Re #2333 set min version for mqtt

.github/dependabot.yml

@@ -4,6 +4,10 @@ updates:
     directory: /
     schedule:
       interval: "weekly"
+    "caronc/apprise":
+      versioning-strategy: "increase"
+      schedule:
+        interval: "daily"
     groups:
       all:
         patterns:

.github/workflows/test-only.yml

@@ -72,7 +72,11 @@ jobs:
         run: |
           # Playwright via Sockpuppetbrowser fetch
           # tests/visualselector/test_fetch_data.py will do browser steps  
-          docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
+
 
       - name: Playwright and SocketPuppetBrowser - Headers and requests
         run: |       
@@ -87,8 +91,11 @@ jobs:
 # STRAIGHT TO CDP
       - name: Pyppeteer and SocketPuppetBrowser - Specific tests in built container
         run: |
-          # Playwright via Sockpuppetbrowser fetch
+          # Playwright via Sockpuppetbrowser fetch 
-          docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" -e "FAST_PUPPETEER_CHROME_FETCHER=True" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
 
       - name: Pyppeteer and SocketPuppetBrowser - Headers and requests checks
         run: |       

CONTRIBUTING.md

@@ -2,7 +2,7 @@ Contributing is always welcome!
 
 I am no professional flask developer, if you know a better way that something can be done, please let me know!
 
-Otherwise, it's always best to PR into the `dev` branch.
+Otherwise, it's always best to PR into the `master` branch.
 
 Please be sure that all new functionality has a matching test!
 

MANIFEST.in

@@ -1,8 +1,8 @@
 recursive-include changedetectionio/api *
 recursive-include changedetectionio/blueprint *
+recursive-include changedetectionio/content_fetchers *
 recursive-include changedetectionio/model *
 recursive-include changedetectionio/processors *
-recursive-include changedetectionio/res *
 recursive-include changedetectionio/static *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/tests *

README.md

@@ -91,6 +91,14 @@ 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/
 
+### 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.
+
+[<img src="./docs/chrome-extension-screenshot.png" style="max-width:80%;" alt="Chrome Extension to easily add the current web-page to detect a change."  title="Chrome Extension to easily add the current web-page to detect a change."  />](https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop)
+
+[Goto the Chrome Webstore to download the extension.](https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop)
+
 ## Installation
 
 ### Docker

changedetectionio/__init__.py

@@ -2,9 +2,9 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.45.14'
+__version__ = '0.45.20'
 
-from distutils.util import strtobool
+from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError
 import os
 #os.environ['EVENTLET_NO_GREENDNS'] = 'yes'

changedetectionio/api/api_v1.py

@@ -1,5 +1,5 @@
 import os
-from distutils.util import strtobool
+from changedetectionio.strtobool import strtobool
 
 from flask_expects_json import expects_json
 from changedetectionio import queuedWatchMetaData

changedetectionio/blueprint/browser_steps/__init__.py

@@ -12,7 +12,7 @@
 #
 #
 
-from distutils.util import strtobool
+from changedetectionio.strtobool import strtobool
 from flask import Blueprint, request, make_response
 import os
 

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -6,6 +6,8 @@ import re
 from random import randint
 from loguru import logger
 
+from changedetectionio.content_fetchers.base import manage_user_agent
+
 # Two flags, tell the JS which of the "Selector" or "Value" field should be enabled in the front end
 # 0- off, 1- on
 browser_step_ui_config = {'Choose one': '0 0',
@@ -178,6 +180,7 @@ class browsersteps_live_ui(steppable_browser_interface):
     stale = False
     # bump and kill this if idle after X sec
     age_start = 0
+    headers = {}
 
     # use a special driver, maybe locally etc
     command_executor = os.getenv(
@@ -192,7 +195,8 @@ class browsersteps_live_ui(steppable_browser_interface):
 
     browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
 
-    def __init__(self, playwright_browser, proxy=None):
+    def __init__(self, playwright_browser, proxy=None, headers=None):
+        self.headers = headers or {}
         self.age_start = time.time()
         self.playwright_browser = playwright_browser
         if self.context is None:
@@ -206,16 +210,17 @@ class browsersteps_live_ui(steppable_browser_interface):
 
         # @todo handle multiple contexts, bind a unique id from the browser on each req?
         self.context = self.playwright_browser.new_context(
-            # @todo
+            accept_downloads=False,  # Should never be needed
-            #                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
+            bypass_csp=True,  # This is needed to enable JavaScript execution on GitHub and others
-            #               proxy=self.proxy,
+            extra_http_headers=self.headers,
-            # This is needed to enable JavaScript execution on GitHub and others
+            ignore_https_errors=True,
-            bypass_csp=True,
+            proxy=proxy,
-            # Should never be needed
+            service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
-            accept_downloads=False,
+            # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
-            proxy=proxy
+            user_agent=manage_user_agent(headers=self.headers),
         )
 
+
         self.page = self.context.new_page()
 
         # self.page.set_default_navigation_timeout(keep_open)

changedetectionio/blueprint/browser_steps/nonContext.py

@@ -1,5 +1,4 @@
 from playwright.sync_api import PlaywrightContextManager
-import asyncio
 
 # So playwright wants to run as a context manager, but we do something horrible and hacky
 # we are holding the session open for as long as possible, then shutting it down, and opening a new one

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -1,5 +1,5 @@
 
-from distutils.util import strtobool
+from changedetectionio.strtobool import strtobool
 from flask import Blueprint, flash, redirect, url_for
 from flask_login import login_required
 from changedetectionio.store import ChangeDetectionStore

changedetectionio/blueprint/tags/__init__.py

@@ -12,9 +12,15 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         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
+
+        tag_count = Counter(tag for watch in datastore.data['watching'].values() if watch.get('tags') for tag in watch['tags'])
+
         output = render_template("groups-overview.html",
-                                 form=add_form,
                                  available_tags=sorted_tags,
+                                 form=add_form,
+                                 tag_count=tag_count
                                  )
 
         return output

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

@@ -3,7 +3,7 @@
 {% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
 <script>
-    const notification_base_url="{{url_for('ajax_callback_send_notification_test', watch_uuid=uuid)}}";
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test', mode="group-settings")}}";
 </script>
 
