Improve docker-compose browserless docker container, add env var for STEALTH and BLOCK_ADS

README.md

@@ -3,9 +3,9 @@
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
-## Web Site Change Detection, Monitoring and Notification - Self-Hosted or SaaS.
+## Self-Hosted, Open Source, Change Monitoring of Web Pages
 
-_Know when web pages change! Stay ontop of new information! get notifications when important website content changes_ 
+_Know when web pages change! Stay ontop of new information!_ 
 
 Live your data-life *pro-actively* instead of *re-actively*.
 
@@ -33,7 +33,6 @@ Free, Open-source web page monitoring, notification and change detection. Don't
 - New software releases, security advisories when you're not on their mailing list.
 - Festivals with changes
 - Realestate listing changes
-- Know when your favourite whiskey is on sale, or other special deals are announced before anyone else
 - COVID related news from government websites
 - University/organisation news from their website
 - Detect and monitor changes in JSON API responses 
@@ -119,7 +118,7 @@ See the wiki for more information https://github.com/dgtlmoon/changedetection.io
 ## Filters
 XPath, JSONPath and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools.
 
-(We support LXML `re:test`, `re:math` and `re:replace`.)
+(We support LXML re:test, re:math and re:replace.)
 
 ## Notifications
 

changedetectionio/__init__.py

@@ -44,7 +44,7 @@ from flask_wtf import CSRFProtect
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.39.16'
+__version__ = '0.39.15'
 
 datastore = None
 
@@ -298,7 +298,7 @@ def changedetection_app(config=None, datastore_o=None):
         # 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
+        # @todo needs a .itemsWithTag() or something
         for uuid, watch in datastore.data['watching'].items():
 
             if limit_tag != None:
@@ -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;charset=utf-8')
+        response.headers.set('Content-Type', 'application/rss+xml')
         return response
 
     @app.route("/", methods=['GET'])
@@ -403,6 +403,8 @@ def changedetection_app(config=None, datastore_o=None):
                 watch['uuid'] = uuid
                 sorted_watches.append(watch)
 
+        sorted_watches.sort(key=lambda x: x['last_changed'], reverse=True)
+
         existing_tags = datastore.get_all_tags()
 
         form = forms.quickWatchForm(request.form)
@@ -431,9 +433,7 @@ def changedetection_app(config=None, datastore_o=None):
     def ajax_callback_send_notification_test():
 
         import apprise
-        from .apprise_asset import asset
-        apobj = apprise.Apprise(asset=asset)
-
+        apobj = apprise.Apprise()
 
         # validate URLS
         if not len(request.form['notification_urls'].strip()):
@@ -459,38 +459,37 @@ def changedetection_app(config=None, datastore_o=None):
         return 'OK'
 
 
-    @app.route("/clear_history/<string:uuid>", methods=['GET'])
+    @app.route("/scrub/<string:uuid>", methods=['GET'])
     @login_required
-    def clear_watch_history(uuid):
+    def scrub_watch(uuid):
         try:
-            datastore.clear_watch_history(uuid)
+            datastore.scrub_watch(uuid)
         except KeyError:
             flash('Watch not found', 'error')
         else:
-            flash("Cleared snapshot history for watch {}".format(uuid))
+            flash("Scrubbed watch {}".format(uuid))
 
         return redirect(url_for('index'))
 
-    @app.route("/clear_history", methods=['GET', 'POST'])
+    @app.route("/scrub", methods=['GET', 'POST'])
     @login_required
-    def clear_all_history():
+    def scrub_page():
 
         if request.method == 'POST':
             confirmtext = request.form.get('confirmtext')
 
-            if confirmtext == 'clear':
+            if confirmtext == 'scrub':
                 changes_removed = 0
                 for uuid in datastore.data['watching'].keys():
-                    datastore.clear_watch_history(uuid)
-                    #TODO: KeyError not checked, as it is above
+                    datastore.scrub_watch(uuid)
 
-                flash("Cleared snapshot history for all watches")
+                flash("Cleared all snapshot history")
             else:
                 flash('Incorrect confirmation text.', 'error')
 
             return redirect(url_for('index'))
 
-        output = render_template("clear_all_history.html")
+        output = render_template("scrub.html")
         return output
 
