WIP

.github/workflows/test-only.yml

@@ -30,7 +30,7 @@ jobs:
 
           # 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 browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
 
       - name: Build changedetection.io container for testing
         run: |         
@@ -55,19 +55,9 @@ jobs:
           # Playwright/Browserless fetch
           docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
           
-          # Settings headers playwright tests - Call back in from Browserless, check headers
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "USE_EXPERIMENTAL_PUPPETEER_FETCH=yes" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
-          
           # restock detection via playwright - added name=changedet here so that playwright/browserless can connect to it
           docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
 
-      - name: Test with puppeteer fetcher and disk cache
-        run: |
-          docker run --rm -e "PUPPETEER_DISK_CACHE=/tmp/data/" -e "USE_EXPERIMENTAL_PUPPETEER_FETCH=yes" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
-          # Browserless would have had -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" added above
-
       - name: Test proxy interaction
         run: |
           cd changedetectionio

Dockerfile

@@ -1,5 +1,5 @@
 # pip dependencies install stage
-FROM python:3.10-slim-bookworm as builder
+FROM python:3.10-slim as builder
 
 # See `cryptography` pin comment in requirements.txt
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
@@ -29,10 +29,10 @@ RUN pip install --target=/dependencies playwright~=1.27.1 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
-FROM python:3.10-slim-bookworm
+FROM python:3.10-slim
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    libssl3 \
+    libssl1.1 \
     libxslt1.1 \
     # For pdftohtml
     poppler-utils \

README-pip.md

@@ -2,10 +2,10 @@
 
 Live your data-life pro-actively, track website content changes and receive notifications via Discord, Email, Slack, Telegram and 70+ more
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://changedetection.io)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=pip)
 
 
-[**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://changedetection.io) 
+[**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://lemonade.changedetection.io/start) 
 
 
 #### Example use cases

README.md

@@ -5,13 +5,13 @@
 _Live your data-life pro-actively._ 
 
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://changedetection.io?src=github)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=github)
 
 [![Release Version][release-shield]][release-link] [![Docker Pulls][docker-pulls]][docker-link] [![License][license-shield]](LICENSE.md)
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
-[**Don't have time? Let us host it for you! try our $8.99/month subscription - use our proxies and support!**](https://changedetection.io) , _half the price of other website change monitoring services!_
+[**Don't have time? Let us host it for you! try our $8.99/month subscription - use our proxies and support!**](https://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
 
 - Chrome browser included.
 - Super fast, no registration needed setup.
@@ -22,11 +22,11 @@ _Live your data-life pro-actively._
 
 Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://changedetection.io?src=github)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://lemonade.changedetection.io/start?src=github)
 
 ### Easily see what changed, examine by word, line, or individual character.
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://changedetection.io?src=github)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://lemonade.changedetection.io/start?src=github)
 
 
 ### Perform interactive browser steps
@@ -35,7 +35,7 @@ Fill in text boxes, click buttons and more, setup your changedetection scenario.
 
 Using the **Browser Steps** configuration, add basic steps before performing change detection, such as logging into websites, adding a product to a cart, accept cookie logins, entering dates and refining searches.
 
-[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Website change detection with interactive browser steps, login, cookies etc" />](https://changedetection.io?src=github)
+[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Website change detection with interactive browser steps, login, cookies etc" />](https://lemonade.changedetection.io/start?src=github)
 
 After **Browser Steps** have been run, then visit the **Visual Selector** tab to refine the content you're interested in.
 Requires Playwright to be enabled.
@@ -66,7 +66,6 @@ Requires Playwright to be enabled.
 - Proactively search for jobs, get notified when companies update their careers page, search job portals for keywords.
 - Get alerts when new job positions are open on Bamboo HR and other job platforms
 - Website defacement monitoring
-- Pokémon Card Restock Tracker / Pokémon TCG Tracker
 
 _Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
 
@@ -145,7 +144,7 @@ See the wiki for more information https://github.com/dgtlmoon/changedetection.io
 ## Filters
 
 XPath, JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools. 
-(We support LXML `re:test`, `re:match` and `re:replace`.)
+(We support LXML `re:test`, `re:math` and `re:replace`.)
 
 ## Notifications
 
@@ -238,7 +237,7 @@ Supports managing the website watch list [via our API](https://changedetection.i
 Do you use changedetection.io to make money? does it save you time or money? Does it make your life easier? less stressful? Remember, we write this software when we should be doing actual paid work, we have to buy food and pay rent just like you.
 
 
-Firstly, consider taking out a [change detection monthly subscription - unlimited checks and watches](https://changedetection.io?src=github) , even if you don't use it, you still get the warm fuzzy feeling of helping out the project. (And who knows, you might just use it!)
+Firstly, consider taking out a [change detection monthly subscription - unlimited checks and watches](https://lemonade.changedetection.io/start) , even if you don't use it, you still get the warm fuzzy feeling of helping out the project. (And who knows, you might just use it!)
 
 Or directly donate an amount PayPal [![Donate](https://img.shields.io/badge/Donate-PayPal-green.svg)](https://www.paypal.com/donate/?hosted_button_id=7CP6HR9ZCNDYJ)
 

changedetectionio/__init__.py

@@ -33,12 +33,10 @@ from flask import (
     url_for,
 )
 
-from flask_paginate import Pagination, get_page_parameter
-
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.42.3'
+__version__ = '0.41.1'
 
 datastore = None
 
@@ -124,15 +122,6 @@ def _jinja2_filter_datetimestamp(timestamp, format="%Y-%m-%d %H:%M:%S"):
 
     return timeago.format(timestamp, time.time())
 
-
-@app.template_filter('pagination_slice')
-def _jinja2_filter_pagination_slice(arr, skip):
-    per_page = datastore.data['settings']['application'].get('pager_size', 50)
-    if per_page:
-        return arr[skip:skip + per_page]
-
-    return arr
-
 @app.template_filter('format_seconds_ago')
 def _jinja2_filter_seconds_precise(timestamp):
     if timestamp == False:
@@ -412,41 +401,24 @@ def changedetection_app(config=None, datastore_o=None):
 
         # Sort by last_changed and add the uuid which is usually the key..
         sorted_watches = []
-        search_q = request.args.get('q').strip().lower() if request.args.get('q') else False
         for uuid, watch in datastore.data['watching'].items():
 
