tweak test

Co-authored-by: bwees <branonwees@gmail.com>

README.md

@@ -3,9 +3,9 @@
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
-## Self-Hosted, Open Source, Change Monitoring of Web Pages
+## Web Site Change Detection, Monitoring and Notification - Self-Hosted or SaaS.
 
-_Know when web pages change! Stay ontop of new information!_ 
+_Know when web pages change! Stay ontop of new information! get notifications when important website content changes_ 
 
 Live your data-life *pro-actively* instead of *re-actively*.
 

changedetectionio/__init__.py

@@ -361,7 +361,7 @@ def changedetection_app(config=None, datastore_o=None):
                 fe.pubDate(dt)
 
         response = make_response(fg.rss_str())
-        response.headers.set('Content-Type', 'application/rss+xml')
+        response.headers.set('Content-Type', 'application/rss+xml;charset=utf-8')
         return response
 
     @app.route("/", methods=['GET'])

changedetectionio/content_fetcher.py

@@ -46,6 +46,7 @@ class Fetcher():
     headers = None
 
     fetcher_description = "No description"
+    webdriver_js_execute_code = None
     xpath_element_js = """               
                 // Include the getXpath script directly, easier than fetching
                 !function(e,n){"object"==typeof exports&&"undefined"!=typeof module?module.exports=n():"function"==typeof define&&define.amd?define(n):(e=e||self).getXPath=n()}(this,function(){return function(e){var n=e;if(n&&n.id)return'//*[@id="'+n.id+'"]';for(var o=[];n&&Node.ELEMENT_NODE===n.nodeType;){for(var i=0,r=!1,d=n.previousSibling;d;)d.nodeType!==Node.DOCUMENT_TYPE_NODE&&d.nodeName===n.nodeName&&i++,d=d.previousSibling;for(d=n.nextSibling;d;){if(d.nodeName===n.nodeName){r=!0;break}d=d.nextSibling}o.push((n.prefix?n.prefix+":":"")+n.localName+(i||r?"["+(i+1)+"]":"")),n=n.parentNode}return o.length?"/"+o.reverse().join("/"):""}});
@@ -175,7 +176,6 @@ class Fetcher():
 
     # Will be needed in the future by the VisualSelector, always get this where possible.
     screenshot = False
-    fetcher_description = "No description"
     system_http_proxy = os.getenv('HTTP_PROXY')
     system_https_proxy = os.getenv('HTTPS_PROXY')
 
@@ -309,13 +309,19 @@ class base_html_playwright(Fetcher):
                 page.set_default_navigation_timeout(90000)
                 page.set_default_timeout(90000)
 
-               # Bug - never set viewport size BEFORE page.goto
+                # Listen for all console events and handle errors
+                page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
+
+                # Bug - never set viewport size BEFORE page.goto
 
                 # Waits for the next navigation. Using Python context manager
                 # prevents a race condition between clicking and waiting for a navigation.
                 with page.expect_navigation():
                     response = page.goto(url, wait_until='load')
 
+                if self.webdriver_js_execute_code is not None:
+                    page.evaluate(self.webdriver_js_execute_code)
+
             except playwright._impl._api_types.TimeoutError as e:
                 context.close()
                 browser.close()
@@ -447,6 +453,12 @@ class base_html_webdriver(Fetcher):
 
         self.driver.set_window_size(1280, 1024)
         self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+
+        if self.webdriver_js_execute_code is not None:
+            self.driver.execute_script(self.webdriver_js_execute_code)
+            # Selenium doesn't automatically wait for actions as good as Playwright, so wait again
+            self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+
         self.screenshot = self.driver.get_screenshot_as_png()
 
         # @todo - how to check this? is it possible?

changedetectionio/fetch_site_status.py

@@ -11,6 +11,7 @@ urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 
 # Some common stuff here that can be moved to a base class
+# (set_proxy_from_list)
 class perform_site_check():
 
     def __init__(self, *args, datastore, **kwargs):
@@ -45,6 +46,20 @@ class perform_site_check():
 
         return proxy_args
 
+    # Doesn't look like python supports forward slash auto enclosure in re.findall
+    # So convert it to inline flag "foobar(?i)" type configuration
+    def forward_slash_enclosed_regex_to_options(self, regex):
+        res = re.search(r'^/(.*?)/(\w+)$', regex, re.IGNORECASE)
+
+        if res:
+            regex = res.group(1)
+            regex += '(?{})'.format(res.group(2))
+        else:
+            regex += '(?{})'.format('i')
+
+        return regex
+
+
     def run(self, uuid):
         timestamp = int(time.time())  # used for storage etc too
 