 
@@ -657,8 +656,7 @@ def changedetection_app(config=None, datastore_o=None):
                                      current_base_url=datastore.data['settings']['application']['base_url'],
                                      emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
                                      visualselector_data_is_ready=visualselector_data_is_ready,
-                                     visualselector_enabled=visualselector_enabled,
-                                     playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False)
+                                     visualselector_enabled=visualselector_enabled
                                      )
 
         return output
@@ -834,7 +832,7 @@ def changedetection_app(config=None, datastore_o=None):
                                  newest=newest_version_file_contents,
                                  previous=previous_version_file_contents,
                                  extra_stylesheets=extra_stylesheets,
-                                 versions=dates[:-1], # All except current/last
+                                 versions=dates[1:],
                                  uuid=uuid,
                                  newest_version_timestamp=dates[-1],
                                  current_previous_version=str(previous_version),
@@ -858,7 +856,7 @@ def changedetection_app(config=None, datastore_o=None):
             uuid = list(datastore.data['watching'].keys()).pop()
 
         # Normally you would never reach this, because the 'preview' button is not available when there's no history
-        # However they may try to clear snapshots and reload the page
+        # However they may try to scrub and reload the page
         if datastore.data['watching'][uuid].history_n == 0:
             flash("Preview unavailable - No fetch/check completed or triggers not reached", "error")
             return redirect(url_for('index'))
@@ -1372,4 +1370,4 @@ def ticker_thread_check_time_launch_checks():
         time.sleep(1)
 
         # Should be low so we can break this out in testing
-        app.config.exit.wait(1)
+        app.config.exit.wait(1)

changedetectionio/apprise_asset.py

@@ -1,11 +0,0 @@
-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/changedetection.py

@@ -35,7 +35,7 @@ def main():
     create_datastore_dir = False
 
     for opt, arg in opts:
-        #        if opt == '--clear-all-history':
+        #        if opt == '--purge':
         # Remove history, the actual files you need to delete manually.
         #            for uuid, watch in datastore.data['watching'].items():
         #                watch.update({'history': {}, 'last_checked': 0, 'last_changed': 0, 'previous_md5': None})

changedetectionio/content_fetcher.py

@@ -46,7 +46,6 @@ 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("/"):""}});
@@ -176,6 +175,7 @@ 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')
 
@@ -301,27 +301,18 @@ class base_html_playwright(Fetcher):
                 accept_downloads=False
             )
 
-            if len(request_headers):
-                context.set_extra_http_headers(request_headers)
-
             page = context.new_page()
             try:
                 page.set_default_navigation_timeout(90000)
                 page.set_default_timeout(90000)
 
-                # 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
+               # 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()
@@ -453,12 +444,6 @@ 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

@@ -1,5 +1,4 @@
 import hashlib
-import logging
 import os
 import re
 import time
@@ -106,9 +105,6 @@ 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()
 
@@ -150,9 +146,7 @@ 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..
@@ -218,7 +212,7 @@ class perform_site_check():
                 result = re.findall(s_re.encode('utf8'), stripped_text_from_html,
                                     flags=re.MULTILINE | re.DOTALL | re.LOCALE)
                 if result:
-                    regex_matched_output = regex_matched_output + result
+                    regex_matched_output.append(result[0])
 
             if regex_matched_output:
                 stripped_text_from_html = b'\n'.join(regex_matched_output)
@@ -261,6 +255,9 @@ class perform_site_check():
         # Looks like something changed, but did it match all the rules?
         if blocked:
             changed_detected = False
+        else:
+            update_obj["last_changed"] = timestamp
+
 
         # Extract title as title
         if is_html:
@@ -268,16 +265,6 @@ class perform_site_check():
                 if not watch['title'] or not len(watch['title']):
                     update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
 
-        if changed_detected:
-            if watch.get('check_unique_lines', False):
-                has_unique_lines = watch.lines_contain_something_unique_compared_to_history(lines=stripped_text_from_html.splitlines())
-                # One or more lines? unsure?
-                if not has_unique_lines:
-                    logging.debug("check_unique_lines: UUID {} didnt have anything new setting change_detected=False".format(uuid))
-                    changed_detected = False
-                else:
-                    logging.debug("check_unique_lines: UUID {} had unique content".format(uuid))
-
         # Always record the new checksum
         update_obj["previous_md5"] = fetched_md5
 

changedetectionio/forms.py

@@ -340,12 +340,9 @@ class watchForm(commonSettingsForm):
     body = TextAreaField('Request body', [validators.Optional()])
     method = SelectField('Request method', choices=valid_method, default=default_method)
     ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
-    check_unique_lines = BooleanField('Only trigger when new lines appear', default=False)
     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')

