Skip removing old screenshots for notification tests

.github/workflows/test-only.yml

@@ -28,7 +28,6 @@ jobs:
     uses: ./.github/workflows/test-stack-reusable-workflow.yml
     with:
       python-version: '3.11'
-      skip-pypuppeteer: true
 
   test-application-3-12:
     needs: lint-code

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

@@ -7,7 +7,7 @@ on:
         description: 'Python version to use'
         required: true
         type: string
-        default: '3.10'
+        default: '3.11'
       skip-pypuppeteer:
         description: 'Skip PyPuppeteer (not supported in 3.11/3.12)'
         required: false

Dockerfile

@@ -1,8 +1,5 @@
 # pip dependencies install stage
 
-# @NOTE! I would love to move to 3.11 but it breaks the async handler in changedetectionio/content_fetchers/puppeteer.py
-#        If you know how to fix it, please do! and test it for both 3.10 and 3.11
-
 ARG PYTHON_VERSION=3.11
 
 FROM python:${PYTHON_VERSION}-slim-bookworm AS builder

README.md

@@ -89,7 +89,7 @@ _Need an actual Chrome runner with Javascript support? We support fetching via W
 #### Key Features
 
 - Lots of trigger filters, such as "Trigger on text", "Remove text by selector", "Ignore text", "Extract text", also using regular-expressions!
-- Target elements with xPath(1.0) and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
+- Target elements with xPath 1 and xPath 2, CSS Selectors, Easily monitor complex JSON with JSONPath or jq
 - Switch between fast non-JS and Chrome JS based "fetchers"
 - Track changes in PDF files (Monitor text changed in the PDF, Also monitor PDF filesize and checksums)
 - Easily specify how often a site should be checked

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.49.7'
+__version__ = '0.49.12'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError
@@ -11,6 +11,7 @@ os.environ['EVENTLET_NO_GREENDNS'] = 'yes'
 import eventlet
 import eventlet.wsgi
 import getopt
+import platform
 import signal
 import socket
 import sys
@@ -19,7 +20,6 @@ from changedetectionio import store
 from changedetectionio.flask_app import changedetection_app
 from loguru import logger
 
-
 # Only global so we can access it in the signal handler
 app = None
 datastore = None
@@ -29,8 +29,6 @@ def get_version():
 
 # Parent wrapper or OS sends us a SIGTERM/SIGINT, do everything required for a clean shutdown
 def sigshutdown_handler(_signo, _stack_frame):
-    global app
-    global datastore
     name = signal.Signals(_signo).name
     logger.critical(f'Shutdown: Got Signal - {name} ({_signo}), Saving DB to disk and calling shutdown')
     datastore.sync_to_json()
@@ -147,6 +145,19 @@ def main():
 
     signal.signal(signal.SIGTERM, sigshutdown_handler)
     signal.signal(signal.SIGINT, sigshutdown_handler)
+    
+    # Custom signal handler for memory cleanup
+    def sigusr_clean_handler(_signo, _stack_frame):
+        from changedetectionio.gc_cleanup import memory_cleanup
+        logger.info('SIGUSR1 received: Running memory cleanup')
+        return memory_cleanup(app)
+
+    # Register the SIGUSR1 signal handler
+    # Only register the signal handler if running on Linux
+    if platform.system() == "Linux":
+        signal.signal(signal.SIGUSR1, sigusr_clean_handler)
+    else:
+        logger.info("SIGUSR1 handler only registered on Linux, skipped.")
 
     # Go into cleanup mode
     if do_cleanup:

changedetectionio/api/Search.py

@@ -0,0 +1,51 @@
+from flask_restful import Resource, abort
+from flask import request
+from . import auth
+
+class Search(Resource):
+    def __init__(self, **kwargs):
+        # datastore is a black box dependency
+        self.datastore = kwargs['datastore']
+
+    @auth.check_token
+    def get(self):
+        """
+        @api {get} /api/v1/search Search for watches
+        @apiDescription Search watches by URL or title text
+        @apiExample {curl} Example usage:
+            curl "http://localhost:5000/api/v1/search?q=https://example.com/page1" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            curl "http://localhost:5000/api/v1/search?q=https://example.com/page1?tag=Favourites" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            curl "http://localhost:5000/api/v1/search?q=https://example.com?partial=true" -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+        @apiName Search
+        @apiGroup Watch Management
+        @apiQuery {String} q Search query to match against watch URLs and titles
+        @apiQuery {String} [tag] Optional name of tag to limit results (name not UUID)
+        @apiQuery {String} [partial] Allow partial matching of URL query
+        @apiSuccess (200) {Object} JSON Object containing matched watches
+        """
+        query = request.args.get('q', '').strip()
+        tag_limit = request.args.get('tag', '').strip()
+        from changedetectionio.strtobool import strtobool
+        partial = bool(strtobool(request.args.get('partial', '0'))) if 'partial' in request.args else False
+
+        # Require a search query
+        if not query:
+            abort(400, message="Search query 'q' parameter is required")
+
+        # Use the search function from the datastore
+        matching_uuids = self.datastore.search_watches_for_url(query=query, tag_limit=tag_limit, partial=partial)
+
+        # Build the response with watch details
+        results = {}
+        for uuid in matching_uuids:
+            watch = self.datastore.data['watching'].get(uuid)
+            results[uuid] = {
+                'last_changed': watch.last_changed,
+                'last_checked': watch['last_checked'],
+                'last_error': watch['last_error'],
+                'title': watch['title'],
+                'url': watch['url'],
+                'viewed': watch.viewed
+            }
+
+        return results, 200

changedetectionio/apprise_asset.py

@@ -1,12 +0,0 @@
-from changedetectionio import apprise_plugin
-import apprise
-
-# Create our AppriseAsset and populate it with some of our new values:
-# https://github.com/caronc/apprise/wiki/Development_API#the-apprise-asset-object
-asset = apprise.AppriseAsset(
-   image_url_logo='https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
-)
-
-asset.app_id = "changedetection.io"
-asset.app_desc = "ChangeDetection.io best and simplest website monitoring and change detection"
-asset.app_url = "https://changedetection.io"

changedetectionio/apprise_plugin/__init__.py

@@ -1,98 +0,0 @@
-# include the decorator
-from apprise.decorators import notify
-from loguru import logger
-from requests.structures import CaseInsensitiveDict
-
-
-@notify(on="delete")
-@notify(on="deletes")
-@notify(on="get")
-@notify(on="gets")
-@notify(on="post")
-@notify(on="posts")
-@notify(on="put")
-@notify(on="puts")
-def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
-    import requests
-    import json
-    import re
-
-    from urllib.parse import unquote_plus
-    from apprise.utils.parse import parse_url as apprise_parse_url
-
-    url = kwargs['meta'].get('url')
-    schema = kwargs['meta'].get('schema').lower().strip()
-
-    # Choose POST, GET etc from requests
-    method =  re.sub(rf's$', '', schema)
-    requests_method = getattr(requests, method)
-
-    params = CaseInsensitiveDict({}) # Added to requests
-    auth = None
-    has_error = False
-
-    # Convert /foobar?+some-header=hello to proper header dictionary
-    results = apprise_parse_url(url)
-
-    # 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 = CaseInsensitiveDict({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
-    # In Apprise, it relies on prefixing each request arg with "-", because it uses say &method=update as a flag for apprise
-    # 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[unquote_plus(k)] = unquote_plus(v)
-
-    # Determine Authentication
-    auth = ''
-    if results.get('user') and results.get('password'):
-        auth = (unquote_plus(results.get('user')), unquote_plus(results.get('user')))
-    elif results.get('user'):
-        auth = (unquote_plus(results.get('user')))
-
-    # If it smells like it could be JSON and no content-type was already set, offer a default content type.
-    if body and '{' in body[:100] and not headers.get('Content-Type'):
-        json_header = 'application/json; charset=utf-8'
-        try:
-            # Try if it's JSON
-            json.loads(body)
-            headers['Content-Type'] = json_header
-        except ValueError as e:
-            logger.warning(f"Could not automatically add '{json_header}' header to the notification because the document failed to parse as JSON: {e}")
-            pass
-
-    # POSTS -> HTTPS etc
-    if schema.lower().endswith('s'):
-        url = re.sub(rf'^{schema}', 'https', results.get('url'))
-    else:
-        url = re.sub(rf'^{schema}', 'http', results.get('url'))
-
-    status_str = ''
-    try:
-        r = requests_method(url,
-          auth=auth,
-          data=body.encode('utf-8') if type(body) is str else body,
-          headers=headers,
-          params=params
-        )
-
-        if not (200 <= r.status_code < 300):
-            status_str = f"Error sending '{method.upper()}' request to {url} - Status: {r.status_code}: '{r.reason}'"
-            logger.error(status_str)
-            has_error = True
-        else:
-            logger.info(f"Sent '{method.upper()}' request to {url}")
-            has_error = False
-
-    except requests.RequestException as e:
-        status_str = f"Error sending '{method.upper()}' request to {url} - {str(e)}"
-        logger.error(status_str)
-        has_error = True
-
-    if has_error:
-        raise TypeError(status_str)
-
-    return True

changedetectionio/apprise_plugin/assets.py

@@ -0,0 +1,16 @@
+from apprise import AppriseAsset
+
+# Refer to:
+# https://github.com/caronc/apprise/wiki/Development_API#the-apprise-asset-object
+
+APPRISE_APP_ID = "changedetection.io"
+APPRISE_APP_DESC = "ChangeDetection.io best and simplest website monitoring and change detection"
+APPRISE_APP_URL = "https://changedetection.io"
+APPRISE_AVATAR_URL = "https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png"
+
+apprise_asset = AppriseAsset(
+    app_id=APPRISE_APP_ID,
+    app_desc=APPRISE_APP_DESC,
+    app_url=APPRISE_APP_URL,
+    image_url_logo=APPRISE_AVATAR_URL,
+)

changedetectionio/apprise_plugin/custom_handlers.py

@@ -0,0 +1,112 @@
+import json
+import re
+from urllib.parse import unquote_plus
+
+import requests
+from apprise.decorators import notify
+from apprise.utils.parse import parse_url as apprise_parse_url
+from loguru import logger
+from requests.structures import CaseInsensitiveDict
+
+SUPPORTED_HTTP_METHODS = {"get", "post", "put", "delete", "patch", "head"}
+
+
+def notify_supported_methods(func):
+    for method in SUPPORTED_HTTP_METHODS:
+        func = notify(on=method)(func)
+        # Add support for https, for each supported http method
+        func = notify(on=f"{method}s")(func)
+    return func
+
+
+def _get_auth(parsed_url: dict) -> str | tuple[str, str]:
+    user: str | None = parsed_url.get("user")
+    password: str | None = parsed_url.get("password")
+
+    if user is not None and password is not None:
+        return (unquote_plus(user), unquote_plus(password))
+
+    if user is not None:
+        return unquote_plus(user)
+
+    return ""
+
+
+def _get_headers(parsed_url: dict, body: str) -> CaseInsensitiveDict:
+    headers = CaseInsensitiveDict(
+        {unquote_plus(k).title(): unquote_plus(v) for k, v in parsed_url["qsd+"].items()}
+    )
+
+    # If Content-Type is not specified, guess if the body is a valid JSON
+    if headers.get("Content-Type") is None:
+        try:
+            json.loads(body)
+            headers["Content-Type"] = "application/json; charset=utf-8"
+        except Exception:
+            pass
+
+    return headers
+
+
+def _get_params(parsed_url: dict) -> CaseInsensitiveDict:
+    # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
+    # In Apprise, it relies on prefixing each request arg with "-", because it uses say &method=update as a flag for apprise
+    # but here we are making straight requests, so we need todo convert this against apprise's logic
+    params = CaseInsensitiveDict(
+        {
+            unquote_plus(k): unquote_plus(v)
+            for k, v in parsed_url["qsd"].items()
+            if k.strip("-") not in parsed_url["qsd-"]
+            and k.strip("+") not in parsed_url["qsd+"]
+        }
+    )
+
+    return params
+
+
+@notify_supported_methods
+def apprise_http_custom_handler(
+    body: str,
+    title: str,
+    notify_type: str,
+    meta: dict,
+    *args,
+    **kwargs,
+) -> bool:
+    url: str = meta.get("url")
+    schema: str = meta.get("schema")
+    method: str = re.sub(r"s$", "", schema).upper()
+
+    # Convert /foobar?+some-header=hello to proper header dictionary
+    parsed_url: dict[str, str | dict | None] | None = apprise_parse_url(url)
+    if parsed_url is None:
+        return False
+
+    auth = _get_auth(parsed_url=parsed_url)
+    headers = _get_headers(parsed_url=parsed_url, body=body)
+    params = _get_params(parsed_url=parsed_url)
+
+    url = re.sub(rf"^{schema}", "https" if schema.endswith("s") else "http", parsed_url.get("url"))
+
+    try:
+        response = requests.request(
+            method=method,
+            url=url,
+            auth=auth,
+            headers=headers,
+            params=params,
+            data=body.encode("utf-8") if isinstance(body, str) else body,
+        )
+
+        response.raise_for_status()
+
+        logger.info(f"Successfully sent custom notification to {url}")
+        return True
+
+    except requests.RequestException as e:
+        logger.error(f"Remote host error while sending custom notification to {url}: {e}")
+        return False
+
+    except Exception as e:
+        logger.error(f"Unexpected error occurred while sending custom notification to {url}: {e}")
+        return False

changedetectionio/auth_decorator.py

@@ -20,10 +20,7 @@ def login_optionally_required(func):
         has_password_enabled = datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False)
 
         # Permitted
-        if request.endpoint and 'static_content' in request.endpoint and request.view_args and request.view_args.get('group') == 'styles':
-            return func(*args, **kwargs)
-        # Permitted
-        elif request.endpoint and 'diff_history_page' in request.endpoint and datastore.data['settings']['application'].get('shared_diff_access'):
+        if request.endpoint and 'diff_history_page' in request.endpoint and datastore.data['settings']['application'].get('shared_diff_access'):
             return func(*args, **kwargs)
         elif request.method in flask_login.config.EXEMPT_METHODS:
             return func(*args, **kwargs)

changedetectionio/blueprint/browser_steps/__init__.py

@@ -23,7 +23,6 @@ from loguru import logger
 browsersteps_sessions = {}
 io_interface_context = None
 import json
-import base64
 import hashlib
 from flask import Response
 
@@ -34,10 +33,8 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         from . import nonContext
         from . import browser_steps
         import time
-        global browsersteps_sessions
         global io_interface_context
 
-
         # We keep the playwright session open for many minutes
         keepalive_seconds = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
 
