More debug around queue size

"Ignore text" is now "Remove text", it works the same but it removes the text instead of ignoring it, which is the same thing, but makes the code simpler

.github/ISSUE_TEMPLATE/bug_report.md

@@ -27,6 +27,10 @@ A clear and concise description of what the bug is.
 **Version**
 *Exact version* in the top right area: 0....
 
+**How did you install?**
+
+Docker, Pip, from source directly etc
+
 **To Reproduce**
 
 Steps to reproduce the behavior:

.gitignore

@@ -10,5 +10,6 @@ dist
 venv
 test-datastore/*
 test-datastore
+test-memory.log
 *.egg-info*
 .vscode/settings.json

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 \

MANIFEST.in

@@ -1,4 +1,5 @@
 recursive-include changedetectionio/api *
+recursive-include changedetectionio/apprise_plugin *
 recursive-include changedetectionio/blueprint *
 recursive-include changedetectionio/content_fetchers *
 recursive-include changedetectionio/model *

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.46.01'
+__version__ = '0.47.06'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError

changedetectionio/api/api_v1.py

@@ -58,7 +58,7 @@ class Watch(Resource):
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
 
         if request.args.get('recheck'):
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             return "OK", 200
         if request.args.get('paused', '') == 'paused':
             self.datastore.data['watching'].get(uuid).pause()
@@ -246,7 +246,7 @@ class CreateWatch(Resource):
 
         new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags)
         if new_uuid:
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
+            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
             return {'uuid': new_uuid}, 201
         else:
             return "Invalid or unsupported URL", 400
@@ -303,7 +303,7 @@ class CreateWatch(Resource):
 
         if request.args.get('recheck_all'):
             for uuid in self.datastore.data['watching'].keys():
-                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             return {'status': "OK"}, 200
 
         return list, 200

changedetectionio/apprise_plugin/__init__.py

@@ -0,0 +1,82 @@
+# include the decorator
+from apprise.decorators import notify
+from loguru import logger
+
+@notify(on="delete")
+@notify(on="deletes")
+@notify(on="get")
+@notify(on="gets")
+@notify(on="post")
+@notify(on="posts")
+@notify(on="put")
+@notify(on="puts")
+def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
+    import requests
+    import json
+    from urllib.parse import unquote_plus
+    from apprise.utils import parse_url as apprise_parse_url
+    from apprise import URLBase
+
+    url = kwargs['meta'].get('url')
+
+    if url.startswith('post'):
+        r = requests.post
+    elif url.startswith('get'):
+        r = requests.get
+    elif url.startswith('put'):
+        r = requests.put
+    elif url.startswith('delete'):
+        r = requests.delete
+
+    url = url.replace('post://', 'http://')
+    url = url.replace('posts://', 'https://')
+    url = url.replace('put://', 'http://')
+    url = url.replace('puts://', 'https://')
+    url = url.replace('get://', 'http://')
+    url = url.replace('gets://', 'https://')
+    url = url.replace('put://', 'http://')
+    url = url.replace('puts://', 'https://')
+    url = url.replace('delete://', 'http://')
+    url = url.replace('deletes://', 'https://')
+
+    headers = {}
+    params = {}
+    auth = None
+
+    # Convert /foobar?+some-header=hello to proper header dictionary
+    results = apprise_parse_url(url)
+    if results:
+        # Add our headers that the user can potentially over-ride if they wish
+        # to to our returned result set and tidy entries by unquoting them
+        headers = {unquote_plus(x): unquote_plus(y)
+                   for x, y in results['qsd+'].items()}
+
+        # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
+        # In Apprise, it relies on prefixing each request arg with "-", because it uses say &method=update as a flag for apprise
+        # but here we are making straight requests, so we need todo convert this against apprise's logic
+        for k, v in results['qsd'].items():
+            if not k.strip('+-') in results['qsd+'].keys():
+                params[unquote_plus(k)] = unquote_plus(v)
+
+        # Determine Authentication
+        auth = ''
+        if results.get('user') and results.get('password'):
+            auth = (unquote_plus(results.get('user')), unquote_plus(results.get('user')))
+        elif results.get('user'):
+            auth = (unquote_plus(results.get('user')))
+
+    # Try to auto-guess if it's JSON
+    h = 'application/json; charset=utf-8'
+    try:
+        json.loads(body)
+        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'),
+      auth=auth,
+      data=body.encode('utf-8') if type(body) is str else body,
+      headers=headers,
+      params=params
+      )

changedetectionio/blueprint/backups/__init__.py

@@ -0,0 +1,164 @@
+import datetime
+import glob
+import threading
+
+from flask import Blueprint, render_template, send_from_directory, flash, url_for, redirect, abort
+import os
+
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio.flask_app import login_optionally_required
+from loguru import logger
+
+BACKUP_FILENAME_FORMAT = "changedetection-backup-{}.zip"
+
+
+def create_backup(datastore_path, watches: dict):
+    logger.debug("Creating backup...")
+    import zipfile
+    from pathlib import Path
+
+    # create a ZipFile object
+    timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
+    backupname = BACKUP_FILENAME_FORMAT.format(timestamp)
+    backup_filepath = os.path.join(datastore_path, backupname)
+
+    with zipfile.ZipFile(backup_filepath.replace('.zip', '.tmp'), "w",
+                         compression=zipfile.ZIP_DEFLATED,
+                         compresslevel=8) as zipObj:
+
+        # Add the index
+        zipObj.write(os.path.join(datastore_path, "url-watches.json"), arcname="url-watches.json")
+
+        # Add the flask app secret
+        zipObj.write(os.path.join(datastore_path, "secret.txt"), arcname="secret.txt")
+
+        # Add any data in the watch data directory.
+        for uuid, w in watches.items():
+            for f in Path(w.watch_data_dir).glob('*'):
+                zipObj.write(f,
+                             # Use the full path to access the file, but make the file 'relative' in the Zip.
+                             arcname=os.path.join(f.parts[-2], f.parts[-1]),
+                             compress_type=zipfile.ZIP_DEFLATED,
+                             compresslevel=8)
+
+        # Create a list file with just the URLs, so it's easier to port somewhere else in the future
+        list_file = "url-list.txt"
+        with open(os.path.join(datastore_path, list_file), "w") as f:
+            for uuid in watches:
+                url = watches[uuid]["url"]
+                f.write("{}\r\n".format(url))
+        list_with_tags_file = "url-list-with-tags.txt"
+        with open(
+                os.path.join(datastore_path, list_with_tags_file), "w"
+        ) as f:
+            for uuid in watches:
+                url = watches[uuid].get('url')
+                tag = watches[uuid].get('tags', {})
+                f.write("{} {}\r\n".format(url, tag))
+
+        # Add it to the Zip
+        zipObj.write(
+            os.path.join(datastore_path, list_file),
+            arcname=list_file,
+            compress_type=zipfile.ZIP_DEFLATED,
+            compresslevel=8,
+        )
+        zipObj.write(
+            os.path.join(datastore_path, list_with_tags_file),
+            arcname=list_with_tags_file,
+            compress_type=zipfile.ZIP_DEFLATED,
+            compresslevel=8,
+        )
+
+    # Now it's done, rename it so it shows up finally and its completed being written.
+    os.rename(backup_filepath.replace('.zip', '.tmp'), backup_filepath.replace('.tmp', '.zip'))
+
+
+def construct_blueprint(datastore: ChangeDetectionStore):
+    backups_blueprint = Blueprint('backups', __name__, template_folder="templates")
+    backup_threads = []
+
+    @login_optionally_required
+    @backups_blueprint.route("/request-backup", methods=['GET'])
+    def request_backup():
+        if any(thread.is_alive() for thread in backup_threads):
+            flash("A backup is already running, check back in a few minutes", "error")
+            return redirect(url_for('backups.index'))
+
+        if len(find_backups()) > int(os.getenv("MAX_NUMBER_BACKUPS", 100)):
+            flash("Maximum number of backups reached, please remove some", "error")
+            return redirect(url_for('backups.index'))
+
+        # Be sure we're written fresh
+        datastore.sync_to_json()
+        zip_thread = threading.Thread(target=create_backup, args=(datastore.datastore_path, datastore.data.get("watching")))
+        zip_thread.start()
+        backup_threads.append(zip_thread)
+        flash("Backup building in background, check back in a few minutes.")
+
+        return redirect(url_for('backups.index'))
+
+    def find_backups():
+        backup_filepath = os.path.join(datastore.datastore_path, BACKUP_FILENAME_FORMAT.format("*"))
+        backups = glob.glob(backup_filepath)
+        backup_info = []
+
+        for backup in backups:
+            size = os.path.getsize(backup) / (1024 * 1024)
+            creation_time = os.path.getctime(backup)
+            backup_info.append({
+                'filename': os.path.basename(backup),
+                'filesize': f"{size:.2f}",
+                'creation_time': creation_time
+            })
+
+        backup_info.sort(key=lambda x: x['creation_time'], reverse=True)
+
+        return backup_info
+
+    @login_optionally_required
+    @backups_blueprint.route("/download/<string:filename>", methods=['GET'])
+    def download_backup(filename):
+        import re
+        filename = filename.strip()
+        backup_filename_regex = BACKUP_FILENAME_FORMAT.format("\d+")
+
+        full_path = os.path.join(os.path.abspath(datastore.datastore_path), filename)
+        if not full_path.startswith(os.path.abspath(datastore.datastore_path)):
+            abort(404)
+
+        if filename == 'latest':
+            backups = find_backups()
+            filename = backups[0]['filename']
+
+        if not re.match(r"^" + backup_filename_regex + "$", filename):
+            abort(400)  # Bad Request if the filename doesn't match the pattern
+
+        logger.debug(f"Backup download request for '{full_path}'")
+        return send_from_directory(os.path.abspath(datastore.datastore_path), filename, as_attachment=True)
+
+    @login_optionally_required
+    @backups_blueprint.route("/", methods=['GET'])
+    def index():
+        backups = find_backups()
+        output = render_template("overview.html",
+                                 available_backups=backups,
+                                 backup_running=any(thread.is_alive() for thread in backup_threads)
+                                 )
+
+        return output
+
+    @login_optionally_required
+    @backups_blueprint.route("/remove-backups", methods=['GET'])
+    def remove_backups():
+
+        backup_filepath = os.path.join(datastore.datastore_path, BACKUP_FILENAME_FORMAT.format("*"))
+        backups = glob.glob(backup_filepath)
+        for backup in backups:
+            os.unlink(backup)
+
+        flash("Backups were deleted.")
+
+        return redirect(url_for('backups.index'))
+
+    return backups_blueprint

changedetectionio/blueprint/backups/templates/overview.html

@@ -0,0 +1,36 @@
+{% extends 'base.html' %}
+{% block content %}
+    {% from '_helpers.html' import render_simple_field, render_field %}
+    <div class="edit-form">
+        <div class="box-wrap inner">
+            <h4>Backups</h4>
+            {% if backup_running %}
+                <p>
+                    <strong>A backup is running!</strong>
+                </p>
+            {% endif %}
+            <p>
+                Here you can download and request a new backup, when a backup is completed you will see it listed below.
+            </p>
+            <br>
+                {% if available_backups %}
+                    <ul>
+                    {% for backup in available_backups %}
+                        <li><a href="{{ url_for('backups.download_backup', filename=backup["filename"]) }}">{{ backup["filename"] }}</a> {{  backup["filesize"] }} Mb</li>
+                    {% endfor %}
+                    </ul>
+                {% else %}
+                    <p>
+                    <strong>No backups found.</strong>
+                    </p>
+                {% endif %}
+
+            <a class="pure-button pure-button-primary" href="{{ url_for('backups.request_backup') }}">Create backup</a>
+            {% if available_backups %}
+                <a class="pure-button button-small button-error " href="{{ url_for('backups.remove_backups') }}">Remove backups</a>
+            {% endif %}
+        </div>
+    </div>
+
+
+{% endblock %}

changedetectionio/blueprint/browser_steps/__init__.py

@@ -85,7 +85,8 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         browsersteps_start_session['browserstepper'] = browser_steps.browsersteps_live_ui(
             playwright_browser=browsersteps_start_session['browser'],
             proxy=proxy,
-            start_url=datastore.data['watching'][watch_uuid].get('url')
+            start_url=datastore.data['watching'][watch_uuid].get('url'),
+            headers=datastore.data['watching'][watch_uuid].get('headers')
         )
 
         # For test

changedetectionio/blueprint/browser_steps/browser_steps.py

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

changedetectionio/blueprint/check_proxies/__init__.py

@@ -1,4 +1,7 @@
+import importlib
 from concurrent.futures import ThreadPoolExecutor
+
+from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
 from changedetectionio.store import ChangeDetectionStore
 
 from functools import wraps
@@ -30,7 +33,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def long_task(uuid, preferred_proxy):
         import time
         from changedetectionio.content_fetchers import exceptions as content_fetcher_exceptions
-        from changedetectionio.processors.text_json_diff import text_json_diff
         from changedetectionio.safe_jinja import render as jinja_render
 
         status = {'status': '', 'length': 0, 'text': ''}
@@ -38,8 +40,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         contents = ''
         now = time.time()
         try:
-            update_handler = text_json_diff.perform_site_check(datastore=datastore, watch_uuid=uuid)
-            update_handler.call_browser()
+            processor_module = importlib.import_module("changedetectionio.processors.text_json_diff.processor")
+            update_handler = processor_module.perform_site_check(datastore=datastore,
+                                                                 watch_uuid=uuid
+                                                                 )
+
+            update_handler.call_browser(preferred_proxy_id=preferred_proxy)
         # title, size is len contents not len xfer
         except content_fetcher_exceptions.Non200ErrorCodeReceived as e:
             if e.status_code == 404:
@@ -48,7 +54,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 status.update({'status': 'ERROR', 'length': len(contents), 'text': f"{e.status_code} - Access denied"})
             else:
                 status.update({'status': 'ERROR', 'length': len(contents), 'text': f"Status code: {e.status_code}"})
-        except text_json_diff.FilterNotFoundInResponse:
+        except FilterNotFoundInResponse:
             status.update({'status': 'OK', 'length': len(contents), 'text': f"OK but CSS/xPath filter not found (page changed layout?)"})
         except content_fetcher_exceptions.EmptyReply as e:
             if e.status_code == 403 or e.status_code == 401:

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -19,7 +19,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
         datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_ACCEPT
         datastore.data['watching'][uuid]['processor'] = 'restock_diff'
         datastore.data['watching'][uuid].clear_watch()
-        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
         return redirect(url_for("index"))
 
     @login_required

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">
@@ -58,9 +57,9 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                         {% if '/text()' in  field %}
                           <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br>
                         {% endif %}
-                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br>
-
-                    <ul>
+                        <span class="pure-form-message-inline">One CSS, xPath, JSON Path/JQ selector per line, <i>any</i> rules that matches will be used.<br>
+                    <div data-target="#advanced-help-selectors" class="toggle-show pure-button button-tag button-xsmall">Show advanced help and tips</div>
+                    <ul id="advanced-help-selectors">
                         <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
                         <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
                             <ul>
@@ -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/base.py

@@ -65,8 +65,8 @@ class Fetcher():
 
     def __init__(self):
         import importlib.resources
-        self.xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text()
-        self.instock_data_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text()
+        self.xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text(encoding='utf-8')
+        self.instock_data_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text(encoding='utf-8')
 
