': f" - Edit - {watch.label}",
-                'extra_processor_config': form.extra_tab_content(),
                 'extra_notification_token_placeholder_info': datastore.get_unique_notification_token_placeholders_available(),
+                'extra_processor_config': form.extra_tab_content(),
+                'extra_title': f" - Edit - {watch.label}",
                 'form': form,
                 'has_default_notification_urls': True if len(datastore.data['settings']['application']['notification_urls']) else False,
                 'has_extra_headers_file': len(datastore.get_all_headers_in_textfile_for_watch(uuid=uuid)) > 0,
@@ -851,6 +885,7 @@ def changedetection_app(config=None, datastore_o=None):
                 'jq_support': jq_support,
                 'playwright_enabled': os.getenv('PLAYWRIGHT_DRIVER_URL', False),
                 'settings_application': datastore.data['settings']['application'],
+                'timezone_default_config': datastore.data['settings']['application'].get('timezone'),
                 'using_global_webdriver_wait': not default['webdriver_delay'],
                 'uuid': uuid,
                 'visualselector_enabled': visualselector_enabled,
@@ -880,6 +915,8 @@ def changedetection_app(config=None, datastore_o=None):
     @login_optionally_required
     def settings_page():
         from changedetectionio import forms
+        from datetime import datetime
+        from zoneinfo import available_timezones
 
         default = deepcopy(datastore.data['settings'])
         if datastore.proxy_list is not None:
@@ -947,14 +984,20 @@ def changedetection_app(config=None, datastore_o=None):
             else:
                 flash("An error occurred, please see below.", "error")
 
+        # Convert to ISO 8601 format, all date/time relative events stored as UTC time
+        utc_time = datetime.now(ZoneInfo("UTC")).isoformat()
+
         output = render_template("settings.html",
                                  api_key=datastore.data['settings']['application'].get('api_access_token'),
+                                 available_timezones=sorted(available_timezones()),
                                  emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
                                  extra_notification_token_placeholder_info=datastore.get_unique_notification_token_placeholders_available(),
                                  form=form,
                                  hide_remove_pass=os.getenv("SALTED_PASS", False),
                                  min_system_recheck_seconds=int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3)),
-                                 settings_application=datastore.data['settings']['application']
+                                 settings_application=datastore.data['settings']['application'],
+                                 timezone_default_config=datastore.data['settings']['application'].get('timezone'),
+                                 utc_time=utc_time,
                                  )
 
         return output
@@ -1235,78 +1278,6 @@ def changedetection_app(config=None, datastore_o=None):
 
         return output
 
-    # We're good but backups are even better!
-    @app.route("/backup", methods=['GET'])
-    @login_optionally_required
-    def get_backup():
-
-        import zipfile
-        from pathlib import Path
-
-        # Remove any existing backup file, for now we just keep one file
-
-        for previous_backup_filename in Path(datastore_o.datastore_path).rglob('changedetection-backup-*.zip'):
-            os.unlink(previous_backup_filename)
-
-        # create a ZipFile object
-        timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
-        backupname = "changedetection-backup-{}.zip".format(timestamp)
-        backup_filepath = os.path.join(datastore_o.datastore_path, backupname)
-
-        with zipfile.ZipFile(backup_filepath, "w",
-                             compression=zipfile.ZIP_DEFLATED,
-                             compresslevel=8) as zipObj:
-
-            # Be sure we're written fresh
-            datastore.sync_to_json()
-
-            # Add the index
-            zipObj.write(os.path.join(datastore_o.datastore_path, "url-watches.json"), arcname="url-watches.json")
-
-            # Add the flask app secret
-            zipObj.write(os.path.join(datastore_o.datastore_path, "secret.txt"), arcname="secret.txt")
-
-            # Add any data in the watch data directory.
-            for uuid, w in datastore.data['watching'].items():
-                for f in Path(w.watch_data_dir).glob('*'):
-                    zipObj.write(f,
-                                 # Use the full path to access the file, but make the file 'relative' in the Zip.
-                                 arcname=os.path.join(f.parts[-2], f.parts[-1]),
-                                 compress_type=zipfile.ZIP_DEFLATED,
-                                 compresslevel=8)
-
-            # Create a list file with just the URLs, so it's easier to port somewhere else in the future
-            list_file = "url-list.txt"
-            with open(os.path.join(datastore_o.datastore_path, list_file), "w") as f:
-                for uuid in datastore.data["watching"]:
-                    url = datastore.data["watching"][uuid]["url"]
-                    f.write("{}\r\n".format(url))
-            list_with_tags_file = "url-list-with-tags.txt"
-            with open(
-                os.path.join(datastore_o.datastore_path, list_with_tags_file), "w"
-            ) as f:
-                for uuid in datastore.data["watching"]:
-                    url = datastore.data["watching"][uuid].get('url')
-                    tag = datastore.data["watching"][uuid].get('tags', {})
-                    f.write("{} {}\r\n".format(url, tag))
-
-            # Add it to the Zip
-            zipObj.write(
-                os.path.join(datastore_o.datastore_path, list_file),
-                arcname=list_file,
-                compress_type=zipfile.ZIP_DEFLATED,
-                compresslevel=8,
-            )
-            zipObj.write(
-                os.path.join(datastore_o.datastore_path, list_with_tags_file),
-                arcname=list_with_tags_file,
-                compress_type=zipfile.ZIP_DEFLATED,
-                compresslevel=8,
-            )
-
-        # Send_from_directory needs to be the full absolute path
-        return send_from_directory(os.path.abspath(datastore_o.datastore_path), backupname, as_attachment=True)
-
     @app.route("/static/<string:group>/<string:filename>", methods=['GET'])
     def static_content(group, filename):
         from flask import make_response
@@ -1339,12 +1310,23 @@ def changedetection_app(config=None, datastore_o=None):
 
             # These files should be in our subdirectory
             try:
-                # set nocache, set content-type
-                response = make_response(send_from_directory(os.path.join(datastore_o.datastore_path, filename), "elements.json"))
-                response.headers['Content-type'] = 'application/json'
-                response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
-                response.headers['Pragma'] = 'no-cache'
-                response.headers['Expires'] = 0
+                # set nocache, set content-type,
+                # `filename` is actually directory UUID of the watch
+                watch_directory = str(os.path.join(datastore_o.datastore_path, filename))
+                response = None
+                if os.path.isfile(os.path.join(watch_directory, "elements.deflate")):
+                    response = make_response(send_from_directory(watch_directory, "elements.deflate"))
+                    response.headers['Content-Type'] = 'application/json'
+                    response.headers['Content-Encoding'] = 'deflate'
+                else:
+                    logger.error(f'Request elements.deflate at "{watch_directory}" but was notfound.')
+                    abort(404)
+
+                if response:
+                    response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+                    response.headers['Pragma'] = 'no-cache'
+                    response.headers['Expires'] = "0"
+
                 return response
 
             except FileNotFoundError:
@@ -1413,13 +1395,13 @@ def changedetection_app(config=None, datastore_o=None):
         if new_uuid:
             if add_paused:
                 flash('Watch added in Paused state, saving will unpause.')
-                return redirect(url_for('edit_page', uuid=new_uuid, unpause_on_save=1))
+                return redirect(url_for('edit_page', uuid=new_uuid, unpause_on_save=1, tag=request.args.get('tag')))
             else:
                 # Straight into the queue.
                 update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
                 flash("Watch added.")
 
-        return redirect(url_for('index'))
+        return redirect(url_for('index', tag=request.args.get('tag','')))
 
 
 
@@ -1686,13 +1668,15 @@ def changedetection_app(config=None, datastore_o=None):
     import changedetectionio.blueprint.check_proxies as check_proxies
     app.register_blueprint(check_proxies.construct_blueprint(datastore=datastore), url_prefix='/check_proxy')
 
+    import changedetectionio.blueprint.backups as backups
+    app.register_blueprint(backups.construct_blueprint(datastore), url_prefix='/backups')
 
     # @todo handle ctrl break
     ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks).start()
     threading.Thread(target=notification_runner).start()
 
     # Check for new release version, but not when running in test/build or pytest
-    if not os.getenv("GITHUB_REF", False) and not config.get('disable_checkver') == True:
+    if not os.getenv("GITHUB_REF", False) and not strtobool(os.getenv('DISABLE_VERSION_CHECK', 'no')):
         threading.Thread(target=check_for_new_version).start()
 
     return app
@@ -1776,7 +1760,6 @@ def notification_runner():
 def ticker_thread_check_time_launch_checks():
     import random
     from changedetectionio import update_worker
-
     proxy_last_called_time = {}
 
     recheck_time_minimum_seconds = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
@@ -1810,12 +1793,14 @@ def ticker_thread_check_time_launch_checks():
             except RuntimeError as e:
                 # RuntimeError: dictionary changed size during iteration
                 time.sleep(0.1)
+                watch_uuid_list = []
             else:
                 break
 
         # Re #438 - Don't place more watches in the queue to be checked if the queue is already large
         while update_q.qsize() >= 2000:
-            time.sleep(1)
+            logger.warning(f"Recheck watches queue size limit reached ({MAX_QUEUE_SIZE}), skipping adding more items")
+            time.sleep(3)
 
 
         recheck_time_system_seconds = int(datastore.threshold_seconds)
@@ -1832,6 +1817,28 @@ def ticker_thread_check_time_launch_checks():
             if watch['paused']:
                 continue
 
+            # @todo - Maybe make this a hook?
+            # Time schedule limit - Decide between watch or global settings
+            if watch.get('time_between_check_use_default'):
+                time_schedule_limit = datastore.data['settings']['requests'].get('time_schedule_limit', {})
+                logger.trace(f"{uuid} Time scheduler - Using system/global settings")
+            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')
+
+            if time_schedule_limit and time_schedule_limit.get('enabled'):
+                try:
+                    result = is_within_schedule(time_schedule_limit=time_schedule_limit,
+                                                default_tz=tz_name
+                                                )
+                    if not result:
+                        logger.trace(f"{uuid} Time scheduler - not within schedule skipping.")
+                        continue
+                except Exception as e:
+                    logger.error(
+                        f"{uuid} - Recheck scheduler, error handling timezone, check skipped - TZ name '{tz_name}' - {str(e)}")
+                    return False
             # If they supplied an individual entry minutes to threshold.
             threshold = recheck_time_system_seconds if watch.get('time_between_check_use_default') else watch.threshold_seconds()
 

changedetectionio/forms.py

@@ -1,12 +1,14 @@
 import os
 import re
 from loguru import logger
+from wtforms.widgets.core import TimeInput
 
 from changedetectionio.strtobool import strtobool
 
 from wtforms import (
     BooleanField,
     Form,
+    Field,
     IntegerField,
     RadioField,
     SelectField,
@@ -125,6 +127,87 @@ class StringTagUUID(StringField):
 
         return 'error'
 