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>

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

@@ -27,6 +27,7 @@
             <thead>
             <tr>
                 <th></th>
+                <th># Watches</th>
                 <th>Tag / Label name</th>
                 <th></th>
             </tr>
@@ -45,7 +46,8 @@
                 <td class="watch-controls">
                     <a class="link-mute state-{{'on' if tag.notification_muted else 'off'}}" href="{{url_for('tags.mute', uuid=tag.uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute" ></a>
                 </td>
-                <td class="title-col inline">{{tag.title}}</td>
+                <td>{{ "{:,}".format(tag_count[uuid]) if uuid in tag_count else 0 }}</td>
+                <td class="title-col inline"> <a href="{{url_for('index', tag=uuid) }}">{{ tag.title }}</a></td>
                 <td>
                     <a class="pure-button pure-button-primary" href="{{ url_for('tags.form_tag_edit', uuid=uuid) }}">Edit</a>&nbsp;
                     <a class="pure-button pure-button-primary" href="{{ url_for('tags.delete', uuid=uuid) }}" title="Deletes and removes tag">Delete</a>

changedetectionio/content_fetchers/__init__.py

@@ -1,6 +1,6 @@
 import sys
-from distutils.util import strtobool
+from changedetectionio.strtobool import strtobool
-
+from loguru import logger
 from changedetectionio.content_fetchers.exceptions import BrowserStepsStepException
 import os
 
@@ -29,10 +29,15 @@ def available_fetchers():
 # rather than site-specific.
 use_playwright_as_chrome_fetcher = os.getenv('PLAYWRIGHT_DRIVER_URL', False)
 if use_playwright_as_chrome_fetcher:
+    # @note - For now, browser steps always uses playwright
     if not strtobool(os.getenv('FAST_PUPPETEER_CHROME_FETCHER', 'False')):
+        logger.debug('Using Playwright library as fetcher')
         from .playwright import fetcher as html_webdriver
     else:
+        logger.debug('Using direct Python Puppeteer library as fetcher')
         from .puppeteer import fetcher as html_webdriver
 
 else:
+    logger.debug("Falling back to selenium as fetcher")
     from .webdriver_selenium import fetcher as html_webdriver
+

changedetectionio/content_fetchers/base.py

@@ -5,6 +5,40 @@ from loguru import logger
 from changedetectionio.content_fetchers import BrowserStepsStepException
 
 
+def manage_user_agent(headers, current_ua=''):
+    """
+    Basic setting of user-agent
+
+    NOTE!!!!!! The service that does the actual Chrome fetching should handle any anti-robot techniques
+    THERE ARE MANY WAYS THAT IT CAN BE DETECTED AS A ROBOT!!
+    This does not take care of
+    - Scraping of 'navigator' (platform, productSub, vendor, oscpu etc etc) browser object (navigator.appVersion) etc
+    - TCP/IP fingerprint JA3 etc
+    - Graphic rendering fingerprinting
+    - Your IP being obviously in a pool of bad actors
+    - Too many requests
+    - Scraping of SCH-UA browser replies (thanks google!!)
+    - Scraping of ServiceWorker, new window calls etc
+
+    See https://filipvitas.medium.com/how-to-set-user-agent-header-with-puppeteer-js-and-not-fail-28c7a02165da
+    Puppeteer requests https://github.com/dgtlmoon/pyppeteerstealth
+
+    :param page:
+    :param headers:
+    :return:
+    """
+    # Ask it what the user agent is, if its obviously ChromeHeadless, switch it to the default
+    ua_in_custom_headers = next((v for k, v in headers.items() if k.lower() == "user-agent"), None)
+    if ua_in_custom_headers:
+        return ua_in_custom_headers
+
+    if not ua_in_custom_headers and current_ua:
+        current_ua = current_ua.replace('HeadlessChrome', 'Chrome')
+        return current_ua
+
+    return None
+
+
 class Fetcher():
     browser_connection_is_custom = None
     browser_connection_url = None

changedetectionio/content_fetchers/playwright.py

@@ -3,7 +3,8 @@ import os
 from urllib.parse import urlparse
 
 from loguru import logger
-from changedetectionio.content_fetchers.base import Fetcher
+
+from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
 from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, ScreenshotUnavailable
 
 class fetcher(Fetcher):
@@ -102,19 +103,16 @@ class fetcher(Fetcher):
             # Set user agent to prevent Cloudflare from blocking the browser
             # Use the default one configured in the App.py model that's passed from fetch_site_status.py
             context = browser.new_context(
-                user_agent={k.lower(): v for k, v in request_headers.items()}.get('user-agent', None),
+                accept_downloads=False,  # Should never be needed
+                bypass_csp=True,  # This is needed to enable JavaScript execution on GitHub and others
+                extra_http_headers=request_headers,
+                ignore_https_errors=True,
                 proxy=self.proxy,
-                # This is needed to enable JavaScript execution on GitHub and others
+                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'), # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
-                bypass_csp=True,
+                user_agent=manage_user_agent(headers=request_headers),
-                # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
-                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
-                # Should never be needed
-                accept_downloads=False
             )
 
             self.page = context.new_page()
-            if len(request_headers):
-                context.set_extra_http_headers(request_headers)
 
             # Listen for all console events and handle errors
             self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))

changedetectionio/content_fetchers/puppeteer.py

@@ -5,7 +5,8 @@ import websockets.exceptions
 from urllib.parse import urlparse
 
 from loguru import logger
-from changedetectionio.content_fetchers.base import Fetcher
+
+from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
 from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, BrowserFetchTimedOut, BrowserConnectError
 
 
@@ -100,10 +101,11 @@ class fetcher(Fetcher):
         else:
             self.page = await browser.newPage()
 
+        await self.page.setUserAgent(manage_user_agent(headers=request_headers, current_ua=await self.page.evaluate('navigator.userAgent')))
+
         await self.page.setBypassCSP(True)
         if request_headers:
             await self.page.setExtraHTTPHeaders(request_headers)
-            # @todo check user-agent worked
 
         # SOCKS5 with authentication is not supported (yet)
         # https://github.com/microsoft/playwright/issues/10567
@@ -212,8 +214,12 @@ class fetcher(Fetcher):
                 logger.error('ERROR: Failed to get viewport-only reduced screenshot :(')
                 pass
         finally:
+            # It's good to log here in the case that the browser crashes on shutting down but we still get the data we need
+            logger.success(f"Fetching '{url}' complete, closing page")
             await self.page.close()
+            logger.success(f"Fetching '{url}' complete, closing browser")
             await browser.close()
+        logger.success(f"Fetching '{url}' complete, exiting puppeteer fetch.")
 
     async def main(self, **kwargs):
         await self.fetch_page(**kwargs)

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

@@ -17,8 +17,9 @@ function isItemInStock() {
         'as soon as stock is available',
         'ausverkauft', // sold out
         'available for back order',
-        'back-order or out of stock',
+        'awaiting stock',
         'back in stock soon',
+        'back-order or out of stock',
         'backordered',
         'benachrichtigt mich', // notify me
         'brak na stanie',
@@ -57,16 +58,20 @@ function isItemInStock() {
         'sold-out',
         'temporarily out of stock',
         'temporarily unavailable',
+        'there were no search results for',
+        'this item is currently unavailable',
         'tickets unavailable',
         'tijdelijk uitverkocht',
         'unavailable tickets',
         'vorbestellung ist bald möglich',
+        'we couldn\'t find any products that match',
         'we do not currently have an estimate of when this product will be back in stock.',
         'we don\'t know when or if this item will be back in stock.',
+        'we were not able to find a match',
         'zur zeit nicht an lager',
         '品切れ',
-        '已售完',
         '已售',
+        '已售完',
         '품절'
     ];
 

changedetectionio/flask_app.py

@@ -6,7 +6,7 @@ import queue
 import threading
 import time
 from copy import deepcopy
-from distutils.util import strtobool
+from changedetectionio.strtobool import strtobool
 from functools import wraps
 from threading import Event
 