-            if limit_tag:
+            if limit_tag != None:
                 # Support for comma separated list of tags.
-                if not watch.get('tag'):
+                if watch['tag'] is None:
                     continue
-                for tag_in_watch in watch.get('tag', '').split(','):
+                for tag_in_watch in watch['tag'].split(','):
                     tag_in_watch = tag_in_watch.strip()
                     if tag_in_watch == limit_tag:
                         watch['uuid'] = uuid
-                        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)
-                        else:
-                            sorted_watches.append(watch)
+                        sorted_watches.append(watch)
 
             else:
-                #watch['uuid'] = uuid
-                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)
-                else:
-                    sorted_watches.append(watch)
+                watch['uuid'] = uuid
+                sorted_watches.append(watch)
 
         existing_tags = datastore.get_all_tags()
         form = forms.quickWatchForm(request.form)
-        page = request.args.get(get_page_parameter(), type=int, default=1)
-        total_count = len(sorted_watches)
-
-        pagination = Pagination(page=page,
-                                total=total_count,
-                                per_page=datastore.data['settings']['application'].get('pager_size', 50), css_framework="semantic")
-
-
         output = render_template(
             "watch-overview.html",
                                  # Don't link to hosting when we're on the hosting environment
@@ -457,29 +429,16 @@ def changedetection_app(config=None, datastore_o=None):
                                  has_proxies=datastore.proxy_list,
                                  has_unviewed=datastore.has_unviewed,
                                  hosted_sticky=os.getenv("SALTED_PASS", False) == False,
-                                 pagination=pagination,
                                  queued_uuids=[q_uuid.item['uuid'] for q_uuid in update_q.queue],
-                                 search_q=request.args.get('q','').strip(),
-                                 sort_attribute=request.args.get('sort') if request.args.get('sort') else request.cookies.get('sort'),
-                                 sort_order=request.args.get('order') if request.args.get('order') else request.cookies.get('order'),
                                  system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),
                                  tags=existing_tags,
                                  watches=sorted_watches
                                  )
 
+
         if session.get('share-link'):
             del(session['share-link'])
-
-        resp = make_response(output)
-
-        # The template can run on cookie or url query info
-        if request.args.get('sort'):
-            resp.set_cookie('sort', request.args.get('sort'))
-        if request.args.get('order'):
-            resp.set_cookie('order', request.args.get('order'))
-
-        return resp
-
+        return output
 
 
     # AJAX endpoint for sending a test
@@ -504,19 +463,11 @@ def changedetection_app(config=None, datastore_o=None):
 
         try:
             n_object = {'watch_url': request.form['window_url'],
-                        'notification_urls': request.form['notification_urls'].splitlines()
+                        'notification_urls': request.form['notification_urls'].splitlines(),
+                        'notification_title': request.form['notification_title'].strip(),
+                        'notification_body': request.form['notification_body'].strip(),
+                        'notification_format': request.form['notification_format'].strip()
                         }
-
-            # Only use if present, if not set in n_object it should use the default system value
-            if 'notification_format' in request.form and request.form['notification_format'].strip():
-                n_object['notification_format'] = request.form.get('notification_format', '').strip()
-
-            if 'notification_title' in request.form and request.form['notification_title'].strip():
-                n_object['notification_title'] = request.form.get('notification_title', '').strip()
-
-            if 'notification_body' in request.form and request.form['notification_body'].strip():
-                n_object['notification_body'] = request.form.get('notification_body', '').strip()
-
             notification_q.put(n_object)
         except Exception as e:
             return make_response({'error': str(e)}, 400)
@@ -713,7 +664,6 @@ def changedetection_app(config=None, datastore_o=None):
                                      form=form,
                                      has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
                                      has_empty_checktime=using_default_check_time,
-                                     has_extra_headers_file=watch.has_extra_headers_file or datastore.has_extra_headers_file,
                                      is_html_webdriver=is_html_webdriver,
                                      jq_support=jq_support,
                                      playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False),
@@ -729,7 +679,7 @@ def changedetection_app(config=None, datastore_o=None):
     @app.route("/settings", methods=['GET', "POST"])
     @login_optionally_required
     def settings_page():
-        from changedetectionio import content_fetcher, forms
+        from . import forms
 
         default = deepcopy(datastore.data['settings'])
         if datastore.proxy_list is not None:
@@ -1308,13 +1258,6 @@ def changedetection_app(config=None, datastore_o=None):
                     datastore.data['watching'][uuid.strip()]['paused'] = False
             flash("{} watches unpaused".format(len(uuids)))
 
-        elif (op == 'mark-viewed'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.set_last_viewed(uuid, int(time.time()))
-            flash("{} watches updated".format(len(uuids)))
-
         elif (op == 'mute'):
             for uuid in uuids:
                 uuid = uuid.strip()
@@ -1337,13 +1280,6 @@ def changedetection_app(config=None, datastore_o=None):
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
             flash("{} watches queued for rechecking".format(len(uuids)))
 
-        elif (op == 'clear-history'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    datastore.clear_watch_history(uuid)
-            flash("{} watches cleared/reset.".format(len(uuids)))
-
         elif (op == 'notification-default'):
             from changedetectionio.notification import (
                 default_notification_format_for_watch
@@ -1458,7 +1394,6 @@ def check_for_new_version():
         # Check daily
         app.config.exit.wait(86400)
 
-
 def notification_runner():
     global notification_debug_log
     from datetime import datetime

changedetectionio/blueprint/browser_steps/__init__.py

@@ -27,106 +27,58 @@ import os
 import logging
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio import login_optionally_required
+browsersteps_live_ui_o = {}
+browsersteps_playwright_browser_interface = None
+browsersteps_playwright_browser_interface_browser = None
+browsersteps_playwright_browser_interface_context = None
+browsersteps_playwright_browser_interface_end_time = None
+browsersteps_playwright_browser_interface_start_time = None
 
-browsersteps_sessions = {}
-io_interface_context = None
+def cleanup_playwright_session():
 
+    global browsersteps_live_ui_o
+    global browsersteps_playwright_browser_interface
+    global browsersteps_playwright_browser_interface_browser
+    global browsersteps_playwright_browser_interface_context
+    global browsersteps_playwright_browser_interface_end_time
+    global browsersteps_playwright_browser_interface_start_time
+
+    browsersteps_live_ui_o = {}
+    browsersteps_playwright_browser_interface = None
+    browsersteps_playwright_browser_interface_browser = None
+    browsersteps_playwright_browser_interface_end_time = None
+    browsersteps_playwright_browser_interface_start_time = None
+
+    print("Cleaning up old playwright session because time was up, calling .goodbye()")
+    try:
+        browsersteps_playwright_browser_interface_context.goodbye()
+    except Exception as e:
+        print ("Got exception in shutdown, probably OK")
+        print (str(e))
+
+    browsersteps_playwright_browser_interface_context = None
+
+    print ("Cleaning up old playwright session because time was up - done")
 
 def construct_blueprint(datastore: ChangeDetectionStore):
+
     browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
 
