UI - Improve error handling when a module is missing when editing a URL/link

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -25,6 +25,7 @@ browser_step_ui_config = {'Choose one': '0 0',
                           'Click element if exists': '1 0',
                           'Click element': '1 0',
                           'Click element containing text': '0 1',
+                          'Click element containing text if exists': '0 1',
                           'Enter text in field': '1 1',
                           'Execute JS': '0 1',
 #                          'Extract text and use as filter': '1 0',
@@ -96,12 +97,24 @@ class steppable_browser_interface():
         return self.action_goto_url(value=self.start_url)
 
     def action_click_element_containing_text(self, selector=None, value=''):
+        logger.debug("Clicking element containing text")
         if not len(value.strip()):
             return
         elem = self.page.get_by_text(value)
         if elem.count():
             elem.first.click(delay=randint(200, 500), timeout=3000)
 
+    def action_click_element_containing_text_if_exists(self, selector=None, value=''):
+        logger.debug("Clicking element containing text if exists")
+        if not len(value.strip()):
+            return
+        elem = self.page.get_by_text(value)
+        logger.debug(f"Clicking element containing text - {elem.count()} elements found")
+        if elem.count():
+            elem.first.click(delay=randint(200, 500), timeout=3000)
+        else:
+            return
+
     def action_enter_text_in_field(self, selector, value):
         if not len(selector.strip()):
             return

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

@@ -89,11 +89,13 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                     {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
 footer
 nav
-.stockticker") }}
+.stockticker
+//*[contains(text(), 'Advertisement')]") }}
                     <span class="pure-form-message-inline">
                         <ul>
-                          <li> Remove HTML element(s) by CSS selector before text conversion. </li>
-                          <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
+                          <li> Remove HTML element(s) by CSS and XPath selectors before text conversion. </li>
+                          <li> Don't paste HTML here, use only CSS and XPath selectors </li>
+                          <li> Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
                 </fieldset>

changedetectionio/flask_app.py

@@ -1,6 +1,8 @@
 #!/usr/bin/env python3
 
 import datetime
+import importlib
+
 import flask_login
 import locale
 import os
@@ -10,7 +12,9 @@ import threading
 import time
 import timeago
 
+from .content_fetchers.exceptions import ReplyWithContentButNoText
 from .processors import find_processors, get_parent_module, get_custom_watch_obj_for_processor
+from .processors.text_json_diff.processor import FilterNotFoundInResponse
 from .safe_jinja import render as jinja_render
 from changedetectionio.strtobool import strtobool
 from copy import deepcopy
@@ -1396,6 +1400,58 @@ def changedetection_app(config=None, datastore_o=None):
         # Return a 500 error
         abort(500)
 
+    @app.route("/edit/<string:uuid>/preview-rendered", methods=['POST'])
+    @login_optionally_required
+    def watch_get_preview_rendered(uuid):
+        '''For when viewing the "preview" of the rendered text from inside of Edit'''
+        now = time.time()
+        import brotli
+        from . import forms
+
+        text_after_filter = ''
+        tmp_watch = deepcopy(datastore.data['watching'].get(uuid))
+
+        if tmp_watch and tmp_watch.history and os.path.isdir(tmp_watch.watch_data_dir):
+            # Splice in the temporary stuff from the form
+            form = forms.processor_text_json_diff_form(formdata=request.form if request.method == 'POST' else None,
+                                                       data=request.form
+                                                       )
+            # Only update vars that came in via the AJAX post
+            p = {k: v for k, v in form.data.items() if k in request.form.keys()}
+            tmp_watch.update(p)
+
+            latest_filename = next(reversed(tmp_watch.history))
+            html_fname = os.path.join(tmp_watch.watch_data_dir, f"{latest_filename}.html.br")
+            with open(html_fname, 'rb') as f:
+                decompressed_data = brotli.decompress(f.read()).decode('utf-8') if html_fname.endswith('.br') else f.read().decode('utf-8')
+
+                # Just like a normal change detection except provide a fake "watch" object and dont call .call_browser()
+                processor_module = importlib.import_module("changedetectionio.processors.text_json_diff.processor")
+                update_handler = processor_module.perform_site_check(datastore=datastore,
+                                                                     watch_uuid=uuid # probably not needed anymore anyway?
+                                                                     )
+                # Use the last loaded HTML as the input
+                update_handler.fetcher.content = decompressed_data
+                update_handler.fetcher.headers['content-type'] = tmp_watch.get('content-type')
+                try:
+                    changed_detected, update_obj, contents, text_after_filter = update_handler.run_changedetection(
+                        watch=tmp_watch,
+                        skip_when_checksum_same=False,
+                    )
+                except FilterNotFoundInResponse as e:
+                    text_after_filter = f"Filter not found in HTML: {str(e)}"
+                except ReplyWithContentButNoText as e:
+                    text_after_filter = f"Filter found but no text (empty result)"
+                except Exception as e:
+                    text_after_filter = f"Error: {str(e)}"
+
+            if not text_after_filter.strip():
+                text_after_filter = 'Empty content'
+
+        logger.trace(f"Parsed in {time.time()-now:.3f}s")
+        return text_after_filter.strip()
+
+
     @app.route("/form/add/quickwatch", methods=['POST'])
     @login_optionally_required
     def form_quick_watch_add():

changedetectionio/forms.py

@@ -1,5 +1,6 @@
 import os
 import re
+from loguru import logger
 
 from changedetectionio.strtobool import strtobool
 
@@ -469,7 +470,7 @@ class processor_text_json_diff_form(commonSettingsForm):
 
     include_filters = StringListField('CSS/JSONPath/JQ/XPath Filters', [ValidateCSSJSONXPATHInput()], default='')
 