@@ -106,6 +121,9 @@ class perform_site_check():
         elif system_webdriver_delay is not None:
             fetcher.render_extract_delay = system_webdriver_delay
 
+        if watch['webdriver_js_execute_code'] is not None and watch['webdriver_js_execute_code'].strip():
+            fetcher.webdriver_js_execute_code = watch['webdriver_js_execute_code']
+
         fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_code, watch['css_filter'])
         fetcher.quit()
 
@@ -147,7 +165,9 @@ class perform_site_check():
                 is_html = False
 
         if is_html or is_source:
+            
             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
+            fetcher.content = html_tools.workarounds_for_obfuscations(fetcher.content)
             html_content = fetcher.content
 
             # If not JSON,  and if it's not text/plain..
@@ -210,15 +230,27 @@ class perform_site_check():
         if len(extract_text) > 0:
             regex_matched_output = []
             for s_re in extract_text:
-                result = re.findall(s_re.encode('utf8'), stripped_text_from_html,
-                                    flags=re.MULTILINE | re.DOTALL | re.LOCALE)
-                if result:
-                    regex_matched_output.append(result[0])
+                # incase they specified something in '/.../x'
+                regex = self.forward_slash_enclosed_regex_to_options(s_re)
+                result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
 
+                for l in result:
+                    if type(l) is tuple:
+                        #@todo - some formatter option default (between groups)
+                        regex_matched_output += list(l) + [b'\n']
+                    else:
+                        # @todo - some formatter option default (between each ungrouped result)
+                        regex_matched_output += [l] + [b'\n']
+
+            # Now we will only show what the regex matched
+            stripped_text_from_html = b''
+            text_content_before_ignored_filter = b''
             if regex_matched_output:
-                stripped_text_from_html = b'\n'.join(regex_matched_output)
+                # @todo some formatter for presentation?
+                stripped_text_from_html = b''.join(regex_matched_output)
                 text_content_before_ignored_filter = stripped_text_from_html
 
+
         # Re #133 - if we should strip whitespaces from triggering the change detected comparison
         if self.datastore.data['settings']['application'].get('ignore_whitespace', False):
             fetched_md5 = hashlib.md5(stripped_text_from_html.translate(None, b'\r\n\t ')).hexdigest()

changedetectionio/forms.py

@@ -344,9 +344,13 @@ class watchForm(commonSettingsForm):
     trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
     text_should_not_be_present = StringListField('Block change-detection if text matches', [validators.Optional(), ValidateListRegex()])
 
+    webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
+
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
     save_and_preview_button = SubmitField('Save & Preview', render_kw={"class": "pure-button pure-button-primary"})
     proxy = RadioField('Proxy')
+    filter_failure_notification_send = BooleanField(
+        'Send a notification when the filter can no longer be found on the page', default=False)
 
     def validate(self, **kwargs):
         if not super().validate():
@@ -385,6 +389,11 @@ class globalSettingsApplicationForm(commonSettingsForm):
     api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
     password = SaltyPasswordField()
 
+    filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',
+                                                                  render_kw={"style": "width: 5em;"},
+                                                                  validators=[validators.NumberRange(min=0,
+                                                                                                     message="Should contain zero or more attempts")])
+
 
 class globalSettingsForm(Form):
     # Define these as FormFields/"sub forms", this way it matches the JSON storage

changedetectionio/html_tools.py

@@ -1,5 +1,4 @@
 import json
-import re
 from typing import List
 
 from bs4 import BeautifulSoup
@@ -8,16 +7,23 @@ import re
 from inscriptis import get_text
 from inscriptis.model.config import ParserConfig
 
+class FilterNotFoundInResponse(ValueError):
+    def __init__(self, msg):
+        ValueError.__init__(self, msg)
 
 class JSONNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
 
+
 # Given a CSS Rule, and a blob of HTML, return the blob of HTML that matches
 def css_filter(css_filter, html_content):
     soup = BeautifulSoup(html_content, "html.parser")
     html_block = ""
-    for item in soup.select(css_filter, separator=""):
+    r = soup.select(css_filter, separator="")
+    if len(html_content) > 0 and len(r) == 0:
+        raise FilterNotFoundInResponse(css_filter)
+    for item in r:
         html_block += str(item)
 
     return html_block + "\n"
@@ -42,8 +48,12 @@ def xpath_filter(xpath_filter, html_content):
     tree = html.fromstring(bytes(html_content, encoding='utf-8'))
     html_block = ""
 