@@ -104,8 +101,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # A new session was requested, return sessionID
 
         import uuid
-        global browsersteps_sessions
-
         browsersteps_session_id = str(uuid.uuid4())
         watch_uuid = request.args.get('uuid')
 
@@ -149,7 +144,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def browsersteps_ui_update():
         import base64
         import playwright._impl._errors
-        global browsersteps_sessions
         from changedetectionio.blueprint.browser_steps import browser_steps
 
         remaining =0

changedetectionio/blueprint/rss/__init__.py

@@ -1,102 +1 @@
-import time
-import datetime
-import pytz
-from flask import Blueprint, make_response, request, url_for
-from loguru import logger
-from feedgen.feed import FeedGenerator
-
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio.safe_jinja import render as jinja_render
-
-def construct_blueprint(datastore: ChangeDetectionStore):
-    rss_blueprint = Blueprint('rss', __name__)
-    
-    # Import the login decorator if needed
-    # from changedetectionio.auth_decorator import login_optionally_required
-    @rss_blueprint.route("", methods=['GET'])
-    def feed():
-        now = time.time()
-        # Always requires token set
-        app_rss_token = datastore.data['settings']['application'].get('rss_access_token')
-        rss_url_token = request.args.get('token')
-        if rss_url_token != app_rss_token:
-            return "Access denied, bad token", 403
-
-        from changedetectionio import diff
-        limit_tag = request.args.get('tag', '').lower().strip()
-        # Be sure limit_tag is a uuid
-        for uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
-            if limit_tag == tag.get('title', '').lower().strip():
-                limit_tag = uuid
-
-        # Sort by last_changed and add the uuid which is usually the key..
-        sorted_watches = []
-
-        # @todo needs a .itemsWithTag() or something - then we can use that in Jinaj2 and throw this away
-        for uuid, watch in datastore.data['watching'].items():
-            # @todo tag notification_muted skip also (improve Watch model)
-            if datastore.data['settings']['application'].get('rss_hide_muted_watches') and watch.get('notification_muted'):
-                continue
-            if limit_tag and not limit_tag in watch['tags']:
-                continue
-            watch['uuid'] = uuid
-            sorted_watches.append(watch)
-
-        sorted_watches.sort(key=lambda x: x.last_changed, reverse=False)
-
-        fg = FeedGenerator()
-        fg.title('changedetection.io')
-        fg.description('Feed description')
-        fg.link(href='https://changedetection.io')
-
-        for watch in sorted_watches:
-
-            dates = list(watch.history.keys())
-            # Re #521 - Don't bother processing this one if theres less than 2 snapshots, means we never had a change detected.
-            if len(dates) < 2:
-                continue
-
-            if not watch.viewed:
-                # Re #239 - GUID needs to be individual for each event
-                # @todo In the future make this a configurable link back (see work on BASE_URL https://github.com/dgtlmoon/changedetection.io/pull/228)
-                guid = "{}/{}".format(watch['uuid'], watch.last_changed)
-                fe = fg.add_entry()
-
-                # Include a link to the diff page, they will have to login here to see if password protection is enabled.
-                # Description is the page you watch, link takes you to the diff JS UI page
-                # Dict val base_url will get overriden with the env var if it is set.
-                ext_base_url = datastore.data['settings']['application'].get('active_base_url')
-
-                # Because we are called via whatever web server, flask should figure out the right path (
-                diff_link = {'href': url_for('ui.ui_views.diff_history_page', uuid=watch['uuid'], _external=True)}
-
-                fe.link(link=diff_link)
-
-                # @todo watch should be a getter - watch.get('title') (internally if URL else..)
-
-                watch_title = watch.get('title') if watch.get('title') else watch.get('url')
-                fe.title(title=watch_title)
-
-                html_diff = diff.render_diff(previous_version_file_contents=watch.get_history_snapshot(dates[-2]),
-                                             newest_version_file_contents=watch.get_history_snapshot(dates[-1]),
-                                             include_equal=False,
-                                             line_feed_sep="<br>")
-
-                # @todo Make this configurable and also consider html-colored markup
-                # @todo User could decide if <link> goes to the diff page, or to the watch link
-                rss_template = "<html><body>\n<h4><a href=\"{{watch_url}}\">{{watch_title}}</a></h4>\n<p>{{html_diff}}</p>\n</body></html>\n"
-                content = jinja_render(template_str=rss_template, watch_title=watch_title, html_diff=html_diff, watch_url=watch.link)
-
-                fe.content(content=content, type='CDATA')
-
-                fe.guid(guid, permalink=False)
-                dt = datetime.datetime.fromtimestamp(int(watch.newest_history_key))
-                dt = dt.replace(tzinfo=pytz.UTC)
-                fe.pubDate(dt)
-
-        response = make_response(fg.rss_str())
-        response.headers.set('Content-Type', 'application/rss+xml;charset=utf-8')
-        logger.trace(f"RSS generated in {time.time() - now:.3f}s")
-        return response
-
-    return rss_blueprint
+RSS_FORMAT_TYPES = [('plaintext', 'Plain text'), ('html', 'HTML Color')]

changedetectionio/blueprint/rss/blueprint.py

@@ -0,0 +1,147 @@
+
+from changedetectionio.safe_jinja import render as jinja_render
+from changedetectionio.store import ChangeDetectionStore
+from feedgen.feed import FeedGenerator
+from flask import Blueprint, make_response, request, url_for, redirect
+from loguru import logger
+import datetime
+import pytz
+import re
+import time
+
+
+BAD_CHARS_REGEX=r'[\x00-\x08\x0B\x0C\x0E-\x1F]'
+
+# Anything that is not text/UTF-8 should be stripped before it breaks feedgen (such as binary data etc)
+def scan_invalid_chars_in_rss(content):
+    for match in re.finditer(BAD_CHARS_REGEX, content):
+        i = match.start()
+        bad_char = content[i]
+        hex_value = f"0x{ord(bad_char):02x}"
+        # Grab context
+        start = max(0, i - 20)
+        end = min(len(content), i + 21)
+        context = content[start:end].replace('\n', '\\n').replace('\r', '\\r')
+        logger.warning(f"Invalid char {hex_value} at pos {i}: ...{context}...")
+        # First match is enough
+        return True
+
+    return False
+
+
+def clean_entry_content(content):
+    cleaned = re.sub(BAD_CHARS_REGEX, '', content)
+    return cleaned
+
+def construct_blueprint(datastore: ChangeDetectionStore):
+    rss_blueprint = Blueprint('rss', __name__)
+
+    # Some RSS reader situations ended up with rss/ (forward slash after RSS) due
+    # to some earlier blueprint rerouting work, it should goto feed.
+    @rss_blueprint.route("/", methods=['GET'])
+    def extraslash():
+        return redirect(url_for('rss.feed'))
+
+    # Import the login decorator if needed
+    # from changedetectionio.auth_decorator import login_optionally_required
+    @rss_blueprint.route("", methods=['GET'])
+    def feed():
+        now = time.time()
+        # Always requires token set
+        app_rss_token = datastore.data['settings']['application'].get('rss_access_token')
+        rss_url_token = request.args.get('token')
+        if rss_url_token != app_rss_token:
+            return "Access denied, bad token", 403
+
+        from changedetectionio import diff
+        limit_tag = request.args.get('tag', '').lower().strip()
+        # Be sure limit_tag is a uuid
+        for uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
+            if limit_tag == tag.get('title', '').lower().strip():
+                limit_tag = uuid
+
+        # Sort by last_changed and add the uuid which is usually the key..
+        sorted_watches = []
+
+        # @todo needs a .itemsWithTag() or something - then we can use that in Jinaj2 and throw this away
+        for uuid, watch in datastore.data['watching'].items():
+            # @todo tag notification_muted skip also (improve Watch model)
+            if datastore.data['settings']['application'].get('rss_hide_muted_watches') and watch.get('notification_muted'):
+                continue
+            if limit_tag and not limit_tag in watch['tags']:
+                continue
+            watch['uuid'] = uuid
+            sorted_watches.append(watch)
+
+        sorted_watches.sort(key=lambda x: x.last_changed, reverse=False)
+
+        fg = FeedGenerator()
+        fg.title('changedetection.io')
+        fg.description('Feed description')
+        fg.link(href='https://changedetection.io')
+
+        html_colour_enable = False
+        if datastore.data['settings']['application'].get('rss_content_format') == 'html':
+            html_colour_enable = True
+
+        for watch in sorted_watches:
+
+            dates = list(watch.history.keys())
+            # Re #521 - Don't bother processing this one if theres less than 2 snapshots, means we never had a change detected.
+            if len(dates) < 2:
+                continue
+
+            if not watch.viewed:
+                # Re #239 - GUID needs to be individual for each event
+                # @todo In the future make this a configurable link back (see work on BASE_URL https://github.com/dgtlmoon/changedetection.io/pull/228)
+                guid = "{}/{}".format(watch['uuid'], watch.last_changed)
+                fe = fg.add_entry()
+
+                # Include a link to the diff page, they will have to login here to see if password protection is enabled.
+                # Description is the page you watch, link takes you to the diff JS UI page
+                # Dict val base_url will get overriden with the env var if it is set.
+                ext_base_url = datastore.data['settings']['application'].get('active_base_url')
+                # @todo fix
+
+                # Because we are called via whatever web server, flask should figure out the right path (
+                diff_link = {'href': url_for('ui.ui_views.diff_history_page', uuid=watch['uuid'], _external=True)}
+
+                fe.link(link=diff_link)
+
+                # @todo watch should be a getter - watch.get('title') (internally if URL else..)
+
+                watch_title = watch.get('title') if watch.get('title') else watch.get('url')
+                fe.title(title=watch_title)
+                try:
+
+                    html_diff = diff.render_diff(previous_version_file_contents=watch.get_history_snapshot(dates[-2]),
+                                                 newest_version_file_contents=watch.get_history_snapshot(dates[-1]),
+                                                 include_equal=False,
+                                                 line_feed_sep="<br>",
+                                                 html_colour=html_colour_enable
+                                                 )
+                except FileNotFoundError as e:
+                    html_diff = f"History snapshot file for watch {watch.get('uuid')}@{watch.last_changed} - '{watch.get('title')} not found."
+
+                # @todo Make this configurable and also consider html-colored markup
+                # @todo User could decide if <link> goes to the diff page, or to the watch link
+                rss_template = "<html><body>\n<h4><a href=\"{{watch_url}}\">{{watch_title}}</a></h4>\n<p>{{html_diff}}</p>\n</body></html>\n"
+
+                content = jinja_render(template_str=rss_template, watch_title=watch_title, html_diff=html_diff, watch_url=watch.link)
+
+                # Out of range chars could also break feedgen
+                if scan_invalid_chars_in_rss(content):
+                    content = clean_entry_content(content)
+
+                fe.content(content=content, type='CDATA')
+                fe.guid(guid, permalink=False)
+                dt = datetime.datetime.fromtimestamp(int(watch.newest_history_key))
+                dt = dt.replace(tzinfo=pytz.UTC)
+                fe.pubDate(dt)
+
+        response = make_response(fg.rss_str())
+        response.headers.set('Content-Type', 'application/rss+xml;charset=utf-8')
+        logger.trace(f"RSS generated in {time.time() - now:.3f}s")
+        return response
+
+    return rss_blueprint

changedetectionio/blueprint/settings/templates/settings.html

@@ -78,7 +78,10 @@
                         {{ render_field(form.application.form.pager_size) }}
                         <span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
                     </div>
-
+                    <div class="pure-control-group">
+                        {{ render_field(form.application.form.rss_content_format) }}
+                        <span class="pure-form-message-inline">Love RSS? Does your reader support HTML? Set it here</span>
+                    </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.extract_title_as_title) }}
                         <span class="pure-form-message-inline">Note: This will automatically apply to all existing watches.</span>
@@ -214,7 +217,7 @@ nav
                         <a id="chrome-extension-link"
                            title="Try our new Chrome Extension!"
                            href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
-                            <img alt="Chrome store icon" src="{{ url_for('static_content', group='images', filename='Google-Chrome-icon.png') }}" alt="Chrome">
+                            <img alt="Chrome store icon" src="{{ url_for('static_content', group='images', filename='google-chrome-icon.png') }}" alt="Chrome">
                             Chrome Webstore
                         </a>
                     </p>

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

@@ -13,6 +13,7 @@
     /*const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');*/
 /*{% endif %}*/
 
+{% set has_tag_filters_extra='' %}
 
 </script>
 
@@ -46,59 +47,12 @@
             </div>
 
             <div class="tab-pane-inner" id="filters-and-triggers">
-                    <div class="pure-control-group">
-                        {% set field = render_field(form.include_filters,
-                            rows=5,
-                            placeholder="#example
-xpath://body/div/span[contains(@class, 'example-class')]",
-                            class="m-d")
-                        %}
-                        {{ field }}
-                        {% if '/text()' in  field %}
-                          <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br>
-                        {% endif %}
-                        <span class="pure-form-message-inline">One CSS, xPath, JSON Path/JQ selector per line, <i>any</i> rules that matches will be used.<br>
-                    <div data-target="#advanced-help-selectors" class="toggle-show pure-button button-tag button-xsmall">Show advanced help and tips</div>
-                    <ul id="advanced-help-selectors">
-                        <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
-                        <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
-                            <ul>
-                                <li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required,  <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
-                                {% if jq_support %}
-                                <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>. Prefix <code>jqraw:</code> outputs the results as text instead of a JSON list.</li>
-                                {% else %}
-                                <li>jq support not installed</li>
-                                {% endif %}
-                            </ul>
-                        </li>
-                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash. To specify XPath to be used explicitly or the XPath rule starts with an XPath function: Prefix with <code>xpath:</code>
-                            <ul>
-                                <li>Example:  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath:count(//*[contains(@class, 'sametext')])</code>, <a
-                                href="http://xpather.com/" target="new">test your XPath here</a></li>
-                                <li>Example: Get all titles from an RSS feed <code>//title/text()</code></li>
-                                <li>To use XPath1.0: Prefix with <code>xpath1:</code></li>
-                            </ul>
-                            </li>
-                    </ul>
-                    Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
-                                href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
-                </span>
-                    </div>
-                <fieldset class="pure-control-group">
-                    {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
-footer
-nav
-.stockticker
-//*[contains(text(), 'Advertisement')]") }}
-                    <span class="pure-form-message-inline">
-                        <ul>
-                          <li> Remove HTML element(s) by CSS and XPath selectors before text conversion. </li>
-                          <li> Don't paste HTML here, use only CSS and XPath selectors </li>
-                          <li> Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML. </li>
-                        </ul>
-                      </span>
-                </fieldset>
-
+                <p>These settings are <strong><i>added</i></strong> to any existing watch configurations.</p>
+                {% include "edit/include_subtract.html" %}
+                <div class="text-filtering border-fieldset">
+                    <h3>Text filtering</h3>
+                    {% include "edit/text-options.html" %}
+                </div>
             </div>
 
         {# rendered sub Template #}

changedetectionio/blueprint/ui/__init__.py

@@ -96,12 +96,13 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
             uuid = list(datastore.data['watching'].keys()).pop()
 
         new_uuid = datastore.clone(uuid)
-        if new_uuid:
-            if not datastore.data['watching'].get(uuid).get('paused'):
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
-            flash('Cloned.')
 