-    subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
+    subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_json=False)])
 
     extract_text = StringListField('Extract text', [ValidateListRegex()])
 
@@ -480,8 +481,10 @@ class processor_text_json_diff_form(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 unique lines appear', default=False)
+    check_unique_lines = BooleanField('Only trigger when unique lines appear in all history', default=False)
+    remove_duplicate_lines = BooleanField('Remove duplicate lines of text', default=False)
     sort_text_alphabetically =  BooleanField('Sort text alphabetically', default=False)
+    trim_text_whitespace = BooleanField('Trim whitespace before and after text', default=False)
 
     filter_text_added = BooleanField('Added lines', default=True)
     filter_text_replaced = BooleanField('Replaced/changed lines', default=True)
@@ -523,9 +526,16 @@ class processor_text_json_diff_form(commonSettingsForm):
         try:
             from changedetectionio.safe_jinja import render as jinja_render
             jinja_render(template_str=self.url.data)
+        except ModuleNotFoundError as e:
+            # incase jinja2_time or others is missing
+            logger.error(e)
+            self.url.errors.append(e)
+            result = False
         except Exception as e:
+            logger.error(e)
             self.url.errors.append('Invalid template syntax')
             result = False
+
         return result
 
 class SingleExtraProxy(Form):
@@ -576,7 +586,7 @@ class globalSettingsApplicationForm(commonSettingsForm):
     empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
     fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetchers.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
-    global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
+    global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_json=False)])
     ignore_whitespace = BooleanField('Ignore whitespace')
     password = SaltyPasswordField()
     pager_size = IntegerField('Pager size',

changedetectionio/html_tools.py

@@ -1,4 +1,5 @@
 from typing import List
+from lxml import etree
 import json
 import re
 
@@ -57,11 +58,26 @@ def subtractive_css_selector(css_selector, html_content):
         item.decompose()
     return str(soup)
 
+def subtractive_xpath_selector(xpath_selector, html_content): 
+    html_tree = etree.HTML(html_content)
+    elements_to_remove = html_tree.xpath(xpath_selector)
+
+    for element in elements_to_remove:
+        element.getparent().remove(element)
+
+    modified_html = etree.tostring(html_tree, method="html").decode("utf-8")
+    return modified_html
 
 def element_removal(selectors: List[str], html_content):
-    """Joins individual filters into one css filter."""
-    selector = ",".join(selectors)
-    return subtractive_css_selector(selector, html_content)
+    """Removes elements that match a list of CSS or xPath selectors."""
+    modified_html = html_content
+    for selector in selectors:
+        if selector.startswith(('xpath:', 'xpath1:', '//')):
+            xpath_selector = selector.removeprefix('xpath:').removeprefix('xpath1:')
+            modified_html = subtractive_xpath_selector(xpath_selector, modified_html)
+        else:
+            modified_html = subtractive_css_selector(selector, modified_html)
+    return modified_html
 
 def elementpath_tostring(obj):
     """

changedetectionio/model/__init__.py

@@ -18,6 +18,7 @@ class watch_base(dict):
             'check_count': 0,
             'check_unique_lines': False,  # On change-detected, compare against all history if its something new
             'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
+            'content-type': None,
             'date_created': None,
             'extract_text': [],  # Extract text by regex after filters
             'extract_title_as_title': False,
@@ -60,6 +61,8 @@ class watch_base(dict):
             'time_between_check_use_default': True,
             'title': None,
             'track_ldjson_price_data': None,
+            'trim_text_whitespace': False,
+            'remove_duplicate_lines': False,
             'trigger_text': [],  # List of text or regex to wait for until a change is detected
             'url': '',
             'uuid': str(uuid.uuid4()),

changedetectionio/processors/__init__.py

@@ -1,4 +1,6 @@
 from abc import abstractmethod
+
+from changedetectionio.content_fetchers.base import Fetcher
 from changedetectionio.strtobool import strtobool
 
 from copy import deepcopy
@@ -23,10 +25,11 @@ class difference_detection_processor():
         super().__init__(*args, **kwargs)
         self.datastore = datastore
         self.watch = deepcopy(self.datastore.data['watching'].get(watch_uuid))
+        # Generic fetcher that should be extended (requests, playwright etc)
+        self.fetcher = Fetcher()
 
     def call_browser(self):
         from requests.structures import CaseInsensitiveDict
-        from changedetectionio.content_fetchers.exceptions import EmptyReply
 
         # Protect against file:// access
         if re.search(r'^file://', self.watch.get('url', '').strip(), re.IGNORECASE):
@@ -159,7 +162,7 @@ class difference_detection_processor():
         some_data = 'xxxxx'
         update_obj["previous_md5"] = hashlib.md5(some_data.encode('utf-8')).hexdigest()
         changed_detected = False
-        return changed_detected, update_obj, ''.encode('utf-8')
+        return changed_detected, update_obj, ''.encode('utf-8'), b''
 
 
 def find_sub_packages(package_name):

changedetectionio/processors/restock_diff/processor.py

@@ -143,8 +143,6 @@ class perform_site_check(difference_detection_processor):
     def run_changedetection(self, watch, skip_when_checksum_same=True):
         import hashlib
 
-        from concurrent.futures import ProcessPoolExecutor
-        from functools import partial
         if not watch:
             raise Exception("Watch no longer exists.")
 