-    def start_browsersteps_session(watch_uuid):
-        from . import nonContext
-        from . import browser_steps
-        import time
-        global browsersteps_sessions
-        global io_interface_context
-
-
-        # We keep the playwright session open for many minutes
-        seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
-
-        browsersteps_start_session = {'start_time': time.time()}
-
-        # You can only have one of these running
-        # This should be very fine to leave running for the life of the application
-        # @idea - Make it global so the pool of watch fetchers can use it also
-        if not io_interface_context:
-            io_interface_context = nonContext.c_sync_playwright()
-            # Start the Playwright context, which is actually a nodejs sub-process and communicates over STDIN/STDOUT pipes
-            io_interface_context = io_interface_context.start()
-
-
-        # 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)
-        except Exception as e:
-            if 'ECONNREFUSED' in str(e):
-                return make_response('Unable to start the Playwright Browser session, is it running?', 401)
-            else:
-                return make_response(str(e), 401)
-
-        proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
-        proxy = None
-        if proxy_id:
-            proxy_url = datastore.proxy_list.get(proxy_id).get('url')
-            if proxy_url:
-
-                # Playwright needs separate username and password values
-                from urllib.parse import urlparse
-                parsed = urlparse(proxy_url)
-                proxy = {'server': proxy_url}
-
-                if parsed.username:
-                    proxy['username'] = parsed.username
-
-                if parsed.password:
-                    proxy['password'] = parsed.password
-
-                print("Browser Steps: UUID {} selected proxy {}".format(watch_uuid, proxy_url))
-
-        # Tell Playwright to connect to Chrome and setup a new session via our stepper interface
-        browsersteps_start_session['browserstepper'] = browser_steps.browsersteps_live_ui(
-            playwright_browser=browsersteps_start_session['browser'],
-            proxy=proxy)
-
-        # For test
-        #browsersteps_start_session['browserstepper'].action_goto_url(value="http://example.com?time="+str(time.time()))
-
-        return browsersteps_start_session
-
-
     @login_optionally_required
-    @browser_steps_blueprint.route("/browsersteps_start_session", methods=['GET'])
-    def browsersteps_start_session():
-        # A new session was requested, return sessionID
-
-        import uuid
-        global browsersteps_sessions
-
-        browsersteps_session_id = str(uuid.uuid4())
-        watch_uuid = request.args.get('uuid')
-
-        if not watch_uuid:
-            return make_response('No Watch UUID specified', 500)
-
-        print("Starting connection with playwright")
-        logging.debug("browser_steps.py connecting")
-        browsersteps_sessions[browsersteps_session_id] = start_browsersteps_session(watch_uuid)
-        print("Starting connection with playwright - done")
-        return {'browsersteps_session_id': browsersteps_session_id}
-
-    # A request for an action was received
-    @login_optionally_required
-    @browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
+    @browser_steps_blueprint.route("/browsersteps_update", methods=['GET', 'POST'])
     def browsersteps_ui_update():
         import base64
         import playwright._impl._api_types
-        global browsersteps_sessions
+        import time
+
         from changedetectionio.blueprint.browser_steps import browser_steps
 
+        global browsersteps_live_ui_o, browsersteps_playwright_browser_interface_end_time
+        global browsersteps_playwright_browser_interface_browser
+        global browsersteps_playwright_browser_interface
+        global browsersteps_playwright_browser_interface_start_time
+
+        step_n = None
         remaining =0
         uuid = request.args.get('uuid')
 
@@ -135,9 +87,13 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         if not browsersteps_session_id:
             return make_response('No browsersteps_session_id specified', 500)
 
-        if not browsersteps_sessions.get(browsersteps_session_id):
-            return make_response('No session exists under that ID', 500)
-
+        # Because we don't "really" run in a context manager ( we make the playwright interface global/long-living )
+        # We need to manage the shutdown when the time is up
+        if browsersteps_playwright_browser_interface_end_time:
+            remaining = browsersteps_playwright_browser_interface_end_time-time.time()
+            if browsersteps_playwright_browser_interface_end_time and remaining <= 0:
+                cleanup_playwright_session()
+                return make_response('Browser session expired, please reload the Browser Steps interface', 401)
 
         # Actions - step/apply/etc, do the thing and return state
         if request.method == 'POST':
@@ -156,7 +112,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             # @todo try.. accept.. nice errors not popups..
             try:
 
-                browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(action_name=step_operation,
+                this_session = browsersteps_live_ui_o.get(browsersteps_session_id)
+                if not this_session:
+                    print("Browser exited")
+                    return make_response('Browser session ran out of time :( Please reload this page.', 401)
+
+                this_session.call_action(action_name=step_operation,
                                          selector=step_selector,
                                          optional_value=step_optional_value)
 
@@ -168,43 +129,99 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             # Get visual selector ready/update its data (also use the current filter info from the page?)
             # When the last 'apply' button was pressed
             # @todo this adds overhead because the xpath selection is happening twice
-            u = browsersteps_sessions[browsersteps_session_id]['browserstepper'].page.url
+            u = this_session.page.url
             if is_last_step and u:
-                (screenshot, xpath_data) = browsersteps_sessions[browsersteps_session_id]['browserstepper'].request_visualselector_data()
+                (screenshot, xpath_data) = this_session.request_visualselector_data()
                 datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
                 datastore.save_xpath_data(watch_uuid=uuid, data=xpath_data)
 
-#        if not this_session.page:
-#            cleanup_playwright_session()
-#            return make_response('Browser session ran out of time :( Please reload this page.', 401)
+        # Setup interface
+        if request.method == 'GET':
 
-        # Screenshots and other info only needed on requesting a step (POST)
-        try:
-            state = browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
-        except playwright._impl._api_types.Error as e:
-            return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
+            if not browsersteps_playwright_browser_interface:
+                print("Starting connection with playwright")
+                logging.debug("browser_steps.py connecting")
 
-        # Use send_file() which is way faster than read/write loop on bytes
-        import json
-        from tempfile import mkstemp
-        from flask import send_file
-        tmp_fd, tmp_file = mkstemp(text=True, suffix=".json", prefix="changedetectionio-")
+                global browsersteps_playwright_browser_interface_context
+                from . import nonContext
+                browsersteps_playwright_browser_interface_context = nonContext.c_sync_playwright()
+                browsersteps_playwright_browser_interface = browsersteps_playwright_browser_interface_context.start()
 
-        output = json.dumps({'screenshot': "data:image/jpeg;base64,{}".format(
-            base64.b64encode(state[0]).decode('ascii')),
-            'xpath_data': state[1],
-            'session_age_start': browsersteps_sessions[browsersteps_session_id]['browserstepper'].age_start,
-            'browser_time_remaining': round(remaining)
-        })
+                time.sleep(1)
+                # At 20 minutes, some other variable is closing it
+                # @todo find out what it is and set it
+                seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
 
-        with os.fdopen(tmp_fd, 'w') as f:
-            f.write(output)
+                # 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_playwright_browser_interface_browser = browsersteps_playwright_browser_interface.chromium.connect_over_cdp(
+                        os.getenv('PLAYWRIGHT_DRIVER_URL', '') + keepalive)
+                except Exception as e:
+                    if 'ECONNREFUSED' in str(e):
+                        return make_response('Unable to start the Playwright session properly, is it running?', 401)
 