@@ -30,6 +30,7 @@ from flask_compress import Compress as FlaskCompress
 from flask_login import current_user
 from flask_paginate import Pagination, get_page_parameter
 from flask_restful import abort, Api
+from flask_cors import CORS
 from flask_wtf import CSRFProtect
 from loguru import logger
 
@@ -53,6 +54,9 @@ app = Flask(__name__,
             static_folder="static",
             template_folder="templates")
 
+# Enable CORS, especially useful for the Chrome extension to operate from anywhere
+CORS(app)
+
 # Super handy for compressing large BrowserSteps responses and others
 FlaskCompress(app)
 
@@ -512,21 +516,38 @@ def changedetection_app(config=None, datastore_o=None):
 
         watch = datastore.data['watching'].get(watch_uuid) if watch_uuid else None
 
-        # validate URLS
+        notification_urls = request.form['notification_urls'].strip().splitlines()
-        if not len(request.form['notification_urls'].strip()):
-            return make_response({'error': 'No Notification URLs set'}, 400)
 
-        for server_url in request.form['notification_urls'].splitlines():
+        if not notification_urls:
-            if len(server_url.strip()):
+            logger.debug("Test notification - Trying by group/tag in the edit form if available")
-                if not apobj.add(server_url):
+            # On an edit page, we should also fire off to the tags if they have notifications
-                    message = '{} is not a valid AppRise URL.'.format(server_url)
+            if request.form.get('tags') and request.form['tags'].strip():
-                    return make_response({'error': message}, 400)
+                for k in request.form['tags'].split(','):
+                    tag = datastore.tag_exists_by_name(k.strip())
+                    notification_urls = tag.get('notifications_urls') if tag and tag.get('notifications_urls') else None
+
+        is_global_settings_form = request.args.get('mode', '') == 'global-settings'
+        is_group_settings_form = request.args.get('mode', '') == 'group-settings'
+        if not notification_urls and not is_global_settings_form and not is_group_settings_form:
+            # In the global settings, use only what is typed currently in the text box
+            logger.debug("Test notification - Trying by global system settings notifications")
+            if datastore.data['settings']['application'].get('notification_urls'):
+                notification_urls = datastore.data['settings']['application']['notification_urls']
+
+
+        if not notification_urls:
+            return 'No Notification URLs set/found'
+
+        for n_url in notification_urls:
+            if len(n_url.strip()):
+                if not apobj.add(n_url):
+                    return f'Error - {n_url} is not a valid AppRise URL.'
 
         try:
             # use the same as when it is triggered, but then override it with the form test values
             n_object = {
                 'watch_url': request.form['window_url'],
-                'notification_urls': request.form['notification_urls'].splitlines()
+                'notification_urls': notification_urls
             }
 
             # Only use if present, if not set in n_object it should use the default system value
@@ -545,7 +566,7 @@ def changedetection_app(config=None, datastore_o=None):
         except Exception as e:
             return make_response({'error': str(e)}, 400)
 
-        return 'OK'
+        return 'OK - Sent test notifications'
 
 
     @app.route("/clear_history/<string:uuid>", methods=['GET'])
@@ -582,6 +603,12 @@ def changedetection_app(config=None, datastore_o=None):
         output = render_template("clear_all_history.html")
         return output
 
+    def _watch_has_tag_options_set(watch):
+        """This should be fixed better so that Tag is some proper Model, a tag is just a Watch also"""
+        for tag_uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
+            if tag_uuid in watch.get('tags', []) and (tag.get('include_filters') or tag.get('subtractive_selectors')):
+                return True
+
     @app.route("/edit/<string:uuid>", methods=['GET', 'POST'])
     @login_optionally_required
     # https://stackoverflow.com/questions/42984453/wtforms-populate-form-with-data-if-data-exists
@@ -752,6 +779,7 @@ def changedetection_app(config=None, datastore_o=None):
                                      has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
                                      has_empty_checktime=using_default_check_time,
                                      has_extra_headers_file=len(datastore.get_all_headers_in_textfile_for_watch(uuid=uuid)) > 0,
+                                     has_special_tag_options=_watch_has_tag_options_set(watch=watch),
                                      is_html_webdriver=is_html_webdriver,
                                      jq_support=jq_support,
                                      playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False),
@@ -1275,9 +1303,8 @@ def changedetection_app(config=None, datastore_o=None):
 
         url = request.form.get('url').strip()
         if datastore.url_exists(url):
-            flash('The URL {} already exists'.format(url), "error")
+            flash(f'Warning, URL {url} already exists', "notice")
-            return redirect(url_for('index'))
+            
-
         add_paused = request.form.get('edit_and_watch_submit_button') != None
         processor = request.form.get('processor', 'text_json_diff')
         new_uuid = datastore.add_watch(url=url, tag=request.form.get('tags').strip(), extras={'paused': add_paused, 'processor': processor})
@@ -1427,6 +1454,13 @@ def changedetection_app(config=None, datastore_o=None):
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
             flash("{} watches queued for rechecking".format(len(uuids)))
 
+        elif (op == 'clear-errors'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid]["last_error"] = False
+            flash(f"{len(uuids)} watches errors cleared")
+
         elif (op == 'clear-history'):
             for uuid in uuids:
                 uuid = uuid.strip()

changedetectionio/forms.py

@@ -1,6 +1,6 @@
 import os
 import re
-from distutils.util import strtobool
+from changedetectionio.strtobool import strtobool
 
 from wtforms import (
     BooleanField,

changedetectionio/html_tools.py

@@ -169,14 +169,14 @@ def xpath1_filter(xpath_filter, html_content, append_pretty_line_formatting=Fals
         # And where the matched result doesn't include something that will cause Inscriptis to add a newline
         # (This way each 'match' reliably has a new-line in the diff)
         # Divs are converted to 4 whitespaces by inscriptis
-        if append_pretty_line_formatting and len(html_block) and (not hasattr( element, 'tag' ) or not element.tag in (['br', 'hr', 'div', 'p'])):
+        if append_pretty_line_formatting and len(html_block) and (not hasattr(element, 'tag') or not element.tag in (['br', 'hr', 'div', 'p'])):
             html_block += TEXT_FILTER_LIST_LINE_SUFFIX
 