changedetectionio/html_tools.py

@@ -202,17 +202,3 @@ 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

@@ -1,4 +1,8 @@
-from os import getenv
+import collections
+import os
+
+import uuid as uuid_builder
+
 from changedetectionio.notification import (
     default_notification_body,
     default_notification_format,
@@ -11,16 +15,16 @@ class model(dict):
             'watching': {},
             'settings': {
                 'headers': {
-                    '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'),
+                    'User-Agent': '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': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
+                    'timeout': 15,  # Default 15 seconds
                     'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
                     'jitter_seconds': 0,
-                    'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "10")),  # Number of threads, lower is better for slow connections
+                    'workers': 10,  # Number of threads, lower is better for slow connections
                     'proxy': None # Preferred proxy connection
                 },
                 'application': {
@@ -29,7 +33,7 @@ class model(dict):
                     'base_url' : None,
                     'extract_title_as_title': False,
                     'empty_pages_are_a_change': False,
-                    'fetch_backend': getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
+                    'fetch_backend': os.getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
                     'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
                     'global_subtractive_selectors': [],
                     'ignore_whitespace': True,

changedetectionio/model/Watch.py

@@ -2,7 +2,6 @@ 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,
@@ -42,17 +41,15 @@ class model(dict):
             'text_should_not_be_present': [], # Text that should not present
             'fetch_backend': None,
             '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
             # Re #110, so then if this is set to None, we know to use the default value instead
             # 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_js_execute_code': None, # Run before change-detection
+            'webdriver_delay': None
         }
     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)
@@ -161,21 +158,8 @@ class model(dict):
 
     def threshold_seconds(self):
         seconds = 0
-        for m, n in mtable.items():
+        for m, n in self.mtable.items():
             x = self.get('time_between_check', {}).get(m, None)
             if x:
                 seconds += x * n
         return seconds
-
-    # Iterate over all history texts and see if something new exists
-    def lines_contain_something_unique_compared_to_history(self, lines=[]):
-        local_lines = [l.decode('utf-8').strip().lower() for l in lines]
-
-        # Compare each lines (set) against each history text file (set) looking for something new..
-        for k, v in self.history.items():
-            alist = [line.decode('utf-8').strip().lower() for line in open(v, 'rb')]
-            res = set(alist) != set(local_lines)
-            if res:
-                return True
-
-        return False

changedetectionio/notification.py

@@ -49,9 +49,9 @@ def process_notification(n_object, datastore):
     # raise it as an exception
     apobjs=[]
     sent_objs=[]
-    from .apprise_asset import asset
     for url in n_object['notification_urls']:
-        apobj = apprise.Apprise(debug=True, asset=asset)
+
+        apobj = apprise.Apprise(debug=True)
         url = url.strip()
         if len(url):
             print(">> Process Notification: AppRise notifying {}".format(url))
@@ -64,7 +64,7 @@ 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 and not url.startswith('mail'):
+                if not 'avatar_url' in url:
                     url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
 
                 if url.startswith('tgram://'):
@@ -79,20 +79,13 @@ 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://') or url.startswith('https://discordapp.com/api/webhooks'):
+                elif url.startswith('discord://'):
                     # 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'):
-                        url = "{}?format={}".format(url, n_format)
-
                 apobj.add(url)
 
                 apobj.notify(

changedetectionio/static/images/spread-white.svg

@@ -1,20 +0,0 @@
-<?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/js/watch-settings.js

@@ -1,30 +1,13 @@
 $(document).ready(function() {
     function toggle() {
-        if ($('input[name="fetch_backend"]:checked').val() == 'html_webdriver') {
-            if(playwright_enabled) {
-                // playwright supports headers, so hide everything else
-                // See #664
-                $('#requests-override-options #request-method').hide();
-                $('#requests-override-options #request-body').hide();
-
-                // @todo connect this one up
-                $('#ignore-status-codes-option').hide();
-            } else {
-                // selenium/webdriver doesnt support anything afaik, hide it all
-                $('#requests-override-options').hide();
-            }
-
-
+        if ($('input[name="fetch_backend"]:checked').val() != 'html_requests') {
+            $('#requests-override-options').hide();
             $('#webdriver-override-options').show();
-
         } else {
-
             $('#requests-override-options').show();
-            $('#requests-override-options *:hidden').show();
             $('#webdriver-override-options').hide();
         }
     }
-
     $('input[name="fetch_backend"]').click(function (e) {
         toggle();
     });