+class TimeDurationForm(Form):
+    hours = SelectField(choices=[(f"{i}", f"{i}") for i in range(0, 25)], default="24",  validators=[validators.Optional()])
+    minutes = SelectField(choices=[(f"{i}", f"{i}") for i in range(0, 60)], default="00", validators=[validators.Optional()])
+
+class TimeStringField(Field):
+    """
+    A WTForms field for time inputs (HH:MM) that stores the value as a string.
+    """
+    widget = TimeInput()  # Use the built-in time input widget
+
+    def _value(self):
+        """
+        Returns the value for rendering in the form.
+        """
+        return self.data if self.data is not None else ""
+
+    def process_formdata(self, valuelist):
+        """
+        Processes the raw input from the form and stores it as a string.
+        """
+        if valuelist:
+            time_str = valuelist[0]
+            # Simple validation for HH:MM format
+            if not time_str or len(time_str.split(":")) != 2:
+                raise ValidationError("Invalid time format. Use HH:MM.")
+            self.data = time_str
+
+
+class validateTimeZoneName(object):
+    """
+       Flask wtform validators wont work with basic auth
+    """
+
+    def __init__(self, message=None):
+        self.message = message
+
+    def __call__(self, form, field):
+        from zoneinfo import available_timezones
+        python_timezones = available_timezones()
+        if field.data and field.data not in python_timezones:
+            raise ValidationError("Not a valid timezone name")
+
+class ScheduleLimitDaySubForm(Form):
+    enabled = BooleanField("not set", default=True)
+    start_time = TimeStringField("Start At", default="00:00", render_kw={"placeholder": "HH:MM"}, validators=[validators.Optional()])
+    duration = FormField(TimeDurationForm, label="Run duration")
+
+class ScheduleLimitForm(Form):
+    enabled = BooleanField("Use time scheduler", default=False)
+    # Because the label for=""" doesnt line up/work with the actual checkbox
+    monday = FormField(ScheduleLimitDaySubForm, label="")
+    tuesday = FormField(ScheduleLimitDaySubForm, label="")
+    wednesday = FormField(ScheduleLimitDaySubForm, label="")
+    thursday = FormField(ScheduleLimitDaySubForm, label="")
+    friday = FormField(ScheduleLimitDaySubForm, label="")
+    saturday = FormField(ScheduleLimitDaySubForm, label="")
+    sunday = FormField(ScheduleLimitDaySubForm, label="")
+
+    timezone = StringField("Optional timezone to run in",
+                                  render_kw={"list": "timezones"},
+                                  validators=[validateTimeZoneName()]
+                                  )
+    def __init__(
+        self,
+        formdata=None,
+        obj=None,
+        prefix="",
+        data=None,
+        meta=None,
+        **kwargs,
+    ):
+        super().__init__(formdata, obj, prefix, data, meta, **kwargs)
+        self.monday.form.enabled.label.text="Monday"
+        self.tuesday.form.enabled.label.text = "Tuesday"
+        self.wednesday.form.enabled.label.text = "Wednesday"
+        self.thursday.form.enabled.label.text = "Thursday"
+        self.friday.form.enabled.label.text = "Friday"
+        self.saturday.form.enabled.label.text = "Saturday"
+        self.sunday.form.enabled.label.text = "Sunday"
+
+
 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")])
@@ -225,8 +308,12 @@ class ValidateAppRiseServers(object):
         # so that the custom endpoints are registered
         from changedetectionio.apprise_plugin import apprise_custom_api_call_wrapper
         for server_url in field.data:
-            if not apobj.add(server_url):
-                message = field.gettext('\'%s\' is not a valid AppRise URL.' % (server_url))
+            url = server_url.strip()
+            if url.startswith("#"):
+                continue
+
+            if not apobj.add(url):
+                message = field.gettext('\'%s\' is not a valid AppRise URL.' % (url))
                 raise ValidationError(message)
 
 class ValidateJinja2Template(object):
@@ -279,6 +366,7 @@ class validateURL(object):
         # This should raise a ValidationError() or not
         validate_url(field.data)
 
+
 def validate_url(test_url):
     # If hosts that only contain alphanumerics are allowed ("localhost" for example)
     try:
@@ -438,6 +526,7 @@ class commonSettingsForm(Form):
     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()])
     webdriver_delay = IntegerField('Wait seconds before extracting text', validators=[validators.Optional(), validators.NumberRange(min=1, message="Should contain one or more seconds")])
 
 
@@ -448,7 +537,6 @@ class importForm(Form):
     xlsx_file = FileField('Upload .xlsx file', validators=[FileAllowed(['xlsx'], 'Must be .xlsx file!')])
     file_mapping = SelectField('File mapping', [validators.DataRequired()], choices={('wachete', 'Wachete mapping'), ('custom','Custom mapping')})
 
-
 class SingleBrowserStep(Form):
 
     operation = SelectField('Operation', [validators.Optional()], choices=browser_step_ui_config.keys())
@@ -466,6 +554,9 @@ class processor_text_json_diff_form(commonSettingsForm):
     tags = StringTagUUID('Group tag', [validators.Optional()], default='')
 
     time_between_check = FormField(TimeBetweenCheckForm)
+
+    time_schedule_limit = FormField(ScheduleLimitForm)
+
     time_between_check_use_default = BooleanField('Use global settings for time between check', default=False)
 
     include_filters = StringListField('CSS/JSONPath/JQ/XPath Filters', [ValidateCSSJSONXPATHInput()], default='')
@@ -515,6 +606,7 @@ class processor_text_json_diff_form(commonSettingsForm):
         if not super().validate():
             return False
 
+        from changedetectionio.safe_jinja import render as jinja_render
         result = True
 
         # Fail form validation when a body is set for a GET
@@ -524,20 +616,65 @@ class processor_text_json_diff_form(commonSettingsForm):
 
         # Attempt to validate jinja2 templates in the URL
         try:
-            from changedetectionio.safe_jinja import render as jinja_render
             jinja_render(template_str=self.url.data)
         except ModuleNotFoundError as e:
             # incase jinja2_time or others is missing
             logger.error(e)
-            self.url.errors.append(e)
+            self.url.errors.append(f'Invalid template syntax configuration: {e}')
             result = False
         except Exception as e:
             logger.error(e)
-            self.url.errors.append('Invalid template syntax')
+            self.url.errors.append(f'Invalid template syntax: {e}')
             result = False
 
+        # Attempt to validate jinja2 templates in the body
+        if self.body.data and self.body.data.strip():
+            try:
+                jinja_render(template_str=self.body.data)
+            except ModuleNotFoundError as e:
+                # incase jinja2_time or others is missing
+                logger.error(e)
+                self.body.errors.append(f'Invalid template syntax configuration: {e}')
+                result = False
+            except Exception as e:
+                logger.error(e)
+                self.body.errors.append(f'Invalid template syntax: {e}')
+                result = False
+
+        # Attempt to validate jinja2 templates in the headers
+        if len(self.headers.data) > 0:
+            try:
+                for header, value in self.headers.data.items():
+                    jinja_render(template_str=value)
+            except ModuleNotFoundError as e:
+                # incase jinja2_time or others is missing
+                logger.error(e)
+                self.headers.errors.append(f'Invalid template syntax configuration: {e}')
+                result = False
+            except Exception as e:
+                logger.error(e)
+                self.headers.errors.append(f'Invalid template syntax in "{header}" header: {e}')
+                result = False
+
         return result
 
+    def __init__(
+            self,
+            formdata=None,
+            obj=None,
+            prefix="",
+            data=None,
+            meta=None,
+            **kwargs,
+    ):
+        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')
+            if default_tz:
+                self.time_schedule_limit.form.timezone.render_kw['placeholder'] = default_tz
+
+
+
 class SingleExtraProxy(Form):
 
     # maybe better to set some <script>var..
@@ -558,6 +695,7 @@ class DefaultUAInputForm(Form):
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
     time_between_check = FormField(TimeBetweenCheckForm)
+    time_schedule_limit = FormField(ScheduleLimitForm)
     proxy = RadioField('Proxy')
     jitter_seconds = IntegerField('Random jitter seconds ± check',
                                   render_kw={"style": "width: 5em;"},

changedetectionio/html_tools.py

@@ -54,29 +54,64 @@ def include_filters(include_filters, html_content, append_pretty_line_formatting
 def subtractive_css_selector(css_selector, html_content):
     from bs4 import BeautifulSoup
     soup = BeautifulSoup(html_content, "html.parser")
-    for item in soup.select(css_selector):
+
+    # 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)
+
+    # Then, remove them in a separate loop
+    for item in elements_to_remove:
         item.decompose()
+
     return str(soup)
 
-def subtractive_xpath_selector(xpath_selector, html_content): 
+def subtractive_xpath_selector(selectors: List[str], html_content: str) -> str:
+    # Parse the HTML content using lxml
     html_tree = etree.HTML(html_content)
-    elements_to_remove = html_tree.xpath(xpath_selector)
 
+    # First, collect all elements to remove
+    elements_to_remove = []
+
+    # Iterate over the list of XPath selectors
+    for selector in selectors:
+        # Collect elements for each selector
+        elements_to_remove.extend(html_tree.xpath(selector))
+
+    # Then, remove them in a separate loop
     for element in elements_to_remove:
-        element.getparent().remove(element)
+        if element.getparent() is not None:  # Ensure the element has a parent before removing
+            element.getparent().remove(element)
 
+    # Convert the modified HTML tree back to a string
     modified_html = etree.tostring(html_tree, method="html").decode("utf-8")
     return modified_html
 
+
 def element_removal(selectors: List[str], html_content):
-    """Removes elements that match a list of CSS or xPath selectors."""
+    """Removes elements that match a list of CSS or XPath selectors."""
     modified_html = html_content
+    css_selectors = []
+    xpath_selectors = []
+
     for selector in selectors:
         if selector.startswith(('xpath:', 'xpath1:', '//')):
+            # Handle XPath selectors separately
             xpath_selector = selector.removeprefix('xpath:').removeprefix('xpath1:')
-            modified_html = subtractive_xpath_selector(xpath_selector, modified_html)
+            xpath_selectors.append(xpath_selector)
         else:
-            modified_html = subtractive_css_selector(selector, modified_html)
+            # Collect CSS selectors as one "hit", see comment in subtractive_css_selector
+            css_selectors.append(selector.strip().strip(","))
+
+    if xpath_selectors:
+        modified_html = subtractive_xpath_selector(xpath_selectors, modified_html)
+
+    if css_selectors:
+        # Remove duplicates, then combine all CSS selectors into one string, separated by commas
+        # This stops the elements index shifting
+        unique_selectors = list(set(css_selectors))  # Ensure uniqueness
+        combined_css_selector = " , ".join(unique_selectors)
+        modified_html = subtractive_css_selector(combined_css_selector, modified_html)
+
+
     return modified_html
 
 def elementpath_tostring(obj):

changedetectionio/model/App.py

@@ -52,7 +52,8 @@ class model(dict):
                     'schema_version' : 0,
                     'shared_diff_access': False,
                     'webdriver_delay': None , # Extra delay in seconds before extracting text
-                    'tags': {} #@todo use Tag.model initialisers
+                    'tags': {}, #@todo use Tag.model initialisers
+                    'timezone': None, # Default IANA timezone name
                 }
             }
         }

changedetectionio/model/Watch.py

@@ -89,6 +89,10 @@ class model(watch_base):
 
         if ready_url.startswith('source:'):
             ready_url=ready_url.replace('source:', '')
+
+        # Also double check it after any Jinja2 formatting just incase
+        if not is_safe_url(ready_url):
+            return 'DISABLED'
         return ready_url
 
     def clear_watch(self):
@@ -335,7 +339,6 @@ class model(watch_base):
         # @todo bump static cache of the last timestamp so we dont need to examine the file to set a proper ''viewed'' status
         return snapshot_fname
 
-    @property
     @property
     def has_empty_checktime(self):
         # using all() + dictionary comprehension
@@ -534,16 +537,17 @@ class model(watch_base):
 
     def save_xpath_data(self, data, as_error=False):
         import json
+        import zlib
 
         if as_error:
-            target_path = os.path.join(self.watch_data_dir, "elements-error.json")
+            target_path = os.path.join(str(self.watch_data_dir), "elements-error.deflate")
         else:
-            target_path = os.path.join(self.watch_data_dir, "elements.json")
+            target_path = os.path.join(str(self.watch_data_dir), "elements.deflate")
 
         self.ensure_data_dir_exists()
 
-        with open(target_path, 'w') as f:
-            f.write(json.dumps(data))
+        with open(target_path, 'wb') as f:
+            f.write(zlib.compress(json.dumps(data).encode()))
             f.close()
 