-        return redirect(url_for('watchlist.index'))
+        if not datastore.data['watching'].get(uuid).get('paused'):
+            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
+
+        flash('Cloned, you are editing the new watch.')
+
+        return redirect(url_for("ui.ui_edit.edit_page", uuid=new_uuid))
 
     @ui_blueprint.route("/checknow", methods=['GET'])
     @login_optionally_required
@@ -124,7 +125,10 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
 
         else:
             # Recheck all, including muted
-            for watch_uuid, watch in datastore.data['watching'].items():
+            # Get most overdue first
+            for k in sorted(datastore.data['watching'].items(), key=lambda item: item[1].get('last_checked', 0)):
+                watch_uuid = k[0]
+                watch = k[1]
                 if not watch['paused']:
                     if watch_uuid not in running_uuids:
                         if with_errors and not watch.get('last_error'):
@@ -139,7 +143,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_updat
         if i == 1:
             flash("Queued 1 watch for rechecking.")
         if i > 1:
-            flash("Queued {} watches for rechecking.".format(i))
+            flash(f"Queued {i} watches for rechecking.")
         if i == 0:
             flash("No watches available to recheck.")
 

changedetectionio/blueprint/ui/notification.py

@@ -4,6 +4,7 @@ from loguru import logger
 
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
+from changedetectionio.notification import process_notification
 
 def construct_blueprint(datastore: ChangeDetectionStore):
     notification_blueprint = Blueprint('ui_notification', __name__, template_folder="../ui/templates")
@@ -17,11 +18,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         # Watch_uuid could be unset in the case it`s used in tag editor, global settings
         import apprise
-        from changedetectionio.apprise_asset import asset
-        apobj = apprise.Apprise(asset=asset)
+        from ...apprise_plugin.assets import apprise_asset
+        from ...apprise_plugin.custom_handlers import apprise_http_custom_handler  # noqa: F401
+        apobj = apprise.Apprise(asset=apprise_asset)
 
-        # so that the custom endpoints are registered
-        from changedetectionio.apprise_plugin import apprise_custom_api_call_wrapper
         is_global_settings_form = request.args.get('mode', '') == 'global-settings'
         is_group_settings_form = request.args.get('mode', '') == 'group-settings'
 
@@ -90,7 +90,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
             n_object['as_async'] = False
             n_object.update(watch.extra_notification_token_values())
-            from changedetectionio.notification import process_notification
             sent_obj = process_notification(n_object, datastore)
 
         except Exception as e:

changedetectionio/blueprint/watchlist/__init__.py

@@ -1,7 +1,5 @@
-import flask_login
 import os
 import time
-import timeago
 
 from flask import Blueprint, request, make_response, render_template, redirect, url_for, flash, session
 from flask_login import current_user
@@ -10,7 +8,6 @@ from flask_paginate import Pagination, get_page_parameter
 from changedetectionio import forms
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio.auth_decorator import login_optionally_required
-from changedetectionio.strtobool import strtobool
 
 def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
     watchlist_blueprint = Blueprint('watchlist', __name__, template_folder="templates")
@@ -77,7 +74,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
         sorted_tags = sorted(datastore.data['settings']['application'].get('tags').items(), key=lambda x: x[1]['title'])
         output = render_template(
             "watch-overview.html",
-                                 # Don't link to hosting when we're on the hosting environment
                                  active_tag=active_tag,
                                  active_tag_uuid=active_tag_uuid,
                                  app_rss_token=datastore.data['settings']['application'].get('rss_access_token'),
@@ -88,9 +84,10 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                                  has_proxies=datastore.proxy_list,
                                  has_unviewed=datastore.has_unviewed,
                                  hosted_sticky=os.getenv("SALTED_PASS", False) == False,
+                                 now_time_server=time.time(),
                                  pagination=pagination,
                                  queued_uuids=[q_uuid.item['uuid'] for q_uuid in update_q.queue],
-                                 search_q=request.args.get('q','').strip(),
+                                 search_q=request.args.get('q', '').strip(),
                                  sort_attribute=request.args.get('sort') if request.args.get('sort') else request.cookies.get('sort'),
                                  sort_order=request.args.get('order') if request.args.get('order') else request.cookies.get('order'),
                                  system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),

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

@@ -3,7 +3,16 @@
 {% from '_helpers.html' import render_simple_field, render_field, render_nolabel_field, sort_by_title %}
 <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
 <script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
+<script>let nowtimeserver={{ now_time_server }};</script>
 
+<style>
+.checking-now .last-checked {
+    background-image: linear-gradient(to bottom, transparent 0%, rgba(0,0,0,0.05) 40%, rgba(0,0,0,0.1) 100%);
+    background-size: 0 100%;
+    background-repeat: no-repeat;
+    transition: background-size 0.9s ease
+}
+</style>
 <div class="box">
 
     <form class="pure-form" action="{{ url_for('ui.ui_views.form_quick_watch_add', tag=active_tag_uuid) }}" method="POST" id="new-watch-form">
@@ -91,8 +100,8 @@
             {% endif %}
             {% for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))|pagination_slice(skip=pagination.skip) %}
 
-                {% set is_unviewed =  watch.newest_history_key| int > watch.last_viewed and watch.history_n>=2 %}
-
+                {% set is_unviewed = watch.newest_history_key| int > watch.last_viewed and watch.history_n>=2 %}
+                {% set checking_now = is_checking_now(watch) %}
             <tr id="{{ watch.uuid }}"
                 class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }} processor-{{ watch['processor'] }}
                 {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
@@ -100,7 +109,9 @@
                 {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
                 {% if is_unviewed %}unviewed{% endif %}
                 {% if watch.has_restock_info %} has-restock-info {% if watch['restock']['in_stock'] %}in-stock{% else %}not-in-stock{% endif %} {% else %}no-restock-info{% endif %}
-                {% if watch.uuid in queued_uuids %}queued{% endif %}">
+                {% if watch.uuid in queued_uuids %}queued{% endif %}
+                {% if checking_now %}checking-now{% endif %}
+                ">
                 <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span>{{ loop.index+pagination.skip }}</span></td>
                 <td class="inline watch-controls">
                     {% if not watch.paused %}
@@ -119,7 +130,7 @@
                          or (  watch.get_fetch_backend == "system" and system_default_fetcher == 'html_webdriver'  )
                          or "extra_browser_" in watch.get_fetch_backend
                     %}
-                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" alt="Using a Chrome browser" title="Using a Chrome browser" >
+                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='google-chrome-icon.png')}}" alt="Using a Chrome browser" title="Using a Chrome browser" >
                     {% endif %}
 
                     {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" >{% endif %}
@@ -178,7 +189,14 @@
                     {% endif %}
                 </td>
 {% endif %}
-                <td class="last-checked" data-timestamp="{{ watch.last_checked }}">{{watch|format_last_checked_time|safe}}</td>
+            {#last_checked becomes fetch-start-time#}
+                <td class="last-checked" data-timestamp="{{ watch.last_checked }}" {% if checking_now %} data-fetchduration={{ watch.fetch_time }} data-eta_complete="{{ watch.last_checked+watch.fetch_time }}" {% endif %} >
+                    {% if checking_now %}
+                        <span class="spinner"></span><span> Checking now</span>
+                    {% else %}
+                        {{watch|format_last_checked_time|safe}}</td>
+                    {% endif %}
+
                 <td class="last-changed" data-timestamp="{{ watch.last_changed }}">{% if watch.history_n >=2 and watch.last_changed >0 %}
                     {{watch.last_changed|format_timestamp_timeago}}
                     {% else %}
@@ -223,7 +241,7 @@
                 all {% if active_tag_uuid %} in "{{active_tag.title}}"{%endif%}</a>
             </li>
             <li>
-                <a href="{{ url_for('rss.feed', tag=active_tag_uuid, token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='Generic_Feed-icon.svg')}}" height="15"></a>
+                <a href="{{ url_for('rss.feed', tag=active_tag_uuid, token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='generic_feed-icon.svg')}}" height="15"></a>
             </li>
         </ul>
         {{ pagination.links }}

changedetectionio/conditions/__init__.py

@@ -8,7 +8,7 @@ from . import default_plugin
 
 # List of all supported JSON Logic operators
 operator_choices = [
-    (None, "Choose one"),
+    (None, "Choose one - Operator"),
     (">", "Greater Than"),
     ("<", "Less Than"),
     (">=", "Greater Than or Equal To"),
@@ -21,7 +21,7 @@ operator_choices = [
 
 # Fields available in the rules
 field_choices = [
-    (None, "Choose one"),
+    (None, "Choose one - Field"),
 ]
 
 # The data we will feed the JSON Rules to see if it passes the test/conditions or not
@@ -116,8 +116,7 @@ def execute_ruleset_against_all_plugins(current_watch_uuid: str, application_dat
             if not jsonLogic(logic=ruleset, data=EXECUTE_DATA, operations=CUSTOM_OPERATIONS):
                 result = False
 
-    return result
-
+    return {'executed_data': EXECUTE_DATA, 'result': result}
 
 # Load plugins dynamically
 for plugin in plugin_manager.get_plugins():

changedetectionio/conditions/blueprint.py

@@ -67,7 +67,8 @@ def construct_blueprint(datastore):
 
             return jsonify({
                 'status': 'success',
-                'result': result,
+                'result': result.get('result'),
+                'data': result.get('executed_data'),
                 'message': 'Condition passes' if result else 'Condition does not pass'
             })
 

changedetectionio/conditions/form.py

@@ -19,7 +19,7 @@ class ConditionFormRow(Form):
         validators=[validators.Optional()]
     )
 
-    value = StringField("Value", validators=[validators.Optional()])
+    value = StringField("Value", validators=[validators.Optional()], render_kw={"placeholder": "A value"})
 
     def validate(self, extra_validators=None):
         # First, run the default validators

changedetectionio/content_fetchers/base.py

@@ -87,7 +87,7 @@ class Fetcher():
         pass
 
     @abstractmethod
-    def quit(self):
+    def quit(self, watch=None):
         return
 
     @abstractmethod

changedetectionio/content_fetchers/requests.py

@@ -96,3 +96,17 @@ class fetcher(Fetcher):
 
 
         self.raw_content = r.content
+
+    def quit(self, watch=None):
+
+        # In case they switched to `requests` fetcher from something else
+        # Then the screenshot could be old, in any case, it's not used here.
+        # REMOVE_REQUESTS_OLD_SCREENSHOTS - Mainly used for testing
+        if strtobool(os.getenv("REMOVE_REQUESTS_OLD_SCREENSHOTS", 'true')):
+            screenshot = watch.get_screenshot()
+            if screenshot:
+                try:
+                    os.unlink(screenshot)
+                except Exception as e:
+                    logger.warning(f"Failed to unlink screenshot: {screenshot} - {e}")
+

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

@@ -75,13 +75,19 @@ function isItemInStock() {
         'rupture',
         'sold out',
         'sold-out',
+        'stok habis',
+        'stok kosong',
+        'stok varian ini habis',
         'stokta yok',
         'temporarily out of stock',
         'temporarily unavailable',
         'there were no search results for',
         'this item is currently unavailable',
         'tickets unavailable',
+        'tidak dijual',
+        'tidak tersedia',
         'tijdelijk uitverkocht',
+        'tiket tidak tersedia',
         'tükendi',
         'unavailable nearby',
         'unavailable tickets',

changedetectionio/content_fetchers/webdriver_selenium.py

@@ -112,7 +112,7 @@ class fetcher(Fetcher):
         self.quit()
         return True
 
-    def quit(self):
+    def quit(self, watch=None):
         if self.driver:
             try:
                 self.driver.quit()

changedetectionio/flask_app.py

@@ -34,6 +34,7 @@ from loguru import logger
 from changedetectionio import __version__
 from changedetectionio import queuedWatchMetaData
 from changedetectionio.api import Watch, WatchHistory, WatchSingleHistory, CreateWatch, Import, SystemInfo, Tag, Tags
+from changedetectionio.api.Search import Search
 from .time_handler import is_within_schedule
 
 datastore = None
@@ -122,14 +123,18 @@ def _jinja2_filter_format_number_locale(value: float) -> str:
 
     return formatted_value
 
+@app.template_global('is_checking_now')
+def _watch_is_checking_now(watch_obj, format="%Y-%m-%d %H:%M:%S"):
+    # Worker thread tells us which UUID it is currently processing.
+    for t in running_update_threads:
+        if t.current_uuid == watch_obj['uuid']:
+            return True
+
+
 # We use the whole watch object from the store/JSON so we can see if there's some related status in terms of a thread
 # running or something similar.
 @app.template_filter('format_last_checked_time')
 def _jinja2_filter_datetime(watch_obj, format="%Y-%m-%d %H:%M:%S"):
-    # Worker thread tells us which UUID it is currently processing.
-    for t in running_update_threads:
-        if t.current_uuid == watch_obj['uuid']:
-            return '<span class="spinner"></span><span> Checking now</span>'
 
     if watch_obj['last_checked'] == 0:
         return 'Not yet'
@@ -228,7 +233,8 @@ def changedetection_app(config=None, datastore_o=None):
 
         if has_password_enabled and not flask_login.current_user.is_authenticated:
             # Permitted
-            if request.endpoint and request.endpoint == 'static_content' and request.view_args and request.view_args.get('group') in ['styles', 'js', 'images', 'favicons']:
+            if request.endpoint and request.endpoint == 'static_content' and request.view_args:
+                # Handled by static_content handler
                 return None
             # Permitted
             elif request.endpoint and 'login' in request.endpoint:
@@ -275,6 +281,9 @@ def changedetection_app(config=None, datastore_o=None):
 
     watch_api.add_resource(Tag, '/api/v1/tag', '/api/v1/tag/<string:uuid>',
                            resource_class_kwargs={'datastore': datastore})
+                           
+    watch_api.add_resource(Search, '/api/v1/search',
+                           resource_class_kwargs={'datastore': datastore})
 
