0.45.7.1

Build: python libraries - pinning more libraries (#1962 )
Build: python libraries - eventlet + dnspython dep problems were fixed (#1963 )
2025-11-02 23:57:22 +00:00 · 2023-11-11 20:42:16 +01:00 · 2023-11-11 20:41:21 +01:00 · 2023-11-11 20:16:09 +01:00 · 2023-11-10 17:50:09 +01:00 · 2023-11-10 17:39:49 +01:00
53 changed files with 1640 additions and 447 deletions
--- a/.github/workflows/test-only.yml
+++ b/.github/workflows/test-only.yml
@@ -29,8 +29,8 @@ jobs:
          docker network create changedet-network

          # Selenium+browserless
-          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome-debug:3.141.59
-          docker run --network changedet-network -d --hostname browserless -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
+          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome:4
+          docker run --network changedet-network -d --hostname browserless -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.60-chrome-stable

      - name: Build changedetection.io container for testing
        run: |         
@@ -83,6 +83,7 @@ jobs:
        run: |
          cd changedetectionio
          ./run_proxy_tests.sh
+          # And again with PLAYWRIGHT_DRIVER_URL=..
          cd ..

      - name: Test changedetection.io container starts+runs basically without error
--- a/12
+++ b/12
@@ -1,5 +1,5 @@
 # pip dependencies install stage
-FROM python:3.11-slim-bullseye as builder
+FROM python:3.11-slim-bookworm as builder

 # See `cryptography` pin comment in requirements.txt
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
@@ -20,19 +20,23 @@ WORKDIR /install

 COPY requirements.txt /requirements.txt

+# Instructing pip to fetch wheels from piwheels.org" on ARMv6 and ARMv7 machines
+RUN if [ "$(dpkg --print-architecture)" = "armhf" ] || [ "$(dpkg --print-architecture)" = "armel" ]; then \
+      printf "[global]\nextra-index-url=https://www.piwheels.org/simple\n" > /etc/pip.conf; \
+    fi;
+
 RUN pip install --target=/dependencies -r /requirements.txt

 # Playwright is an alternative to Selenium
 # Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
 # https://github.com/dgtlmoon/changedetection.io/pull/1067 also musl/alpine (not supported)
-RUN pip install --target=/dependencies playwright~=1.27.1 \
+RUN pip install --target=/dependencies playwright~=1.39 \
    || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."

 # Final image stage
-FROM python:3.11-slim-bullseye
+FROM python:3.11-slim-bookworm

 RUN apt-get update && apt-get install -y --no-install-recommends \
-    libssl1.1 \
    libxslt1.1 \
    # For pdftohtml
    poppler-utils \
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -16,3 +16,4 @@ global-exclude venv

 global-exclude test-datastore
 global-exclude changedetection.io*dist-info
+global-exclude changedetectionio/tests/proxy_socks5/test-datastore
--- a/README.md
+++ b/README.md
@@ -232,6 +232,13 @@ See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configura

 Raspberry Pi and linux/arm/v6 linux/arm/v7 arm64 devices are supported! See the wiki for [details](https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver)

+## Import support
+
+Easily [import your list of websites to watch for changes in Excel .xslx file format](https://changedetection.io/tutorial/how-import-your-website-change-detection-lists-excel), or paste in lists of website URLs as plaintext. 
+
+Excel import is recommended - that way you can better organise tags/groups of websites and other features.
+
+
 ## API Support

 Supports managing the website watch list [via our API](https://changedetection.io/docs/api_v1/index.html)
--- a/changedetectionio/init.py
+++ b/changedetectionio/init.py
@@ -38,7 +38,7 @@ from flask_paginate import Pagination, get_page_parameter
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1

-__version__ = '0.45.3'
+__version__ = '0.45.7.1'

 from changedetectionio.store import BASE_URL_NOT_SET_TEXT

@@ -186,7 +186,6 @@ class User(flask_login.UserMixin):

    pass

-
 def login_optionally_required(func):
    @wraps(func)
    def decorated_view(*args, **kwargs):
@@ -199,7 +198,6 @@ def login_optionally_required(func):
        # Permitted
        elif request.endpoint == 'diff_history_page' and datastore.data['settings']['application'].get('shared_diff_access'):
            return func(*args, **kwargs)
-
        elif request.method in flask_login.config.EXEMPT_METHODS:
            return func(*args, **kwargs)
        elif app.config.get('LOGIN_DISABLED'):
@@ -418,11 +416,18 @@ def changedetection_app(config=None, datastore_o=None):

        # Sort by last_changed and add the uuid which is usually the key..
        sorted_watches = []
+        with_errors = request.args.get('with_errors') == "1"
+        errored_count = 0
        search_q = request.args.get('q').strip().lower() if request.args.get('q') else False
        for uuid, watch in datastore.data['watching'].items():
+            if with_errors and not watch.get('last_error'):
+                continue
+
            if limit_tag and not limit_tag in watch['tags']:
                    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)
@@ -444,6 +449,7 @@ def changedetection_app(config=None, datastore_o=None):
                                 active_tag=limit_tag,
                                 app_rss_token=datastore.data['settings']['application']['rss_access_token'],
                                 datastore=datastore,
+                                 errored_count=errored_count,
                                 form=form,
                                 guid=datastore.data['app_guid'],
                                 has_proxies=datastore.proxy_list,
@@ -624,7 +630,6 @@ def changedetection_app(config=None, datastore_o=None):

            if request.args.get('unpause_on_save'):
                extra_update_obj['paused'] = False
-
            # Re #110, if they submit the same as the default value, set it to None, so we continue to follow the default
            # Assume we use the default value, unless something relevant is different, then use the form value
            # values could be None, 0 etc.
@@ -710,11 +715,11 @@ def changedetection_app(config=None, datastore_o=None):

            # Only works reliably with Playwright
            visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and is_html_webdriver
-
            output = render_template("edit.html",
                                     available_processors=processors.available_processors(),
                                     browser_steps_config=browser_step_ui_config,
                                     emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
+                                     extra_title=f" - Edit - {watch.label}",
                                     form=form,
                                     has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
                                     has_empty_checktime=using_default_check_time,
@@ -817,6 +822,7 @@ def changedetection_app(config=None, datastore_o=None):
        from . import forms

        if request.method == 'POST':
+
            from .importer import import_url_list, import_distill_io_json

            # URL List import
@@ -840,11 +846,32 @@ def changedetection_app(config=None, datastore_o=None):
                for uuid in d_importer.new_uuids:
                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))

+            # XLSX importer
+            if request.files and request.files.get('xlsx_file'):
+                file = request.files['xlsx_file']
+                from .importer import import_xlsx_wachete, import_xlsx_custom
+
+                if request.values.get('file_mapping') == 'wachete':
+                    w_importer = import_xlsx_wachete()
+                    w_importer.run(data=file, flash=flash, datastore=datastore)
+                else:
+                    w_importer = import_xlsx_custom()
+                    # Building mapping of col # to col # type
+                    map = {}
+                    for i in range(10):
+                        c = request.values.get(f"custom_xlsx[col_{i}]")
+                        v = request.values.get(f"custom_xlsx[col_type_{i}]")
+                        if c and v:
+                            map[int(c)] = v
+
+                    w_importer.import_profile = map
+                    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}))

-        form = forms.importForm(formdata=request.form if request.method == 'POST' else None,
-#                               data=default,
-                               )
        # Could be some remaining, or we could be on GET
+        form = forms.importForm(formdata=request.form if request.method == 'POST' else None)
        output = render_template("import.html",
                                 form=form,
                                 import_url_list_remaining="\n".join(remaining_urls),
@@ -858,7 +885,10 @@ def changedetection_app(config=None, datastore_o=None):
    def mark_all_viewed():

        # Save the current newest history as the most recently viewed
+        with_errors = request.args.get('with_errors') == "1"
        for watch_uuid, watch in datastore.data['watching'].items():
+            if with_errors and not watch.get('last_error'):
+                continue
            datastore.set_last_viewed(watch_uuid, int(time.time()))

        return redirect(url_for('index'))
@@ -914,21 +944,29 @@ def changedetection_app(config=None, datastore_o=None):

        # Read as binary and force decode as UTF-8
        # Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
-        try:
-            newest_version_file_contents = watch.get_history_snapshot(dates[-1])
-        except Exception as e:
-            newest_version_file_contents = "Unable to read {}.\n".format(dates[-1])
-
-        previous_version = request.args.get('previous_version')
-        previous_timestamp = dates[-2]
-        if previous_version:
-            previous_timestamp = previous_version
+        from_version = request.args.get('from_version')
+        from_version_index = -2 # second newest
+        if from_version and from_version in dates:
+            from_version_index = dates.index(from_version)
+        else:
+            from_version = dates[from_version_index]

        try:
-            previous_version_file_contents = watch.get_history_snapshot(previous_timestamp)
+            from_version_file_contents = watch.get_history_snapshot(dates[from_version_index])
        except Exception as e:
-            previous_version_file_contents = "Unable to read {}.\n".format(previous_timestamp)
+            from_version_file_contents = "Unable to read to-version at index{}.\n".format(dates[from_version_index])

+        to_version = request.args.get('to_version')
+        to_version_index = -1
+        if to_version and to_version in dates:
+            to_version_index = dates.index(to_version)
+        else:
+            to_version = dates[to_version_index]
+
+        try:
+            to_version_file_contents = watch.get_history_snapshot(dates[to_version_index])
+        except Exception as e:
+            to_version_file_contents = "Unable to read to-version at index{}.\n".format(dates[to_version_index])

        screenshot_url = watch.get_screenshot()

@@ -944,22 +982,24 @@ def changedetection_app(config=None, datastore_o=None):

        output = render_template("diff.html",
                                 current_diff_url=watch['url'],
-                                 current_previous_version=str(previous_version),
+                                 from_version=str(from_version),
+                                 to_version=str(to_version),
                                 extra_stylesheets=extra_stylesheets,
-                                 extra_title=" - Diff - {}".format(watch['title'] if watch['title'] else watch['url']),
+                                 extra_title=f" - Diff - {watch.label}",
                                 extract_form=extract_form,
                                 is_html_webdriver=is_html_webdriver,
                                 last_error=watch['last_error'],
                                 last_error_screenshot=watch.get_error_snapshot(),
                                 last_error_text=watch.get_error_text(),
                                 left_sticky=True,
-                                 newest=newest_version_file_contents,
+                                 newest=to_version_file_contents,
                                 newest_version_timestamp=dates[-1],
                                 password_enabled_and_share_is_off=password_enabled_and_share_is_off,
-                                 previous=previous_version_file_contents,
+                                 from_version_file_contents=from_version_file_contents,
+                                 to_version_file_contents=to_version_file_contents,
                                 screenshot=screenshot_url,
                                 uuid=uuid,
-                                 versions=dates[:-1], # All except current/last
+                                 versions=dates, # All except current/last
                                 watch_a=watch
                                 )

@@ -1168,8 +1208,7 @@ def changedetection_app(config=None, datastore_o=None):
            # These files should be in our subdirectory
            try:
                # set nocache, set content-type
-                watch_dir = datastore_o.datastore_path + "/" + filename
-                response = make_response(send_from_directory(filename="elements.json", directory=watch_dir, path=watch_dir + "/elements.json"))
+                response = make_response(send_from_directory(os.path.join(datastore_o.datastore_path, filename), "elements.json"))
                response.headers['Content-type'] = 'application/json'
                response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
                response.headers['Pragma'] = 'no-cache'
@@ -1257,6 +1296,8 @@ def changedetection_app(config=None, datastore_o=None):
        # Forced recheck will skip the 'skip if content is the same' rule (, 'reprocess_existing_data': True})))
        tag = request.args.get('tag')
        uuid = request.args.get('uuid')
+        with_errors = request.args.get('with_errors') == "1"
+
        i = 0

        running_uuids = []
@@ -1272,6 +1313,8 @@ def changedetection_app(config=None, datastore_o=None):
            # Items that have this current tag
            for watch_uuid, watch in datastore.data['watching'].items():
                if tag in watch.get('tags', {}):
+                    if with_errors and not watch.get('last_error'):
+                        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})
@@ -1282,8 +1325,11 @@ def changedetection_app(config=None, datastore_o=None):
            # No tag, no uuid, add everything.
            for watch_uuid, watch in datastore.data['watching'].items():
                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}))
                    i += 1
+
        flash("{} watches queued for rechecking.".format(i))
        return redirect(url_for('index', tag=tag))

@@ -1431,6 +1477,7 @@ def changedetection_app(config=None, datastore_o=None):
        return redirect(url_for('index'))

    @app.route("/highlight_submit_ignore_url", methods=['POST'])
+    @login_optionally_required
    def highlight_submit_ignore_url():
        import re
        mode = request.form.get('mode')
--- a/changedetectionio/blueprint/browser_steps/init.py
+++ b/changedetectionio/blueprint/browser_steps/init.py
@@ -23,8 +23,10 @@

 from distutils.util import strtobool
 from flask import Blueprint, request, make_response
-import os
 import logging
+import os
+import re
+
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio import login_optionally_required

@@ -44,7 +46,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):


        # We keep the playwright session open for many minutes
-        seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
+        keepalive_seconds = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60

        browsersteps_start_session = {'start_time': time.time()}

@@ -56,16 +58,18 @@ def construct_blueprint(datastore: ChangeDetectionStore):
            # Start the Playwright context, which is actually a nodejs sub-process and communicates over STDIN/STDOUT pipes
            io_interface_context = io_interface_context.start()

+        keepalive_ms = ((keepalive_seconds + 3) * 1000)
+        base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '')
+        a = "?" if not '?' in base_url else '&'
+        base_url += a + f"timeout={keepalive_ms}"

-        # keep it alive for 10 seconds more than we advertise, sometimes it helps to keep it shutting down cleanly
-        keepalive = "&timeout={}".format(((seconds_keepalive + 3) * 1000))
        try:
-            browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(
-                os.getenv('PLAYWRIGHT_DRIVER_URL', '') + keepalive)
+            browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(base_url)
        except Exception as e:
            if 'ECONNREFUSED' in str(e):
                return make_response('Unable to start the Playwright Browser session, is it running?', 401)
            else:
+                # Other errors, bad URL syntax, bad reply etc
                return make_response(str(e), 401)

        proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
@@ -118,6 +122,31 @@ def construct_blueprint(datastore: ChangeDetectionStore):
        print("Starting connection with playwright - done")
        return {'browsersteps_session_id': browsersteps_session_id}