-    for item in tree.xpath(xpath_filter.strip(), namespaces={'re':'http://exslt.org/regular-expressions'}):
-        html_block+= etree.tostring(item, pretty_print=True).decode('utf-8')+"<br/>"
+    r = tree.xpath(xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'})
+    if len(html_content) > 0 and len(r) == 0:
+        raise FilterNotFoundInResponse(xpath_filter)
+
+    for item in r:
+        html_block += etree.tostring(item, pretty_print=True).decode('utf-8') + "<br/>"
 
     return html_block
 
@@ -202,3 +212,17 @@ def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
 
     return text_content
 
+def workarounds_for_obfuscations(content):
+    """
+    Some sites are using sneaky tactics to make prices and other information un-renderable by Inscriptis
+    This could go into its own Pip package in the future, for faster updates
+    """
+
+    # HomeDepot.com style <span>$<!-- -->90<!-- -->.<!-- -->74</span>
+    # https://github.com/weblyzard/inscriptis/issues/45
+    if not content:
+        return content
+
+    content = re.sub('<!--\s+-->', '', content)
+
+    return content

changedetectionio/model/App.py

@@ -1,30 +1,28 @@
-import collections
-import os
-
-import uuid as uuid_builder
-
+from os import getenv
 from changedetectionio.notification import (
     default_notification_body,
     default_notification_format,
     default_notification_title,
 )
 
+_FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT = 6
+
 class model(dict):
     base_config = {
             'note': "Hello! If you change this file manually, please be sure to restart your changedetection.io instance!",
             'watching': {},
             'settings': {
                 'headers': {
-                    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36',
+                    'User-Agent': getenv("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'),
                     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
                     'Accept-Encoding': 'gzip, deflate',  # No support for brolti in python requests yet.
                     'Accept-Language': 'en-GB,en-US;q=0.9,en;'
                 },
                 'requests': {
-                    'timeout': 15,  # Default 15 seconds
+                    'timeout': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
                     'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
                     'jitter_seconds': 0,
-                    'workers': 10,  # Number of threads, lower is better for slow connections
+                    'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "10")),  # Number of threads, lower is better for slow connections
                     'proxy': None # Preferred proxy connection
                 },
                 'application': {
@@ -33,7 +31,8 @@ class model(dict):
                     'base_url' : None,
                     'extract_title_as_title': False,
                     'empty_pages_are_a_change': False,
-                    'fetch_backend': os.getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
+                    'fetch_backend': getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
+                    'filter_failure_notification_threshold_attempts': _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT,
                     'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
                     'global_subtractive_selectors': [],
                     'ignore_whitespace': True,

changedetectionio/model/Watch.py

@@ -2,6 +2,7 @@ import os
 import uuid as uuid_builder
 
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
+mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
 
 from changedetectionio.notification import (
     default_notification_body,
@@ -40,6 +41,8 @@ class model(dict):
             'trigger_text': [],  # List of text or regex to wait for until a change is detected
             'text_should_not_be_present': [], # Text that should not present
             'fetch_backend': None,
+            'filter_failure_notification_send': True,
+            'consecutive_filter_failures': 0, # Every time the CSS/xPath filter cannot be located, reset when all is fine.
             'extract_title_as_title': False,
             'check_unique_lines': False, # On change-detected, compare against all history if its something new
             'proxy': None, # Preferred proxy connection
@@ -47,10 +50,11 @@ class model(dict):
             # Requires setting to None on submit if it's the same as the default
             # Should be all None by default, so we use the system default in this case.
             'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
-            'webdriver_delay': None
+            'webdriver_delay': None,
+            'webdriver_js_execute_code': None, # Run before change-detection
         }
     jitter_seconds = 0
-    mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
+
     def __init__(self, *arg, **kw):
         import uuid
         self.update(self.__base_config)
@@ -159,7 +163,7 @@ class model(dict):
 
     def threshold_seconds(self):
         seconds = 0
-        for m, n in self.mtable.items():
+        for m, n in mtable.items():
             x = self.get('time_between_check', {}).get(m, None)
             if x:
                 seconds += x * n

changedetectionio/notification.py

@@ -34,7 +34,6 @@ def process_notification(n_object, datastore):
         valid_notification_formats[default_notification_format],
     )
 