     # Save as PNG, PNG is larger but better for doing visual diff in the future

changedetectionio/model/__init__.py

@@ -59,6 +59,65 @@ class watch_base(dict):
             'text_should_not_be_present': [],  # Text that should not present
             'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
             'time_between_check_use_default': True,
+            "time_schedule_limit": {
+                "enabled": False,
+                "monday": {
+                    "enabled": True,
+                    "start_time": "00:00",
+                    "duration": {
+                        "hours": "24",
+                        "minutes": "00"
+                    }
+                },
+                "tuesday": {
+                    "enabled": True,
+                    "start_time": "00:00",
+                    "duration": {
+                        "hours": "24",
+                        "minutes": "00"
+                    }
+                },
+                "wednesday": {
+                    "enabled": True,
+                    "start_time": "00:00",
+                    "duration": {
+                        "hours": "24",
+                        "minutes": "00"
+                    }
+                },
+                "thursday": {
+                    "enabled": True,
+                    "start_time": "00:00",
+                    "duration": {
+                        "hours": "24",
+                        "minutes": "00"
+                    }
+                },
+                "friday": {
+                    "enabled": True,
+                    "start_time": "00:00",
+                    "duration": {
+                        "hours": "24",
+                        "minutes": "00"
+                    }
+                },
+                "saturday": {
+                    "enabled": True,
+                    "start_time": "00:00",
+                    "duration": {
+                        "hours": "24",
+                        "minutes": "00"
+                    }
+                },
+                "sunday": {
+                    "enabled": True,
+                    "start_time": "00:00",
+                    "duration": {
+                        "hours": "24",
+                        "minutes": "00"
+                    }
+                },
+            },
             'title': None,
             'track_ldjson_price_data': None,
             'trim_text_whitespace': False,

changedetectionio/notification.py

@@ -23,7 +23,7 @@ valid_tokens = {
 }
 
 default_notification_format_for_watch = 'System default'
-default_notification_format = 'Text'
+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}}'
 
@@ -31,6 +31,7 @@ valid_notification_formats = {
     'Text': NotifyFormat.TEXT,
     'Markdown': NotifyFormat.MARKDOWN,
     'HTML': NotifyFormat.HTML,
+    'HTML Color': 'htmlcolor',
     # Used only for editing a watch (not for global)
     default_notification_format_for_watch: default_notification_format_for_watch
 }
@@ -76,9 +77,16 @@ def process_notification(n_object, datastore):
 
             # 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'):
+                n_body = n_body.replace("\n", '<br>')
+
             n_title = jinja_render(template_str=n_object.get('notification_title', ''), **notification_parameters)
 
             url = url.strip()
+            if url.startswith('#'):
+                logger.trace(f"Skipping commented out notification URL - {url}")
+                continue
+
             if not url:
                 logger.warning(f"Process Notification: skipping empty notification URL.")
                 continue

changedetectionio/processors/__init__.py

@@ -31,15 +31,15 @@ class difference_detection_processor():
 
         from requests.structures import CaseInsensitiveDict
 
-        # Protect against file:// access
-        if re.search(r'^file://', self.watch.get('url', '').strip(), re.IGNORECASE):
+        url = self.watch.link
+
+        # Protect against file:, file:/, file:// access, check the real "link" without any meta "source:" etc prepended.
+        if re.search(r'^file:', url.strip(), re.IGNORECASE):
             if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
                 raise Exception(
                     "file:// type access is denied for security reasons."
                 )
 
-        url = self.watch.link
-
         # Requests, playwright, other browser via wss:// etc, fetch_extra_something
         prefer_fetch_backend = self.watch.get('fetch_backend', 'system')
 
@@ -102,6 +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
         request_headers = CaseInsensitiveDict()
 
         ua = self.datastore.data['settings']['requests'].get('default_ua')
@@ -118,9 +119,15 @@ class difference_detection_processor():
         if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
             request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
 
+        for header_name in request_headers:
+            request_headers.update({header_name: jinja_render(template_str=request_headers.get(header_name))})
+
         timeout = self.datastore.data['settings']['requests'].get('timeout')
 
         request_body = self.watch.get('body')
+        if request_body:
+            request_body = jinja_render(template_str=self.watch.get('body'))
+        
         request_method = self.watch.get('method')
         ignore_status_codes = self.watch.get('ignore_status_codes', False)
 

changedetectionio/processors/restock_diff/processor.py

@@ -40,7 +40,7 @@ def _deduplicate_prices(data):
 
         if isinstance(datum.value, list):
             # Process each item in the list
-            normalized_value = set([float(re.sub(r'[^\d.]', '', str(item))) for item in datum.value])
+            normalized_value = set([float(re.sub(r'[^\d.]', '', str(item))) for item in datum.value if str(item).strip()])
             unique_data.update(normalized_value)
         else:
             # Process single value

changedetectionio/static/images/schedule.svg

@@ -0,0 +1,225 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   version="1.1"
+   id="Layer_1"
+   x="0px"
+   y="0px"
+   viewBox="0 0 661.20001 665.40002"
+   xml:space="preserve"
+   width="661.20001"
+   height="665.40002"
+   inkscape:version="1.1.2 (0a00cf5339, 2022-02-04)"
+   sodipodi:docname="schedule.svg"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg"><defs
+   id="defs77" /><sodipodi:namedview
+   id="namedview75"
+   pagecolor="#ffffff"
+   bordercolor="#666666"
+   borderopacity="1.0"
+   inkscape:pageshadow="2"
+   inkscape:pageopacity="0.0"
+   inkscape:pagecheckerboard="0"
+   showgrid="false"
+   fit-margin-top="0"
+   fit-margin-left="0"
+   fit-margin-right="0"
+   fit-margin-bottom="0"
+   inkscape:zoom="1.2458671"
+   inkscape:cx="300.59386"
+   inkscape:cy="332.29869"
+   inkscape:window-width="1920"
+   inkscape:window-height="1051"
+   inkscape:window-x="1920"
+   inkscape:window-y="0"
+   inkscape:window-maximized="1"
+   inkscape:current-layer="g72" /> <style
+   type="text/css"
+   id="style2"> .st0{fill:#FFFFFF;} .st1{fill:#C1272D;} .st2{fill:#991D26;} .st3{fill:#CCCCCC;} .st4{fill:#E6E6E6;} .st5{fill:#F7931E;} .st6{fill:#F2F2F2;} .st7{fill:none;stroke:#999999;stroke-width:17.9763;stroke-linecap:round;stroke-miterlimit:10;} .st8{fill:none;stroke:#333333;stroke-width:8.9882;stroke-linecap:round;stroke-miterlimit:10;} .st9{fill:none;stroke:#C1272D;stroke-width:5.9921;stroke-linecap:round;stroke-miterlimit:10;} .st10{fill:#245F7F;} </style> <g
+   id="g72"
+   transform="translate(-149.4,-147.3)"> <path
+   class="st0"
+   d="M 601.2,699.8 H 205 c -30.7,0 -55.6,-24.9 -55.6,-55.6 V 248 c 0,-30.7 24.9,-55.6 55.6,-55.6 h 396.2 c 30.7,0 55.6,24.9 55.6,55.6 v 396.2 c 0,30.7 -24.9,55.6 -55.6,55.6 z"
+   id="path4"
+   style="fill:#dfdfdf;fill-opacity:1" /> <path
+   class="st1"
+   d="M 601.2,192.4 H 205 c -30.7,0 -55.6,24.9 -55.6,55.6 v 88.5 H 656.8 V 248 c 0,-30.7 -24.9,-55.6 -55.6,-55.6 z"
+   id="path6"
+   style="fill:#d62128;fill-opacity:1" /> <circle
+   class="st2"
+   cx="253.3"
+   cy="264.5"
+   r="36.700001"
+   id="circle8" /> <circle
+   class="st2"
+   cx="551.59998"
+   cy="264.5"
+   r="36.700001"
+   id="circle10" /> <path
+   class="st3"
+   d="m 253.3,275.7 v 0 c -11.8,0 -21.3,-9.6 -21.3,-21.3 v -85.8 c 0,-11.8 9.6,-21.3 21.3,-21.3 v 0 c 11.8,0 21.3,9.6 21.3,21.3 v 85.8 c 0,11.8 -9.5,21.3 -21.3,21.3 z"
+   id="path12" /> <path
+   class="st3"
+   d="m 551.6,275.7 v 0 c -11.8,0 -21.3,-9.6 -21.3,-21.3 v -85.8 c 0,-11.8 9.6,-21.3 21.3,-21.3 v 0 c 11.8,0 21.3,9.6 21.3,21.3 v 85.8 c 0.1,11.8 -9.5,21.3 -21.3,21.3 z"
+   id="path14" /> <rect
+   x="215.7"
+   y="370.89999"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect16"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="313"
+   y="370.89999"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect18"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="410.20001"
+   y="370.89999"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect20"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="507.5"
+   y="370.89999"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect22"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="215.7"
+   y="465"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect24"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="313"
+   y="465"
+   class="st1"
+   width="75.199997"
+   height="75.199997"
+   id="rect26"
+   style="fill:#27c12b;fill-opacity:1" /> <rect
+   x="410.20001"
+   y="465"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect28"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="507.5"
+   y="465"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect30" /> <rect
+   x="215.7"
+   y="559.09998"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect32"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="313"
+   y="559.09998"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect34"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="410.20001"
+   y="559.09998"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect36"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="507.5"
+   y="559.09998"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect38" /> <g
+   id="g70"> <circle
+   class="st5"
+   cx="621.90002"
+   cy="624"
+   r="188.7"
+   id="circle40" /> <circle
+   class="st0"
+   cx="621.90002"
+   cy="624"
+   r="148"
+   id="circle42" /> <path
+   class="st6"
+   d="m 486.6,636.8 c 0,-81.7 66.3,-148 148,-148 37.6,0 72,14.1 98.1,37.2 -27.1,-30.6 -66.7,-49.9 -110.8,-49.9 -81.7,0 -148,66.3 -148,148 0,44.1 19.3,83.7 49.9,110.8 -23.1,-26.2 -37.2,-60.5 -37.2,-98.1 z"
+   id="path44" /> <polyline
+   class="st7"
+   points="621.9,530.4 621.9,624 559,624  "
+   id="polyline46" /> <g
+   id="g64"> <line
+   class="st8"
+   x1="621.90002"
+   y1="508.29999"
+   x2="621.90002"
+   y2="497.10001"
+   id="line48" /> <line
+   class="st8"
+   x1="621.90002"
+   y1="756.29999"
+   x2="621.90002"
+   y2="745.09998"
+   id="line50" /> <line
+   class="st8"
+   x1="740.29999"
+   y1="626.70001"
+   x2="751.5"
+   y2="626.70001"
+   id="line52" /> <line
+   class="st8"
+   x1="492.29999"
+   y1="626.70001"
+   x2="503.5"
+   y2="626.70001"
+   id="line54" /> <line
+   class="st8"
+   x1="705.59998"
+   y1="710.40002"
+   x2="713.5"
+   y2="718.29999"
+   id="line56" /> <line
+   class="st8"
+   x1="530.29999"
+   y1="535.09998"
+   x2="538.20001"
+   y2="543"
+   id="line58" /> <line
+   class="st8"
+   x1="538.20001"
+   y1="710.40002"
+   x2="530.29999"
+   y2="718.29999"
+   id="line60" /> <line
+   class="st8"
+   x1="713.5"
+   y1="535.09998"
+   x2="705.59998"
+   y2="543"
+   id="line62" /> </g> <line
+   class="st9"
+   x1="604.40002"
+   y1="606.29999"
+   x2="684.5"
+   y2="687.40002"
+   id="line66" /> <circle
+   class="st10"
+   cx="621.90002"
+   cy="624"
+   r="16.1"
+   id="circle68" /> </g> </g> </svg>

changedetectionio/static/js/global-settings.js

@@ -24,5 +24,19 @@ $(document).ready(function () {
         $(target).toggle();
     });
 