-        if type(element) == etree._ElementStringResult:
+        # Some kind of text, UTF-8 or other
-            html_block += str(element)
+        if isinstance(element, (str, bytes)):
-        elif type(element) == etree._ElementUnicodeResult:
+            html_block += element
-            html_block += str(element)
         else:
+            # Return the HTML which will get parsed as text
             html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
 
     return html_block

changedetectionio/model/Watch.py

@@ -1,4 +1,4 @@
-from distutils.util import strtobool
+from changedetectionio.strtobool import strtobool
 import os
 import re
 import time
@@ -362,6 +362,7 @@ class model(dict):
         # @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

changedetectionio/processors/__init__.py

@@ -3,7 +3,7 @@ import os
 import hashlib
 import re
 from copy import deepcopy
-from distutils.util import strtobool
+from changedetectionio.strtobool import strtobool
 from loguru import logger
 
 class difference_detection_processor():

changedetectionio/processors/text_json_diff.py

@@ -119,7 +119,7 @@ class perform_site_check(difference_detection_processor):
         include_filters_from_tags = self.datastore.get_tag_overrides_for_watch(uuid=uuid, attr='include_filters')
 
         # 1845 - remove duplicated filters in both group and watch include filter
-        include_filters_rule = list({*watch.get('include_filters', []), *include_filters_from_tags})
+        include_filters_rule = list(dict.fromkeys(watch.get('include_filters', []) + include_filters_from_tags))
 
         subtractive_selectors = [*self.datastore.get_tag_overrides_for_watch(uuid=uuid, attr='subtractive_selectors'),
                                  *watch.get("subtractive_selectors", []),

changedetectionio/static/js/browser-steps.js

@@ -160,6 +160,12 @@ $(document).ready(function () {
                     e.offsetX > item.left * y_scale && e.offsetX < item.left * y_scale + item.width * y_scale
 
                 ) {
+                    // Ignore really large ones, because we are scraping 'div' also from xpath_element_scraper but
+                    // that div or whatever could be some wrapper and would generally make you select the whole page
+                    if (item.width > 800 && item.height > 400) {
+                        return
+                    }
+
                     // There could be many elements here, record them all and then we'll find out which is the most 'useful'
                     // (input, textarea, button, A etc)
                     if (item.width < xpath_data['browser_width']) {

changedetectionio/static/js/notifications.js

@@ -28,15 +28,11 @@ $(document).ready(function() {
       notification_format: $('#notification_format').val(),
       notification_title: $('#notification_title').val(),
       notification_urls: $('.notification-urls').val(),
+      tags: $('#tags').val(),
       window_url: window.location.href,
     }
 
 
-    if (!data['notification_urls'].length) {
-      alert("Notification URL list is empty, cannot send test.")
-      return;
-    }
-
     $.ajax({
       type: "POST",
       url: notification_base_url,
@@ -49,7 +45,7 @@ $(document).ready(function() {
       }
     }).done(function(data){
       console.log(data);
-      alert('Sent');
+      alert(data);
     }).fail(function(data){
       console.log(data);
       alert('There was an error communicating with the server.');

changedetectionio/static/styles/diff.css

@@ -68,7 +68,7 @@
   --color-last-checked: #bbb;
   --color-text-footer: #444;
   --color-border-watch-table-cell: #eee;
-  --color-text-watch-tag-list: #e70069;
+  --color-text-watch-tag-list: rgba(231, 0, 105, 0.4);
   --color-background-new-watch-form: rgba(0, 0, 0, 0.05);
   --color-background-new-watch-input: var(--color-white);
   --color-text-new-watch-input: var(--color-text);
@@ -111,7 +111,7 @@ html[data-darkmode="true"] {
   --color-background-input: var(--color-grey-350);
   --color-text-input-description: var(--color-grey-600);
   --color-text-input-placeholder: var(--color-grey-600);
-  --color-text-watch-tag-list: #fa3e92;
+  --color-text-watch-tag-list: rgba(250, 62, 146, 0.4);
   --color-background-code: var(--color-grey-200);
   --color-background-tab: rgba(0, 0, 0, 0.2);
   --color-background-tab-hover: rgba(0, 0, 0, 0.5);

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

@@ -75,7 +75,7 @@
   --color-text-footer: #444;
   --color-border-watch-table-cell: #eee;
 
-  --color-text-watch-tag-list: #e70069;
+  --color-text-watch-tag-list: rgba(231, 0, 105, 0.4);
   --color-background-new-watch-form: rgba(0, 0, 0, 0.05);
   --color-background-new-watch-input: var(--color-white);
   --color-text-new-watch-input: var(--color-text);
@@ -127,7 +127,7 @@ html[data-darkmode="true"] {
   --color-background-input: var(--color-grey-350);
   --color-text-input-description: var(--color-grey-600);
   --color-text-input-placeholder: var(--color-grey-600);
-  --color-text-watch-tag-list: #fa3e92;
+  --color-text-watch-tag-list: rgba(250, 62, 146, 0.4);
   --color-background-code: var(--color-grey-200);
 
   --color-background-tab: rgba(0, 0, 0, 0.2);

changedetectionio/static/styles/scss/styles.scss

@@ -187,8 +187,11 @@ code {
 }
 
 .watch-tag-list {
-  color: var(--color-text-watch-tag-list);
+  color: var(--color-white);
   white-space: nowrap;
+  background: var(--color-text-watch-tag-list);
+  border-radius: 5px;
+  padding: 2px 5px;
 }
 
 .box {
@@ -1096,3 +1099,16 @@ ul {
   white-space: nowrap;
 }
 
+#chrome-extension-link {
+  img {
+    height: 21px;
+    padding: 2px;
+    vertical-align: middle;
+  }
+
+  padding: 9px;
+  border: 1px solid var(--color-grey-800);
+  border-radius: 10px;
+  vertical-align: middle;
+}
+

changedetectionio/static/styles/styles.css

@@ -284,7 +284,7 @@ ul#requests-extra_browsers {
   --color-last-checked: #bbb;
   --color-text-footer: #444;
   --color-border-watch-table-cell: #eee;
-  --color-text-watch-tag-list: #e70069;
+  --color-text-watch-tag-list: rgba(231, 0, 105, 0.4);
   --color-background-new-watch-form: rgba(0, 0, 0, 0.05);
   --color-background-new-watch-input: var(--color-white);
   --color-text-new-watch-input: var(--color-text);
@@ -327,7 +327,7 @@ html[data-darkmode="true"] {
   --color-background-input: var(--color-grey-350);
   --color-text-input-description: var(--color-grey-600);
   --color-text-input-placeholder: var(--color-grey-600);
-  --color-text-watch-tag-list: #fa3e92;
+  --color-text-watch-tag-list: rgba(250, 62, 146, 0.4);
   --color-background-code: var(--color-grey-200);
   --color-background-tab: rgba(0, 0, 0, 0.2);
   --color-background-tab-hover: rgba(0, 0, 0, 0.5);
@@ -532,8 +532,11 @@ code {
     margin: 0 3px 0 5px; }
 