     @abstractmethod
     def get_error(self):
@@ -81,7 +81,8 @@ class Fetcher():
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
         # Should set self.error, self.status_code and self.content
         pass
 

changedetectionio/content_fetchers/playwright.py

@@ -83,7 +83,8 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
 
         from playwright.sync_api import sync_playwright
         import playwright._impl._errors
@@ -130,7 +131,7 @@ class fetcher(Fetcher):
             if response is None:
                 context.close()
                 browser.close()
-                logger.debug("Content Fetcher > Response object was none")
+                logger.debug("Content Fetcher > Response object from the browser communication was none")
                 raise EmptyReply(url=url, status_code=None)
 
             try:
@@ -166,10 +167,10 @@ class fetcher(Fetcher):
 
                 raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
 
-            if len(self.page.content().strip()) == 0:
+            if not empty_pages_are_a_change and len(self.page.content().strip()) == 0:
+                logger.debug("Content Fetcher > Content was empty, empty_pages_are_a_change = False")
                 context.close()
                 browser.close()
-                logger.debug("Content Fetcher > Content was empty")
                 raise EmptyReply(url=url, status_code=response.status)
 
             # Run Browser Steps here

changedetectionio/content_fetchers/puppeteer.py

@@ -75,7 +75,8 @@ class fetcher(Fetcher):
                          request_method,
                          ignore_status_codes,
                          current_include_filters,
-                         is_binary
+                         is_binary,
+                         empty_pages_are_a_change
                          ):
 
         from changedetectionio.content_fetchers import visualselector_xpath_selectors
@@ -153,7 +154,7 @@ class fetcher(Fetcher):
         if response is None:
             await self.page.close()
             await browser.close()
-            logger.warning("Content Fetcher > Response object was none")
+            logger.warning("Content Fetcher > Response object was none (as in, the response from the browser was empty, not just the content)")
             raise EmptyReply(url=url, status_code=None)
 
         self.headers = response.headers
@@ -186,10 +187,11 @@ class fetcher(Fetcher):
 
             raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
         content = await self.page.content
-        if len(content.strip()) == 0:
+
+        if not empty_pages_are_a_change and len(content.strip()) == 0:
+            logger.error("Content Fetcher > Content was empty (empty_pages_are_a_change is False), closing browsers")
             await self.page.close()
             await browser.close()
-            logger.error("Content Fetcher > Content was empty")
             raise EmptyReply(url=url, status_code=response.status)
 
         # Run Browser Steps here
@@ -247,7 +249,7 @@ class fetcher(Fetcher):
         await self.fetch_page(**kwargs)
 
     def run(self, url, timeout, request_headers, request_body, request_method, ignore_status_codes=False,
-            current_include_filters=None, is_binary=False):
+            current_include_filters=None, is_binary=False, empty_pages_are_a_change=False):
 
         #@todo make update_worker async which could run any of these content_fetchers within memory and time constraints
         max_time = os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180)
@@ -262,7 +264,8 @@ class fetcher(Fetcher):
                 request_method=request_method,
                 ignore_status_codes=ignore_status_codes,
                 current_include_filters=current_include_filters,
-                is_binary=is_binary
+                is_binary=is_binary,
+                empty_pages_are_a_change=empty_pages_are_a_change
             ), timeout=max_time))
         except asyncio.TimeoutError:
             raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))

changedetectionio/content_fetchers/requests.py

@@ -1,9 +1,6 @@
+from loguru import logger
 import hashlib
 import os
-
-import chardet
-import requests
-
 from changedetectionio import strtobool
 from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
 from changedetectionio.content_fetchers.base import Fetcher
@@ -26,7 +23,11 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
+
+        import chardet
+        import requests
 
         if self.browser_steps_get_valid_steps():
             raise BrowserStepsInUnsupportedFetcher(url=url)
@@ -53,7 +54,7 @@ class fetcher(Fetcher):
             session.mount('file://', FileAdapter())
 
         r = session.request(method=request_method,
-                            data=request_body,
+                            data=request_body.encode('utf-8') if type(request_body) is str else request_body,
                             url=url,
                             headers=request_headers,
                             timeout=timeout,
@@ -74,7 +75,11 @@ class fetcher(Fetcher):
         self.headers = r.headers
 
         if not r.content or not len(r.content):
-            raise EmptyReply(url=url, status_code=r.status_code)
+            logger.debug(f"Requests returned empty content for '{url}'")
+            if not empty_pages_are_a_change:
+                raise EmptyReply(url=url, status_code=r.status_code)
+            else:
+                logger.debug(f"URL {url} gave zero byte content reply with Status Code {r.status_code}, but empty_pages_are_a_change = True")
 
         # @todo test this
         # @todo maybe you really want to test zero-byte return pages?

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

@@ -30,6 +30,8 @@ function isItemInStock() {
         'dieser artikel ist bald wieder verfügbar',
         'dostępne wkrótce',
         'en rupture de stock',
+        'esgotado',
+        'indisponível',
         'isn\'t in stock right now',
         'isnt in stock right now',
         'isn’t in stock right now',
@@ -57,6 +59,7 @@ function isItemInStock() {
         'notify me when available',
         'notify me',
         'notify when available',
+        'não disponível',
         'não estamos a aceitar encomendas',
         'out of stock',
         'out-of-stock',
@@ -75,6 +78,7 @@ function isItemInStock() {
         'vergriffen',
         'vorbestellen',
         'vorbestellung ist bald möglich',
+        'we don\'t currently have any',
         'we couldn\'t find any products that match',
         'we do not currently have an estimate of when this product will be back in stock.',
         'we don\'t know when or if this item will be back in stock.',
@@ -153,10 +157,14 @@ 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) {
@@ -173,7 +181,8 @@ function isItemInStock() {
         const element = elementsToScan[i];
         // outside the 'fold' or some weird text in the heading area
         // .getBoundingClientRect() was causing a crash in chrome 119, can only be run on contentVisibility != hidden
-        if (element.getBoundingClientRect().top + window.scrollY >= vh + 150 || element.getBoundingClientRect().top + window.scrollY <= 100) {
+        // Note: theres also an automated test that places the 'out of stock' text fairly low down
+        if (element.getBoundingClientRect().top + window.scrollY >= vh + 250 || element.getBoundingClientRect().top + window.scrollY <= 100) {
             continue
         }
         elementText = "";
@@ -187,7 +196,7 @@ function isItemInStock() {
             // and these mean its out of stock
             for (const outOfStockText of outOfStockTexts) {
                 if (elementText.includes(outOfStockText)) {
-                    console.log(`Selected 'Out of Stock' - found text "${outOfStockText}" - "${elementText}"`)
+                    console.log(`Selected 'Out of Stock' - found text "${outOfStockText}" - "${elementText}" - offset top ${element.getBoundingClientRect().top}, page height is ${vh}`)
                     return outOfStockText; // item is out of stock
                 }
             }

changedetectionio/content_fetchers/res/xpath_element_scraper.js

@@ -164,6 +164,15 @@ visibleElementsArray.forEach(function (element) {
         }
     }
 
+    let label = "not-interesting" // A placeholder, the actual labels for training are done by hand for now
+
+    let text = element.textContent.trim().slice(0, 30).trim();
+    while (/\n{2,}|\t{2,}/.test(text)) {
+        text = text.replace(/\n{2,}/g, '\n').replace(/\t{2,}/g, '\t')
+    }
+
+    // Try to identify any possible currency amounts "Sale: 4000" or "Sale now 3000 Kc", can help with the training.
+    const hasDigitCurrency = (/\d/.test(text.slice(0, 6)) || /\d/.test(text.slice(-6)) ) &&  /([€£$¥₩₹]|USD|AUD|EUR|Kč|kr|SEK|,–)/.test(text) ;
 
     size_pos.push({
         xpath: xpath_result,
@@ -171,9 +180,16 @@ visibleElementsArray.forEach(function (element) {
         height: Math.round(bbox['height']),
         left: Math.floor(bbox['left']),
         top: Math.floor(bbox['top']) + scroll_y,
+        // tagName used by Browser Steps
         tagName: (element.tagName) ? element.tagName.toLowerCase() : '',
+        // tagtype used by Browser Steps
         tagtype: (element.tagName.toLowerCase() === 'input' && element.type) ? element.type.toLowerCase() : '',
-        isClickable: window.getComputedStyle(element).cursor == "pointer"
+        isClickable: window.getComputedStyle(element).cursor === "pointer",
+        // Used by the keras trainer
+        fontSize: window.getComputedStyle(element).getPropertyValue('font-size'),
+        fontWeight: window.getComputedStyle(element).getPropertyValue('font-weight'),
+        hasDigitCurrency: hasDigitCurrency,
+        label: label,
     });
 
 });

changedetectionio/content_fetchers/webdriver_selenium.py

@@ -56,7 +56,8 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
 
         from selenium import webdriver
         from selenium.webdriver.chrome.options import Options as ChromeOptions

changedetectionio/flask_app.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 
 import datetime
+
 import flask_login
 import locale
 import os
@@ -52,6 +53,7 @@ extra_stylesheets = []
 
 update_q = queue.PriorityQueue()
 notification_q = queue.Queue()
+MAX_QUEUE_SIZE = 2000
 
 app = Flask(__name__,
             static_url_path="",
@@ -66,7 +68,6 @@ FlaskCompress(app)
 
 # Stop browser caching of assets
 app.config['SEND_FILE_MAX_AGE_DEFAULT'] = 0
-
 app.config.exit = Event()
 
 app.config['NEW_VERSION_AVAILABLE'] = False
@@ -469,7 +470,7 @@ def changedetection_app(config=None, datastore_o=None):
                     continue
             if watch.get('last_error'):
                 errored_count += 1
-                
+
             if search_q:
                 if (watch.get('title') and search_q in watch.get('title').lower()) or search_q in watch.get('url', '').lower():
                     sorted_watches.append(watch)
@@ -532,23 +533,32 @@ def changedetection_app(config=None, datastore_o=None):
     @login_optionally_required
     def ajax_callback_send_notification_test(watch_uuid=None):
 
-        # Watch_uuid could be unset in the case its used in tag editor, global setings
+        # Watch_uuid could be unset in the case it`s used in tag editor, global settings
         import apprise
         import random
         from .apprise_asset import asset
         apobj = apprise.Apprise(asset=asset)
 
+        # so that the custom endpoints are registered
+        from changedetectionio.apprise_plugin import apprise_custom_api_call_wrapper
         is_global_settings_form = request.args.get('mode', '') == 'global-settings'
         is_group_settings_form = request.args.get('mode', '') == 'group-settings'
 
         # Use an existing random one on the global/main settings form
-        if not watch_uuid and (is_global_settings_form or is_group_settings_form):
+        if not watch_uuid and (is_global_settings_form or is_group_settings_form) \
+                and datastore.data.get('watching'):
             logger.debug(f"Send test notification - Choosing random Watch {watch_uuid}")
             watch_uuid = random.choice(list(datastore.data['watching'].keys()))
 
+        if not watch_uuid:
+            return make_response("Error: You must have atleast one watch configured for 'test notification' to work", 400)
+
         watch = datastore.data['watching'].get(watch_uuid)
 
-        notification_urls = request.form['notification_urls'].strip().splitlines()
+        notification_urls = None
+
+        if request.form.get('notification_urls'):
+            notification_urls = request.form['notification_urls'].strip().splitlines()
 
         if not notification_urls:
             logger.debug("Test notification - Trying by group/tag in the edit form if available")
@@ -566,12 +576,12 @@ def changedetection_app(config=None, datastore_o=None):
 
 
         if not notification_urls:
-            return 'No Notification URLs set/found'
+            return 'Error: No Notification URLs set/found'
 
         for n_url in notification_urls:
             if len(n_url.strip()):
                 if not apobj.add(n_url):
-                    return f'Error - {n_url} is not a valid AppRise URL.'
+                    return f'Error:  {n_url} is not a valid AppRise URL.'
 
         try:
             # use the same as when it is triggered, but then override it with the form test values
@@ -590,11 +600,13 @@ def changedetection_app(config=None, datastore_o=None):
             if 'notification_body' in request.form and request.form['notification_body'].strip():
                 n_object['notification_body'] = request.form.get('notification_body', '').strip()
 
+            n_object.update(watch.extra_notification_token_values())
+
             from . import update_worker
             new_worker = update_worker.update_worker(update_q, notification_q, app, datastore)
             new_worker.queue_notification_for_watch(notification_q=notification_q, n_object=n_object, watch=watch)
         except Exception as e:
-            return make_response({'error': str(e)}, 400)
+            return make_response(f"Error: str(e)", 400)
 
         return 'OK - Sent test notifications'
 
@@ -786,15 +798,15 @@ def changedetection_app(config=None, datastore_o=None):
             # Recast it if need be to right data Watch handler
             watch_class = get_custom_watch_obj_for_processor(form.data.get('processor'))
             datastore.data['watching'][uuid] = watch_class(datastore_path=datastore_o.datastore_path, default=datastore.data['watching'][uuid])
-
             flash("Updated watch - unpaused!" if request.args.get('unpause_on_save') else "Updated watch.")
 
             # Re #286 - We wait for syncing new data to disk in another thread every 60 seconds
             # But in the case something is added we should save straight away
             datastore.needs_write_urgent = True
 
-            # Queue the watch for immediate recheck, with a higher priority
-            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+            if not datastore.data['watching'][uuid].get('paused'):
+                # Queue the watch for immediate recheck, with a higher priority
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
             # Diff page [edit] link should go back to diff page
             if request.args.get("next") and request.args.get("next") == 'diff':
@@ -975,7 +987,7 @@ def changedetection_app(config=None, datastore_o=None):
                 importer = import_url_list()
                 importer.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', 'text_json_diff'))
                 for uuid in importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
                 if len(importer.remaining_data) == 0:
                     return redirect(url_for('index'))
@@ -988,7 +1000,7 @@ def changedetection_app(config=None, datastore_o=None):
                 d_importer = import_distill_io_json()
                 d_importer.run(data=request.values.get('distill-io'), flash=flash, datastore=datastore)
                 for uuid in d_importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
             # XLSX importer
             if request.files and request.files.get('xlsx_file'):
@@ -1012,7 +1024,7 @@ def changedetection_app(config=None, datastore_o=None):
                     w_importer.run(data=file, flash=flash, datastore=datastore)
 
                 for uuid in w_importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
         # Could be some remaining, or we could be on GET
         form = forms.importForm(formdata=request.form if request.method == 'POST' else None)
@@ -1153,8 +1165,6 @@ 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
 
