Fixing page update

(its utf-16 by default python string)

Dockerfile

@@ -37,6 +37,7 @@ RUN pip install --target=/dependencies playwright~=1.41.2 \
 
 # Final image stage
 FROM python:${PYTHON_VERSION}-slim-bookworm
+LABEL org.opencontainers.image.source="https://github.com/dgtlmoon/changedetection.io"
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libxslt1.1 \

changedetectionio/apprise_plugin/__init__.py

@@ -1,5 +1,6 @@
 # include the decorator
 from apprise.decorators import notify
+from loguru import logger
 
 @notify(on="delete")
 @notify(on="deletes")
@@ -64,10 +65,12 @@ def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
             auth = (URLBase.unquote(results.get('user')))
 
     # Try to auto-guess if it's JSON
+    h = 'application/json; charset=utf-8'
     try:
         json.loads(body)
-        headers['Content-Type'] = 'application/json; charset=utf-8'
+        headers['Content-Type'] = h
     except ValueError as e:
+        logger.warning(f"Could not automatically add '{h}' header to the {kwargs['meta'].get('schema')}:// notification because the document failed to parse as JSON: {e}")
         pass
 
     r(results.get('url'),

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

@@ -17,7 +17,6 @@
 </script>
 
 <script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
-<!--<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>-->
 <script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 
 <div class="edit-form monospaced-textarea">
@@ -89,11 +88,13 @@ 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/content_fetchers/__init__.py

@@ -4,7 +4,9 @@ from loguru import logger
 from changedetectionio.content_fetchers.exceptions import BrowserStepsStepException
 import os
 
-visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4,header,footer,section,article,aside,details,main,nav,section,summary'
+# Visual Selector scraper - 'Button' is there because some sites have <button>OUT OF STOCK</button>.
+visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4,header,footer,section,article,aside,details,main,nav,section,summary,button'
+
 
 # available_fetchers() will scan this implementation looking for anything starting with html_
 # this information is used in the form selections

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

@@ -154,10 +154,14 @@ function isItemInStock() {
         }
 
         elementText = "";
-        if (element.tagName.toLowerCase() === "input") {
-            elementText = element.value.toLowerCase().trim();
-        } else {
-            elementText = getElementBaseText(element);
+        try {
+            if (element.tagName.toLowerCase() === "input") {
+                elementText = element.value.toLowerCase().trim();
+            } else {
+                elementText = getElementBaseText(element);
+            }
+        } catch (e) {
+            console.warn('stock-not-in-stock.js scraper - handling element for gettext failed', e);
         }
 
         if (elementText.length) {

changedetectionio/flask_app.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 
 import datetime
+
 import flask_login
 import locale
 import os
@@ -1154,8 +1155,6 @@ def changedetection_app(config=None, datastore_o=None):
     @login_optionally_required
     def preview_page(uuid):
         content = []
-        ignored_line_numbers = []
-        trigger_line_numbers = []
         versions = []
         timestamp = None
 
@@ -1172,11 +1171,10 @@ def changedetection_app(config=None, datastore_o=None):
         system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
         extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
 
-
         is_html_webdriver = False
         if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
             is_html_webdriver = True
-
+        triggered_line_numbers = []
         if datastore.data['watching'][uuid].history_n == 0 and (watch.get_error_text() or watch.get_error_snapshot()):
             flash("Preview unavailable - No fetch/check completed or triggers not reached", "error")
         else:
@@ -1189,31 +1187,12 @@ def changedetection_app(config=None, datastore_o=None):
 
             try:
                 versions = list(watch.history.keys())
-                tmp = watch.get_history_snapshot(timestamp).splitlines()
+                content = watch.get_history_snapshot(timestamp)
 
-                # Get what needs to be highlighted
-                ignore_rules = watch.get('ignore_text', []) + datastore.data['settings']['application']['global_ignore_text']
-
-                # .readlines will keep the \n, but we will parse it here again, in the future tidy this up
-                ignored_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
-                                                                    wordlist=ignore_rules,
-                                                                    mode='line numbers'
-                                                                    )
-
-                trigger_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
-                                                                    wordlist=watch['trigger_text'],
-                                                                    mode='line numbers'
-                                                                    )
-                # Prepare the classes and lines used in the template
-                i=0
-                for l in tmp:
-                    classes=[]
-                    i+=1
-                    if i in ignored_line_numbers:
-                        classes.append('ignored')
-                    if i in trigger_line_numbers:
-                        classes.append('triggered')
-                    content.append({'line': l, 'classes': ' '.join(classes)})
+                triggered_line_numbers = html_tools.strip_ignore_text(content=content,
+                                                                      wordlist=watch['trigger_text'],
+                                                                      mode='line numbers'
+                                                                      )
 
             except Exception as e:
                 content.append({'line': f"File doesnt exist or unable to read timestamp {timestamp}", 'classes': ''})
@@ -1224,8 +1203,7 @@ def changedetection_app(config=None, datastore_o=None):
                                  history_n=watch.history_n,
                                  extra_stylesheets=extra_stylesheets,
                                  extra_title=f" - Diff - {watch.label} @ {timestamp}",
-                                 ignored_line_numbers=ignored_line_numbers,
-                                 triggered_line_numbers=trigger_line_numbers,
+                                 triggered_line_numbers=triggered_line_numbers,
                                  current_diff_url=watch['url'],
                                  screenshot=watch.get_screenshot(),
                                  watch=watch,
@@ -1396,6 +1374,15 @@ def changedetection_app(config=None, datastore_o=None):
         # Return a 500 error
         abort(500)
 
+    # Ajax callback
+    @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'''
+        from .processors.text_json_diff import prepare_filter_prevew
+        return prepare_filter_prevew(watch_uuid=uuid, datastore=datastore)
+
+
     @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
 
@@ -469,19 +470,21 @@ 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()])
 
     title = StringField('Title', default='')
 
-    ignore_text = StringListField('Ignore text', [ValidateListRegex()])
+    ignore_text = StringListField('Ignore lines containing', [ValidateListRegex()])
     headers = StringDictKeyValue('Request headers')
     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

@@ -1,12 +1,13 @@
 from typing import List
+from lxml import etree
 import json
 import re
 
-
 # HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
 TEXT_FILTER_LIST_LINE_SUFFIX = "<br>"
-
+TRANSLATE_WHITESPACE_TABLE = str.maketrans('', '', '\r\n\t ')
 PERL_STYLE_REGEX = r'^/(.*?)/([a-z]*)?$'
+
 # 'price' , 'lowPrice', 'highPrice' are usually under here
 # All of those may or may not appear on different websites - I didnt find a way todo case-insensitive searching here
 LD_JSON_PRODUCT_OFFER_SELECTORS = ["json:$..offers", "json:$..Offers"]
@@ -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):
     """
@@ -310,6 +326,7 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
 #          - "line numbers" return a list of line numbers that match (int list)
 #
 # wordlist - list of regex's (str) or words (str)
+# Preserves all linefeeds and other whitespacing, its not the job of this to remove that
 def strip_ignore_text(content, wordlist, mode="content"):
     i = 0
     output = []
@@ -325,32 +342,30 @@ def strip_ignore_text(content, wordlist, mode="content"):
         else:
             ignore_text.append(k.strip())
 
-    for line in content.splitlines():
+    for line in content.splitlines(keepends=True):
         i += 1
         # Always ignore blank lines in this mode. (when this function gets called)
         got_match = False
-        if len(line.strip()):
-            for l in ignore_text:
-                if l.lower() in line.lower():
+        for l in ignore_text:
+            if l.lower() in line.lower():
+                got_match = True
+
+        if not got_match:
+            for r in ignore_regex:
+                if r.search(line):
                     got_match = True
 
-            if not got_match:
-                for r in ignore_regex:
-                    if r.search(line):
-                        got_match = True
-
-            if not got_match:
-                # Not ignored
-                output.append(line.encode('utf8'))
-            else:
-                ignored_line_numbers.append(i)
-
+        if not got_match:
+            # Not ignored, and should preserve "keepends"
+            output.append(line)
+        else:
+            ignored_line_numbers.append(i)
 
     # Used for finding out what to highlight
     if mode == "line numbers":
         return ignored_line_numbers
 
-    return "\n".encode('utf8').join(output)
+    return ''.join(output)
 
 def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False) -> str:
     from xml.sax.saxutils import escape as xml_escape

changedetectionio/model/Watch.py

@@ -6,6 +6,8 @@ import re
 from pathlib import Path
 from loguru import logger
 
+from ..html_tools import TRANSLATE_WHITESPACE_TABLE
+
 # Allowable protocols, protects against javascript: etc
 # file:// is further checked by ALLOW_FILE_URI
 SAFE_PROTOCOL_REGEX='^(http|https|ftp|file):'
@@ -36,8 +38,9 @@ class model(watch_base):
     jitter_seconds = 0
 
     def __init__(self, *arg, **kw):
-        self.__datastore_path = kw['datastore_path']
-        del kw['datastore_path']
+        self.__datastore_path = kw.get('datastore_path')
+        if kw.get('datastore_path'):
+            del kw['datastore_path']
         super(model, self).__init__(*arg, **kw)
         if kw.get('default'):
             self.update(kw['default'])
@@ -171,6 +174,10 @@ class model(watch_base):
         """
         tmp_history = {}
 