 .watch-tag-list {
-  color: var(--color-text-watch-tag-list);
+  color: var(--color-white);
-  white-space: nowrap; }
+  white-space: nowrap;
+  background: var(--color-text-watch-tag-list);
+  border-radius: 5px;
+  padding: 2px 5px; }
 
 .box {
   max-width: 80%;
@@ -1180,3 +1183,13 @@ ul {
   .restock-label.not-in-stock {
     background-color: var(--color-background-button-cancel);
     color: #777; }
+
+#chrome-extension-link {
+  padding: 9px;
+  border: 1px solid var(--color-grey-800);
+  border-radius: 10px;
+  vertical-align: middle; }
+  #chrome-extension-link img {
+    height: 21px;
+    padding: 2px;
+    vertical-align: middle; }

changedetectionio/store.py

@@ -1,4 +1,4 @@
-from distutils.util import strtobool
+from changedetectionio.strtobool import strtobool
 
 from flask import (
     flash
@@ -657,7 +657,10 @@ class ChangeDetectionStore:
         return res
 
     def tag_exists_by_name(self, tag_name):
-        return any(v.get('title', '').lower() == tag_name.lower() for k, v in self.__data['settings']['application']['tags'].items())
+        # Check if any tag dictionary has a 'title' attribute matching the provided tag_name
+        tags = self.__data['settings']['application']['tags'].values()
+        return next((v for v in tags if v.get('title', '').lower() == tag_name.lower()),
+                    None)
 
     def get_updates_available(self):
         import inspect

changedetectionio/strtobool.py

@@ -0,0 +1,23 @@
+# Because strtobool was removed in python 3.12 distutils
+
+_MAP = {
+    'y': True,
+    'yes': True,
+    't': True,
+    'true': True,
+    'on': True,
+    '1': True,
+    'n': False,
+    'no': False,
+    'f': False,
+    'false': False,
+    'off': False,
+    '0': False
+}
+
+
+def strtobool(value):
+    try:
+        return _MAP[str(value).lower()]
+    except KeyError:
+        raise ValueError('"{}" is not a valid bool value'.format(value))

changedetectionio/templates/base.html

@@ -147,7 +147,19 @@
     <section class="content">
         <div id="overlay">
             <div class="content">
-                <strong>changedetection.io needs your support!</strong><br>
+                <h4>Try our Chrome extension</h4>
+                <p>
+                    <a id="chrome-extension-link"
+                       title="Try our new Chrome Extension!"
+                       href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
+                        <img src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}">
+                        Chrome Webstore
+                    </a>
+                </p>
+
+                Easily add the current web-page from your browser directly into your changedetection.io tool, more great features coming soon!
+
+                <h4>Changedetection.io needs your support!</h4>
                 <p>
                     You can help us by supporting changedetection.io on these platforms;
                 </p>

changedetectionio/templates/edit.html

@@ -7,7 +7,8 @@
 <script>
     const browser_steps_available_screenshots=JSON.parse('{{ watch.get_browsersteps_available_screenshots|tojson }}');
     const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
-    const browser_steps_fetch_screenshot_image_url="{{url_for('browser_steps.browser_steps_fetch_screenshot_image', uuid=uuid)}}";
+    <!-- Should be _external so that firefox and others load it more reliably -->
+    const browser_steps_fetch_screenshot_image_url="{{url_for('browser_steps.browser_steps_fetch_screenshot_image', uuid=uuid, _external=True)}}";
     const browser_steps_last_error_step={{ watch.browser_steps_last_error_step|tojson }};
     const browser_steps_start_url="{{url_for('browser_steps.browsersteps_start_session', uuid=uuid)}}";
     const browser_steps_sync_url="{{url_for('browser_steps.browsersteps_ui_update', uuid=uuid)}}";
@@ -31,6 +32,7 @@
 <script src="{{url_for('static_content', group='js', filename='browser-steps.js')}}" defer></script>
 {% endif %}
 
+{% set has_tag_filters_extra="WARNING: Watch has tag/groups set with special filters\n" if has_special_tag_options else '' %}
 <script src="{{url_for('static_content', group='js', filename='recheck-proxy.js')}}" defer></script>
 
 <div class="edit-form monospaced-textarea">
@@ -280,7 +282,7 @@ User-Agent: wonderbra 1.0") }}
                     <div class="pure-control-group">
                         {% set field = render_field(form.include_filters,
                             rows=5,
-                            placeholder="#example
+                            placeholder=has_tag_filters_extra+"#example
 xpath://body/div/span[contains(@class, 'example-class')]",
                             class="m-d")
                         %}
@@ -316,13 +318,14 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                 </span>
                     </div>
                 <fieldset class="pure-control-group">
-                    {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
+                    {{ render_field(form.subtractive_selectors, rows=5, placeholder=has_tag_filters_extra+"header
 footer
 nav
 .stockticker") }}
                     <span class="pure-form-message-inline">
                         <ul>
                           <li> Remove HTML element(s) by CSS selector before text conversion. </li>
+                          <li> Don't paste HTML here, use only CSS selectors </li>
                           <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
@@ -436,7 +439,7 @@ Unavailable") }}
                     <div class="pure-control-group">
                         {% if visualselector_enabled %}
                             <span class="pure-form-message-inline">
-                                The Visual Selector tool lets you select the <i>text</i> elements that will be used for the change detection &dash; after the <i>Browser Steps</i> has completed.<br><br>
+                                The Visual Selector tool lets you select the <i>text</i> elements that will be used for the change detection &dash; after the <i>Browser Steps</i> has completed, this tool is a helper to manage filters in the  "CSS/JSONPath/JQ/XPath Filters" box of the <a href="#filters-and-triggers">Filters & Triggers</a> tab.
                             </span>
 
                             <div id="selector-header">

changedetectionio/templates/import.html

@@ -107,7 +107,7 @@
                                     <option value="" style="color: #aaa"> -- none --</option>
                                     <option value="url">URL</option>
                                     <option value="title">Title</option>
-                                    <option value="include_filter">CSS/xPath filter</option>
+                                    <option value="include_filters">CSS/xPath filter</option>
                                     <option value="tag">Group / Tag name(s)</option>
                                     <option value="interval_minutes">Recheck time (minutes)</option>
                                 </select></td>

changedetectionio/templates/settings.html

@@ -4,7 +4,7 @@
 {% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
 <script>
-    const notification_base_url="{{url_for('ajax_callback_send_notification_test', watch_uuid=uuid)}}";
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test', mode="global-settings")}}";
 {% if emailprefix %}
     const email_notification_prefix=JSON.parse('{{emailprefix|tojson}}');
 {% endif %}
@@ -168,12 +168,12 @@ nav
            </div>
 