@@ -1171,11 +1181,10 @@ 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:
@@ -1188,31 +1197,12 @@ 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': ''})
@@ -1223,8 +1213,7 @@ 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,
@@ -1248,78 +1237,6 @@ def changedetection_app(config=None, datastore_o=None):
 
         return output
 
-    # We're good but backups are even better!
-    @app.route("/backup", methods=['GET'])
-    @login_optionally_required
-    def get_backup():
-
-        import zipfile
-        from pathlib import Path
-
-        # Remove any existing backup file, for now we just keep one file
-
-        for previous_backup_filename in Path(datastore_o.datastore_path).rglob('changedetection-backup-*.zip'):
-            os.unlink(previous_backup_filename)
-
-        # create a ZipFile object
-        timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
-        backupname = "changedetection-backup-{}.zip".format(timestamp)
-        backup_filepath = os.path.join(datastore_o.datastore_path, backupname)
-
-        with zipfile.ZipFile(backup_filepath, "w",
-                             compression=zipfile.ZIP_DEFLATED,
-                             compresslevel=8) as zipObj:
-
-            # Be sure we're written fresh
-            datastore.sync_to_json()
-
-            # Add the index
-            zipObj.write(os.path.join(datastore_o.datastore_path, "url-watches.json"), arcname="url-watches.json")
-
-            # Add the flask app secret
-            zipObj.write(os.path.join(datastore_o.datastore_path, "secret.txt"), arcname="secret.txt")
-
-            # Add any data in the watch data directory.
-            for uuid, w in datastore.data['watching'].items():
-                for f in Path(w.watch_data_dir).glob('*'):
-                    zipObj.write(f,
-                                 # Use the full path to access the file, but make the file 'relative' in the Zip.
-                                 arcname=os.path.join(f.parts[-2], f.parts[-1]),
-                                 compress_type=zipfile.ZIP_DEFLATED,
-                                 compresslevel=8)
-
-            # Create a list file with just the URLs, so it's easier to port somewhere else in the future
-            list_file = "url-list.txt"
-            with open(os.path.join(datastore_o.datastore_path, list_file), "w") as f:
-                for uuid in datastore.data["watching"]:
-                    url = datastore.data["watching"][uuid]["url"]
-                    f.write("{}\r\n".format(url))
-            list_with_tags_file = "url-list-with-tags.txt"
-            with open(
-                os.path.join(datastore_o.datastore_path, list_with_tags_file), "w"
-            ) as f:
-                for uuid in datastore.data["watching"]:
-                    url = datastore.data["watching"][uuid].get('url')
-                    tag = datastore.data["watching"][uuid].get('tags', {})
-                    f.write("{} {}\r\n".format(url, tag))
-
-            # Add it to the Zip
-            zipObj.write(
-                os.path.join(datastore_o.datastore_path, list_file),
-                arcname=list_file,
-                compress_type=zipfile.ZIP_DEFLATED,
-                compresslevel=8,
-            )
-            zipObj.write(
-                os.path.join(datastore_o.datastore_path, list_with_tags_file),
-                arcname=list_with_tags_file,
-                compress_type=zipfile.ZIP_DEFLATED,
-                compresslevel=8,
-            )
-
-        # Send_from_directory needs to be the full absolute path
-        return send_from_directory(os.path.abspath(datastore_o.datastore_path), backupname, as_attachment=True)
-
     @app.route("/static/<string:group>/<string:filename>", methods=['GET'])
     def static_content(group, filename):
         from flask import make_response
@@ -1377,22 +1294,33 @@ def changedetection_app(config=None, datastore_o=None):
         import brotli
 
         watch = datastore.data['watching'].get(uuid)
-        if watch and os.path.isdir(watch.watch_data_dir):
-            latest_filename = list(watch.history.keys())[0]
+        if watch and watch.history.keys() and os.path.isdir(watch.watch_data_dir):
+            latest_filename = list(watch.history.keys())[-1]
             html_fname = os.path.join(watch.watch_data_dir, f"{latest_filename}.html.br")
-            if html_fname.endswith('.br'):
-                # Read and decompress the Brotli file
-                with open(html_fname, 'rb') as f:
+            with open(html_fname, 'rb') as f:
+                if html_fname.endswith('.br'):
+                    # Read and decompress the Brotli file
                     decompressed_data = brotli.decompress(f.read())
+                else:
+                    decompressed_data = f.read()
 
-                buffer = BytesIO(decompressed_data)
+            buffer = BytesIO(decompressed_data)
 
-                return send_file(buffer, as_attachment=True, download_name=f"{latest_filename}.html", mimetype='text/html')
+            return send_file(buffer, as_attachment=True, download_name=f"{latest_filename}.html", mimetype='text/html')
 
 
         # 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():
@@ -1407,7 +1335,7 @@ def changedetection_app(config=None, datastore_o=None):
         url = request.form.get('url').strip()
         if datastore.url_exists(url):
             flash(f'Warning, URL {url} already exists', "notice")
-            
+
         add_paused = request.form.get('edit_and_watch_submit_button') != None
         processor = request.form.get('processor', 'text_json_diff')
         new_uuid = datastore.add_watch(url=url, tag=request.form.get('tags').strip(), extras={'paused': add_paused, 'processor': processor})
@@ -1453,7 +1381,7 @@ def changedetection_app(config=None, datastore_o=None):
         new_uuid = datastore.clone(uuid)
         if new_uuid:
             if not datastore.data['watching'].get(uuid).get('paused'):
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
             flash('Cloned.')
 
         return redirect(url_for('index'))
@@ -1474,7 +1402,7 @@ def changedetection_app(config=None, datastore_o=None):
 
         if uuid:
             if uuid not in running_uuids:
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             i = 1
 
         elif tag:
@@ -1485,7 +1413,7 @@ def changedetection_app(config=None, datastore_o=None):
                         continue
                     if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
                         update_q.put(
-                            queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False})
+                            queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid})
                         )
                         i += 1
 
@@ -1495,9 +1423,8 @@ def changedetection_app(config=None, datastore_o=None):
                 if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
                     if with_errors and not watch.get('last_error'):
                         continue
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
                     i += 1
-
         flash(f"{i} watches queued for rechecking.")
         return redirect(url_for('index', tag=tag))
 
@@ -1554,7 +1481,7 @@ def changedetection_app(config=None, datastore_o=None):
                 uuid = uuid.strip()
                 if datastore.data['watching'].get(uuid):
                     # Recheck and require a full reprocessing
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             flash("{} watches queued for rechecking".format(len(uuids)))
 
         elif (op == 'clear-errors'):
@@ -1689,6 +1616,9 @@ def changedetection_app(config=None, datastore_o=None):
     import changedetectionio.blueprint.check_proxies as check_proxies
     app.register_blueprint(check_proxies.construct_blueprint(datastore=datastore), url_prefix='/check_proxy')
 
+    import changedetectionio.blueprint.backups as backups
+    app.register_blueprint(backups.construct_blueprint(datastore), url_prefix='/backups')
+
 
     # @todo handle ctrl break
     ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks).start()
@@ -1813,12 +1743,14 @@ def ticker_thread_check_time_launch_checks():
             except RuntimeError as e:
                 # RuntimeError: dictionary changed size during iteration
                 time.sleep(0.1)
+                watch_uuid_list = []
             else:
                 break
 
         # Re #438 - Don't place more watches in the queue to be checked if the queue is already large
         while update_q.qsize() >= 2000:
-            time.sleep(1)
+            logger.warning(f"Recheck watches queue size limit reached ({MAX_QUEUE_SIZE}), skipping adding more items")
+            time.sleep(3)
 
 
         recheck_time_system_seconds = int(datastore.threshold_seconds)
@@ -1878,7 +1810,7 @@ def ticker_thread_check_time_launch_checks():
                         f"{now - watch['last_checked']:0.2f}s since last checked")
 
                     # Into the queue with you
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=priority, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=priority, item={'uuid': uuid}))
 
                     # Reset for next time
                     watch.jitter_seconds = 0

changedetectionio/forms.py

@@ -1,5 +1,6 @@
 import os
 import re
+from loguru import logger
 
 from changedetectionio.strtobool import strtobool
 
@@ -221,7 +222,8 @@ class ValidateAppRiseServers(object):
     def __call__(self, form, field):
         import apprise
         apobj = apprise.Apprise()
-
+        # so that the custom endpoints are registered
+        from changedetectionio.apprise_plugin import apprise_custom_api_call_wrapper
         for server_url in field.data:
             if not apobj.add(server_url):
                 message = field.gettext('\'%s\' is not a valid AppRise URL.' % (server_url))
@@ -468,19 +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)
@@ -492,7 +496,7 @@ class processor_text_json_diff_form(commonSettingsForm):
     text_should_not_be_present = StringListField('Block change-detection while text matches', [validators.Optional(), ValidateListRegex()])
     webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
 
-    save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
+    save_button = SubmitField('Save', render_kw={"class": "pure-button button-small pure-button-primary"})
 
     proxy = RadioField('Proxy')
     filter_failure_notification_send = BooleanField(
@@ -511,6 +515,7 @@ class processor_text_json_diff_form(commonSettingsForm):
         if not super().validate():
             return False
 
+        from changedetectionio.safe_jinja import render as jinja_render
         result = True
 
         # Fail form validation when a body is set for a GET
@@ -520,11 +525,46 @@ class processor_text_json_diff_form(commonSettingsForm):
 
         # Attempt to validate jinja2 templates in the URL
         try:
-            from changedetectionio.safe_jinja import render as jinja_render
             jinja_render(template_str=self.url.data)
-        except Exception as e:
-            self.url.errors.append('Invalid template syntax')
+        except ModuleNotFoundError as e:
+            # incase jinja2_time or others is missing
+            logger.error(e)
+            self.url.errors.append(f'Invalid template syntax configuration: {e}')
             result = False
+        except Exception as e:
+            logger.error(e)
+            self.url.errors.append(f'Invalid template syntax: {e}')
+            result = False
+
+        # Attempt to validate jinja2 templates in the body
+        if self.body.data and self.body.data.strip():
+            try:
+                jinja_render(template_str=self.body.data)
+            except ModuleNotFoundError as e:
+                # incase jinja2_time or others is missing
+                logger.error(e)
+                self.body.errors.append(f'Invalid template syntax configuration: {e}')
+                result = False
+            except Exception as e:
+                logger.error(e)
+                self.body.errors.append(f'Invalid template syntax: {e}')
+                result = False
+
+        # Attempt to validate jinja2 templates in the headers
+        if len(self.headers.data) > 0:
+            try:
+                for header, value in self.headers.data.items():
+                    jinja_render(template_str=value)
+            except ModuleNotFoundError as e:
+                # incase jinja2_time or others is missing
+                logger.error(e)
+                self.headers.errors.append(f'Invalid template syntax configuration: {e}')
+                result = False
+            except Exception as e:
+                logger.error(e)
+                self.headers.errors.append(f'Invalid template syntax in "{header}" header: {e}')
+                result = False
+
         return result
 
 class SingleExtraProxy(Form):
@@ -575,7 +615,7 @@ 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',
@@ -605,7 +645,7 @@ class globalSettingsForm(Form):
 
     requests = FormField(globalSettingsRequestForm)
     application = FormField(globalSettingsApplicationForm)
-    save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
+    save_button = SubmitField('Save', render_kw={"class": "pure-button button-small pure-button-primary"})
 
 
 class extractDataForm(Form):

changedetectionio/html_tools.py

@@ -1,18 +1,13 @@
-
-from bs4 import BeautifulSoup
-from inscriptis import get_text
-from jsonpath_ng.ext import parse
 from typing import List
-from inscriptis.model.config import ParserConfig
-from xml.sax.saxutils import escape as xml_escape
+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"]
@@ -39,6 +34,7 @@ def perl_style_slash_enclosed_regex_to_options(regex):
 
 # Given a CSS Rule, and a blob of HTML, return the blob of HTML that matches
 def include_filters(include_filters, html_content, append_pretty_line_formatting=False):
+    from bs4 import BeautifulSoup
     soup = BeautifulSoup(html_content, "html.parser")
     html_block = ""
     r = soup.select(include_filters, separator="")
@@ -56,16 +52,67 @@ def include_filters(include_filters, html_content, append_pretty_line_formatting
     return html_block
 
 def subtractive_css_selector(css_selector, html_content):
+    from bs4 import BeautifulSoup
     soup = BeautifulSoup(html_content, "html.parser")
-    for item in soup.select(css_selector):
+
+    # So that the elements dont shift their index, build a list of elements here which will be pointers to their place in the DOM
+    elements_to_remove = soup.select(css_selector)
+
+    # Then, remove them in a separate loop
+    for item in elements_to_remove:
         item.decompose()
+
     return str(soup)
 
+def subtractive_xpath_selector(selectors: List[str], html_content: str) -> str:
+    # Parse the HTML content using lxml
+    html_tree = etree.HTML(html_content)
+
+    # First, collect all elements to remove
+    elements_to_remove = []
+
+    # Iterate over the list of XPath selectors
+    for selector in selectors:
+        # Collect elements for each selector
+        elements_to_remove.extend(html_tree.xpath(selector))
+
+    # Then, remove them in a separate loop
+    for element in elements_to_remove:
+        if element.getparent() is not None:  # Ensure the element has a parent before removing
+            element.getparent().remove(element)
+
+    # Convert the modified HTML tree back to a string
+    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
+    css_selectors = []
+    xpath_selectors = []
+
+    for selector in selectors:
+        if selector.startswith(('xpath:', 'xpath1:', '//')):
+            # Handle XPath selectors separately
+            xpath_selector = selector.removeprefix('xpath:').removeprefix('xpath1:')
+            xpath_selectors.append(xpath_selector)
+        else:
+            # Collect CSS selectors as one "hit", see comment in subtractive_css_selector
+            css_selectors.append(selector.strip().strip(","))
+
+    if xpath_selectors:
+        modified_html = subtractive_xpath_selector(xpath_selectors, modified_html)
+
+    if css_selectors:
+        # Remove duplicates, then combine all CSS selectors into one string, separated by commas
+        # This stops the elements index shifting
+        unique_selectors = list(set(css_selectors))  # Ensure uniqueness
+        combined_css_selector = " , ".join(unique_selectors)
+        modified_html = subtractive_css_selector(combined_css_selector, modified_html)
+
+
+    return modified_html
 
 def elementpath_tostring(obj):
     """
@@ -181,6 +228,7 @@ def xpath1_filter(xpath_filter, html_content, append_pretty_line_formatting=Fals
 
 # Extract/find element
 def extract_element(find='title', html_content=''):
+    from bs4 import BeautifulSoup
 
     #Re #106, be sure to handle when its not found
     element_text = None
@@ -194,6 +242,8 @@ def extract_element(find='title', html_content=''):
 
 #
 def _parse_json(json_data, json_filter):
+    from jsonpath_ng.ext import parse
+
     if json_filter.startswith("json:"):
         jsonpath_expression = parse(json_filter.replace('json:', ''))
         match = jsonpath_expression.find(json_data)
@@ -242,6 +292,8 @@ def _get_stripped_text_from_json_match(match):
 # json_filter - ie json:$..price
 # ensure_is_ldjson_info_type - str "product", optional, "@type == product" (I dont know how to do that as a json selector)
 def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None):
+    from bs4 import BeautifulSoup
+
     stripped_text_from_html = False
 # https://github.com/dgtlmoon/changedetection.io/pull/2041#issuecomment-1848397161w
     # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded within HTML tags
@@ -309,6 +361,7 @@ 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 = []
@@ -324,34 +377,33 @@ 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
     pattern = '<!\[CDATA\[(\s*(?:.(?<!\]\]>)\s*)*)\]\]>'
     def repl(m):
         text = m.group(1)
@@ -360,6 +412,9 @@ def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False
     return re.sub(pattern, repl, html_content)
 
 def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=False) -> str:
+    from inscriptis import get_text
+    from inscriptis.model.config import ParserConfig
+
     """Converts html string to a string with just the text. If ignoring
     rendering anchor tag content is enable, anchor tag content are also
     included in the text

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'])
@@ -86,6 +89,10 @@ class model(watch_base):
 
         if ready_url.startswith('source:'):
             ready_url=ready_url.replace('source:', '')
+
+        # Also double check it after any Jinja2 formatting just incase
+        if not is_safe_url(ready_url):
+            return 'DISABLED'
         return ready_url
 
     def clear_watch(self):
@@ -171,6 +178,10 @@ 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 +318,13 @@ 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 +356,32 @@ 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 +425,8 @@ 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/notification.py

@@ -1,9 +1,10 @@
-import apprise
+
 import time
 from apprise import NotifyFormat
-import json
+import apprise
 from loguru import logger
 
+
 valid_tokens = {
     'base_url': '',
     'current_snapshot': '',
@@ -34,86 +35,11 @@ valid_notification_formats = {
     default_notification_format_for_watch: default_notification_format_for_watch
 }
 