 
 
@@ -343,11 +352,15 @@ def changedetection_app(config=None, datastore_o=None):
     @app.route("/static/<string:group>/<string:filename>", methods=['GET'])
     def static_content(group, filename):
         from flask import make_response
+        import re
+        group = re.sub(r'[^\w.-]+', '', group.lower())
+        filename = re.sub(r'[^\w.-]+', '', filename.lower())
 
         if group == 'screenshot':
             # Could be sensitive, follow password requirements
             if datastore.data['settings']['application']['password'] and not flask_login.current_user.is_authenticated:
-                abort(403)
+                if not datastore.data['settings']['application'].get('shared_diff_access'):
+                    abort(403)
 
             screenshot_filename = "last-screenshot.png" if not request.args.get('error_screenshot') else "last-error-screenshot.png"
 
@@ -396,7 +409,7 @@ def changedetection_app(config=None, datastore_o=None):
 
         # These files should be in our subdirectory
         try:
-            return send_from_directory("static/{}".format(group), path=filename)
+            return send_from_directory(f"static/{group}", path=filename)
         except FileNotFoundError:
             abort(404)
 
@@ -425,7 +438,7 @@ def changedetection_app(config=None, datastore_o=None):
     import changedetectionio.conditions.blueprint as conditions
     app.register_blueprint(conditions.construct_blueprint(datastore), url_prefix='/conditions')
 
-    import changedetectionio.blueprint.rss as rss
+    import changedetectionio.blueprint.rss.blueprint as rss
     app.register_blueprint(rss.construct_blueprint(datastore), url_prefix='/rss')
 
     # watchlist UI buttons etc
@@ -434,6 +447,16 @@ def changedetection_app(config=None, datastore_o=None):
 
     import changedetectionio.blueprint.watchlist as watchlist
     app.register_blueprint(watchlist.construct_blueprint(datastore=datastore, update_q=update_q, queuedWatchMetaData=queuedWatchMetaData), url_prefix='')
+    
+    # Memory cleanup endpoint
+    @app.route('/gc-cleanup', methods=['GET'])
+    @login_optionally_required
+    def gc_cleanup():
+        from changedetectionio.gc_cleanup import memory_cleanup
+        from flask import jsonify
+
+        result = memory_cleanup(app)
+        return jsonify({"status": "success", "message": "Memory cleanup completed", "result": result})
 
     # @todo handle ctrl break
     ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks).start()

changedetectionio/forms.py

@@ -3,6 +3,7 @@ import re
 from loguru import logger
 from wtforms.widgets.core import TimeInput
 
+from changedetectionio.blueprint.rss import RSS_FORMAT_TYPES
 from changedetectionio.conditions.form import ConditionFormRow
 from changedetectionio.strtobool import strtobool
 
@@ -305,10 +306,10 @@ class ValidateAppRiseServers(object):
 
     def __call__(self, form, field):
         import apprise
-        apobj = apprise.Apprise()
+        from .apprise_plugin.assets import apprise_asset
+        from .apprise_plugin.custom_handlers import apprise_http_custom_handler  # noqa: F401
 
-        # so that the custom endpoints are registered
-        from .apprise_asset import asset
+        apobj = apprise.Apprise(asset=apprise_asset)
 
         for server_url in field.data:
             url = server_url.strip()
@@ -585,7 +586,7 @@ class processor_text_json_diff_form(commonSettingsForm):
     filter_text_replaced = BooleanField('Replaced/changed lines', default=True)
     filter_text_removed = BooleanField('Removed lines', default=True)
 
-    trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
+    trigger_text = StringListField('Keyword triggers - Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
     if os.getenv("PLAYWRIGHT_DRIVER_URL"):
         browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
     text_should_not_be_present = StringListField('Block change-detection while text matches', [validators.Optional(), ValidateListRegex()])
@@ -739,6 +740,9 @@ class globalSettingsApplicationForm(commonSettingsForm):
                               render_kw={"style": "width: 5em;"},
                               validators=[validators.NumberRange(min=0,
                                                                  message="Should be atleast zero (disabled)")])
+
+    rss_content_format = SelectField('RSS Content format', choices=RSS_FORMAT_TYPES)
+
     removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
     render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
     shared_diff_access = BooleanField('Allow access to view diff page when password is enabled', default=False, validators=[validators.Optional()])

changedetectionio/gc_cleanup.py

@@ -0,0 +1,162 @@
+#!/usr/bin/env python3
+
+import ctypes
+import gc
+import re
+import psutil
+import sys
+import threading
+import importlib
+from loguru import logger
+
+def memory_cleanup(app=None):
+    """
+    Perform comprehensive memory cleanup operations and log memory usage
+    at each step with nicely formatted numbers.
+    
+    Args:
+        app: Optional Flask app instance for clearing Flask-specific caches
+        
+    Returns:
+        str: Status message
+    """
+    # Get current process
+    process = psutil.Process()
+    
+    # Log initial memory usage with nicely formatted numbers
+    current_memory = process.memory_info().rss / 1024 / 1024
+    logger.debug(f"Memory cleanup started - Current memory usage: {current_memory:,.2f} MB")
+
+    # 1. Standard garbage collection - force full collection on all generations
+    gc.collect(0)  # Collect youngest generation
+    gc.collect(1)  # Collect middle generation
+    gc.collect(2)  # Collect oldest generation
+
+    # Run full collection again to ensure maximum cleanup
+    gc.collect()
+    current_memory = process.memory_info().rss / 1024 / 1024
+    logger.debug(f"After full gc.collect() - Memory usage: {current_memory:,.2f} MB")
+    
+
+    # 3. Call libc's malloc_trim to release memory back to the OS
+    libc = ctypes.CDLL("libc.so.6")
+    libc.malloc_trim(0)
+    current_memory = process.memory_info().rss / 1024 / 1024
+    logger.debug(f"After malloc_trim(0) - Memory usage: {current_memory:,.2f} MB")
+    
+    # 4. Clear Python's regex cache
+    re.purge()
+    current_memory = process.memory_info().rss / 1024 / 1024
+    logger.debug(f"After re.purge() - Memory usage: {current_memory:,.2f} MB")
+
+    # 5. Reset thread-local storage
+    # Create a new thread local object to encourage cleanup of old ones
+    threading.local()
+    current_memory = process.memory_info().rss / 1024 / 1024
+    logger.debug(f"After threading.local() - Memory usage: {current_memory:,.2f} MB")
+
+    # 6. Clear sys.intern cache if Python version supports it
+    try:
+        sys.intern.clear()
+        current_memory = process.memory_info().rss / 1024 / 1024
+        logger.debug(f"After sys.intern.clear() - Memory usage: {current_memory:,.2f} MB")
+    except (AttributeError, TypeError):
+        logger.debug("sys.intern.clear() not supported in this Python version")
+    
+    # 7. Clear XML/lxml caches if available
+    try:
+        # Check if lxml.etree is in use
+        lxml_etree = sys.modules.get('lxml.etree')
+        if lxml_etree:
+            # Clear module-level caches
+            if hasattr(lxml_etree, 'clear_error_log'):
+                lxml_etree.clear_error_log()
+            
+            # Check for _ErrorLog and _RotatingErrorLog objects and clear them
+            for obj in gc.get_objects():
+                if hasattr(obj, '__class__') and hasattr(obj.__class__, '__name__'):
+                    class_name = obj.__class__.__name__
+                    if class_name in ('_ErrorLog', '_RotatingErrorLog', '_DomainErrorLog') and hasattr(obj, 'clear'):
+                        try:
+                            obj.clear()
+                        except (AttributeError, TypeError):
+                            pass
+                    
+                    # Clear Element objects which can hold references to documents
+                    elif class_name in ('_Element', 'ElementBase') and hasattr(obj, 'clear'):
+                        try:
+                            obj.clear()
+                        except (AttributeError, TypeError):
+                            pass
+            
+            current_memory = process.memory_info().rss / 1024 / 1024
+            logger.debug(f"After lxml.etree cleanup - Memory usage: {current_memory:,.2f} MB")
+
+        # Check if lxml.html is in use
+        lxml_html = sys.modules.get('lxml.html')
+        if lxml_html:
+            # Clear HTML-specific element types
+            for obj in gc.get_objects():
+                if hasattr(obj, '__class__') and hasattr(obj.__class__, '__name__'):
+                    class_name = obj.__class__.__name__
+                    if class_name in ('HtmlElement', 'FormElement', 'InputElement',
+                                    'SelectElement', 'TextareaElement', 'CheckboxGroup',
+                                    'RadioGroup', 'MultipleSelectOptions', 'FieldsDict') and hasattr(obj, 'clear'):
+                        try:
+                            obj.clear()
+                        except (AttributeError, TypeError):
+                            pass
+
+            current_memory = process.memory_info().rss / 1024 / 1024
+            logger.debug(f"After lxml.html cleanup - Memory usage: {current_memory:,.2f} MB")
+    except (ImportError, AttributeError):
+        logger.debug("lxml cleanup not applicable")
+    
+    # 8. Clear JSON parser caches if applicable
+    try:
+        # Check if json module is being used and try to clear its cache
+        json_module = sys.modules.get('json')
+        if json_module and hasattr(json_module, '_default_encoder'):
+            json_module._default_encoder.markers.clear()
+            current_memory = process.memory_info().rss / 1024 / 1024
+            logger.debug(f"After JSON parser cleanup - Memory usage: {current_memory:,.2f} MB")
+    except (AttributeError, KeyError):
+        logger.debug("JSON cleanup not applicable")
+    
+    # 9. Force Python's memory allocator to release unused memory
+    try:
+        if hasattr(sys, 'pypy_version_info'):
+            # PyPy has different memory management
+            gc.collect()
+        else:
+            # CPython - try to release unused memory
+            ctypes.pythonapi.PyGC_Collect()
+            current_memory = process.memory_info().rss / 1024 / 1024
+            logger.debug(f"After PyGC_Collect - Memory usage: {current_memory:,.2f} MB")
+    except (AttributeError, TypeError):
+        logger.debug("PyGC_Collect not supported")
+    
+    # 10. Clear Flask-specific caches if applicable
+    if app:
+        try:
+            # Clear Flask caches if they exist
+            for key in list(app.config.get('_cache', {}).keys()):
+                app.config['_cache'].pop(key, None)
+            
+            # Clear Jinja2 template cache if available
+            if hasattr(app, 'jinja_env') and hasattr(app.jinja_env, 'cache'):
+                app.jinja_env.cache.clear()
+            
+            current_memory = process.memory_info().rss / 1024 / 1024
+            logger.debug(f"After Flask cache clear - Memory usage: {current_memory:,.2f} MB")
+        except (AttributeError, KeyError):
+            logger.debug("No Flask cache to clear")
+    
+    # Final garbage collection pass
+    gc.collect()
+    libc.malloc_trim(0)
+    
+    # Log final memory usage
+    final_memory = process.memory_info().rss / 1024 / 1024
+    logger.info(f"Memory cleanup completed - Final memory usage: {final_memory:,.2f} MB")
+    return "cleaned"

changedetectionio/model/App.py

@@ -1,4 +1,7 @@
 from os import getenv
+
+from changedetectionio.blueprint.rss import RSS_FORMAT_TYPES
+
 from changedetectionio.notification import (
     default_notification_body,
     default_notification_format,
@@ -9,6 +12,8 @@ from changedetectionio.notification import (
 _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT = 6
 DEFAULT_SETTINGS_HEADERS_USERAGENT='Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36'
 
+
+
 class model(dict):
     base_config = {
             'note': "Hello! If you change this file manually, please be sure to restart your changedetection.io instance!",
@@ -48,6 +53,7 @@ class model(dict):
                     'password': False,
                     'render_anchor_tag_content': False,
                     'rss_access_token': None,
+                    'rss_content_format': RSS_FORMAT_TYPES[0][0],
                     'rss_hide_muted_watches': True,
                     'schema_version' : 0,
                     'shared_diff_access': False,

changedetectionio/model/Watch.py

@@ -575,7 +575,7 @@ class model(watch_base):
         import brotli
         filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
 
-        if not os.path.isfile(filepath):
+        if not os.path.isfile(filepath) or os.path.getsize(filepath) == 0:
             # If a previous attempt doesnt yet exist, just snarf the previous snapshot instead
             dates = list(self.history.keys())
             if len(dates):

changedetectionio/notification.py

@@ -4,6 +4,9 @@ from apprise import NotifyFormat
 import apprise
 from loguru import logger
 
+from .apprise_plugin.assets import APPRISE_AVATAR_URL
+from .apprise_plugin.custom_handlers import apprise_http_custom_handler  # noqa: F401
+from .safe_jinja import render as jinja_render
 
 valid_tokens = {
     'base_url': '',
@@ -39,10 +42,6 @@ valid_notification_formats = {
 
 
 def process_notification(n_object, datastore):
-    # so that the custom endpoints are registered
-    from changedetectionio.apprise_plugin import apprise_custom_api_call_wrapper
-
-    from .safe_jinja import render as jinja_render
     now = time.time()
     if n_object.get('notification_timestamp'):
         logger.trace(f"Time since queued {now-n_object['notification_timestamp']:.3f}s")
@@ -66,12 +65,12 @@ def process_notification(n_object, datastore):
     # raise it as an exception
 
     sent_objs = []
-    from .apprise_asset import asset
+    from .apprise_plugin.assets import apprise_asset
 
     if 'as_async' in n_object:
-        asset.async_mode = n_object.get('as_async')
+        apprise_asset.async_mode = n_object.get('as_async')
 
-    apobj = apprise.Apprise(debug=True, asset=asset)
+    apobj = apprise.Apprise(debug=True, asset=apprise_asset)
 
     if not n_object.get('notification_urls'):
         return None
@@ -112,7 +111,7 @@ def process_notification(n_object, datastore):
                     and not url.startswith('get') \
                     and not url.startswith('delete') \
                     and not url.startswith('put'):
-                url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
+                url += k + f"avatar_url={APPRISE_AVATAR_URL}"
 
             if url.startswith('tgram://'):
                 # Telegram only supports a limit subset of HTML, remove the '<br>' we place in.

changedetectionio/processors/__init__.py

@@ -159,7 +159,7 @@ class difference_detection_processor():
                          )
 
         #@todo .quit here could go on close object, so we can run JS if change-detected
-        self.fetcher.quit()
+        self.fetcher.quit(watch=self.watch)
 
         # After init, call run_changedetection() which will do the actual change-detection
 

changedetectionio/processors/text_json_diff/processor.py

@@ -252,6 +252,7 @@ class perform_site_check(difference_detection_processor):
 