changedetectionio/static/styles/.gitignore

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

changedetectionio/store.py

@@ -158,7 +158,8 @@ class ChangeDetectionStore:
     @property
     def threshold_seconds(self):
         seconds = 0
-        for m, n in Watch.mtable.items():
+        mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
+        for m, n in mtable.items():
             x = self.__data['settings']['requests']['time_between_check'].get(m)
             if x:
                 seconds += x * n
@@ -249,7 +250,7 @@ class ChangeDetectionStore:
         return self.data['watching'][uuid].get(val)
 
     # Remove a watchs data but keep the entry (URL etc)
-    def clear_watch_history(self, uuid):
+    def scrub_watch(self, uuid):
         import pathlib
 
         self.__data['watching'][uuid].update(
@@ -297,8 +298,7 @@ class ChangeDetectionStore:
                           'ignore_text', 'css_filter',
                           'subtractive_selectors', 'trigger_text',
                           'extract_title_as_title', 'extract_text',
-                          'text_should_not_be_present',
-                          'webdriver_js_execute_code']:
+                          'text_should_not_be_present']:
                     if res.get(k):
                         apply_extras[k] = res[k]
 
@@ -518,11 +518,3 @@ class ChangeDetectionStore:
                 # But we should set it back to a empty dict so we don't break if this schema runs on an earlier version.
                 # In the distant future we can remove this entirely
                 self.data['watching'][uuid]['history'] = {}
-
-    # We incorrectly stored last_changed when there was not a change, and then confused the output list table
-    def update_3(self):
-        for uuid, watch in self.data['watching'].items():
-            # Be sure it's recalculated
-            p = watch.history
-            if watch.history_n < 2:
-                watch['last_changed'] = 0

changedetectionio/templates/diff.html

@@ -22,7 +22,7 @@
             {% if versions|length >= 1 %}
             <label for="diff-version">Compare newest (<span id="current-v-date"></span>) with</label>
             <select id="diff-version" name="previous_version">
-                {% for version in versions|reverse %}
+                {% for version in versions %}
                 <option value="{{version}}" {% if version== current_previous_version %} selected="" {% endif %}>
                     {{version}}
                 </option>

changedetectionio/templates/edit.html

@@ -7,7 +7,6 @@
     const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
     const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
     const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
-    const playwright_enabled={% if playwright_enabled %} true {% else %} false {% endif %};
 
 {% if emailprefix %}
     const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');
@@ -25,7 +24,7 @@
         <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 Filter Selector</a></li>
+            <li class="tab"><a id="visualselector-tab" href="#visualselector">Visual 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>
@@ -82,39 +81,33 @@
                     </div>
                 {% endif %}
                 <fieldset id="webdriver-override-options">
+                    <div class="pure-form-message-inline">
+                        <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.
+                    </div>
                     <div class="pure-control-group">
                         {{ render_field(form.webdriver_delay) }}
-                        <div class="pure-form-message-inline">
-                            <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>
-                    <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>
+                    {% if using_global_webdriver_wait %}
+                    <div class="pure-form-message-inline">
+                        <strong>Using the current global default settings</strong>
                     </div>
+                    {% endif %}
                 </fieldset>
                 <fieldset class="pure-group" id="requests-override-options">
-                    {% if not playwright_enabled %}
-                        <div class="pure-form-message-inline">
-                            <strong>Request override is currently only used by the <i>Basic fast Plaintext/HTTP Client</i> method.</strong>
-                        </div>
-                    {% endif %}
-                    <div class="pure-control-group" id="request-method">
+                    <div class="pure-form-message-inline">
+                        <strong>Request override is currently only used by the <i>Basic fast Plaintext/HTTP Client</i> method.</strong>
+                    </div>
+                    <div class="pure-control-group">
                         {{ render_field(form.method) }}
                     </div>
-                    <div class="pure-control-group" id="request-headers">
+                    <div class="pure-control-group">
 {{ render_field(form.headers, rows=5, placeholder="Example
 Cookie: foobar
 User-Agent: wonderbra 1.0") }}
                     </div>
-                    <div class="pure-control-group" id="request-body">
+                    <div class="pure-control-group">
                                         {{ render_field(form.body, rows=5, placeholder="Example
 {
    \"name\":\"John\",
@@ -122,7 +115,7 @@ User-Agent: wonderbra 1.0") }}
    \"car\":null
 }") }}
                     </div>
-                    <div id="ignore-status-codes-option">
+                    <div>
                         {{ render_checkbox_field(form.ignore_status_codes) }}
                     </div>
                 </fieldset>
@@ -150,12 +143,6 @@ User-Agent: wonderbra 1.0") }}
                                 </li>
                             </ul>
                     </div>
-                    <fieldset>
-                        <div class="pure-control-group">
-                            {{ render_checkbox_field(form.check_unique_lines) }}
-                            <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
-                        </div>
-                    </fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.css_filter, placeholder=".class-name or #some-id, or other CSS selector rule.",
                         class="m-d") }}
@@ -190,7 +177,7 @@ 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 entire line in forward slash <code>/regex/</code></li>
+                            <li>Regular Expression support, wrap the 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>
@@ -243,7 +230,7 @@ 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 %}
@@ -288,8 +275,8 @@ Unavailable") }}
 