+    // Time zone config related
+    $(".local-time").each(function (e) {
+        $(this).text(new Date($(this).data("utc")).toLocaleString());
+    })
+
+    const timezoneInput = $('#application-timezone');
+    if(timezoneInput.length) {
+        const timezone = Intl.DateTimeFormat().resolvedOptions().timeZone;
+        if (!timezoneInput.val().trim()) {
+            timezoneInput.val(timezone);
+            timezoneInput.after('<div class="timezone-message">The timezone was set from your browser, <strong>be sure to press save!</strong></div>');
+        }
+    }
+
 });
 

changedetectionio/static/js/plugins.js

@@ -159,4 +159,38 @@
         // Return the current request in case it's needed
         return requests[namespace];
     };
-})(jQuery);
+})(jQuery);
+
+
+
+function toggleOpacity(checkboxSelector, fieldSelector, inverted) {
+    const checkbox = document.querySelector(checkboxSelector);
+    const fields = document.querySelectorAll(fieldSelector);
+
+    function updateOpacity() {
+        const opacityValue = !checkbox.checked ? (inverted ? 0.6 : 1) : (inverted ? 1 : 0.6);
+        fields.forEach(field => {
+            field.style.opacity = opacityValue;
+        });
+    }
+
+    // Initial setup
+    updateOpacity();
+    checkbox.addEventListener('change', updateOpacity);
+}
+
+function toggleVisibility(checkboxSelector, fieldSelector, inverted) {
+    const checkbox = document.querySelector(checkboxSelector);
+    const fields = document.querySelectorAll(fieldSelector);
+
+    function updateOpacity() {
+        const opacityValue = !checkbox.checked ? (inverted ? 'none' : 'block') : (inverted ? 'block' : 'none');
+        fields.forEach(field => {
+            field.style.display = opacityValue;
+        });
+    }
+
+    // Initial setup
+    updateOpacity();
+    checkbox.addEventListener('change', updateOpacity);
+}

changedetectionio/static/js/scheduler.js

@@ -0,0 +1,109 @@
+function getTimeInTimezone(timezone) {
+    const now = new Date();
+    const options = {
+        timeZone: timezone,
+        weekday: 'long',
+        year: 'numeric',
+        hour12: false,
+        month: '2-digit',
+        day: '2-digit',
+        hour: '2-digit',
+        minute: '2-digit',
+        second: '2-digit',
+    };
+
+    const formatter = new Intl.DateTimeFormat('en-US', options);
+    return formatter.format(now);
+}
+
+$(document).ready(function () {
+
+    let exceedsLimit = false;
+    const warning_text = $("#timespan-warning")
+    const timezone_text_widget = $("input[id*='time_schedule_limit-timezone']")
+
+    toggleVisibility('#time_schedule_limit-enabled, #requests-time_schedule_limit-enabled', '#schedule-day-limits-wrapper', true)
+
+    setInterval(() => {
+        let success = true;
+        try {
+            // Show the current local time according to either placeholder or entered TZ name
+            if (timezone_text_widget.val().length) {
+                $('#local-time-in-tz').text(getTimeInTimezone(timezone_text_widget.val()));
+            } else {
+                // So maybe use what is in the placeholder (which will be the default settings)
+                $('#local-time-in-tz').text(getTimeInTimezone(timezone_text_widget.attr('placeholder')));
+            }
+        } catch (error) {
+            success = false;
+            $('#local-time-in-tz').text("");
+            console.error(timezone_text_widget.val())
+        }
+
+        $(timezone_text_widget).toggleClass('error', !success);
+
+    }, 500);
+
+    $('#schedule-day-limits-wrapper').on('change click blur', 'input, checkbox, select', function() {
+
+        let allOk = true;
+
+        // Controls setting the warning that the time could overlap into the next day
+        $("li.day-schedule").each(function () {
+            const $schedule = $(this);
+            const $checkbox = $schedule.find("input[type='checkbox']");
+
+            if ($checkbox.is(":checked")) {
+                const timeValue = $schedule.find("input[type='time']").val();
+                const durationHours = parseInt($schedule.find("select[name*='-duration-hours']").val(), 10) || 0;
+                const durationMinutes = parseInt($schedule.find("select[name*='-duration-minutes']").val(), 10) || 0;
+
+                if (timeValue) {
+                    const [startHours, startMinutes] = timeValue.split(":").map(Number);
+                    const totalMinutes = (startHours * 60 + startMinutes) + (durationHours * 60 + durationMinutes);
+
+                    exceedsLimit = totalMinutes > 1440
+                    if (exceedsLimit) {
+                        allOk = false
+                    }
+                    // Set the row/day-of-week highlight
+                    $schedule.toggleClass("warning", exceedsLimit);
+                }
+            } else {
+                $schedule.toggleClass("warning", false);
+            }
+        });
+
+        warning_text.toggle(!allOk)
+    });
+
+    $('table[id*="time_schedule_limit-saturday"], table[id*="time_schedule_limit-sunday"]').addClass("weekend-day")
+
+    // Presets [weekend] [business hours] etc
+    $(document).on('click', '[data-template].set-schedule', function () {
+        // Get the value of the 'data-template' attribute
+        switch ($(this).attr('data-template')) {
+            case 'business-hours':
+                $('.day-schedule table:not(.weekend-day) input[type="time"]').val('09:00')
+                $('.day-schedule table:not(.weekend-day) select[id*="-duration-hours"]').val('8');
+                $('.day-schedule table:not(.weekend-day) select[id*="-duration-minutes"]').val('0');
+                $('.day-schedule input[id*="-enabled"]').prop('checked', true);
+                $('.day-schedule .weekend-day input[id*="-enabled"]').prop('checked', false);
+                break;
+            case 'weekend':
+                $('.day-schedule .weekend-day input[type="time"][id$="start-time"]').val('00:00')
+                $('.day-schedule .weekend-day select[id*="-duration-hours"]').val('24');
+                $('.day-schedule .weekend-day select[id*="-duration-minutes"]').val('0');
+                $('.day-schedule input[id*="-enabled"]').prop('checked', false);
+                $('.day-schedule .weekend-day input[id*="-enabled"]').prop('checked', true);
+                break;
+            case 'reset':
+
+                $('.day-schedule input[type="time"]').val('00:00')
+                $('.day-schedule select[id*="-duration-hours"]').val('24');
+                $('.day-schedule select[id*="-duration-minutes"]').val('0');
+                $('.day-schedule input[id*="-enabled"]').prop('checked', true);
+                break;
+        }
+    });
+});

changedetectionio/static/js/visual-selector.js

@@ -132,6 +132,7 @@ $(document).ready(() => {
         }).done((data) => {
             $fetchingUpdateNoticeElem.html("Rendering..");
             selectorData = data;
+
             sortScrapedElementsBySize();
             console.log(`Reported browser width from backend: ${data['browser_width']}`);
 

changedetectionio/static/js/watch-settings.js

@@ -1,17 +1,3 @@
-function toggleOpacity(checkboxSelector, fieldSelector, inverted) {
-    const checkbox = document.querySelector(checkboxSelector);
-    const fields = document.querySelectorAll(fieldSelector);
-    function updateOpacity() {
-        const opacityValue = !checkbox.checked ? (inverted ? 0.6 : 1) : (inverted ? 1 : 0.6);
-        fields.forEach(field => {
-            field.style.opacity = opacityValue;
-        });
-    }
-    // Initial setup
-    updateOpacity();
-    checkbox.addEventListener('change', updateOpacity);
-}
-
 
 function request_textpreview_update() {
     if (!$('body').hasClass('preview-text-enabled')) {
@@ -57,7 +43,9 @@ function request_textpreview_update() {
     })
 }
 
+
 $(document).ready(function () {
+
     $('#notification-setting-reset-to-default').click(function (e) {
         $('#notification_title').val('');
         $('#notification_body').val('');
@@ -70,11 +58,12 @@ $(document).ready(function () {
         $('#notification-tokens-info').toggle();
     });
 
-    toggleOpacity('#time_between_check_use_default', '#time_between_check', false);
+    toggleOpacity('#time_between_check_use_default', '#time-check-widget-wrapper, #time-between-check-schedule', false);
+
 
     const vh = Math.max(document.documentElement.clientHeight || 0, window.innerHeight || 0);
-    $("#text-preview-inner").css('max-height', (vh-300)+"px");
-    $("#text-preview-before-inner").css('max-height', (vh-300)+"px");
+    $("#text-preview-inner").css('max-height', (vh - 300) + "px");
+    $("#text-preview-before-inner").css('max-height', (vh - 300) + "px");
 
     $("#activate-text-preview").click(function (e) {
         $('body').toggleClass('preview-text-enabled')

changedetectionio/store.py

@@ -374,7 +374,7 @@ class ChangeDetectionStore:
     def visualselector_data_is_ready(self, watch_uuid):
         output_path = "{}/{}".format(self.datastore_path, watch_uuid)
         screenshot_filename = "{}/last-screenshot.png".format(output_path)
-        elements_index_filename = "{}/elements.json".format(output_path)
+        elements_index_filename = "{}/elements.deflate".format(output_path)
         if path.isfile(screenshot_filename) and  path.isfile(elements_index_filename) :
             return True
 
@@ -909,3 +909,18 @@ class ChangeDetectionStore:
             if self.data['watching'][uuid].get('in_stock_only'):
                 del (self.data['watching'][uuid]['in_stock_only'])
 
+    # Compress old elements.json to elements.deflate, saving disk, this compression is pretty fast.
+    def update_19(self):
+        import zlib
+
+        for uuid, watch in self.data['watching'].items():
+            json_path = os.path.join(self.datastore_path, uuid, "elements.json")
+            deflate_path = os.path.join(self.datastore_path, uuid, "elements.deflate")
+
+            if os.path.exists(json_path):
+                with open(json_path, "rb") as f_j:
+                    with open(deflate_path, "wb") as f_d:
+                        logger.debug(f"Compressing {str(json_path)} to {str(deflate_path)}..")
+                        f_d.write(zlib.compress(f_j.read()))
+                        os.unlink(json_path)
+

changedetectionio/templates/_helpers.html

@@ -59,4 +59,100 @@
 
 {% macro render_button(field) %}
   {{ field(**kwargs)|safe }}
+{% endmacro %}
+
+{% macro render_time_schedule_form(form, available_timezones, timezone_default_config) %}
+    <style>
+    .day-schedule *, .day-schedule select {
+        display: inline-block;
+    }
+
+    .day-schedule label[for*="time_schedule_limit-"][for$="-enabled"] {
+        min-width: 6rem;
+        font-weight: bold;
+    }
+    .day-schedule label {
+        font-weight: normal;
+    }
+
+    .day-schedule table label {
+        padding-left: 0.5rem;
+        padding-right: 0.5rem;
+    }
+    #timespan-warning, input[id*='time_schedule_limit-timezone'].error {
+        color: #ff0000;
+    }
+    .day-schedule.warning table {
+        background-color: #ffbbc2;
+    }
+    ul#day-wrapper {
+        list-style: none;
+    }
+    #timezone-info > * {
+        display: inline-block;
+    }
+
+    #scheduler-icon-label {
+        background-position: left center;
+        background-repeat: no-repeat;
+        background-size: contain;
+        display: inline-block;
+        vertical-align: middle;
+        padding-left: 50px;
+        background-image: url({{ url_for('static_content', group='images', filename='schedule.svg') }});
+    }
+    #timespan-warning {
+        display: none;
+    }
+    </style>
+    <br>
+
+    {% if timezone_default_config %}
+    <div>
+        <span id="scheduler-icon-label" style="">
+            {{ render_checkbox_field(form.time_schedule_limit.enabled) }}
+            <div class="pure-form-message-inline">
+                Set a hourly/week day schedule
+            </div>
+        </span>
+
+    </div>
+    <br>
+    <div id="schedule-day-limits-wrapper">
+        <label>Schedule time limits</label><a data-template="business-hours"
+                                              class="set-schedule pure-button button-secondary button-xsmall">Business
+        hours</a>
+        <a data-template="weekend" class="set-schedule pure-button button-secondary button-xsmall">Weekends</a>
+        <a data-template="reset" class="set-schedule pure-button button-xsmall">Reset</a><br>
+        <br>
+
+        <ul id="day-wrapper">
+            {% for day in ['monday', 'tuesday', 'wednesday', 'thursday', 'friday', 'saturday', 'sunday'] %}
+                <li class="day-schedule" id="schedule-{{ day }}">
+                    {{ render_nolabel_field(form.time_schedule_limit[day]) }}
+                </li>
+            {% endfor %}
+            <li id="timespan-warning">Warning, one or more of your 'days' has a duration that would extend into the next day.<br>
+            This could have unintended consequences.</li>
+            <li id="timezone-info">
+                {{ render_field(form.time_schedule_limit.timezone, placeholder=timezone_default_config) }} <span id="local-time-in-tz"></span>
+                <datalist id="timezones" style="display: none;">
+                    {% for timezone in available_timezones %}
+                        <option value="{{ timezone }}">{{ timezone }}</option>
+                    {% endfor %}
+                </datalist>
+            </li>
+        </ul>
+    <br>
+        <span class="pure-form-message-inline">
+         <a href="https://changedetection.io/tutorials">More help and examples about using the scheduler</a>
+        </span>
+    </div>
+    {% else %}
+        <span class="pure-form-message-inline">
+            Want to use a time schedule? <a href="{{url_for('settings_page')}}#timedate">First confirm/save your Time Zone Settings</a>
+        </span>
+        <br>
+    {% endif %}
+
 {% endmacro %}