+        # In the case we are only using the watch for processing without history
+        if not self.watch_data_dir:
+            return []
+
         # Read the history file as a dict
         fname = os.path.join(self.watch_data_dir, "history.txt")
         if os.path.isfile(fname):
@@ -307,13 +314,13 @@ class model(watch_base):
             dest = os.path.join(self.watch_data_dir, snapshot_fname)
             if not os.path.exists(dest):
                 with open(dest, 'wb') as f:
-                    f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
+                    f.write(brotli.compress(contents.encode('utf-8'), mode=brotli.MODE_TEXT))
         else:
             snapshot_fname = f"{snapshot_id}.txt"
             dest = os.path.join(self.watch_data_dir, snapshot_fname)
             if not os.path.exists(dest):
                 with open(dest, 'wb') as f:
-                    f.write(contents)
+                    f.write(contents.encode('utf-8'))
 
         # Append to index
         # @todo check last char was \n
@@ -345,14 +352,32 @@ class model(watch_base):
         return seconds
 
     # Iterate over all history texts and see if something new exists
-    def lines_contain_something_unique_compared_to_history(self, lines: list):
-        local_lines = set([l.decode('utf-8').strip().lower() for l in lines])
+    # Always applying .strip() to start/end but optionally replace any other whitespace
+    def lines_contain_something_unique_compared_to_history(self, lines: list, ignore_whitespace=False):
+        local_lines = []
+        if lines:
+            if ignore_whitespace:
+                if isinstance(lines[0], str): # Can be either str or bytes depending on what was on the disk
+                    local_lines = set([l.translate(TRANSLATE_WHITESPACE_TABLE).lower() for l in lines])
+                else:
+                    local_lines = set([l.decode('utf-8').translate(TRANSLATE_WHITESPACE_TABLE).lower() for l in lines])
+            else:
+                if isinstance(lines[0], str): # Can be either str or bytes depending on what was on the disk
+                    local_lines = set([l.strip().lower() for l in lines])
+                else:
+                    local_lines = set([l.decode('utf-8').strip().lower() for l in lines])
+
 
         # Compare each lines (set) against each history text file (set) looking for something new..
         existing_history = set({})
         for k, v in self.history.items():
             content = self.get_history_snapshot(k)
-            alist = set([line.strip().lower() for line in content.splitlines()])
+
+            if ignore_whitespace:
+                alist = set([line.translate(TRANSLATE_WHITESPACE_TABLE).lower() for line in content.splitlines()])
+            else:
+                alist = set([line.strip().lower() for line in content.splitlines()])
+
             existing_history = existing_history.union(alist)
 
         # Check that everything in local_lines(new stuff) already exists in existing_history - it should
@@ -396,8 +421,8 @@ class model(watch_base):
     @property
     def watch_data_dir(self):
         # The base dir of the watch data
-        return os.path.join(self.__datastore_path, self['uuid'])
-    
+        return os.path.join(self.__datastore_path, self['uuid']) if self.__datastore_path else None
+
     def get_error_text(self):
         """Return the text saved from a previous request that resulted in a non-200 error"""
         fname = os.path.join(self.watch_data_dir, "last-error.txt")

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

@@ -1,14 +1,14 @@
 from abc import abstractmethod
+from changedetectionio.content_fetchers.base import Fetcher
 from changedetectionio.strtobool import strtobool
-
 from copy import deepcopy
 from loguru import logger
 import hashlib
-import os
-import re
 import importlib
-import pkgutil
 import inspect
+import os
+import pkgutil
+import re
 
 class difference_detection_processor():
 
@@ -23,10 +23,11 @@ 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):
@@ -154,7 +155,7 @@ class difference_detection_processor():
         # After init, call run_changedetection() which will do the actual change-detection
 
     @abstractmethod
-    def run_changedetection(self, watch, skip_when_checksum_same=True):
+    def run_changedetection(self, watch, skip_when_checksum_same: bool = True):
         update_obj = {'last_notification_error': False, 'last_error': False}
         some_data = 'xxxxx'
         update_obj["previous_md5"] = hashlib.md5(some_data.encode('utf-8')).hexdigest()

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.",
@@ -221,12 +229,21 @@ class perform_site_check(difference_detection_processor):
                 xpath_data=self.fetcher.xpath_data
                 )
 
+        logger.debug(f"self.fetcher.instock_data is - '{self.fetcher.instock_data}' and itemprop_availability.get('availability') is {itemprop_availability.get('availability')}")
         # Nothing automatic in microdata found, revert to scraping the page
         if self.fetcher.instock_data and itemprop_availability.get('availability') is None:
             # 'Possibly in stock' comes from stock-not-in-stock.js when no string found above the fold.
             # Careful! this does not really come from chrome/js when the watch is set to plaintext
             update_obj['restock']["in_stock"] = True if self.fetcher.instock_data == 'Possibly in stock' else False
-            logger.debug(f"Watch UUID {watch.get('uuid')} restock check returned '{self.fetcher.instock_data}' from JS scraper.")
+            logger.debug(f"Watch UUID {watch.get('uuid')} restock check returned instock_data - '{self.fetcher.instock_data}' from JS scraper.")
+
+        # Very often websites will lie about the 'availability' in the metadata, so if the scraped version says its NOT in stock, use that.
+        if self.fetcher.instock_data and self.fetcher.instock_data != 'Possibly in stock':
+            if update_obj['restock'].get('in_stock'):
+                logger.warning(
+                    f"Lie detected in the availability machine data!! when scraping said its not in stock!! itemprop was '{itemprop_availability}' and scraped from browser was '{self.fetcher.instock_data}' update obj was {update_obj['restock']} ")
+                logger.warning(f"Setting instock to FALSE, scraper found '{self.fetcher.instock_data}' in the body but metadata reported not-in-stock")
+                update_obj['restock']["in_stock"] = False
 
         # What we store in the snapshot
         price = update_obj.get('restock').get('price') if update_obj.get('restock').get('price') else ""
@@ -290,4 +307,4 @@ 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.strip()

changedetectionio/processors/text_json_diff/__init__.py

@@ -0,0 +1,118 @@
+
+from loguru import logger
+
+
+
+def _task(watch, update_handler):
+    from changedetectionio.content_fetchers.exceptions import ReplyWithContentButNoText
+    from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
+
+    text_after_filter = ''
+
+    try:
+        # The slow process (we run 2 of these in parallel)
+        changed_detected, update_obj, text_after_filter = update_handler.run_changedetection(
+            watch=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'
+
+    # because run_changedetection always returns bytes due to saving the snapshots etc
+    text_after_filter = text_after_filter.decode('utf-8') if isinstance(text_after_filter, bytes) else text_after_filter
+
+    return text_after_filter
+
+
+def prepare_filter_prevew(datastore, watch_uuid):
+    '''Used by @app.route("/edit/<string:uuid>/preview-rendered", methods=['POST'])'''
+    from changedetectionio import forms, html_tools
+    from changedetectionio.model.Watch import model as watch_model
+    from concurrent.futures import ProcessPoolExecutor
+    from copy import deepcopy
+    from flask import request, jsonify
+    import brotli
+    import importlib
+    import os
+    import time
+    now = time.time()
+
+    text_after_filter = ''
+    text_before_filter = ''
+    trigger_line_numbers = []
+    ignore_line_numbers = []
+
+    tmp_watch = deepcopy(datastore.data['watching'].get(watch_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)
+        blank_watch_no_filters = watch_model()
+        blank_watch_no_filters['url'] = tmp_watch.get('url')
+
+        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=tmp_watch.get('uuid')  # probably not needed anymore anyway?
+                                                                 )
+            # Use the last loaded HTML as the input
+            update_handler.datastore = datastore
+            update_handler.fetcher.content = str(decompressed_data) # str() because playwright/puppeteer/requests return string
+            update_handler.fetcher.headers['content-type'] = tmp_watch.get('content-type')
+
+            # Process our watch with filters and the HTML from disk, and also a blank watch with no filters but also with the same HTML from disk
+            # Do this as a parallel process because it could take some time
+            with ProcessPoolExecutor(max_workers=2) as executor:
+                future1 = executor.submit(_task, tmp_watch, update_handler)
+                future2 = executor.submit(_task, blank_watch_no_filters, update_handler)
+
+                text_after_filter = future1.result()
+                text_before_filter = future2.result()
+
+    try:
+        trigger_line_numbers = html_tools.strip_ignore_text(content=text_after_filter,
+                                                            wordlist=tmp_watch['trigger_text'],
+                                                            mode='line numbers'
+                                                            )
+    except Exception as e:
+        text_before_filter = f"Error: {str(e)}"
+
+    try:
+        text_to_ignore = tmp_watch.get('ignore_text', []) + datastore.data['settings']['application'].get('global_ignore_text', [])
+        ignore_line_numbers = html_tools.strip_ignore_text(content=text_after_filter,
+                                                           wordlist=text_to_ignore,
+                                                           mode='line numbers'
+                                                           )
+    except Exception as e:
+        text_before_filter = f"Error: {str(e)}"
+
+    logger.trace(f"Parsed in {time.time() - now:.3f}s")
+
+    return jsonify(
+        {
+            'after_filter': text_after_filter,
+            'before_filter': text_before_filter.decode('utf-8') if isinstance(text_before_filter, bytes) else text_before_filter,
+            'duration': time.time() - now,
+            'trigger_line_numbers': trigger_line_numbers,
+            'ignore_line_numbers': ignore_line_numbers,
+        }
+    )
+

changedetectionio/processors/text_json_diff/processor.py

@@ -7,7 +7,7 @@ import re
 import urllib3
 
 from changedetectionio.processors import difference_detection_processor
-from changedetectionio.html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text
+from changedetectionio.html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text, TRANSLATE_WHITESPACE_TABLE
 from changedetectionio import html_tools, content_fetchers
 from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
 from loguru import logger
@@ -36,9 +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 = ""
         screenshot = False  # as bytes
@@ -174,30 +171,20 @@ 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)
@@ -210,22 +197,16 @@ 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:
-            # 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() ))
+        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())
 