-# include the decorator
-from apprise.decorators import notify
-
-@notify(on="delete")
-@notify(on="deletes")
-@notify(on="get")
-@notify(on="gets")
-@notify(on="post")
-@notify(on="posts")
-@notify(on="put")
-@notify(on="puts")
-def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
-    import requests
-    from apprise.utils import parse_url as apprise_parse_url
-    from apprise import URLBase
-
-    url = kwargs['meta'].get('url')
-
-    if url.startswith('post'):
-        r = requests.post
-    elif url.startswith('get'):
-        r = requests.get
-    elif url.startswith('put'):
-        r = requests.put
-    elif url.startswith('delete'):
-        r = requests.delete
-
-    url = url.replace('post://', 'http://')
-    url = url.replace('posts://', 'https://')
-    url = url.replace('put://', 'http://')
-    url = url.replace('puts://', 'https://')
-    url = url.replace('get://', 'http://')
-    url = url.replace('gets://', 'https://')
-    url = url.replace('put://', 'http://')
-    url = url.replace('puts://', 'https://')
-    url = url.replace('delete://', 'http://')
-    url = url.replace('deletes://', 'https://')
-
-    headers = {}
-    params = {}
-    auth = None
-
-    # Convert /foobar?+some-header=hello to proper header dictionary
-    results = apprise_parse_url(url)
-    if results:
-        # Add our headers that the user can potentially over-ride if they wish
-        # to to our returned result set and tidy entries by unquoting them
-        headers = {URLBase.unquote(x): URLBase.unquote(y)
-                   for x, y in results['qsd+'].items()}
-
-        # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
-        # In Apprise, it relies on prefixing each request arg with "-", because it uses say &method=update as a flag for apprise
-        # but here we are making straight requests, so we need todo convert this against apprise's logic
-        for k, v in results['qsd'].items():
-            if not k.strip('+-') in results['qsd+'].keys():
-                params[URLBase.unquote(k)] = URLBase.unquote(v)
-
-        # Determine Authentication
-        auth = ''
-        if results.get('user') and results.get('password'):
-            auth = (URLBase.unquote(results.get('user')), URLBase.unquote(results.get('user')))
-        elif results.get('user'):
-            auth = (URLBase.unquote(results.get('user')))
-
-    # Try to auto-guess if it's JSON
-    try:
-        json.loads(body)
-        headers['Content-Type'] = 'application/json; charset=utf-8'
-    except ValueError as e:
-        pass
-
-    r(results.get('url'),
-      auth=auth,
-      data=body,
-      headers=headers,
-      params=params
-      )
 
 
 def process_notification(n_object, datastore):
+    # so that the custom endpoints are registered
+    from changedetectionio.apprise_plugin import apprise_custom_api_call_wrapper
 
     from .safe_jinja import render as jinja_render
     now = time.time()

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():
 
@@ -18,28 +18,33 @@ class difference_detection_processor():
     screenshot = None
     watch = None
     xpath_data = None
+    preferred_proxy = None
 
     def __init__(self, *args, datastore, watch_uuid, **kwargs):
         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, preferred_proxy_id=None):
 
-    def call_browser(self):
         from requests.structures import CaseInsensitiveDict
-        # Protect against file:// access
-        if re.search(r'^file://', self.watch.get('url', '').strip(), re.IGNORECASE):
+
+        url = self.watch.link
+
+        # Protect against file://, file:/ access, check the real "link" without any meta "source:" etc prepended.
+        if re.search(r'^file:/', url.strip(), re.IGNORECASE):
             if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
                 raise Exception(
                     "file:// type access is denied for security reasons."
                 )
 
-        url = self.watch.link
-
         # Requests, playwright, other browser via wss:// etc, fetch_extra_something
         prefer_fetch_backend = self.watch.get('fetch_backend', 'system')
 
         # Proxy ID "key"
-        preferred_proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=self.watch.get('uuid'))
+        preferred_proxy_id = preferred_proxy_id if preferred_proxy_id else self.datastore.get_preferred_proxy_for_watch(uuid=self.watch.get('uuid'))
 
         # Pluggable content self.fetcher
         if not prefer_fetch_backend or prefer_fetch_backend == 'system':
@@ -97,6 +102,7 @@ class difference_detection_processor():
             self.fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, self.watch.get('uuid'))
 
         # Tweak the base config with the per-watch ones
+        from changedetectionio.safe_jinja import render as jinja_render
         request_headers = CaseInsensitiveDict()
 
         ua = self.datastore.data['settings']['requests'].get('default_ua')
@@ -113,9 +119,15 @@ class difference_detection_processor():
         if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
             request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
 
+        for header_name in request_headers:
+            request_headers.update({header_name: jinja_render(template_str=request_headers.get(header_name))})
+
         timeout = self.datastore.data['settings']['requests'].get('timeout')
 
         request_body = self.watch.get('body')
+        if request_body:
+            request_body = jinja_render(template_str=self.watch.get('body'))
+        
         request_method = self.watch.get('method')
         ignore_status_codes = self.watch.get('ignore_status_codes', False)
 
@@ -133,8 +145,18 @@ class difference_detection_processor():
         is_binary = self.watch.is_pdf
 
         # And here we go! call the right browser with browser-specific settings
-        self.fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, self.watch.get('include_filters'),
-                    is_binary=is_binary)
+        empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
+
+        self.fetcher.run(url=url,
+                         timeout=timeout,
+                         request_headers=request_headers,
+                         request_body=request_body,
+                         request_method=request_method,
+                         ignore_status_codes=ignore_status_codes,
+                         current_include_filters=self.watch.get('include_filters'),
+                         is_binary=is_binary,
+                         empty_pages_are_a_change=empty_pages_are_a_change
+                         )
 
         #@todo .quit here could go on close object, so we can run JS if change-detected
         self.fetcher.quit()
@@ -142,7 +164,7 @@ 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):
         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/__init__.py

@@ -1,11 +1,12 @@
 
-from changedetectionio.model.Watch import model as BaseWatch
-import re
 from babel.numbers import parse_decimal
+from changedetectionio.model.Watch import model as BaseWatch
+from typing import Union
+import re
 
 class Restock(dict):
 
-    def parse_currency(self, raw_value: str) -> float:
+    def parse_currency(self, raw_value: str) -> Union[float, None]:
         # Clean and standardize the value (ie 1,400.00 should be 1400.00), even better would be store the whole thing as an integer.
         standardized_value = raw_value
 
@@ -21,8 +22,11 @@ class Restock(dict):
         # Remove any non-numeric characters except for the decimal point
         standardized_value = re.sub(r'[^\d.-]', '', standardized_value)
 
-        # Convert to float
-        return float(parse_decimal(standardized_value, locale='en'))
+        if standardized_value:
+            # Convert to float
+            return float(parse_decimal(standardized_value, locale='en'))
+
+        return None
 
     def __init__(self, *args, **kwargs):
         # Define default values

changedetectionio/processors/restock_diff/processor.py

@@ -2,8 +2,7 @@ from .. import difference_detection_processor
 from ..exceptions import ProcessorException
 from . import Restock
 from loguru import logger
-import hashlib
-import re
+
 import urllib3
 import time
 
@@ -27,6 +26,30 @@ def _search_prop_by_value(matches, value):
             if value in prop[0]:
                 return prop[1]  # Yield the desired value and exit the function
 
+def _deduplicate_prices(data):
+    import re
+
+    '''
+    Some price data has multiple entries, OR it has a single entry with ['$159', '159', 159, "$ 159"] or just "159"
+    Get all the values, clean it and add it to a set then return the unique values
+    '''
+    unique_data = set()
+
+    # Return the complete 'datum' where its price was not seen before
+    for datum in data:
+
+        if isinstance(datum.value, list):
+            # Process each item in the list
+            normalized_value = set([float(re.sub(r'[^\d.]', '', str(item))) for item in datum.value if str(item).strip()])
+            unique_data.update(normalized_value)
+        else:
+            # Process single value
+            v = float(re.sub(r'[^\d.]', '', str(datum.value)))
+            unique_data.add(v)
+
+    return list(unique_data)
+
+
 # should return Restock()
 # add casting?
 def get_itemprop_availability(html_content) -> Restock:
@@ -36,17 +59,21 @@ def get_itemprop_availability(html_content) -> Restock:
     """
     from jsonpath_ng import parse
 
+    import re
     now = time.time()
     import extruct
     logger.trace(f"Imported extruct module in {time.time() - now:.3f}s")
 
-    value = {}
     now = time.time()
+
     # Extruct is very slow, I'm wondering if some ML is going to be faster (800ms on my i7), 'rdfa' seems to be the heaviest.
-
     syntaxes = ['dublincore', 'json-ld', 'microdata', 'microformat', 'opengraph']
+    try:
+        data = extruct.extract(html_content, syntaxes=syntaxes)
+    except Exception as e:
+        logger.warning(f"Unable to extract data, document parsing with extruct failed with {type(e).__name__} - {str(e)}")
+        return Restock()
 
-    data = extruct.extract(html_content, syntaxes=syntaxes)
     logger.trace(f"Extruct basic extract of all metadata done in {time.time() - now:.3f}s")
 
     # First phase, dead simple scanning of anything that looks useful
@@ -57,18 +84,17 @@ def get_itemprop_availability(html_content) -> Restock:
         pricecurrency_parse = parse('$..(pricecurrency|currency|priceCurrency )')
         availability_parse = parse('$..(availability|Availability)')
 
-        price_result = price_parse.find(data)
+        price_result = _deduplicate_prices(price_parse.find(data))
         if price_result:
             # Right now, we just support single product items, maybe we will store the whole actual metadata seperately in teh future and
             # parse that for the UI?
-            prices_found = set(str(item.value).replace('$', '') for item in price_result)
-            if len(price_result) > 1 and len(prices_found) > 1:
+            if len(price_result) > 1 and len(price_result) > 1:
                 # See of all prices are different, in the case that one product has many embedded data types with the same price
                 # One might have $121.95 and another 121.95 etc
-                logger.warning(f"More than one price found {prices_found}, throwing exception, cant use this plugin.")
+                logger.warning(f"More than one price found {price_result}, throwing exception, cant use this plugin.")
                 raise MoreThanOnePriceFound()
 
-            value['price'] = price_result[0].value
+            value['price'] = price_result[0]
 
         pricecurrency_result = pricecurrency_parse.find(data)
         if pricecurrency_result:
@@ -118,7 +144,9 @@ class perform_site_check(difference_detection_processor):
     screenshot = None
     xpath_data = None
 
-    def run_changedetection(self, watch, skip_when_checksum_same=True):
+    def run_changedetection(self, watch):
+        import hashlib
+
         if not watch:
             raise Exception("Watch no longer exists.")
 
@@ -132,6 +160,20 @@ 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', {})
 
@@ -146,7 +188,7 @@ class perform_site_check(difference_detection_processor):
 
         itemprop_availability = {}
         try:
-            itemprop_availability = get_itemprop_availability(html_content=self.fetcher.content)
+            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.",
@@ -182,7 +224,7 @@ class perform_site_check(difference_detection_processor):
             itemprop_availability['original_price'] = itemprop_availability.get('price')
             update_obj['restock']["original_price"] = itemprop_availability.get('price')
 
-        if not self.fetcher.instock_data and not itemprop_availability.get('availability'):
+        if not self.fetcher.instock_data and not itemprop_availability.get('availability') and not itemprop_availability.get('price'):
             raise ProcessorException(
                 message=f"Unable to extract restock data for this page unfortunately. (Got code {self.fetcher.get_last_status_code()} from server), no embedded stock information was found and nothing interesting in the text, try using this watch with Chrome.",
                 url=watch.get('url'),
@@ -191,12 +233,21 @@ 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 ""
@@ -260,4 +311,4 @@ 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 +1,115 @@
+
+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)
+    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
@@ -35,7 +35,7 @@ class PDFToHTMLToolNotFound(ValueError):
 # (set_proxy_from_list)
 class perform_site_check(difference_detection_processor):
 
-    def run_changedetection(self, watch, skip_when_checksum_same=True):
+    def run_changedetection(self, watch):
         changed_detected = False
         html_content = ""
         screenshot = False  # as bytes
@@ -58,9 +58,6 @@ class perform_site_check(difference_detection_processor):
         # Watches added automatically in the queue manager will skip if its the same checksum as the previous run
         # Saves a lot of CPU
         update_obj['previous_md5_before_filters'] = hashlib.md5(self.fetcher.content.encode('utf-8')).hexdigest()
-        if skip_when_checksum_same:
-            if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
-                raise content_fetchers.exceptions.checksumFromPreviousCheckWasTheSame()
 
         # Fetching complete, now filters
 
@@ -175,13 +172,13 @@ class perform_site_check(difference_detection_processor):
                                                                     html_content=self.fetcher.content,
                                                                     append_pretty_line_formatting=not watch.is_source_type_url,
                                                                     is_rss=is_rss)
+
                         elif filter_rule.startswith('xpath1:'):
                             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)
+                                                                     html_content=self.fetcher.content,
+                                                                     append_pretty_line_formatting=not watch.is_source_type_url,
+                                                                     is_rss=is_rss)
                         else:
-                            # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
                             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)
@@ -197,25 +194,21 @@ class perform_site_check(difference_detection_processor):
                 else:
                     # extract text
                     do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
-                    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
-                        )
+                    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.
         # Rewrite's the processing text based on only what diff result they want to see
+
         if watch.has_special_diff_filter_options_set() and len(watch.history.keys()):
             # Now the content comes from the diff-parser and not the returned HTTP traffic, so could be some differences
             from changedetectionio import diff
@@ -230,12 +223,12 @@ 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
@@ -256,14 +249,6 @@ 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:
@@ -272,37 +257,53 @@ 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
@@ -330,19 +331,33 @@ class perform_site_check(difference_detection_processor):
             if result:
                 blocked = True
 
-        # The main thing that all this at the moment comes down to :)
-        if watch.get('previous_md5') != fetched_md5:
-            changed_detected = True
 
         # Looks like something changed, but did it match all the rules?
         if blocked:
             changed_detected = False
+        else:
+            # The main thing that all this at the moment comes down to :)
+            if watch.get('previous_md5') != fetched_md5:
+                changed_detected = True
+
+            # Always record the new checksum
+            update_obj["previous_md5"] = fetched_md5
+
+            # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
+            if not watch.get('previous_md5'):
+                watch['previous_md5'] = fetched_md5
 
         logger.debug(f"Watch UUID {watch.get('uuid')} content check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
 
         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")
@@ -350,11 +365,6 @@ class perform_site_check(difference_detection_processor):
                 else:
                     logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} had unique content")
 
-        # Always record the new checksum
-        update_obj["previous_md5"] = fetched_md5
 
-        # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
-        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/global-settings.js

@@ -18,9 +18,11 @@ $(document).ready(function () {
 
     });
 
-    $("#notification-token-toggle").click(function (e) {
+    $(".toggle-show").click(function (e) {
         e.preventDefault();
-        $('#notification-tokens-info').toggle();
+        let target = $(this).data('target');
+        $(target).toggle();
     });
+
 });
 

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/notifications.js

@@ -28,17 +28,14 @@ $(document).ready(function() {
       url: notification_base_url,
       data : data,
         statusCode: {
-        400: function() {
-            // More than likely the CSRF token was lost when the server restarted
-          alert("There was a problem processing the request, please reload the page.");
+        400: function(data) {
+          // More than likely the CSRF token was lost when the server restarted
+          alert(data.responseText);
         }
       }
     }).done(function(data){
       console.log(data);
       alert(data);
-    }).fail(function(data){
-      console.log(data);
-      alert('There was an error communicating with the server.');
     })
   });
 });