         # 615 Extract text by regex
         extract_text = watch.get('extract_text', [])
+        extract_text += self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='extract_text')
         if len(extract_text) > 0:
             regex_matched_output = []
             for s_re in extract_text:
@@ -296,6 +297,8 @@ class perform_site_check(difference_detection_processor):
 ### CALCULATE MD5
         # If there's text to ignore
         text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
+        text_to_ignore += self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='ignore_text')
+
         text_for_checksuming = stripped_text_from_html
         if text_to_ignore:
             text_for_checksuming = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
@@ -308,8 +311,8 @@ class perform_site_check(difference_detection_processor):
 
         ############ Blocking rules, after checksum #################
         blocked = False
-
         trigger_text = watch.get('trigger_text', [])
+        trigger_text += self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='trigger_text')
         if len(trigger_text):
             # Assume blocked
             blocked = True
@@ -324,6 +327,7 @@ class perform_site_check(difference_detection_processor):
                 blocked = False
 
         text_should_not_be_present = watch.get('text_should_not_be_present', [])
+        text_should_not_be_present += self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='text_should_not_be_present')
         if len(text_should_not_be_present):
             # If anything matched, then we should block a change from happening
             result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
@@ -334,12 +338,14 @@ class perform_site_check(difference_detection_processor):
 
         # And check if 'conditions' will let this pass through
         if watch.get('conditions') and watch.get('conditions_match_logic'):
-            if not execute_ruleset_against_all_plugins(current_watch_uuid=watch.get('uuid'),
-                                                application_datastruct=self.datastore.data,
-                                                ephemeral_data={
-                                                    'text': stripped_text_from_html
-                                                }
-                                                ):
+            conditions_result = execute_ruleset_against_all_plugins(current_watch_uuid=watch.get('uuid'),
+                                                                    application_datastruct=self.datastore.data,
+                                                                    ephemeral_data={
+                                                                        'text': stripped_text_from_html
+                                                                    }
+                                                                    )
+
+            if not conditions_result.get('result'):
                 # Conditions say "Condition not met" so we block it.
                 blocked = True
 

changedetectionio/run_basic_tests.sh

@@ -14,7 +14,8 @@ SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
 find tests/test_*py -type f|while read test_name
 do
   echo "TEST RUNNING $test_name"
-  pytest $test_name
+  # REMOVE_REQUESTS_OLD_SCREENSHOTS disabled so that we can write a screenshot and send it in test_notifications.py without a real browser
+  REMOVE_REQUESTS_OLD_SCREENSHOTS=false pytest $test_name
 done
 
 echo "RUNNING WITH BASE_URL SET"
@@ -22,7 +23,7 @@ echo "RUNNING WITH BASE_URL SET"
 # Now re-run some tests with BASE_URL enabled
 # Re #65 - Ability to include a link back to the installation, in the notification.
 export BASE_URL="https://really-unique-domain.io"
-pytest tests/test_notification.py
+REMOVE_REQUESTS_OLD_SCREENSHOTS=false pytest tests/test_notification.py
 
 
 # Re-run with HIDE_REFERER set - could affect login
@@ -32,7 +33,7 @@ pytest tests/test_access_control.py
 # Re-run a few tests that will trigger brotli based storage
 export SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD=5
 pytest tests/test_access_control.py
-pytest tests/test_notification.py
+REMOVE_REQUESTS_OLD_SCREENSHOTS=false pytest tests/test_notification.py
 pytest tests/test_backend.py
 pytest tests/test_rss.py
 pytest tests/test_unique_lines.py

changedetectionio/static/js/conditions.js

@@ -8,7 +8,7 @@ $(document).ready(function () {
         $(".addRuleRow").on("click", function(e) {
             e.preventDefault();
             
-            let currentRow = $(this).closest("tr");
+            let currentRow = $(this).closest(".fieldlist-row");
             
             // Clone without events
             let newRow = currentRow.clone(false);
@@ -29,8 +29,8 @@ $(document).ready(function () {
             e.preventDefault();
             
             // Only remove if there's more than one row
-            if ($("#rulesTable tbody tr").length > 1) {
-                $(this).closest("tr").remove();
+            if ($("#rulesTable .fieldlist-row").length > 1) {
+                $(this).closest(".fieldlist-row").remove();
                 reindexRules();
             }
         });
@@ -39,7 +39,7 @@ $(document).ready(function () {
         $(".verifyRuleRow").on("click", function(e) {
             e.preventDefault();
             
-            let row = $(this).closest("tr");
+            let row = $(this).closest(".fieldlist-row");
             let field = row.find("select[name$='field']").val();
             let operator = row.find("select[name$='operator']").val();
             let value = row.find("input[name$='value']").val();
@@ -52,7 +52,7 @@ $(document).ready(function () {
 
             
             // Create a rule object
-            const rule = {
+            let rule = {
                 field: field,
                 operator: operator,
                 value: value
@@ -96,6 +96,10 @@ $(document).ready(function () {
                 contentType: false, // Let the browser set the correct content type
                 success: function (response) {
                     if (response.status === "success") {
+                        if(rule['field'] !== "page_filtered_text") {
+                            // A little debug helper for the user
+                            $('#verify-state-text').text(`${rule['field']} was value "${response.data[rule['field']]}"`)
+                        }
                         if (response.result) {
                             alert("✅ Condition PASSES verification against current snapshot!");
                         } else {
@@ -124,7 +128,7 @@ $(document).ready(function () {
         $(".addRuleRow, .removeRuleRow, .verifyRuleRow").off("click");
         
         // Reindex all form elements
-        $("#rulesTable tbody tr").each(function(index) {
+        $("#rulesTable .fieldlist-row").each(function(index) {
             $(this).find("select, input").each(function() {
                 let oldName = $(this).attr("name");
                 let oldId = $(this).attr("id");

changedetectionio/static/js/watch-overview.js

@@ -48,6 +48,8 @@ $(function () {
         $('input[type=checkbox]').not(this).prop('checked', this.checked);
     });
 
+    const time_check_step_size_seconds=1;
+
     // checkboxes - show/hide buttons
     $("input[type=checkbox]").click(function (e) {
         if ($('input[type=checkbox]:checked').length) {
@@ -57,5 +59,30 @@ $(function () {
         }
     });
 
+    setInterval(function () {
+        // Background ETA completion for 'checking now'
+        $(".watch-table .checking-now .last-checked").each(function () {
+            const eta_complete = parseFloat($(this).data('eta_complete'));
+            const fetch_duration = parseInt($(this).data('fetchduration'));
+
+            if (eta_complete + 2 > nowtimeserver && fetch_duration > 3) {
+                const remaining_seconds = Math.abs(eta_complete) - nowtimeserver - 1;
+
+                let r = (1.0 - (remaining_seconds / fetch_duration)) * 100;
+                if (r < 10) {
+                    r = 10;
+                }
+                if (r >= 90) {
+                    r = 100;
+                }
+                $(this).css('background-size', `${r}% 100%`);
+                //$(this).text(`${r}% remain ${remaining_seconds}`);
+            } else {
+                $(this).css('background-size', `100% 100%`);
+            }
+        });
+
+        nowtimeserver = nowtimeserver + time_check_step_size_seconds;
+    }, time_check_step_size_seconds * 1000);
 });
 

changedetectionio/static/styles/scss/parts/_conditions_table.scss

@@ -0,0 +1,135 @@
+/* Styles for the flexbox-based table replacement for conditions */
+.fieldlist_formfields {
+  width: 100%;
+  background-color: var(--color-background, #fff);
+  border-radius: 4px;
+  border: 1px solid var(--color-border-table-cell, #cbcbcb);
+  
+  /* Header row */
+  .fieldlist-header {
+    display: flex;
+    background-color: var(--color-background-table-thead, #e0e0e0);
+    font-weight: bold;
+    border-bottom: 1px solid var(--color-border-table-cell, #cbcbcb);
+  }
+  
+  .fieldlist-header-cell {
+    flex: 1;
+    padding: 0.5em 1em;
+    text-align: left;
+    
+    &:last-child {
+      flex: 0 0 120px; /* Fixed width for actions column */
+    }
+  }
+  
+  /* Body rows */
+  .fieldlist-body {
+    display: flex;
+    flex-direction: column;
+  }
+  
+  .fieldlist-row {
+    display: flex;
+    border-bottom: 1px solid var(--color-border-table-cell, #cbcbcb);
+    
+    &:last-child {
+      border-bottom: none;
+    }
+    
+    &:nth-child(2n-1) {
+      background-color: var(--color-table-stripe, #f2f2f2);
+    }
+    
+    &.error-row {
+      background-color: var(--color-error-input, #ffdddd);
+    }
+  }
+  
+  .fieldlist-cell {
+    flex: 1;
+    padding: 0.5em 1em;
+    display: flex;
+    flex-direction: column;
+    justify-content: center;
+    
+    /* Make inputs take up full width of their cell */
+    input, select {
+      width: 100%;
+    }
+    
+    &.fieldlist-actions {
+      flex: 0 0 120px; /* Fixed width for actions column */
+      display: flex;
+      flex-direction: row;
+      align-items: center;
+      gap: 4px;
+    }
+  }
+  
+  /* Error styling */
+  ul.errors {
+    margin-top: 0.5em;
+    margin-bottom: 0;
+    padding: 0.5em;
+    background-color: var(--color-error-background-snapshot-age, #ffdddd);
+    border-radius: 4px;
+    list-style-position: inside;
+  }
+  
+  /* Responsive styles */
+  @media only screen and (max-width: 760px) {
+    .fieldlist-header, .fieldlist-row {
+      flex-direction: column;
+    }
+    
+    .fieldlist-header-cell {
+      display: none;
+    }
+    
+    .fieldlist-row {
+      padding: 0.5em 0;
+      border-bottom: 2px solid var(--color-border-table-cell, #cbcbcb);
+    }
+    
+    .fieldlist-cell {
+      padding: 0.25em 0.5em;
+      
+      &.fieldlist-actions {
+        flex: 1;
+        justify-content: flex-start;
+        padding-top: 0.5em;
+      }
+    }
+    
+    /* Add some spacing between fields on mobile */
+    .fieldlist-cell:not(:last-child) {
+      margin-bottom: 0.5em;
+    }
+    
+    /* Label each cell on mobile view */
+    .fieldlist-cell::before {
+      content: attr(data-label);
+      font-weight: bold;
+      margin-bottom: 0.25em;
+    }
+  }
+}
+
+/* Button styling */
+.fieldlist_formfields {
+  .addRuleRow, .removeRuleRow, .verifyRuleRow {
+    cursor: pointer;
+    border: none;
+    padding: 4px 8px;
+    border-radius: 3px;
+    font-weight: bold;
+    background-color: #aaa;
+    color: var(--color-foreground-text, #fff);
+
+    &:hover {
+      background-color: #999;
+    }
+  }
+
+}

changedetectionio/static/styles/scss/styles.scss

@@ -14,6 +14,7 @@
 @import "parts/_love";
 @import "parts/preview_text_filter";
 @import "parts/_edit";
+@import "parts/_conditions_table";
 
 body {
   color: var(--color-text);

changedetectionio/static/styles/styles.css

@@ -530,6 +530,99 @@ ul#conditions_match_logic {
   ul#conditions_match_logic li {
     padding-right: 1em; }
 
+/* Styles for the flexbox-based table replacement for conditions */
+.fieldlist_formfields {
+  width: 100%;
+  background-color: var(--color-background, #fff);
+  border-radius: 4px;
+  border: 1px solid var(--color-border-table-cell, #cbcbcb);
+  /* Header row */
+  /* Body rows */
+  /* Error styling */
+  /* Responsive styles */ }
+  .fieldlist_formfields .fieldlist-header {
+    display: flex;
+    background-color: var(--color-background-table-thead, #e0e0e0);
+    font-weight: bold;
+    border-bottom: 1px solid var(--color-border-table-cell, #cbcbcb); }
+  .fieldlist_formfields .fieldlist-header-cell {
+    flex: 1;
+    padding: 0.5em 1em;
+    text-align: left; }
+    .fieldlist_formfields .fieldlist-header-cell:last-child {
+      flex: 0 0 120px;
+      /* Fixed width for actions column */ }
+  .fieldlist_formfields .fieldlist-body {
+    display: flex;
+    flex-direction: column; }
+  .fieldlist_formfields .fieldlist-row {
+    display: flex;
+    border-bottom: 1px solid var(--color-border-table-cell, #cbcbcb); }
+    .fieldlist_formfields .fieldlist-row:last-child {
+      border-bottom: none; }
+    .fieldlist_formfields .fieldlist-row:nth-child(2n-1) {
+      background-color: var(--color-table-stripe, #f2f2f2); }
+    .fieldlist_formfields .fieldlist-row.error-row {
+      background-color: var(--color-error-input, #ffdddd); }
+  .fieldlist_formfields .fieldlist-cell {
+    flex: 1;
+    padding: 0.5em 1em;
+    display: flex;
+    flex-direction: column;
+    justify-content: center;
+    /* Make inputs take up full width of their cell */ }
+    .fieldlist_formfields .fieldlist-cell input, .fieldlist_formfields .fieldlist-cell select {
+      width: 100%; }
+    .fieldlist_formfields .fieldlist-cell.fieldlist-actions {
+      flex: 0 0 120px;
+      /* Fixed width for actions column */
+      display: flex;
+      flex-direction: row;
+      align-items: center;
+      gap: 4px; }
+  .fieldlist_formfields ul.errors {
+    margin-top: 0.5em;
+    margin-bottom: 0;
+    padding: 0.5em;
+    background-color: var(--color-error-background-snapshot-age, #ffdddd);
+    border-radius: 4px;
+    list-style-position: inside; }
+  @media only screen and (max-width: 760px) {
+    .fieldlist_formfields {
+      /* Add some spacing between fields on mobile */
+      /* Label each cell on mobile view */ }
+      .fieldlist_formfields .fieldlist-header, .fieldlist_formfields .fieldlist-row {
+        flex-direction: column; }
+      .fieldlist_formfields .fieldlist-header-cell {
+        display: none; }
+      .fieldlist_formfields .fieldlist-row {
+        padding: 0.5em 0;
+        border-bottom: 2px solid var(--color-border-table-cell, #cbcbcb); }
+      .fieldlist_formfields .fieldlist-cell {
+        padding: 0.25em 0.5em; }
+        .fieldlist_formfields .fieldlist-cell.fieldlist-actions {
+          flex: 1;
+          justify-content: flex-start;
+          padding-top: 0.5em; }
+      .fieldlist_formfields .fieldlist-cell:not(:last-child) {
+        margin-bottom: 0.5em; }
+      .fieldlist_formfields .fieldlist-cell::before {
+        content: attr(data-label);
+        font-weight: bold;
+        margin-bottom: 0.25em; } }
+
+/* Button styling */
+.fieldlist_formfields .addRuleRow, .fieldlist_formfields .removeRuleRow, .fieldlist_formfields .verifyRuleRow {
+  cursor: pointer;
+  border: none;
+  padding: 4px 8px;
+  border-radius: 3px;
+  font-weight: bold;
+  background-color: #aaa;
+  color: var(--color-foreground-text, #fff); }
+  .fieldlist_formfields .addRuleRow:hover, .fieldlist_formfields .removeRuleRow:hover, .fieldlist_formfields .verifyRuleRow:hover {
+    background-color: #999; }
+
 body {
   color: var(--color-text);
   background: var(--color-background-page);

changedetectionio/store.py

@@ -251,8 +251,14 @@ class ChangeDetectionStore:
     # Clone a watch by UUID
     def clone(self, uuid):
         url = self.data['watching'][uuid].get('url')
-        extras = self.data['watching'][uuid]
+        extras = deepcopy(self.data['watching'][uuid])
         new_uuid = self.add_watch(url=url, extras=extras)
+        watch = self.data['watching'][new_uuid]
+
+        if self.data['settings']['application'].get('extract_title_as_title') or watch['extract_title_as_title']:
+            # Because it will be recalculated on the next fetch
+            self.data['watching'][new_uuid]['title'] = None
+
         return new_uuid
 
     def url_exists(self, url):
@@ -363,7 +369,6 @@ class ChangeDetectionStore:
         new_watch.ensure_data_dir_exists()
         self.__data['watching'][new_uuid] = new_watch
 