                     <a href="{{url_for('form_delete', uuid=uuid)}}"
                        class="pure-button button-small button-error ">Delete</a>
-                    <a href="{{url_for('clear_watch_history', uuid=uuid)}}"
-                       class="pure-button button-small button-error ">Clear History</a>
+                    <a href="{{url_for('scrub_watch', uuid=uuid)}}"
+                       class="pure-button button-small button-error ">Scrub</a>
                     <a href="{{url_for('form_clone', uuid=uuid)}}"
                        class="pure-button button-small ">Create Copy</a>
                 </div>

changedetectionio/templates/scrub.html

@@ -3,22 +3,22 @@
 {% block content %}
 <div class="edit-form">
     <div class="box-wrap inner">
-    <form class="pure-form pure-form-stacked" action="{{url_for('clear_all_history')}}" method="POST">
+    <form class="pure-form pure-form-stacked" action="{{url_for('scrub_page')}}" method="POST">
         <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
         <fieldset>
             <div class="pure-control-group">
-                This will remove version history (snapshots) for ALL watches, but keep your list of URLs! <br/>
+                This will remove ALL version snapshots/data, but keep your list of URLs. <br/>
                 You may like to use the <strong>BACKUP</strong> link first.<br/>
             </div>
             <br/>
             <div class="pure-control-group">
                 <label for="confirmtext">Confirmation text</label>
                 <input type="text" id="confirmtext" required="" name="confirmtext" value="" size="10"/>
-                <span class="pure-form-message-inline">Type in the word <strong>clear</strong> to confirm that you understand.</span>
+                <span class="pure-form-message-inline">Type in the word <strong>scrub</strong> to confirm that you understand!</span>
             </div>
             <br/>
             <div class="pure-control-group">
-                <button type="submit" class="pure-button pure-button-primary">Clear History!</button>
+                <button type="submit" class="pure-button pure-button-primary">Scrub!</button>
             </div>
             <br/>
             <div class="pure-control-group">

changedetectionio/templates/settings.html

@@ -148,7 +148,7 @@ 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 entire line in forward slash <code>/regex/</code></li>
+                            <li>Regular Expression support, wrap the 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>
@@ -173,7 +173,7 @@ nav
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}
                     <a href="{{url_for('index')}}" class="pure-button button-small button-cancel">Back</a>
-                    <a href="{{url_for('clear_all_history')}}" class="pure-button button-small button-cancel">Clear Snapshot History</a>
+                    <a href="{{url_for('scrub_page')}}" class="pure-button button-small button-cancel">Delete History Snapshot Data</a>
                 </div>
 
             </div>

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-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>
+        <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>
     </form>
     <div>
         <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag }}">All</a>
@@ -40,7 +40,7 @@
             <tbody>
 