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/recheck-proxy.js

@@ -1,14 +1,14 @@
 $(function () {
     /* add container before each proxy location to show status */
-
-    var option_li = $('.fetch-backend-proxy li').filter(function() {
-        return $("input",this)[0].value.length >0;
-    });
-
-    //var option_li = $('.fetch-backend-proxy li');
     var isActive = false;
-    $(option_li).prepend('<div class="proxy-status"></div>');
-    $(option_li).append('<div class="proxy-timing"></div><div class="proxy-check-details"></div>');
+
+    function setup_html_widget() {
+        var option_li = $('.fetch-backend-proxy li').filter(function () {
+            return $("input", this)[0].value.length > 0;
+        });
+        $(option_li).prepend('<div class="proxy-status"></div>');
+        $(option_li).append('<div class="proxy-timing"></div><div class="proxy-check-details"></div>');
+    }
 
     function set_proxy_check_status(proxy_key, state) {
         // select input by value name
@@ -59,8 +59,14 @@ $(function () {
     }
 
     $('#check-all-proxies').click(function (e) {
+
         e.preventDefault()
-        $('body').addClass('proxy-check-active');
+
+        if (!$('body').hasClass('proxy-check-active')) {
+            setup_html_widget();
+            $('body').addClass('proxy-check-active');
+        }
+
         $('.proxy-check-details').html('');
         $('.proxy-status').html('<span class="spinner"></span>').fadeIn();
         $('.proxy-timing').html('');

changedetectionio/static/js/tabs.js

@@ -26,8 +26,7 @@ function set_active_tab() {
     if (tab.length) {
         tab[0].parentElement.className = "active";
     }
-    // hash could move the page down
-    window.scrollTo(0, 0);
+
 }
 
 function focus_error_tab() {

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/diff.css

@@ -153,7 +153,8 @@ html[data-darkmode="true"] {
     border: 1px solid transparent;
     vertical-align: top;
     font: 1em monospace;
-    text-align: left; }
+    text-align: left;
+    overflow: clip; }
   #diff-ui pre {
     white-space: pre-wrap; }
 
@@ -172,7 +173,9 @@ ins {
   text-decoration: none; }
 
 #result {
-  white-space: pre-wrap; }
+  white-space: pre-wrap;
+  word-break: break-word;
+  overflow-wrap: break-word; }
 
 #settings {
   background: rgba(0, 0, 0, 0.05);
@@ -231,3 +234,12 @@ td#diff-col div {
   border-radius: 5px;
   background: var(--color-background);
   box-shadow: 1px 1px 4px var(--color-shadow-jump); }
+
+.pure-form button.reset-margin {
+  margin: 0px; }
+
+.diff-fieldset {
+  display: flex;
+  align-items: center;
+  gap: 4px;
+  flex-wrap: wrap; }

changedetectionio/static/styles/scss/diff.scss

@@ -24,6 +24,7 @@
     vertical-align: top;
     font: 1em monospace;
     text-align: left;
+    overflow: clip; // clip overflowing contents to cell boundariess
   }
 
   pre {
@@ -50,6 +51,8 @@ ins {
 
 #result {
   white-space: pre-wrap;
+  word-break: break-word;
+  overflow-wrap: break-word;
 
   .change {
     span {}
@@ -134,3 +137,15 @@ td#diff-col div {
   background: var(--color-background);
   box-shadow: 1px 1px 4px var(--color-shadow-jump);
 }
+
+// resets button margin to 0px
+.pure-form button.reset-margin {
+  margin: 0px;
+}
+
+.diff-fieldset {
+  display: flex;
+  align-items: center;
+  gap: 4px;
+  flex-wrap: wrap;
+}

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/_extra_browsers.scss

@@ -11,7 +11,22 @@ ul#requests-extra_browsers {
   /* each proxy entry is a `table` */
   table {
     tr {
-      display: inline;
+      display: table-row; // default display for small screens
+      input[type=text] {
+        width: 100%;
+      }
+    }
+  }
+  
+  // apply inline display for larger screens
+  @media only screen and (min-width: 1280px) {
+    table {
+      tr {
+        display: inline;
+        input[type=text] {
+          width: 100%;
+        }
+      }
     }
   }
 }

changedetectionio/static/styles/scss/parts/_extra_proxies.scss

@@ -11,7 +11,19 @@ ul#requests-extra_proxies {
   /* each proxy entry is a `table` */
   table {
     tr {
-      display: inline;
+      display: table-row; // default display for small screens
+      input[type=text] {
+        width: 100%;
+      }
+    }
+  }
+  
+  // apply inline display for large screens
+  @media only screen and (min-width: 1024px) {
+    table {
+      tr {
+        display: inline;
+      }
     }
   }
 }
@@ -25,15 +37,19 @@ ul#requests-extra_proxies {
 
 body.proxy-check-active {
   #request {
+    // Padding set by flex layout
+    /*
     .proxy-status {
       width: 2em;
     }
+    */
 
     .proxy-check-details {
       font-size: 80%;
       color: #555;
       display: block;
-      padding-left: 4em;
+      padding-left: 2em;
+      max-width: 500px;
     }
 
     .proxy-timing {

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);
 }
@@ -122,8 +147,14 @@ button.toggle-button {
   }
 }
 
+
+.tab-pane-inner {
+  // .tab-pane-inner will have the #id that the tab button jumps/anchors to
+  scroll-margin-top: 200px;
+}
+
 section.content {
-  padding-top: 5em;
+  padding-top: 100px;
   padding-bottom: 1em;
   flex-direction: column;
   display: flex;
@@ -320,10 +351,6 @@ a.pure-button-selected {
   background: var(--color-background-button-cancel);
 }
 
-#save_button {
-  margin-right: 1rem;
-}
-
 .messages {
   li {
     list-style: none;
@@ -620,9 +647,9 @@ footer {
       list-style: none;
 
       li {
-        >* {
-          display: inline-block;
-        }
+        display: flex;
+        align-items: center;
+        gap: 1em;
       }
     }
   }
@@ -682,6 +709,12 @@ 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 +730,24 @@ 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 +866,11 @@ 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 */
@@ -881,6 +937,7 @@ $form-edge-padding: 20px;
 }
 
 .tab-pane-inner {
+
   &:not(:target) {
     display: none;
   }
@@ -930,6 +987,13 @@ 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 +1037,28 @@ 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 {
@@ -95,26 +112,34 @@ ul#requests-extra_proxies {
   ul#requests-extra_proxies li > label {
     display: none; }
   ul#requests-extra_proxies table tr {
-    display: inline; }
+    display: table-row; }
+    ul#requests-extra_proxies table tr input[type=text] {
+      width: 100%; }
+  @media only screen and (min-width: 1024px) {
+    ul#requests-extra_proxies table tr {
+      display: inline; } }
 
 #request {
   /* Auto proxy scan/checker */ }
   #request label[for=proxy] {
     display: inline-block; }
 
-body.proxy-check-active #request .proxy-status {
-  width: 2em; }
-
-body.proxy-check-active #request .proxy-check-details {
-  font-size: 80%;
-  color: #555;
-  display: block;
-  padding-left: 4em; }
-
-body.proxy-check-active #request .proxy-timing {
-  font-size: 80%;
-  padding-left: 1rem;
-  color: var(--color-link); }
+body.proxy-check-active #request {
+  /*
+    .proxy-status {
+      width: 2em;
+    }
+    */ }
+  body.proxy-check-active #request .proxy-check-details {
+    font-size: 80%;
+    color: #555;
+    display: block;
+    padding-left: 2em;
+    max-width: 500px; }
+  body.proxy-check-active #request .proxy-timing {
+    font-size: 80%;
+    padding-left: 1rem;
+    color: var(--color-link); }
 
 #recommended-proxy {
   display: grid;
@@ -141,7 +166,14 @@ ul#requests-extra_browsers {
   ul#requests-extra_browsers li > label {
     display: none; }
   ul#requests-extra_browsers table tr {
-    display: inline; }
+    display: table-row; }
+    ul#requests-extra_browsers table tr input[type=text] {
+      width: 100%; }
+  @media only screen and (min-width: 1280px) {
+    ul#requests-extra_browsers table tr {
+      display: inline; }
+      ul#requests-extra_browsers table tr input[type=text] {
+        width: 100%; } }
 
 #extra-browsers-setting {
   border: 1px solid var(--color-grey-800);
@@ -411,6 +443,83 @@ 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 +588,26 @@ 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); }
 
@@ -491,8 +617,11 @@ button.toggle-button {
     background-color: var(--color-background-menu-link-hover);
     color: var(--color-text-menu-link-hover); }
 
+.tab-pane-inner {
+  scroll-margin-top: 200px; }
+
 section.content {
-  padding-top: 5em;
+  padding-top: 100px;
   padding-bottom: 1em;
   flex-direction: column;
   display: flex;
@@ -634,9 +763,6 @@ 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 +961,10 @@ 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 +1000,24 @@ 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 +1109,10 @@ 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 +1173,8 @@ 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 +1183,10 @@ 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 +1215,21 @@ 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 +1358,9 @@ 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
@@ -11,7 +12,6 @@ from threading import Lock
 import json
 import os
 import re
-import requests
 import secrets
 import threading
 import time
@@ -270,6 +270,7 @@ class ChangeDetectionStore:
         self.needs_write_urgent = True
 
     def add_watch(self, url, tag='', extras=None, tag_uuids=None, write_to_disk_now=True):
+        import requests
 
         if extras is None:
             extras = {}
@@ -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

@@ -11,8 +11,11 @@
     class="notification-urls" )
                             }}
                             <div class="pure-form-message-inline">
-                              <ul>
-                                <li>Use <a target=_new href="https://github.com/caronc/apprise">AppRise 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>.</li>
+                                <p>
+                                <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">
                                 <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>
@@ -40,7 +43,7 @@
 
                             </div>
                             <div class="pure-controls">
-                                <div id="notification-token-toggle" class="pure-button button-tag button-xsmall">Show token/placeholders</div>
+                                <div data-target="#notification-tokens-info" class="toggle-show pure-button button-tag button-xsmall">Show token/placeholders</div>
                             </div>
                             <div class="pure-controls" style="display: none;" id="notification-tokens-info">
                                 <table class="pure-table" id="token-table">

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>
@@ -68,7 +70,7 @@
                 <a href="{{ url_for('import_page')}}" class="pure-menu-link">IMPORT</a>
               </li>
               <li class="pure-menu-item">
-                <a href="{{ url_for('get_backup')}}" class="pure-menu-link">BACKUP</a>
+                <a href="{{ url_for('backups.index')}}" class="pure-menu-link">BACKUPS</a>
               </li>
             {% else %}
               <li class="pure-menu-item">
@@ -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/diff.html

@@ -14,7 +14,7 @@
 
 <div id="settings">
     <form class="pure-form " action="" method="GET" id="diff-form">
-        <fieldset>
+        <fieldset class="diff-fieldset">
             {% if versions|length >= 1 %}
                 <strong>Compare</strong>
                 <del class="change"><span>from</span></del>
@@ -33,7 +33,7 @@
                         </option>
                     {% endfor %}
                 </select>
-                <button type="submit" class="pure-button pure-button-primary">Go</button>
+                <button type="submit" class="pure-button pure-button-primary reset-margin">Go</button>
             {% endif %}
         </fieldset>
         <fieldset>

changedetectionio/templates/edit.html

@@ -4,6 +4,7 @@
 {% from '_common_fields.html' import render_common_settings_form %}
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='vis.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
 <script>
     const browser_steps_available_screenshots=JSON.parse('{{ watch.get_browsersteps_available_screenshots|tojson }}');
     const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
@@ -23,9 +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 %}
@@ -49,7 +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>
@@ -65,8 +65,8 @@
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.url, placeholder="https://...", required=true, class="m-d") }}
-                        <span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span><br>
-                        <span class="pure-form-message-inline">You can use variables in the URL, perfect for inserting the current date and other logic, <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a></span><br>
+                        <div class="pure-form-message">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></div>
+                        <div class="pure-form-message">Variables are supported in the URL (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
                     </div>
                     <div class="pure-control-group inline-radio">
                         {{ render_field(form.processor) }}
@@ -149,21 +149,24 @@
                             {{ render_field(form.method) }}
                         </div>
                         <div id="request-body">
-                                            {{ render_field(form.body, rows=5, placeholder="Example
+                                            {{ render_field(form.body, rows=7, placeholder="Example
 {
    \"name\":\"John\",
    \"age\":30,
-   \"car\":null
+   \"car\":null,
+   \"year\":{% now 'Europe/Berlin', '%Y' %}
 }") }}
                         </div>
+                        <div class="pure-form-message">Variables are supported in the request body (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
                     </div>
                 </fieldset>
             <!-- hmm -->
                 <div class="pure-control-group advanced-options"  style="display: none;">
-                    {{ render_field(form.headers, rows=5, placeholder="Example
+                    {{ render_field(form.headers, rows=7, placeholder="Example
 Cookie: foobar
-User-Agent: wonderbra 1.0") }}
-
+User-Agent: wonderbra 1.0
+Math: {{ 1 + 1 }}") }}
+                        <div class="pure-form-message">Variables are supported in the request header values (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
                         <div class="pure-form-message-inline">
                             {% if has_extra_headers_file %}
                                 <strong>Alert! Extra headers file found and will be added to this watch!</strong>
@@ -199,7 +202,7 @@ 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" >
@@ -214,7 +217,7 @@ 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>
@@ -253,7 +256,10 @@ 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>
@@ -275,9 +281,9 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                         {% if '/text()' in  field %}
                           <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br>
                         {% endif %}
-                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br>
-
-                    <ul>
+                        <span class="pure-form-message-inline">One CSS, xPath, JSON Path/JQ selector per line, <i>any</i> rules that matches will be used.<br>
+<p><div data-target="#advanced-help-selectors" class="toggle-show pure-button button-tag button-xsmall">Show advanced help and tips</div><br></p>
+                    <ul id="advanced-help-selectors" style="display: none;">
                         <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
                         <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
                             <ul>
@@ -297,21 +303,25 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                                 <li>To use XPath1.0: Prefix with <code>xpath1:</code></li>
                             </ul>
                             </li>
-                    </ul>
-                    Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
+                    <li>
+                        Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
                                 href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
+                    </li>
+                    </ul>
+
                 </span>
                     </div>
                 <fieldset class="pure-control-group">
                     {{ render_field(form.subtractive_selectors, rows=5, placeholder=has_tag_filters_extra+"header
 footer
 nav
-.stockticker") }}
+.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>
@@ -322,18 +332,25 @@ 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">
@@ -356,10 +373,10 @@ 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>
 
@@ -383,7 +400,9 @@ 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;
@@ -403,7 +422,27 @@ 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

@@ -76,7 +76,7 @@
                     </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.empty_pages_are_a_change) }}
-                        <span class="pure-form-message-inline">When a page contains HTML, but no renderable text appears (empty page), is this considered a change?</span>
+                        <span class="pure-form-message-inline">When a request returns no content, or the HTML does not contain any text, is this considered a change?</span>
                     </div>
                 {% if form.requests.proxy %}
                     <div class="pure-control-group inline-radio">
@@ -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>
@@ -274,7 +276,7 @@ nav
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}
                     <a href="{{url_for('index')}}" class="pure-button button-small button-cancel">Back</a>
-                    <a href="{{url_for('clear_all_history')}}" class="pure-button button-small button-cancel">Clear Snapshot History</a>
+                    <a href="{{url_for('clear_all_history')}}" class="pure-button button-small button-error">Clear Snapshot History</a>
                 </div>
             </div>
         </form>

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/itemprop_test_examples/README.md