-
     # Insert variables into the notification content
     notification_parameters = create_notification_parameters(n_object, datastore)
 
@@ -64,7 +63,7 @@ def process_notification(n_object, datastore):
 
                 # So if no avatar_url is specified, add one so it can be correctly calculated into the total payload
                 k = '?' if not '?' in url else '&'
-                if not 'avatar_url' in url:
+                if not 'avatar_url' in url and not url.startswith('mail'):
                     url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
 
                 if url.startswith('tgram://'):
@@ -79,13 +78,21 @@ def process_notification(n_object, datastore):
                     n_title = n_title[0:payload_max_size]
                     n_body = n_body[0:body_limit]
 
-                elif url.startswith('discord://'):
+                elif url.startswith('discord://') or url.startswith('https://discordapp.com/api/webhooks'):
                     # real limit is 2000, but minus some for extra metadata
                     payload_max_size = 1700
                     body_limit = max(0, payload_max_size - len(n_title))
                     n_title = n_title[0:payload_max_size]
                     n_body = n_body[0:body_limit]
 
+                elif url.startswith('mailto'):
+                    # Apprise will default to HTML, so we need to override it
+                    # So that whats' generated in n_body is in line with what is going to be sent.
+                    # https://github.com/caronc/apprise/issues/633#issuecomment-1191449321
+                    if not 'format=' in url and (n_format == 'text' or n_format == 'markdown'):
+                        prefix = '?' if not '?' in url else '&'
+                        url = "{}{}format={}".format(url, prefix, n_format)
+
                 apobj.add(url)
 
                 apobj.notify(

changedetectionio/static/images/spread-white.svg

@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   width="18"
+   height="19.92"
+   viewBox="0 0 18 19.92"
+   version="1.1"
+   id="svg6"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg">
+  <defs
+     id="defs10" />
+  <path
+     d="M -3,-2 H 21 V 22 H -3 Z"
+     fill="none"
+     id="path2" />
+  <path
+     d="m 15,14.08 c -0.76,0 -1.44,0.3 -1.96,0.77 L 5.91,10.7 C 5.96,10.47 6,10.24 6,10 6,9.76 5.96,9.53 5.91,9.3 L 12.96,5.19 C 13.5,5.69 14.21,6 15,6 16.66,6 18,4.66 18,3 18,1.34 16.66,0 15,0 c -1.66,0 -3,1.34 -3,3 0,0.24 0.04,0.47 0.09,0.7 L 5.04,7.81 C 4.5,7.31 3.79,7 3,7 1.34,7 0,8.34 0,10 c 0,1.66 1.34,3 3,3 0.79,0 1.5,-0.31 2.04,-0.81 l 7.12,4.16 c -0.05,0.21 -0.08,0.43 -0.08,0.65 0,1.61 1.31,2.92 2.92,2.92 1.61,0 2.92,-1.31 2.92,-2.92 0,-1.61 -1.31,-2.92 -2.92,-2.92 z"
+     id="path4"
+     style="fill:#ffffff;fill-opacity:1" />
+</svg>

changedetectionio/static/styles/.gitignore

@@ -1 +1,3 @@
 node_modules
+package-lock.json
+

changedetectionio/store.py

@@ -158,8 +158,7 @@ class ChangeDetectionStore:
     @property
     def threshold_seconds(self):
         seconds = 0
-        mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
-        for m, n in mtable.items():
+        for m, n in Watch.mtable.items():
             x = self.__data['settings']['requests']['time_between_check'].get(m)
             if x:
                 seconds += x * n
@@ -298,7 +297,8 @@ class ChangeDetectionStore:
                           'ignore_text', 'css_filter',
                           'subtractive_selectors', 'trigger_text',
                           'extract_title_as_title', 'extract_text',
-                          'text_should_not_be_present']:
+                          'text_should_not_be_present',
+                          'webdriver_js_execute_code']:
                     if res.get(k):
                         apply_extras[k] = res[k]
 

changedetectionio/templates/edit.html

@@ -25,7 +25,7 @@
         <ul>
             <li class="tab" id="default-tab"><a href="#general">General</a></li>
             <li class="tab"><a href="#request">Request</a></li>
-            <li class="tab"><a id="visualselector-tab" href="#visualselector">Visual Selector</a></li>
+            <li class="tab"><a id="visualselector-tab" href="#visualselector">Visual Filter Selector</a></li>
             <li class="tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
             <li class="tab"><a href="#notifications">Notifications</a></li>
         </ul>
@@ -62,6 +62,12 @@
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.extract_title_as_title) }}
                     </div>
+                    <div class="pure-control-group">
+                        {{ render_checkbox_field(form.filter_failure_notification_send) }}
+                        <span class="pure-form-message-inline">
+                         Sends a notification when the filter can no longer be seen on the page, good for knowing when the page changed and your filter will not work anymore.
+                        </span>
+                    </div>
                 </fieldset>
             </div>
 