@@ -158,6 +156,20 @@ class perform_site_check(difference_detection_processor):
         update_obj['content_type'] = self.fetcher.headers.get('Content-Type', '')
         update_obj["last_check_status"] = self.fetcher.get_last_status_code()
 
+        # Only try to process restock information (like scraping for keywords) if the page was actually rendered correctly.
+        # Otherwise it will assume "in stock" because nothing suggesting the opposite was found
+        from ...html_tools import html_to_text
+        text = html_to_text(self.fetcher.content)
+        logger.debug(f"Length of text after conversion: {len(text)}")
+        if not len(text):
+            from ...content_fetchers.exceptions import ReplyWithContentButNoText
+            raise ReplyWithContentButNoText(url=watch.link,
+                                            status_code=self.fetcher.get_last_status_code(),
+                                            screenshot=self.fetcher.screenshot,
+                                            html_content=self.fetcher.content,
+                                            xpath_data=self.fetcher.xpath_data
+                                            )
+
         # Which restock settings to compare against?
         restock_settings = watch.get('restock_settings', {})
 
@@ -172,11 +184,7 @@ class perform_site_check(difference_detection_processor):
 
         itemprop_availability = {}
         try:
-            with ProcessPoolExecutor() as executor:
-                # Use functools.partial to create a callable with arguments
-                # anything using bs4/lxml etc is quite "leaky"
-                future = executor.submit(partial(get_itemprop_availability, self.fetcher.content))
-                itemprop_availability = future.result()
+            itemprop_availability = get_itemprop_availability(self.fetcher.content)
         except MoreThanOnePriceFound as e:
             # Add the real data
             raise ProcessorException(message="Cannot run, more than one price detected, this plugin is only for product pages with ONE product, try the content-change detection mode.",
@@ -290,4 +298,4 @@ class perform_site_check(difference_detection_processor):
         # Always record the new checksum
         update_obj["previous_md5"] = fetched_md5
 
-        return changed_detected, update_obj, snapshot_content.encode('utf-8').strip()
+        return changed_detected, update_obj, snapshot_content.encode('utf-8').strip(), b''

changedetectionio/processors/text_json_diff/processor.py

@@ -36,8 +36,6 @@ class PDFToHTMLToolNotFound(ValueError):
 class perform_site_check(difference_detection_processor):
 
     def run_changedetection(self, watch, skip_when_checksum_same=True):
-        from concurrent.futures import ProcessPoolExecutor
-        from functools import partial
 
         changed_detected = False
         html_content = ""
@@ -174,30 +172,20 @@ class perform_site_check(difference_detection_processor):
                     for filter_rule in include_filters_rule:
                         # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
                         if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
-                            with ProcessPoolExecutor() as executor:
-                                # Use functools.partial to create a callable with arguments - anything using bs4/lxml etc is quite "leaky"
-                                future = executor.submit(partial(html_tools.xpath_filter, xpath_filter=filter_rule.replace('xpath:', ''),
+                            html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
                                                                     html_content=self.fetcher.content,
                                                                     append_pretty_line_formatting=not watch.is_source_type_url,
-                                                                    is_rss=is_rss))
-                                html_content += future.result()
+                                                                    is_rss=is_rss)
 
                         elif filter_rule.startswith('xpath1:'):
-                            with ProcessPoolExecutor() as executor:
-                                # Use functools.partial to create a callable with arguments - anything using bs4/lxml etc is quite "leaky"
-                                future = executor.submit(partial(html_tools.xpath1_filter, xpath_filter=filter_rule.replace('xpath1:', ''),
-                                                                    html_content=self.fetcher.content,
-                                                                    append_pretty_line_formatting=not watch.is_source_type_url,
-                                                                    is_rss=is_rss))
-                                html_content += future.result()
+                            html_content += html_tools.xpath1_filter(xpath_filter=filter_rule.replace('xpath1:', ''),
+                                                                     html_content=self.fetcher.content,
+                                                                     append_pretty_line_formatting=not watch.is_source_type_url,
+                                                                     is_rss=is_rss)
                         else:
-                            with ProcessPoolExecutor() as executor:
-                                # Use functools.partial to create a callable with arguments - anything using bs4/lxml etc is quite "leaky"
-                                # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-                                future = executor.submit(partial(html_tools.include_filters, include_filters=filter_rule,
+                            html_content += html_tools.include_filters(include_filters=filter_rule,
                                                                        html_content=self.fetcher.content,
-                                                                       append_pretty_line_formatting=not watch.is_source_type_url))
-                                html_content += future.result()
+                                                                       append_pretty_line_formatting=not watch.is_source_type_url)
 
                     if not html_content.strip():
                         raise FilterNotFoundInResponse(msg=include_filters_rule, screenshot=self.fetcher.screenshot, xpath_data=self.fetcher.xpath_data)
@@ -210,19 +198,23 @@ class perform_site_check(difference_detection_processor):
                 else:
                     # extract text
                     do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
-                    with ProcessPoolExecutor() as executor:
-                        # Use functools.partial to create a callable with arguments - anything using bs4/lxml etc is quite "leaky"
-                        # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-                        future = executor.submit(partial(html_tools.html_to_text, html_content=html_content,
-                            render_anchor_tag_content=do_anchor,
-                            is_rss=is_rss)) #1874 activate the <title workaround hack
-                        stripped_text_from_html = future.result()
+                    stripped_text_from_html = html_tools.html_to_text(html_content=html_content,
+                                                                      render_anchor_tag_content=do_anchor,
+                                                                      is_rss=is_rss)  # 1874 activate the <title workaround hack
 