@@ -0,0 +1,6 @@
+# A list of real world examples!
+
+Always the price should be 666.66 for our tests
+
+see test_restock_itemprop.py::test_special_prop_examples
+

changedetectionio/tests/itemprop_test_examples/a.txt

@@ -0,0 +1,25 @@
+<div class="PriceSection PriceSection_PriceSection__Vx1_Q PriceSection_variantHuge__P9qxg PdpPriceSection"
+     data-testid="price-section"
+     data-optly-product-tile-price-section="true"><span
+        class="PriceRange ProductPrice variant-huge" itemprop="offers"
+        itemscope="" itemtype="http://schema.org/Offer"><div
+        class="VisuallyHidden_VisuallyHidden__VBD83">$155.55</div><span
+        aria-hidden="true" class="Price variant-huge" data-testid="price"
+        itemprop="price"><sup class="sup" data-testid="price-symbol"
+                              itemprop="priceCurrency" content="AUD">$</sup><span
+        class="dollars" data-testid="price-value" itemprop="price"
+        content="155.55">155.55</span><span class="extras"><span class="sup"
+                                                              data-testid="price-sup"></span></span></span></span>
+</div>
+
+<script type="application/ld+json">{
+                                "@type": "Product",
+                                "@context": "https://schema.org",
+                                "name": "test",
+                                "description": "test",
+                                "offers": {
+                                    "@type": "Offer",
+                                    "priceCurrency": "AUD",
+                                    "price": 155.55
+                                },
+                            }</script>

changedetectionio/tests/proxy_list/test_proxy.py

@@ -16,4 +16,4 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     )
 
     assert b"1 Imported" in res.data
-    time.sleep(3)
+    wait_for_all_checks(client)

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 json
 import os
-import time
 from flask import url_for
-from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
 
 
+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 +78,25 @@ 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
+
+    # PROXY CHECKER WIDGET CHECK - this needs more checking
+    uuid = extract_UUID_from_client(client)
+
+    res = client.get(
+        url_for("check_proxies.start_check", uuid=uuid),
+        follow_redirects=True
+    )
+    # It's probably already finished super fast :(
+    #assert b"RUNNING" in res.data
+    
+    wait_for_all_checks(client)
+    res = client.get(
+        url_for("check_proxies.get_recheck_status", uuid=uuid),
+        follow_redirects=True
+    )
+    assert b"OK" in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' 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/restock/test_restock.py

@@ -2,7 +2,7 @@
 import os
 import time
 from flask import url_for
-from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client, wait_for_notification_endpoint_output
 from changedetectionio.notification import (
     default_notification_body,
     default_notification_format,
@@ -94,7 +94,7 @@ def test_restock_detection(client, live_server, measure_memory_usage):
     assert b'not-in-stock' not in res.data
 
     # We should have a notification
-    time.sleep(2)
+    wait_for_notification_endpoint_output()
     assert os.path.isfile("test-datastore/notification.txt"), "Notification received"
     os.unlink("test-datastore/notification.txt")
 
@@ -103,6 +103,7 @@ def test_restock_detection(client, live_server, measure_memory_usage):
     set_original_response()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
+    time.sleep(5)
     assert not os.path.isfile("test-datastore/notification.txt"), "No notification should have fired when it went OUT OF STOCK by default"
 
     # BUT we should see that it correctly shows "not in stock"

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -2,7 +2,7 @@
 import os.path
 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, wait_for_notification_endpoint_output
 from changedetectionio import html_tools
 
 
@@ -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)
@@ -78,6 +77,8 @@ def test_check_removed_line_contains_trigger(client, live_server, measure_memory
 
     # The trigger line is REMOVED,  this should trigger
     set_original(excluding='The golden line')
+
+    # Check in the processor here what's going on, its triggering empty-reply and no change.
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
@@ -112,7 +113,7 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     res = client.post(
         url_for("settings_page"),
         data={"application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
-              "application-notification_body": 'triggered text was -{{triggered_text}}-',
+              "application-notification_body": 'triggered text was -{{triggered_text}}- 网站监测 内容更新了',
               # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
               "application-notification_urls": test_notification_url,
               "application-minutes_between_check": 180,
@@ -153,6 +154,7 @@ 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
@@ -165,12 +167,12 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     assert b'unviewed' in res.data
 
     # Takes a moment for apprise to fire
-    time.sleep(3)
+    wait_for_notification_endpoint_output()
     assert os.path.isfile("test-datastore/notification.txt"), "Notification fired because I can see the output file"
-    with open("test-datastore/notification.txt", 'r') as f:
-        response= f.read()
-        assert '-Oh yes please-' in response
-
+    with open("test-datastore/notification.txt", 'rb') as f:
+        response = f.read()
+        assert b'-Oh yes please-' in response
+        assert '网站监测 内容更新了'.encode('utf-8') in response
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/test_backend.py

@@ -69,6 +69,12 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
 
     wait_for_all_checks(client)
 
+    uuid = extract_UUID_from_client(client)
+
+    # Check the 'get latest snapshot works'
+    res = client.get(url_for("watch_get_latest_html", uuid=uuid))
+    assert b'which has this one new line' in res.data
+
     # Now something should be ready, indicated by having a 'unviewed' class
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
@@ -86,7 +92,7 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     assert expected_url.encode('utf-8') in res.data
 
     # Following the 'diff' link, it should no longer display as 'unviewed' even after we recheck it a few times
-    res = client.get(url_for("diff_history_page", uuid="first"))
+    res = client.get(url_for("diff_history_page", uuid=uuid))
     assert b'selected=""' in res.data, "Confirm diff history page loaded"
 
     # Check the [preview] pulls the right one
@@ -143,18 +149,12 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     assert b'unviewed' not in res.data
 
     # #2458 "clear history" should make the Watch object update its status correctly when the first snapshot lands again
-    uuid = extract_UUID_from_client(client)
     client.get(url_for("clear_watch_history", uuid=uuid))
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'preview/' in res.data
 
-
-    # Check the 'get latest snapshot works'
-    res = client.get(url_for("watch_get_latest_html", uuid=uuid))
-    assert b'<head><title>head title</title></head>' in res.data
-
     #
     # Cleanup everything
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

changedetectionio/tests/test_backup.py

@@ -26,8 +26,24 @@ def test_backup(client, live_server, measure_memory_usage):
     assert b"1 Imported" in res.data
     wait_for_all_checks(client)
 
+    # Launch the thread in the background to create the backup
     res = client.get(
-        url_for("get_backup"),
+        url_for("backups.request_backup"),
+        follow_redirects=True
+    )
+    time.sleep(2)
+
+    res = client.get(
+        url_for("backups.index"),
+        follow_redirects=True
+    )
+    # Can see the download link to the backup
+    assert b'<a href="/backups/download/changedetection-backup-20' in res.data
+    assert b'Remove backups' in res.data
+
+    # Get the latest one
+    res = client.get(
+        url_for("backups.download_backup", filename="latest"),
         follow_redirects=True
     )
 
@@ -44,3 +60,11 @@ def test_backup(client, live_server, measure_memory_usage):
 
     # Should be two txt files in the archive (history and the snapshot)
     assert len(newlist) == 2
+
+    # Get the latest one
+    res = client.get(
+        url_for("backups.remove_backups"),
+        follow_redirects=True
+    )
+
+    assert b'No backups found.' in res.data

changedetectionio/tests/test_block_while_text_present.py

@@ -65,11 +65,8 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
     live_server_setup(live_server)
     # Use a mix of case in ZzZ to prove it works case-insensitive.
     ignore_text = "out of stoCk\r\nfoobar"
-
     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)
@@ -127,13 +124,24 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
     assert b'unviewed' not in res.data
     assert b'/test-endpoint' in res.data
 
+    # 2548
+    # Going back to the ORIGINAL should NOT trigger a change
+    set_original_ignore_response()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
 
-    # Now we set a change where the text is gone, it should now trigger
+
+    # Now we set a change where the text is gone AND its different content, it should now trigger
     set_modified_response_minus_block_text()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
+
+
+
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/test_element_removal.py

@@ -5,12 +5,41 @@ import time
 from flask import url_for
 
 from ..html_tools import *
-from .util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
 
 
 def test_setup(live_server):
     live_server_setup(live_server)
 
+def set_response_with_multiple_index():
+    data= """<!DOCTYPE html>
+<html>
+<body>
+
+<!-- NOTE!! CHROME WILL ADD TBODY HERE IF ITS NOT THERE!! -->
+<table style="width:100%">
+  <tr>
+    <th>Person 1</th>
+    <th>Person 2</th>
+    <th>Person 3</th>
+  </tr>
+  <tr>
+    <td>Emil</td>
+    <td>Tobias</td>
+    <td>Linus</td>
+  </tr>
+  <tr>
+    <td>16</td>
+    <td>14</td>
+    <td>10</td>
+  </tr>
+</table>
+</body>
+</html>
+"""
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(data)
+
 
 def set_original_response():
     test_return_data = """<html>
@@ -87,6 +116,9 @@ 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 +126,16 @@ 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 (
@@ -107,12 +148,10 @@ across multiple lines
 
 
 def test_element_removal_full(client, live_server, measure_memory_usage):
-    sleep_time_for_fetch_thread = 3
+    #live_server_setup(live_server)
 
     set_original_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)
@@ -120,7 +159,8 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
         url_for("import_page"), data={"urls": test_url}, follow_redirects=True
     )
     assert b"1 Imported" in res.data
-    time.sleep(1)
+    wait_for_all_checks(client)
+
     # Goto the edit page, add the filter data
     # Not sure why \r needs to be added - absent of the #changetext this is not necessary
     subtractive_selectors_data = "header\r\nfooter\r\nnav\r\n#changetext"
@@ -136,6 +176,7 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
         follow_redirects=True,
     )
     assert b"Updated watch." in res.data
+    wait_for_all_checks(client)
 
     # Check it saved
     res = client.get(
@@ -144,10 +185,10 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
     assert bytes(subtractive_selectors_data.encode("utf-8")) in res.data
 
     # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
 
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # so that we set the state to 'unviewed' after all the edits
     client.get(url_for("diff_history_page", uuid="first"))
@@ -156,11 +197,70 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
     set_modified_response()
 
     # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
 
     # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # There should not be an unviewed change, as changes should be removed
     res = client.get(url_for("index"))
     assert b"unviewed" not in res.data
+
+# Re #2752
+def test_element_removal_nth_offset_no_shift(client, live_server, measure_memory_usage):
+    #live_server_setup(live_server)
+
+    set_response_with_multiple_index()
+    subtractive_selectors_data = ["""
+body > table > tr:nth-child(1) > th:nth-child(2)
+body > table >  tr:nth-child(2) > td:nth-child(2)
+body > table > tr:nth-child(3) > td:nth-child(2)
+body > table > tr:nth-child(1) > th:nth-child(3)
+body > table >  tr:nth-child(2) > td:nth-child(3)
+body > table > tr:nth-child(3) > td:nth-child(3)""",
+"""//body/table/tr[1]/th[2]
+//body/table/tr[2]/td[2]
+//body/table/tr[3]/td[2]
+//body/table/tr[1]/th[3]
+//body/table/tr[2]/td[3]
+//body/table/tr[3]/td[3]"""]
+
+    for selector_list in subtractive_selectors_data:
+
+        res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+        assert b'Deleted' in res.data
+
+        # 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)
+
+        res = client.post(
+            url_for("edit_page", uuid="first"),
+            data={
+                "subtractive_selectors": selector_list,
+                "url": test_url,
+                "tags": "",
+                "fetch_backend": "html_requests",
+            },
+            follow_redirects=True,
+        )
+        assert b"Updated watch." in res.data
+        wait_for_all_checks(client)
+
+        res = client.get(
+            url_for("preview_page", uuid="first"),
+            follow_redirects=True
+        )
+
+        assert b"Tobias" not in res.data
+        assert b"Linus" not in res.data
+        assert b"Person 2" not in res.data
+        assert b"Person 3" not in res.data
+        # First column should exist
+        assert b"Emil" in res.data
+

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_exist_changes.py

@@ -4,7 +4,7 @@
 import os
 import time
 from flask import url_for
-from .util import set_original_response, live_server_setup
+from .util import set_original_response, live_server_setup, wait_for_notification_endpoint_output
 from changedetectionio.model import App
 
 
@@ -102,14 +102,15 @@ def test_filter_doesnt_exist_then_exists_should_get_notification(client, live_se
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
-    time.sleep(3)
+    wait_for_notification_endpoint_output()
 
     # Shouldn't exist, shouldn't have fired
     assert not os.path.isfile("test-datastore/notification.txt")
     # Now the filter should exist
     set_response_with_filter()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(3)
+
+    wait_for_notification_endpoint_output()
 
     assert os.path.isfile("test-datastore/notification.txt")
 

changedetectionio/tests/test_filter_failure_notification.py

@@ -1,7 +1,9 @@
 import os
 import time
+from loguru import logger
 from flask import url_for
-from .util import set_original_response, live_server_setup, extract_UUID_from_client, wait_for_all_checks
+from .util import set_original_response, live_server_setup, extract_UUID_from_client, wait_for_all_checks, \
+    wait_for_notification_endpoint_output
 from changedetectionio.model import App
 
 
@@ -26,6 +28,12 @@ def run_filter_test(client, live_server, content_filter):
     # Response WITHOUT the filter ID element
     set_original_response()
 
+    # Goto the edit page, add our ignore text
+    notification_url = url_for('test_notification_endpoint', _external=True).replace('http', 'json')
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+
     # cleanup for the next
     client.get(
         url_for("form_delete", uuid="all"),
@@ -34,83 +42,92 @@ def run_filter_test(client, live_server, content_filter):
     if os.path.isfile("test-datastore/notification.txt"):
         os.unlink("test-datastore/notification.txt")
 
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
     res = client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": test_url, "tags": ''},
+        url_for("import_page"),
+        data={"urls": test_url},
         follow_redirects=True
     )
 
-    assert b"Watch added" in res.data
-
-    # Give the thread time to pick up the first version
+    assert b"1 Imported" in res.data
     wait_for_all_checks(client)
 
-    # Goto the edit page, add our ignore text
-    # Add our URL to the import page
-    url = url_for('test_notification_endpoint', _external=True)
-    notification_url = url.replace('http', 'json')
+    uuid = extract_UUID_from_client(client)
 
-    print(">>>> Notification URL: " + notification_url)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid]['consecutive_filter_failures'] == 0, "No filter = No filter failure"
 
-    # Just a regular notification setting, this will be used by the special 'filter not found' notification
-    notification_form_data = {"notification_urls": notification_url,
-                              "notification_title": "New ChangeDetection.io Notification - {{watch_url}}",
-                              "notification_body": "BASE URL: {{base_url}}\n"
-                                                   "Watch URL: {{watch_url}}\n"
-                                                   "Watch UUID: {{watch_uuid}}\n"
-                                                   "Watch title: {{watch_title}}\n"
-                                                   "Watch tag: {{watch_tag}}\n"
-                                                   "Preview: {{preview_url}}\n"
-                                                   "Diff URL: {{diff_url}}\n"
-                                                   "Snapshot: {{current_snapshot}}\n"
-                                                   "Diff: {{diff}}\n"
-                                                   "Diff Full: {{diff_full}}\n"
-                                                   "Diff as Patch: {{diff_patch}}\n"
-                                                   ":-)",
-                              "notification_format": "Text"}
+    watch_data = {"notification_urls": notification_url,
+                  "notification_title": "New ChangeDetection.io Notification - {{watch_url}}",
+                  "notification_body": "BASE URL: {{base_url}}\n"
+                                       "Watch URL: {{watch_url}}\n"
+                                       "Watch UUID: {{watch_uuid}}\n"
+                                       "Watch title: {{watch_title}}\n"
+                                       "Watch tag: {{watch_tag}}\n"
+                                       "Preview: {{preview_url}}\n"
+                                       "Diff URL: {{diff_url}}\n"
+                                       "Snapshot: {{current_snapshot}}\n"
+                                       "Diff: {{diff}}\n"
+                                       "Diff Full: {{diff_full}}\n"
+                                       "Diff as Patch: {{diff_patch}}\n"
+                                       ":-)",
+                  "notification_format": "Text",
+                  "fetch_backend": "html_requests",
+                  "filter_failure_notification_send": 'y',
+                  "headers": "",
+                  "tags": "my tag",
+                  "title": "my title 123",
+                  "time_between_check-hours": 5,  # So that the queue runner doesnt also put it in
+                  "url": test_url,
+                  }
 