         # Re #340 - return the content before the 'ignore text' was applied
-        text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
+        # Also used to calculate/show what was removed
+        text_content_before_ignored_filter = stripped_text_from_html
 
         # @todo whitespace coming from missing rtrim()?
         # stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
@@ -244,12 +225,12 @@ class perform_site_check(difference_detection_processor):
                                              line_feed_sep="\n",
                                              include_change_type_prefix=False)
 
-            watch.save_last_text_fetched_before_filters(text_content_before_ignored_filter)
+            watch.save_last_text_fetched_before_filters(text_content_before_ignored_filter.encode('utf-8'))
 
             if not rendered_diff and stripped_text_from_html:
                 # 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()
+                c = hashlib.md5(stripped_text_from_html.translate(TRANSLATE_WHITESPACE_TABLE).encode('utf-8')).hexdigest()
                 return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8')
             else:
                 stripped_text_from_html = rendered_diff
@@ -270,14 +251,6 @@ class perform_site_check(difference_detection_processor):
 
         update_obj["last_check_status"] = self.fetcher.get_last_status_code()
 
-        # If there's text to skip
-        # @todo we could abstract out the get_text() to handle this cleaner
-        text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
-        if len(text_to_ignore):
-            stripped_text_from_html = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
-        else:
-            stripped_text_from_html = stripped_text_from_html.encode('utf8')
-
         # 615 Extract text by regex
         extract_text = watch.get('extract_text', [])
         if len(extract_text) > 0:
@@ -286,37 +259,53 @@ class perform_site_check(difference_detection_processor):
                 # incase they specified something in '/.../x'
                 if re.search(PERL_STYLE_REGEX, s_re, re.IGNORECASE):
                     regex = html_tools.perl_style_slash_enclosed_regex_to_options(s_re)
-                    result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
+                    result = re.findall(regex, stripped_text_from_html)
 
                     for l in result:
                         if type(l) is tuple:
                             # @todo - some formatter option default (between groups)
-                            regex_matched_output += list(l) + [b'\n']
+                            regex_matched_output += list(l) + ['\n']
                         else:
                             # @todo - some formatter option default (between each ungrouped result)
-                            regex_matched_output += [l] + [b'\n']
+                            regex_matched_output += [l] + ['\n']
                 else:
                     # Doesnt look like regex, just hunt for plaintext and return that which matches
                     # `stripped_text_from_html` will be bytes, so we must encode s_re also to bytes
-                    r = re.compile(re.escape(s_re.encode('utf-8')), re.IGNORECASE)
+                    r = re.compile(re.escape(s_re), re.IGNORECASE)
                     res = r.findall(stripped_text_from_html)
                     if res:
                         for match in res:
-                            regex_matched_output += [match] + [b'\n']
+                            regex_matched_output += [match] + ['\n']
+
+            ##########################################################
+            stripped_text_from_html = ''
 
-            # Now we will only show what the regex matched
-            stripped_text_from_html = b''
-            text_content_before_ignored_filter = b''
             if regex_matched_output:
                 # @todo some formatter for presentation?
-                stripped_text_from_html = b''.join(regex_matched_output)
-                text_content_before_ignored_filter = stripped_text_from_html
+                stripped_text_from_html = ''.join(regex_matched_output)
+
+        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()))
+
+### CALCULATE MD5
+        # If there's text to ignore
+        text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
+        text_for_checksuming = stripped_text_from_html
+        if text_to_ignore:
+            text_for_checksuming = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
 
         # 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()
+        if text_for_checksuming and self.datastore.data['settings']['application'].get('ignore_whitespace', False):
+            fetched_md5 = hashlib.md5(text_for_checksuming.translate(TRANSLATE_WHITESPACE_TABLE).encode('utf-8')).hexdigest()
         else:
-            fetched_md5 = hashlib.md5(stripped_text_from_html).hexdigest()
+            fetched_md5 = hashlib.md5(text_for_checksuming.encode('utf-8')).hexdigest()
 
         ############ Blocking rules, after checksum #################
         blocked = False
@@ -356,7 +345,13 @@ class perform_site_check(difference_detection_processor):
 
         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())
+                ignore_whitespace = self.datastore.data['settings']['application'].get('ignore_whitespace')
+
+                has_unique_lines = watch.lines_contain_something_unique_compared_to_history(
+                    lines=stripped_text_from_html.splitlines(),
+                    ignore_whitespace=ignore_whitespace
+                )
+
                 # One or more lines? unsure?
                 if not has_unique_lines:
                     logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} didnt have anything new setting change_detected=False")
@@ -371,4 +366,5 @@ 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
+        # stripped_text_from_html - Everything after filters and NO 'ignored' content
+        return changed_detected, update_obj, 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/limit.js

@@ -1,56 +0,0 @@
-/**
- * debounce
- * @param {integer} milliseconds This param indicates the number of milliseconds
- *     to wait after the last call before calling the original function.
- * @param {object} What "this" refers to in the returned function.
- * @return {function} This returns a function that when called will wait the
- *     indicated number of milliseconds after the last call before
- *     calling the original function.
- */
-Function.prototype.debounce = function (milliseconds, context) {
-    var baseFunction = this,
-        timer = null,
-        wait = milliseconds;
-
-    return function () {
-        var self = context || this,
-            args = arguments;
-
-        function complete() {
-            baseFunction.apply(self, args);
-            timer = null;
-        }
-
-        if (timer) {
-            clearTimeout(timer);
-        }
-
-        timer = setTimeout(complete, wait);
-    };
-};
-
-/**
-* throttle
-* @param {integer} milliseconds This param indicates the number of milliseconds
-*     to wait between calls before calling the original function.
-* @param {object} What "this" refers to in the returned function.
-* @return {function} This returns a function that when called will wait the
-*     indicated number of milliseconds between calls before
-*     calling the original function.
-*/
-Function.prototype.throttle = function (milliseconds, context) {
-    var baseFunction = this,
-        lastEventTimestamp = null,
-        limit = milliseconds;
-
-    return function () {
-        var self = context || this,
-            args = arguments,
-            now = Date.now();
-
-        if (!lastEventTimestamp || now - lastEventTimestamp >= limit) {
-            lastEventTimestamp = now;
-            baseFunction.apply(self, args);
-        }
-    };
-};