changedetectionio/templates/base.html

@@ -70,7 +70,7 @@
                 <a href="{{ url_for('import_page')}}" class="pure-menu-link">IMPORT</a>
               </li>
               <li class="pure-menu-item">
-                <a href="{{ url_for('get_backup')}}" class="pure-menu-link">BACKUP</a>
+                <a href="{{ url_for('backups.index')}}" class="pure-menu-link">BACKUPS</a>
               </li>
             {% else %}
               <li class="pure-menu-item">

changedetectionio/templates/edit.html

@@ -1,10 +1,11 @@
 {% 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_time_schedule_form %}
 {% 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>
 <script src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='scheduler.js')}}" defer></script>
 <script>
     const browser_steps_available_screenshots=JSON.parse('{{ watch.get_browsersteps_available_screenshots|tojson }}');
     const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
@@ -58,15 +59,15 @@
 
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked"
-              action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next'), unpause_on_save = request.args.get('unpause_on_save')) }}" method="POST">
+              action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next'), unpause_on_save = request.args.get('unpause_on_save'), tag = request.args.get('tag')) }}" method="POST">
              <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
 
             <div class="tab-pane-inner" id="general">
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.url, placeholder="https://...", required=true, class="m-d") }}
-                        <span class="pure-form-message-inline">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></span><br>
-                        <span class="pure-form-message-inline">You can use variables in the URL, perfect for inserting the current date and other logic, <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a></span><br>
+                        <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 inline-radio">
                         {{ render_field(form.processor) }}
@@ -79,9 +80,24 @@
                         <span class="pure-form-message-inline">Organisational tag/group name used in the main listing page</span>
                     </div>
                     <div class="pure-control-group time-between-check border-fieldset">
-                        {{ render_field(form.time_between_check, class="time-check-widget") }}
+
                         {{ render_checkbox_field(form.time_between_check_use_default, class="use-default-timecheck") }}
-                    </div>
+                        <br>
+                        <div id="time-check-widget-wrapper">
+                            {{ render_field(form.time_between_check, class="time-check-widget") }}
+
+                            <span class="pure-form-message-inline">
+                             The interval/amount of time between each check.
+                            </span>
+                        </div>
+                        <div id="time-between-check-schedule">
+                            <!-- Start Time and End Time -->
+                            <div id="limit-between-time">
+                                {{ render_time_schedule_form(form, available_timezones, timezone_default_config) }}
+                            </div>
+                        </div>
+<br>
+              </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.extract_title_as_title) }}
                     </div>
@@ -149,21 +165,24 @@
                             {{ render_field(form.method) }}
                         </div>
                         <div id="request-body">
-                                            {{ render_field(form.body, rows=5, placeholder="Example
+                                            {{ render_field(form.body, rows=7, placeholder="Example
 {
    \"name\":\"John\",
    \"age\":30,
-   \"car\":null
+   \"car\":null,
+   \"year\":{% now 'Europe/Berlin', '%Y' %}
 }") }}
                         </div>
+                        <div class="pure-form-message">Variables are supported in the request body (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
                     </div>
                 </fieldset>
             <!-- hmm -->
                 <div class="pure-control-group advanced-options"  style="display: none;">
-                    {{ render_field(form.headers, rows=5, placeholder="Example
+                    {{ render_field(form.headers, rows=7, placeholder="Example
 Cookie: foobar
-User-Agent: wonderbra 1.0") }}
-
+User-Agent: wonderbra 1.0
+Math: {{ 1 + 1 }}") }}
+                        <div class="pure-form-message">Variables are supported in the request header values (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
                         <div class="pure-form-message-inline">
                             {% if has_extra_headers_file %}
                                 <strong>Alert! Extra headers file found and will be added to this watch!</strong>

changedetectionio/templates/settings.html

@@ -1,7 +1,7 @@
 {% 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_time_schedule_form %}
 {% from '_common_fields.html' import render_common_settings_form %}
 <script>
     const notification_base_url="{{url_for('ajax_callback_send_notification_test', mode="global-settings")}}";
@@ -10,9 +10,11 @@
 {% endif %}
 </script>
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='plugins.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='vis.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='scheduler.js')}}" defer></script>
 <div class="edit-form">
     <div class="tabs collapsable">
         <ul>
@@ -21,6 +23,7 @@
             <li class="tab"><a href="#fetching">Fetching</a></li>
             <li class="tab"><a href="#filters">Global Filters</a></li>
             <li class="tab"><a href="#api">API</a></li>
+            <li class="tab"><a href="#timedate">Time &amp Date</a></li>
             <li class="tab"><a href="#proxies">CAPTCHA &amp; Proxies</a></li>
         </ul>
     </div>
@@ -32,6 +35,12 @@
                     <div class="pure-control-group">
                         {{ render_field(form.requests.form.time_between_check, class="time-check-widget") }}
                         <span class="pure-form-message-inline">Default recheck time for all watches, current system minimum is <i>{{min_system_recheck_seconds}}</i> seconds (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Misc-system-settings#enviroment-variables">more info</a>).</span>
+                            <div id="time-between-check-schedule">
+                                <!-- Start Time and End Time -->
+                                <div id="limit-between-time">
+                                    {{ render_time_schedule_form(form.requests, available_timezones, timezone_default_config) }}
+                                </div>
+                        </div>
                     </div>
                     <div class="pure-control-group">
                         {{ render_field(form.requests.form.jitter_seconds, class="jitter_seconds") }}
@@ -211,6 +220,23 @@ nav
                     </p>
                 </div>
             </div>
+            <div class="tab-pane-inner" id="timedate">
+                <div class="pure-control-group">
+                    Ensure the settings below are correct, they are used to manage the time schedule for checking your web page watches.
+                </div>
+                <div class="pure-control-group">
+                    <p><strong>UTC Time &amp Date from Server:</strong> <span id="utc-time" >{{ utc_time }}</span></p>
+                    <p><strong>Local Time &amp Date in Browser:</strong> <span class="local-time" data-utc="{{ utc_time }}"></span></p>
+                    <p>
+                       {{ render_field(form.application.form.timezone) }}
+                        <datalist id="timezones" style="display: none;">
+                            {% for tz_name in available_timezones %}
+                                <option value="{{ tz_name }}">{{ tz_name }}</option>
+                            {% endfor %}
+                        </datalist>
+                    </p>
+                </div>
+            </div>
             <div class="tab-pane-inner" id="proxies">
                 <div id="recommended-proxy">
                     <div>

changedetectionio/templates/watch-overview.html

@@ -6,7 +6,7 @@
 
 <div class="box">
 
-    <form class="pure-form" action="{{ url_for('form_quick_watch_add') }}" method="POST" id="new-watch-form">
+    <form class="pure-form" action="{{ url_for('form_quick_watch_add', tag=active_tag_uuid) }}" method="POST" id="new-watch-form">
         <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
         <fieldset>
             <legend>Add a new change detection watch</legend>
@@ -187,7 +187,7 @@
                 <td>
                     <a {% if watch.uuid in queued_uuids %}disabled="true"{% endif %} href="{{ url_for('form_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}"
                        class="recheck pure-button pure-button-primary">{% if watch.uuid in queued_uuids %}Queued{% else %}Recheck{% endif %}</a>
-                    <a href="{{ url_for('edit_page', uuid=watch.uuid)}}#general" class="pure-button pure-button-primary">Edit</a>
+                    <a href="{{ url_for('edit_page', uuid=watch.uuid, tag=active_tag_uuid)}}#general" class="pure-button pure-button-primary">Edit</a>
                     {% if watch.history_n >= 2 %}
 
                         {%  if is_unviewed %}

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -113,7 +113,8 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     res = client.post(
         url_for("settings_page"),
         data={"application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
-              "application-notification_body": 'triggered text was -{{triggered_text}}- 网站监测 内容更新了',
+              # triggered_text will contain multiple lines
+              "application-notification_body": 'triggered text was -{{triggered_text}}- ### 网站监测 内容更新了 ####',
               # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
               "application-notification_urls": test_notification_url,
               "application-minutes_between_check": 180,
@@ -171,7 +172,7 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     assert os.path.isfile("test-datastore/notification.txt"), "Notification fired because I can see the output file"
     with open("test-datastore/notification.txt", 'rb') as f:
         response = f.read()
-        assert b'-Oh yes please-' in response
+        assert b'-Oh yes please' in response
         assert '网站监测 内容更新了'.encode('utf-8') in response
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

changedetectionio/tests/test_backup.py

@@ -26,8 +26,24 @@ def test_backup(client, live_server, measure_memory_usage):
     assert b"1 Imported" in res.data
     wait_for_all_checks(client)
 
+    # Launch the thread in the background to create the backup
     res = client.get(
-        url_for("get_backup"),
+        url_for("backups.request_backup"),
+        follow_redirects=True
+    )
+    time.sleep(2)
+
+    res = client.get(
+        url_for("backups.index"),
+        follow_redirects=True
+    )
+    # Can see the download link to the backup
+    assert b'<a href="/backups/download/changedetection-backup-20' in res.data
+    assert b'Remove backups' in res.data
+
+    # Get the latest one
+    res = client.get(
+        url_for("backups.download_backup", filename="latest"),
         follow_redirects=True
     )
 
@@ -44,3 +60,11 @@ def test_backup(client, live_server, measure_memory_usage):
 
     # Should be two txt files in the archive (history and the snapshot)
     assert len(newlist) == 2
+
+    # Get the latest one
+    res = client.get(
+        url_for("backups.remove_backups"),
+        follow_redirects=True
+    )
+
+    assert b'No backups found.' in res.data

changedetectionio/tests/test_css_selector.py

@@ -125,8 +125,7 @@ def test_check_markup_include_filters_restriction(client, live_server, measure_m
 
 # Tests the whole stack works with the CSS Filter
 def test_check_multiple_filters(client, live_server, measure_memory_usage):
-    sleep_time_for_fetch_thread = 3
-
+    #live_server_setup(live_server)
     include_filters = "#blob-a\r\nxpath://*[contains(@id,'blob-b')]"
 
     with open("test-datastore/endpoint-content.txt", "w") as f:
@@ -138,9 +137,6 @@ def test_check_multiple_filters(client, live_server, measure_memory_usage):
      </html>
     """)
 
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(
@@ -149,7 +145,7 @@ def test_check_multiple_filters(client, live_server, measure_memory_usage):
         follow_redirects=True
     )
     assert b"1 Imported" in res.data
-    time.sleep(1)
+    wait_for_all_checks(client)
 
     # Goto the edit page, add our ignore text
     # Add our URL to the import page
@@ -165,7 +161,7 @@ def test_check_multiple_filters(client, live_server, measure_memory_usage):
     assert b"Updated watch." in res.data
 
     # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     res = client.get(
         url_for("preview_page", uuid="first"),

changedetectionio/tests/test_element_removal.py

@@ -11,6 +11,35 @@ from .util import live_server_setup, wait_for_all_checks
 def test_setup(live_server):
     live_server_setup(live_server)
 