+    @login_optionally_required
+    @browser_steps_blueprint.route("/browsersteps_image", methods=['GET'])
+    def browser_steps_fetch_screenshot_image():
+        from flask import (
+            make_response,
+            request,
+            send_from_directory,
+        )
+        uuid = request.args.get('uuid')
+        step_n = int(request.args.get('step_n'))
+
+        watch = datastore.data['watching'].get(uuid)
+        filename = f"step_before-{step_n}.jpeg" if request.args.get('type', '') == 'before' else f"step_{step_n}.jpeg"
+
+        if step_n and watch and os.path.isfile(os.path.join(watch.watch_data_dir, filename)):
+            response = make_response(send_from_directory(directory=watch.watch_data_dir, path=filename))
+            response.headers['Content-type'] = 'image/jpeg'
+            response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+            response.headers['Pragma'] = 'no-cache'
+            response.headers['Expires'] = 0
+            return response
+
+        else:
+            return make_response('Unable to fetch image, is the URL correct? does the watch exist? does the step_type-n.jpeg exist?', 401)
+
    # A request for an action was received
    @login_optionally_required
    @browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
--- a/changedetectionio/blueprint/browser_steps/browser_steps.py
+++ b/changedetectionio/blueprint/browser_steps/browser_steps.py
@@ -77,13 +77,13 @@ class steppable_browser_interface():
    def action_goto_url(self, selector=None, value=None):
        # self.page.set_viewport_size({"width": 1280, "height": 5000})
        now = time.time()
-        response = self.page.goto(value, timeout=0, wait_until='commit')
-
-        # Wait_until = commit
-        # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
-        # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
-        # This seemed to solve nearly all 'TimeoutErrors'
+        response = self.page.goto(value, timeout=0, wait_until='load')
+        # Should be the same as the puppeteer_fetch.js methods, means, load with no timeout set (skip timeout)
+        #and also wait for seconds ?
+        #await page.waitForTimeout(1000);
+        #await page.waitForTimeout(extra_wait_ms);
        print("Time to goto URL ", time.time() - now)
+        return response

    def action_click_element_containing_text(self, selector=None, value=''):
        if not len(value.strip()):
@@ -99,7 +99,8 @@ class steppable_browser_interface():
        self.page.fill(selector, value, timeout=10 * 1000)

    def action_execute_js(self, selector, value):
-        self.page.evaluate(value)
+        response = self.page.evaluate(value)
+        return response

    def action_click_element(self, selector, value):
        print("Clicking element")
@@ -138,13 +139,13 @@ class steppable_browser_interface():
    def action_wait_for_text(self, selector, value):
        import json
        v = json.dumps(value)
-        self.page.wait_for_function(f'document.querySelector("body").innerText.includes({v});', timeout=90000)
+        self.page.wait_for_function(f'document.querySelector("body").innerText.includes({v});', timeout=30000)

    def action_wait_for_text_in_element(self, selector, value):
        import json
        s = json.dumps(selector)
        v = json.dumps(value)
-        self.page.wait_for_function(f'document.querySelector({s}).innerText.includes({v});', timeout=90000)
+        self.page.wait_for_function(f'document.querySelector({s}).innerText.includes({v});', timeout=30000)

    # @todo - in the future make some popout interface to capture what needs to be set
    # https://playwright.dev/python/docs/api/class-keyboard
--- a/changedetectionio/content_fetcher.py
+++ b/changedetectionio/content_fetcher.py
@@ -1,12 +1,15 @@
-import hashlib
 from abc import abstractmethod
+from distutils.util import strtobool
+from urllib.parse import urlparse
 import chardet
+import hashlib
 import json
 import logging
 import os
 import requests
 import sys
 import time
+import urllib.parse

 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'

@@ -156,6 +159,16 @@ class Fetcher():
        """
        return {k.lower(): v for k, v in self.headers.items()}

+    def browser_steps_get_valid_steps(self):
+        if self.browser_steps is not None and len(self.browser_steps):
+            valid_steps = filter(
+                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+                self.browser_steps)
+
+            return valid_steps
+
+        return None
+
    def iterate_browser_steps(self):
        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
        from playwright._impl._api_types import TimeoutError
@@ -167,10 +180,7 @@ class Fetcher():
        if self.browser_steps is not None and len(self.browser_steps):
            interface = steppable_browser_interface()
            interface.page = self.page
-
-            valid_steps = filter(
-                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
-                self.browser_steps)
+            valid_steps = self.browser_steps_get_valid_steps()

            for step in valid_steps:
                step_n += 1
@@ -266,7 +276,6 @@ class base_html_playwright(Fetcher):

        if self.proxy:
            # Playwright needs separate username and password values
-            from urllib.parse import urlparse
            parsed = urlparse(self.proxy.get('server'))
            if parsed.username:
                self.proxy['username'] = parsed.username
@@ -321,13 +330,11 @@ class base_html_playwright(Fetcher):

        # Append proxy connect string
        if self.proxy:
-            import urllib.parse
            # Remove username/password if it exists in the URL or you will receive "ERR_NO_SUPPORTED_PROXIES" error
            # Actual authentication handled by Puppeteer/node
            o = urlparse(self.proxy.get('server'))
            proxy_url = urllib.parse.quote(o._replace(netloc="{}:{}".format(o.hostname, o.port)).geturl())
-            browserless_function_url = f"{browserless_function_url}&--proxy-server={proxy_url}&dumpio=true"
-
+            browserless_function_url = f"{browserless_function_url}&--proxy-server={proxy_url}"

        try:
            amp = '&' if '?' in browserless_function_url else '?'
@@ -347,7 +354,7 @@ class base_html_playwright(Fetcher):
                        'url': url,
                        'user_agent': {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None),
                        'proxy_username': self.proxy.get('username', '') if self.proxy else False,
-                        'proxy_password': self.proxy.get('password', '') if self.proxy else False,
+                        'proxy_password': self.proxy.get('password', '') if self.proxy and self.proxy.get('username') else False,
                        'no_cache_list': [
                            'twitter',
                            '.pdf'
@@ -416,8 +423,8 @@ class base_html_playwright(Fetcher):
                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
                self.browser_steps))

-        if not has_browser_steps:
-            if os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
+        if not has_browser_steps and os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
+            if strtobool(os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH')):
                # Temporary backup solution until we rewrite the playwright code
                return self.run_fetch_browserless_puppeteer(
                    url,
@@ -434,6 +441,7 @@ class base_html_playwright(Fetcher):

        self.delete_browser_steps_screenshots()
        response = None
+
        with sync_playwright() as p:
            browser_type = getattr(p, self.browser_type)

@@ -442,6 +450,9 @@ class base_html_playwright(Fetcher):
            # 60,000 connection timeout only
            browser = browser_type.connect_over_cdp(self.command_executor, timeout=60000)

+            # SOCKS5 with authentication is not supported (yet)
+            # https://github.com/microsoft/playwright/issues/10567
+
            # Set user agent to prevent Cloudflare from blocking the browser
            # Use the default one configured in the App.py model that's passed from fetch_site_status.py
            context = browser.new_context(
@@ -459,40 +470,26 @@ class base_html_playwright(Fetcher):
            if len(request_headers):
                context.set_extra_http_headers(request_headers)

-                self.page.set_default_navigation_timeout(90000)
-                self.page.set_default_timeout(90000)
+            # Listen for all console events and handle errors
+            self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))

-                # Listen for all console events and handle errors
-                self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
+            # Re-use as much code from browser steps as possible so its the same
+            from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+            browsersteps_interface = steppable_browser_interface()
+            browsersteps_interface.page = self.page

-            # Goto page
-            try:
-                # Wait_until = commit
-                # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
-                # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
-                # This seemed to solve nearly all 'TimeoutErrors'
-                response = self.page.goto(url, wait_until='commit')
-            except playwright._impl._api_types.Error as e:
-                # Retry once - https://github.com/browserless/chrome/issues/2485
-                # Sometimes errors related to invalid cert's and other can be random
-                print("Content Fetcher > retrying request got error - ", str(e))
-                time.sleep(1)
-                response = self.page.goto(url, wait_until='commit')
+            response = browsersteps_interface.action_goto_url(value=url)
+            self.headers = response.all_headers()

-            except Exception as e:
-                print("Content Fetcher > Other exception when page.goto", str(e))
+            if response is None:
                context.close()
                browser.close()
-                raise PageUnloadable(url=url, status_code=None, message=str(e))
+                print("Content Fetcher > Response object was none")
+                raise EmptyReply(url=url, status_code=None)

-            # Execute any browser steps
            try:
-                extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-                self.page.wait_for_timeout(extra_wait * 1000)
-
                if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
-                    self.page.evaluate(self.webdriver_js_execute_code)
-
+                    browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
            except playwright._impl._api_types.TimeoutError as e:
                context.close()
                browser.close()
@@ -504,28 +501,26 @@ class base_html_playwright(Fetcher):
                browser.close()
                raise PageUnloadable(url=url, status_code=None, message=str(e))

-            if response is None:
-                context.close()
-                browser.close()
-                print("Content Fetcher > Response object was none")
-                raise EmptyReply(url=url, status_code=None)
-
-            # Run Browser Steps here
-            self.iterate_browser_steps()
-
            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-            time.sleep(extra_wait)
+            self.page.wait_for_timeout(extra_wait * 1000)
+

-            self.content = self.page.content()
            self.status_code = response.status
+
+            if self.status_code != 200 and not ignore_status_codes:
+                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code)
+
            if len(self.page.content().strip()) == 0:
                context.close()
                browser.close()
                print("Content Fetcher > Content was empty")
                raise EmptyReply(url=url, status_code=response.status)

-            self.status_code = response.status
-            self.headers = response.all_headers()
+            # Run Browser Steps here
+            if self.browser_steps_get_valid_steps():
+                self.iterate_browser_steps()
+                
+            self.page.wait_for_timeout(extra_wait * 1000)

            # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
            if current_include_filters is not None:
@@ -537,6 +532,7 @@ class base_html_playwright(Fetcher):
                "async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
            self.instock_data = self.page.evaluate("async () => {" + self.instock_data_js + "}")

+            self.content = self.page.content()
            # Bug 3 in Playwright screenshot handling
            # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
            # JPEG is better here because the screenshots can be very very large
@@ -551,7 +547,7 @@ class base_html_playwright(Fetcher):
            except Exception as e:
                context.close()
                browser.close()
-                raise ScreenshotUnavailable(url=url, status_code=None)
+                raise ScreenshotUnavailable(url=url, status_code=response.status_code)

            context.close()
            browser.close()
@@ -610,15 +606,17 @@ class base_html_webdriver(Fetcher):
            is_binary=False):

        from selenium import webdriver
-        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+        from selenium.webdriver.chrome.options import Options as ChromeOptions
        from selenium.common.exceptions import WebDriverException
        # request_body, request_method unused for now, until some magic in the future happens.

-        # check env for WEBDRIVER_URL
+        options = ChromeOptions()
+        if self.proxy:
+            options.proxy = self.proxy
+
        self.driver = webdriver.Remote(
            command_executor=self.command_executor,
-            desired_capabilities=DesiredCapabilities.CHROME,
-            proxy=self.proxy)
+            options=options)

        try:
            self.driver.get(url)
@@ -650,11 +648,11 @@ class base_html_webdriver(Fetcher):
    # Does the connection to the webdriver work? run a test connection.
    def is_ready(self):
        from selenium import webdriver
-        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+        from selenium.webdriver.chrome.options import Options as ChromeOptions

        self.driver = webdriver.Remote(
            command_executor=self.command_executor,
-            desired_capabilities=DesiredCapabilities.CHROME)
+            options=ChromeOptions())

        # driver.quit() seems to cause better exceptions
        self.quit()
@@ -693,6 +691,10 @@ class html_requests(Fetcher):
        proxies = {}

        # Allows override the proxy on a per-request basis
+
+        # https://requests.readthedocs.io/en/latest/user/advanced/#socks
+        # Should also work with `socks5://user:pass@host:port` type syntax.
+
        if self.proxy_override:
            proxies = {'http': self.proxy_override, 'https': self.proxy_override, 'ftp': self.proxy_override}
        else:
--- a/changedetectionio/forms.py
+++ b/changedetectionio/forms.py
@@ -15,14 +15,20 @@ from wtforms import (
    validators,
    widgets
 )
+from flask_wtf.file import FileField, FileAllowed
 from wtforms.fields import FieldList
+
 from wtforms.validators import ValidationError

+from validators.url import url as url_validator
+
+
 # default
 # each select <option data-enabled="enabled-0-0"
 from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config

-from changedetectionio import content_fetcher
+from changedetectionio import content_fetcher, html_tools
+
 from changedetectionio.notification import (
    valid_notification_formats,
 )
@@ -40,7 +46,7 @@ valid_method = {
 }

 default_method = 'GET'
-
+allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))

 class StringListField(StringField):
    widget = widgets.TextArea()
@@ -260,19 +266,23 @@ class validateURL(object):
        self.message = message

    def __call__(self, form, field):
-        import validators
-        # If hosts that only contain alphanumerics are allowed ("localhost" for example)
-        allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
-        try:
-            validators.url(field.data.strip(), simple_host=allow_simplehost)
-        except validators.ValidationFailure:
-            message = field.gettext('\'%s\' is not a valid URL.' % (field.data.strip()))
-            raise ValidationError(message)
+        # This should raise a ValidationError() or not
+        validate_url(field.data)

-        from .model.Watch import is_safe_url
-        if not is_safe_url(field.data):
-            raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX')
+def validate_url(test_url):
+    # If hosts that only contain alphanumerics are allowed ("localhost" for example)
+    try:
+        url_validator(test_url, simple_host=allow_simplehost)
+    except validators.ValidationError:
+        #@todo check for xss
+        message = f"'{test_url}' is not a valid URL."
+        # This should be wtforms.validators.
+        raise ValidationError(message)

+    from .model.Watch import is_safe_url
+    if not is_safe_url(test_url):
+        # This should be wtforms.validators.
+        raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX or incorrect URL format')

 class ValidateListRegex(object):
    """
@@ -284,11 +294,10 @@ class ValidateListRegex(object):
    def __call__(self, form, field):

        for line in field.data:
-            if line[0] == '/' and line[-1] == '/':
-                # Because internally we dont wrap in /
-                line = line.strip('/')
+            if re.search(html_tools.PERL_STYLE_REGEX, line, re.IGNORECASE):
                try:
-                    re.compile(line)
+                    regex = html_tools.perl_style_slash_enclosed_regex_to_options(line)
+                    re.compile(regex)
                except re.error:
                    message = field.gettext('RegEx \'%s\' is not a valid regular expression.')
                    raise ValidationError(message % (line))
@@ -398,6 +407,9 @@ class importForm(Form):
    from . import processors
    processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
    urls = TextAreaField('URLs')
+    xlsx_file = FileField('Upload .xlsx file', validators=[FileAllowed(['xlsx'], 'Must be .xlsx file!')])
+    file_mapping = SelectField('File mapping', [validators.DataRequired()], choices={('wachete', 'Wachete mapping'), ('custom','Custom mapping')})
+

 class SingleBrowserStep(Form):

@@ -481,7 +493,7 @@ class SingleExtraProxy(Form):

    # maybe better to set some <script>var..
    proxy_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
-    proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "http://user:pass@...:3128", "size":50})
+    proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "socks5:// or regular proxy http://user:pass@...:3128", "size":50})
    # @todo do the validation here instead

 # datastore.data['settings']['requests']..
--- a/changedetectionio/html_tools.py
+++ b/changedetectionio/html_tools.py
@@ -1,9 +1,12 @@

 from bs4 import BeautifulSoup
 from inscriptis import get_text
-from inscriptis.model.config import ParserConfig
 from jsonpath_ng.ext import parse
 from typing import List
+from inscriptis.css_profiles import CSS_PROFILES, HtmlElement
+from inscriptis.html_properties import Display
+from inscriptis.model.config import ParserConfig
+from xml.sax.saxutils import escape as xml_escape
 import json
 import re

@@ -68,10 +71,15 @@ def element_removal(selectors: List[str], html_content):


 # Return str Utf-8 of matched rules
-def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False):
+def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_rss=False):
    from lxml import etree, html

-    tree = html.fromstring(bytes(html_content, encoding='utf-8'))
+    parser = None
+    if is_rss:
+        # So that we can keep CDATA for cdata_in_document_to_text() to process
+        parser = etree.XMLParser(strip_cdata=False)
+
+    tree = html.fromstring(bytes(html_content, encoding='utf-8'), parser=parser)
    html_block = ""

    r = tree.xpath(xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'})
@@ -94,7 +102,6 @@ def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False

    return html_block

-
 # Extract/find element
 def extract_element(find='title', html_content=''):

@@ -260,8 +267,15 @@ def strip_ignore_text(content, wordlist, mode="content"):

    return "\n".encode('utf8').join(output)

+def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False) -> str:
+    pattern = '<!\[CDATA\[(\s*(?:.(?<!\]\]>)\s*)*)\]\]>'
+    def repl(m):
+        text = m.group(1)
+        return xml_escape(html_to_text(html_content=text)).strip()