changedetectionio/static/js/plugins.js

@@ -0,0 +1,162 @@
+(function ($) {
+    /**
+     * debounce
+     * @param {integer} milliseconds This param indicates the number of milliseconds
+     *     to wait after the last call before calling the original function.
+     * @param {object} What "this" refers to in the returned function.
+     * @return {function} This returns a function that when called will wait the
+     *     indicated number of milliseconds after the last call before
+     *     calling the original function.
+     */
+    Function.prototype.debounce = function (milliseconds, context) {
+        var baseFunction = this,
+            timer = null,
+            wait = milliseconds;
+
+        return function () {
+            var self = context || this,
+                args = arguments;
+
+            function complete() {
+                baseFunction.apply(self, args);
+                timer = null;
+            }
+
+            if (timer) {
+                clearTimeout(timer);
+            }
+
+            timer = setTimeout(complete, wait);
+        };
+    };
+
+    /**
+     * throttle
+     * @param {integer} milliseconds This param indicates the number of milliseconds
+     *     to wait between calls before calling the original function.
+     * @param {object} What "this" refers to in the returned function.
+     * @return {function} This returns a function that when called will wait the
+     *     indicated number of milliseconds between calls before
+     *     calling the original function.
+     */
+    Function.prototype.throttle = function (milliseconds, context) {
+        var baseFunction = this,
+            lastEventTimestamp = null,
+            limit = milliseconds;
+
+        return function () {
+            var self = context || this,
+                args = arguments,
+                now = Date.now();
+
+            if (!lastEventTimestamp || now - lastEventTimestamp >= limit) {
+                lastEventTimestamp = now;
+                baseFunction.apply(self, args);
+            }
+        };
+    };
+
+    $.fn.highlightLines = function (configurations) {
+        return this.each(function () {
+            const $pre = $(this);
+            const textContent = $pre.text();
+            const lines = textContent.split(/\r?\n/); // Handles both \n and \r\n line endings
+
+            // Build a map of line numbers to styles
+            const lineStyles = {};
+
+            configurations.forEach(config => {
+                const {color, lines: lineNumbers} = config;
+                lineNumbers.forEach(lineNumber => {
+                    lineStyles[lineNumber] = color;
+                });
+            });
+
+            // Function to escape HTML characters
+            function escapeHtml(text) {
+                return text.replace(/[&<>"'`=\/]/g, function (s) {
+                    return "&#" + s.charCodeAt(0) + ";";
+                });
+            }
+
+            // Process each line
+            const processedLines = lines.map((line, index) => {
+                const lineNumber = index + 1; // Line numbers start at 1
+                const escapedLine = escapeHtml(line);
+                const color = lineStyles[lineNumber];
+
+                if (color) {
+                    // Wrap the line in a span with inline style
+                    return `<span style="background-color: ${color}">${escapedLine}</span>`;
+                } else {
+                    return escapedLine;
+                }
+            });
+
+            // Join the lines back together
+            const newContent = processedLines.join('\n');
+
+            // Set the new content as HTML
+            $pre.html(newContent);
+        });
+    };
+    $.fn.miniTabs = function (tabsConfig, options) {
+        const settings = {
+            tabClass: 'minitab',
+            tabsContainerClass: 'minitabs',
+            activeClass: 'active',
+            ...(options || {})
+        };
+
+        return this.each(function () {
+            const $wrapper = $(this);
+            const $contents = $wrapper.find('div[id]').hide();
+            const $tabsContainer = $('<div>', {class: settings.tabsContainerClass}).prependTo($wrapper);
+
+            // Generate tabs
+            Object.entries(tabsConfig).forEach(([tabTitle, contentSelector], index) => {
+                const $content = $wrapper.find(contentSelector);
+                if (index === 0) $content.show(); // Show first content by default
+
+                $('<a>', {
+                    class: `${settings.tabClass}${index === 0 ? ` ${settings.activeClass}` : ''}`,
+                    text: tabTitle,
+                    'data-target': contentSelector
+                }).appendTo($tabsContainer);
+            });
+
+            // Tab click event
+            $tabsContainer.on('click', `.${settings.tabClass}`, function (e) {
+                e.preventDefault();
+                const $tab = $(this);
+                const target = $tab.data('target');
+
+                // Update active tab
+                $tabsContainer.find(`.${settings.tabClass}`).removeClass(settings.activeClass);
+                $tab.addClass(settings.activeClass);
+
+                // Show/hide content
+                $contents.hide();
+                $wrapper.find(target).show();
+            });
+        });
+    };
+
+    // 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);

changedetectionio/static/js/preview.js

@@ -1,53 +1,63 @@
-function redirect_to_version(version) {
-    var currentUrl = window.location.href;
-    var baseUrl = currentUrl.split('?')[0]; // Base URL without query parameters
+function redirectToVersion(version) {
+    var currentUrl = window.location.href.split('?')[0]; // Base URL without query parameters
     var anchor = '';
 
     // Check if there is an anchor
-    if (baseUrl.indexOf('#') !== -1) {
-        anchor = baseUrl.substring(baseUrl.indexOf('#'));
-        baseUrl = baseUrl.substring(0, baseUrl.indexOf('#'));
+    if (currentUrl.indexOf('#') !== -1) {
+        anchor = currentUrl.substring(currentUrl.indexOf('#'));
+        currentUrl = currentUrl.substring(0, currentUrl.indexOf('#'));
     }
-    window.location.href = baseUrl + '?version=' + version + anchor;
+
+    window.location.href = currentUrl + '?version=' + version + anchor;
 }
 
-document.addEventListener('keydown', function (event) {
-    var selectElement = document.getElementById('preview-version');
-    if (selectElement) {
-        var selectedOption = selectElement.querySelector('option:checked');
-        if (selectedOption) {
-            if (event.key === 'ArrowLeft') {
-                if (selectedOption.previousElementSibling) {
-                    redirect_to_version(selectedOption.previousElementSibling.value);
-                }
-            } else if (event.key === 'ArrowRight') {
-                if (selectedOption.nextElementSibling) {
-                    redirect_to_version(selectedOption.nextElementSibling.value);
-                }
+function setupDateWidget() {
+    $(document).on('keydown', function (event) {
+        var $selectElement = $('#preview-version');
+        var $selectedOption = $selectElement.find('option:selected');
+
+        if ($selectedOption.length) {
+            if (event.key === 'ArrowLeft' && $selectedOption.prev().length) {
+                redirectToVersion($selectedOption.prev().val());
+            } else if (event.key === 'ArrowRight' && $selectedOption.next().length) {
+                redirectToVersion($selectedOption.next().val());
             }
         }
-    }
-});
+    });
 
+    $('#preview-version').on('change', function () {
+        redirectToVersion($(this).val());
+    });
 
-document.getElementById('preview-version').addEventListener('change', function () {
-    redirect_to_version(this.value);
-});
+    var $selectedOption = $('#preview-version option:selected');
 
-var selectElement = document.getElementById('preview-version');
-if (selectElement) {
-    var selectedOption = selectElement.querySelector('option:checked');
-    if (selectedOption) {
-        if (selectedOption.previousElementSibling) {
-            document.getElementById('btn-previous').href = "?version=" + selectedOption.previousElementSibling.value;
+    if ($selectedOption.length) {
+        var $prevOption = $selectedOption.prev();
+        var $nextOption = $selectedOption.next();
+
+        if ($prevOption.length) {
+            $('#btn-previous').attr('href', '?version=' + $prevOption.val());
         } else {
-            document.getElementById('btn-previous').remove()
-        }
-        if (selectedOption.nextElementSibling) {
-            document.getElementById('btn-next').href = "?version=" + selectedOption.nextElementSibling.value;
-        } else {
-            document.getElementById('btn-next').remove()
+            $('#btn-previous').remove();
         }
 
+        if ($nextOption.length) {
+            $('#btn-next').attr('href', '?version=' + $nextOption.val());
+        } else {
+            $('#btn-next').remove();
+        }
     }
 }
+
+$(document).ready(function () {
+    if ($('#preview-version').length) {
+        setupDateWidget();
+    }
+
+    $('#diff-col > pre').highlightLines([
+        {
+            'color': '#ee0000',
+            'lines': triggered_line_numbers
+        }
+    ]);
+});

changedetectionio/static/js/toggle-theme.js

@@ -49,4 +49,9 @@ $(document).ready(function () {
         $("#overlay").toggleClass('visible');
         heartpath.style.fill = document.getElementById("overlay").classList.contains("visible") ? '#ff0000' : 'var(--color-background)';
     });
+
+    setInterval(function () {
+        $('body').toggleClass('spinner-active', $.active > 0);
+    }, 2000);
+
 });

changedetectionio/static/js/watch-settings.js

@@ -12,6 +12,51 @@ function toggleOpacity(checkboxSelector, fieldSelector, inverted) {
     checkbox.addEventListener('change', updateOpacity);
 }
 
+
+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() : false) : $element.val();
+    });
+
+    $('body').toggleClass('spinner-active', 1);
+
+    $.abortiveSingularAjax({
+        type: "POST",
+        url: preview_text_edit_filters_url,
+        data: data,
+        namespace: 'watchEdit'
+    }).done(function (data) {
+        console.debug(data['duration'])
+        $('#filters-and-triggers #text-preview-before-inner').text(data['before_filter']);
+        $('#filters-and-triggers #text-preview-inner')
+            .text(data['after_filter'])
+            .highlightLines([
+                {
+                    'color': '#ee0000',
+                    'lines': data['trigger_line_numbers']
+                },
+                {
+                    'color': '#757575',
+                    'lines': data['ignore_line_numbers']
+                }
+            ])
+    }).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 +72,21 @@ $(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");
+    $("#text-preview-before-inner").css('max-height', (vh-300)+"px");
+
+    $("#activate-text-preview").click(function (e) {
+        $('body').toggleClass('preview-text-enabled')
+        request_textpreview_update();
+        const method = $('body').hasClass('preview-text-enabled') ? 'on' : 'off';
+        $('#filters-and-triggers textarea')[method]('blur', request_textpreview_update.throttle(1000));
+        $('#filters-and-triggers input')[method]('change', request_textpreview_update.throttle(1000));
+        $("#filters-and-triggers-tab")[method]('click', request_textpreview_update.throttle(1000));
+    });
+    $('.minitabs-wrapper').miniTabs({
+        "Content after filters": "#text-preview-inner",
+        "Content raw/before filters": "#text-preview-before-inner"
+    });
 });
 