+def set_response_with_multiple_index():
+    data= """<!DOCTYPE html>
+<html>
+<body>
+
+<!-- NOTE!! CHROME WILL ADD TBODY HERE IF ITS NOT THERE!! -->
+<table style="width:100%">
+  <tr>
+    <th>Person 1</th>
+    <th>Person 2</th>
+    <th>Person 3</th>
+  </tr>
+  <tr>
+    <td>Emil</td>
+    <td>Tobias</td>
+    <td>Linus</td>
+  </tr>
+  <tr>
+    <td>16</td>
+    <td>14</td>
+    <td>10</td>
+  </tr>
+</table>
+</body>
+</html>
+"""
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(data)
+
 
 def set_original_response():
     test_return_data = """<html>
@@ -177,3 +206,61 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
     # There should not be an unviewed change, as changes should be removed
     res = client.get(url_for("index"))
     assert b"unviewed" not in res.data
+
+# Re #2752
+def test_element_removal_nth_offset_no_shift(client, live_server, measure_memory_usage):
+    #live_server_setup(live_server)
+
+    set_response_with_multiple_index()
+    subtractive_selectors_data = ["""
+body > table > tr:nth-child(1) > th:nth-child(2)
+body > table >  tr:nth-child(2) > td:nth-child(2)
+body > table > tr:nth-child(3) > td:nth-child(2)
+body > table > tr:nth-child(1) > th:nth-child(3)
+body > table >  tr:nth-child(2) > td:nth-child(3)
+body > table > tr:nth-child(3) > td:nth-child(3)""",
+"""//body/table/tr[1]/th[2]
+//body/table/tr[2]/td[2]
+//body/table/tr[3]/td[2]
+//body/table/tr[1]/th[3]
+//body/table/tr[2]/td[3]
+//body/table/tr[3]/td[3]"""]
+
+    for selector_list in subtractive_selectors_data:
+
+        res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+        assert b'Deleted' in res.data
+
+        # Add our URL to the import page
+        test_url = url_for("test_endpoint", _external=True)
+        res = client.post(
+            url_for("import_page"), data={"urls": test_url}, follow_redirects=True
+        )
+        assert b"1 Imported" in res.data
+        wait_for_all_checks(client)
+
+        res = client.post(
+            url_for("edit_page", uuid="first"),
+            data={
+                "subtractive_selectors": selector_list,
+                "url": test_url,
+                "tags": "",
+                "fetch_backend": "html_requests",
+            },
+            follow_redirects=True,
+        )
+        assert b"Updated watch." in res.data
+        wait_for_all_checks(client)
+
+        res = client.get(
+            url_for("preview_page", uuid="first"),
+            follow_redirects=True
+        )
+
+        assert b"Tobias" not in res.data
+        assert b"Linus" not in res.data
+        assert b"Person 2" not in res.data
+        assert b"Person 3" not in res.data
+        # First column should exist
+        assert b"Emil" in res.data
+

changedetectionio/tests/test_notification.py

@@ -284,7 +284,7 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
     # CUSTOM JSON BODY CHECK for POST://
     set_original_response()
     # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#header-manipulation
-    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?xxx={{ watch_url }}&+custom-header=123"
+    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?xxx={{ watch_url }}&+custom-header=123&+second=hello+world%20%22space%22"
 
     res = client.post(
         url_for("settings_page"),
@@ -326,6 +326,7 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
         assert j['secret'] == 444
         assert j['somebug'] == '网站监测 内容更新了'
 
+
     # URL check, this will always be converted to lowercase
     assert os.path.isfile("test-datastore/notification-url.txt")
     with open("test-datastore/notification-url.txt", 'r') as f:
@@ -337,6 +338,7 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
     with open("test-datastore/notification-headers.txt", 'r') as f:
         notification_headers = f.read()
         assert 'custom-header: 123' in notification_headers.lower()
+        assert 'second: hello world "space"' in notification_headers.lower()
 
 
     # Should always be automatically detected as JSON content type even when we set it as 'Text' (default)
@@ -440,4 +442,67 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
     assert b"Error: You must have atleast one watch configured for 'test notification' to work" in res.data
 
 
+def _test_color_notifications(client, notification_body_token):
 
+    from changedetectionio.diff import ADDED_STYLE, REMOVED_STYLE
+
+    set_original_response()
+
+    if os.path.isfile("test-datastore/notification.txt"):
+        os.unlink("test-datastore/notification.txt")
+
+
+    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?xxx={{ watch_url }}&+custom-header=123"
+
+
+    # otherwise other settings would have already existed from previous tests in this file
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "application-fetch_backend": "html_requests",
+            "application-minutes_between_check": 180,
+            "application-notification_body": notification_body_token,
+            "application-notification_format": "HTML Color",
+            "application-notification_urls": test_notification_url,
+            "application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
+        },
+        follow_redirects=True
+    )
+    assert b'Settings updated' in res.data
+
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": 'nice one'},
+        follow_redirects=True
+    )
+
+    assert b"Watch added" in res.data
+
+    wait_for_all_checks(client)
+
+    set_modified_response()
+
+
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
+
+    wait_for_all_checks(client)
+    time.sleep(3)
+
+    with open("test-datastore/notification.txt", 'r') as f:
+        x = f.read()
+        assert f'<span style="{REMOVED_STYLE}">Which is across multiple lines' in x
+
+
+    client.get(
+        url_for("form_delete", uuid="all"),
+        follow_redirects=True
+    )
+
+def test_html_color_notifications(client, live_server, measure_memory_usage):
+
+    #live_server_setup(live_server)
+    _test_color_notifications(client, '{{diff}}')
+    _test_color_notifications(client, '{{diff_full}}')
+    

changedetectionio/tests/test_request.py

@@ -45,7 +45,7 @@ def test_headers_in_request(client, live_server, measure_memory_usage):
               "url": test_url,
               "tags": "",
               "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
-              "headers": "xxx:ooo\ncool:yeah\r\ncookie:"+cookie_header},
+              "headers": "jinja2:{{ 1+1 }}\nxxx:ooo\ncool:yeah\r\ncookie:"+cookie_header},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -61,6 +61,7 @@ def test_headers_in_request(client, live_server, measure_memory_usage):
     )
 
     # Flask will convert the header key to uppercase
+    assert b"Jinja2:2" in res.data
     assert b"Xxx:ooo" in res.data
     assert b"Cool:yeah" in res.data
 
@@ -117,7 +118,8 @@ def test_body_in_request(client, live_server, measure_memory_usage):
     wait_for_all_checks(client)
 
     # Now the change which should trigger a change
-    body_value = 'Test Body Value'
+    body_value = 'Test Body Value {{ 1+1 }}'
+    body_value_formatted = 'Test Body Value 2'
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={
@@ -140,8 +142,9 @@ def test_body_in_request(client, live_server, measure_memory_usage):
 
     # If this gets stuck something is wrong, something should always be there
     assert b"No history found" not in res.data
-    # We should see what we sent in the reply
-    assert str.encode(body_value) in res.data
+    # We should see the formatted value of what we sent in the reply
+    assert str.encode(body_value) not in res.data
+    assert str.encode(body_value_formatted) in res.data
 
     ####### data sanity checks
     # Add the test URL twice, we will check

changedetectionio/tests/test_scheduler.py

@@ -0,0 +1,179 @@
+#!/usr/bin/env python3
+
+import time
+from datetime import datetime, timezone
+from zoneinfo import ZoneInfo
+from flask import url_for
+from .util import  live_server_setup, wait_for_all_checks, extract_UUID_from_client
+
+def test_setup(client, live_server):
+    live_server_setup(live_server)
+
+def test_check_basic_scheduler_functionality(client, live_server, measure_memory_usage):
+    #live_server_setup(live_server)
+    days = ['monday', 'tuesday', 'wednesday', 'thursday', 'friday', 'saturday', 'sunday']
+    test_url = url_for('test_random_content_endpoint', _external=True)
+
+    # We use "Pacific/Kiritimati" because its the furthest +14 hours, so it might show up more interesting bugs
+    # The rest of the actual functionality should be covered in the unit-test  unit/test_scheduler.py
+    #####################
+    res = client.post(
+        url_for("settings_page"),
+        data={"application-empty_pages_are_a_change": "",
+              "requests-time_between_check-seconds": 1,
+              "application-timezone": "Pacific/Kiritimati",  # Most Forward Time Zone (UTC+14:00)
+              'application-fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." in res.data
+
+    res = client.get(url_for("settings_page"))
+    assert b'Pacific/Kiritimati' in res.data
+
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+    wait_for_all_checks(client)
+    uuid = extract_UUID_from_client(client)
+
+    # Setup all the days of the weeks using XXX as the placeholder for monday/tuesday/etc
+
+    tpl = {
+        "time_schedule_limit-XXX-start_time": "00:00",
+        "time_schedule_limit-XXX-duration-hours": 24,
+        "time_schedule_limit-XXX-duration-minutes": 0,
+        "time_schedule_limit-XXX-enabled": '',  # All days are turned off
+        "time_schedule_limit-enabled": 'y',  # Scheduler is enabled, all days however are off.
+    }
+
+    scheduler_data = {}
+    for day in days:
+        for key, value in tpl.items():
+            # Replace "XXX" with the current day in the key
+            new_key = key.replace("XXX", day)
+            scheduler_data[new_key] = value
+
+    last_check = live_server.app.config['DATASTORE'].data['watching'][uuid]['last_checked']
+    data = {
+        "url": test_url,
+        "fetch_backend": "html_requests"
+    }
+    data.update(scheduler_data)
+
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data=data,
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+
+    res = client.get(url_for("edit_page", uuid="first"))
+    assert b"Pacific/Kiritimati" in res.data, "Should be Pacific/Kiritimati in placeholder data"
+
+    # "Edit" should not trigger a check because it's not enabled in the schedule.
+    time.sleep(2)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid]['last_checked'] == last_check
+
+    # Enabling today in Kiritimati should work flawless
+    kiritimati_time = datetime.now(timezone.utc).astimezone(ZoneInfo("Pacific/Kiritimati"))
+    kiritimati_time_day_of_week = kiritimati_time.strftime("%A").lower()
+    live_server.app.config['DATASTORE'].data['watching'][uuid]["time_schedule_limit"][kiritimati_time_day_of_week]["enabled"] = True
+    time.sleep(3)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid]['last_checked'] != last_check
+
+    # Cleanup everything
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+
+def test_check_basic_global_scheduler_functionality(client, live_server, measure_memory_usage):
+    #live_server_setup(live_server)
+    days = ['monday', 'tuesday', 'wednesday', 'thursday', 'friday', 'saturday', 'sunday']
+    test_url = url_for('test_random_content_endpoint', _external=True)
+
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+    wait_for_all_checks(client)
+    uuid = extract_UUID_from_client(client)
+
+    # Setup all the days of the weeks using XXX as the placeholder for monday/tuesday/etc
+
+    tpl = {
+        "requests-time_schedule_limit-XXX-start_time": "00:00",
+        "requests-time_schedule_limit-XXX-duration-hours": 24,
+        "requests-time_schedule_limit-XXX-duration-minutes": 0,
+        "requests-time_schedule_limit-XXX-enabled": '',  # All days are turned off
+        "requests-time_schedule_limit-enabled": 'y',  # Scheduler is enabled, all days however are off.
+    }
+
+    scheduler_data = {}
+    for day in days:
+        for key, value in tpl.items():
+            # Replace "XXX" with the current day in the key
+            new_key = key.replace("XXX", day)
+            scheduler_data[new_key] = value
+
+    data = {
+        "application-empty_pages_are_a_change": "",
+        "application-timezone": "Pacific/Kiritimati",  # Most Forward Time Zone (UTC+14:00)
+        'application-fetch_backend': "html_requests",
+        "requests-time_between_check-hours": 0,
+        "requests-time_between_check-minutes": 0,
+        "requests-time_between_check-seconds": 1,
+    }
+    data.update(scheduler_data)
+
+    #####################
+    res = client.post(
+        url_for("settings_page"),
+        data=data,
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." in res.data
+
+    res = client.get(url_for("settings_page"))
+    assert b'Pacific/Kiritimati' in res.data
+
+    wait_for_all_checks(client)
+
+    # UI Sanity check
+
+    res = client.get(url_for("edit_page", uuid="first"))
+    assert b"Pacific/Kiritimati" in res.data, "Should be Pacific/Kiritimati in placeholder data"
+
+    #### HITTING SAVE SHOULD NOT TRIGGER A CHECK
+    last_check = live_server.app.config['DATASTORE'].data['watching'][uuid]['last_checked']
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={
+            "url": test_url,
+            "fetch_backend": "html_requests",
+            "time_between_check_use_default": "y"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    time.sleep(2)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid]['last_checked'] == last_check
+
+    # Enabling "today" in Kiritimati time should make the system check that watch
+    kiritimati_time = datetime.now(timezone.utc).astimezone(ZoneInfo("Pacific/Kiritimati"))
+    kiritimati_time_day_of_week = kiritimati_time.strftime("%A").lower()
+    live_server.app.config['DATASTORE'].data['settings']['requests']['time_schedule_limit'][kiritimati_time_day_of_week]["enabled"] = True
+
+    time.sleep(3)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid]['last_checked'] != last_check
+
+    # Cleanup everything
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_security.py