-def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
+    return re.sub(pattern, repl, html_content)
+
+def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=False) -> str:
    """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
@@ -277,16 +291,21 @@ def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
    #  if anchor tag content flag is set to True define a config for
    #  extracting this content
    if render_anchor_tag_content:
-
        parser_config = ParserConfig(
-            annotation_rules={"a": ["hyperlink"]}, display_links=True
+            annotation_rules={"a": ["hyperlink"]},
+            display_links=True
        )
-
-    # otherwise set config to None
+    # otherwise set config to None/default
    else:
        parser_config = None

-    # get text and annotations via inscriptis
+    # RSS Mode - Inscriptis will treat `title` as something else.
+    # Make it as a regular block display element (//item/title)
+    # This is a bit of a hack - the real way it to use XSLT to convert it to HTML #1874
+    if is_rss:
+        html_content = re.sub(r'<title([\s>])', r'<h1\1', html_content)
+        html_content = re.sub(r'</title>', r'</h1>', html_content)
+
    text_content = get_text(html_content, config=parser_config)

    return text_content
--- a/changedetectionio/importer.py
+++ b/changedetectionio/importer.py
@@ -1,6 +1,9 @@
 from abc import ABC, abstractmethod
 import time
 import validators
+from wtforms import ValidationError
+
+from changedetectionio.forms import validate_url


 class Importer():
@@ -12,6 +15,7 @@ class Importer():
        self.new_uuids = []
        self.good = 0
        self.remaining_data = []
+        self.import_profile = None

    @abstractmethod
    def run(self,
@@ -132,3 +136,167 @@ class import_distill_io_json(Importer):
                    good += 1

        flash("{} Imported from Distill.io in {:.2f}s, {} Skipped.".format(len(self.new_uuids), time.time() - now, len(self.remaining_data)))
+
+
+class import_xlsx_wachete(Importer):
+
+    def run(self,
+            data,
+            flash,
+            datastore,
+            ):
+
+        good = 0
+        now = time.time()
+        self.new_uuids = []
+
+        from openpyxl import load_workbook
+
+        try:
+            wb = load_workbook(data)
+        except Exception as e:
+            # @todo correct except
+            flash("Unable to read export XLSX file, something wrong with the file?", 'error')
+            return
+
+        row_id = 2
+        for row in wb.active.iter_rows(min_row=row_id):
+            try:
+                extras = {}
+                data = {}
+                for cell in row:
+                    if not cell.value:
+                        continue
+                    column_title = wb.active.cell(row=1, column=cell.column).value.strip().lower()
+                    data[column_title] = cell.value
+
+                # Forced switch to webdriver/playwright/etc
+                dynamic_wachet = str(data.get('dynamic wachet', '')).strip().lower()  # Convert bool to str to cover all cases
+                # libreoffice and others can have it as =FALSE() =TRUE(), or bool(true)
+                if 'true' in dynamic_wachet or dynamic_wachet == '1':
+                    extras['fetch_backend'] = 'html_webdriver'
+                elif 'false' in dynamic_wachet or dynamic_wachet == '0':
+                    extras['fetch_backend'] = 'html_requests'
+
+                if data.get('xpath'):
+                    # @todo split by || ?
+                    extras['include_filters'] = [data.get('xpath')]
+                if data.get('name'):
+                    extras['title'] = data.get('name').strip()
+                if data.get('interval (min)'):
+                    minutes = int(data.get('interval (min)'))
+                    hours, minutes = divmod(minutes, 60)
+                    days, hours = divmod(hours, 24)
+                    weeks, days = divmod(days, 7)
+                    extras['time_between_check'] = {'weeks': weeks, 'days': days, 'hours': hours, 'minutes': minutes, 'seconds': 0}
+
+                # At minimum a URL is required.
+                if data.get('url'):
+                    try:
+                        validate_url(data.get('url'))
+                    except ValidationError as e:
+                        print(">> import URL error", data.get('url'), str(e))
+                        flash(f"Error processing row number {row_id}, URL value was incorrect, row was skipped.", 'error')
+                        # Don't bother processing anything else on this row
+                        continue
+
+                    new_uuid = datastore.add_watch(url=data['url'].strip(),
+                                                   extras=extras,
+                                                   tag=data.get('folder'),
+                                                   write_to_disk_now=False)
+                    if new_uuid:
+                        # Straight into the queue.
+                        self.new_uuids.append(new_uuid)
+                        good += 1
+            except Exception as e:
+                print(e)
+                flash(f"Error processing row number {row_id}, check all cell data types are correct, row was skipped.", 'error')
+            else:
+                row_id += 1
+
+        flash(
+            "{} imported from Wachete .xlsx in {:.2f}s".format(len(self.new_uuids), time.time() - now))
+
+
+class import_xlsx_custom(Importer):
+
+    def run(self,
+            data,
+            flash,
+            datastore,
+            ):
+
+        good = 0
+        now = time.time()
+        self.new_uuids = []
+
+        from openpyxl import load_workbook
+
+        try:
+            wb = load_workbook(data)
+        except Exception as e:
+            # @todo correct except
+            flash("Unable to read export XLSX file, something wrong with the file?", 'error')
+            return
+
+        # @todo cehck atleast 2 rows, same in other method
+        from .forms import validate_url
+        row_i = 1
+
+        try:
+            for row in wb.active.iter_rows():
+                url = None
+                tags = None
+                extras = {}
+
+                for cell in row:
+                    if not self.import_profile.get(cell.col_idx):
+                        continue
+                    if not cell.value:
+                        continue
+
+                    cell_map = self.import_profile.get(cell.col_idx)
+
+                    cell_val = str(cell.value).strip()  # could be bool
+
+                    if cell_map == 'url':
+                        url = cell.value.strip()
+                        try:
+                            validate_url(url)
+                        except ValidationError as e:
+                            print(">> Import URL error", url, str(e))
+                            flash(f"Error processing row number {row_i}, URL value was incorrect, row was skipped.", 'error')
+                            # Don't bother processing anything else on this row
+                            url = None
+                            break
+                    elif cell_map == 'tag':
+                        tags = cell.value.strip()
+                    elif cell_map == 'include_filters':
+                        # @todo validate?
+                        extras['include_filters'] = [cell.value.strip()]
+                    elif cell_map == 'interval_minutes':
+                        hours, minutes = divmod(int(cell_val), 60)
+                        days, hours = divmod(hours, 24)
+                        weeks, days = divmod(days, 7)
+                        extras['time_between_check'] = {'weeks': weeks, 'days': days, 'hours': hours, 'minutes': minutes, 'seconds': 0}
+                    else:
+                        extras[cell_map] = cell_val
+
+                # At minimum a URL is required.
+                if url:
+                    new_uuid = datastore.add_watch(url=url,
+                                                   extras=extras,
+                                                   tag=tags,
+                                                   write_to_disk_now=False)
+                    if new_uuid:
+                        # Straight into the queue.
+                        self.new_uuids.append(new_uuid)
+                        good += 1
+        except Exception as e:
+            print(e)
+            flash(f"Error processing row number {row_i}, check all cell data types are correct, row was skipped.", 'error')
+        else:
+            row_i += 1
+
+        flash(
+            "{} imported from custom .xlsx in {:.2f}s".format(len(self.new_uuids), time.time() - now))
--- a/changedetectionio/model/Watch.py
+++ b/changedetectionio/model/Watch.py
@@ -4,6 +4,7 @@ import os
 import re
 import time
 import uuid
+from pathlib import Path

 # Allowable protocols, protects against javascript: etc
 # file:// is further checked by ALLOW_FILE_URI
@@ -18,6 +19,7 @@ from changedetectionio.notification import (

 base_config = {
    'body': None,
+    'browser_steps_last_error_step': None,
    'check_unique_lines': False,  # On change-detected, compare against all history if its something new
    'check_count': 0,
    'date_created': None,
@@ -25,6 +27,7 @@ base_config = {
    'extract_text': [],  # Extract text by regex after filters
    'extract_title_as_title': False,
    'fetch_backend': 'system', # plaintext, playwright etc
+    'fetch_time': 0.0,
    'processor': 'text_json_diff', # could be restock_diff or others from .processors
    'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
    'filter_text_added': True,
@@ -167,9 +170,7 @@ class model(dict):
    @property
    def label(self):
        # Used for sorting
-        if self['title']:
-            return self['title']
-        return self['url']
+        return self.get('title') if self.get('title') else self.get('url')

    @property
    def last_changed(self):
@@ -491,3 +492,13 @@ class model(dict):
        filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
        with open(filepath, 'wb') as f:
            f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
+
+    @property
+    def get_browsersteps_available_screenshots(self):
+        "For knowing which screenshots are available to show the user in BrowserSteps UI"
+        available = []
+        for f in Path(self.watch_data_dir).glob('step_before-*.jpeg'):
+            step_n=re.search(r'step_before-(\d+)', f.name)
+            if step_n:
+                available.append(step_n.group(1))
+        return available
--- a/changedetectionio/processors/text_json_diff.py
+++ b/changedetectionio/processors/text_json_diff.py
@@ -11,7 +11,7 @@ from changedetectionio import content_fetcher, html_tools
 from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
 from copy import deepcopy
 from . import difference_detection_processor
-from ..html_tools import PERL_STYLE_REGEX
+from ..html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text

 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)

@@ -153,13 +153,22 @@ class perform_site_check(difference_detection_processor):

        is_json = 'application/json' in fetcher.get_all_headers().get('content-type', '').lower()
        is_html = not is_json
+        is_rss = False
+
+        ctype_header = fetcher.get_all_headers().get('content-type', '').lower()
+        # Go into RSS preprocess for converting CDATA/comment to usable text
+        if any(substring in ctype_header for substring in ['application/xml', 'application/rss', 'text/xml']):
+            if '<rss' in fetcher.content[:100].lower():
+                fetcher.content = cdata_in_document_to_text(html_content=fetcher.content)
+                is_rss = True

        # source: support, basically treat it as plaintext
        if is_source:
            is_html = False
            is_json = False

-        if watch.is_pdf or 'application/pdf' in fetcher.get_all_headers().get('content-type', '').lower():
+        inline_pdf = fetcher.get_all_headers().get('content-disposition', '') and '%PDF-1' in fetcher.content[:10]
+        if watch.is_pdf or 'application/pdf' in fetcher.get_all_headers().get('content-type', '').lower() or inline_pdf:
            from shutil import which
            tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
            if not which(tool):
@@ -242,7 +251,8 @@ class perform_site_check(difference_detection_processor):
                        if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
                            html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
                                                                    html_content=fetcher.content,
-                                                                    append_pretty_line_formatting=not is_source)
+                                                                    append_pretty_line_formatting=not is_source,
+                                                                    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,
@@ -262,8 +272,9 @@ class perform_site_check(difference_detection_processor):
                    do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
                    stripped_text_from_html = \
                        html_tools.html_to_text(
-                            html_content,
-                            render_anchor_tag_content=do_anchor
+                            html_content=html_content,
+                            render_anchor_tag_content=do_anchor,
+                            is_rss=is_rss # #1874 activate the <title workaround hack
                        )

        # Re #340 - return the content before the 'ignore text' was applied
--- a/changedetectionio/res/puppeteer_fetch.js
+++ b/changedetectionio/res/puppeteer_fetch.js
@@ -18,6 +18,7 @@ module.exports = async ({page, context}) => {

    await page.setBypassCSP(true)
    await page.setExtraHTTPHeaders(req_headers);
+
    if (user_agent) {
        await page.setUserAgent(user_agent);
    }
@@ -26,6 +27,10 @@ module.exports = async ({page, context}) => {
    await page.setDefaultNavigationTimeout(0);

    if (proxy_username) {
+        // Setting Proxy-Authentication header is deprecated, and doing so can trigger header change errors from Puppeteer
+        // https://github.com/puppeteer/puppeteer/issues/676 ?
+        // https://help.brightdata.com/hc/en-us/articles/12632549957649-Proxy-Manager-How-to-Guides#h_01HAKWR4Q0AFS8RZTNYWRDFJC2
+        // https://cri.dev/posts/2020-03-30-How-to-solve-Puppeteer-Chrome-Error-ERR_INVALID_ARGUMENT/
        await page.authenticate({
            username: proxy_username,
            password: proxy_password
--- a/changedetectionio/run_proxy_tests.sh
+++ b/changedetectionio/run_proxy_tests.sh
@@ -10,6 +10,40 @@ set -x
 docker run --network changedet-network -d --name squid-one --hostname squid-one --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
 docker run --network changedet-network -d --name squid-two --hostname squid-two --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge

+# SOCKS5 related - start simple Socks5 proxy server
+# SOCKSTEST=xyz should show in the logs of this service to confirm it fetched
+docker run --network changedet-network -d --hostname socks5proxy --name socks5proxy -p 1080:1080 -e PROXY_USER=proxy_user123 -e PROXY_PASSWORD=proxy_pass123 serjs/go-socks5-proxy
+docker run --network changedet-network -d --hostname socks5proxy-noauth -p 1081:1080 --name socks5proxy-noauth  serjs/go-socks5-proxy
+
+echo "---------------------------------- SOCKS5 -------------------"
+# SOCKS5 related - test from proxies.json
+docker run --network changedet-network \
+  -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
+  --rm \
+  -e "SOCKSTEST=proxiesjson" \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+
+# SOCKS5 related - by manually entering in UI
+docker run --network changedet-network \
+  --rm \
+  -e "SOCKSTEST=manual" \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest 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" \
+  -v `pwd`/tests/proxy_socks5/proxies.json-example-noauth:/app/changedetectionio/test-datastore/proxies.json \
+  -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" \
+  --rm \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+
+echo "socks5 server logs"
+docker logs socks5proxy
+echo "----------------------------------"
+
 # Used for configuring a custom proxy URL via the UI
 docker run --network changedet-network -d \
  --name squid-custom \
--- a/changedetectionio/static/js/browser-steps.js
+++ b/changedetectionio/static/js/browser-steps.js
@@ -321,8 +321,14 @@ $(document).ready(function () {
            var s = '<div class="control">' + '<a data-step-index=' + i + ' class="pure-button button-secondary button-green button-xsmall apply" >Apply</a>&nbsp;';
            if (i > 0) {
                // The first step never gets these (Goto-site)
-                s += '<a data-step-index=' + i + ' class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;' +
-                    '<a data-step-index=' + i + ' class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>';
+                s += `<a data-step-index="${i}" class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;` +
+                    `<a data-step-index="${i}" class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>`;
+
+                // if a screenshot is available
+                if (browser_steps_available_screenshots.includes(i.toString())) {
+                    var d = (browser_steps_last_error_step === i+1) ? 'before' : 'after';
+                    s += `&nbsp;<a data-step-index="${i}" class="pure-button button-secondary button-xsmall show-screenshot" title="Show screenshot from last run" data-type="${d}">Pic</a>&nbsp;`;
+                }
            }
            s += '</div>';
            $(this).append(s)
@@ -437,6 +443,24 @@ $(document).ready(function () {

    });

+    $('ul#browser_steps li .control .show-screenshot').click(function (element) {
+        var step_n = $(event.currentTarget).data('step-index');
+        w = window.open(this.href, "_blank", "width=640,height=480");
+        const t = $(event.currentTarget).data('type');
+
+        const url = browser_steps_fetch_screenshot_image_url + `&step_n=${step_n}&type=${t}`;
+        w.document.body.innerHTML = `<!DOCTYPE html>
+            <html lang="en">
+                <body>
+                    <img src="${url}" style="width: 100%" alt="Browser Step at step ${step_n} from last run." title="Browser Step at step ${step_n} from last run."/>
+                </body>
+        </html>`;
+        w.document.title = `Browser Step at step ${step_n} from last run.`;
+    });
+
+    if (browser_steps_last_error_step) {
+        $("ul#browser_steps>li:nth-child("+browser_steps_last_error_step+")").addClass("browser-step-with-error");
+    }