-    notification_form_data.update({
-        "url": test_url,
-        "tags": "my tag",
-        "title": "my title 123",
-        "headers": "",
-        "filter_failure_notification_send": 'y',
-        "include_filters": content_filter,
-        "fetch_backend": "html_requests"})
-
-    # A POST here will also reset the filter failure counter (filter_failure_notification_threshold_attempts)
     res = client.post(
-        url_for("edit_page", uuid="first"),
-        data=notification_form_data,
+        url_for("edit_page", uuid=uuid),
+        data=watch_data,
         follow_redirects=True
     )
-
     assert b"Updated watch." in res.data
     wait_for_all_checks(client)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid]['consecutive_filter_failures'] == 0, "No filter = No filter failure"
 
-    # Now the notification should not exist, because we didnt reach the threshold
+    # Now add a filter, because recheck hours == 5, ONLY pressing of the [edit] or [recheck all] should trigger
+    watch_data['include_filters'] = content_filter
+    res = client.post(
+        url_for("edit_page", uuid=uuid),
+        data=watch_data,
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+
+    # It should have checked once so far and given this error (because we hit SAVE)
+
+    wait_for_all_checks(client)
     assert not os.path.isfile("test-datastore/notification.txt")
 
+    # Hitting [save] would have triggered a recheck, and we have a filter, so this would be ONE failure
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid]['consecutive_filter_failures'] == 1, "Should have been checked once"
+
     # recheck it up to just before the threshold, including the fact that in the previous POST it would have rechecked (and incremented)
-    for i in range(0, App._FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT-2):
+    # Add 4 more checks
+    checked = 0
+    ATTEMPT_THRESHOLD_SETTING = live_server.app.config['DATASTORE'].data['settings']['application'].get('filter_failure_notification_threshold_attempts', 0)
+    for i in range(0, ATTEMPT_THRESHOLD_SETTING - 2):
+        checked += 1
         client.get(url_for("form_watch_checknow"), follow_redirects=True)
         wait_for_all_checks(client)
-        time.sleep(2) # delay for apprise to fire
-        assert not os.path.isfile("test-datastore/notification.txt"), f"test-datastore/notification.txt should not exist - Attempt {i} when threshold is {App._FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT}"
-
-    # We should see something in the frontend
-    res = client.get(url_for("index"))
-    assert b'Warning, no filters were found' in res.data
+        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)
-    time.sleep(2)  # delay for apprise to fire
+    wait_for_notification_endpoint_output()
+
     # Now it should exist and contain our "filter not found" alert
     assert os.path.isfile("test-datastore/notification.txt")
-
     with open("test-datastore/notification.txt", 'r') as f:
         notification = f.read()
 
@@ -123,10 +140,11 @@ def run_filter_test(client, live_server, content_filter):
     set_response_with_filter()
 
     # Try several times, it should NOT have 'filter not found'
-    for i in range(0, App._FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT):
+    for i in range(0, ATTEMPT_THRESHOLD_SETTING + 2):
         client.get(url_for("form_watch_checknow"), follow_redirects=True)
         wait_for_all_checks(client)
 
+    wait_for_notification_endpoint_output()
     # It should have sent a notification, but..
     assert os.path.isfile("test-datastore/notification.txt")
     # but it should not contain the info about a failed filter (because there was none in this case)
@@ -135,9 +153,6 @@ def run_filter_test(client, live_server, content_filter):
     assert not 'CSS/xPath filter was not present in the page' in notification
 
     # Re #1247 - All tokens got replaced correctly in the notification
-    res = client.get(url_for("index"))
-    uuid = extract_UUID_from_client(client)
-    # UUID is correct, but notification contains tag uuid as UUIID wtf
     assert uuid in notification
 
     # cleanup for the next
@@ -152,9 +167,11 @@ def test_setup(live_server):
     live_server_setup(live_server)
 
 def test_check_include_filters_failure_notification(client, live_server, measure_memory_usage):
+#    live_server_setup(live_server)
     run_filter_test(client, live_server,'#nope-doesnt-exist')
 
 def test_check_xpath_filter_failure_notification(client, live_server, measure_memory_usage):
+#    live_server_setup(live_server)
     run_filter_test(client, live_server, '//*[@id="nope-doesnt-exist"]')
 
 # Test that notification is never sent

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_live_preview.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+
+from flask import url_for
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+
+
+def set_response():
+
+    data = f"""<html>
+       <body>Awesome, you made it<br>
+yeah the socks request worked<br>
+something to ignore<br>
+something to trigger<br>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(data)
+
+def test_content_filter_live_preview(client, live_server, measure_memory_usage):
+    live_server_setup(live_server)
+    set_response()
+
+    test_url = url_for('test_endpoint', _external=True)
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": ''},
+        follow_redirects=True
+    )
+    uuid = extract_UUID_from_client(client)
+    res = client.post(
+        url_for("edit_page", uuid=uuid),
+        data={
+            "include_filters": "",
+            "fetch_backend": 'html_requests',
+            "ignore_text": "something to ignore",
+            "trigger_text": "something to trigger",
+            "url": test_url,
+        },
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    wait_for_all_checks(client)
+
+    # The endpoint is a POST and accepts the form values to override the watch preview
+    import json
+
+    # DEFAULT OUTPUT WITHOUT ANYTHING UPDATED/CHANGED - SHOULD SEE THE WATCH DEFAULTS
+    res = client.post(
+        url_for("watch_get_preview_rendered", uuid=uuid)
+    )
+    default_return = json.loads(res.data.decode('utf-8'))
+    assert default_return.get('after_filter')
+    assert default_return.get('before_filter')
+    assert default_return.get('ignore_line_numbers') == [3] # "something to ignore" line 3
+    assert default_return.get('trigger_line_numbers') == [4] # "something to trigger" line 4
+
+    # SEND AN UPDATE AND WE SHOULD SEE THE OUTPUT CHANGE SO WE KNOW TO HIGHLIGHT NEW STUFF
+    res = client.post(
+        url_for("watch_get_preview_rendered", uuid=uuid),
+        data={
+            "include_filters": "",
+            "fetch_backend": 'html_requests',
+            "ignore_text": "sOckS", # Also be sure case insensitive works
+            "trigger_text": "AweSOme",
+            "url": test_url,
+        },
+    )
+    reply = json.loads(res.data.decode('utf-8'))
+    assert reply.get('after_filter')
+    assert reply.get('before_filter')
+    assert reply.get('ignore_line_numbers') == [2]  # Ignored - "socks" on line 2
+    assert reply.get('trigger_line_numbers') == [1]  # Triggers "Awesome" in line 1
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_nonrenderable_pages.py

@@ -1,11 +1,8 @@
 #!/usr/bin/env python3
 
-import time
 from flask import url_for
-from urllib.request import urlopen
-from .util import set_original_response, set_modified_response, live_server_setup
-
-sleep_time_for_fetch_thread = 3
+from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
+import time
 
 
 def set_nonrenderable_response():
@@ -16,12 +13,18 @@ def set_nonrenderable_response():
      </body>
      </html>
     """
-
     with open("test-datastore/endpoint-content.txt", "w") as f:
         f.write(test_return_data)
+    time.sleep(1)
 
     return None
 
+def set_zero_byte_response():
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write("")
+    time.sleep(1)
+    return None
+
 def test_check_basic_change_detection_functionality(client, live_server, measure_memory_usage):
     set_original_response()
     live_server_setup(live_server)
@@ -35,18 +38,11 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
 
     assert b"1 Imported" in res.data
 
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
-    # Do this a few times.. ensures we dont accidently set the status
-    for n in range(3):
-        client.get(url_for("form_watch_checknow"), follow_redirects=True)
-
-        # Give the thread time to pick it up
-        time.sleep(sleep_time_for_fetch_thread)
-
-        # It should report nothing found (no new 'unviewed' class)
-        res = client.get(url_for("index"))
-        assert b'unviewed' not in res.data
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
 
 
     #####################
@@ -64,7 +60,7 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     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"))
@@ -86,14 +82,20 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     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' in res.data
+    client.get(url_for("mark_all_viewed"), follow_redirects=True)
 
-
-
+    # A totally zero byte (#2528) response should also not trigger an error
+    set_zero_byte_response()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data # A change should have registered because empty_pages_are_a_change is ON
+    assert b'fetch-error' not in res.data
 
     #
     # Cleanup everything

changedetectionio/tests/test_notification.py

@@ -284,18 +284,18 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
     # CUSTOM JSON BODY CHECK for POST://
     set_original_response()
     # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#header-manipulation
-    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?xxx={{ watch_url }}&+custom-header=123"
+    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?xxx={{ watch_url }}&+custom-header=123&+second=hello+world%20%22space%22"
 
     res = client.post(
         url_for("settings_page"),
         data={
               "application-fetch_backend": "html_requests",
               "application-minutes_between_check": 180,
-              "application-notification_body": '{ "url" : "{{ watch_url }}", "secret": 444 }',
+              "application-notification_body": '{ "url" : "{{ watch_url }}", "secret": 444, "somebug": "网站监测 内容更新了" }',
               "application-notification_format": default_notification_format,
               "application-notification_urls": test_notification_url,
               # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
-              "application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
+              "application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }} ",
               },
         follow_redirects=True
     )
@@ -324,6 +324,8 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
         j = json.loads(x)
         assert j['url'].startswith('http://localhost')
         assert j['secret'] == 444
+        assert j['somebug'] == '网站监测 内容更新了'
+
 
     # URL check, this will always be converted to lowercase
     assert os.path.isfile("test-datastore/notification-url.txt")
@@ -336,6 +338,7 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
     with open("test-datastore/notification-headers.txt", 'r') as f:
         notification_headers = f.read()
         assert 'custom-header: 123' in notification_headers.lower()
+        assert 'second: hello world "space"' in notification_headers.lower()
 
 
     # Should always be automatically detected as JSON content type even when we set it as 'Text' (default)
@@ -354,9 +357,10 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
 #2510
 def test_global_send_test_notification(client, live_server, measure_memory_usage):
 
-
     #live_server_setup(live_server)
     set_original_response()
+    if os.path.isfile("test-datastore/notification.txt"):
+        os.unlink("test-datastore/notification.txt")
 
     # otherwise other settings would have already existed from previous tests in this file
     res = client.post(
@@ -364,7 +368,8 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
         data={
             "application-fetch_backend": "html_requests",
             "application-minutes_between_check": 180,
-            "application-notification_body": 'change detection is cool',
+            #1995 UTF-8 content should be encoded
+            "application-notification_body": 'change detection is cool 网站监测 内容更新了',
             "application-notification_format": default_notification_format,
             "application-notification_urls": "",
             "application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
@@ -399,8 +404,7 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
 
     with open("test-datastore/notification.txt", 'r') as f:
         x = f.read()
-        assert 'change detection is coo' in x
-
+        assert 'change detection is cool 网站监测 内容更新了' in x
 
     os.unlink("test-datastore/notification.txt")
 
@@ -420,10 +424,22 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
     with open("test-datastore/notification.txt", 'r') as f:
         x = f.read()
         # Should come from notification.py default handler when there is no notification body to pull from
-        assert 'change detection is coo' in x
+        assert 'change detection is cool 网站监测 内容更新了' in x
 
     client.get(
         url_for("form_delete", uuid="all"),
         follow_redirects=True
     )
 
+    ######### Test global/system settings - When everything is deleted it should give a helpful error
+    # See #2727
+    res = client.post(
+        url_for("ajax_callback_send_notification_test")+"?mode=global-settings",
+        data={"notification_urls": test_notification_url},
+        follow_redirects=True
+    )
+    assert res.status_code == 400
+    assert b"Error: You must have atleast one watch configured for 'test notification' to work" in res.data
+
+
+

changedetectionio/tests/test_preview_endpoints.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+
+import time
+from flask import url_for
+from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
+
+
+# `subtractive_selectors` should still work in `source:` type requests
+def test_fetch_pdf(client, live_server, measure_memory_usage):
+    import shutil
+    shutil.copy("tests/test.pdf", "test-datastore/endpoint-test.pdf")
+
+    live_server_setup(live_server)
+    test_url = url_for('test_pdf_endpoint', _external=True)
+    # Add our URL to the import page
+    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)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    # PDF header should not be there (it was converted to text)
+    assert b'PDF' not in res.data[:10]
+    assert b'hello world' in res.data
+
+    # So we know if the file changes in other ways
+    import hashlib
+    original_md5 = hashlib.md5(open("test-datastore/endpoint-test.pdf", 'rb').read()).hexdigest().upper()
+    # We should have one
+    assert len(original_md5) > 0
+    # And it's going to be in the document
+    assert b'Document checksum - ' + bytes(str(original_md5).encode('utf-8')) in res.data
+
+    shutil.copy("tests/test2.pdf", "test-datastore/endpoint-test.pdf")
+    changed_md5 = hashlib.md5(open("test-datastore/endpoint-test.pdf", 'rb').read()).hexdigest().upper()
+    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)
+
+    # Now something should be ready, indicated by having a 'unviewed' class
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    # The original checksum should be not be here anymore (cdio adds it to the bottom of the text)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert original_md5.encode('utf-8') not in res.data
+    assert changed_md5.encode('utf-8') in res.data
+
+    res = client.get(
+        url_for("diff_history_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert original_md5.encode('utf-8') in res.data
+    assert changed_md5.encode('utf-8') in res.data
+
+    assert b'here is a change' in res.data

changedetectionio/tests/test_request.py

@@ -45,7 +45,7 @@ def test_headers_in_request(client, live_server, measure_memory_usage):
               "url": test_url,
               "tags": "",
               "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
-              "headers": "xxx:ooo\ncool:yeah\r\ncookie:"+cookie_header},
+              "headers": "jinja2:{{ 1+1 }}\nxxx:ooo\ncool:yeah\r\ncookie:"+cookie_header},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -61,6 +61,7 @@ def test_headers_in_request(client, live_server, measure_memory_usage):
     )
 
     # Flask will convert the header key to uppercase
+    assert b"Jinja2:2" in res.data
     assert b"Xxx:ooo" in res.data
     assert b"Cool:yeah" in res.data
 
@@ -117,7 +118,8 @@ def test_body_in_request(client, live_server, measure_memory_usage):
     wait_for_all_checks(client)
 
     # Now the change which should trigger a change
-    body_value = 'Test Body Value'
+    body_value = 'Test Body Value {{ 1+1 }}'
+    body_value_formatted = 'Test Body Value 2'
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={
@@ -140,8 +142,9 @@ def test_body_in_request(client, live_server, measure_memory_usage):
 
     # If this gets stuck something is wrong, something should always be there
     assert b"No history found" not in res.data
-    # We should see what we sent in the reply
-    assert str.encode(body_value) in res.data
+    # We should see the formatted value of what we sent in the reply
+    assert str.encode(body_value) not in res.data
+    assert str.encode(body_value_formatted) in res.data
 