             <div class="tab-pane-inner" id="api">
-
+                <h4>API Access</h4>
                 <p>Drive your changedetection.io via API, More about <a href="https://github.com/dgtlmoon/changedetection.io/wiki/API-Reference">API access here</a></p>
 
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.api_access_token_enabled) }}
-                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header</div><br>
+                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header - required for the Chrome Extension to work</div><br>
                     <div class="pure-form-message-inline"><br>API Key <span id="api-key">{{api_key}}</span>
                         <span style="display:none;" id="api-key-copy" >copy</span>
                     </div>
@@ -181,6 +181,20 @@ nav
                 <div class="pure-control-group">
                     <a href="{{url_for('settings_reset_api_key')}}" class="pure-button button-small button-cancel">Regenerate API key</a>
                 </div>
+                <div class="pure-control-group">
+                    <h4>Chrome Extension</h4>
+                    <p>Easily add any web-page to your changedetection.io installation from within Chrome.</p>
+                    <strong>Step 1</strong> Install the extension, <strong>Step 2</strong> Navigate to this page,
+                    <strong>Step 3</strong> Open the extension from the toolbar and click "<i>Sync API Access</i>"
+                    <p>
+                        <a id="chrome-extension-link"
+                           title="Try our new Chrome Extension!"
+                           href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
+                            <img src="{{ url_for('static_content', group='images', filename='Google-Chrome-icon.png') }}">
+                            Chrome Webstore
+                        </a>
+                    </p>
+                </div>
             </div>
             <div class="tab-pane-inner" id="proxies">
                 <div id="recommended-proxy">

changedetectionio/templates/watch-overview.html

@@ -37,6 +37,7 @@
         <button class="pure-button button-secondary button-xsmall" name="op" value="assign-tag" id="checkbox-assign-tag">Tag</button>
         <button class="pure-button button-secondary button-xsmall" name="op" value="mark-viewed">Mark viewed</button>
         <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default">Use default notification</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="clear-errors">Clear errors</button>
         <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="clear-history">Clear/reset history</button>
         <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="delete">Delete</button>
     </div>

changedetectionio/tests/fetchers/test_custom_js_before_content.py

@@ -0,0 +1,56 @@
+import os
+from flask import url_for
+from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+
+
+def test_execute_custom_js(client, live_server):
+
+    live_server_setup(live_server)
+    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
+
+    test_url = url_for('test_interactive_html_endpoint', _external=True)
+    test_url = test_url.replace('localhost.localdomain', 'cdio')
+    test_url = test_url.replace('localhost', 'cdio')
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+        data={
+            "url": test_url,
+            "tags": "",
+            'fetch_backend': "html_webdriver",
+            'webdriver_js_execute_code': 'document.querySelector("button[name=test-button]").click();',
+            'headers': "testheader: yes\buser-agent: MyCustomAgent",
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+
+    uuid = extract_UUID_from_client(client)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n >= 1, "Watch history had atleast 1 (everything fetched OK)"
+
+    assert b"This text should be removed" not in res.data
+
+    # Check HTML conversion detected and workd
+    res = client.get(
+        url_for("preview_page", uuid=uuid),
+        follow_redirects=True
+    )
+    assert b"This text should be removed" not in res.data
+    assert b"I smell JavaScript because the button was pressed" in res.data
+
+    assert b"testheader: yes" in res.data
+    assert b"user-agent: mycustomagent" in res.data
+
+    client.get(
+        url_for("form_delete", uuid="all"),
+        follow_redirects=True
+    )

changedetectionio/tests/restock/test_restock.py

@@ -95,7 +95,7 @@ def test_restock_detection(client, live_server):
 
     # We should have a notification
     time.sleep(2)
-    assert os.path.isfile("test-datastore/notification.txt")
+    assert os.path.isfile("test-datastore/notification.txt"), "Notification received"
     os.unlink("test-datastore/notification.txt")
 
     # Default behaviour is to only fire notification when it goes OUT OF STOCK -> IN STOCK
@@ -103,4 +103,9 @@ def test_restock_detection(client, live_server):
     set_original_response()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
-    assert not os.path.isfile("test-datastore/notification.txt")
+    assert not os.path.isfile("test-datastore/notification.txt"), "No notification should have fired when it went OUT OF STOCK by default"
+
+    # BUT we should see that it correctly shows "not in stock"
+    res = client.get(url_for("index"))
+    assert b'not-in-stock' in res.data, "Correctly showing NOT IN STOCK in the list after it changed from IN STOCK"
+

changedetectionio/tests/test_group.py

@@ -100,6 +100,12 @@ def test_setup_group_tag(client, live_server):
     assert b'Should be only this' in res.data
     assert b'And never this' not in res.data
 
+    res = client.get(
+        url_for("edit_page", uuid="first"),
+        follow_redirects=True
+    )
+    # 2307 the UI notice should appear in the placeholder
+    assert b'WARNING: Watch has tag/groups set with special filters' in res.data
 
     # RSS Group tag filter
     # An extra one that should be excluded
@@ -321,3 +327,154 @@ def test_clone_tag_on_quickwatchform_add(client, live_server):
 