    $("ul#browser_steps select").change(function () {
        set_greyed_state();
--- a/changedetectionio/static/js/diff-render.js
+++ b/changedetectionio/static/js/diff-render.js
@@ -1,110 +1,120 @@
-var a = document.getElementById("a");
-var b = document.getElementById("b");
-var result = document.getElementById("result");
+$(document).ready(function () {
+    var a = document.getElementById("a");
+    var b = document.getElementById("b");
+    var result = document.getElementById("result");
+    var inputs;

-function changed() {
-  // https://github.com/kpdecker/jsdiff/issues/389
-  // I would love to use `{ignoreWhitespace: true}` here but it breaks the formatting
-  options = {
-    ignoreWhitespace: document.getElementById("ignoreWhitespace").checked,
-  };
+    $('#jump-next-diff').click(function () {

-  var diff = Diff[window.diffType](a.textContent, b.textContent, options);
-  var fragment = document.createDocumentFragment();
-  for (var i = 0; i < diff.length; i++) {
-    if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
-      var swap = diff[i];
-      diff[i] = diff[i + 1];
-      diff[i + 1] = swap;
+        var element = inputs[inputs.current];
+        var headerOffset = 80;
+        var elementPosition = element.getBoundingClientRect().top;
+        var offsetPosition = elementPosition - headerOffset + window.scrollY;
+
+        window.scrollTo({
+            top: offsetPosition,
+            behavior: "smooth",
+        });
+
+        inputs.current++;
+        if (inputs.current >= inputs.length) {
+            inputs.current = 0;
+        }
+    });
+
+    function changed() {
+        // https://github.com/kpdecker/jsdiff/issues/389
+        // I would love to use `{ignoreWhitespace: true}` here but it breaks the formatting
+        options = {
+            ignoreWhitespace: document.getElementById("ignoreWhitespace").checked,
+        };
+
+        var diff = Diff[window.diffType](a.textContent, b.textContent, options);
+        var fragment = document.createDocumentFragment();
+        for (var i = 0; i < diff.length; i++) {
+            if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
+                var swap = diff[i];
+                diff[i] = diff[i + 1];
+                diff[i + 1] = swap;
+            }
+
+            var node;
+            if (diff[i].removed) {
+                node = document.createElement("del");
+                node.classList.add("change");
+                const wrapper = node.appendChild(document.createElement("span"));
+                wrapper.appendChild(document.createTextNode(diff[i].value));
+            } else if (diff[i].added) {
+                node = document.createElement("ins");
+                node.classList.add("change");
+                const wrapper = node.appendChild(document.createElement("span"));
+                wrapper.appendChild(document.createTextNode(diff[i].value));
+            } else {
+                node = document.createTextNode(diff[i].value);
+            }
+            fragment.appendChild(node);
+        }
+
+        result.textContent = "";
+        result.appendChild(fragment);
+
+        // For nice mouse-over hover/title information
+        const removed_current_option = $('#diff-version option:selected')
+        if (removed_current_option) {
+            $('del').each(function () {
+                $(this).prop('title', 'Removed '+removed_current_option[0].label);
+            });
+        }
+        const inserted_current_option = $('#current-version option:selected')
+        if (removed_current_option) {
+            $('ins').each(function () {
+                $(this).prop('title', 'Inserted '+inserted_current_option[0].label);
+            });
+        }
+        // Set the list of possible differences to jump to
+        inputs = document.querySelectorAll('#diff-ui .change')
+        // Set the "current" diff pointer
+        inputs.current = 0;
+        // Goto diff
+        $('#jump-next-diff').click();
    }

-    var node;
-    if (diff[i].removed) {
-      node = document.createElement("del");
-      node.classList.add("change");
-      const wrapper = node.appendChild(document.createElement("span"));
-      wrapper.appendChild(document.createTextNode(diff[i].value));
-    } else if (diff[i].added) {
-      node = document.createElement("ins");
-      node.classList.add("change");
-      const wrapper = node.appendChild(document.createElement("span"));
-      wrapper.appendChild(document.createTextNode(diff[i].value));
-    } else {
-      node = document.createTextNode(diff[i].value);
-    }
-    fragment.appendChild(node);
-  }
-
-  result.textContent = "";
-  result.appendChild(fragment);
-
-  // Jump at start
-  inputs.current = 0;
-  next_diff();
-}
-
-window.onload = function () {
-  /* Convert what is options from UTC time.time() to local browser time */
-  var diffList = document.getElementById("diff-version");
-  if (typeof diffList != "undefined" && diffList != null) {
-    for (var option of diffList.options) {
-      var dateObject = new Date(option.value * 1000);
-      option.label = dateObject.toLocaleString();
-    }
-  }
-
-  /* Set current version date as local time in the browser also */
-  var current_v = document.getElementById("current-v-date");
-  var dateObject = new Date(newest_version_timestamp * 1000);
-  current_v.innerHTML = dateObject.toLocaleString();
-  onDiffTypeChange(
-    document.querySelector('#settings [name="diff_type"]:checked'),
-  );
-  changed();
-};
-
-a.onpaste = a.onchange = b.onpaste = b.onchange = changed;
-
-if ("oninput" in a) {
-  a.oninput = b.oninput = changed;
-} else {
-  a.onkeyup = b.onkeyup = changed;
-}
-
-function onDiffTypeChange(radio) {
-  window.diffType = radio.value;
-  // Not necessary
-  //	document.title = "Diff " + radio.value.slice(4);
-}
-
-var radio = document.getElementsByName("diff_type");
-for (var i = 0; i < radio.length; i++) {
-  radio[i].onchange = function (e) {
-    onDiffTypeChange(e.target);
+    $('.needs-localtime').each(function () {
+        for (var option of this.options) {
+            var dateObject = new Date(option.value * 1000);
+            option.label = dateObject.toLocaleString(undefined, {dateStyle: "full", timeStyle: "medium"});
+        }
+    })
+    onDiffTypeChange(
+        document.querySelector('#settings [name="diff_type"]:checked'),
+    );
    changed();
-  };
-}

-document.getElementById("ignoreWhitespace").onchange = function (e) {
-  changed();
-};
+    a.onpaste = a.onchange = b.onpaste = b.onchange = changed;

-var inputs = document.getElementsByClassName("change");
-inputs.current = 0;
+    if ("oninput" in a) {
+        a.oninput = b.oninput = changed;
+    } else {
+        a.onkeyup = b.onkeyup = changed;
+    }

-function next_diff() {
-  var element = inputs[inputs.current];
-  var headerOffset = 80;
-  var elementPosition = element.getBoundingClientRect().top;
-  var offsetPosition = elementPosition - headerOffset + window.scrollY;
+    function onDiffTypeChange(radio) {
+        window.diffType = radio.value;
+        // Not necessary
+        //	document.title = "Diff " + radio.value.slice(4);
+    }

-  window.scrollTo({
-    top: offsetPosition,
-    behavior: "smooth",
-  });
+    var radio = document.getElementsByName("diff_type");
+    for (var i = 0; i < radio.length; i++) {
+        radio[i].onchange = function (e) {
+            onDiffTypeChange(e.target);
+            changed();
+        };
+    }
+
+    document.getElementById("ignoreWhitespace").onchange = function (e) {
+        changed();
+    };
+
+});

-  inputs.current++;
-  if (inputs.current >= inputs.length) {
-    inputs.current = 0;
-  }
-}
--- a/changedetectionio/static/js/toggle-theme.js
+++ b/changedetectionio/static/js/toggle-theme.js
@@ -3,45 +3,50 @@
 * Toggles theme between light and dark mode.
 */
 $(document).ready(function () {
-  const button = document.getElementById("toggle-light-mode");
+    const button = document.getElementById("toggle-light-mode");

-  button.onclick = () => {
-    const htmlElement = document.getElementsByTagName("html");
-    const isDarkMode = htmlElement[0].dataset.darkmode === "true";
-    htmlElement[0].dataset.darkmode = !isDarkMode;
-    setCookieValue(!isDarkMode);
-  };
+    button.onclick = () => {
+        const htmlElement = document.getElementsByTagName("html");
+        const isDarkMode = htmlElement[0].dataset.darkmode === "true";
+        htmlElement[0].dataset.darkmode = !isDarkMode;
+        setCookieValue(!isDarkMode);
+    };

-  const setCookieValue = (value) => {
-    document.cookie = `css_dark_mode=${value};max-age=31536000;path=/`
-  }
+    const setCookieValue = (value) => {
+        document.cookie = `css_dark_mode=${value};max-age=31536000;path=/`
+    }

-  // Search input box behaviour
+    // Search input box behaviour
    const toggle_search = document.getElementById("toggle-search");
-  const search_q = document.getElementById("search-q");
-  window.addEventListener('keydown', function (e) {
+    const search_q = document.getElementById("search-q");
+    if(search_q) {
+      window.addEventListener('keydown', function (e) {
+        if (e.altKey == true && e.keyCode == 83) {
+          search_q.classList.toggle('expanded');
+          search_q.focus();
+        }
+      });

-    if (e.altKey == true && e.keyCode == 83)
-      search_q.classList.toggle('expanded');
-      search_q.focus();
-  });
-
-
-  search_q.onkeydown = (e) => {
-    var key = e.keyCode || e.which;
-    if (key === 13) {
-      document.searchForm.submit();
+      search_q.onkeydown = (e) => {
+        var key = e.keyCode || e.which;
+        if (key === 13) {
+          document.searchForm.submit();
+        }
+      };
+      toggle_search.onclick = () => {
+        // Could be that they want to search something once text is in there
+        if (search_q.value.length) {
+          document.searchForm.submit();
+        } else {
+          // If not..
+          search_q.classList.toggle('expanded');
+          search_q.focus();
+        }
+      };
    }
-  };
-  toggle_search.onclick = () => {
-    // Could be that they want to search something once text is in there
-    if (search_q.value.length) {
-      document.searchForm.submit();
-    } else {
-      // If not..
-      search_q.classList.toggle('expanded');
-      search_q.focus();
-    }
-  };

+    $('#heart-us').click(function () {
+        $("#overlay").toggleClass('visible');
+        heartpath.style.fill = document.getElementById("overlay").classList.contains("visible") ? '#ff0000' : 'var(--color-background)';
+    });
 });
--- a/changedetectionio/static/js/watch-overview.js
+++ b/changedetectionio/static/js/watch-overview.js
@@ -4,6 +4,14 @@ $(function () {
        $(this).closest('.unviewed').removeClass('unviewed');
    });

+    $('td[data-timestamp]').each(function () {
+        $(this).prop('title', new Intl.DateTimeFormat(undefined,
+            {
+                dateStyle: 'full',
+                timeStyle: 'long'
+            }).format($(this).data('timestamp') * 1000));
+    })
+
    $("#checkbox-assign-tag").click(function (e) {
        $('#op_extradata').val(prompt("Enter a tag name"));
    });
--- a/changedetectionio/static/styles/diff.css
+++ b/changedetectionio/static/styles/diff.css
@@ -187,6 +187,10 @@ ins {
    padding: 0.5em; }
  #settings ins {
    padding: 0.5em; }
+  #settings option:checked {
+    font-weight: bold; }
+  #settings [type=radio], #settings [type=checkbox] {
+    vertical-align: middle; }

 .source {
  position: absolute;
--- a/changedetectionio/static/styles/scss/diff.scss
+++ b/changedetectionio/static/styles/scss/diff.scss
@@ -77,6 +77,13 @@ ins {
  ins {
    padding: 0.5em;
  }
+
+  option:checked {
+    font-weight: bold;
+  }
+  [type=radio],[type=checkbox] {
+    vertical-align: middle;
+  }
 }

 .source {
--- a/changedetectionio/static/styles/scss/parts/_browser-steps.scss
+++ b/changedetectionio/static/styles/scss/parts/_browser-steps.scss
@@ -6,6 +6,10 @@
  }

  li {
+    &.browser-step-with-error {
+      background-color: #ffd6d6;
+      border-radius: 4px;
+    }
    &:not(:first-child) {
      &:hover {
        opacity: 1.0;
--- a/changedetectionio/static/styles/scss/parts/_darkmode.scss
+++ b/changedetectionio/static/styles/scss/parts/_darkmode.scss
@@ -1,6 +1,6 @@

 #toggle-light-mode {
-  width: 3rem;
+/*  width: 3rem;*/
  /* default */
  .icon-dark {
    display: none;
--- a/changedetectionio/static/styles/scss/parts/_love.scss
+++ b/changedetectionio/static/styles/scss/parts/_love.scss
@@ -0,0 +1,38 @@
+#overlay {
+
+  opacity: 0.95;
+  position: fixed;
+
+  width: 350px;
+  max-width: 100%;
+  height: 100%;
+  top: 0;
+  right: -350px;
+  background-color: var(--color-table-stripe);
+  z-index: 2;
+
+  transform: translateX(0);
+  transition: transform .5s ease;
+
+
+  &.visible {
+    transform: translateX(-100%);
+
+  }
+
+  .content {
+    font-size: 0.875rem;
+    padding: 1rem;
+    margin-top: 5rem;
+    max-width: 400px;
+    color: var(--color-watch-table-row-text);
+  }
+}
+
+#heartpath {
+  &:hover {
+    fill: #ff0000 !important;
+    transition: all ease 0.3s !important;
+  }
+  transition: all ease 0.3s !important;
+}
--- a/changedetectionio/static/styles/scss/parts/_menu.scss
+++ b/changedetectionio/static/styles/scss/parts/_menu.scss
@@ -0,0 +1,25 @@
+.pure-menu-link {
+  padding: 0.5rem 1em;
+  line-height: 1.2rem;
+}
+
+.pure-menu-item {
+  svg {
+    height: 1.2rem;
+  }
+  * {
+    vertical-align: middle;
+  }
+  .github-link {
+    height: 1.8rem;
+    display: block;
+    svg {
+      height: 100%;
+    }
+  }
+  .bi-heart {
+    &:hover {
+      cursor: pointer;
+    }
+  }
+}
--- a/changedetectionio/static/styles/scss/parts/_visualselector.scss
+++ b/changedetectionio/static/styles/scss/parts/_visualselector.scss
@@ -0,0 +1,28 @@
+
+#selector-wrapper {
+  height: 100%;
+  max-height: 70vh;
+  overflow-y: scroll;
+  position: relative;
+
+  //width: 100%;
+  >img {
+    position: absolute;
+    z-index: 4;
+    max-width: 100%;
+  }
+
+  >canvas {
+    position: relative;
+    z-index: 5;
+    max-width: 100%;
+
+    &:hover {
+      cursor: pointer;
+    }
+  }
+}
+
+#selector-current-xpath {
+  font-size: 80%;
+}
--- a/changedetectionio/static/styles/scss/styles.scss
+++ b/changedetectionio/static/styles/scss/styles.scss
@@ -9,6 +9,8 @@
@import "parts/_spinners";
@import "parts/_variables";
@import "parts/_darkmode";
+@import "parts/_menu";
+@import "parts/_love";

 body {
  color: var(--color-text);
@@ -55,11 +57,6 @@ a.github-link {
  }
 }

-
-#toggle-search {
-  width: 2rem;
-}
-
 #search-q {
  opacity: 0;
  -webkit-transition: all .9s ease;
@@ -471,7 +468,11 @@ footer {
  padding: 10px;

  &#left-sticky {
-    left: 0px;
+    left: 0;
+    position: fixed;
+    border-top-right-radius: 5px;
+    border-bottom-right-radius: 5px;
+    box-shadow: 1px 1px 4px var(--color-shadow-jump);
  }