-        response = make_response(send_file(path_or_file=tmp_file,
-                                           mimetype='application/json; charset=UTF-8',
-                                           etag=True))
-        # No longer needed
-        os.unlink(tmp_file)
+                browsersteps_playwright_browser_interface_end_time = time.time() + (seconds_keepalive-3)
+                print("Starting connection with playwright - done")
+
+            if not browsersteps_live_ui_o.get(browsersteps_session_id):
+                # Boot up a new session
+                proxy_id = datastore.get_preferred_proxy_for_watch(uuid=uuid)
+                proxy = None
+                if proxy_id:
+                    proxy_url = datastore.proxy_list.get(proxy_id).get('url')
+                    if proxy_url:
+                        proxy = {'server': proxy_url}
+                        print("Browser Steps: UUID {} Using proxy {}".format(uuid, proxy_url))
+
+                # Begin the new "Playwright Context" that re-uses the playwright interface
+                # Each session is a "Playwright Context" as a list, that uses the playwright interface
+                browsersteps_live_ui_o[browsersteps_session_id] = browser_steps.browsersteps_live_ui(
+                    playwright_browser=browsersteps_playwright_browser_interface_browser,
+                    proxy=proxy)
+                this_session = browsersteps_live_ui_o[browsersteps_session_id]
+
+        if not this_session.page:
+            cleanup_playwright_session()
+            return make_response('Browser session ran out of time :( Please reload this page.', 401)
+
+        response = None
+
+        if request.method == 'POST':
+            # Screenshots and other info only needed on requesting a step (POST)
+            try:
+                state = this_session.get_current_state()
+            except playwright._impl._api_types.Error as e:
+                return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
+
+            # Use send_file() which is way faster than read/write loop on bytes
+            import json
+            from tempfile import mkstemp
+            from flask import send_file
+            tmp_fd, tmp_file = mkstemp(text=True, suffix=".json", prefix="changedetectionio-")
+
+            output = json.dumps({'screenshot': "data:image/jpeg;base64,{}".format(
+                base64.b64encode(state[0]).decode('ascii')),
+                'xpath_data': state[1],
+                'session_age_start': this_session.age_start,
+                'browser_time_remaining': round(remaining)
+            })
+
+            with os.fdopen(tmp_fd, 'w') as f:
+                f.write(output)
+
+            response = make_response(send_file(path_or_file=tmp_file,
+                                               mimetype='application/json; charset=UTF-8',
+                                               etag=True))
+            # No longer needed
+            os.unlink(tmp_file)
+
+        elif request.method == 'GET':
+            # Just enough to get the session rolling, it will call for goto-site via POST next
+            response = make_response({
+                'session_age_start': this_session.age_start,
+                'browser_time_remaining': round(remaining)
+            })
 
         return response
 

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -71,10 +71,10 @@ class steppable_browser_interface():
             optional_value = str(jinja2_env.from_string(optional_value).render())
 
         action_handler(selector, optional_value)
-        self.page.wait_for_timeout(1.5 * 1000)
+        self.page.wait_for_timeout(3 * 1000)
         print("Call action done in", time.time() - now)
 
-    def action_goto_url(self, selector=None, value=None):
+    def action_goto_url(self, selector, value):
         # self.page.set_viewport_size({"width": 1280, "height": 5000})
         now = time.time()
         response = self.page.goto(value, timeout=0, wait_until='commit')
@@ -105,8 +105,7 @@ class steppable_browser_interface():
         print("Clicking element")
         if not len(selector.strip()):
             return
-
-        self.page.click(selector=selector, timeout=30 * 1000, delay=randint(200, 500))
+        self.page.click(selector, timeout=10 * 1000, delay=randint(200, 500))
 
     def action_click_element_if_exists(self, selector, value):
         import playwright._impl._api_types as _api_types
@@ -133,18 +132,18 @@ class steppable_browser_interface():
         self.page.wait_for_timeout(1000)
 
     def action_wait_for_seconds(self, selector, value):
-        self.page.wait_for_timeout(float(value.strip()) * 1000)
+        self.page.wait_for_timeout(int(value) * 1000)
 
     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
@@ -238,7 +237,7 @@ class browsersteps_live_ui(steppable_browser_interface):
     def get_current_state(self):
         """Return the screenshot and interactive elements mapping, generally always called after action_()"""
         from pkg_resources import resource_string
-        xpath_element_js = resource_string(__name__, "../../res/xpath_element_scraper.js").decode('utf-8')
+        xpath_element_js = resource_string(__name__, "../res/xpath_element_scraper.js").decode('utf-8')
         now = time.time()
         self.page.wait_for_timeout(1 * 1000)
 
@@ -273,8 +272,8 @@ class browsersteps_live_ui(steppable_browser_interface):
         self.page.evaluate("var include_filters=''")
         from pkg_resources import resource_string
         # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
-        xpath_element_js = resource_string(__name__, "../../res/xpath_element_scraper.js").decode('utf-8')
-        from changedetectionio.content_fetcher import visualselector_xpath_selectors
+        xpath_element_js = resource_string(__name__, "../res/xpath_element_scraper.js").decode('utf-8')
+        from changedetectionio.fetchers import visualselector_xpath_selectors
         xpath_element_js = xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
         xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")
         screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))

changedetectionio/changedetection.py

@@ -13,7 +13,7 @@ import signal
 import socket
 import sys
 
-from . import store, changedetection_app, content_fetcher
+from . import store, changedetection_app
 from . import __version__
 