@@ -88,14 +94,17 @@
                             <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
                             <br/>
                             This will wait <i>n</i> seconds before extracting the text.
+                            {% if using_global_webdriver_wait %}
+                            <br/><strong>Using the current global default settings</strong>
+                            {% endif %}
                         </div>
-
                     </div>
-                    {% if using_global_webdriver_wait %}
-                    <div class="pure-form-message-inline">
-                        <strong>Using the current global default settings</strong>
+                    <div class="pure-control-group">
+                        {{ render_field(form.webdriver_js_execute_code) }}
+                        <div class="pure-form-message-inline">
+                            Run this code before performing change detection, handy for filling in fields and other actions <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Run-JavaScript-before-change-detection">More help and examples here</a>
+                        </div>
                     </div>
-                    {% endif %}
                 </fieldset>
                 <fieldset class="pure-group" id="requests-override-options">
                     {% if not playwright_enabled %}
@@ -187,7 +196,7 @@ nav
                     <span class="pure-form-message-inline">
                         <ul>
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                            <li>Regular Expression support, wrap the line in forward slash <code>/regex/</code></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>
                             <li>Use the preview/show current tab to see ignores</li>
                         </ul>
@@ -230,8 +239,15 @@ Unavailable") }}
                         {{ render_field(form.extract_text, rows=5, placeholder="\d+ online") }}
                         <span class="pure-form-message-inline">
                     <ul>
-                        <li>Extracts text in the final output after other filters using regular expressions, for example <code>\d+ online</code></li>
-                        <li>One line per regular-expression.</li>
+                        <li>Extracts text in the final output (line by line) after other filters using regular expressions;
+                            <ul>
+                                <li>Regular expression &dash; example <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>
+                            </ul>
+                        </li>
+                        <li>One line per regular-expression/ string match</li>
                     </ul>
                         </span>
                     </div>
@@ -240,7 +256,7 @@ Unavailable") }}
 
             <div class="tab-pane-inner visual-selector-ui" id="visualselector">
                 <img id="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
-
+                <strong>Pro-tip:</strong> This tool is only for limiting which elements will be included on a change-detection, not for interacting with browser directly.
                 <fieldset>
                     <div class="pure-control-group">
                         {% if visualselector_enabled %}

changedetectionio/templates/settings.html

@@ -36,7 +36,13 @@
                         {{ render_field(form.requests.form.jitter_seconds, class="jitter_seconds") }}
                         <span class="pure-form-message-inline">Example - 3 seconds random jitter could trigger up to 3 seconds earlier or up to 3 seconds later</span>
                     </div>
-
+                    <div class="pure-control-group">
+                        {{ render_field(form.application.form.filter_failure_notification_threshold_attempts, class="filter_failure_notification_threshold_attempts") }}
+                        <span class="pure-form-message-inline">After this many consecutive times that the CSS/xPath filter is missing, send a notification
+                            <br/>
+                        Set to <strong>0</strong> to disable
+                        </span>
+                    </div>
                     <div class="pure-control-group">
                         {% if not hide_remove_pass %}
                             {% if current_user.is_authenticated %}
@@ -148,7 +154,7 @@ nav
                         <ul>
                             <li>Note: This is applied globally in addition to the per-watch rules.</li>
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                            <li>Regular Expression support, wrap the line in forward slash <code>/regex/</code></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>
                             <li>Use the preview/show current tab to see ignores</li>
                         </ul>

changedetectionio/templates/watch-overview.html

@@ -14,7 +14,7 @@
                 {{ render_simple_field(form.tag, value=active_tag if active_tag else '', placeholder="watch group") }}
             <button type="submit" class="pure-button pure-button-primary">Watch</button>
         </fieldset>
-        <span style="color:#eee; font-size: 80%;"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread.svg')}}" /> Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></a></span>
+        <span style="color:#eee; font-size: 80%;"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" /> Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></a></span>
     </form>
     <div>
         <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag }}">All</a>