  &#right-sticky {
@@ -939,32 +940,7 @@ ul {
  }
 }

-#selector-wrapper {
-  height: 100%;
-  overflow-y: scroll;
-  position: relative;
-
-  //width: 100%;
-  >img {
-    position: absolute;
-    z-index: 4;
-    max-width: 100%;
-  }
-
-  >canvas {
-    position: relative;
-    z-index: 5;
-    max-width: 100%;
-
-    &:hover {
-      cursor: pointer;
-    }
-  }
-}
-
-#selector-current-xpath {
-  font-size: 80%;
-}
+@import "parts/_visualselector";

 #webdriver-override-options {
  input[type="number"] {
@@ -1103,3 +1079,4 @@ ul {
  border-radius: 3px;
  white-space: nowrap;
 }
+
--- a/changedetectionio/static/styles/styles.css
+++ b/changedetectionio/static/styles/styles.css
@@ -26,6 +26,9 @@
  #browser_steps li {
    list-style: decimal;
    padding: 5px; }
+    #browser_steps li.browser-step-with-error {
+      background-color: #ffd6d6;
+      border-radius: 4px; }
    #browser_steps li:not(:first-child):hover {
      opacity: 1.0; }
    #browser_steps li .control {
@@ -328,7 +331,7 @@ html[data-darkmode="true"] {
      color: var(--color-watch-table-error); }

 #toggle-light-mode {
-  width: 3rem;
+  /*  width: 3rem;*/
  /* default */ }
  #toggle-light-mode .icon-dark {
    display: none; }
@@ -339,6 +342,52 @@ html[data-darkmode="true"] #toggle-light-mode .icon-light {
 html[data-darkmode="true"] #toggle-light-mode .icon-dark {
  display: block; }

+.pure-menu-link {
+  padding: 0.5rem 1em;
+  line-height: 1.2rem; }
+
+.pure-menu-item svg {
+  height: 1.2rem; }
+
+.pure-menu-item * {
+  vertical-align: middle; }
+
+.pure-menu-item .github-link {
+  height: 1.8rem;
+  display: block; }
+  .pure-menu-item .github-link svg {
+    height: 100%; }
+
+.pure-menu-item .bi-heart:hover {
+  cursor: pointer; }
+
+#overlay {
+  opacity: 0.95;
+  position: fixed;
+  width: 350px;
+  max-width: 100%;
+  height: 100%;
+  top: 0;
+  right: -350px;
+  background-color: var(--color-table-stripe);
+  z-index: 2;
+  transform: translateX(0);
+  transition: transform .5s ease; }
+  #overlay.visible {
+    transform: translateX(-100%); }
+  #overlay .content {
+    font-size: 0.875rem;
+    padding: 1rem;
+    margin-top: 5rem;
+    max-width: 400px;
+    color: var(--color-watch-table-row-text); }
+
+#heartpath {
+  transition: all ease 0.3s !important; }
+  #heartpath:hover {
+    fill: #ff0000 !important;
+    transition: all ease 0.3s !important; }
+
 body {
  color: var(--color-text);
  background: var(--color-background-page); }
@@ -373,9 +422,6 @@ a.github-link {
  a.github-link:hover {
    color: var(--color-icon-github-hover); }

-#toggle-search {
-  width: 2rem; }
-
 #search-q {
  opacity: 0;
  -webkit-transition: all .9s ease;
@@ -667,7 +713,11 @@ footer {
  background: var(--color-background);
  padding: 10px; }
  .sticky-tab#left-sticky {
-    left: 0px; }
+    left: 0;
+    position: fixed;
+    border-top-right-radius: 5px;
+    border-bottom-right-radius: 5px;
+    box-shadow: 1px 1px 4px var(--color-shadow-jump); }
  .sticky-tab#right-sticky {
    right: 0px; }
  .sticky-tab#hosted-sticky {
@@ -976,6 +1026,7 @@ ul {

 #selector-wrapper {
  height: 100%;
+  max-height: 70vh;
  overflow-y: scroll;
  position: relative; }
  #selector-wrapper > img {
--- a/changedetectionio/store.py
+++ b/changedetectionio/store.py
@@ -42,6 +42,7 @@ class ChangeDetectionStore:
        self.__data = App.model()
        self.datastore_path = datastore_path
        self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
+        print(">>> Datastore path is ", self.json_store_path)
        self.needs_write = False
        self.start_time = time.time()
        self.stop_thread = False
@@ -95,6 +96,14 @@ class ChangeDetectionStore:
                self.add_watch(url='https://changedetection.io/CHANGELOG.txt',
                               tag='changedetection.io',
                               extras={'fetch_backend': 'html_requests'})
+
+            updates_available = self.get_updates_available()
+            self.__data['settings']['application']['schema_version'] = updates_available.pop()
+
+        else:
+            # Bump the update version by running updates
+            self.run_updates()
+
        self.__data['version_tag'] = version_tag

        # Just to test that proxies.json if it exists, doesnt throw a parsing error on startup
@@ -124,9 +133,6 @@ class ChangeDetectionStore:
            secret = secrets.token_hex(16)
            self.__data['settings']['application']['api_access_token'] = secret

-        # Bump the update version by running updates
-        self.run_updates()
-
        self.needs_write = True

        # Finally start the thread that will manage periodic data saves to JSON
@@ -238,12 +244,16 @@ class ChangeDetectionStore:
        import pathlib

        self.__data['watching'][uuid].update({
-                'last_checked': 0,
+                'browser_steps_last_error_step' : None,
+                'check_count': 0,
+                'fetch_time' : 0.0,
                'has_ldjson_price_data': None,
+                'last_checked': 0,
                'last_error': False,
                'last_notification_error': False,
                'last_viewed': 0,
                'previous_md5': False,
+                'previous_md5_before_filters': False,
                'track_ldjson_price_data': None,
            })

@@ -350,6 +360,8 @@ class ChangeDetectionStore:
        if write_to_disk_now:
            self.sync_to_json()

+        print("added ", url)
+
        return new_uuid

    def visualselector_data_is_ready(self, watch_uuid):
@@ -624,14 +636,8 @@ class ChangeDetectionStore:
    def tag_exists_by_name(self, tag_name):
        return any(v.get('title', '').lower() == tag_name.lower() for k, v in self.__data['settings']['application']['tags'].items())

-    # Run all updates
-    # IMPORTANT - Each update could be run even when they have a new install and the schema is correct
-    #             So therefor - each `update_n` should be very careful about checking if it needs to actually run
-    #             Probably we should bump the current update schema version with each tag release version?
-    def run_updates(self):
+    def get_updates_available(self):
        import inspect
-        import shutil
-
        updates_available = []
        for i, o in inspect.getmembers(self, predicate=inspect.ismethod):
            m = re.search(r'update_(\d+)$', i)
@@ -639,6 +645,15 @@ class ChangeDetectionStore:
                updates_available.append(int(m.group(1)))
        updates_available.sort()

+        return updates_available
+
+    # Run all updates
+    # IMPORTANT - Each update could be run even when they have a new install and the schema is correct
+    #             So therefor - each `update_n` should be very careful about checking if it needs to actually run
+    #             Probably we should bump the current update schema version with each tag release version?
+    def run_updates(self):
+        import shutil
+        updates_available = self.get_updates_available()
        for update_n in updates_available:
            if update_n > self.__data['settings']['application']['schema_version']:
                print ("Applying update_{}".format((update_n)))
--- a/changedetectionio/templates/base.html
+++ b/changedetectionio/templates/base.html
@@ -85,6 +85,7 @@
              <a href="{{url_for('logout')}}" class="pure-menu-link">LOG OUT</a>
            </li>
          {% endif %}
+          {% if current_user.is_authenticated or not has_password %}
          <li class="pure-menu-item pure-form" id="search-menu-item">
            <!-- We use GET here so it offers people a chance to set bookmarks etc -->
            <form name="searchForm" action="" method="GET">
@@ -95,6 +96,7 @@
              </button>
            </form>
          </li>
+          {% endif %}
          <li class="pure-menu-item">
            <button class="toggle-button" id ="toggle-light-mode" type="button" title="Toggle Light/Dark Mode">
              <span class="visually-hidden">Toggle light/dark mode</span>
@@ -106,6 +108,20 @@
              </span>
            </button>
          </li>
+          <li class="pure-menu-item" id="heart-us">
+                <svg
+                   fill="#ff0000"
+                   class="bi bi-heart"
+                   preserveAspectRatio="xMidYMid meet"
+                   viewBox="0 0 16.9 16.1"
+                   id="svg-heart"
+                   xmlns="http://www.w3.org/2000/svg"
+                   xmlns:svg="http://www.w3.org/2000/svg">
+                  <path id="heartpath" d="M 5.338316,0.50302766 C 0.71136983,0.50647126 -3.9576371,7.2707777 8.5004254,15.503028 23.833425,5.3700277 13.220206,-2.5384409 8.6762066,1.6475589 c -0.060791,0.054322 -0.11943,0.1110064 -0.1757812,0.1699219 -0.057,-0.059 -0.1157813,-0.116875 -0.1757812,-0.171875 C 7.4724566,0.86129334 6.4060729,0.50223298 5.338316,0.50302766 Z"
+                     style="fill:var(--color-background);fill-opacity:1;stroke:#ff0000;stroke-opacity:1" />
+                </svg>
+
+          </li>
          <li class="pure-menu-item">
            <a class="github-link" href="https://github.com/dgtlmoon/changedetection.io">
              {% include "svgs/github.svg" %}
@@ -121,14 +137,52 @@
    {% endif %}
    {% if left_sticky %}
      <div class="sticky-tab" id="left-sticky">
-        <a href="{{url_for('preview_page', uuid=uuid)}}">Show current snapshot</a>
+        <a href="{{url_for('preview_page', uuid=uuid)}}">Show current snapshot</a><br>
+          Visualise <strong>triggers</strong> and <strong>ignored text</strong>
      </div>
    {% endif %}
    {% if right_sticky %}
      <div class="sticky-tab" id="right-sticky">{{ right_sticky }}</div>
    {% endif %}
    <section class="content">
-      <header>
+        <div id="overlay">
+            <div class="content">
+                <strong>changedetection.io needs your support!</strong><br>
+                <p>
+                    You can help us by supporting changedetection.io on these platforms;
+                </p>
+                <p>
+                <ul>
+                    <li>
+                        <a href="https://alternativeto.net/software/changedetection-io/about/">Rate us at
+                        AlternativeTo.net</a>
+                    </li>
+                <li>
+                    <a href="https://github.com/dgtlmoon/changedetection.io">Star us on GitHub</a>
+                </li>
+                <li>
+                    <a href="https://twitter.com/change_det_io">Follow us at Twitter/X</a>
+                </li>
+                <li>
+                    <a href="https://www.linkedin.com/company/changedetection-io">Check us out on LinkedIn</a>
+                </li>
+                <li>
+                    And tell your friends and colleagues :)
+                </li>
+                </ul>
+                </p>
+                <p>
+                    The more popular changedetection.io is, the more time we can dedicate to adding amazing features!
+                </p>
+                <p>
+                    Many thanks :)<br>
+                </p>
+                <p>
+                    <i>changedetection.io team</i>
+                </p>
+            </div>
+        </div>
+        <header>
        {% block header %}{% endblock %}
      </header>

--- a/changedetectionio/templates/diff.html
+++ b/changedetectionio/templates/diff.html
@@ -13,10 +13,31 @@
 <script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>

 <div id="settings">
-    <h1>Differences</h1>
    <form class="pure-form " action="" method="GET">
        <fieldset>
-
+            {% if versions|length >= 1 %}
+                <strong>Compare</strong>
+                <del class="change"><span>from</span></del>
+                <select id="diff-version" name="from_version" class="needs-localtime">
+                    {% for version in versions|reverse %}
+                        <option value="{{ version }}" {% if version== from_version %} selected="" {% endif %}>
+                            {{ version }}
+                        </option>
+                    {% endfor %}
+                </select>
+                <ins class="change"><span>to</span></ins>
+                <select id="current-version" name="to_version" class="needs-localtime">
+                    {% for version in versions|reverse %}
+                        <option value="{{ version }}" {% if version== to_version %} selected="" {% endif %}>
+                            {{ version }}
+                        </option>
+                    {% endfor %}
+                </select>
+                <button type="submit" class="pure-button pure-button-primary">Go</button>
+            {% endif %}
+        </fieldset>
+        <fieldset>
+            <strong>Style</strong>
            <label for="diffWords" class="pure-checkbox">
                <input type="radio" name="diff_type" id="diffWords" value="diffWords"> Words</label>
            <label for="diffLines" class="pure-checkbox">
@@ -26,32 +47,20 @@
                <input type="radio" name="diff_type" id="diffChars" value="diffChars"> Chars</label>
            <!-- @todo - when mimetype is JSON, select this by default? -->
            <label for="diffJson" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffJson" value="diffJson" > JSON</label>
+                <input type="radio" name="diff_type" id="diffJson" value="diffJson"> JSON</label>

-            {% if versions|length >= 1 %}
-            <label for="diff-version">Compare newest (<span id="current-v-date"></span>) with</label>
-            <select id="diff-version" name="previous_version">
-                {% for version in versions|reverse %}
-                <option value="{{version}}" {% if version== current_previous_version %} selected="" {% endif %}>
-                    {{version}}
-                </option>
-                {% endfor %}
-            </select>
-            <button type="submit" class="pure-button pure-button-primary">Go</button>
-            {% endif %}
-        </fieldset>
-    </form>
-    <del>Removed text</del>
-    <ins>Inserted Text</ins>
-    <span>
+            <span>
        <!-- https://github.com/kpdecker/jsdiff/issues/389 ? -->
        <label for="ignoreWhitespace" class="pure-checkbox" id="label-diff-ignorewhitespace">
-            <input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace" > Ignore Whitespace</label>
+            <input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace"> Ignore Whitespace</label>
    </span>
+        </fieldset>
+    </form>
+
 </div>

 <div id="diff-jump">
-    <a onclick="next_diff();">Jump</a>
+    <a id="jump-next-diff" title="Jump to next difference">Jump</a>
 </div>

 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
@@ -79,8 +88,6 @@
    </div>

     <div class="tab-pane-inner" id="text">
-         <div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored, highlight text to add to ignore filters</div>
-
         {% if password_enabled_and_share_is_off %}
           <div class="tip">Pro-tip: You can enable <strong>"share access when password is enabled"</strong> from settings</div>
         {% endif %}
@@ -91,8 +98,8 @@
             <tbody>
             <tr>
                 <!-- just proof of concept copied straight from github.com/kpdecker/jsdiff -->
-                 <td id="a" style="display: none;">{{previous}}</td>
-                 <td id="b" style="display: none;">{{newest}}</td>
+                 <td id="a" style="display: none;">{{from_version_file_contents}}</td>
+                 <td id="b" style="display: none;">{{to_version_file_contents}}</td>
                 <td id="diff-col">
                     <span id="result" class="highlightable-filter"></span>
                 </td>
--- a/changedetectionio/templates/edit.html
+++ b/changedetectionio/templates/edit.html
@@ -4,8 +4,10 @@
 {% from '_common_fields.jinja' import render_common_settings_form %}
 <script src="{{url_for('static_content', group='js', filename='tabs.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 }}');
+    const browser_steps_fetch_screenshot_image_url="{{url_for('browser_steps.browser_steps_fetch_screenshot_image', uuid=uuid)}}";
+    const browser_steps_last_error_step={{ watch.browser_steps_last_error_step|tojson }};
    const browser_steps_start_url="{{url_for('browser_steps.browsersteps_start_session', uuid=uuid)}}";
    const browser_steps_sync_url="{{url_for('browser_steps.browsersteps_ui_update', uuid=uuid)}}";
 {% if emailprefix %}
@@ -49,6 +51,7 @@
            <li class="tab"><a href="#restock">Restock Detection</a></li>
            {% endif %}
            <li class="tab"><a href="#notifications">Notifications</a></li>
+            <li class="tab"><a href="#stats">Stats</a></li>
        </ul>
    </div>