 # Only global so we can access it in the signal handler

changedetectionio/content_fetcher.py

@@ -1,746 +0,0 @@
-import hashlib
-from abc import abstractmethod
-import chardet
-import json
-import logging
-import os
-import requests
-import sys
-import time
-
-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'
-
-
-class Non200ErrorCodeReceived(Exception):
-    def __init__(self, status_code, url, screenshot=None, xpath_data=None, page_html=None):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        self.xpath_data = xpath_data
-        self.page_text = None
-
-        if page_html:
-            from changedetectionio import html_tools
-            self.page_text = html_tools.html_to_text(page_html)
-        return
-
-
-class checksumFromPreviousCheckWasTheSame(Exception):
-    def __init__(self):
-        return
-
-
-class JSActionExceptions(Exception):
-    def __init__(self, status_code, url, screenshot, message=''):
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        self.message = message
-        return
-
-
-class BrowserStepsStepTimout(Exception):
-    def __init__(self, step_n):
-        self.step_n = step_n
-        return
-
-
-class PageUnloadable(Exception):
-    def __init__(self, status_code, url, message, screenshot=False):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        self.message = message
-        return
-
-
-class EmptyReply(Exception):
-    def __init__(self, status_code, url, screenshot=None):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        return
-
-
-class ScreenshotUnavailable(Exception):
-    def __init__(self, status_code, url, page_html=None):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        if page_html:
-            from html_tools import html_to_text
-            self.page_text = html_to_text(page_html)
-        return
-
-
-class ReplyWithContentButNoText(Exception):
-    def __init__(self, status_code, url, screenshot=None):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        return
-
-
-class Fetcher():
-    browser_steps = None
-    browser_steps_screenshot_path = None
-    content = None
-    error = None
-    fetcher_description = "No description"
-    headers = {}
-    status_code = None
-    webdriver_js_execute_code = None
-    xpath_data = None
-    xpath_element_js = ""
-    instock_data = None
-    instock_data_js = ""
-
-    # Will be needed in the future by the VisualSelector, always get this where possible.
-    screenshot = False
-    system_http_proxy = os.getenv('HTTP_PROXY')
-    system_https_proxy = os.getenv('HTTPS_PROXY')
-
-    # Time ONTOP of the system defined env minimum time
-    render_extract_delay = 0
-
-    def __init__(self):
-        from pkg_resources import resource_string
-        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
-        self.xpath_element_js = resource_string(__name__, "res/xpath_element_scraper.js").decode('utf-8')
-        self.instock_data_js = resource_string(__name__, "res/stock-not-in-stock.js").decode('utf-8')
-
-    @abstractmethod
-    def get_error(self):
-        return self.error
-
-    @abstractmethod
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-        # Should set self.error, self.status_code and self.content
-        pass
-
-    @abstractmethod
-    def quit(self):
-        return
-
-    @abstractmethod
-    def get_last_status_code(self):
-        return self.status_code
-
-    @abstractmethod
-    def screenshot_step(self, step_n):
-        return None
-
-    @abstractmethod
-    # Return true/false if this checker is ready to run, in the case it needs todo some special config check etc
-    def is_ready(self):
-        return True
-
-    def get_all_headers(self):
-        """
-        Get all headers but ensure all keys are lowercase
-        :return:
-        """
-        return {k.lower(): v for k, v in self.headers.items()}
-
-    def iterate_browser_steps(self):
-        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
-        from playwright._impl._api_types import TimeoutError
-        from jinja2 import Environment
-        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
-
-        step_n = 0
-
-        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)
-
-            for step in valid_steps:
-                step_n += 1
-                print(">> Iterating check - browser Step n {} - {}...".format(step_n, step['operation']))
-                self.screenshot_step("before-" + str(step_n))
-                self.save_step_html("before-" + str(step_n))
-                try:
-                    optional_value = step['optional_value']
-                    selector = step['selector']
-                    # Support for jinja2 template in step values, with date module added
-                    if '{%' in step['optional_value'] or '{{' in step['optional_value']:
-                        optional_value = str(jinja2_env.from_string(step['optional_value']).render())
-                    if '{%' in step['selector'] or '{{' in step['selector']:
-                        selector = str(jinja2_env.from_string(step['selector']).render())
-
-                    getattr(interface, "call_action")(action_name=step['operation'],
-                                                      selector=selector,
-                                                      optional_value=optional_value)
-                    self.screenshot_step(step_n)
-                    self.save_step_html(step_n)
-                except TimeoutError as e:
-                    print(str(e))
-                    # Stop processing here
-                    raise BrowserStepsStepTimout(step_n=step_n)
-
-    # It's always good to reset these
-    def delete_browser_steps_screenshots(self):
-        import glob
-        if self.browser_steps_screenshot_path is not None:
-            dest = os.path.join(self.browser_steps_screenshot_path, 'step_*.jpeg')
-            files = glob.glob(dest)
-            for f in files:
-                os.unlink(f)
-
-
-#   Maybe for the future, each fetcher provides its own diff output, could be used for text, image
-#   the current one would return javascript output (as we use JS to generate the diff)
-#
-def available_fetchers():
-    # See the if statement at the bottom of this file for how we switch between playwright and webdriver
-    import inspect
-    p = []
-    for name, obj in inspect.getmembers(sys.modules[__name__], inspect.isclass):
-        if inspect.isclass(obj):
-            # @todo html_ is maybe better as fetcher_ or something
-            # In this case, make sure to edit the default one in store.py and fetch_site_status.py
-            if name.startswith('html_'):
-                t = tuple([name, obj.fetcher_description])
-                p.append(t)
-
-    return p
-
-
-class base_html_playwright(Fetcher):
-    fetcher_description = "Playwright {}/Javascript".format(
-        os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
-    )
-    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
-        fetcher_description += " via '{}'".format(os.getenv("PLAYWRIGHT_DRIVER_URL"))
-
-    browser_type = ''
-    command_executor = ''
-
-    # Configs for Proxy setup
-    # In the ENV vars, is prefixed with "playwright_proxy_", so it is for example "playwright_proxy_server"
-    playwright_proxy_settings_mappings = ['bypass', 'server', 'username', 'password']
-
-    proxy = None
-
-    def __init__(self, proxy_override=None):
-        super().__init__()
-        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
-        self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
-        self.command_executor = os.getenv(
-            "PLAYWRIGHT_DRIVER_URL",
-            'ws://playwright-chrome:3000'
-        ).strip('"')
-
-        # If any proxy settings are enabled, then we should setup the proxy object
-        proxy_args = {}
-        for k in self.playwright_proxy_settings_mappings:
-            v = os.getenv('playwright_proxy_' + k, False)
-            if v:
-                proxy_args[k] = v.strip('"')
-
-        if proxy_args:
-            self.proxy = proxy_args
-
-        # allow per-watch proxy selection override
-        if proxy_override:
-            self.proxy = {'server': proxy_override}
-
-        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
-                self.proxy['password'] = parsed.password
-
-    def screenshot_step(self, step_n=''):
-        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=85)
-
-        if self.browser_steps_screenshot_path is not None:
-            destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.jpeg'.format(step_n))