     res = client.get(url_for("tags.delete_all"), follow_redirects=True)
     assert b'All tags deleted' in res.data
+
+def test_order_of_filters_tag_filter_and_watch_filter(client, live_server):
+
+    # Add a tag with some config, import a tag and it should roughly work
+    res = client.post(
+        url_for("tags.form_tag_add"),
+        data={"name": "test-tag-keep-order"},
+        follow_redirects=True
+    )
+    assert b"Tag added" in res.data
+    assert b"test-tag-keep-order" in res.data
+    tag_filters = [
+            '#only-this', # duplicated filters
+            '#only-this',
+            '#only-this',
+            '#only-this',
+            ]
+
+    res = client.post(
+        url_for("tags.form_tag_edit_submit", uuid="first"),
+        data={"name": "test-tag-keep-order",
+              "include_filters": '\n'.join(tag_filters) },
+        follow_redirects=True
+    )
+    assert b"Updated" in res.data
+    tag_uuid = get_UUID_for_tag_name(client, name="test-tag-keep-order")
+    res = client.get(
+        url_for("tags.form_tag_edit", uuid="first")
+    )
+    assert b"#only-this" in res.data
+
+
+    d = """<html>
+       <body>
+     Some initial text<br>
+     <p id="only-this">And 1 this</p>
+     <br>
+     <p id="not-this">And 2 this</p>
+     <p id="">And 3 this</p><!--/html/body/p[3]/-->
+     <p id="">And 4 this</p><!--/html/body/p[4]/-->
+     <p id="">And 5 this</p><!--/html/body/p[5]/-->
+     <p id="">And 6 this</p><!--/html/body/p[6]/-->
+     <p id="">And 7 this</p><!--/html/body/p[7]/-->
+     <p id="">And 8 this</p><!--/html/body/p[8]/-->
+     <p id="">And 9 this</p><!--/html/body/p[9]/-->
+     <p id="">And 10 this</p><!--/html/body/p[10]/-->
+     <p id="">And 11 this</p><!--/html/body/p[11]/-->
+     <p id="">And 12 this</p><!--/html/body/p[12]/-->
+     <p id="">And 13 this</p><!--/html/body/p[13]/-->
+     <p id="">And 14 this</p><!--/html/body/p[14]/-->
+     <p id="not-this">And 15 this</p><!--/html/body/p[15]/-->
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(d)
+
+    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)
+
+    filters = [
+            '/html/body/p[3]',
+            '/html/body/p[4]',
+            '/html/body/p[5]',
+            '/html/body/p[6]',
+            '/html/body/p[7]',
+            '/html/body/p[8]',
+            '/html/body/p[9]',
+            '/html/body/p[10]',
+            '/html/body/p[11]',
+            '/html/body/p[12]',
+            '/html/body/p[13]', # duplicated tags
+            '/html/body/p[13]',
+            '/html/body/p[13]',
+            '/html/body/p[13]',
+            '/html/body/p[13]',
+            '/html/body/p[14]',
+            ]
+
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"include_filters": '\n'.join(filters),
+            "url": test_url,
+            "tags": "test-tag-keep-order",
+            "headers": "",
+            '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"And 1 this" in res.data  # test-tag-keep-order
+
+    a_tag_filter_check = b'And 1 this' #'#only-this' of tag_filters
+    # check there is no duplication of tag_filters
+    assert res.data.count(a_tag_filter_check) == 1, f"duplicated filters didn't removed {res.data.count(a_tag_filter_check)} of {a_tag_filter_check} in {res.data=}"
+
+    a_filter_check = b"And 13 this" # '/html/body/p[13]'
+    # check there is no duplication of filters
+    assert res.data.count(a_filter_check) == 1, f"duplicated filters didn't removed. {res.data.count(a_filter_check)} of {a_filter_check} in {res.data=}"
+
+    a_filter_check_not_include = b"And 2 this" # '/html/body/p[2]'
+    assert a_filter_check_not_include not in res.data
+
+    checklist = [
+            b"And 3 this",
+            b"And 4 this",
+            b"And 5 this",
+            b"And 6 this",
+            b"And 7 this",
+            b"And 8 this",
+            b"And 9 this",
+            b"And 10 this",
+            b"And 11 this",
+            b"And 12 this",
+            b"And 13 this",
+            b"And 14 this",
+            b"And 1 this", # result of filter from tag.
+            ]
+    # check whether everything a user requested is there
+    for test in checklist:
+        assert test in res.data
+
+    # check whether everything a user requested is in order of filters.
+    n = 0
+    for test in checklist:
+        t_index = res.data[n:].find(test)
+        # if the text is not searched, return -1.
+        assert t_index >= 0, f"""failed because {test=} not in {res.data[n:]=}
+#####################
+Looks like some feature changed the order of result of filters.
+#####################
+the {test} appeared before. {test in res.data[:n]=}
+{res.data[:n]=}
+        """
+        n += t_index + len(test)
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_pdf.py

@@ -29,7 +29,8 @@ def test_fetch_pdf(client, live_server):
         follow_redirects=True
     )
 
-    assert b'PDF-1.5' not in res.data
+    # PDF header should not be there (it was converted to text)
+    assert b'PDF' not in res.data[:10]
     assert b'hello world' in res.data
 
     # So we know if the file changes in other ways

changedetectionio/tests/test_xpath_selector.py

@@ -1,4 +1,4 @@
-#!/usr/bin/python3
+# -*- coding: utf-8 -*-
 
 import time
 from flask import url_for
@@ -255,6 +255,69 @@ def test_xpath23_prefix_validation(client, live_server):
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
+def test_xpath1_lxml(client, live_server):
+    #live_server_setup(live_server)
+
+    d = '''<?xml version="1.0" encoding="UTF-8"?>
+    <rss xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
+    	<channel>
+    		<title>rpilocator.com</title>
+    		<link>https://rpilocator.com</link>
+    		<description>Find Raspberry Pi Computers in Stock</description>
+    		<lastBuildDate>Thu, 19 May 2022 23:27:30 GMT</lastBuildDate>
+    		<image>
+    			<url>https://rpilocator.com/favicon.png</url>
+    			<title>rpilocator.com</title>
+    			<link>https://rpilocator.com/</link>
+    			<width>32</width>
+    			<height>32</height>
+    		</image>
+    		<item>
+    			<title>Stock Alert (UK): RPi CM4</title>
+    			<foo>something else unrelated</foo>
+    		</item>
+    		<item>
+    			<title>Stock Alert (UK): Big monitorěěěě</title>
+    			<foo>something else unrelated</foo>
+    		</item>		
+    	</channel>
+    </rss>'''.encode('utf-8')
+
+    with open("test-datastore/endpoint-content.txt", "wb") as f:
+        f.write(d)
+
+
+    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={"include_filters": "xpath1://title/text()", "url": test_url, "tags": "", "headers": "",
+              'fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+
+    ##### #2312
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'_ElementStringResult' not in res.data # tested with 5.1.1 when it was removed and 5.1.0
+    assert b'Exception' not in res.data
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert b"rpilocator.com" in res.data  # in selector
+    assert "Stock Alert (UK): Big monitorěěěě".encode('utf-8') in res.data  # not in selector
+
+    #####
+
 
 def test_xpath1_validation(client, live_server):
     # Add our URL to the import page

changedetectionio/tests/util.py

@@ -242,5 +242,28 @@ def live_server_setup(live_server):
             resp.headers['Content-Type'] = 'application/pdf'
             return resp
 
+    @live_server.app.route('/test-interactive-html-endpoint')
+    def test_interactive_html_endpoint():
+        header_text=""
+        for k,v in request.headers.items():
+            header_text += f"{k}: {v}<br>"
+
+        resp = make_response(f"""
+        <html>
+          <body>
+          Primitive JS check for <pre>changedetectionio/tests/visualselector/test_fetch_data.py</pre>
+            <p id="remove">This text should be removed</p>
+              <form onsubmit="event.preventDefault();">
+            <!-- obfuscated text so that we dont accidentally get a false positive due to conversion of the source :) --->
+                <button name="test-button" onclick="getElementById('remove').remove();getElementById('some-content').innerHTML = atob('SSBzbWVsbCBKYXZhU2NyaXB0IGJlY2F1c2UgdGhlIGJ1dHRvbiB3YXMgcHJlc3NlZCE=')">Click here</button>
+                <div id=some-content></div>
+                <pre>
+                {header_text.lower()}
+                </pre>
+              </body>
+         </html>""", 200)
+        resp.headers['Content-Type'] = 'text/html'
+        return resp
+
     live_server.start()
 