 
-            {% for watch in watches|sort(attribute='last_changed', reverse=True) %}
+            {% for watch in watches %}
             <tr id="{{ watch.uuid }}"
                 class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }}
                 {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
@@ -68,7 +68,7 @@
                     {% endif %}
                 </td>
                 <td class="last-checked">{{watch|format_last_checked_time|safe}}</td>
-                <td class="last-changed">{% if watch.history_n >=2 and watch.last_changed >0 %}
+                <td class="last-changed">{% if watch.history_n >=2 and watch.last_changed %}
                     {{watch.last_changed|format_timestamp_timeago}}
                     {% else %}
                     Not yet

changedetectionio/tests/test_api.py

@@ -95,8 +95,6 @@ def test_api_simple(client, live_server):
     assert watch_uuid in json.loads(res.data).keys()
     before_recheck_info = json.loads(res.data)[watch_uuid]
     assert before_recheck_info['last_checked'] != 0
-    #705 `last_changed` should be zero on the first check
-    assert before_recheck_info['last_changed'] == 0
     assert before_recheck_info['title'] == 'My test URL'
 
     set_modified_response()

changedetectionio/tests/test_extract_regex.py

@@ -33,7 +33,7 @@ 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<br/>  2000 online )</div>
+     <div id="changetext">Some text that did change ( 1000 online <br/> 80 guests)</div>
      </body>
      </html>
     """
@@ -119,12 +119,9 @@ 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
 
     # 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_obfuscations.py

@@ -1,43 +0,0 @@
-#!/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/tests/test_unique_lines.py

@@ -1,104 +0,0 @@
-#!/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>
-     <p>Some initial text</p>
-     <p>Which is across multiple lines</p>
-     <p>So let's see what happens.</p>
-     </body>
-     </html>
-    """
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-
-
-# The same but just re-ordered the text
-def set_modified_swapped_lines():
-    # Re-ordered and with some whitespacing, should get stripped() too.
-    test_return_data = """<html>
-     <body>
-     <p>Some initial text</p>
-     <p>   So let's see what happens.</p>
-     <p>&nbsp;Which is across multiple lines</p>     
-     </body>
-     </html>
-    """
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-
-
-def set_modified_with_trigger_text_response():
-    test_return_data = """<html>
-     <body>
-     <p>Some initial text</p>
-     <p>So let's see what happens.</p>
-     <p>and a new line!</p>
-     <p>Which is across multiple lines</p>     
-     </body>
-     </html>
-    """
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-
-
-def test_unique_lines_functionality(client, live_server):
-    live_server_setup(live_server)
-
-    sleep_time_for_fetch_thread = 3
-
-    set_original_ignore_response()
-    # 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("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-    time.sleep(sleep_time_for_fetch_thread)
-
-    # Add our URL to the import page
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={"check_unique_lines": "y",
-              "url": test_url,
-              "fetch_backend": "html_requests"},
-        follow_redirects=True
-    )
-    assert b"Updated watch." in res.data
-    assert b'unviewed' not in res.data
-
-    #  Make a change
-    set_modified_swapped_lines()
-
-    time.sleep(sleep_time_for_fetch_thread)
-    # 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)
-
-    # It should report nothing found (no new 'unviewed' class)
-    res = client.get(url_for("index"))
-    assert b'unviewed' not in res.data
-
-
-    # Now set the content which contains the new text and re-ordered existing text
-    set_modified_with_trigger_text_response()
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
-    res = client.get(url_for("index"))
-    assert b'unviewed' in res.data
-

changedetectionio/update_worker.py

@@ -98,9 +98,7 @@ class update_worker(threading.Thread):
 
                                 # Notifications should only trigger on the second time (first time, we gather the initial snapshot)
                                 if watch.history_n >= 2:
-                                    # Atleast 2, means there really was a change
-                                    self.datastore.update_watch(uuid=uuid, update_obj={'last_changed': round(now)})
-
+                                    print(">> Change detected in UUID {} - {}".format(uuid, watch['url']))
                                     watch_history = watch.history
                                     dates = list(watch_history.keys())
                                     # Theoretically it's possible that this could be just 1 long,
@@ -111,6 +109,7 @@ class update_worker(threading.Thread):
                                         )
                                     prev_fname = watch_history[dates[-2]]
 
+
                                     # Did it have any notification alerts to hit?
                                     if len(watch['notification_urls']):
                                         print(">>> Notifications queued for UUID from watch {}".format(uuid))
@@ -158,7 +157,6 @@ class update_worker(threading.Thread):
                         # Always record that we atleast tried
                         self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
                                                                            'last_checked': round(time.time())})
-
                         # Always save the screenshot if it's available
                         if screenshot:
                             self.datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)

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/?stealth=1&--disable-web-security=true
+  #      - PLAYWRIGHT_DRIVER_URL=ws://playwright-chrome:3000/
   #
   #       Playwright proxy settings playwright_proxy_server, playwright_proxy_bypass, playwright_proxy_username, playwright_proxy_password
   #
@@ -78,6 +78,9 @@ 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