@@ -109,7 +112,7 @@
                        <span class="pure-form-message-inline">
                            <p>Use the <strong>Basic</strong> method (default) where your watched site doesn't need Javascript to render.</p>
                            <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
-                            Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using BrightData Proxies, find out more here.</a>
+                            Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
                        </span>
                    </div>
                {% if form.proxy %}
@@ -441,7 +444,35 @@ Unavailable") }}
                </fieldset>
            </div>
            {% endif %}
-
+            <div class="tab-pane-inner" id="stats">
+                <div class="pure-control-group">
+                    <style>
+                    #stats-table tr > td:first-child {
+                        font-weight: bold;
+                    }
+                    </style>
+                    <table class="pure-table" id="stats-table">
+                        <tbody>
+                        <tr>
+                            <td>Check count</td>
+                            <td>{{ "{:,}".format( watch.check_count) }}</td>
+                        </tr>
+                        <tr>
+                            <td>Consecutive filter failures</td>
+                            <td>{{ "{:,}".format( watch.consecutive_filter_failures) }}</td>
+                        </tr>
+                        <tr>
+                            <td>History length</td>
+                            <td>{{ "{:,}".format(watch.history|length) }}</td>
+                        </tr>
+                        <tr>
+                            <td>Last fetch time</td>
+                            <td>{{ watch.fetch_time }}s</td>
+                        </tr>
+                        </tbody>
+                    </table>
+                </div>
+            </div>
            <div id="actions">
                <div class="pure-control-group">
                    {{ render_button(form.save_button) }}
--- a/changedetectionio/templates/import.html
+++ b/changedetectionio/templates/import.html
@@ -8,11 +8,12 @@
        <ul>
            <li class="tab" id=""><a href="#url-list">URL List</a></li>
            <li class="tab"><a href="#distill-io">Distill.io</a></li>
+            <li class="tab"><a href="#xlsx">.XLSX &amp; Wachete</a></li>
        </ul>
    </div>

    <div class="box-wrap inner">
-        <form class="pure-form pure-form-aligned" action="{{url_for('import_page')}}" method="POST">
+        <form class="pure-form" action="{{url_for('import_page')}}" method="POST" enctype="multipart/form-data">
            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
            <div class="tab-pane-inner" id="url-list">
                    <legend>
@@ -79,6 +80,42 @@
 " rows="25">{{ original_distill_json }}</textarea>

            </div>
+            <div class="tab-pane-inner" id="xlsx">
+            <fieldset>
+                <div class="pure-control-group">
+                {{ render_field(form.xlsx_file, class="processor") }}
+                </div>
+                <div class="pure-control-group">
+                    {{ render_field(form.file_mapping, class="processor") }}
+                </div>
+            </fieldset>
+                <div class="pure-control-group">
+                <span class="pure-form-message-inline">
+                    Table of custom column and data types mapping for the <strong>Custom mapping</strong> File mapping type.
+                </span>
+                    <table style="border: 1px solid #aaa; padding: 0.5rem; border-radius: 4px;">
+                        <tr>
+                            <td><strong>Column #</strong></td>
+                            {% for n in range(4) %}
+                                <td><input type="number" name="custom_xlsx[col_{{n}}]" style="width: 4rem;" min="1"></td>
+                            {%  endfor %}
+                        </tr>
+                        <tr>
+                            <td><strong>Type</strong></td>
+                            {% for n in range(4) %}
+                                <td><select name="custom_xlsx[col_type_{{n}}]">
+                                    <option value="" style="color: #aaa"> -- none --</option>
+                                    <option value="url">URL</option>
+                                    <option value="title">Title</option>
+                                    <option value="include_filter">CSS/xPath filter</option>
+                                    <option value="tag">Group / Tag name(s)</option>
+                                    <option value="interval_minutes">Recheck time (minutes)</option>
+                                </select></td>
+                            {%  endfor %}
+                        </tr>
+                    </table>
+                </div>
+            </div>
            <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">Import</button>
        </form>

--- a/changedetectionio/templates/settings.html
+++ b/changedetectionio/templates/settings.html
@@ -109,7 +109,7 @@
                        <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
                    </span>
                    <br>
-                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using BrightData Proxies, find out more here.</a>
+                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
                </div>
                <fieldset class="pure-group" id="webdriver-override-options">
                    <div class="pure-form-message-inline">
@@ -229,7 +229,8 @@ nav

                <div class="pure-control-group">
                {{ render_field(form.requests.form.extra_proxies) }}
-                <span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span>
+                <span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span><br>
+                <span class="pure-form-message-inline">SOCKS5 proxies with authentication are only supported with 'plain requests' fetcher, for other fetchers you should whitelist the IP access instead</span>
                </div>
            </div>
            <div id="actions">
--- a/changedetectionio/templates/svgs/github.svg
+++ b/changedetectionio/templates/svgs/github.svg
@@ -1,3 +1,6 @@
-<svg class="octicon octicon-mark-github v-align-middle" height="32" viewbox="0 0 16 16" version="1.1" width="32" aria-hidden="true">
-  <path fill-rule="evenodd" d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0016 8c0-4.42-3.58-8-8-8z"></path>
+<svg class="octicon octicon-mark-github v-align-middle"  viewbox="0 0 16 16" version="1.1" aria-hidden="true">
+    <path
+     fill-rule="evenodd"
+     d="M 8,0 C 3.58,0 0,3.58 0,8 c 0,3.54 2.29,6.53 5.47,7.59 0.4,0.07 0.55,-0.17 0.55,-0.38 0,-0.19 -0.01,-0.82 -0.01,-1.49 C 4,14.09 3.48,13.23 3.32,12.78 3.23,12.55 2.84,11.84 2.5,11.65 2.22,11.5 1.82,11.13 2.49,11.12 3.12,11.11 3.57,11.7 3.72,11.94 4.44,13.15 5.59,12.81 6.05,12.6 6.12,12.08 6.33,11.73 6.56,11.53 4.78,11.33 2.92,10.64 2.92,7.58 2.92,6.71 3.23,5.99 3.74,5.43 3.66,5.23 3.38,4.41 3.82,3.31 c 0,0 0.67,-0.21 2.2,0.82 0.64,-0.18 1.32,-0.27 2,-0.27 0.68,0 1.36,0.09 2,0.27 1.53,-1.04 2.2,-0.82 2.2,-0.82 0.44,1.1 0.16,1.92 0.08,2.12 0.51,0.56 0.82,1.27 0.82,2.15 0,3.07 -1.87,3.75 -3.65,3.95 0.29,0.25 0.54,0.73 0.54,1.48 0,1.07 -0.01,1.93 -0.01,2.2 0,0.21 0.15,0.46 0.55,0.38 A 8.013,8.013 0 0 0 16,8 C 16,3.58 12.42,0 8,0 Z"
+     id="path2" />
 </svg>
--- a/changedetectionio/templates/watch-overview.html
+++ b/changedetectionio/templates/watch-overview.html
@@ -154,8 +154,8 @@
                    {% endfor %}

                </td>
-                <td class="last-checked">{{watch|format_last_checked_time|safe}}</td>
-                <td class="last-changed">{% if watch.history_n >=2 and watch.last_changed >0 %}
+                <td class="last-checked" data-timestamp="{{ watch.last_checked }}">{{watch|format_last_checked_time|safe}}</td>
+                <td class="last-changed" data-timestamp="{{ watch.last_changed }}">{% if watch.history_n >=2 and watch.last_changed >0 %}
                    {{watch.last_changed|format_timestamp_timeago}}
                    {% else %}
                    Not yet
@@ -178,13 +178,18 @@
            </tbody>
        </table>
        <ul id="post-list-buttons">
+            {% if errored_count %}
+            <li>
+                <a href="{{url_for('index', with_errors=1, tag=request.args.get('tag')) }}" class="pure-button button-tag button-error ">With errors ({{ errored_count }})</a>
+            </li>
+            {% endif %}
            {% if has_unviewed %}
            <li>
-                <a href="{{url_for('mark_all_viewed', tag=request.args.get('tag')) }}" class="pure-button button-tag ">Mark all viewed</a>
+                <a href="{{url_for('mark_all_viewed',with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Mark all viewed</a>
            </li>
            {% endif %}
            <li>
-               <a href="{{ url_for('form_watch_checknow', tag=active_tag) }}" class="pure-button button-tag ">Recheck
+               <a href="{{ url_for('form_watch_checknow', tag=active_tag, with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Recheck
                all {% if active_tag%} in "{{tags[active_tag].title}}"{%endif%}</a>
            </li>
            <li>
--- a/changedetectionio/tests/fetchers/test_content.py
+++ b/changedetectionio/tests/fetchers/test_content.py
@@ -28,8 +28,6 @@ def test_fetch_webdriver_content(client, live_server):
    )

    assert b"1 Imported" in res.data
-    time.sleep(3)
-
    wait_for_all_checks(client)


--- a/changedetectionio/tests/import/spreadsheet.xlsx
+++ b/changedetectionio/tests/import/spreadsheet.xlsx
--- a/changedetectionio/tests/proxy_list/test_multiple_proxy.py
+++ b/changedetectionio/tests/proxy_list/test_multiple_proxy.py
@@ -2,12 +2,11 @@

 import time
 from flask import url_for
-from ..util import live_server_setup
+from ..util import live_server_setup, wait_for_all_checks
+

 def test_preferred_proxy(client, live_server):
-    time.sleep(1)
    live_server_setup(live_server)
-    time.sleep(1)
    url = "http://chosen.changedetection.io"

    res = client.post(
@@ -20,7 +19,7 @@ def test_preferred_proxy(client, live_server):

    assert b"1 Imported" in res.data

-    time.sleep(2)
+    wait_for_all_checks(client)
    res = client.post(
        url_for("edit_page", uuid="first"),
        data={
@@ -34,5 +33,5 @@ def test_preferred_proxy(client, live_server):
        follow_redirects=True
    )
    assert b"Updated watch." in res.data
-    time.sleep(2)
+    wait_for_all_checks(client)
    # Now the request should appear in the second-squid logs
--- a/changedetectionio/tests/proxy_socks5/proxies.json-example
+++ b/changedetectionio/tests/proxy_socks5/proxies.json-example
@@ -0,0 +1,6 @@
+{
+  "socks5proxy": {
+    "label": "socks5proxy",
+    "url": "socks5://proxy_user123:proxy_pass123@socks5proxy:1080"
+  }
+}
--- a/changedetectionio/tests/proxy_socks5/proxies.json-example-noauth
+++ b/changedetectionio/tests/proxy_socks5/proxies.json-example-noauth
@@ -0,0 +1,6 @@
+{
+  "socks5proxy": {
+    "label": "socks5proxy",
+    "url": "socks5://socks5proxy-noauth:1080"
+  }
+}
--- a/changedetectionio/tests/proxy_socks5/test_socks5_proxy.py
+++ b/changedetectionio/tests/proxy_socks5/test_socks5_proxy.py
@@ -0,0 +1,63 @@
+#!/usr/bin/python3
+import os
+import time
+from flask import url_for
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
+
+
+def test_socks5(client, live_server):
+    live_server_setup(live_server)
+
+    # Setup a proxy
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "requests-time_between_check-minutes": 180,
+            "application-ignore_whitespace": "y",
+            "application-fetch_backend": "html_requests",
+            # set in .github/workflows/test-only.yml
+            "requests-extra_proxies-0-proxy_url": "socks5://proxy_user123:proxy_pass123@socks5proxy:1080",
+            "requests-extra_proxies-0-proxy_name": "socks5proxy",
+        },
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." in res.data
+
+    test_url = "https://changedetection.io/CHANGELOG.txt?socks-test-tag=" + os.getenv('SOCKSTEST', '')
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    res = client.get(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+    )
+    # check the proxy is offered as expected
+    assert b'ui-0socks5proxy' in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+        data={
+            "include_filters": "",
+            "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
+            "headers": "",
+            "proxy": "ui-0socks5proxy",
+            "tags": "",
+            "url": test_url,
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    # Should see the proper string
+    assert "+0200:".encode('utf-8') in res.data
--- a/changedetectionio/tests/proxy_socks5/test_socks5_proxy_sources.py
+++ b/changedetectionio/tests/proxy_socks5/test_socks5_proxy_sources.py
@@ -0,0 +1,52 @@
+#!/usr/bin/python3
+import os
+import time
+from flask import url_for
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
+
+
+# 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):
+    live_server_setup(live_server)
+
+    test_url = "https://changedetection.io/CHANGELOG.txt?socks-test-tag=" + os.getenv('SOCKSTEST', '')
+
+    res = client.get(url_for("settings_page"))
+    assert b'name="requests-proxy" type="radio" value="socks5proxy"' in res.data
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    res = client.get(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+    )
+    # check the proxy is offered as expected
+    assert b'name="proxy" type="radio" value="socks5proxy"' in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+        data={
+            "include_filters": "",
+            "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
+            "headers": "",
+            "proxy": "socks5proxy",
+            "tags": "",
+            "url": test_url,
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    # Should see the proper string
+    assert "+0200:".encode('utf-8') in res.data
--- a/changedetectionio/tests/test_access_control.py
+++ b/changedetectionio/tests/test_access_control.py
@@ -1,4 +1,4 @@
-from . util import live_server_setup, extract_UUID_from_client
+from .util import live_server_setup, extract_UUID_from_client, wait_for_all_checks
 from flask import url_for
 import time

@@ -19,10 +19,16 @@ def test_check_access_control(app, client, live_server):
        )

        assert b"1 Imported" in res.data
-        time.sleep(2)
-        res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+        time.sleep(3)
+        # causes a 'Popped wrong request context.' error when client. is accessed?
+        #wait_for_all_checks(client)
+
+        res = c.get(url_for("form_watch_checknow"), follow_redirects=True)
        assert b'1 watches queued for rechecking.' in res.data
-        time.sleep(2)
+        time.sleep(3)
+        # causes a 'Popped wrong request context.' error when client. is accessed?
+        #wait_for_all_checks(client)
+

        # Enable password check and diff page access bypass
        res = c.post(
@@ -42,7 +48,7 @@ def test_check_access_control(app, client, live_server):
        assert b"Login" in res.data

        # The diff page should return something valid when logged out
-        res = client.get(url_for("diff_history_page", uuid="first"))
+        res = c.get(url_for("diff_history_page", uuid="first"))
        assert b'Random content' in res.data

        # Check wrong password does not let us in
@@ -83,6 +89,8 @@ def test_check_access_control(app, client, live_server):
        res = c.get(url_for("logout"),
            follow_redirects=True)

+        assert b"Login" in res.data
+
        res = c.get(url_for("settings_page"),
            follow_redirects=True)

@@ -160,5 +168,5 @@ def test_check_access_control(app, client, live_server):
        assert b"Login" in res.data

        # The diff page should return something valid when logged out
-        res = client.get(url_for("diff_history_page", uuid="first"))
+        res = c.get(url_for("diff_history_page", uuid="first"))
        assert b'Random content' not in res.data
--- a/changedetectionio/tests/test_backend.py
+++ b/changedetectionio/tests/test_backend.py
@@ -89,7 +89,7 @@ def test_check_basic_change_detection_functionality(client, live_server):

    # 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"))
-    assert b'Compare newest' in res.data
+    assert b'selected=""' in res.data, "Confirm diff history page loaded"

    # Check the [preview] pulls the right one
    res = client.get(
--- a/changedetectionio/tests/test_extract_regex.py
+++ b/changedetectionio/tests/test_extract_regex.py
@@ -202,3 +202,35 @@ def test_check_filter_and_regex_extract(client, live_server):