-            logging.debug("Saving step screenshot to {}".format(destination))
-            with open(destination, 'wb') as f:
-                f.write(screenshot)
-
-    def save_step_html(self, step_n):
-        content = self.page.content()
-        destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.html'.format(step_n))
-        logging.debug("Saving step HTML to {}".format(destination))
-        with open(destination, 'w') as f:
-            f.write(content)
-
-    def run_fetch_browserless_puppeteer(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-
-        from pkg_resources import resource_string
-
-        extra_wait_ms = (int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay) * 1000
-
-        self.xpath_element_js = self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
-        code = resource_string(__name__, "res/puppeteer_fetch.js").decode('utf-8')
-        # In the future inject this is a proper JS package
-        code = code.replace('%xpath_scrape_code%', self.xpath_element_js)
-        code = code.replace('%instock_scrape_code%', self.instock_data_js)
-
-        from requests.exceptions import ConnectTimeout, ReadTimeout
-        wait_browserless_seconds = 240
-
-        browserless_function_url = os.getenv('BROWSERLESS_FUNCTION_URL')
-        from urllib.parse import urlparse
-        if not browserless_function_url:
-            # Convert/try to guess from PLAYWRIGHT_DRIVER_URL
-            o = urlparse(os.getenv('PLAYWRIGHT_DRIVER_URL'))
-            browserless_function_url = o._replace(scheme="http")._replace(path="function").geturl()
-
-
-        # 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"
-
-
-        try:
-            amp = '&' if '?' in browserless_function_url else '?'
-            response = requests.request(
-                method="POST",
-                json={
-                    "code": code,
-                    "context": {
-                        # Very primitive disk cache - USE WITH EXTREME CAUTION
-                        # Run browserless container  with -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]"
-                        'disk_cache_dir': os.getenv("PUPPETEER_DISK_CACHE", False), # or path to disk cache ending in /, ie /tmp/cache/
-                        'execute_js': self.webdriver_js_execute_code,
-                        'extra_wait_ms': extra_wait_ms,
-                        'include_filters': current_include_filters,
-                        'req_headers': request_headers,
-                        'screenshot_quality': int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)),
-                        'url': url,
-                        'user_agent': request_headers.get('User-Agent', 'Mozilla/5.0'),
-                        'proxy_username': self.proxy.get('username','') if self.proxy else False,
-                        'proxy_password': self.proxy.get('password', '') if self.proxy else False,
-                        'no_cache_list': [
-                            'twitter',
-                            '.pdf'
-                        ],
-                        # Could use https://github.com/easylist/easylist here, or install a plugin
-                        'block_url_list': [
-                            'adnxs.com',
-                            'analytics.twitter.com',
-                            'doubleclick.net',
-                            'google-analytics.com',
-                            'googletagmanager',
-                            'trustpilot.com'
-                        ]
-                    }
-                },
-                # @todo /function needs adding ws:// to http:// rebuild this
-                url=browserless_function_url+f"{amp}--disable-features=AudioServiceOutOfProcess&dumpio=true&--disable-remote-fonts",
-                timeout=wait_browserless_seconds)
-
-        except ReadTimeout:
-            raise PageUnloadable(url=url, status_code=None, message=f"No response from browserless in {wait_browserless_seconds}s")
-        except ConnectTimeout:
-            raise PageUnloadable(url=url, status_code=None, message=f"Timed out connecting to browserless, retrying..")
-        else:
-            # 200 Here means that the communication to browserless worked only, not the page state
-            if response.status_code == 200:
-                import base64
-
-                x = response.json()
-                if not x.get('screenshot'):
-                    # https://github.com/puppeteer/puppeteer/blob/v1.0.0/docs/troubleshooting.md#tips
-                    # https://github.com/puppeteer/puppeteer/issues/1834
-                    # https://github.com/puppeteer/puppeteer/issues/1834#issuecomment-381047051
-                    # Check your memory is shared and big enough
-                    raise ScreenshotUnavailable(url=url, status_code=None)
-
-                if not x.get('content', '').strip():
-                    raise EmptyReply(url=url, status_code=None)
-
-                if x.get('status_code', 200) != 200 and not ignore_status_codes:
-                    raise Non200ErrorCodeReceived(url=url, status_code=x.get('status_code', 200), page_html=x['content'])
-
-                self.content = x.get('content')
-                self.headers = x.get('headers')
-                self.instock_data = x.get('instock_data')
-                self.screenshot = base64.b64decode(x.get('screenshot'))
-                self.status_code = x.get('status_code')
-                self.xpath_data = x.get('xpath_data')
-
-            else:
-                # Some other error from browserless
-                raise PageUnloadable(url=url, status_code=None, message=response.content.decode('utf-8'))
-
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-
-        # For now, USE_EXPERIMENTAL_PUPPETEER_FETCH is not supported by watches with BrowserSteps (for now!)
-        has_browser_steps = self.browser_steps and list(filter(
-                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'):
-                # Temporary backup solution until we rewrite the playwright code
-                return self.run_fetch_browserless_puppeteer(
-                    url,
-                    timeout,
-                    request_headers,
-                    request_body,
-                    request_method,
-                    ignore_status_codes,
-                    current_include_filters,
-                    is_binary)
-
-        from playwright.sync_api import sync_playwright
-        import playwright._impl._api_types
-
-        self.delete_browser_steps_screenshots()
-        response = None
-        with sync_playwright() as p:
-            browser_type = getattr(p, self.browser_type)
-
-            # Seemed to cause a connection Exception even tho I can see it connect
-            # self.browser = browser_type.connect(self.command_executor, timeout=timeout*1000)
-            # 60,000 connection timeout only
-            browser = browser_type.connect_over_cdp(self.command_executor, timeout=60000)
-
-            # 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(
-                user_agent=request_headers.get('User-Agent', 'Mozilla/5.0'),
-                proxy=self.proxy,
-                # This is needed to enable JavaScript execution on GitHub and others
-                bypass_csp=True,
-                # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
-                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
-                # Should never be needed
-                accept_downloads=False
-            )
-
-            self.page = context.new_page()
-            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}"))
-
-            # 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')
-
-            except Exception as e:
-                print("Content Fetcher > Other exception when page.goto", str(e))
-                context.close()
-                browser.close()
-                raise PageUnloadable(url=url, status_code=None, message=str(e))
-
-            # 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)
-
-            except playwright._impl._api_types.TimeoutError as e:
-                context.close()
-                browser.close()
-                # This can be ok, we will try to grab what we could retrieve
-                pass
-            except Exception as e:
-                print("Content Fetcher > Other exception when executing custom JS code", str(e))
-                context.close()
-                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.content = self.page.content()