changedetectionio/tests/test_extract_regex.py

@@ -15,7 +15,7 @@ def set_original_response():
      </br>
      So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
-     <div id="changetext">Some text that will change</div>
+     <div class="changetext">Some text that will change</div>     
      </body>
      </html>
     """
@@ -33,7 +33,8 @@ def set_modified_response():
      </br>
      So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
-     <div id="changetext">Some text that did change ( 1000 online <br/> 80 guests)</div>
+     <div class="changetext">Some text that did change ( 1000 online <br/> 80 guests<br/>  2000 online )</div>
+     <div class="changetext">SomeCase insensitive 3456</div>
      </body>
      </html>
     """
@@ -44,11 +45,78 @@ def set_modified_response():
     return None
 
 
-def test_check_filter_and_regex_extract(client, live_server):
-    sleep_time_for_fetch_thread = 3
+def set_multiline_response():
+    test_return_data = """<html>
+       <body>
+     
+     <p>Something <br/>
+        across 6 billion multiple<br/>
+        lines
+     </p>
+     
+     <div>aaand something lines</div>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+    return None
+
+
+def test_setup(client, live_server):
 
     live_server_setup(live_server)
-    css_filter = "#changetext"
+
+def test_check_filter_multiline(client, live_server):
+
+    set_multiline_response()
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    time.sleep(3)
+
+    # Goto the edit page, add our ignore text
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"css_filter": '',
+              'extract_text': '/something.+?6 billion.+?lines/si',
+              "url": test_url,
+              "tag": "",
+              "headers": "",
+              'fetch_backend': "html_requests"
+              },
+        follow_redirects=True
+    )
+
+    assert b"Updated watch." in res.data
+    time.sleep(3)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+
+    assert b'<div class="">Something' in res.data
+    assert b'<div class="">across 6 billion multiple' in res.data
+    assert b'<div class="">lines' in res.data
+
+    # but the last one, which also says 'lines' shouldnt be here (non-greedy match checking)
+    assert b'aaand something lines' not in res.data
+
+def test_check_filter_and_regex_extract(client, live_server):
+    sleep_time_for_fetch_thread = 3
+    css_filter = ".changetext"
 
     set_original_response()
 
@@ -64,6 +132,7 @@ def test_check_filter_and_regex_extract(client, live_server):
     )
     assert b"1 Imported" in res.data
 
+    time.sleep(1)
     # Trigger a check
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
@@ -75,7 +144,7 @@ def test_check_filter_and_regex_extract(client, live_server):
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={"css_filter": css_filter,
-              'extract_text': '\d+ online\n\d+ guests',
+              'extract_text': '\d+ online\r\n\d+ guests\r\n/somecase insensitive \d+/i\r\n/somecase insensitive (345\d)/i',
               "url": test_url,
               "tag": "",
               "headers": "",
@@ -86,15 +155,6 @@ def test_check_filter_and_regex_extract(client, live_server):
 
     assert b"Updated watch." in res.data
 
-    # Check it saved
-    res = client.get(
-        url_for("edit_page", uuid="first"),
-    )
-    assert b'\d+ online' in res.data
-
-    # Trigger a check
-#    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 
@@ -119,9 +179,20 @@ def test_check_filter_and_regex_extract(client, live_server):
 
     # Class will be blank for now because the frontend didnt apply the diff
     assert b'<div class="">1000 online' in res.data
-    
+
+    # All regex matching should be here
+    assert b'<div class="">2000 online' in res.data
+
     # Both regexs should be here
     assert b'<div class="">80 guests' in res.data
 
+    # Regex with flag handling should be here
+    assert b'<div class="">SomeCase insensitive 3456' in res.data
+
+    # Singular group from /somecase insensitive (345\d)/i
+    assert b'<div class="">3456' in res.data
+
+    # Regex with multiline flag handling should be here
+
     # Should not be here
-    assert b'Some text that did change' not in res.data
+    assert b'Some text that did change' not in res.data