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/_minitabs.scss

@@ -0,0 +1,47 @@
+.minitabs-wrapper {
+  width: 100%;
+
+  > div[id] {
+    padding: 20px;
+    border: 1px solid #ccc;
+    border-top: none;
+  }
+
+  .minitabs-content {
+    width: 100%;
+    display: flex;
+    > div {
+      flex: 1 1 auto;
+      min-width: 0;
+      overflow: scroll;
+    }
+  }
+
+  .minitabs {
+    display: flex;
+    border-bottom: 1px solid #ccc;
+  }
+
+  .minitab {
+    flex: 1;
+    text-align: center;
+    padding: 12px 0;
+    text-decoration: none;
+    color: #333;
+    background-color: #f1f1f1;
+    border: 1px solid #ccc;
+    border-bottom: none;
+    cursor: pointer;
+    transition: background-color 0.3s;
+  }
+
+  .minitab:hover {
+    background-color: #ddd;
+  }
+
+  .minitab.active {
+    background-color: #fff;
+    font-weight: bold;
+  }
+
+}

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

@@ -0,0 +1,55 @@
+@import "minitabs";
+
+body.preview-text-enabled {
+
+  @media (min-width: 800px) {
+    #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: 20px;
+    padding-top: 1rem;
+    padding-bottom: 1rem;
+    display: block !important;
+  }
+
+  #activate-text-preview {
+      background-color: var(--color-grey-500);
+  }
+
+  /* actual preview area */
+  .monospace-preview {
+    background: var(--color-background-input);
+    border: 1px solid var(--color-grey-600);
+    padding: 1rem;
+    color: var(--color-text-input);
+    font-family: "Courier New", Courier, monospace; /* Sets the font to a monospace type */
+    font-size: 70%;
+    word-break: break-word;
+    white-space: pre-wrap; /* Preserves whitespace and line breaks like <pre> */
+  }
+}
+
+#activate-text-preview {
+  right: 0;
+  position: absolute;
+  z-index: 3;
+  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);
@@ -105,10 +106,34 @@ button.toggle-button {
   padding: 5px;
   display: flex;
   justify-content: space-between;
-  border-bottom: 2px solid var(--color-menu-accent);
   align-items: center;
 }
 
+#pure-menu-horizontal-spinner {
+  height: 3px;
+  background: linear-gradient(-75deg, #ff6000, #ff8f00, #ffdd00, #ed0000);
+  background-size: 400% 400%;
+  width: 100%;
+  animation: gradient 200s ease infinite;
+}
+
+body.spinner-active {
+  #pure-menu-horizontal-spinner {
+    animation: gradient 1s ease infinite;
+  }
+}
+
+@keyframes gradient {
+	0% {
+		background-position: 0% 50%;
+	}
+	50% {
+		background-position: 100% 50%;
+	}
+	100% {
+		background-position: 0% 50%;
+	}
+}
 .pure-menu-heading {
   color: var(--color-text-menu-heading);
 }
@@ -320,10 +345,6 @@ a.pure-button-selected {
   background: var(--color-background-button-cancel);
 }
 
-#save_button {
-  margin-right: 1rem;
-}
-
 .messages {
   li {
     list-style: none;
@@ -620,9 +641,9 @@ footer {
       list-style: none;
 
       li {
-        >* {
-          display: inline-block;
-        }
+        display: flex;
+        align-items: center;
+        gap: 1em;
       }
     }
   }
@@ -682,6 +703,12 @@ footer {
       tr {
         th {
           display: inline-block;
+          // Hide the "Last" text for smaller screens
+          @media (max-width: 768px) {
+            .hide-on-mobile {
+              display: none; 
+            }
+          }
         }
       }
       .empty-cell {
@@ -697,6 +724,24 @@ footer {
       }
     }
 
+    tbody {
+      tr {
+        display: flex;
+        flex-wrap: wrap;
+
+        // The third child of each row will take up the remaining space
+        // This is useful for the URL column, which should expand to fill the remaining space
+        :nth-child(3) {
+          flex-grow: 1;
+        }
+        // The last three children (from the end) of each row will take up the full width
+        // This is useful for the "Last Checked", "Last Changed", and the action buttons columns, which should each take up the full width
+        :nth-last-child(-n+3) {
+          flex-basis: 100%;
+        }
+      }
+    }
+
     .last-checked {
       >span {
         vertical-align: middle;
@@ -815,6 +860,11 @@ textarea::placeholder {
 - We dont use 'size' with <input> because `size` is too unreliable to override, and will often push-out
 - Rely always on width in CSS
 */
+/** Set max width for input field */
+.m-d {
+  min-width: 100%;
+}
+
 @media only screen and (min-width: 761px) {
 
   /* m-d is medium-desktop */
@@ -930,6 +980,13 @@ body.full-width {
     background: var(--color-background);
   }
 
+  /* Make action buttons have consistent size and spacing */
+  #actions .pure-control-group {
+    display: flex;
+    gap: 0.625em;
+    flex-wrap: wrap;
+  }
+
   .pure-form-message-inline {
     padding-left: 0;
     color: var(--color-text-input-description);
@@ -973,6 +1030,28 @@ ul {
   }
 }
 
+@media only screen and (max-width: 760px) {
+  .time-check-widget {
+    tbody {
+      display: grid;
+      grid-template-columns: auto 1fr auto 1fr;
+      gap: 0.625em 0.3125em;
+      align-items: center;
+    }    
+    tr {
+      display: contents; 
+      th {
+        text-align: right;
+        padding-right: 5px;
+      }
+      input[type="number"] {
+        width: 100%;
+        max-width: 5em;
+      }
+    }
+  }
+}
+
 @import "parts/_visualselector";
 
 #webdriver_delay {

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 +428,83 @@ html[data-darkmode="true"] #toggle-light-mode .icon-dark {
     fill: #ff0000 !important;
     transition: all ease 0.3s !important; }
 
+.minitabs-wrapper {
+  width: 100%; }
+  .minitabs-wrapper > div[id] {
+    padding: 20px;
+    border: 1px solid #ccc;
+    border-top: none; }
+  .minitabs-wrapper .minitabs-content {
+    width: 100%;
+    display: flex; }
+    .minitabs-wrapper .minitabs-content > div {
+      flex: 1 1 auto;
+      min-width: 0;
+      overflow: scroll; }
+  .minitabs-wrapper .minitabs {
+    display: flex;
+    border-bottom: 1px solid #ccc; }
+  .minitabs-wrapper .minitab {
+    flex: 1;
+    text-align: center;
+    padding: 12px 0;
+    text-decoration: none;
+    color: #333;
+    background-color: #f1f1f1;
+    border: 1px solid #ccc;
+    border-bottom: none;
+    cursor: pointer;
+    transition: background-color 0.3s; }
+  .minitabs-wrapper .minitab:hover {
+    background-color: #ddd; }
+  .minitabs-wrapper .minitab.active {
+    background-color: #fff;
+    font-weight: bold; }
+
+body.preview-text-enabled {
+  /* layout of the page */
+  /* actual preview area */ }
+  @media (min-width: 800px) {
+    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: 20px;
+    padding-top: 1rem;
+    padding-bottom: 1rem;
+    display: block !important; }
+  body.preview-text-enabled #activate-text-preview {
+    background-color: var(--color-grey-500); }
+  body.preview-text-enabled .monospace-preview {
+    background: var(--color-background-input);
+    border: 1px solid var(--color-grey-600);
+    padding: 1rem;
+    color: var(--color-text-input);
+    font-family: "Courier New", Courier, monospace;
+    /* Sets the font to a monospace type */
+    font-size: 70%;
+    word-break: break-word;
+    white-space: pre-wrap;
+    /* Preserves whitespace and line breaks like <pre> */ }
+
+#activate-text-preview {
+  right: 0;
+  position: absolute;
+  z-index: 3;
+  box-shadow: 1px 1px 4px var(--color-shadow-jump); }
+
 body {
   color: var(--color-text);
   background: var(--color-background-page);
@@ -479,9 +573,26 @@ button.toggle-button {
   padding: 5px;
   display: flex;
   justify-content: space-between;
-  border-bottom: 2px solid var(--color-menu-accent);
   align-items: center; }
 
+#pure-menu-horizontal-spinner {
+  height: 3px;
+  background: linear-gradient(-75deg, #ff6000, #ff8f00, #ffdd00, #ed0000);
+  background-size: 400% 400%;
+  width: 100%;
+  animation: gradient 200s ease infinite; }
+
+body.spinner-active #pure-menu-horizontal-spinner {
+  animation: gradient 1s ease infinite; }
+
+@keyframes gradient {
+  0% {
+    background-position: 0% 50%; }
+  50% {
+    background-position: 100% 50%; }
+  100% {
+    background-position: 0% 50%; } }
+
 .pure-menu-heading {
   color: var(--color-text-menu-heading); }
 
@@ -634,9 +745,6 @@ a.pure-button-selected {
 .button-cancel {
   background: var(--color-background-button-cancel); }
 