-            self.status_code = response.status
-            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()
-
-            # 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:
-                self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
-            else:
-                self.page.evaluate("var include_filters=''")
-
-            self.xpath_data = self.page.evaluate(
-                "async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
-            self.instock_data = self.page.evaluate("async () => {" + self.instock_data_js + "}")
-
-            # 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
-
-            # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
-            # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
-            # acceptable screenshot quality here
-            try:
-                # The actual screenshot
-                self.screenshot = self.page.screenshot(type='jpeg', full_page=True,
-                                                       quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
-            except Exception as e:
-                context.close()
-                browser.close()
-                raise ScreenshotUnavailable(url=url, status_code=None)
-
-            context.close()
-            browser.close()
-
-
-class base_html_webdriver(Fetcher):
-    if os.getenv("WEBDRIVER_URL"):
-        fetcher_description = "WebDriver Chrome/Javascript via '{}'".format(os.getenv("WEBDRIVER_URL"))
-    else:
-        fetcher_description = "WebDriver Chrome/Javascript"
-
-    command_executor = ''
-
-    # Configs for Proxy setup
-    # In the ENV vars, is prefixed with "webdriver_", so it is for example "webdriver_sslProxy"
-    selenium_proxy_settings_mappings = ['proxyType', 'ftpProxy', 'httpProxy', 'noProxy',
-                                        'proxyAutoconfigUrl', 'sslProxy', 'autodetect',
-                                        'socksProxy', 'socksVersion', 'socksUsername', 'socksPassword']
-    proxy = None
-
-    def __init__(self, proxy_override=None):
-        super().__init__()
-        from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
-
-        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
-        self.command_executor = os.getenv("WEBDRIVER_URL", 'http://browser-chrome:4444/wd/hub').strip('"')
-
-        # If any proxy settings are enabled, then we should setup the proxy object
-        proxy_args = {}
-        for k in self.selenium_proxy_settings_mappings:
-            v = os.getenv('webdriver_' + k, False)
-            if v:
-                proxy_args[k] = v.strip('"')
-
-        # Map back standard HTTP_ and HTTPS_PROXY to webDriver httpProxy/sslProxy
-        if not proxy_args.get('webdriver_httpProxy') and self.system_http_proxy:
-            proxy_args['httpProxy'] = self.system_http_proxy
-        if not proxy_args.get('webdriver_sslProxy') and self.system_https_proxy:
-            proxy_args['httpsProxy'] = self.system_https_proxy
-
-        # Allows override the proxy on a per-request basis
-        if proxy_override is not None:
-            proxy_args['httpProxy'] = proxy_override
-
-        if proxy_args:
-            self.proxy = SeleniumProxy(raw=proxy_args)
-
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-
-        from selenium import webdriver
-        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
-        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
-        self.driver = webdriver.Remote(
-            command_executor=self.command_executor,
-            desired_capabilities=DesiredCapabilities.CHROME,
-            proxy=self.proxy)
-
-        try:
-            self.driver.get(url)
-        except WebDriverException as e:
-            # Be sure we close the session window
-            self.quit()
-            raise
-
-        self.driver.set_window_size(1280, 1024)
-        self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
-
-        if self.webdriver_js_execute_code is not None:
-            self.driver.execute_script(self.webdriver_js_execute_code)
-            # Selenium doesn't automatically wait for actions as good as Playwright, so wait again
-            self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
-
-        # @todo - how to check this? is it possible?
-        self.status_code = 200
-        # @todo somehow we should try to get this working for WebDriver
-        # raise EmptyReply(url=url, status_code=r.status_code)
-
-        # @todo - dom wait loaded?
-        time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay)
-        self.content = self.driver.page_source
-        self.headers = {}
-
-        self.screenshot = self.driver.get_screenshot_as_png()
-
-    # 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
-
-        self.driver = webdriver.Remote(
-            command_executor=self.command_executor,
-            desired_capabilities=DesiredCapabilities.CHROME)
-
-        # driver.quit() seems to cause better exceptions
-        self.quit()
-        return True
-
-    def quit(self):
-        if self.driver:
-            try:
-                self.driver.quit()
-            except Exception as e:
-                print("Content Fetcher > Exception in chrome shutdown/quit" + str(e))
-
-
-# "html_requests" is listed as the default fetcher in store.py!
-class html_requests(Fetcher):
-    fetcher_description = "Basic fast Plaintext/HTTP Client"
-
-    def __init__(self, proxy_override=None):
-        self.proxy_override = proxy_override
-
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-
-        # Make requests use a more modern looking user-agent
-        if not 'User-Agent' in request_headers:
-            request_headers['User-Agent'] = os.getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT",
-                                                      'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36')
-
-        proxies = {}
-
-        # Allows override the proxy on a per-request basis
-        if self.proxy_override:
-            proxies = {'http': self.proxy_override, 'https': self.proxy_override, 'ftp': self.proxy_override}
-        else:
-            if self.system_http_proxy:
-                proxies['http'] = self.system_http_proxy
-            if self.system_https_proxy:
-                proxies['https'] = self.system_https_proxy
-
-        r = requests.request(method=request_method,
-                             data=request_body,
-                             url=url,
-                             headers=request_headers,
-                             timeout=timeout,
-                             proxies=proxies,
-                             verify=False)
-
-        # If the response did not tell us what encoding format to expect, Then use chardet to override what `requests` thinks.
-        # For example - some sites don't tell us it's utf-8, but return utf-8 content
-        # This seems to not occur when using webdriver/selenium, it seems to detect the text encoding more reliably.
-        # https://github.com/psf/requests/issues/1604 good info about requests encoding detection
-        if not is_binary:
-            # Don't run this for PDF (and requests identified as binary) takes a _long_ time
-            if not r.headers.get('content-type') or not 'charset=' in r.headers.get('content-type'):
-                encoding = chardet.detect(r.content)['encoding']
-                if encoding:
-                    r.encoding = encoding
-
-        if not r.content or not len(r.content):
-            raise EmptyReply(url=url, status_code=r.status_code)
-
-        # @todo test this
-        # @todo maybe you really want to test zero-byte return pages?
-        if r.status_code != 200 and not ignore_status_codes:
-            # maybe check with content works?
-            raise Non200ErrorCodeReceived(url=url, status_code=r.status_code, page_html=r.text)
-
-        self.status_code = r.status_code
-        if is_binary:
-            # Binary files just return their checksum until we add something smarter
-            self.content = hashlib.md5(r.content).hexdigest()
-        else:
-            self.content = r.text
-
-        self.headers = r.headers
-        self.raw_content = r.content
-
-
-# Decide which is the 'real' HTML webdriver, this is more a system wide config
-# rather than site-specific.
-use_playwright_as_chrome_fetcher = os.getenv('PLAYWRIGHT_DRIVER_URL', False)
-if use_playwright_as_chrome_fetcher:
-    html_webdriver = base_html_playwright
-else:
-    html_webdriver = base_html_webdriver