@@ -1,9 +1,7 @@
 import os
 
 from flask import url_for
-from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
-import time
-
+from .util import live_server_setup, wait_for_all_checks
 from .. import strtobool
 
 
@@ -61,32 +59,44 @@ def test_bad_access(client, live_server, measure_memory_usage):
     assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
 
 
-def test_file_access(client, live_server, measure_memory_usage):
-    #live_server_setup(live_server)
+def _runner_test_various_file_slash(client, file_uri):
 
-    test_file_path = "/tmp/test-file.txt"
-
-    # file:// is permitted by default, but it will be caught by ALLOW_FILE_URI
     client.post(
         url_for("form_quick_watch_add"),
-        data={"url": f"file://{test_file_path}", "tags": ''},
+        data={"url": file_uri, "tags": ''},
         follow_redirects=True
     )
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
 
+    substrings = [b"URLs with hostname components are not permitted", b"No connection adapters were found for"]
+
+
     # If it is enabled at test time
     if strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
-        res = client.get(
-            url_for("preview_page", uuid="first"),
-            follow_redirects=True
-        )
+        if file_uri.startswith('file:///'):
+            # This one should be the full qualified path to the file and should get the contents of this file
+            res = client.get(
+                url_for("preview_page", uuid="first"),
+                follow_redirects=True
+            )
+            assert b'_runner_test_various_file_slash' in res.data
+        else:
+            # This will give some error from requests or if it went to chrome, will give some other error :-)
+            assert any(s in res.data for s in substrings)
 
-        # Should see something (this file added by run_basic_tests.sh)
-        assert b"Hello world" in res.data
-    else:
-        # Default should be here
-        assert b'file:// type access is denied for security reasons.' in res.data
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+def test_file_slash_access(client, live_server, measure_memory_usage):
+    #live_server_setup(live_server)
+
+    # file: is NOT permitted by default, so it will be caught by ALLOW_FILE_URI check
+
+    test_file_path = os.path.abspath(__file__)
+    _runner_test_various_file_slash(client, file_uri=f"file://{test_file_path}")
+    _runner_test_various_file_slash(client, file_uri=f"file:/{test_file_path}")
+    _runner_test_various_file_slash(client, file_uri=f"file:{test_file_path}") # CVE-2024-56509
 
 def test_xss(client, live_server, measure_memory_usage):
     #live_server_setup(live_server)

changedetectionio/tests/unit/test_scheduler.py

@@ -0,0 +1,53 @@
+#!/usr/bin/env python3
+
+# run from dir above changedetectionio/ dir
+# python3 -m unittest changedetectionio.tests.unit.test_jinja2_security
+
+import unittest
+from datetime import datetime, timedelta
+from zoneinfo import ZoneInfo
+
+class TestScheduler(unittest.TestCase):
+
+    # UTC+14:00 (Line Islands, Kiribati) is the farthest ahead, always ahead of UTC.
+    # UTC-12:00 (Baker Island, Howland Island) is the farthest behind, always one calendar day behind UTC.
+
+    def test_timezone_basic_time_within_schedule(self):
+        from changedetectionio import time_handler
+
+        timezone_str = 'Europe/Berlin'
+        debug_datetime = datetime.now(ZoneInfo(timezone_str))
+        day_of_week = debug_datetime.strftime('%A')
+        time_str = str(debug_datetime.hour)+':00'
+        duration = 60  # minutes
+
+        # The current time should always be within 60 minutes of [time_hour]:00
+        result = time_handler.am_i_inside_time(day_of_week=day_of_week,
+                                               time_str=time_str,
+                                               timezone_str=timezone_str,
+                                               duration=duration)
+
+        self.assertEqual(result, True, f"{debug_datetime} is within time scheduler {day_of_week} {time_str} in {timezone_str} for {duration} minutes")
+
+    def test_timezone_basic_time_outside_schedule(self):
+        from changedetectionio import time_handler
+
+        timezone_str = 'Europe/Berlin'
+        # We try a date in the future..
+        debug_datetime = datetime.now(ZoneInfo(timezone_str))+ timedelta(days=-1)
+        day_of_week = debug_datetime.strftime('%A')
+        time_str = str(debug_datetime.hour) + ':00'
+        duration = 60*24  # minutes
+
+        # The current time should always be within 60 minutes of [time_hour]:00
+        result = time_handler.am_i_inside_time(day_of_week=day_of_week,
+                                               time_str=time_str,
+                                               timezone_str=timezone_str,
+                                               duration=duration)
+
+        self.assertNotEqual(result, True,
+                         f"{debug_datetime} is NOT within time scheduler {day_of_week} {time_str} in {timezone_str} for {duration} minutes")
+
+
+if __name__ == '__main__':
+    unittest.main()

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -54,15 +54,21 @@ def test_visual_selector_content_ready(client, live_server, measure_memory_usage
 
 
     assert os.path.isfile(os.path.join('test-datastore', uuid, 'last-screenshot.png')), "last-screenshot.png should exist"
-    assert os.path.isfile(os.path.join('test-datastore', uuid, 'elements.json')), "xpath elements.json data should exist"
+    assert os.path.isfile(os.path.join('test-datastore', uuid, 'elements.deflate')), "xpath elements.deflate data should exist"
 
     # Open it and see if it roughly looks correct
-    with open(os.path.join('test-datastore', uuid, 'elements.json'), 'r') as f:
-        json.load(f)
+    with open(os.path.join('test-datastore', uuid, 'elements.deflate'), 'rb') as f:
+        import zlib
+        compressed_data = f.read()
+        decompressed_data = zlib.decompress(compressed_data)
+        # See if any error was thrown
+        json_data = json.loads(decompressed_data.decode('utf-8'))
 
     # Attempt to fetch it via the web hook that the browser would use
     res = client.get(url_for('static_content', group='visual_selector_data', filename=uuid))
-    json.loads(res.data)
+    decompressed_data = zlib.decompress(res.data)
+    json_data = json.loads(decompressed_data.decode('utf-8'))
+    
     assert res.mimetype == 'application/json'
     assert res.status_code == 200
 

changedetectionio/time_handler.py

@@ -0,0 +1,105 @@
+from datetime import timedelta, datetime
+from enum import IntEnum
+from zoneinfo import ZoneInfo
+
+
+class Weekday(IntEnum):
+    """Enumeration for days of the week."""
+    Monday = 0
+    Tuesday = 1
+    Wednesday = 2
+    Thursday = 3
+    Friday = 4
+    Saturday = 5
+    Sunday = 6
+
+
+def am_i_inside_time(
+        day_of_week: str,
+        time_str: str,
+        timezone_str: str,
+        duration: int = 15,
+) -> bool:
+    """
+    Determines if the current time falls within a specified time range.
+
+    Parameters:
+        day_of_week (str): The day of the week (e.g., 'Monday').
+        time_str (str): The start time in 'HH:MM' format.
+        timezone_str (str): The timezone identifier (e.g., 'Europe/Berlin').
+        duration (int, optional): The duration of the time range in minutes. Default is 15.
+
+    Returns:
+        bool: True if the current time is within the time range, False otherwise.
+    """
+    # Parse the target day of the week
+    try:
+        target_weekday = Weekday[day_of_week.capitalize()]
+    except KeyError:
+        raise ValueError(f"Invalid day_of_week: '{day_of_week}'. Must be a valid weekday name.")
+
+    # Parse the start time
+    try:
+        target_time = datetime.strptime(time_str, '%H:%M').time()
+    except ValueError:
+        raise ValueError(f"Invalid time_str: '{time_str}'. Must be in 'HH:MM' format.")
+
+    # Define the timezone
+    try:
+        tz = ZoneInfo(timezone_str)
+    except Exception:
+        raise ValueError(f"Invalid timezone_str: '{timezone_str}'. Must be a valid timezone identifier.")
+
+    # Get the current time in the specified timezone
+    now_tz = datetime.now(tz)
+
+    # Check if the current day matches the target day or overlaps due to duration
+    current_weekday = now_tz.weekday()
+    start_datetime_tz = datetime.combine(now_tz.date(), target_time, tzinfo=tz)
+
+    # Handle previous day's overlap
+    if target_weekday == (current_weekday - 1) % 7:
+        # Calculate start and end times for the overlap from the previous day
+        start_datetime_tz -= timedelta(days=1)
+        end_datetime_tz = start_datetime_tz + timedelta(minutes=duration)
+        if start_datetime_tz <= now_tz < end_datetime_tz:
+            return True
+
+    # Handle current day's range
+    if target_weekday == current_weekday:
+        end_datetime_tz = start_datetime_tz + timedelta(minutes=duration)
+        if start_datetime_tz <= now_tz < end_datetime_tz:
+            return True
+
+    # Handle next day's overlap
+    if target_weekday == (current_weekday + 1) % 7:
+        end_datetime_tz = start_datetime_tz + timedelta(minutes=duration)
+        if now_tz < start_datetime_tz and now_tz + timedelta(days=1) < end_datetime_tz:
+            return True
+
+    return False
+
+
+def is_within_schedule(time_schedule_limit, default_tz="UTC"):
+    if time_schedule_limit and time_schedule_limit.get('enabled'):
+        # Get the timezone the time schedule is in, so we know what day it is there
+        tz_name = time_schedule_limit.get('timezone')
+        if not tz_name:
+            tz_name = default_tz
+
+        now_day_name_in_tz = datetime.now(ZoneInfo(tz_name.strip())).strftime('%A')
+        selected_day_schedule = time_schedule_limit.get(now_day_name_in_tz.lower())
+        if not selected_day_schedule.get('enabled'):
+            return False
+
+        duration = selected_day_schedule.get('duration')
+        selected_day_run_duration_m = int(duration.get('hours')) * 60 + int(duration.get('minutes'))
+
+        is_valid = am_i_inside_time(day_of_week=now_day_name_in_tz,
+                                    time_str=selected_day_schedule['start_time'],
+                                    timezone_str=tz_name,
+                                    duration=selected_day_run_duration_m)
+
+        return is_valid
+
+    return False

changedetectionio/update_worker.py

@@ -28,6 +28,8 @@ class update_worker(threading.Thread):
 
     def queue_notification_for_watch(self, notification_q, n_object, watch):
         from changedetectionio import diff
+        from changedetectionio.notification import default_notification_format_for_watch
+
         dates = []
         trigger_text = ''
 
@@ -44,11 +46,21 @@ class update_worker(threading.Thread):
         else:
             snapshot_contents = "No snapshot/history available, the watch should fetch atleast once."
 