-#save_button {
-  margin-right: 1rem; }
-
 .messages li {
   list-style: none;
   padding: 1em;
@@ -835,8 +943,10 @@ footer {
   .pure-form .inline-radio ul {
     margin: 0px;
     list-style: none; }
-    .pure-form .inline-radio ul li > * {
-      display: inline-block; }
+    .pure-form .inline-radio ul li {
+      display: flex;
+      align-items: center;
+      gap: 1em; }
 
 @media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 1024px) {
   .box {
@@ -872,12 +982,24 @@ footer {
     .watch-table thead {
       display: block; }
       .watch-table thead tr th {
-        display: inline-block; }
+        display: inline-block; } }
+      @media only screen and (max-width: 760px) and (max-width: 768px), (min-device-width: 768px) and (max-device-width: 800px) and (max-width: 768px) {
+        .watch-table thead tr th .hide-on-mobile {
+          display: none; } }
+
+@media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 800px) {
       .watch-table thead .empty-cell {
         display: none; }
     .watch-table tbody td,
     .watch-table tbody tr {
       display: block; }
+    .watch-table tbody tr {
+      display: flex;
+      flex-wrap: wrap; }
+      .watch-table tbody tr :nth-child(3) {
+        flex-grow: 1; }
+      .watch-table tbody tr :nth-last-child(-n+3) {
+        flex-basis: 100%; }
     .watch-table .last-checked > span {
       vertical-align: middle; }
     .watch-table .last-checked::before {
@@ -969,6 +1091,10 @@ textarea::placeholder {
 - We dont use 'size' with <input> because `size` is too unreliable to override, and will often push-out
 - Rely always on width in CSS
 */
+/** Set max width for input field */
+.m-d {
+  min-width: 100%; }
+
 @media only screen and (min-width: 761px) {
   /* m-d is medium-desktop */
   .m-d {
@@ -1029,7 +1155,8 @@ body.full-width .edit-form {
 .edit-form {
   min-width: 70%;
   /* so it cant overflow */
-  max-width: 95%; }
+  max-width: 95%;
+  /* Make action buttons have consistent size and spacing */ }
   .edit-form .box-wrap {
     position: relative; }
   .edit-form .inner {
@@ -1038,6 +1165,10 @@ body.full-width .edit-form {
   .edit-form #actions {
     display: block;
     background: var(--color-background); }
+  .edit-form #actions .pure-control-group {
+    display: flex;
+    gap: 0.625em;
+    flex-wrap: wrap; }
   .edit-form .pure-form-message-inline {
     padding-left: 0;
     color: var(--color-text-input-description); }
@@ -1066,6 +1197,21 @@ ul {
   .time-check-widget tr input[type="number"] {
     width: 5em; }
 
+@media only screen and (max-width: 760px) {
+  .time-check-widget tbody {
+    display: grid;
+    grid-template-columns: auto 1fr auto 1fr;
+    gap: 0.625em 0.3125em;
+    align-items: center; }
+  .time-check-widget tr {
+    display: contents; }
+    .time-check-widget tr th {
+      text-align: right;
+      padding-right: 5px; }
+    .time-check-widget tr input[type="number"] {
+      width: 100%;
+      max-width: 5em; } }
+
 #selector-wrapper {
   height: 100%;
   text-align: center;
@@ -1194,11 +1340,9 @@ 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/store.py

@@ -4,6 +4,7 @@ from flask import (
     flash
 )
 
+from .html_tools import TRANSLATE_WHITESPACE_TABLE
 from . model import App, Watch
 from copy import deepcopy, copy
 from os import path, unlink
@@ -750,17 +751,17 @@ class ChangeDetectionStore:
     def update_5(self):
         # If the watch notification body, title look the same as the global one, unset it, so the watch defaults back to using the main settings
         # In other words - the watch notification_title and notification_body are not needed if they are the same as the default one
-        current_system_body = self.data['settings']['application']['notification_body'].translate(str.maketrans('', '', "\r\n "))
-        current_system_title = self.data['settings']['application']['notification_body'].translate(str.maketrans('', '', "\r\n "))
+        current_system_body = self.data['settings']['application']['notification_body'].translate(TRANSLATE_WHITESPACE_TABLE)
+        current_system_title = self.data['settings']['application']['notification_body'].translate(TRANSLATE_WHITESPACE_TABLE)
         for uuid, watch in self.data['watching'].items():
             try:
                 watch_body = watch.get('notification_body', '')
-                if watch_body and watch_body.translate(str.maketrans('', '', "\r\n ")) == current_system_body:
+                if watch_body and watch_body.translate(TRANSLATE_WHITESPACE_TABLE) == current_system_body:
                     # Looks the same as the default one, so unset it
                     watch['notification_body'] = None
 
                 watch_title = watch.get('notification_title', '')
-                if watch_title and watch_title.translate(str.maketrans('', '', "\r\n ")) == current_system_title:
+                if watch_title and watch_title.translate(TRANSLATE_WHITESPACE_TABLE) == current_system_title:
                     # Looks the same as the default one, so unset it
                     watch['notification_title'] = None
             except Exception as e:

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

@@ -33,9 +33,11 @@
     <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">
+    <div class="pure-menu-fixed" style="width: 100%;">
+      <div class="home-menu pure-menu pure-menu-horizontal" id="nav-menu">
+
         {% if has_password and not current_user.is_authenticated %}
           <a class="pure-menu-heading" href="https://changedetection.io" rel="noopener">
             <strong>Change</strong>Detection.io</a>
@@ -129,7 +131,12 @@
           </li>
         </ul>
       </div>
+      <div id="pure-menu-horizontal-spinner"></div>
+      </div>
+
     </div>
+
+
     {% if hosted_sticky %}
       <div class="sticky-tab" id="hosted-sticky">
         <a href="https://changedetection.io/?ref={{guid}}">Let us host your instance!</a>

changedetectionio/templates/edit.html

@@ -24,9 +24,8 @@
     const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
     const default_system_fetch_backend="{{ settings_application['fetch_backend'] }}";
 </script>
-
+<script src="{{url_for('static_content', group='js', filename='plugins.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
-<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
 {% if playwright_enabled %}
@@ -50,7 +49,7 @@
             {% 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 +199,7 @@ 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 +214,7 @@ 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 +253,10 @@ 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 +312,13 @@ 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>
@@ -326,18 +329,25 @@ nav
                         {{ render_checkbox_field(form.filter_text_added) }}
                         {{ render_checkbox_field(form.filter_text_replaced) }}
                         {{ render_checkbox_field(form.filter_text_removed) }}
-                    <span class="pure-form-message-inline">Note: Depending on the length and similarity of the text on each line, the algorithm may consider an <strong>addition</strong> instead of <strong>replacement</strong> for example.</span>
-                    <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>
+                    <span class="pure-form-message-inline">Note: Depending on the length and similarity of the text on each line, the algorithm may consider an <strong>addition</strong> instead of <strong>replacement</strong> for example.</span><br>
+                    <span class="pure-form-message-inline">&nbsp;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">&nbsp;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">
@@ -360,10 +370,10 @@ nav
 ") }}
                     <span class="pure-form-message-inline">
                         <ul>
+                            <li>Matching text will be <strong>ignored</strong> in the text snapshot (you can still see it but it wont trigger a change)</li>
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
                             <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
                             <li>Changing this will affect the comparison checksum which may trigger an alert</li>
-                            <li>Use the preview/show current tab to see ignores</li>
                         </ul>
                 </span>
 
@@ -387,7 +397,9 @@ Unavailable") }}
                 </fieldset>
                 <fieldset>
                     <div class="pure-control-group">
-                        {{ render_field(form.extract_text, rows=5, placeholder="\d+ online") }}
+                        {{ render_field(form.extract_text, rows=5, placeholder="/.+?\d+ comments.+?/
+ or
+keyword") }}
                         <span class="pure-form-message-inline">
                     <ul>
                         <li>Extracts text in the final output (line by line) after other filters using regular expressions or string match;
@@ -407,7 +419,27 @@ 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>
+                    <br>
+                    {#<div id="text-preview-controls"><span id="text-preview-refresh" class="pure-button button-xsmall">Refresh</span></div>#}
+                    <div class="minitabs-wrapper">
+                      <div class="minitabs-content">
+                          <div id="text-preview-inner" class="monospace-preview">
+                              <p>Loading...</p>
+                          </div>
+                          <div id="text-preview-before-inner" style="display: none;" class="monospace-preview">
+                              <p>Loading...</p>
+                          </div>
+                      </div>
+                    </div>
+            </div>
+          </div>
+        </div>
+
+        {% endif %}
         {# rendered sub Template #}
         {% if extra_form_content %}
             <div class="tab-pane-inner" id="extras_tab">

changedetectionio/templates/preview.html

@@ -3,11 +3,13 @@
 {% block content %}
     <script>
         const screenshot_url = "{{url_for('static_content', group='screenshot', filename=uuid)}}";
+        const triggered_line_numbers = {{ triggered_line_numbers|tojson }};
         {% if last_error_screenshot %}
             const error_screenshot_url = "{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
         {% endif %}
         const highlight_submit_ignore_url = "{{url_for('highlight_submit_ignore_url', uuid=uuid)}}";
     </script>
+    <script src="{{url_for('static_content', group='js', filename='plugins.js')}}"></script>
     <script src="{{ url_for('static_content', group='js', filename='diff-overview.js') }}" defer></script>
     <script src="{{ url_for('static_content', group='js', filename='preview.js') }}" defer></script>
     <script src="{{ url_for('static_content', group='js', filename='tabs.js') }}" defer></script>
@@ -67,16 +69,15 @@
 