-        if watch.get('sort_text_alphabetically') and stripped_text_from_html:
+
+        if watch.get('trim_text_whitespace'):
+            stripped_text_from_html = '\n'.join(line.strip() for line in stripped_text_from_html.replace("\n\n", "\n").splitlines())
+
+        if watch.get('remove_duplicate_lines'):
+            stripped_text_from_html = '\n'.join(dict.fromkeys(line for line in stripped_text_from_html.replace("\n\n", "\n").splitlines()))
+
+        if watch.get('sort_text_alphabetically'):
             # Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap
             # we end up with 'Some text\n\n', sorting will add all those extra \n at the start, so we remove them here.
-            stripped_text_from_html = stripped_text_from_html.replace('\n\n', '\n')
-            stripped_text_from_html = '\n'.join( sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower() ))
+            stripped_text_from_html = stripped_text_from_html.replace("\n\n", "\n")
+            stripped_text_from_html = '\n'.join(sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower()))
+
 
         # Re #340 - return the content before the 'ignore text' was applied
         text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
@@ -250,7 +242,7 @@ class perform_site_check(difference_detection_processor):
                 # We had some content, but no differences were found
                 # Store our new file as the MD5 so it will trigger in the future
                 c = hashlib.md5(text_content_before_ignored_filter.translate(None, b'\r\n\t ')).hexdigest()
-                return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8')
+                return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8'), stripped_text_from_html.encode('utf-8')
             else:
                 stripped_text_from_html = rendered_diff
 
@@ -304,7 +296,7 @@ class perform_site_check(difference_detection_processor):
                         for match in res:
                             regex_matched_output += [match] + [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:
@@ -312,6 +304,8 @@ class perform_site_check(difference_detection_processor):
                 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()
@@ -371,4 +365,4 @@ class perform_site_check(difference_detection_processor):
         if not watch.get('previous_md5'):
             watch['previous_md5'] = fetched_md5
 
-        return changed_detected, update_obj, text_content_before_ignored_filter
+        return changed_detected, update_obj, text_content_before_ignored_filter, stripped_text_from_html

changedetectionio/run_socks_proxy_tests.sh

@@ -16,25 +16,31 @@ echo "---------------------------------- SOCKS5 -------------------"
 docker run --network changedet-network \
   -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
   --rm \
+  -e "FLASK_SERVER_NAME=cdio" \
+  --hostname cdio \
   -e "SOCKSTEST=proxiesjson" \
   test-changedetectionio \
-  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+  bash -c 'cd changedetectionio && pytest --live-server-host=0.0.0.0 --live-server-port=5004  -s tests/proxy_socks5/test_socks5_proxy_sources.py'
 
 # SOCKS5 related - by manually entering in UI
 docker run --network changedet-network \
   --rm \
+  -e "FLASK_SERVER_NAME=cdio" \
+  --hostname cdio \
   -e "SOCKSTEST=manual" \
   test-changedetectionio \
-  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy.py'
+  bash -c 'cd changedetectionio && pytest --live-server-host=0.0.0.0 --live-server-port=5004  -s tests/proxy_socks5/test_socks5_proxy.py'
 
 # SOCKS5 related - test from proxies.json via playwright - NOTE- PLAYWRIGHT DOESNT SUPPORT AUTHENTICATING PROXY
 docker run --network changedet-network \
   -e "SOCKSTEST=manual-playwright" \
+  --hostname cdio \
+  -e "FLASK_SERVER_NAME=cdio" \
   -v `pwd`/tests/proxy_socks5/proxies.json-example-noauth:/app/changedetectionio/test-datastore/proxies.json \
   -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" \
   --rm \
   test-changedetectionio \
-  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+  bash -c 'cd changedetectionio && pytest --live-server-host=0.0.0.0 --live-server-port=5004  -s tests/proxy_socks5/test_socks5_proxy_sources.py'
 
 echo "socks5 server logs"
 docker logs socks5proxy

changedetectionio/static/js/watch-settings.js

@@ -12,6 +12,55 @@ function toggleOpacity(checkboxSelector, fieldSelector, inverted) {
     checkbox.addEventListener('change', updateOpacity);
 }
 
+(function($) {
+    // Object to store ongoing requests by namespace
+    const requests = {};
+
+    $.abortiveSingularAjax = function(options) {
+        const namespace = options.namespace || 'default';
+
+        // Abort the current request in this namespace if it's still ongoing
+        if (requests[namespace]) {
+            requests[namespace].abort();
+        }
+
+        // Start a new AJAX request and store its reference in the correct namespace
+        requests[namespace] = $.ajax(options);
+
+        // Return the current request in case it's needed
+        return requests[namespace];
+    };
+})(jQuery);
+
+function request_textpreview_update() {
+    if (!$('body').hasClass('preview-text-enabled')) {
+        console.error("Preview text was requested but body tag was not setup")
+        return
+    }
+
+    const data = {};
+    $('textarea:visible, input:visible').each(function () {
+        const $element = $(this); // Cache the jQuery object for the current element
+        const name = $element.attr('name'); // Get the name attribute of the element
+        data[name] = $element.is(':checkbox') ? ($element.is(':checked') ? $element.val() : undefined) : $element.val();
+    });
+
+    $.abortiveSingularAjax({
+        type: "POST",
+        url: preview_text_edit_filters_url,
+        data: data,
+        namespace: 'watchEdit'
+    }).done(function (data) {
+        $('#filters-and-triggers #text-preview-inner').text(data);
+    }).fail(function (error) {
+        if (error.statusText === 'abort') {
+            console.log('Request was aborted due to a new request being fired.');
+        } else {
+            $('#filters-and-triggers #text-preview-inner').text('There was an error communicating with the server.');
+        }
+    })
+}
+
 $(document).ready(function () {
     $('#notification-setting-reset-to-default').click(function (e) {
         $('#notification_title').val('');
@@ -27,5 +76,22 @@ $(document).ready(function () {
 
     toggleOpacity('#time_between_check_use_default', '#time_between_check', false);
 