changedetectionio/tests/test_filter_failure_notification.py

@@ -0,0 +1,134 @@
+import os
+import time
+import re
+from flask import url_for
+from .util import set_original_response, live_server_setup
+from changedetectionio.model import App
+
+
+def set_response_with_filter():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+     <div id="nope-doesnt-exist">Some text thats the same</div>     
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+    return None
+
+def run_filter_test(client, content_filter):
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("form_watch_add"),
+        data={"url": test_url, "tag": ''},
+        follow_redirects=True
+    )
+    assert b"Watch added" in res.data
+
+    # Give the thread time to pick up the first version
+    time.sleep(3)
+
+    # Goto the edit page, add our ignore text
+    # Add our URL to the import page
+    url = url_for('test_notification_endpoint', _external=True)
+    notification_url = url.replace('http', 'json')
+
+    print(">>>> Notification URL: " + notification_url)
+
+    # Just a regular notification setting, this will be used by the special 'filter not found' notification
+    notification_form_data = {"notification_urls": notification_url,
+                              "notification_title": "New ChangeDetection.io Notification - {watch_url}",
+                              "notification_body": "BASE URL: {base_url}\n"
+                                                   "Watch URL: {watch_url}\n"
+                                                   "Watch UUID: {watch_uuid}\n"
+                                                   "Watch title: {watch_title}\n"
+                                                   "Watch tag: {watch_tag}\n"
+                                                   "Preview: {preview_url}\n"
+                                                   "Diff URL: {diff_url}\n"
+                                                   "Snapshot: {current_snapshot}\n"
+                                                   "Diff: {diff}\n"
+                                                   "Diff Full: {diff_full}\n"
+                                                   ":-)",
+                              "notification_format": "Text"}
+
+    notification_form_data.update({
+        "url": test_url,
+        "tag": "my tag",
+        "title": "my title",
+        "headers": "",
+        "css_filter": content_filter,
+        "fetch_backend": "html_requests"})
+
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data=notification_form_data,
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    time.sleep(3)
+
+    # Now the notification should not exist, because we didnt reach the threshold
+    assert not os.path.isfile("test-datastore/notification.txt")
+
+    for i in range(0, App._FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT):
+        res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+        time.sleep(3)
+
+    # We should see something in the frontend
+    assert b'Did the page change its layout' in res.data
+
+    # Now it should exist and contain our "filter not found" alert
+    assert os.path.isfile("test-datastore/notification.txt")
+    notification = False
+    with open("test-datastore/notification.txt", 'r') as f:
+        notification = f.read()
+    assert 'CSS/xPath filter was not present in the page' in notification
+    assert content_filter.replace('"', '\\"') in notification
+
+    # Remove it and prove that it doesnt trigger when not expected
+    os.unlink("test-datastore/notification.txt")
+    set_response_with_filter()
+
+    for i in range(0, App._FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT):
+        client.get(url_for("form_watch_checknow"), follow_redirects=True)
+        time.sleep(3)
+
+    # It should have sent a notification, but..
+    assert os.path.isfile("test-datastore/notification.txt")
+    # but it should not contain the info about the failed filter
+    with open("test-datastore/notification.txt", 'r') as f:
+        notification = f.read()
+    assert not 'CSS/xPath filter was not present in the page' in notification
+
+    # cleanup for the next
+    client.get(
+        url_for("form_delete", uuid="all"),
+        follow_redirects=True
+    )
+    os.unlink("test-datastore/notification.txt")
+
+
+def test_setup(live_server):
+    live_server_setup(live_server)
+
+def test_check_css_filter_failure_notification(client, live_server):
+    set_original_response()
+    time.sleep(1)
+    run_filter_test(client, '#nope-doesnt-exist')
+
+def test_check_xpath_filter_failure_notification(client, live_server):
+    set_original_response()
+    time.sleep(1)
+    run_filter_test(client, '//*[@id="nope-doesnt-exist"]')
+

changedetectionio/tests/test_obfuscations.py

@@ -0,0 +1,43 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from .util import live_server_setup
+
+
+def set_original_ignore_response():
+    test_return_data = """<html>
+       <body>
+     <span>The price is</span><span>$<!-- -->90<!-- -->.<!-- -->74</span>
+     </body>
+     </html>
+
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def test_obfuscations(client, live_server):
+    set_original_ignore_response()
+    live_server_setup(live_server)
+    time.sleep(1)
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    # Give the thread time to pick it up
+    time.sleep(3)
+
+    # Check HTML conversion detected and workd
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert b'$90.74' in res.data

changedetectionio/update_worker.py

@@ -3,6 +3,8 @@ import queue
 import time
 
 from changedetectionio import content_fetcher
+from changedetectionio.html_tools import FilterNotFoundInResponse
+
 # A single update worker
 #
 # Requests for checking on a single site(watch) from a queue of watches
@@ -19,6 +21,32 @@ class update_worker(threading.Thread):
         self.datastore = datastore
         super().__init__(*args, **kwargs)
 