-
         if write_to_disk_now:
             self.sync_to_json()
 
@@ -631,6 +636,41 @@ class ChangeDetectionStore:
             if watch.get('processor') == processor_name:
                 return True
         return False
+        
+    def search_watches_for_url(self, query, tag_limit=None, partial=False):
+        """Search watches by URL, title, or error messages
+        
+        Args:
+            query (str): Search term to match against watch URLs, titles, and error messages
+            tag_limit (str, optional): Optional tag name to limit search results
+            partial: (bool, optional): sub-string matching
+
+        Returns:
+            list: List of UUIDs of watches that match the search criteria
+        """
+        matching_uuids = []
+        query = query.lower().strip()
+        tag = self.tag_exists_by_name(tag_limit) if tag_limit else False
+
+        for uuid, watch in self.data['watching'].items():
+            # Filter by tag if requested
+            if tag_limit:
+                if not tag.get('uuid') in watch.get('tags', []):
+                    continue
+
+            # Search in URL, title, or error messages
+            if partial:
+                if ((watch.get('title') and query in watch.get('title').lower()) or
+                    query in watch.get('url', '').lower() or
+                    (watch.get('last_error') and query in watch.get('last_error').lower())):
+                    matching_uuids.append(uuid)
+            else:
+                if ((watch.get('title') and query == watch.get('title').lower()) or
+                        query == watch.get('url', '').lower() or
+                        (watch.get('last_error') and query == watch.get('last_error').lower())):
+                    matching_uuids.append(uuid)
+
+        return matching_uuids
 
     def get_unique_notification_tokens_available(self):
         # Ask each type of watch if they have any extra notification token to add to the validation

changedetectionio/templates/_helpers.html

@@ -61,21 +61,20 @@
   {{ field(**kwargs)|safe }}
 {% endmacro %}
 
-{% macro render_fieldlist_of_formfields_as_table(fieldlist, table_id="rulesTable") %}
-  <table class="fieldlist_formfields pure-table" id="{{ table_id }}">
-    <thead>
-      <tr>
-        {% for subfield in fieldlist[0] %}
-          <th>{{ subfield.label }}</th>
-        {% endfor %}
-        <th>Actions</th>
-      </tr>
-    </thead>
-    <tbody>
+{% macro render_conditions_fieldlist_of_formfields_as_table(fieldlist, table_id="rulesTable") %}
+  <div class="fieldlist_formfields" id="{{ table_id }}">
+    <div class="fieldlist-header">
+      {% for subfield in fieldlist[0] %}
+        <div class="fieldlist-header-cell">{{ subfield.label }}</div>
+      {% endfor %}
+      <div class="fieldlist-header-cell">Actions</div>
+    </div>
+    <div class="fieldlist-body">
       {% for form_row in fieldlist %}
-        <tr {% if form_row.errors %} class="error-row" {% endif %}>
+        <div class="fieldlist-row {% if form_row.errors %}error-row{% endif %}">
           {% for subfield in form_row %}
-            <td>
+            <div class="fieldlist-cell">
+
               {{ subfield()|safe }}
               {% if subfield.errors %}
                 <ul class="errors">
@@ -84,17 +83,17 @@
                   {% endfor %}
                 </ul>
               {% endif %}
-            </td>
+            </div>
           {% endfor %}
-          <td>
-            <button type="button" class="addRuleRow">+</button>
-            <button type="button" class="removeRuleRow">-</button>
+          <div class="fieldlist-cell fieldlist-actions">
+            <button type="button" class="addRuleRow" title="Add a row/rule after">+</button>
+            <button type="button" class="removeRuleRow" title="Remove this row/rule">-</button>
             <button type="button" class="verifyRuleRow" title="Verify this rule against current snapshot">✓</button>
-          </td>
-        </tr>
+          </div>
+        </div>
       {% endfor %}
-    </tbody>
-  </table>
+    </div>
+  </div>
 {% endmacro %}
 
 

changedetectionio/templates/base.html

@@ -157,15 +157,13 @@
                 <h4>Try our Chrome extension</h4>
                 <p>
                     <a id="chrome-extension-link"
-                       title="Try our new Chrome Extension!"
+                       title="Chrome Extension - Web Page Change Detection with changedetection.io!"
                        href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
-                        <img alt="Chrome store icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}">
+                        <img alt="Chrome store icon" 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;
@@ -173,17 +171,20 @@
                 <p>
                 <ul>
                     <li>
-                        <a href="https://alternativeto.net/software/changedetection-io/about/">Rate us at
+                        <a href="https://alternativeto.net/software/changedetection-io/about/" title="Web page change detection at alternativeto.net">Rate us at
                         AlternativeTo.net</a>
                     </li>
                 <li>
-                    <a href="https://github.com/dgtlmoon/changedetection.io">Star us on GitHub</a>
+                    <a href="https://github.com/dgtlmoon/changedetection.io" title="Web page change detection on GitHub">Star us on GitHub</a>
                 </li>
                 <li>
-                    <a href="https://twitter.com/change_det_io">Follow us at Twitter/X</a>
+                    <a rel="nofollow" href="https://twitter.com/change_det_io" title="Web page change detection on Twitter">Follow us at Twitter/X</a>
                 </li>
                 <li>
-                    <a href="https://www.linkedin.com/company/changedetection-io">Check us out on LinkedIn</a>
+                    <a rel="nofollow" href="https://www.g2.com/products/changedetection-io/reviews" title="Web page change detection reviews at G2">G2 Software reviews</a>
+                </li>
+                <li>
+                    <a rel="nofollow" href="https://www.linkedin.com/company/changedetection-io" title="Visit web page change detection at LinkedIn">Check us out on LinkedIn</a>
                 </li>
                 <li>
                     And tell your friends and colleagues :)

changedetectionio/templates/edit.html

@@ -1,6 +1,6 @@
 {% extends 'base.html' %}
 {% block content %}
-{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_time_schedule_form, playwright_warning, only_webdriver_type_watches_warning, render_fieldlist_of_formfields_as_table %}
+{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_time_schedule_form, playwright_warning, only_webdriver_type_watches_warning, render_conditions_fieldlist_of_formfields_as_table %}
 {% 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>
@@ -289,25 +289,13 @@ Math: {{ 1 + 1 }}") }}
                     <script>
                         const verify_condition_rule_url="{{url_for('conditions.verify_condition_single_rule', watch_uuid=uuid)}}";
                     </script>
-                <style>
-                    .verifyRuleRow {
-                        background-color: #4caf50;
-                        color: white;
-                        border: none;
-                        cursor: pointer;
-                        font-weight: bold;
-                    }
-                    .verifyRuleRow:hover {
-                        background-color: #45a049;
-                    }
-                </style>
                 <div class="pure-control-group">
                     {{ render_field(form.conditions_match_logic) }}
-                    {{ render_fieldlist_of_formfields_as_table(form.conditions) }}
+                    {{ render_conditions_fieldlist_of_formfields_as_table(form.conditions) }}
                     <div class="pure-form-message-inline">
-                        <br>
-                        Use the verify (✓) button to test if a condition passes against the current snapshot.<br><br>
-                        Did you know that <strong>conditions</strong> can be extended with your own custom plugin? tutorials coming soon!<br>
+
+                        <p id="verify-state-text">Use the verify (✓) button to test if a condition passes against the current snapshot.</p>
+                       Read a quick tutorial about <a href="https://changedetection.io/tutorial/conditional-actions-web-page-changes">using conditional web page changes here</a>.<br>
                     </div>
                 </div>
             </div>
@@ -326,61 +314,8 @@ Math: {{ 1 + 1 }}") }}
                                 </li>
                             </ul>
                     </div>
-                    <div class="pure-control-group">
-                        {% set field = render_field(form.include_filters,
-                            rows=5,
-                            placeholder=has_tag_filters_extra+"#example
-xpath://body/div/span[contains(@class, 'example-class')]",
-                            class="m-d")
-                        %}
-                        {{ field }}
-                        {% if '/text()' in  field %}
-                          <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br>
-                        {% endif %}
-                        <span class="pure-form-message-inline">One CSS, xPath, JSON Path/JQ selector per line, <i>any</i> rules that matches will be used.<br>
-                        <span data-target="#advanced-help-selectors" class="toggle-show pure-button button-tag button-xsmall">Show advanced help and tips</span><br>
-                    <ul id="advanced-help-selectors" style="display: none;">
-                        <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
-                        <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
-                            <ul>
-                                <li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required,  <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
-                                {% if jq_support %}
-                                <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>. Prefix <code>jqraw:</code> outputs the results as text instead of a JSON list.</li>
-                                {% else %}
-                                <li>jq support not installed</li>
-                                {% endif %}
-                            </ul>
-                        </li>
-                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash. To specify XPath to be used explicitly or the XPath rule starts with an XPath function: Prefix with <code>xpath:</code>
-                            <ul>
-                                <li>Example:  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath:count(//*[contains(@class, 'sametext')])</code>, <a
-                                href="http://xpather.com/" target="new">test your XPath here</a></li>
-                                <li>Example: Get all titles from an RSS feed <code>//title/text()</code></li>
-                                <li>To use XPath1.0: Prefix with <code>xpath1:</code></li>
-                            </ul>
-                            </li>
-                    <li>
-                        Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
-                                href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
-                    </li>
-                    </ul>
 
-                </span>
-                    </div>
-                <fieldset class="pure-control-group">
-                    {{ render_field(form.subtractive_selectors, rows=5, placeholder=has_tag_filters_extra+"header
-footer
-nav
-.stockticker
-//*[contains(text(), 'Advertisement')]") }}
-                    <span class="pure-form-message-inline">
-                        <ul>
-                          <li> Remove HTML element(s) by CSS and XPath selectors before text conversion. </li>
-                          <li> Don't paste HTML here, use only CSS and XPath selectors </li>
-                          <li> Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML. </li>
-                        </ul>
-                      </span>
-                </fieldset>
+{% include "edit/include_subtract.html" %}
                 <div class="text-filtering border-fieldset">
                 <fieldset class="pure-group" id="text-filtering-type-options">
                     <h3>Text filtering</h3>
@@ -408,76 +343,9 @@ nav
                     {{ render_checkbox_field(form.trim_text_whitespace) }}
                     <span class="pure-form-message-inline">Remove any whitespace before and after each line of text</span>
                 </fieldset>
-                <fieldset>
-                    <div class="pure-control-group">
-                        {{ render_field(form.trigger_text, rows=5, placeholder="Some text to wait for in a line
-/some.regex\d{2}/ for case-INsensitive regex
-") }}
-                        <span class="pure-form-message-inline">
-                    <ul>
-                        <li>Text to wait for before triggering a change/notification, all text and regex are tested <i>case-insensitive</i>.</li>
-                        <li>Trigger text is processed from the result-text that comes out of any CSS/JSON Filters for this watch</li>
-                        <li>Each line is processed separately (think of each line as "OR")</li>
-                        <li>Note: Wrap in forward slash / to use regex  example: <code>/foo\d/</code></li>
-                    </ul>
-                        </span>
-                    </div>
-                </fieldset>
-                <fieldset class="pure-group">
-                    {{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
-/some.regex\d{2}/ for case-INsensitive regex
-") }}
-                    <span class="pure-form-message-inline">
-                        <ul>
-                            <li>Matching text will be <strong>ignored</strong> in the text snapshot (you can still see it but it wont trigger a change)</li>
-                            <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
-                            <li>Changing this will affect the comparison checksum which may trigger an alert</li>
-                        </ul>
-                </span>
-
-                </fieldset>
-
-                <fieldset>
-                    <div class="pure-control-group">
-                        {{ render_field(form.text_should_not_be_present, rows=5, placeholder="For example: Out of stock
-Sold out
-Not in stock
-Unavailable") }}
-                        <span class="pure-form-message-inline">
-                            <ul>
-                                <li>Block change-detection while this text is on the page, all text and regex are tested <i>case-insensitive</i>, good for waiting for when a product is available again</li>
-                                <li>Block text is processed from the result-text that comes out of any CSS/JSON Filters for this watch</li>
-                                <li>All lines here must not exist (think of each line as "OR")</li>
-                                <li>Note: Wrap in forward slash / to use regex  example: <code>/foo\d/</code></li>
-                            </ul>
-                        </span>
-                    </div>
-                </fieldset>
-                <fieldset>
-                    <div class="pure-control-group">
-                        {{ render_field(form.extract_text, rows=5, placeholder="/.+?\d+ comments.+?/
- or
-keyword") }}
-                        <span class="pure-form-message-inline">
-                    <ul>
-                        <li>Extracts text in the final output (line by line) after other filters using regular expressions or string match;
-                            <ul>
-                                <li>Regular expression &dash; example <code>/reports.+?2022/i</code></li>
-                                <li>Don't forget to consider the white-space at the start of a line <code>/.+?reports.+?2022/i</code></li>
-                                <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br></li>
-                                <li>Keyword example &dash; example <code>Out of stock</code></li>
-                                <li>Use groups to extract just that text &dash; example <code>/reports.+?(\d+)/i</code> returns a list of years only</li>
-                                <li>Example - match lines containing a keyword <code>/.*icecream.*/</code></li>
-                            </ul>
-                        </li>
-                        <li>One line per regular-expression/string match</li>
-                    </ul>
-                        </span>
-                    </div>
-                </fieldset>
+                {% include "edit/text-options.html" %}
                 </div>
-            </div>
+              </div>
               <div id="text-preview" style="display: none;" >
                     <script>
                         const preview_text_edit_filters_url="{{url_for('ui.ui_edit.watch_get_preview_rendered', uuid=uuid)}}";
@@ -588,10 +456,10 @@ keyword") }}
                     {{ render_button(form.save_button) }}
                     <a href="{{url_for('ui.form_delete', uuid=uuid)}}"
                        class="pure-button button-small button-error ">Delete</a>
-                    <a href="{{url_for('ui.clear_watch_history', uuid=uuid)}}"
-                       class="pure-button button-small button-error ">Clear History</a>
+                    {% if watch.history_n %}<a href="{{url_for('ui.clear_watch_history', uuid=uuid)}}"
+                       class="pure-button button-small button-error ">Clear History</a>{% endif %}
                     <a href="{{url_for('ui.form_clone', uuid=uuid)}}"
-                       class="pure-button button-small ">Create Copy</a>
+                       class="pure-button button-small ">Clone &amp; Edit</a>
                 </div>
             </div>
         </form>