+    const vh = Math.max(document.documentElement.clientHeight || 0, window.innerHeight || 0);
+    $("#text-preview-inner").css('max-height', (vh-300)+"px");
+
+    // Realtime preview of 'Filters & Text' setup
+    var debounced_request_textpreview_update = request_textpreview_update.debounce(100);
+
+    $("#activate-text-preview").click(function (e) {
+        $('body').toggleClass('preview-text-enabled')
+        request_textpreview_update();
+
+        const method = $('body').hasClass('preview-text-enabled') ? 'on' : 'off';
+        $("#text-preview-refresh")[method]('click', debounced_request_textpreview_update);
+        $('textarea:visible')[method]('keyup blur', debounced_request_textpreview_update);
+        $('input:visible')[method]('keyup blur change', debounced_request_textpreview_update);
+        $("#filters-and-triggers-tab")[method]('click', debounced_request_textpreview_update);
+    });
+
 });
 

changedetectionio/static/styles/scss/parts/_browser-steps.scss

@@ -40,15 +40,29 @@
   }
 }
 
-#browser-steps-fieldlist {
-  height: 100%;
-  overflow-y: scroll;
-}
 
 #browser-steps .flex-wrapper {
   display: flex;
   flex-flow: row;
   height: 70vh;
+  font-size: 80%;
+  #browser-steps-ui {
+    flex-grow: 1;      /* Allow it to grow and fill the available space */
+    flex-shrink: 1;    /* Allow it to shrink if needed */
+    flex-basis: 0;     /* Start with 0 base width so it stretches as much as possible */
+    background-color: #eee;
+    border-radius: 5px;
+
+  }
+
+  #browser-steps-fieldlist {
+    flex-grow: 0;      /* Don't allow it to grow */
+    flex-shrink: 0;    /* Don't allow it to shrink */
+    flex-basis: auto;  /* Base width is determined by the content */
+    max-width: 400px;  /* Set a max width to prevent overflow */
+    padding-left: 1rem;
+    overflow-y: scroll;
+  }
 }
 
 /*  this is duplicate :( */

changedetectionio/static/styles/scss/parts/_preview_text_filter.scss

@@ -0,0 +1,45 @@
+body.preview-text-enabled {
+  #filters-and-triggers > div {
+    display: flex; /* Establishes Flexbox layout */
+    gap: 20px; /* Adds space between the columns */
+    position: relative; /* Ensures the sticky positioning is relative to this parent */
+  }
+
+  /* layout of the page */
+  #edit-text-filter, #text-preview {
+    flex: 1; /* Each column takes an equal amount of available space */
+    align-self: flex-start; /* Aligns the right column to the start, allowing it to maintain its content height */
+  }
+
+  #edit-text-filter {
+    #pro-tips {
+      display: none;
+    }
+  }
+
+  #text-preview {
+    position: sticky;
+    top: 25px;
+    display: block !important;
+  }
+
+  /* actual preview area */
+  #text-preview-inner {
+    background: var(--color-grey-900);
+    border: 1px solid var(--color-grey-600);
+    padding: 1rem;
+    color: #333;
+    font-family: "Courier New", Courier, monospace; /* Sets the font to a monospace type */
+    font-size: 12px;
+    overflow-x: scroll;
+    white-space: pre-wrap; /* Preserves whitespace and line breaks like <pre> */
+    overflow-wrap: break-word; /* Allows long words to break and wrap to the next line */
+  }
+}
+
+#activate-text-preview {
+  right: 0;
+  position: absolute;
+  z-index: 0;
+  box-shadow: 1px 1px 4px var(--color-shadow-jump);
+}

changedetectionio/static/styles/scss/styles.scss

@@ -12,6 +12,7 @@
 @import "parts/_darkmode";
 @import "parts/_menu";
 @import "parts/_love";
+@import "parts/preview_text_filter";
 
 body {
   color: var(--color-text);

changedetectionio/static/styles/styles.css

@@ -46,14 +46,31 @@
     #browser_steps li > label {
       display: none; }
 
-#browser-steps-fieldlist {
-  height: 100%;
-  overflow-y: scroll; }
-
 #browser-steps .flex-wrapper {
   display: flex;
   flex-flow: row;
-  height: 70vh; }
+  height: 70vh;
+  font-size: 80%; }
+  #browser-steps .flex-wrapper #browser-steps-ui {
+    flex-grow: 1;
+    /* Allow it to grow and fill the available space */
+    flex-shrink: 1;
+    /* Allow it to shrink if needed */
+    flex-basis: 0;
+    /* Start with 0 base width so it stretches as much as possible */
+    background-color: #eee;
+    border-radius: 5px; }
+  #browser-steps .flex-wrapper #browser-steps-fieldlist {
+    flex-grow: 0;
+    /* Don't allow it to grow */
+    flex-shrink: 0;
+    /* Don't allow it to shrink */
+    flex-basis: auto;
+    /* Base width is determined by the content */
+    max-width: 400px;
+    /* Set a max width to prevent overflow */
+    padding-left: 1rem;
+    overflow-y: scroll; }
 