         <div class="tab-pane-inner" id="text">
             <div class="snapshot-age">{{ current_version|format_timestamp_timeago }}</div>
-            <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span>
             <span class="tip"><strong>Pro-tip</strong>: Highlight text to add to ignore filters</span>
 
             <table>
                 <tbody>
                 <tr>
                     <td id="diff-col" class="highlightable-filter">
-                        {% for row in content %}
-                            <div class="{{ row.classes }}">{{ row.line }}</div>
-                        {% endfor %}
+                        <pre style="border-left: 2px solid #ddd;">
+{{ content }}
+                        </pre>
                     </td>
                 </tr>
                 </tbody>

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>
@@ -170,11 +172,11 @@ nav
                     <span class="pure-form-message-inline">Note: This is applied globally in addition to the per-watch rules.</span><br>
                     <span class="pure-form-message-inline">
                         <ul>
+                            <li>Matching text will be <strong>ignored</strong> in the text snapshot (you can still see it but it wont trigger a change)</li>
                             <li>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>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>
                      </span>
                     </fieldset>

changedetectionio/templates/watch-overview.html

@@ -78,8 +78,8 @@
              {% if any_has_restock_price_processor %}
                 <th>Restock &amp; Price</th>
              {% endif %}
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag_uuid)}}">Last Checked <span class='arrow {{link_order}}'></span></a></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag_uuid)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag_uuid)}}"><span class="hide-on-mobile">Last</span> Checked <span class='arrow {{link_order}}'></span></a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag_uuid)}}"><span class="hide-on-mobile">Last</span> Changed <span class='arrow {{link_order}}'></span></a></th>
                 <th class="empty-cell"></th>
             </tr>
             </thead>
@@ -191,9 +191,9 @@
                     {% if watch.history_n >= 2 %}
 
                         {%  if is_unviewed %}
-                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid, from_version=watch.get_next_snapshot_key_to_last_viewed) }}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid, from_version=watch.get_next_snapshot_key_to_last_viewed) }}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">History</a>
                         {% else %}
-                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">History</a>
                         {% endif %}
 
                     {% else %}

changedetectionio/tests/proxy_list/test_select_custom_proxy.py

@@ -44,7 +44,7 @@ def test_select_custom(client, live_server, measure_memory_usage):
         follow_redirects=True
     )
     # We should see something via proxy
-    assert b'<div class=""> - 0.' in res.data
+    assert b' - 0.' in res.data
 
     #
     # Now we should see the request in the container logs for "squid-squid-custom" because it will be the only default

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_add_replace_remove_filter.py

@@ -39,9 +39,8 @@ def test_setup(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
 
 def test_check_removed_line_contains_trigger(client, live_server, measure_memory_usage):
-
+    #live_server_setup(live_server)
     # Give the endpoint time to spin up
-    time.sleep(1)
     set_original()
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
@@ -152,7 +151,9 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
 
     # A line thats not the trigger should not trigger anything
     res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     assert b'1 watches queued for rechecking.' in res.data
+
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' not 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_extract_regex.py

@@ -71,7 +71,7 @@ def test_setup(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
 
 def test_check_filter_multiline(client, live_server, measure_memory_usage):
-    #live_server_setup(live_server)
+   # live_server_setup(live_server)
     set_multiline_response()
 
     # Add our URL to the import page
@@ -115,9 +115,9 @@ def test_check_filter_multiline(client, live_server, measure_memory_usage):
     # Plaintext that doesnt look like a regex should match also
     assert b'and this should be' in res.data
 
-    assert b'<div class="">Something' in res.data
-    assert b'<div class="">across 6 billion multiple' in res.data
-    assert b'<div class="">lines' in res.data
+    assert b'Something' in res.data
+    assert b'across 6 billion multiple' in res.data
+    assert b'lines' in res.data
 
     # but the last one, which also says 'lines' shouldnt be here (non-greedy match checking)
     assert b'aaand something lines' not in res.data
@@ -183,20 +183,19 @@ def test_check_filter_and_regex_extract(client, live_server, measure_memory_usag
         follow_redirects=True
     )
 
-    # Class will be blank for now because the frontend didnt apply the diff
-    assert b'<div class="">1000 online' in res.data
+    assert b'1000 online' in res.data
 
     # All regex matching should be here
-    assert b'<div class="">2000 online' in res.data
+    assert b'2000 online' in res.data
 
     # Both regexs should be here
-    assert b'<div class="">80 guests' in res.data
+    assert b'80 guests' in res.data
 
     # Regex with flag handling should be here
-    assert b'<div class="">SomeCase insensitive 3456' in res.data
+    assert b'SomeCase insensitive 3456' in res.data
 
     # Singular group from /somecase insensitive (345\d)/i
-    assert b'<div class="">3456' in res.data
+    assert b'3456' in res.data
 
     # Regex with multiline flag handling should be here
 

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_ignore.py

@@ -23,7 +23,7 @@ def set_original_ignore_response():
         f.write(test_return_data)
 
 
-def test_highlight_ignore(client, live_server, measure_memory_usage):
+def test_ignore(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
     set_original_ignore_response()
     test_url = url_for('test_endpoint', _external=True)
@@ -51,9 +51,9 @@ def test_highlight_ignore(client, live_server, measure_memory_usage):
     # Should return a link
     assert b'href' in res.data
 
-    # And it should register in the preview page
+    # It should not be in the preview anymore
     res = client.get(url_for("preview_page", uuid=uuid))
-    assert b'<div class="ignored">oh yeah 456' in res.data
+    assert b'<div class="ignored">oh yeah 456' not in res.data
 
     # Should be in base.html
     assert b'csrftoken' in res.data

changedetectionio/tests/test_ignore_regex_text.py

@@ -33,13 +33,17 @@ def test_strip_regex_text_func():
 
     stripped_content = html_tools.strip_ignore_text(test_content, ignore_lines)
 
-    assert b"but 1 lines" in stripped_content
-    assert b"igNORe-cAse text" not in stripped_content
-    assert b"but 1234 lines" not in stripped_content
-    assert b"really" not in stripped_content
-    assert b"not this" not in stripped_content
+    assert "but 1 lines" in stripped_content
+    assert "igNORe-cAse text" not in stripped_content
+    assert "but 1234 lines" not in stripped_content
+    assert "really" not in stripped_content
+    assert "not this" not in stripped_content
 
     # Check line number reporting
     stripped_content = html_tools.strip_ignore_text(test_content, ignore_lines, mode="line numbers")
     assert stripped_content == [2, 5, 6, 7, 8, 10]
 
+    # Check that linefeeds are preserved when there are is no matching ignores
+    content = "some text\n\nand other text\n"
+    stripped_content = html_tools.strip_ignore_text(content, ignore_lines)
+    assert content == stripped_content

changedetectionio/tests/test_ignore_text.py

@@ -22,10 +22,15 @@ def test_strip_text_func():
     ignore_lines = ["sometimes"]
 
     stripped_content = html_tools.strip_ignore_text(test_content, ignore_lines)
+    assert "sometimes" not in stripped_content
+    assert "Some content" in stripped_content
 
-    assert b"sometimes" not in stripped_content
-    assert b"Some content" in stripped_content
+    # Check that line feeds dont get chewed up when something is found
+    test_content = "Some initial text\n\nWhich is across multiple lines\n\nZZZZz\n\n\nSo let's see what happens."
+    ignore = ['something irrelevent but just to check', 'XXXXX', 'YYYYY', 'ZZZZZ']
 
+    stripped_content = html_tools.strip_ignore_text(test_content, ignore)
+    assert stripped_content == "Some initial text\n\nWhich is across multiple lines\n\n\n\nSo let's see what happens."
 
 def set_original_ignore_response():
     test_return_data = """<html>
@@ -79,14 +84,14 @@ def set_modified_ignore_response():
         f.write(test_return_data)
 
 
+# Ignore text now just removes it entirely, is a LOT more simpler code this way
+
 def test_check_ignore_text_functionality(client, live_server, measure_memory_usage):
 
     # Use a mix of case in ZzZ to prove it works case-insensitive.
     ignore_text = "XXXXX\r\nYYYYY\r\nzZzZZ\r\nnew ignore stuff"
     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)
@@ -141,8 +146,6 @@ def test_check_ignore_text_functionality(client, live_server, measure_memory_usa
 
 
 