changedetectionio/templates/edit/include_subtract.html

@@ -0,0 +1,55 @@
+                    <div class="pure-control-group">
+                        {% set field = render_field(form.include_filters,
+                            rows=5,
+                            placeholder=has_tag_filters_extra+"#example
+xpath://body/div/span[contains(@class, 'example-class')]",
+                            class="m-d")
+                        %}
+                        {{ field }}
+                        {% if '/text()' in  field %}
+                          <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br>
+                        {% endif %}
+                        <span class="pure-form-message-inline">One CSS, xPath 1 &amp; 2, JSON Path/JQ selector per line, <i>any</i> rules that matches will be used.<br>
+                        <span data-target="#advanced-help-selectors" class="toggle-show pure-button button-tag button-xsmall">Show advanced help and tips</span><br>
+                    <ul id="advanced-help-selectors" style="display: none;">
+                        <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
+                        <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
+                            <ul>
+                                <li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required,  <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
+                                {% if jq_support %}
+                                <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>. Prefix <code>jqraw:</code> outputs the results as text instead of a JSON list.</li>
+                                {% else %}
+                                <li>jq support not installed</li>
+                                {% endif %}
+                            </ul>
+                        </li>
+                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash. To specify XPath to be used explicitly or the XPath rule starts with an XPath function: Prefix with <code>xpath:</code>
+                            <ul>
+                                <li>Example:  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath:count(//*[contains(@class, 'sametext')])</code>, <a
+                                href="http://xpather.com/" target="new">test your XPath here</a></li>
+                                <li>Example: Get all titles from an RSS feed <code>//title/text()</code></li>
+                                <li>To use XPath1.0: Prefix with <code>xpath1:</code></li>
+                            </ul>
+                            </li>
+                    <li>
+                        Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
+                                href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
+                    </li>
+                    </ul>
+
+                </span>
+                    </div>
+                <fieldset class="pure-control-group">
+                    {{ render_field(form.subtractive_selectors, rows=5, placeholder=has_tag_filters_extra+"header
+footer
+nav
+.stockticker
+//*[contains(text(), 'Advertisement')]") }}
+                    <span class="pure-form-message-inline">
+                        <ul>
+                          <li> Remove HTML element(s) by CSS and XPath selectors before text conversion. </li>
+                          <li> Don't paste HTML here, use only CSS and XPath selectors </li>
+                          <li> Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML. </li>
+                        </ul>
+                      </span>
+                </fieldset>

changedetectionio/templates/edit/text-options.html

@@ -0,0 +1,69 @@
+
+                <fieldset>
+                    <div class="pure-control-group">
+                        {{ render_field(form.trigger_text, rows=5, placeholder="Some text to wait for in a line
+/some.regex\d{2}/ for case-INsensitive regex
+") }}
+                        <span class="pure-form-message-inline">
+                    <ul>
+                        <li>Text to wait for before triggering a change/notification, all text and regex are tested <i>case-insensitive</i>.</li>
+                        <li>Trigger text is processed from the result-text that comes out of any CSS/JSON Filters for this watch</li>
+                        <li>Each line is processed separately (think of each line as "OR")</li>
+                        <li>Note: Wrap in forward slash / to use regex  example: <code>/foo\d/</code></li>
+                    </ul>
+                        </span>
+                    </div>
+                </fieldset>
+                <fieldset class="pure-group">
+                    {{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
+/some.regex\d{2}/ for case-INsensitive regex
+") }}
+                    <span class="pure-form-message-inline">
+                        <ul>
+                            <li>Matching text will be <strong>ignored</strong> in the text snapshot (you can still see it but it wont trigger a change)</li>
+                            <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
+                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
+                            <li>Changing this will affect the comparison checksum which may trigger an alert</li>
+                        </ul>
+                </span>
+
+                </fieldset>
+
+                <fieldset>
+                    <div class="pure-control-group">
+                        {{ render_field(form.text_should_not_be_present, rows=5, placeholder="For example: Out of stock
+Sold out
+Not in stock
+Unavailable") }}
+                        <span class="pure-form-message-inline">
+                            <ul>
+                                <li>Block change-detection while this text is on the page, all text and regex are tested <i>case-insensitive</i>, good for waiting for when a product is available again</li>
+                                <li>Block text is processed from the result-text that comes out of any CSS/JSON Filters for this watch</li>
+                                <li>All lines here must not exist (think of each line as "OR")</li>
+                                <li>Note: Wrap in forward slash / to use regex  example: <code>/foo\d/</code></li>
+                            </ul>
+                        </span>
+                    </div>
+                </fieldset>
+                <fieldset>
+                    <div class="pure-control-group">
+                        {{ render_field(form.extract_text, rows=5, placeholder="/.+?\d+ comments.+?/
+ or
+keyword") }}
+                        <span class="pure-form-message-inline">
+                    <ul>
+                        <li>Extracts text in the final output (line by line) after other filters using regular expressions or string match;
+                            <ul>
+                                <li>Regular expression &dash; example <code>/reports.+?2022/i</code></li>
+                                <li>Don't forget to consider the white-space at the start of a line <code>/.+?reports.+?2022/i</code></li>
+                                <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br></li>
+                                <li>Keyword example &dash; example <code>Out of stock</code></li>
+                                <li>Use groups to extract just that text &dash; example <code>/reports.+?(\d+)/i</code> returns a list of years only</li>
+                                <li>Example - match lines containing a keyword <code>/.*icecream.*/</code></li>
+                            </ul>
+                        </li>
+                        <li>One line per regular-expression/string match</li>
+                    </ul>
+                        </span>
+                    </div>
+                </fieldset>

changedetectionio/tests/apprise/test_apprise_asset.py

@@ -0,0 +1,24 @@
+import pytest
+from apprise import AppriseAsset
+
+from changedetectionio.apprise_asset import (
+    APPRISE_APP_DESC,
+    APPRISE_APP_ID,
+    APPRISE_APP_URL,
+    APPRISE_AVATAR_URL,
+)
+
+
+@pytest.fixture(scope="function")
+def apprise_asset() -> AppriseAsset:
+    from changedetectionio.apprise_asset import apprise_asset
+
+    return apprise_asset
+
+
+def test_apprise_asset_init(apprise_asset: AppriseAsset):
+    assert isinstance(apprise_asset, AppriseAsset)
+    assert apprise_asset.app_id == APPRISE_APP_ID
+    assert apprise_asset.app_desc == APPRISE_APP_DESC
+    assert apprise_asset.app_url == APPRISE_APP_URL
+    assert apprise_asset.image_url_logo == APPRISE_AVATAR_URL

changedetectionio/tests/apprise/test_apprise_custom_api_call.py

@@ -0,0 +1,211 @@
+import json
+from unittest.mock import patch
+
+import pytest
+import requests
+from apprise.utils.parse import parse_url as apprise_parse_url
+
+from ...apprise_plugin.custom_handlers import (
+    _get_auth,
+    _get_headers,
+    _get_params,
+    apprise_http_custom_handler,
+    SUPPORTED_HTTP_METHODS,
+)
+
+
+@pytest.mark.parametrize(
+    "url,expected_auth",
+    [
+        ("get://user:pass@localhost:9999", ("user", "pass")),
+        ("get://user@localhost:9999", "user"),
+        ("get://localhost:9999", ""),
+        ("get://user%20name:pass%20word@localhost:9999", ("user name", "pass word")),
+    ],
+)
+def test_get_auth(url, expected_auth):
+    """Test authentication extraction with various URL formats."""
+    parsed_url = apprise_parse_url(url)
+    assert _get_auth(parsed_url) == expected_auth
+
+
+@pytest.mark.parametrize(
+    "url,body,expected_content_type",
+    [
+        (
+            "get://localhost:9999?+content-type=application/xml",
+            "test",
+            "application/xml",
+        ),
+        ("get://localhost:9999", '{"key": "value"}', "application/json; charset=utf-8"),
+        ("get://localhost:9999", "plain text", None),
+        ("get://localhost:9999?+content-type=text/plain", "test", "text/plain"),
+    ],
+)
+def test_get_headers(url, body, expected_content_type):
+    """Test header extraction and content type detection."""
+    parsed_url = apprise_parse_url(url)
+    headers = _get_headers(parsed_url, body)
+
+    if expected_content_type:
+        assert headers.get("Content-Type") == expected_content_type
+
+
+@pytest.mark.parametrize(
+    "url,expected_params",
+    [
+        ("get://localhost:9999?param1=value1", {"param1": "value1"}),
+        ("get://localhost:9999?param1=value1&-param2=ignored", {"param1": "value1"}),
+        ("get://localhost:9999?param1=value1&+header=test", {"param1": "value1"}),
+        (
+            "get://localhost:9999?encoded%20param=encoded%20value",
+            {"encoded param": "encoded value"},
+        ),
+    ],
+)
+def test_get_params(url, expected_params):
+    """Test parameter extraction with URL encoding and exclusion logic."""
+    parsed_url = apprise_parse_url(url)
+    params = _get_params(parsed_url)
+    assert dict(params) == expected_params
+
+
+@pytest.mark.parametrize(
+    "url,schema,method",
+    [
+        ("get://localhost:9999", "get", "GET"),
+        ("post://localhost:9999", "post", "POST"),
+        ("delete://localhost:9999", "delete", "DELETE"),
+    ],
+)
+@patch("requests.request")
+def test_apprise_custom_api_call_success(mock_request, url, schema, method):
+    """Test successful API calls with different HTTP methods and schemas."""
+    mock_request.return_value.raise_for_status.return_value = None
+
+    meta = {"url": url, "schema": schema}
+    result = apprise_http_custom_handler(
+        body="test body", title="Test Title", notify_type="info", meta=meta
+    )
+
+    assert result is True
+    mock_request.assert_called_once()
+
+    call_args = mock_request.call_args
+    assert call_args[1]["method"] == method.upper()
+    assert call_args[1]["url"].startswith("http")
+
+
+@patch("requests.request")
+def test_apprise_custom_api_call_with_auth(mock_request):
+    """Test API call with authentication."""
+    mock_request.return_value.raise_for_status.return_value = None
+
+    url = "get://user:pass@localhost:9999/secure"
+    meta = {"url": url, "schema": "get"}
+
+    result = apprise_http_custom_handler(
+        body=json.dumps({"key": "value"}),
+        title="Secure Test",
+        notify_type="info",
+        meta=meta,
+    )
+
+    assert result is True
+    mock_request.assert_called_once()
+    call_args = mock_request.call_args
+    assert call_args[1]["auth"] == ("user", "pass")
+
+
+@pytest.mark.parametrize(
+    "exception_type,expected_result",
+    [
+        (requests.RequestException, False),
+        (requests.HTTPError, False),
+        (Exception, False),
+    ],
+)
+@patch("requests.request")
+def test_apprise_custom_api_call_failure(mock_request, exception_type, expected_result):
+    """Test various failure scenarios."""
+    url = "get://localhost:9999/error"
+    meta = {"url": url, "schema": "get"}
+
+    # Simulate different types of exceptions
+    mock_request.side_effect = exception_type("Error occurred")
+
+    result = apprise_http_custom_handler(
+        body="error body", title="Error Test", notify_type="error", meta=meta
+    )
+
+    assert result == expected_result
+
+
+def test_invalid_url_parsing():
+    """Test handling of invalid URL parsing."""
+    meta = {"url": "invalid://url", "schema": "invalid"}
+    result = apprise_http_custom_handler(
+        body="test", title="Invalid URL", notify_type="info", meta=meta
+    )
+
+    assert result is False
+
+
+@pytest.mark.parametrize(
+    "schema,expected_method",
+    [
+        (http_method, http_method.upper())
+        for http_method in SUPPORTED_HTTP_METHODS
+    ],
+)
+@patch("requests.request")
+def test_http_methods(mock_request, schema, expected_method):
+    """Test all supported HTTP methods."""
+    mock_request.return_value.raise_for_status.return_value = None
+
+    url = f"{schema}://localhost:9999"
+
+    result = apprise_http_custom_handler(
+        body="test body",
+        title="Test Title",
+        notify_type="info",
+        meta={"url": url, "schema": schema},
+    )
+
+    assert result is True
+    mock_request.assert_called_once()
+
+    call_args = mock_request.call_args
+    assert call_args[1]["method"] == expected_method
+
+
+@pytest.mark.parametrize(
+    "input_schema,expected_method",
+    [
+        (f"{http_method}s", http_method.upper())
+        for http_method in SUPPORTED_HTTP_METHODS
+    ],
+)
+@patch("requests.request")
+def test_https_method_conversion(
+    mock_request, input_schema, expected_method
+):
+    """Validate that methods ending with 's' use HTTPS and correct HTTP method."""
+    mock_request.return_value.raise_for_status.return_value = None
+
+    url = f"{input_schema}://localhost:9999"
+
+    result = apprise_http_custom_handler(
+        body="test body",
+        title="Test Title",
+        notify_type="info",
+        meta={"url": url, "schema": input_schema},
+    )
+
+    assert result is True
+    mock_request.assert_called_once()
+
+    call_args = mock_request.call_args
+
+    assert call_args[1]["method"] == expected_method
+    assert call_args[1]["url"].startswith("https")

changedetectionio/tests/smtp/test_notification_smtp.py

@@ -25,7 +25,6 @@ def test_setup(live_server):
 
 def get_last_message_from_smtp_server():
     import socket
-    global smtp_test_server
     port = 11080  # socket server port number
 
     client_socket = socket.socket()  # instantiate
@@ -44,7 +43,6 @@ def test_check_notification_email_formats_default_HTML(client, live_server, meas
     # live_server_setup(live_server)
     set_original_response()
 