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -7,15 +7,19 @@ from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_cli
 def test_setup(client, live_server):
     live_server_setup(live_server)
 
+
 # Add a site in paused mode, add an invalid filter, we should still have visual selector data ready
 def test_visual_selector_content_ready(client, live_server):
+
     import os
     import json
 
     assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
 
     # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
-    test_url = "https://changedetection.io/ci-test/test-runjs.html"
+    test_url = url_for('test_interactive_html_endpoint', _external=True)
+    test_url = test_url.replace('localhost.localdomain', 'cdio')
+    test_url = test_url.replace('localhost', 'cdio')
 
     res = client.post(
         url_for("form_quick_watch_add"),
@@ -23,28 +27,31 @@ def test_visual_selector_content_ready(client, live_server):
         follow_redirects=True
     )
     assert b"Watch added in Paused state, saving will unpause" in res.data
-
+    uuid = extract_UUID_from_client(client)
     res = client.post(
-        url_for("edit_page", uuid="first", unpause_on_save=1),
+        url_for("edit_page", uuid=uuid, unpause_on_save=1),
         data={
-              "url": test_url,
+            "url": test_url,
-              "tags": "",
+            "tags": "",
-              "headers": "",
+            # For now, cookies doesnt work in headers because it must be a full cookiejar object
-              'fetch_backend': "html_webdriver",
+            'headers': "testheader: yes\buser-agent: MyCustomAgent",
-              'webdriver_js_execute_code': 'document.querySelector("button[name=test-button]").click();'
+            'fetch_backend': "html_webdriver",
         },
         follow_redirects=True
     )
     assert b"unpaused" in res.data
     wait_for_all_checks(client)
-    uuid = extract_UUID_from_client(client)
 
-    # Check the JS execute code before extract worked
+
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n >= 1, "Watch history had atleast 1 (everything fetched OK)"
+
     res = client.get(
-        url_for("preview_page", uuid="first"),
+        url_for("preview_page", uuid=uuid),
         follow_redirects=True
     )
-    assert b'I smell JavaScript' in res.data
+    assert b"testheader: yes" in res.data
+    assert b"user-agent: mycustomagent" in res.data
+
 
     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"
@@ -74,30 +81,33 @@ def test_visual_selector_content_ready(client, live_server):
 
 def test_basic_browserstep(client, live_server):
 
-    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
     #live_server_setup(live_server)
+    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
 
-    # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
+    test_url = url_for('test_interactive_html_endpoint', _external=True)
-    test_url = "https://changedetection.io/ci-test/test-runjs.html"
+    test_url = test_url.replace('localhost.localdomain', 'cdio')
+    test_url = test_url.replace('localhost', 'cdio')
 
     res = client.post(
         url_for("form_quick_watch_add"),
         data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
         follow_redirects=True
     )
+
     assert b"Watch added in Paused state, saving will unpause" in res.data
 
     res = client.post(
         url_for("edit_page", uuid="first", unpause_on_save=1),
         data={
-              "url": test_url,
+            "url": test_url,
-              "tags": "",
+            "tags": "",
-              "headers": "",
+            'fetch_backend': "html_webdriver",
-              'fetch_backend': "html_webdriver",
+            'browser_steps-0-operation': 'Goto site',
-              'browser_steps-0-operation': 'Goto site',
+            'browser_steps-1-operation': 'Click element',
-              'browser_steps-1-operation': 'Click element',
+            'browser_steps-1-selector': 'button[name=test-button]',
-              'browser_steps-1-selector': 'button[name=test-button]',
+            'browser_steps-1-optional_value': '',
-              'browser_steps-1-optional_value': ''
+            # For now, cookies doesnt work in headers because it must be a full cookiejar object
+            'headers': "testheader: yes\buser-agent: MyCustomAgent",
         },
         follow_redirects=True
     )
@@ -105,6 +115,9 @@ def test_basic_browserstep(client, live_server):
     wait_for_all_checks(client)
 
     uuid = extract_UUID_from_client(client)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n >= 1, "Watch history had atleast 1 (everything fetched OK)"
+
+    assert b"This text should be removed" not in res.data
 
     # Check HTML conversion detected and workd
     res = client.get(
@@ -114,13 +127,19 @@ def test_basic_browserstep(client, live_server):
     assert b"This text should be removed" not in res.data
     assert b"I smell JavaScript because the button was pressed" in res.data
 
+    assert b"testheader: yes" in res.data
+    assert b"user-agent: mycustomagent" in res.data
+
+    four_o_four_url =  url_for('test_endpoint', status_code=404, _external=True)
+    four_o_four_url = four_o_four_url.replace('localhost.localdomain', 'cdio')
+    four_o_four_url = four_o_four_url.replace('localhost', 'cdio')
+
     # now test for 404 errors
     res = client.post(
         url_for("edit_page", uuid=uuid, unpause_on_save=1),
         data={
-              "url": "https://changedetection.io/404",
+              "url": four_o_four_url,
               "tags": "",
-              "headers": "",
               'fetch_backend': "html_webdriver",
               'browser_steps-0-operation': 'Goto site',
               'browser_steps-1-operation': 'Click element',

changedetectionio/update_worker.py

@@ -462,7 +462,7 @@ class update_worker(threading.Thread):
                     except Exception as e:
                         logger.error(f"Exception reached processing watch UUID: {uuid}")
                         logger.error(str(e))
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Exception: " + str(e)})
                         # Other serious error
                         process_changedetection_results = False
 #                        import traceback

requirements.txt

@@ -9,6 +9,7 @@ flask-login>=0.6.3
 flask-paginate
 flask_expects_json~=1.7
 flask_restful
+flask_cors # For the Chrome extension to operate
 flask_wtf~=1.2
 flask~=2.3
 inscriptis~=2.2
@@ -35,10 +36,12 @@ dnspython==2.3.0 # related to eventlet fixes
 # jq not available on Windows so must be installed manually
 
 # Notification library
-apprise~=1.7.1
+apprise~=1.7.4
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
-paho-mqtt
+# 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
 
 # This mainly affects some ARM builds, which unlike the other builds ignores "ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1"
 # so without this pinning, the newer versions on ARM will forcefully try to build rust, which results in "rust compiler not found"
@@ -49,7 +52,7 @@ cryptography~=3.4
 beautifulsoup4
 
 # XPath filtering, lxml is required by bs4 anyway, but put it here to be safe.
-lxml
+lxml >=4.8.0,<6
 
 # XPath 2.0-3.1 support - 4.2.0 broke something?
 elementpath==4.1.5
@@ -72,7 +75,7 @@ pillow
 # playwright is installed at Dockerfile build time because it's not available on all platforms
 
 # experimental release
-pyppeteer-ng==2.0.0rc2
+pyppeteer-ng==2.0.0rc5
 
 # Include pytest, so if theres a support issue we can ask them to run these tests on their setup
 pytest ~=7.2