    # Should not be here
    assert b'Some text that did change' not in res.data
+
+
+
+def test_regex_error_handling(client, live_server):
+
+    #live_server_setup(live_server)
+
+    # 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
+
+    ### test regex error handling
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"extract_text": '/something bad\d{3/XYZ',
+              "url": test_url,
+              "fetch_backend": "html_requests"},
+        follow_redirects=True
+    )
+
+    with open('/tmp/fuck.html', 'wb') as f:
+        f.write(res.data)
+
+    assert b'is not a valid regular expression.' in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
--- a/changedetectionio/tests/test_import.py
+++ b/changedetectionio/tests/test_import.py
@@ -1,16 +1,19 @@
 #!/usr/bin/python3
-
+import io
+import os
 import time

 from flask import url_for

-from .util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
+
+
 def test_setup(client, live_server):
    live_server_setup(live_server)

 def test_import(client, live_server):
    # Give the endpoint time to spin up
-    time.sleep(1)
+    wait_for_all_checks(client)

    res = client.post(
        url_for("import_page"),
@@ -119,3 +122,97 @@ def test_import_distillio(client, live_server):
    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
    # Clear flask alerts
    res = client.get(url_for("index"))
+
+def test_import_custom_xlsx(client, live_server):
+    """Test can upload a excel spreadsheet and the watches are created correctly"""
+
+    #live_server_setup(live_server)
+
+    dirname = os.path.dirname(__file__)
+    filename = os.path.join(dirname, 'import/spreadsheet.xlsx')
+    with open(filename, 'rb') as f:
+
+        data= {
+            'file_mapping': 'custom',
+            'custom_xlsx[col_0]': '1',
+            'custom_xlsx[col_1]': '3',
+            'custom_xlsx[col_2]': '5',
+            'custom_xlsx[col_3]': '4',
+            'custom_xlsx[col_type_0]': 'title',
+            'custom_xlsx[col_type_1]': 'url',
+            'custom_xlsx[col_type_2]': 'include_filters',
+            'custom_xlsx[col_type_3]': 'interval_minutes',
+            'xlsx_file': (io.BytesIO(f.read()), 'spreadsheet.xlsx')
+        }
+
+    res = client.post(
+        url_for("import_page"),
+        data=data,
+        follow_redirects=True,
+    )
+
+    assert b'4 imported from custom .xlsx' in res.data
+    # Because this row was actually just a header with no usable URL, we should get an error
+    assert b'Error processing row number 1' in res.data
+
+    res = client.get(
+        url_for("index")
+    )
+
+    assert b'Somesite results ABC' in res.data
+    assert b'City news results' in res.data
+
+    # Just find one to check over
+    for uuid, watch in live_server.app.config['DATASTORE'].data['watching'].items():
+        if watch.get('title') == 'Somesite results ABC':
+            filters = watch.get('include_filters')
+            assert filters[0] == '/html[1]/body[1]/div[4]/div[1]/div[1]/div[1]||//*[@id=\'content\']/div[3]/div[1]/div[1]||//*[@id=\'content\']/div[1]'
+            assert watch.get('time_between_check') == {'weeks': 0, 'days': 1, 'hours': 6, 'minutes': 24, 'seconds': 0}
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+def test_import_watchete_xlsx(client, live_server):
+    """Test can upload a excel spreadsheet and the watches are created correctly"""
+
+    #live_server_setup(live_server)
+    dirname = os.path.dirname(__file__)
+    filename = os.path.join(dirname, 'import/spreadsheet.xlsx')
+    with open(filename, 'rb') as f:
+
+        data= {
+            'file_mapping': 'wachete',
+            'xlsx_file': (io.BytesIO(f.read()), 'spreadsheet.xlsx')
+        }
+
+    res = client.post(
+        url_for("import_page"),
+        data=data,
+        follow_redirects=True,
+    )
+
+    assert b'4 imported from Wachete .xlsx' in res.data
+
+    res = client.get(
+        url_for("index")
+    )
+
+    assert b'Somesite results ABC' in res.data
+    assert b'City news results' in res.data
+
+    # Just find one to check over
+    for uuid, watch in live_server.app.config['DATASTORE'].data['watching'].items():
+        if watch.get('title') == 'Somesite results ABC':
+            filters = watch.get('include_filters')
+            assert filters[0] == '/html[1]/body[1]/div[4]/div[1]/div[1]/div[1]||//*[@id=\'content\']/div[3]/div[1]/div[1]||//*[@id=\'content\']/div[1]'
+            assert watch.get('time_between_check') == {'weeks': 0, 'days': 1, 'hours': 6, 'minutes': 24, 'seconds': 0}
+            assert watch.get('fetch_backend') == 'html_requests' # Has inactive 'dynamic wachet'
+
+        if watch.get('title') == 'JS website':
+            assert watch.get('fetch_backend') == 'html_webdriver' # Has active 'dynamic wachet'
+
+        if watch.get('title') == 'system default website':
+            assert watch.get('fetch_backend') == 'system' # uses default if blank
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
--- a/changedetectionio/tests/test_rss.py
+++ b/changedetectionio/tests/test_rss.py
@@ -2,12 +2,61 @@

 import time
 from flask import url_for
-from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI
+from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI, \
+    extract_UUID_from_client


+def set_original_cdata_xml():
+    test_return_data = """<rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:media="http://search.yahoo.com/mrss/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
+    <channel>
+    <title>Gizi</title>
+    <link>https://test.com</link>
+    <atom:link href="https://testsite.com" rel="self" type="application/rss+xml"/>
+    <description>
+    <![CDATA[ The Future Could Be Here ]]>
+    </description>
+    <language>en</language>
+    <item>
+    <title>
+    <![CDATA[ <img src="https://testsite.com/hacked.jpg"> Hackers can access your computer ]]>
+    </title>
+    <link>https://testsite.com/news/12341234234</link>
+    <description>
+    <![CDATA[ <img class="type:primaryImage" src="https://testsite.com/701c981da04869e.jpg"/><p>The days of Terminator and The Matrix could be closer. But be positive.</p><p><a href="https://testsite.com">Read more link...</a></p> ]]>
+    </description>
+    <category>cybernetics</category>
+    <category>rand corporation</category>
+    <pubDate>Tue, 17 Oct 2023 15:10:00 GMT</pubDate>
+    <guid isPermaLink="false">1850933241</guid>
+    <dc:creator>
+    <![CDATA[ Mr Hacker News ]]>
+    </dc:creator>
+    <media:thumbnail url="https://testsite.com/thumbnail-c224e10d81488e818701c981da04869e.jpg"/>
+    </item>
+
+    <item>
+        <title>    Some other title    </title>
+        <link>https://testsite.com/news/12341234236</link>
+        <description>
+        Some other description
+        </description>
+    </item>    
+    </channel>
+    </rss>
+            """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def test_setup(client, live_server):
+    live_server_setup(live_server)
+
 def test_rss_and_token(client, live_server):
+    #    live_server_setup(live_server)
+
    set_original_response()
-    live_server_setup(live_server)
+    rss_token = extract_rss_token_from_UI(client)

    # Add our URL to the import page
    res = client.post(
@@ -17,11 +66,11 @@ def test_rss_and_token(client, live_server):
    )

    assert b"1 Imported" in res.data
-    rss_token = extract_rss_token_from_UI(client)

-    time.sleep(2)
+    wait_for_all_checks(client)
+    set_modified_response()
    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(2)
+    wait_for_all_checks(client)

    # Add our URL to the import page
    res = client.get(
@@ -37,3 +86,80 @@ def test_rss_and_token(client, live_server):
    )
    assert b"Access denied, bad token" not in res.data
    assert b"Random content" in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+
+def test_basic_cdata_rss_markup(client, live_server):
+    #live_server_setup(live_server)
+
+    set_original_cdata_xml()
+
+    test_url = url_for('test_endpoint', content_type="application/xml", _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
+    )
+    assert b'CDATA' not in res.data
+    assert b'<![' not in res.data
+    assert b'Hackers can access your computer' in res.data
+    assert b'The days of Terminator' in res.data
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+
+def test_rss_xpath_filtering(client, live_server):
+    #live_server_setup(live_server)
+
+    set_original_cdata_xml()
+
+    test_url = url_for('test_endpoint', content_type="application/xml", _external=True)
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    uuid = extract_UUID_from_client(client)
+    res = client.post(
+        url_for("edit_page", uuid=uuid, unpause_on_save=1),
+        data={
+                "include_filters": "//item/title",
+                "fetch_backend": "html_requests",
+                "headers": "",
+                "proxy": "no-proxy",
+                "tags": "",
+                "url": test_url,
+              },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+    assert b'CDATA' not in res.data
+    assert b'<![' not in res.data
+    # #1874  All but the first <title was getting selected
+    # Convert any HTML with just a top level <title> to <h1> to be sure title renders
+
+    assert b'Hackers can access your computer' in res.data # Should ONLY be selected by the xpath
+    assert b'Some other title' in res.data  # Should ONLY be selected by the xpath
+    assert b'The days of Terminator' not in res.data # Should NOT be selected by the xpath
+    assert b'Some other description' not in res.data  # Should NOT be selected by the xpath
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
--- a/changedetectionio/tests/test_xpath_selector.py
+++ b/changedetectionio/tests/test_xpath_selector.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

 from ..html_tools import *

@@ -86,14 +86,14 @@ def test_check_xpath_filter_utf8(client, live_server):
        follow_redirects=True
    )
    assert b"1 Imported" in res.data
-    time.sleep(1)
+    wait_for_all_checks(client)
    res = client.post(
        url_for("edit_page", uuid="first"),
        data={"include_filters": filter, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
        follow_redirects=True
    )
    assert b"Updated watch." in res.data
-    time.sleep(3)
+    wait_for_all_checks(client)
    res = client.get(url_for("index"))
    assert b'Unicode strings with encoding declaration are not supported.' not in res.data
    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
@@ -140,14 +140,14 @@ def test_check_xpath_text_function_utf8(client, live_server):
        follow_redirects=True
    )
    assert b"1 Imported" in res.data
-    time.sleep(1)
+    wait_for_all_checks(client)
    res = client.post(
        url_for("edit_page", uuid="first"),
        data={"include_filters": filter, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
        follow_redirects=True
    )
    assert b"Updated watch." in res.data
-    time.sleep(3)
+    wait_for_all_checks(client)
    res = client.get(url_for("index"))
    assert b'Unicode strings with encoding declaration are not supported.' not in res.data

@@ -164,7 +164,6 @@ def test_check_xpath_text_function_utf8(client, live_server):
    assert b'Deleted' in res.data

 def test_check_markup_xpath_filter_restriction(client, live_server):
-    sleep_time_for_fetch_thread = 3

    xpath_filter = "//*[contains(@class, 'sametext')]"

@@ -183,7 +182,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
    assert b"1 Imported" in res.data

    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)

    # Goto the edit page, add our ignore text
    # Add our URL to the import page
@@ -195,7 +194,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
    assert b"Updated watch." in res.data

    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)

    # view it/reset state back to viewed
    client.get(url_for("diff_history_page", uuid="first"), follow_redirects=True)
@@ -206,7 +205,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
    # 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)

    res = client.get(url_for("index"))
    assert b'unviewed' not in res.data
@@ -216,9 +215,6 @@ def test_check_markup_xpath_filter_restriction(client, live_server):

 def test_xpath_validation(client, live_server):

-    # Give the endpoint time to spin up
-    time.sleep(1)
-
    # Add our URL to the import page
    test_url = url_for('test_endpoint', _external=True)
    res = client.post(
@@ -227,7 +223,7 @@ def test_xpath_validation(client, live_server):
        follow_redirects=True
    )
    assert b"1 Imported" in res.data
-    time.sleep(2)
+    wait_for_all_checks(client)

    res = client.post(
        url_for("edit_page", uuid="first"),
@@ -244,11 +240,8 @@ def test_check_with_prefix_include_filters(client, live_server):
    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
    assert b'Deleted' in res.data

-    # Give the endpoint time to spin up
-    time.sleep(1)
-
    set_original_response()
-
+    wait_for_all_checks(client)
    # Add our URL to the import page
    test_url = url_for('test_endpoint', _external=True)
    res = client.post(
@@ -257,7 +250,7 @@ def test_check_with_prefix_include_filters(client, live_server):
        follow_redirects=True
    )
    assert b"1 Imported" in res.data
-    time.sleep(3)
+    wait_for_all_checks(client)

    res = client.post(
        url_for("edit_page", uuid="first"),
@@ -266,7 +259,7 @@ def test_check_with_prefix_include_filters(client, live_server):
    )

    assert b"Updated watch." in res.data
-    time.sleep(3)
+    wait_for_all_checks(client)

    res = client.get(
        url_for("preview_page", uuid="first"),
@@ -277,3 +270,46 @@ def test_check_with_prefix_include_filters(client, live_server):
    assert b"Some text that will change" not in res.data #not in selector

    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+def test_various_rules(client, live_server):
+    # Just check these don't error
+    #live_server_setup(live_server)
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write("""<html>
+       <body>
+     Some initial text<br>
+     <p>Which is across multiple lines</p>
+     <br>
+     So let's see what happens.  <br>
+     <div class="sametext">Some text thats the same</div>
+     <div class="changetext">Some text that will change</div>
+     <a href=''>some linky </a>
+     <a href=''>another some linky </a>
+     <!-- related to https://github.com/dgtlmoon/changedetection.io/pull/1774 -->
+     <input   type="email"   id="email" />
+     </body>
+     </html>
+    """)
+    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)
+
+
+    for r in ['//div', '//a', 'xpath://div', 'xpath://a']:
+        res = client.post(
+            url_for("edit_page", uuid="first"),
+            data={"include_filters": r,
+                  "url": test_url,
+                  "tags": "",
+                  "headers": "",
+                  'fetch_backend': "html_requests"},
+            follow_redirects=True
+        )
+        wait_for_all_checks(client)
+        assert b"Updated watch." in res.data
+        res = client.get(url_for("index"))
+        assert b'fetch-error' not in res.data, f"Should not see errors after '{r} filter"
--- a/changedetectionio/tests/visualselector/test_fetch_data.py
+++ b/changedetectionio/tests/visualselector/test_fetch_data.py
@@ -1,18 +1,19 @@
 #!/usr/bin/python3

 import time
+import os
 from flask import url_for
 from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client

+def test_setup(client, live_server):
+    live_server_setup(live_server)
+
 # Add a site in paused mode, add an invalid filter, we should still have visual selector data ready
 def test_visual_selector_content_ready(client, live_server):
    import os
    import json

    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
-    time.sleep(1)
-    live_server_setup(live_server)
-

    # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
    test_url = "https://changedetection.io/ci-test/test-runjs.html"
@@ -53,6 +54,13 @@ def test_visual_selector_content_ready(client, live_server):
    with open(os.path.join('test-datastore', uuid, 'elements.json'), 'r') as f:
        json.load(f)

+    # Attempt to fetch it via the web hook that the browser would use
+    res = client.get(url_for('static_content', group='visual_selector_data', filename=uuid))
+    json.loads(res.data)
+    assert res.mimetype == 'application/json'
+    assert res.status_code == 200
+
+
    # Some options should be enabled
    # @todo - in the future, the visibility should be toggled by JS from the request type setting
    res = client.get(
@@ -60,4 +68,75 @@ def test_visual_selector_content_ready(client, live_server):
        follow_redirects=True
    )
    assert b'notification_screenshot' in res.data
+    client.get(
+        url_for("form_delete", uuid="all"),
+        follow_redirects=True
+    )