     ####### data sanity checks
     # Add the test URL twice, we will check

changedetectionio/tests/test_restock_itemprop.py

@@ -3,7 +3,7 @@ import os
 import time
 
 from flask import url_for
-from .util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+from .util import live_server_setup, wait_for_all_checks, wait_for_notification_endpoint_output, extract_UUID_from_client
 from ..notification import default_notification_format
 
 instock_props = [
@@ -146,14 +146,13 @@ def _run_test_minmax_limit(client, extra_watch_edit_form):
         data={"url": test_url, "tags": 'restock tests', 'processor': 'restock_diff'},
         follow_redirects=True
     )
-
-    # A change in price, should trigger a change by default
     wait_for_all_checks(client)
 
     data = {
         "tags": "",
         "url": test_url,
         "headers": "",
+        "time_between_check-hours": 5,
         'fetch_backend': "html_requests"
     }
     data.update(extra_watch_edit_form)
@@ -178,11 +177,9 @@ def _run_test_minmax_limit(client, extra_watch_edit_form):
     assert b'1,000.45' or b'1000.45' in res.data #depending on locale
     assert b'unviewed' not in res.data
 
-
     # price changed to something LESS than min (900), SHOULD be a change
     set_original_response(props_markup=instock_props[0], price='890.45')
-    # let previous runs wait
-    time.sleep(1)
+
     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)
@@ -197,7 +194,8 @@ def _run_test_minmax_limit(client, extra_watch_edit_form):
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
-    assert b'1,890.45' or b'1890.45' in res.data
+    # Depending on the LOCALE it may be either of these (generally for US/default/etc)
+    assert b'1,890.45' in res.data or b'1890.45' in res.data
     assert b'unviewed' in res.data
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
@@ -362,13 +360,19 @@ def test_change_with_notification_values(client, live_server):
     set_original_response(props_markup=instock_props[0], price='1950.45')
     client.get(url_for("form_watch_checknow"))
     wait_for_all_checks(client)
-    time.sleep(3)
+    wait_for_notification_endpoint_output()
     assert os.path.isfile("test-datastore/notification.txt"), "Notification received"
     with open("test-datastore/notification.txt", 'r') as f:
         notification = f.read()
         assert "new price 1950.45" in notification
         assert "title new price 1950.45" in notification
 
+    ## Now test the "SEND TEST NOTIFICATION" is working
+    os.unlink("test-datastore/notification.txt")
+    uuid = extract_UUID_from_client(client)
+    res = client.post(url_for("ajax_callback_send_notification_test", watch_uuid=uuid), data={}, follow_redirects=True)
+    time.sleep(5)
+    assert os.path.isfile("test-datastore/notification.txt"), "Notification received"
 
 
 def test_data_sanity(client, live_server):
@@ -415,3 +419,31 @@ def test_data_sanity(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"))
     assert test_url2.encode('utf-8') in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+# All examples should give a prive of 666.66
+def test_special_prop_examples(client, live_server):
+    import glob
+    #live_server_setup(live_server)
+
+    test_url = url_for('test_endpoint', _external=True)
+    check_path = os.path.join(os.path.dirname(__file__), "itemprop_test_examples", "*.txt")
+    files = glob.glob(check_path)
+    assert files
+    for test_example_filename in files:
+        with open(test_example_filename, 'r') as example_f:
+            with open("test-datastore/endpoint-content.txt", "w") as test_f:
+                test_f.write(f"<html><body>{example_f.read()}</body></html>")
+
+            # Now fetch it and check the price worked
+            client.post(
+                url_for("form_quick_watch_add"),
+                data={"url": test_url, "tags": 'restock tests', 'processor': 'restock_diff'},
+                follow_redirects=True
+            )
+            wait_for_all_checks(client)
+            res = client.get(url_for("index"))
+            assert b'ception' not in res.data
+            assert b'155.55' in res.data

changedetectionio/tests/test_security.py

@@ -61,10 +61,10 @@ def test_bad_access(client, live_server, measure_memory_usage):
     assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
 
 
-def test_file_access(client, live_server, measure_memory_usage):
+def test_file_slashslash_access(client, live_server, measure_memory_usage):
     #live_server_setup(live_server)
 
-    test_file_path = "/tmp/test-file.txt"
+    test_file_path = os.path.abspath(__file__)
 
     # file:// is permitted by default, but it will be caught by ALLOW_FILE_URI
     client.post(
@@ -82,8 +82,30 @@ def test_file_access(client, live_server, measure_memory_usage):
             follow_redirects=True
         )
 
-        # Should see something (this file added by run_basic_tests.sh)
-        assert b"Hello world" in res.data
+        assert b"test_file_slashslash_access" in res.data
+    else:
+        # Default should be here
+        assert b'file:// type access is denied for security reasons.' in res.data
+
+def test_file_slash_access(client, live_server, measure_memory_usage):
+    #live_server_setup(live_server)
+
+    test_file_path = os.path.abspath(__file__)
+
+    # file:// is permitted by default, but it will be caught by ALLOW_FILE_URI
+    client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": f"file:/{test_file_path}", "tags": ''},
+        follow_redirects=True
+    )
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+
+    # If it is enabled at test time
+    if strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
+        # So it should permit it, but it should fall back to the 'requests' library giving an error
+        # (but means it gets passed to playwright etc)
+        assert b"URLs with hostname components are not permitted" in res.data
     else:
         # Default should be here
         assert b'file:// type access is denied for security reasons.' 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

@@ -76,6 +76,18 @@ def set_more_modified_response():
     return None
 
 
+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)
+        if isfile("test-datastore/notification.txt"):
+            return True
+
+    return False
+
+
 # kinda funky, but works for now
 def extract_api_key_from_UI(client):
     import re

changedetectionio/update_worker.py

@@ -1,6 +1,5 @@
 from .processors.exceptions import ProcessorException
-from . import content_fetchers
-
+import changedetectionio.content_fetchers.exceptions as content_fetchers_exceptions
 from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
 from changedetectionio import html_tools
 
@@ -82,7 +81,8 @@ class update_worker(threading.Thread):
             'watch_url': watch.get('url') if watch else None,
         })
 
-        n_object.update(watch.extra_notification_token_values())
+        if watch:
+            n_object.update(watch.extra_notification_token_values())
 
         logger.trace(f"Main rendered notification placeholders (diff_added etc) calculated in {time.time()-now:.3f}s")
         logger.debug("Queued notification for sending")
@@ -190,7 +190,9 @@ class update_worker(threading.Thread):
                 'screenshot': None
             })
             self.notification_q.put(n_object)
-            logger.error(f"Sent filter not found notification for {watch_uuid}")
+            logger.debug(f"Sent filter not found notification for {watch_uuid}")
+        else:
+            logger.debug(f"NOT sending filter not found notification for {watch_uuid} - no notification URLs")
 
     def send_step_failure_notification(self, watch_uuid, step_n):
         watch = self.datastore.data['watching'].get(watch_uuid, False)
@@ -259,9 +261,6 @@ class update_worker(threading.Thread):
                     try:
                         # Processor is what we are using for detecting the "Change"
                         processor = watch.get('processor', 'text_json_diff')
-                        # Abort processing when the content was the same as the last fetch
-                        skip_when_same_checksum = queued_item_data.item.get('skip_when_checksum_same')
-
 
                         # Init a new 'difference_detection_processor', first look in processors
                         processor_module_name = f"changedetectionio.processors.{processor}.processor"
@@ -277,16 +276,13 @@ class update_worker(threading.Thread):
 
                         update_handler.call_browser()
 
-                        changed_detected, update_obj, contents = update_handler.run_changedetection(
-                            watch=watch,
-                            skip_when_checksum_same=skip_when_same_checksum,
-                        )
+                        changed_detected, update_obj, contents = update_handler.run_changedetection(watch=watch)
 
                         # 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))
@@ -301,7 +297,7 @@ class update_worker(threading.Thread):
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': e.message})
                         process_changedetection_results = False
 
-                    except content_fetchers.exceptions.ReplyWithContentButNoText as e:
+                    except content_fetchers_exceptions.ReplyWithContentButNoText as e:
                         # Totally fine, it's by choice - just continue on, nothing more to care about
                         # Page had elements/content but no renderable text
                         # Backend (not filters) gave zero output
@@ -327,7 +323,7 @@ class update_worker(threading.Thread):
                             
                         process_changedetection_results = False
 
-                    except content_fetchers.exceptions.Non200ErrorCodeReceived as e:
+                    except content_fetchers_exceptions.Non200ErrorCodeReceived as e:
                         if e.status_code == 403:
                             err_text = "Error - 403 (Access denied) received"
                         elif e.status_code == 404:
@@ -337,7 +333,8 @@ 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)
@@ -365,38 +362,42 @@ class update_worker(threading.Thread):
 
                         # Only when enabled, send the notification
                         if watch.get('filter_failure_notification_send', False):
-                            c = watch.get('consecutive_filter_failures', 5)
+                            c = watch.get('consecutive_filter_failures', 0)
                             c += 1
                             # Send notification if we reached the threshold?
-                            threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts',
-                                                                                           0)
-                            logger.warning(f"Filter for {uuid} not found, consecutive_filter_failures: {c}")
-                            if threshold > 0 and c >= threshold:
+                            threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts', 0)
+                            logger.debug(f"Filter for {uuid} not found, consecutive_filter_failures: {c} of threshold {threshold}")
+                            if c >= threshold:
                                 if not watch.get('notification_muted'):
+                                    logger.debug(f"Sending filter failed notification for {uuid}")
                                     self.send_filter_failure_notification(uuid)
                                 c = 0
+                                logger.debug(f"Reset filter failure count back to zero")
 
                             self.datastore.update_watch(uuid=uuid, update_obj={'consecutive_filter_failures': c})
+                        else:
+                            logger.trace(f"{uuid} - filter_failure_notification_send not enabled, skipping")
+
 
                         process_changedetection_results = False
 
-                    except content_fetchers.exceptions.checksumFromPreviousCheckWasTheSame as e:
+                    except content_fetchers_exceptions.checksumFromPreviousCheckWasTheSame as e:
                         # Yes fine, so nothing todo, don't continue to process.
                         process_changedetection_results = False
                         changed_detected = False
-                    except content_fetchers.exceptions.BrowserConnectError as e:
+                    except content_fetchers_exceptions.BrowserConnectError as e:
                         self.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': e.msg
                                                                 }
                                                     )
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.BrowserFetchTimedOut as e:
+                    except content_fetchers_exceptions.BrowserFetchTimedOut as e:
                         self.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': e.msg
                                                                 }
                                                     )
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.BrowserStepsStepException as e:
+                    except content_fetchers_exceptions.BrowserStepsStepException as e:
 
                         if not self.datastore.data['watching'].get(uuid):
                             continue
@@ -423,7 +424,7 @@ class update_worker(threading.Thread):
                                                     )
 
                         if watch.get('filter_failure_notification_send', False):
-                            c = watch.get('consecutive_filter_failures', 5)
+                            c = watch.get('consecutive_filter_failures', 0)
                             c += 1
                             # Send notification if we reached the threshold?
                             threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts',
@@ -438,25 +439,25 @@ class update_worker(threading.Thread):
 
                         process_changedetection_results = False
 
-                    except content_fetchers.exceptions.EmptyReply as e:
+                    except content_fetchers_exceptions.EmptyReply as e:
                         # Some kind of custom to-str handler in the exception handler that does this?
                         err_text = "EmptyReply - try increasing 'Wait seconds before extracting text', Status Code {}".format(e.status_code)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.ScreenshotUnavailable as e:
+                    except content_fetchers_exceptions.ScreenshotUnavailable as e:
                         err_text = "Screenshot unavailable, page did not render fully in the expected time or page was too long - try increasing 'Wait seconds before extracting text'"
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.JSActionExceptions as e:
+                    except content_fetchers_exceptions.JSActionExceptions as e:
                         err_text = "Error running JS Actions - Page request - "+e.message
                         if e.screenshot:
                             watch.save_screenshot(screenshot=e.screenshot, as_error=True)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.PageUnloadable as e:
+                    except content_fetchers_exceptions.PageUnloadable as e:
                         err_text = "Page request from server didnt respond correctly"
                         if e.message:
                             err_text = "{} - {}".format(err_text, e.message)
@@ -468,7 +469,7 @@ class update_worker(threading.Thread):
                                                                            'last_check_status': e.status_code,
                                                                            'has_ldjson_price_data': None})
                         process_changedetection_results = False
-                    except content_fetchers.exceptions.BrowserStepsInUnsupportedFetcher as e:
+                    except content_fetchers_exceptions.BrowserStepsInUnsupportedFetcher as e:
                         err_text = "This watch has Browser Steps configured and so it cannot run with the 'Basic fast Plaintext/HTTP Client', either remove the Browser Steps or select a Chrome fetcher."
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
                         process_changedetection_results = False
@@ -486,6 +487,8 @@ 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

@@ -18,7 +18,7 @@ services:
   #
   #        Log levels are in descending order. (TRACE is the most detailed one)
   #        Log output levels: TRACE, DEBUG(default), INFO, SUCCESS, WARNING, ERROR, CRITICAL
-  #      - LOGGER_LEVEL=DEBUG
+  #      - LOGGER_LEVEL=TRACE
   #
   #       Alternative WebDriver/selenium URL, do not use "'s or 's!
   #      - WEBDRIVER_URL=http://browser-chrome:4444/wd/hub
@@ -29,8 +29,9 @@ services:
   #
   #             https://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.common.proxy
   #
-  #       Alternative Playwright URL, do not use "'s or 's!
-  #      - PLAYWRIGHT_DRIVER_URL=ws://playwright-chrome:3000
+  #       Alternative target "Chrome" Playwright URL, do not use "'s or 's!
+  #       "Playwright" is a driver/librarythat allows changedetection to talk to a Chrome or similar browser.
+  #      - PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000
   #
   #       Playwright proxy settings playwright_proxy_server, playwright_proxy_bypass, playwright_proxy_username, playwright_proxy_password
   #
@@ -57,6 +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
@@ -69,14 +74,14 @@ services:
      # If WEBDRIVER or PLAYWRIGHT are enabled, changedetection container depends on that
      # and must wait before starting (substitute "browser-chrome" with "playwright-chrome" if last one is used)
 #      depends_on:
-#          playwright-chrome:
+#          sockpuppetbrowser:
 #              condition: service_started
 
 
-     # Used for fetching pages via Playwright+Chrome where you need Javascript support.
+     # Sockpuppetbrowser is basically chrome wrapped in an API for allowing fast fetching of web-pages.
      # RECOMMENDED FOR FETCHING PAGES WITH CHROME
-#    playwright-chrome:
-#        hostname: playwright-chrome
+#    sockpuppetbrowser:
+#        hostname: sockpuppetbrowser
 #        image: dgtlmoon/sockpuppetbrowser:latest
 #        cap_add:
 #            - SYS_ADMIN

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~=1.8.0
+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
@@ -59,7 +59,9 @@ elementpath==4.1.5
 
 selenium~=4.14.0
 
-werkzeug~=3.0
+# https://github.com/pallets/werkzeug/issues/2985
+# Maybe related to pytest?
+werkzeug==3.0.6
 
 # Templating, so far just in the URLs but in the future can be for the notifications also
 jinja2~=3.1
@@ -79,8 +81,9 @@ pyppeteerstealth>=0.0.4
 pytest ~=7.2
 pytest-flask ~=1.2
 
-# Pin jsonschema version to prevent build errors on armv6 while rpds-py wheels aren't available (1708)
-jsonschema==4.17.3
+# Anything 4.0 and up but not 5.0
+jsonschema ~= 4.0
+
 
 loguru
 
@@ -92,3 +95,5 @@ babel
 
 # Needed for > 3.10, https://github.com/microsoft/playwright-python/issues/2096
 greenlet >= 3.0.3
+
+