-
-
     # Just to be sure.. set a regular modified change..
     set_modified_original_ignore_response()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
@@ -151,21 +154,19 @@ def test_check_ignore_text_functionality(client, live_server, measure_memory_usa
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
-    # Check the preview/highlighter, we should be able to see what we ignored, but it should be highlighted
-    # We only introduce the "modified" content that includes what we ignore so we can prove the newest version also displays
-    # at /preview
     res = client.get(url_for("preview_page", uuid="first"))
-    # We should be able to see what we ignored
-    assert b'<div class="ignored">new ignore stuff' in res.data
+
+    # SHOULD BE be in the preview, it was added in set_modified_original_ignore_response()
+    # and we have "new ignore stuff" in ignore_text
+    # it is only ignored, it is not removed (it will be highlighted too)
+    assert b'new ignore stuff' in res.data
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
+# When adding some ignore text, it should not trigger a change, even if something else on that line changes
 def test_check_global_ignore_text_functionality(client, live_server, measure_memory_usage):
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
+    #live_server_setup(live_server)
     ignore_text = "XXXXX\r\nYYYYY\r\nZZZZZ"
     set_original_ignore_response()
 
@@ -174,6 +175,7 @@ def test_check_global_ignore_text_functionality(client, live_server, measure_mem
         url_for("settings_page"),
         data={
             "requests-time_between_check-minutes": 180,
+            "application-ignore_whitespace": "y",
             "application-global_ignore_text": ignore_text,
             'application-fetch_backend': "html_requests"
         },
@@ -194,9 +196,7 @@ def test_check_global_ignore_text_functionality(client, live_server, measure_mem
     # Give the thread time to pick it up
     wait_for_all_checks(client)
 
-
-    # Goto the edit page of the item, add our ignore text
-    # Add our URL to the import page
+    #Adding some ignore text should not trigger a change
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={"ignore_text": "something irrelevent but just to check", "url": test_url, 'fetch_backend': "html_requests"},
@@ -212,20 +212,15 @@ def test_check_global_ignore_text_functionality(client, live_server, measure_mem
 
     # 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)
-
-    # so that we are sure everything is viewed and in a known 'nothing changed' state
-    res = client.get(url_for("diff_history_page", uuid="first"))
-
-    # It should report nothing found (no new 'unviewed' class)
+    # It should report nothing found (no new 'unviewed' class), adding random ignore text should not cause a change
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
     assert b'/test-endpoint' in res.data
+#####
 
-
-    #  Make a change which includes the ignore text
+    # Make a change which includes the ignore text, it should be ignored and no 'change' triggered
+    # It adds text with "ZZZZzzzz" and "ZZZZ" is in the ignore list
     set_modified_ignore_response()
 
     # Trigger a check
@@ -235,6 +230,7 @@ def test_check_global_ignore_text_functionality(client, live_server, measure_mem
 
     # It should report nothing found (no new 'unviewed' class)
     res = client.get(url_for("index"))
+
     assert b'unviewed' not in res.data
     assert b'/test-endpoint' in res.data
 

changedetectionio/tests/test_jsonpath_jq_selector.py

@@ -499,7 +499,7 @@ def test_correct_header_detect(client, live_server, measure_memory_usage):
     )
 
     assert b'"hello": 123,' in res.data
-    assert b'&#34;world&#34;: 123</div>' in res.data
+    assert b'&#34;world&#34;: 123' in res.data
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/test_trigger.py

@@ -2,7 +2,7 @@
 
 import time
 from flask import url_for
-from . util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
 
 
 def set_original_ignore_response():
@@ -59,12 +59,9 @@ def test_trigger_functionality(client, live_server, measure_memory_usage):
 
     live_server_setup(live_server)
 
-    sleep_time_for_fetch_thread = 3
     trigger_text = "Add to cart"
     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)
@@ -89,14 +86,14 @@ def test_trigger_functionality(client, live_server, measure_memory_usage):
     )
     assert b"Updated watch." in res.data
 
+    wait_for_all_checks(client)
     # Check it saved
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
     assert bytes(trigger_text.encode('utf-8')) in res.data
 
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+
     
     # so that we set the state to 'unviewed' after all the edits
     client.get(url_for("diff_history_page", uuid="first"))
@@ -104,8 +101,7 @@ def test_trigger_functionality(client, live_server, measure_memory_usage):
     # 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)
+    wait_for_all_checks(client)
 
     # It should report nothing found (no new 'unviewed' class)
     res = client.get(url_for("index"))
@@ -117,19 +113,17 @@ def test_trigger_functionality(client, live_server, measure_memory_usage):
 
     # 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)
+    wait_for_all_checks(client)
 
     # 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 trigger text
-    time.sleep(sleep_time_for_fetch_thread)
     set_modified_with_trigger_text_response()
 
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
     
@@ -142,4 +136,7 @@ def test_trigger_functionality(client, live_server, measure_memory_usage):
     res = client.get(url_for("preview_page", uuid="first"))
 
     # We should be able to see what we triggered on
-    assert b'<div class="triggered">Add to cart' in res.data
+    # The JS highlighter should tell us which lines (also used in the live-preview)
+    assert b'const triggered_line_numbers = [6]' in res.data
+    assert b'Add to cart' in res.data
+

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/test_xpath_selector.py

@@ -161,8 +161,8 @@ def test_check_xpath_text_function_utf8(client, live_server, measure_memory_usag
         follow_redirects=True
     )
 
-    assert b'<div class="">Stock Alert (UK): RPi CM4' in res.data
-    assert b'<div class="">Stock Alert (UK): Big monitor' in res.data
+    assert b'Stock Alert (UK): RPi CM4' in res.data
+    assert b'Stock Alert (UK): Big monitor' in res.data
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/unit/test_watch_model.py

@@ -18,12 +18,13 @@ class TestDiffBuilder(unittest.TestCase):
 
         watch['last_viewed'] = 110
 
-        watch.save_history_text(contents=b"hello world", timestamp=100, snapshot_id=str(uuid_builder.uuid4()))
-        watch.save_history_text(contents=b"hello world", timestamp=105, snapshot_id=str(uuid_builder.uuid4()))
-        watch.save_history_text(contents=b"hello world", timestamp=109, snapshot_id=str(uuid_builder.uuid4()))
-        watch.save_history_text(contents=b"hello world", timestamp=112, snapshot_id=str(uuid_builder.uuid4()))
-        watch.save_history_text(contents=b"hello world", timestamp=115, snapshot_id=str(uuid_builder.uuid4()))
-        watch.save_history_text(contents=b"hello world", timestamp=117, snapshot_id=str(uuid_builder.uuid4()))
+        # Contents from the browser are always returned from the browser/requests/etc as str, str is basically UTF-16 in python
+        watch.save_history_text(contents="hello world", timestamp=100, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents="hello world", timestamp=105, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents="hello world", timestamp=109, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents="hello world", timestamp=112, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents="hello world", timestamp=115, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents="hello world", timestamp=117, snapshot_id=str(uuid_builder.uuid4()))
 
         p = watch.get_next_snapshot_key_to_last_viewed
         assert p == "112", "Correct last-viewed timestamp was detected"

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

@@ -286,8 +286,8 @@ class update_worker(threading.Thread):
                         # Re #342
                         # In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.
                         # We then convert/.decode('utf-8') for the notification etc
-                        if not isinstance(contents, (bytes, bytearray)):
-                            raise Exception("Error - returned data from the fetch handler SHOULD be bytes")
+#                        if not isinstance(contents, (bytes, bytearray)):
+#                            raise Exception("Error - returned data from the fetch handler SHOULD be bytes")
                     except PermissionError as e:
                         logger.critical(f"File permission error updating file, watch: {uuid}")
                         logger.critical(str(e))
@@ -338,7 +338,8 @@ class update_worker(threading.Thread):
                         elif e.status_code == 500:
                             err_text = "Error - 500 (Internal server error) received from the web site"
                         else:
-                            err_text = "Error - Request returned a HTTP error code {}".format(str(e.status_code))
+                            extra = ' (Access denied or blocked)' if str(e.status_code).startswith('4') else ''
+                            err_text = f"Error - Request returned a HTTP error code {e.status_code}{extra}"
 
                         if e.screenshot:
                             watch.save_screenshot(screenshot=e.screenshot, as_error=True)
@@ -491,6 +492,8 @@ 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

docker-compose.yml

@@ -58,6 +58,10 @@ services:
   #
   #        Absolute minimum seconds to recheck, overrides any watch minimum, change to 0 to disable
   #      - MINIMUM_SECONDS_RECHECK_TIME=3
+  #
+  #        If you want to watch local files file:///path/to/file.txt (careful! security implications!)
+  #      - ALLOW_FILE_URI=False
+  
       # Comment out ports: when using behind a reverse proxy , enable networks: etc.
       ports:
         - 5000:5000

requirements.txt

@@ -35,7 +35,7 @@ dnspython==2.6.1 # related to eventlet fixes
 # jq not available on Windows so must be installed manually
 
 # Notification library
-apprise~=1.8.1
+apprise==1.9.0
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 # and 2.0.0 https://github.com/dgtlmoon/changedetection.io/issues/2241 not yet compatible
@@ -93,3 +93,5 @@ babel
 
 # Needed for > 3.10, https://github.com/microsoft/playwright-python/issues/2096
 greenlet >= 3.0.3
+
+