+def test_basic_browserstep(client, live_server):
+
+    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
+    #live_server_setup(live_server)
+
+    # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
+    test_url = "https://changedetection.io/ci-test/test-runjs.html"
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+        data={
+              "url": test_url,
+              "tags": "",
+              "headers": "",
+              'fetch_backend': "html_webdriver",
+              'browser_steps-0-operation': 'Goto site',
+              'browser_steps-1-operation': 'Click element',
+              'browser_steps-1-selector': 'button[name=test-button]',
+              'browser_steps-1-optional_value': ''
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+
+    uuid = extract_UUID_from_client(client)
+
+    # Check HTML conversion detected and workd
+    res = client.get(
+        url_for("preview_page", uuid=uuid),
+        follow_redirects=True
+    )
+    assert b"This text should be removed" not in res.data
+    assert b"I smell JavaScript because the button was pressed" in res.data
+
+    # now test for 404 errors
+    res = client.post(
+        url_for("edit_page", uuid=uuid, unpause_on_save=1),
+        data={
+              "url": "https://changedetection.io/404",
+              "tags": "",
+              "headers": "",
+              'fetch_backend': "html_webdriver",
+              'browser_steps-0-operation': 'Goto site',
+              'browser_steps-1-operation': 'Click element',
+              'browser_steps-1-selector': 'button[name=test-button]',
+              'browser_steps-1-optional_value': ''
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+
+    res = client.get(url_for("index"))
+    assert b'Error - 404' in res.data
+
+    client.get(
+        url_for("form_delete", uuid="all"),
+        follow_redirects=True
+    )
--- a/changedetectionio/update_worker.py
+++ b/changedetectionio/update_worker.py
@@ -238,7 +238,9 @@ class update_worker(threading.Thread):
                            # Used as a default and also by some tests
                            update_handler = text_json_diff.perform_site_check(datastore=self.datastore)

+                        self.datastore.data['watching'][uuid]['browser_steps_last_error_step'] = None
                        changed_detected, update_obj, contents = update_handler.run(uuid, skip_when_checksum_same=queued_item_data.item.get('skip_when_checksum_same'))
+
                        # 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
@@ -324,8 +326,13 @@ class update_worker(threading.Thread):
                        if not self.datastore.data['watching'].get(uuid):
                            continue

-                        err_text = "Warning, browser step at position {} could not run, target not found, check the watch, add a delay if necessary.".format(e.step_n+1)
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
+                        error_step = e.step_n + 1
+                        err_text = f"Warning, browser step at position {error_step} could not run, target not found, check the watch, add a delay if necessary, view Browser Steps to see screenshot at that step"
+                        self.datastore.update_watch(uuid=uuid,
+                                                    update_obj={'last_error': err_text,
+                                                                'browser_steps_last_error_step': error_step
+                                                                }
+                                                    )


                        if self.datastore.data['watching'][uuid].get('filter_failure_notification_send', False):
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -66,25 +66,12 @@ services:
 #        browser-chrome:
 #            condition: service_started

-#    browser-chrome:
-#        hostname: browser-chrome
-#        image: selenium/standalone-chrome-debug:3.141.59
-#        environment:
-#            - VNC_NO_PASSWORD=1
-#            - SCREEN_WIDTH=1920
-#            - SCREEN_HEIGHT=1080
-#            - SCREEN_DEPTH=24
-#        volumes:
-#            # Workaround to avoid the browser crashing inside a docker container
-#            # See https://github.com/SeleniumHQ/docker-selenium#quick-start
-#            - /dev/shm:/dev/shm
-#        restart: unless-stopped
-
     # Used for fetching pages via Playwright+Chrome where you need Javascript support.
-
+     # Note: Playwright/browserless not supported on ARM type devices (rPi etc)
+     # RECOMMENDED FOR FETCHING PAGES WITH CHROME
 #    playwright-chrome:
 #        hostname: playwright-chrome
-#        image: browserless/chrome
+#        image: browserless/chrome:1.60-chrome-stable
 #        restart: unless-stopped
 #        environment:
 #            - SCREEN_WIDTH=1920
@@ -101,6 +88,23 @@ services:
 #             Ignore HTTPS errors, like for self-signed certs
 #            - DEFAULT_IGNORE_HTTPS_ERRORS=true
 #
+
+     # Used for fetching pages via Playwright+Chrome where you need Javascript support.
+     # Note: works well but is deprecated, doesnt fetch full page screenshots and other issues
+#    browser-chrome:
+#        hostname: browser-chrome
+#        image: selenium/standalone-chrome:4
+#        environment:
+#            - VNC_NO_PASSWORD=1
+#            - SCREEN_WIDTH=1920
+#            - SCREEN_HEIGHT=1080
+#            - SCREEN_DEPTH=24
+#        volumes:
+#            # Workaround to avoid the browser crashing inside a docker container
+#            # See https://github.com/SeleniumHQ/docker-selenium#quick-start
+#            - /dev/shm:/dev/shm
+#        restart: unless-stopped
+
 volumes:
  changedetection-data:

--- a/requirements.txt
+++ b/requirements.txt
@@ -1,12 +1,13 @@
-eventlet>=0.31.0
+eventlet>=0.33.3 # related to dnspython fixes
 feedgen~=0.9
 flask-compress
-flask-login~=0.5
+# 0.6.3 included compatibility fix for werkzeug 3.x (2.x had deprecation of url handlers)
+flask-login>=0.6.3
 flask-paginate
 flask_expects_json~=1.7
 flask_restful
-flask_wtf
-flask~=2.0
+flask_wtf~=1.2
+flask~=2.3
 inscriptis~=2.2
 pytz
 timeago~=1.0
@@ -16,7 +17,7 @@ validators~=0.21
 # Set these versions together to avoid a RequestsDependencyWarning
 # >= 2.26 also adds Brotli support if brotli is installed
 brotli~=1.0
-requests[socks] ~=2.28
+requests[socks]

 urllib3>1.26
 chardet>2.3.0
@@ -24,16 +25,12 @@ chardet>2.3.0
 wtforms~=3.0
 jsonpath-ng~=1.5.3

-
-# dnspython 2.3.0 is not compatible with eventlet
-# * https://github.com/eventlet/eventlet/issues/781
-# * https://datastax-oss.atlassian.net/browse/PYTHON-1320
-dnspython<2.3.0
+dnspython~=2.4 # related to eventlet fixes

 # jq not available on Windows so must be installed manually

 # Notification library
-apprise~=1.5.0
+apprise~=1.6.0

 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 paho-mqtt
@@ -49,21 +46,18 @@ beautifulsoup4
 # XPath filtering, lxml is required by bs4 anyway, but put it here to be safe.
 lxml

-# 3.141 was missing socksVersion, 3.150 was not in pypi, so we try 4.1.0
-selenium~=4.1.0
+selenium~=4.14.0

-# https://stackoverflow.com/questions/71652965/importerror-cannot-import-name-safe-str-cmp-from-werkzeug-security/71653849#71653849
-# ImportError: cannot import name 'safe_str_cmp' from 'werkzeug.security'
-# need to revisit flask login versions
-werkzeug~=2.0.0
+werkzeug~=3.0

 # Templating, so far just in the URLs but in the future can be for the notifications also
 jinja2~=3.1
 jinja2-time
-
+openpyxl
 # https://peps.python.org/pep-0508/#environment-markers
 # https://github.com/dgtlmoon/changedetection.io/pull/1009
-jq~=1.3 ;python_version >= "3.8" and sys_platform == "linux"
+jq~=1.3; python_version >= "3.8" and sys_platform == "darwin"
+jq~=1.3; python_version >= "3.8" and sys_platform == "linux"

 # Any current modern version, required so far for screenshot PNG->JPEG conversion but will be used more in the future
 pillow
Author	SHA1	Message	Date
dgtlmoon	06975d6d8f	0.45.7.1	2023-11-11 20:42:16 +01:00
dgtlmoon	f58e5b7f19	Build: python libraries - pinning more libraries (#1962 )	2023-11-11 20:41:21 +01:00
dgtlmoon	e50eff8e35	Build: python libraries - eventlet + dnspython dep problems were fixed (#1963 )	2023-11-11 20:16:09 +01:00
dgtlmoon	07a853ce59	Pip builder - ignore proxy test data if it exists	2023-11-10 17:50:09 +01:00
dgtlmoon	80f8d23309	0.45.7	2023-11-10 17:39:49 +01:00
dgtlmoon	9f41d15908	UI - Fixing issue where search box JS interfered with page render when logged out	2023-11-10 17:38:04 +01:00
dgtlmoon	89797dfe02	0.45.6	2023-11-10 17:32:21 +01:00
dgtlmoon	c905652780	UI - Adding support-us widget <3 (#1956 )	2023-11-10 17:31:00 +01:00
dgtlmoon	99246d3e6d	Visual Selector - Small fix, Improving elements fetcher reliability (#1947 )	2023-11-09 19:13:18 +01:00
dgtlmoon	f9f69bf0dd	Update README.md - Adding import information	2023-11-08 11:55:02 +01:00
dgtlmoon	68efb25e9b	Upgrade playwright browser library (#1942 )	2023-11-07 16:33:29 +01:00
dgtlmoon	70606ab05d	Update docker-compose.yml - playwright version should be the same as in the automated tests	2023-11-06 22:33:22 +01:00
Jai Gupta	d3c8386874	Import - Improved Wachete Excel XLS import support for "dynamic wachet" (sets correct state of using chrome browser or not) column (#1934 )	2023-11-06 12:50:27 +01:00
dgtlmoon	47103d7f3d	Refactor Excel / wachete import, extend tests (#1931 )	2023-11-03 15:43:57 +01:00
dgtlmoon	03c671bfff	Build - Upgrading pip packages (#1915 )	2023-11-01 18:47:12 +01:00
dgtlmoon	e209d9fba0	Ability to Import from Wachete XLSX (or any XLSX) - Wachete alternative made easy (#1921 )	2023-11-01 15:36:49 +01:00
dgtlmoon	3b43da35ec	Docker build - upgrade image to "bookworm" debian version - fix glibc mismatch (#1918 )	2023-10-31 10:31:34 +01:00
dgtlmoon	a0665e1f18	Fetcher - experimental puppeteer fetch - dont rewrite the proxy protocol (fixes socks5 bug)	2023-10-30 16:08:31 +01:00
dgtlmoon	9ffe7e0eaf	Nice format stats (comma sep)	2023-10-29 19:13:15 +01:00
dgtlmoon	3e5671a3a2	Selenium fetcher - Test was on `4.14.1` but documentation was not, change both to `4` (#1912 )	2023-10-29 11:43:27 +01:00
dgtlmoon	cd1aca9ee3	0.45.5	2023-10-28 20:20:24 +02:00
dgtlmoon	6a589e14f3	BrowserSteps - Wrong text taken from browser steps (#1911 )	2023-10-28 20:19:51 +02:00
dgtlmoon	dbb76f3618	0.45.4	2023-10-28 16:48:10 +02:00
dgtlmoon	4ae27af511	Code cleanup - Browser Steps	2023-10-28 14:58:12 +02:00
dgtlmoon	e1860549dc	Fetching - Browser Step enabled watches should also identify 404/non-200 status situations (#1907 )	2023-10-28 14:37:42 +02:00
dgtlmoon	9765d56a23	Text Filters - "Extract Text" filter was not being error checked properly when using a RegEx (#1902 )	2023-10-26 20:19:59 +02:00
dgtlmoon	349111eb35	Fetching/BrowserSteps - Going to a page was using slightly logic to the main way - make them use the same methods (#1890 )	2023-10-26 20:19:22 +02:00
dgtlmoon	71e50569a0	UI - "With errors" tag/button should always show the current tag error count	2023-10-26 19:42:48 +02:00
Marcelo Alencar	c372942295	Build - Add piwheels support for ARMv6 and ARMv7 machines (rPi etc) (#1814 )	2023-10-26 13:46:14 +02:00
Marcelo Alencar	0aef5483d9	Upgrade selenium to 4.14.0 (latest) (#1783 )	2023-10-26 10:09:03 +02:00
dgtlmoon	c266c64b94	UI - Don't show search icon when logged out (#1896 )	2023-10-25 13:31:33 +02:00
dgtlmoon	32e5498a9d	UI - Adding handy "limit to watches with errors" button (#1886 )	2023-10-23 12:22:43 +02:00
dgtlmoon	0ba7928d58	UI - Viewing text differences - Tweaks to "Jump to next change" button	2023-10-23 11:42:01 +02:00
dgtlmoon	1709e8f936	UI - BrowserSteps - Show the screenshot of an error if it happened on a step, highlight which step had the error to make it easier to find out why the step didnt work, minor fixes to timeouts(#1883 )	2023-10-21 09:41:51 +02:00
dgtlmoon	b16d65741c	UI - Visual Selector should be the same page-size as Browser Steps (fit inside the browser viewport)	2023-10-20 16:15:17 +02:00
Constantin Hong	1cadcc6d15	Packaging - Enable jq query for filters package installation for darwin (mac) #1868	2023-10-20 15:11:16 +02:00
dgtlmoon	b58d521d19	UI - Adding [stats] tab to watch Edit page (#1880 )	2023-10-20 11:49:12 +02:00
dgtlmoon	52225f2ad8	Bugfix - [Clear history] button was not clearing all metadata (#1881 )	2023-10-20 11:47:49 +02:00
dgtlmoon	7220afab0a	RSS fetch - RSS field <title> was not rendering as text correctly, added workaround #1879	2023-10-19 16:42:05 +02:00
dgtlmoon	1c0fe4c23e	PDF Fetching - Handle when the PDF is given as inline content without a proper mime header (#1875 )	2023-10-19 13:20:01 +02:00
dgtlmoon	4f6b0eb8a5	Notification library - Bump Apprise notification library to 1.6.0 (#1867 )	2023-10-17 22:18:53 +02:00
dgtlmoon	f707c914b6	RSS Fetching - Handle CDATA (commented out text) in RSS correctly, generally handle RSS better (#1866 )	2023-10-17 18:34:19 +02:00
dgtlmoon	9cb636e638	UI - Adding mouseover/title to show absolute date/time of a last-change or last-checked date #1860	2023-10-17 14:03:19 +02:00
dgtlmoon	1d5fe51157	UI - Difference text viewer - fixing jump to new difference on changing word/line/etc style	2023-10-17 13:43:58 +02:00
dgtlmoon	c0b49d3be9	Testing - Improve xPath tests (#1863 )	2023-10-16 16:48:47 +02:00
dgtlmoon	c4dc85525f	UI - Fixing jump to next difference button after refactor	2023-10-14 23:32:18 +02:00
dgtlmoon	26159840c8	UI - Updating proxy tip link	2023-10-14 23:27:41 +02:00
dgtlmoon	522e9786c6	UI - Adding watch label/title to [edit] page title (#1858 )	2023-10-13 12:51:31 +02:00
dgtlmoon	9ce86a2835	Documentation - Add note that playwright is not supported on ARM type devices #1856	2023-10-12 10:14:31 +02:00
dgtlmoon	f9f6300a70	UI - Difference page - added 'title' to each change for nice mouse-over information about when the change occured	2023-10-11 16:46:54 +02:00
dgtlmoon	7734b22a19	UI - Difference page - Tweak 'preview' page invite text	2023-10-11 16:31:04 +02:00
dgtlmoon	da421fe110	UI - Ability to select between any difference date ( from / to ) and minor UI cleanup for differences page (#1855 )	2023-10-11 16:25:36 +02:00
dgtlmoon	3e2b55a46f	UI - Difference page, make the button to find the preview page for triggers and ignored text easier to find	2023-10-11 16:24:32 +02:00
dgtlmoon	7ace259d70	System - No need to run updates on fresh installs (#1854 )	2023-10-11 14:04:12 +02:00
dgtlmoon	aa6ad7bf47	UI - Proxy configuration helper notes improvements	2023-10-10 15:41:56 +02:00
dgtlmoon	40dd29dbc6	Preview/Difference page - When sharing the preview/difference page, highlight-to-ignore should login should be required (#1852 )	2023-10-10 11:39:44 +02:00
dgtlmoon	7debccca73	Fetching - Clarifying how fetchers work with SOCKS5 proxies	2023-10-09 16:57:30 +02:00