 /*  this is duplicate :( */
 #browsersteps-selector-wrapper {
@@ -411,6 +428,47 @@ html[data-darkmode="true"] #toggle-light-mode .icon-dark {
     fill: #ff0000 !important;
     transition: all ease 0.3s !important; }
 
+body.preview-text-enabled {
+  /* layout of the page */
+  /* actual preview area */ }
+  body.preview-text-enabled #filters-and-triggers > div {
+    display: flex;
+    /* Establishes Flexbox layout */
+    gap: 20px;
+    /* Adds space between the columns */
+    position: relative;
+    /* Ensures the sticky positioning is relative to this parent */ }
+  body.preview-text-enabled #edit-text-filter, body.preview-text-enabled #text-preview {
+    flex: 1;
+    /* Each column takes an equal amount of available space */
+    align-self: flex-start;
+    /* Aligns the right column to the start, allowing it to maintain its content height */ }
+  body.preview-text-enabled #edit-text-filter #pro-tips {
+    display: none; }
+  body.preview-text-enabled #text-preview {
+    position: sticky;
+    top: 25px;
+    display: block !important; }
+  body.preview-text-enabled #text-preview-inner {
+    background: var(--color-grey-900);
+    border: 1px solid var(--color-grey-600);
+    padding: 1rem;
+    color: #333;
+    font-family: "Courier New", Courier, monospace;
+    /* Sets the font to a monospace type */
+    font-size: 12px;
+    overflow-x: scroll;
+    white-space: pre-wrap;
+    /* Preserves whitespace and line breaks like <pre> */
+    overflow-wrap: break-word;
+    /* Allows long words to break and wrap to the next line */ }
+
+#activate-text-preview {
+  right: 0;
+  position: absolute;
+  z-index: 0;
+  box-shadow: 1px 1px 4px var(--color-shadow-jump); }
+
 body {
   color: var(--color-text);
   background: var(--color-background-page);
@@ -1194,11 +1252,9 @@ ul {
   color: #fff;
   opacity: 0.7; }
 
-
 .restock-label svg {
   vertical-align: middle; }
 
-
 #chrome-extension-link {
   padding: 9px;
   border: 1px solid var(--color-grey-800);

changedetectionio/templates/_common_fields.html

@@ -15,7 +15,7 @@
                                 <strong>Tip:</strong> Use <a target=_new href="https://github.com/caronc/apprise">AppRise Notification URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.<br>
 </p>
                                 <div data-target="#advanced-help-notifications" class="toggle-show pure-button button-tag button-xsmall">Show advanced help and tips</div>
-                              <ul style="display: none" id="advanced-help-notifications">
+                                <ul style="display: none" id="advanced-help-notifications">
                                 <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_discord">discord://</a></code> (or <code>https://discord.com/api/webhooks...</code>)) only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
                                 <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> bots can't send messages to other bots, so you should specify chat ID of non-bot user.</li>
                                 <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>

changedetectionio/templates/base.html

@@ -33,7 +33,7 @@
     <script src="{{url_for('static_content', group='js', filename='csrf.js')}}" defer></script>
   </head>
 
-  <body>
+  <body class="">
     <div class="header">
       <div class="home-menu pure-menu pure-menu-horizontal pure-menu-fixed" id="nav-menu">
         {% if has_password and not current_user.is_authenticated %}

changedetectionio/templates/edit.html

@@ -50,7 +50,7 @@
             {% endif %}
             {% if watch['processor'] == 'text_json_diff' %}
             <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" id="filters-and-triggers-tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
             {% endif %}
             <li class="tab"><a href="#notifications">Notifications</a></li>
             <li class="tab"><a href="#stats">Stats</a></li>
@@ -200,7 +200,7 @@ User-Agent: wonderbra 1.0") }}
                         <div id="loading-status-text" style="display: none;">Please wait, first browser step can take a little time to load..<div class="spinner"></div></div>
                         <div class="flex-wrapper" >
 
-                            <div id="browser-steps-ui" class="noselect"  style="width: 100%; background-color: #eee; border-radius: 5px;">
+                            <div id="browser-steps-ui" class="noselect">
 
                                 <div class="noselect"  id="browsersteps-selector-wrapper" style="width: 100%">
                                     <span class="loader" >
@@ -215,7 +215,7 @@ User-Agent: wonderbra 1.0") }}
                                     <canvas  class="noselect" id="browsersteps-selector-canvas" style="max-width: 100%; width: 100%;"></canvas>
                                 </div>
                             </div>
-                            <div id="browser-steps-fieldlist" style="padding-left: 1em;  width: 350px; font-size: 80%;" >
+                            <div id="browser-steps-fieldlist" >
                                 <span id="browser-seconds-remaining">Loading</span> <span style="font-size: 80%;"> (<a target=_new href="https://github.com/dgtlmoon/changedetection.io/pull/478/files#diff-1a79d924d1840c485238e66772391268a89c95b781d69091384cf1ea1ac146c9R4">?</a>) </span>
                                 {{ render_field(form.browser_steps) }}
                             </div>
@@ -254,7 +254,10 @@ User-Agent: wonderbra 1.0") }}
 