+        # If we ended up here with "System default"
+        if n_object.get('notification_format') == default_notification_format_for_watch:
+            n_object['notification_format'] = self.datastore.data['settings']['application'].get('notification_format')
+
+        html_colour_enable = False
         # HTML needs linebreak, but MarkDown and Text can use a linefeed
         if n_object.get('notification_format') == 'HTML':
             line_feed_sep = "<br>"
             # Snapshot will be plaintext on the disk, convert to some kind of HTML
             snapshot_contents = snapshot_contents.replace('\n', line_feed_sep)
+        elif n_object.get('notification_format') == 'HTML Color':
+            line_feed_sep = "<br>"
+            # Snapshot will be plaintext on the disk, convert to some kind of HTML
+            snapshot_contents = snapshot_contents.replace('\n', line_feed_sep)
+            html_colour_enable = True
         else:
             line_feed_sep = "\n"
 
@@ -69,9 +81,9 @@ class update_worker(threading.Thread):
 
         n_object.update({
             'current_snapshot': snapshot_contents,
-            'diff': diff.render_diff(prev_snapshot, current_snapshot, line_feed_sep=line_feed_sep),
+            'diff': diff.render_diff(prev_snapshot, current_snapshot, line_feed_sep=line_feed_sep, html_colour=html_colour_enable),
             'diff_added': diff.render_diff(prev_snapshot, current_snapshot, include_removed=False, line_feed_sep=line_feed_sep),
-            'diff_full': diff.render_diff(prev_snapshot, current_snapshot, include_equal=True, line_feed_sep=line_feed_sep),
+            '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,

debian/changedetection-wrapper

@@ -0,0 +1,3 @@
+#!/bin/sh
+# Wrapper script to run changedetection.io from venv
+exec /opt/changedetection/bin/python3 /opt/changedetection/bin/changedetection.io "$@"

debian/changedetection.io.service

@@ -0,0 +1,31 @@
+[Unit]
+Description=changedetection.io - Website change detection and monitoring
+After=network.target
+Documentation=https://changedetection.io
+
+[Service]
+Type=simple
+User=_changedetection
+Group=_changedetection
+WorkingDirectory=/var/lib/changedetection
+Environment="DATASTORE_PATH=/var/lib/changedetection"
+Environment="HOST=127.0.0.1"
+Environment="PORT=5000"
+ExecStart=/opt/changedetection/bin/changedetection.io -h 127.0.0.1 -p 5000 -d /var/lib/changedetection
+
+# Security hardening
+NoNewPrivileges=true
+PrivateTmp=true
+ProtectSystem=strict
+ProtectHome=true
+ReadWritePaths=/var/lib/changedetection
+ProtectKernelTunables=true
+ProtectKernelModules=true
+ProtectControlGroups=true
+
+# Restart policy
+Restart=on-failure
+RestartSec=10s
+
+[Install]
+WantedBy=multi-user.target

debian/changedetection.io/lib/systemd/system/changedetection.io.service

@@ -0,0 +1,13 @@
+[Unit]
+Description=changedetection.io Service
+After=network.target
+
+[Service]
+User=changedetio
+Group=changedetio
+WorkingDirectory=/opt/changedetection.io
+ExecStart=/opt/changedetection.io/bin/python -m changedetectionio
+Restart=on-failure
+
+[Install]
+WantedBy=multi-user.target

debian/changelog

@@ -0,0 +1,7 @@
+changedetection.io (0.50.38) stable; urgency=medium
+
+  * Initial Debian package release
+  * Service runs as _changedetection user on localhost:5000
+  * Systemd integration with security hardening
+
+ -- dgtlmoon <dgtlmoon@changedetection.io>  Sat, 02 Nov 2024 00:00:00 +0000

debian/compat

@@ -0,0 +1 @@
+13

debian/control

@@ -0,0 +1,38 @@
+Source: changedetection.io
+Section: web
+Priority: optional
+Maintainer: dgtlmoon <dgtlmoon@changedetection.io>
+Build-Depends: debhelper-compat (= 13),
+               dh-python,
+               python3-all (>= 3.10),
+               python3-setuptools,
+               python3-pip,
+               python3-venv
+Standards-Version: 4.6.2
+Homepage: https://changedetection.io
+Vcs-Browser: https://github.com/dgtlmoon/changedetection.io
+Vcs-Git: https://github.com/dgtlmoon/changedetection.io.git
+Rules-Requires-Root: no
+
+Package: changedetection.io
+Architecture: all
+Depends: ${misc:Depends},
+         ${python3:Depends},
+         python3 (>= 3.10),
+         python3-pip,
+         python3-venv,
+         adduser
+Description: Website change detection and monitoring service
+ changedetection.io is a self-hosted open source application for monitoring
+ websites for changes. It detects changes to web pages and sends alerts or
+ notifications when changes are detected.
+ .
+ Features include:
+  * Monitor websites for visual and text changes
+  * XPath, CSS, and JSON filtering
+  * Notifications via multiple services (Apprise)
+  * API for automation
+  * Headless browser support
+ .
+ This package installs changedetection.io as a systemd service running on
+ localhost (127.0.0.1:5000) as the unprivileged _changedetection user.

debian/debhelper-build-stamp

@@ -0,0 +1 @@
+python-changedetection.io

debian/install

@@ -0,0 +1,2 @@
+# Install wrapper script
+debian/changedetection-wrapper usr/bin/changedetection.io

debian/postinst

@@ -0,0 +1,51 @@
+#!/bin/sh
+set -e
+
+case "$1" in
+    configure)
+        # Create system user if it doesn't exist
+        if ! getent passwd _changedetection >/dev/null; then
+            adduser --system --group --home /var/lib/changedetection \
+                    --gecos "changedetection.io service" \
+                    --shell /usr/sbin/nologin \
+                    _changedetection
+        fi
+
+        # Create data directory with proper permissions
+        if [ ! -d /var/lib/changedetection ]; then
+            mkdir -p /var/lib/changedetection
+        fi
+        chown _changedetection:_changedetection /var/lib/changedetection
+        chmod 755 /var/lib/changedetection
+
+        # Reload systemd and enable service
+        if [ -d /run/systemd/system ]; then
+            systemctl daemon-reload >/dev/null || true
+            deb-systemd-helper enable changedetection.io.service >/dev/null || true
+
+            # Start service if this is a fresh install
+            if [ -z "$2" ]; then
+                echo "Starting changedetection.io service..."
+                systemctl start changedetection.io.service || true
+                echo ""
+                echo "changedetection.io has been installed and started."
+                echo "Access it at: http://127.0.0.1:5000"
+                echo ""
+                echo "To check status: systemctl status changedetection.io"
+                echo "To view logs: journalctl -u changedetection.io -f"
+            fi
+        fi
+        ;;
+
+    abort-upgrade|abort-remove|abort-deconfigure)
+        ;;
+
+    *)
+        echo "postinst called with unknown argument \`$1'" >&2
+        exit 1
+        ;;
+esac
+
+#DEBHELPER#
+
+exit 0

debian/postrm

@@ -0,0 +1,29 @@
+#!/bin/sh
+set -e
+
+case "$1" in
+    purge)
+        # Remove system user on purge
+        if getent passwd _changedetection >/dev/null; then
+            deluser --system _changedetection >/dev/null || true
+        fi
+
+        # Remove data directory on purge (with confirmation in package description)
+        if [ -d /var/lib/changedetection ]; then
+            echo "Note: Data directory /var/lib/changedetection has been preserved."
+            echo "Remove manually with: rm -rf /var/lib/changedetection"
+        fi
+        ;;
+
+    remove|upgrade|failed-upgrade|abort-install|abort-upgrade|disappear)
+        ;;
+
+    *)
+        echo "postrm called with unknown argument \`$1'" >&2
+        exit 1
+        ;;
+esac
+
+#DEBHELPER#
+
+exit 0

debian/prerm

@@ -0,0 +1,23 @@
+#!/bin/sh
+set -e
+
+case "$1" in
+    remove|deconfigure)
+        # Stop service before removal
+        if [ -d /run/systemd/system ]; then
+            deb-systemd-invoke stop changedetection.io.service >/dev/null || true
+        fi
+        ;;
+
+    upgrade|failed-upgrade)
+        ;;
+
+    *)
+        echo "prerm called with unknown argument \`$1'" >&2
+        exit 1
+        ;;
+esac
+
+#DEBHELPER#
+
+exit 0

debian/rules

@@ -0,0 +1,37 @@
+#!/usr/bin/make -f
+
+# Debian rules file for changedetection.io
+# This uses a Python virtual environment approach for isolated dependencies
+
+export PYBUILD_NAME=changedetection.io
+export DH_VERBOSE=1
+
+# Use venv installation method
+VENV_DIR = debian/changedetection.io/opt/changedetection
+PYTHON = python3
+
+%:
+	dh $@ --with python3 --buildsystem=pybuild
+
+override_dh_auto_install:
+	# Create virtual environment
+	$(PYTHON) -m venv $(VENV_DIR)
+
+	# Install the package and dependencies into venv
+	$(VENV_DIR)/bin/pip install --upgrade pip setuptools wheel
+	$(VENV_DIR)/bin/pip install .
+
+	# Remove pip and setuptools to reduce size (optional)
+	# $(VENV_DIR)/bin/pip uninstall -y pip setuptools wheel
+
+	# Create wrapper script directory
+	install -d debian/changedetection.io/usr/bin
+
+override_dh_auto_test:
+	# Skip tests during package build
+	# Tests can be run separately with pytest
+	@echo "Skipping tests during package build"
+
+override_dh_auto_clean:
+	dh_auto_clean
+	rm -rf build dist *.egg-info

debian/source/format

@@ -0,0 +1 @@
+3.0 (native)

docker-compose.yml

@@ -61,6 +61,12 @@ services:
   #
   #        If you want to watch local files file:///path/to/file.txt (careful! security implications!)
   #      - ALLOW_FILE_URI=False
+  #
+  #        For complete privacy if you don't want to use the 'check version' / telemetry service
+  #      - DISABLE_VERSION_CHECK=true
+  #
+  #        A valid timezone name to run as (for scheduling watch checking) see https://en.wikipedia.org/wiki/List_of_tz_database_time_zones
+  #      - TZ=America/Los_Angeles
   
       # Comment out ports: when using behind a reverse proxy , enable networks: etc.
       ports:
@@ -74,7 +80,7 @@ services:
      # If WEBDRIVER or PLAYWRIGHT are enabled, changedetection container depends on that
      # and must wait before starting (substitute "browser-chrome" with "playwright-chrome" if last one is used)
 #      depends_on:
-#          playwright-chrome:
+#          sockpuppetbrowser:
 #              condition: service_started
 
 

requirements.txt

@@ -1,7 +1,7 @@
 # Used by Pyppeteer
 pyee
 
-eventlet>=0.36.1 # fixes SSL error on Python 3.12
+eventlet>=0.38.0
 feedgen~=0.9
 flask-compress
 # 0.6.3 included compatibility fix for werkzeug 3.x (2.x had deprecation of url handlers)
@@ -38,9 +38,8 @@ dnspython==2.6.1 # related to eventlet fixes
 apprise==1.9.0
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
-# and 2.0.0 https://github.com/dgtlmoon/changedetection.io/issues/2241 not yet compatible
-# use v1.x due to https://github.com/eclipse/paho.mqtt.python/issues/814
-paho-mqtt>=1.6.1,<2.0.0
+# use any version other than 2.0.x due to https://github.com/eclipse/paho.mqtt.python/issues/814
+paho-mqtt!=2.0.*
 
 # Requires extra wheel for rPi
 cryptography~=42.0.8
@@ -59,7 +58,9 @@ elementpath==4.1.5
 
 selenium~=4.14.0
 
-werkzeug~=3.0
+# https://github.com/pallets/werkzeug/issues/2985
+# Maybe related to pytest?
+werkzeug==3.0.6
 
 # Templating, so far just in the URLs but in the future can be for the notifications also
 jinja2~=3.1
@@ -94,4 +95,5 @@ babel
 # Needed for > 3.10, https://github.com/microsoft/playwright-python/issues/2096
 greenlet >= 3.0.3
 
-
+# Scheduler - Windows seemed to miss a lot of default timezone info (even "UTC" !)
+tzdata