+    def send_filter_failure_notification(self, uuid):
+
+        threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts')
+        watch = self.datastore.data['watching'].get(uuid, False)
+
+        n_object = {'notification_title': 'Changedetection.io - Alert - CSS/xPath filter was not present in the page',
+                    'notification_body': "Your configured CSS/xPath filter of '{}' for {{watch_url}} did not appear on the page after {} attempts, did the page change layout?\n\nLink: {{base_url}}/edit/{{watch_uuid}}\n\nThanks - Your omniscient changedetection.io installation :)\n".format(
+                        watch['css_filter'],
+                        threshold),
+                    'notification_format': 'text'}
+
+        if len(watch['notification_urls']):
+            n_object['notification_urls'] = watch['notification_urls']
+
+        elif len(self.datastore.data['settings']['application']['notification_urls']):
+            n_object['notification_urls'] = self.datastore.data['settings']['application']['notification_urls']
+
+        # Only prepare to notify if the rules above matched
+        if 'notification_urls' in n_object:
+            n_object.update({
+                'watch_url': watch['url'],
+                'uuid': uuid
+            })
+            self.notification_q.put(n_object)
+            print("Sent filter not found notification for {}".format(uuid))
+
     def run(self):
         from changedetectionio import fetch_site_status
 
@@ -55,11 +83,23 @@ class update_worker(threading.Thread):
                     except content_fetcher.ReplyWithContentButNoText as e:
                         # Totally fine, it's by choice - just continue on, nothing more to care about
                         # Page had elements/content but no renderable text
-                        if self.datastore.data['watching'].get(uuid, False) and self.datastore.data['watching'][uuid].get('css_filter'):
-                            self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found (CSS / xPath Filter not found in page?)"})
-                        else:
-                            self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found."})
-                        pass
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found."})
+                    except FilterNotFoundInResponse as e:
+                        err_text = "Filter '{}' not found - Did the page change its layout?".format(str(e))
+                        c = 0
+                        if self.datastore.data['watching'].get(uuid, False):
+                            c = self.datastore.data['watching'][uuid].get('consecutive_filter_failures', 5)
+                        c += 1
+
+                        # Send notification if we reached the threshold?
+                        threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts', 0)
+                        print("Filter for {} not found, consecutive_filter_failures: {}".format(uuid, c))
+                        if threshold >0 and c >= threshold:
+                            self.send_filter_failure_notification(uuid)
+                            c = 0
+
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                                                                           'consecutive_filter_failures': c})
                     except content_fetcher.EmptyReply as e:
                         # Some kind of custom to-str handler in the exception handler that does this?
                         err_text = "EmptyReply - try increasing 'Wait seconds before extracting text', Status Code {}".format(e.status_code)
@@ -73,7 +113,6 @@ class update_worker(threading.Thread):
                         err_text = "Page request from server didnt respond correctly"
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
-
                     except Exception as e:
                         self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
@@ -89,6 +128,7 @@ class update_worker(threading.Thread):
                                 fname = watch.save_history_text(contents=contents, timestamp=str(round(time.time())))
 
                             # Generally update anything interesting returned
+                            update_obj['consecutive_filter_failures'] = 0
                             self.datastore.update_watch(uuid=uuid, update_obj=update_obj)
 
                             # A change was detected

docker-compose.yml

@@ -24,7 +24,7 @@ services:
   #             https://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.common.proxy
   #
   #       Alternative Playwright URL, do not use "'s or 's!
-  #      - PLAYWRIGHT_DRIVER_URL=ws://playwright-chrome:3000/
+  #      - PLAYWRIGHT_DRIVER_URL=ws://playwright-chrome:3000/?stealth=1&--disable-web-security=true
   #
   #       Playwright proxy settings playwright_proxy_server, playwright_proxy_bypass, playwright_proxy_username, playwright_proxy_password
   #
@@ -78,9 +78,6 @@ services:
 #            - SCREEN_HEIGHT=1024
 #            - SCREEN_DEPTH=16
 #            - ENABLE_DEBUGGER=false
-#            - SCREEN_WIDTH=1280
-#            - SCREEN_HEIGHT=1024
-#            - SCREEN_DEPTH=16
 #            - PREBOOT_CHROME=true
 #            - CONNECTION_TIMEOUT=300000
 #            - MAX_CONCURRENT_SESSIONS=10