             {% if watch['processor'] == 'text_json_diff' %}
             <div class="tab-pane-inner" id="filters-and-triggers">
-                    <div class="pure-control-group">
+                <span id="activate-text-preview" class="pure-button pure-button-primary button-xsmall">Activate preview</span>
+              <div>
+              <div id="edit-text-filter">
+                    <div class="pure-control-group" id="pro-tips">
                             <strong>Pro-tips:</strong><br>
                             <ul>
                                 <li>
@@ -310,12 +313,13 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                     {{ render_field(form.subtractive_selectors, rows=5, placeholder=has_tag_filters_extra+"header
 footer
 nav
-.stockticker") }}
+.stockticker
+//*[contains(text(), 'Advertisement')]") }}
                     <span class="pure-form-message-inline">
                         <ul>
-                          <li> Remove HTML element(s) by CSS selector before text conversion. </li>
-                          <li> Don't paste HTML here, use only CSS selectors </li>
-                          <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
+                          <li> Remove HTML element(s) by CSS and XPath selectors before text conversion. </li>
+                          <li> Don't paste HTML here, use only CSS and XPath selectors </li>
+                          <li> Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
                 </fieldset>
@@ -330,14 +334,21 @@ nav
                     <span class="pure-form-message-inline">So it's always better to select <strong>Added</strong>+<strong>Replaced</strong> when you're interested in new content.</span><br>
                     <span class="pure-form-message-inline">When content is merely moved in a list, it will also trigger an <strong>addition</strong>, consider enabling <code><strong>Only trigger when unique lines appear</strong></code></span>
                 </fieldset>
-
+                <fieldset 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>
+                </fieldset>
+                <fieldset class="pure-control-group">
+                    {{ render_checkbox_field(form.remove_duplicate_lines) }}
+                    <span class="pure-form-message-inline">Remove duplicate lines of text</span>
+                </fieldset>
                 <fieldset class="pure-control-group">
                     {{ render_checkbox_field(form.sort_text_alphabetically) }}
                     <span class="pure-form-message-inline">Helps reduce changes detected caused by sites shuffling lines around, combine with <i>check unique lines</i> below.</span>
                 </fieldset>
                 <fieldset 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>
+                    {{ render_checkbox_field(form.trim_text_whitespace) }}
+                    <span class="pure-form-message-inline">Remove any whitespace before and after each line of text</span>
                 </fieldset>
                 <fieldset>
                     <div class="pure-control-group">
@@ -407,7 +418,19 @@ Unavailable") }}
                 </fieldset>
                 </div>
             </div>
-            {% endif %}
+              <div id="text-preview" style="display: none;" >
+                    <script>
+                        const preview_text_edit_filters_url="{{url_for('watch_get_preview_rendered', uuid=uuid)}}";
+                    </script>
+                    <span><strong>Preview of the text that is used for changedetection after all filters run.</strong></span><br>
+                    {#<div id="text-preview-controls"><span id="text-preview-refresh" class="pure-button button-xsmall">Refresh</span></div>#}
+                <p>
+                    <div id="text-preview-inner"></div>
+                </p>
+            </div>
+          </div>
+        </div>
+        {% endif %}
         {# rendered sub Template #}
         {% if extra_form_content %}
             <div class="tab-pane-inner" id="extras_tab">

changedetectionio/templates/settings.html

@@ -155,11 +155,13 @@
                       {{ render_field(form.application.form.global_subtractive_selectors, rows=5, placeholder="header
 footer
 nav
-.stockticker") }}
+.stockticker
+//*[contains(text(), 'Advertisement')]") }}
                       <span class="pure-form-message-inline">
                         <ul>
-                          <li> Remove HTML element(s) by CSS selector before text conversion. </li>
-                          <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
+                          <li> Remove HTML element(s) by CSS and XPath selectors before text conversion. </li>
+                          <li> Don't paste HTML here, use only CSS and XPath selectors </li>
+                          <li> Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
                     </fieldset>

changedetectionio/tests/proxy_socks5/test_socks5_proxy.py

@@ -1,12 +1,27 @@
 #!/usr/bin/env python3
 import os
-import time
 from flask import url_for
 from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
 
 
+def set_response():
+    import time
+    data = f"""<html>
+       <body>
+     <h1>Awesome, you made it</h1>
+     yeah the socks request worked
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(data)
+    time.sleep(1)
+
+
 def test_socks5(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
+    set_response()
 
     # Setup a proxy
     res = client.post(
@@ -24,7 +39,10 @@ def test_socks5(client, live_server, measure_memory_usage):
 
     assert b"Settings updated." in res.data
 
-    test_url = "https://changedetection.io/CHANGELOG.txt?socks-test-tag=" + os.getenv('SOCKSTEST', '')
+    # Because the socks server should connect back to us
+    test_url = url_for('test_endpoint', _external=True) + f"?socks-test-tag={os.getenv('SOCKSTEST', '')}"
+    test_url = test_url.replace('localhost.localdomain', 'cdio')
+    test_url = test_url.replace('localhost', 'cdio')
 
     res = client.post(
         url_for("form_quick_watch_add"),
@@ -60,4 +78,4 @@ def test_socks5(client, live_server, measure_memory_usage):
     )
 
     # Should see the proper string
-    assert "+0200:".encode('utf-8') in res.data
+    assert "Awesome, you made it".encode('utf-8') in res.data

changedetectionio/tests/proxy_socks5/test_socks5_proxy_sources.py

@@ -1,16 +1,32 @@
 #!/usr/bin/env python3
 import os
-import time
 from flask import url_for
 from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
 