-    global smtp_test_server
     notification_url = f'mailto://changedetection@{smtp_test_server}:11025/?to=fff@home.com'
 
     #####################
@@ -99,7 +97,6 @@ def test_check_notification_email_formats_default_Text_override_HTML(client, liv
     # https://github.com/caronc/apprise/issues/633
 
     set_original_response()
-    global smtp_test_server
     notification_url = f'mailto://changedetection@{smtp_test_server}:11025/?to=fff@home.com'
     notification_body = f"""<!DOCTYPE html>
 <html lang="en">

changedetectionio/tests/test_access_control.py

@@ -60,6 +60,11 @@ def test_check_access_control(app, client, live_server):
         res = c.get(url_for('static_content', group='styles', filename='404-testetest.css'))
         assert res.status_code == 404
 
+        # Access to screenshots should be limited by 'shared_diff_access'
+        path = url_for('static_content', group='screenshot', filename='random-uuid-that-will-404.png', _external=True)
+        res = c.get(path)
+        assert res.status_code == 404
+
         # Check wrong password does not let us in
         res = c.post(
             url_for("login"),
@@ -163,7 +168,7 @@ def test_check_access_control(app, client, live_server):
             url_for("settings.settings_page"),
             data={"application-password": "foobar",
                   # Should be disabled
-#                  "application-shared_diff_access": "True",
+                  "application-shared_diff_access": "",
                   "requests-time_between_check-minutes": 180,
                   'application-fetch_backend': "html_requests"},
             follow_redirects=True
@@ -176,6 +181,10 @@ def test_check_access_control(app, client, live_server):
         # Should be logged out
         assert b"Login" in res.data
 
+        # Access to screenshots should be limited by 'shared_diff_access'
+        res = c.get(url_for('static_content', group='screenshot', filename='random-uuid-that-will-403.png'))
+        assert res.status_code == 403
+
         # The diff page should return something valid when logged out
         res = c.get(url_for("ui.ui_views.diff_history_page", uuid="first"))
         assert b'Random content' not in res.data

changedetectionio/tests/test_api_search.py

@@ -0,0 +1,101 @@
+from copy import copy
+
+from flask import url_for
+import json
+import time
+from .util import live_server_setup, wait_for_all_checks
+
+
+def test_api_search(client, live_server):
+    live_server_setup(live_server)
+    api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
+
+    watch_data = {}
+    # Add some test watches
+    urls = [
+        'https://example.com/page1',
+        'https://example.org/testing',
+        'https://test-site.com/example'
+    ]
+
+    # Import the test URLs
+    res = client.post(
+        url_for("imports.import_page"),
+        data={"urls": "\r\n".join(urls)},
+        follow_redirects=True
+    )
+    assert b"3 Imported" in res.data
+    wait_for_all_checks(client)
+
+    # Get a listing, it will be the first one
+    watches_response = client.get(
+        url_for("createwatch"),
+        headers={'x-api-key': api_key}
+    )
+
+
+    # Add a title to one watch for title search testing
+    for uuid, watch in watches_response.json.items():
+
+        watch_data = client.get(url_for("watch", uuid=uuid),
+                                follow_redirects=True,
+                                headers={'x-api-key': api_key}
+                                )
+
+        if urls[0] == watch_data.json['url']:
+            # HTTP PUT ( UPDATE an existing watch )
+            client.put(
+                url_for("watch", uuid=uuid),
+                headers={'x-api-key': api_key, 'content-type': 'application/json'},
+                data=json.dumps({'title': 'Example Title Test'}),
+            )
+
+    # Test search by URL
+    res = client.get(url_for("search")+"?q=https://example.com/page1", headers={'x-api-key': api_key, 'content-type': 'application/json'})
+    assert len(res.json) == 1
+    assert list(res.json.values())[0]['url'] == urls[0]
+
+    # Test search by URL - partial should NOT match without ?partial=true flag
+    res = client.get(url_for("search")+"?q=https://example", headers={'x-api-key': api_key, 'content-type': 'application/json'})
+    assert len(res.json) == 0
+
+
+    # Test search by title
+    res = client.get(url_for("search")+"?q=Example Title Test", headers={'x-api-key': api_key, 'content-type': 'application/json'})
+    assert len(res.json) == 1
+    assert list(res.json.values())[0]['url'] == urls[0]
+    assert list(res.json.values())[0]['title'] == 'Example Title Test'
+
+    # Test search that should return multiple results (partial = true)
+    res = client.get(url_for("search")+"?q=https://example&partial=true", headers={'x-api-key': api_key, 'content-type': 'application/json'})
+    assert len(res.json) == 2
+
+    # Test empty search
+    res = client.get(url_for("search")+"?q=", headers={'x-api-key': api_key, 'content-type': 'application/json'})
+    assert res.status_code == 400
+
+    # Add a tag to test search with tag filter
+    tag_name = 'test-tag'
+    res = client.post(
+        url_for("tag"),
+        data=json.dumps({"title": tag_name}),
+        headers={'content-type': 'application/json', 'x-api-key': api_key}
+    )
+    assert res.status_code == 201
+    tag_uuid = res.json['uuid']
+
+    # Add the tag to one watch
+    for uuid, watch in watches_response.json.items():
+        if urls[2] == watch['url']:
+            client.put(
+                url_for("watch", uuid=uuid),
+                headers={'x-api-key': api_key, 'content-type': 'application/json'},
+                data=json.dumps({'tags': [tag_uuid]}),
+            )
+
+
+    # Test search with tag filter and q
+    res = client.get(url_for("search") + f"?q={urls[2]}&tag={tag_name}", headers={'x-api-key': api_key, 'content-type': 'application/json'})
+    assert len(res.json) == 1
+    assert list(res.json.values())[0]['url'] == urls[2]
+

changedetectionio/tests/test_clone.py

@@ -2,29 +2,39 @@
 
 import time
 from flask import url_for
-from . util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
 
 
-
-def test_trigger_functionality(client, live_server, measure_memory_usage):
+def test_clone_functionality(client, live_server, measure_memory_usage):
 
     live_server_setup(live_server)
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write("<html><body>Some content</body></html>")
 
-    # Give the endpoint time to spin up
-    time.sleep(1)
+    test_url = url_for('test_endpoint', _external=True)
 
     # Add our URL to the import page
     res = client.post(
         url_for("imports.import_page"),
-        data={"urls": "https://changedetection.io"},
+        data={"urls": test_url},
         follow_redirects=True
     )
     assert b"1 Imported" in res.data
+    wait_for_all_checks(client)
 
+    # So that we can be sure the same history doesnt carry over
+    time.sleep(1)
 
     res = client.get(
         url_for("ui.form_clone", uuid="first"),
         follow_redirects=True
     )
+    existing_uuids = set()
 
-    assert b"Cloned." in res.data
+    for uuid, watch in live_server.app.config['DATASTORE'].data['watching'].items():
+        new_uuids = set(watch.history.keys())
+        duplicates = existing_uuids.intersection(new_uuids)
+        assert len(duplicates) == 0
+        existing_uuids.update(new_uuids)
+
+    assert b"Cloned" in res.data

changedetectionio/tests/test_conditions.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 import json
-import urllib
+import time
 
 from flask import url_for
 from .util import live_server_setup, wait_for_all_checks
@@ -113,6 +113,7 @@ def test_conditions_with_text_and_number(client, live_server):
     client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
 
+    time.sleep(2)
     # 75 is > 20 and < 100 and contains "5"
     res = client.get(url_for("watchlist.index"))
     assert b'unviewed' in res.data

changedetectionio/tests/test_group.py

@@ -273,6 +273,7 @@ def test_limit_tag_ui(client, live_server, measure_memory_usage):
     assert b'Deleted' in res.data
     res = client.get(url_for("tags.delete_all"), follow_redirects=True)
     assert b'All tags deleted' in res.data
+
 def test_clone_tag_on_import(client, live_server, measure_memory_usage):
     #live_server_setup(live_server)
     test_url = url_for('test_endpoint', _external=True)
@@ -292,6 +293,7 @@ def test_clone_tag_on_import(client, live_server, measure_memory_usage):
     res = client.get(url_for("ui.form_clone", uuid=watch_uuid), follow_redirects=True)
 
     assert b'Cloned' in res.data
+    res = client.get(url_for("watchlist.index"))
     # 2 times plus the top link to tag
     assert res.data.count(b'test-tag') == 3
     assert res.data.count(b'another-tag') == 3
@@ -317,8 +319,9 @@ def test_clone_tag_on_quickwatchform_add(client, live_server, measure_memory_usa
 
     watch_uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     res = client.get(url_for("ui.form_clone", uuid=watch_uuid), follow_redirects=True)
-
     assert b'Cloned' in res.data
+
+    res = client.get(url_for("watchlist.index"))
     # 2 times plus the top link to tag
     assert res.data.count(b'test-tag') == 3
     assert res.data.count(b'another-tag') == 3

changedetectionio/tests/test_rss.py

@@ -49,6 +49,22 @@ def set_original_cdata_xml():
         f.write(test_return_data)
 
 
+
+def set_html_content(content):
+    test_return_data = f"""<html>
+       <body>
+     Some initial text<br>
+     <p>{content}</p>
+     <br>
+     So let's see what happens.  <br>
+     </body>
+     </html>
+    """
+
+    # Write as UTF-8 encoded bytes
+    with open("test-datastore/endpoint-content.txt", "wb") as f:
+        f.write(test_return_data.encode('utf-8'))
+
 def test_setup(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
 
@@ -164,3 +180,58 @@ def test_rss_xpath_filtering(client, live_server, measure_memory_usage):
     assert b'Some other description' not in res.data  # Should NOT be selected by the xpath
 
     res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
+
+
+def test_rss_bad_chars_breaking(client, live_server):
+    """This should absolutely trigger the RSS builder to go into worst state mode
+
+    - source: prefix means no html conversion (which kinda filters out the bad stuff)
+    - Binary data
+    - Very long so that the saving is performed by Brotli (and decoded back to bytes)
+
+    Otherwise feedgen should support regular unicode
+    """
+    #live_server_setup(live_server)
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        ten_kb_string = "A" * 10_000
+        f.write(ten_kb_string)
+
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("imports.import_page"),
+        data={"urls": "source:"+test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+    wait_for_all_checks(client)
+
+    # Set the bad content
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        jpeg_bytes = "\xff\xd8\xff\xe0\x00\x10XXXXXXXX\x00\x01\x02\x00\x00\x01\x00\x01\x00\x00"  # JPEG header
+        jpeg_bytes += "A" * 10_000
+
+        f.write(jpeg_bytes)
+
+    res = client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
+    assert b'Queued 1 watch for rechecking.' in res.data
+    wait_for_all_checks(client)
+    rss_token = extract_rss_token_from_UI(client)
+
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n == 2
+
+    # Check RSS feed is still working
+    res = client.get(
+        url_for("rss.feed", uuid=uuid, token=rss_token),
+        follow_redirects=False # Important! leave this off! it should not redirect
+    )
+    assert res.status_code == 200
+
+    #assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n == 2
+    #assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n == 2
+
+
+
+
+

changedetectionio/tests/unit/test_conditions.py

@@ -75,7 +75,7 @@ class TestTriggerConditions(unittest.TestCase):
                                                      ephemeral_data={'text': "I saw 500 people at a rock show"})
 
         # @todo - now we can test that 'Extract number' increased more than X since last time
-        self.assertTrue(result)
+        self.assertTrue(result.get('result'))
 
 
 if __name__ == '__main__':

changedetectionio/tests/util.py

@@ -173,7 +173,7 @@ def live_server_setup(live_server):
                 return resp
 
             # Tried using a global var here but didn't seem to work, so reading from a file instead.
-            with open("test-datastore/endpoint-content.txt", "r") as f:
+            with open("test-datastore/endpoint-content.txt", "rb") as f:
                 resp = make_response(f.read(), status_code)
                 if uppercase_headers:
                     resp.headers['CONTENT-TYPE'] = ctype if ctype else 'text/html'

changedetectionio/update_worker.py

@@ -253,8 +253,9 @@ class update_worker(threading.Thread):
                 pass
 
             else:
-                fetch_start_time = time.time()
+
                 uuid = queued_item_data.item.get('uuid')
+                fetch_start_time = round(time.time())  # Also used for a unique history key for now
                 self.current_uuid = uuid
                 if uuid in list(self.datastore.data['watching'].keys()) and self.datastore.data['watching'][uuid].get('url'):
                     changed_detected = False
@@ -262,8 +263,10 @@ class update_worker(threading.Thread):
                     process_changedetection_results = True
                     update_obj = {}
 
+
                     # Clear last errors (move to preflight func?)
                     self.datastore.data['watching'][uuid]['browser_steps_last_error_step'] = None
+                    self.datastore.data['watching'][uuid]['last_checked'] = fetch_start_time
 
                     watch = self.datastore.data['watching'].get(uuid)
 
@@ -287,10 +290,6 @@ class update_worker(threading.Thread):
 
                         update_handler.call_browser()
 
-                        # In reality, the actual time of when the change was detected could be a few seconds after this
-                        # For example it should include when the page stopped rendering if using a playwright/chrome type fetch
-                        fetch_start_time = time.time()
-
                         changed_detected, update_obj, contents = update_handler.run_changedetection(watch=watch)
 
                         # Re #342
@@ -587,7 +586,6 @@ class update_worker(threading.Thread):
                         pass
 
                     self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - fetch_start_time, 3),
-                                                                       'last_checked': int(fetch_start_time),
                                                                        'check_count': count
                                                                        })
 

requirements.txt

@@ -1,6 +1,3 @@
-# Used by Pyppeteer
-pyee
-
 eventlet>=0.38.0
 feedgen~=0.9
 flask-compress
@@ -73,7 +70,8 @@ jq~=1.3; python_version >= "3.8" and sys_platform == "linux"
 
 # playwright is installed at Dockerfile build time because it's not available on all platforms
 
-pyppeteer-ng==2.0.0rc5
+pyppeteer-ng==2.0.0rc9
+
 pyppeteerstealth>=0.0.4
 
 # Include pytest, so if theres a support issue we can ask them to run these tests on their setup