 
+def set_response():
+    import time
+    data = f"""<html>
+       <body>
+     <h1>Awesome, you made it</h1>
+     yeah the socks request worked
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(data)
+    time.sleep(1)
+
 # should be proxies.json mounted from run_proxy_tests.sh already
 # -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json
 def test_socks5_from_proxiesjson_file(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
-
-    test_url = "https://changedetection.io/CHANGELOG.txt?socks-test-tag=" + os.getenv('SOCKSTEST', '')
+    set_response()
+    # Because the socks server should connect back to us
+    test_url = url_for('test_endpoint', _external=True) + f"?socks-test-tag={os.getenv('SOCKSTEST', '')}"
+    test_url = test_url.replace('localhost.localdomain', 'cdio')
+    test_url = test_url.replace('localhost', 'cdio')
 
     res = client.get(url_for("settings_page"))
     assert b'name="requests-proxy" type="radio" value="socks5proxy"' in res.data
@@ -49,4 +65,4 @@ def test_socks5_from_proxiesjson_file(client, live_server, measure_memory_usage)
     )
 
     # Should see the proper string
-    assert "+0200:".encode('utf-8') in res.data
+    assert "Awesome, you made it".encode('utf-8') in res.data

changedetectionio/tests/test_element_removal.py

@@ -87,6 +87,9 @@ def test_element_removal_output():
      Some initial text<br>
      <p>across multiple lines</p>
      <div id="changetext">Some text that changes</div>
+     <div>Some text should be matched by xPath // selector</div>
+     <div>Some text should be matched by xPath selector</div>
+     <div>Some text should be matched by xPath1 selector</div>
      </body>
     <footer>
     <p>Footer</p>
@@ -94,7 +97,16 @@ def test_element_removal_output():
      </html>
     """
     html_blob = element_removal(
-        ["header", "footer", "nav", "#changetext"], html_content=content
+      [
+        "header",
+        "footer",
+        "nav",
+        "#changetext",
+        "//*[contains(text(), 'xPath // selector')]",
+        "xpath://*[contains(text(), 'xPath selector')]",
+        "xpath1://*[contains(text(), 'xPath1 selector')]"
+      ],
+      html_content=content
     )
     text = get_text(html_blob)
     assert (

changedetectionio/tests/test_encoding.py

@@ -3,7 +3,7 @@
 
 import time
 from flask import url_for
-from .util import live_server_setup, wait_for_all_checks
+from .util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
 import pytest
 
 
@@ -38,6 +38,11 @@ def test_check_encoding_detection(client, live_server, measure_memory_usage):
     # Give the thread time to pick it up
     wait_for_all_checks(client)
 
+
+    # Content type recording worked
+    uuid = extract_UUID_from_client(client)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid]['content-type'] == "text/html"
+
     res = client.get(
         url_for("preview_page", uuid="first"),
         follow_redirects=True

changedetectionio/tests/test_filter_failure_notification.py

@@ -116,9 +116,11 @@ def run_filter_test(client, live_server, content_filter):
         res = client.get(url_for("index"))
         assert b'Warning, no filters were found' in res.data
         assert not os.path.isfile("test-datastore/notification.txt")
-
+        time.sleep(1)
+        
     assert live_server.app.config['DATASTORE'].data['watching'][uuid]['consecutive_filter_failures'] == 5
 
+    time.sleep(2)
     # One more check should trigger the _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT threshold
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)

changedetectionio/tests/test_unique_lines.py

@@ -11,6 +11,8 @@ def set_original_ignore_response():
      <p>Some initial text</p>
      <p>Which is across multiple lines</p>
      <p>So let's see what happens.</p>
+     <p>&nbsp;  So let's see what happens.   <br> </p>
+     <p>A - sortable line</p> 
      </body>
      </html>
     """
@@ -164,5 +166,52 @@ def test_sort_lines_functionality(client, live_server, measure_memory_usage):
     assert res.data.find(b'A uppercase') < res.data.find(b'Z last')
     assert res.data.find(b'Some initial text') < res.data.find(b'Which is across multiple lines')
     
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+
+def test_extra_filters(client, live_server, measure_memory_usage):
+    #live_server_setup(live_server)
+
+    set_original_ignore_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
+    wait_for_all_checks(client)
+
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"remove_duplicate_lines": "y",
+              "trim_text_whitespace": "y",
+              "sort_text_alphabetically": "",  # leave this OFF for testing
+              "url": test_url,
+              "fetch_backend": "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    # Give the thread time to pick it up
+    wait_for_all_checks(client)
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("preview_page", uuid="first")
+    )
+
+    assert res.data.count(b"see what happens.") == 1
+
+    # still should remain unsorted ('A - sortable line') stays at the end
+    assert res.data.find(b'A - sortable line') > res.data.find(b'Which is across multiple lines')
+
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/util.py

@@ -78,6 +78,7 @@ def set_more_modified_response():
 
 def wait_for_notification_endpoint_output():
     '''Apprise can take a few seconds to fire'''
+    #@todo - could check the apprise object directly instead of looking for this file
     from os.path import isfile
     for i in range(1, 20):
         time.sleep(1)

changedetectionio/update_worker.py

@@ -278,7 +278,7 @@ class update_worker(threading.Thread):
 
                         update_handler.call_browser()
 
-                        changed_detected, update_obj, contents = update_handler.run_changedetection(
+                        changed_detected, update_obj, contents, content_after_filters = update_handler.run_changedetection(
                             watch=watch,
                             skip_when_checksum_same=skip_when_same_checksum,
                         )
@@ -491,6 +491,8 @@ class update_worker(threading.Thread):
                         if not self.datastore.data['watching'].get(uuid):
                             continue
 
+                        update_obj['content-type'] = update_handler.fetcher.get_all_headers().get('content-type', '').lower()
+
                         # Mark that we never had any failures
                         if not watch.get('ignore_status_codes'):
                             update_obj['consecutive_filter_failures'] = 0