changedetectionio/fetchers/__init__.py

@@ -0,0 +1,150 @@
+from abc import abstractmethod
+import os
+from . import exceptions
+
+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'
+
+
+class Fetcher():
+    browser_steps = None
+    browser_steps_screenshot_path = None
+    content = None
+    error = None
+    fetcher_description = "No description"
+    headers = None
+    status_code = None
+    webdriver_js_execute_code = None
+    xpath_data = None
+    xpath_element_js = ""
+    instock_data = None
+    instock_data_js = ""
+
+    # Will be needed in the future by the VisualSelector, always get this where possible.
+    screenshot = False
+    system_http_proxy = os.getenv('HTTP_PROXY')
+    system_https_proxy = os.getenv('HTTPS_PROXY')
+
+    # Time ONTOP of the system defined env minimum time
+    render_extract_delay = 0
+
+    def __init__(self):
+        from pkg_resources import resource_string
+        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
+        self.xpath_element_js = resource_string(__name__, "../res/xpath_element_scraper.js").decode('utf-8')
+        self.instock_data_js = resource_string(__name__, "../res/stock-not-in-stock.js").decode('utf-8')
+
+
+    @abstractmethod
+    def get_error(self):
+        return self.error
+
+    @abstractmethod
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None,
+            is_binary=False):
+        # Should set self.error, self.status_code and self.content
+        pass
+
+    @abstractmethod
+    def quit(self):
+        return
+
+    @abstractmethod
+    def get_last_status_code(self):
+        return self.status_code
+
+    @abstractmethod
+    def screenshot_step(self, step_n):
+        return None
+
+    @abstractmethod
+    # Return true/false if this checker is ready to run, in the case it needs todo some special config check etc
+    def is_ready(self):
+        return True
+
+    def iterate_browser_steps(self):
+        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+        from playwright._impl._api_types import TimeoutError
+        from jinja2 import Environment
+        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
+
+        step_n = 0
+
+        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)
+
+            for step in valid_steps:
+                step_n += 1
+                print(">> Iterating check - browser Step n {} - {}...".format(step_n, step['operation']))
+                self.screenshot_step("before-"+str(step_n))
+                self.save_step_html("before-"+str(step_n))
+                try:
+                    optional_value = step['optional_value']
+                    selector = step['selector']
+                    # Support for jinja2 template in step values, with date module added
+                    if '{%' in step['optional_value'] or '{{' in step['optional_value']:
+                        optional_value = str(jinja2_env.from_string(step['optional_value']).render())
+                    if '{%' in step['selector'] or '{{' in step['selector']:
+                        selector = str(jinja2_env.from_string(step['selector']).render())
+
+                    getattr(interface, "call_action")(action_name=step['operation'],
+                                                      selector=selector,
+                                                      optional_value=optional_value)
+                    self.screenshot_step(step_n)
+                    self.save_step_html(step_n)
+                except TimeoutError:
+                    # Stop processing here
+                    raise exceptions.BrowserStepsStepTimout(step_n=step_n)
+
+
+
+    # It's always good to reset these
+    def delete_browser_steps_screenshots(self):
+        import glob
+        if self.browser_steps_screenshot_path is not None:
+            dest = os.path.join(self.browser_steps_screenshot_path, 'step_*.jpeg')
+            files = glob.glob(dest)
+            for f in files:
+                os.unlink(f)
+
+#   Maybe for the future, each fetcher provides its own diff output, could be used for text, image
+#   the current one would return javascript output (as we use JS to generate the diff)
+#
+
+
+def available_fetchers():
+    from . import playwright, html_requests, webdriver
+
+    p = []
+    p.append(tuple(['html_requests', html_requests.fetcher.fetcher_description]))
+
+    # Prefer playwright
+    if os.getenv('PLAYWRIGHT_DRIVER_URL', False):
+        p.append(tuple(['html_webdriver', playwright.fetcher.fetcher_description]))
+
+    elif os.getenv('WEBDRIVER_URL'):
+        p.append(tuple(['html_webdriver', webdriver.fetcher.fetcher_description]))
+
+
+    return p
+
+html_webdriver = None
+# Decide which is the 'real' HTML webdriver, this is more a system wide config rather than site-specific.
+use_playwright_as_chrome_fetcher = os.getenv('PLAYWRIGHT_DRIVER_URL', False)
+if use_playwright_as_chrome_fetcher:
+    from . import playwright
+    html_webdriver = getattr(playwright, "fetcher")
+
+else:
+    from . import webdriver
+    html_webdriver = getattr(webdriver, "fetcher")
+

changedetectionio/fetchers/browserless.py

@@ -0,0 +1,71 @@
+from . import Fetcher
+import os
+import requests
+
+
+# Exploit the debugging API to get screenshot and HTML without needing playwright
+# https://www.browserless.io/docs/scrape#debugging
+
+class fetcher(Fetcher):
+    fetcher_description = "Browserless Chrome/Javascript via '{}'".format(os.getenv("BROWSERLESS_DRIVER_URL"))
+
+    command_executor = ''
+    proxy = None
+
+    def __init__(self, proxy_override=None, command_executor=None):
+        super().__init__()
+        self.proxy = proxy_override
+
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None,
+            is_binary=False):
+
+        proxy = ""
+        if self.proxy:
+            proxy = f"--proxy-server={self.proxy}"
+
+        import json
+        r = requests.request(method='POST',
+                             data=json.dumps({
+                                 "url": f"{url}?{proxy}",
+                                 "elements": [],
+                                 "debug": {
+                                     "screenshot": True,
+                                     "console": False,
+                                     "network": True,
+                                     "cookies": False,
+                                     "html": True
+                                 }
+                             }),
+                             url=os.getenv("BROWSERLESS_DRIVER_URL"),
+                             headers={'Content-Type': 'application/json'},
+                             timeout=timeout,
+                             verify=False)
+
+        # "waitFor": "() => document.querySelector('h1')"
+        #        extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+        #        self.page.wait_for_timeout(extra_wait * 1000)
+
+        if r.status_code == 200:
+            # the basic request to browserless was OK, but how was the internal request to the site?
+            result = r.json()
+
+            if result['debug']['network'].get('inbound') and len(result['debug']['network']['inbound']):
+                self.status_code = result['debug']['network']['inbound'][000]['status']
+
+            self.content = result['debug']['html']
+
+            self.headers = {}
+            if result['debug'].get('screenshot'):
+                import base64
+                self.screenshot = base64.b64decode(result['debug']['screenshot'])
+
+    def is_ready(self):
+        # Try ping?
+        return os.getenv("BROWSERLESS_DRIVER_URL", False)

changedetectionio/fetchers/exceptions.py

@@ -0,0 +1,66 @@
+class Non200ErrorCodeReceived(Exception):
+    def __init__(self, status_code, url, screenshot=None, xpath_data=None, page_html=None):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        self.xpath_data = xpath_data
+        self.page_text = None
+
+        if page_html:
+            from changedetectionio import html_tools
+            self.page_text = html_tools.html_to_text(page_html)
+        return
+
+class checksumFromPreviousCheckWasTheSame(Exception):
+    def __init__(self):
+        return
+
+class JSActionExceptions(Exception):
+    def __init__(self, status_code, url, screenshot, message=''):
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        self.message = message
+        return
+
+class BrowserStepsStepTimout(Exception):
+    def __init__(self, step_n):
+        self.step_n = step_n
+        return
+
+
+class PageUnloadable(Exception):
+    def __init__(self, status_code, url, message, screenshot=False):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        self.message = message
+        return
+
+class EmptyReply(Exception):
+    def __init__(self, status_code, url, screenshot=None):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        return
+
+class ScreenshotUnavailable(Exception):
+    def __init__(self, status_code, url, page_html=None):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        if page_html:
+            from ..html_tools import html_to_text
+            self.page_text = html_to_text(page_html)
+        return
+
+class ReplyWithContentButNoText(Exception):
+    def __init__(self, status_code, url, screenshot=None):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        return

changedetectionio/fetchers/html_requests.py

@@ -0,0 +1,80 @@
+from . import Fetcher
+from . import exceptions
+
+
+# "html_requests" is listed as the default fetcher in store.py!
+class fetcher(Fetcher):
+    fetcher_description = "Basic fast Plaintext/HTTP Client"
+
+
+    def __init__(self, proxy_override=None):
+        self.proxy_override = proxy_override
+
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None,
+            is_binary=False):
+
+        import chardet
+        import hashlib
+        import os
+        import requests
+
+        # Make requests use a more modern looking user-agent
+        if not 'User-Agent' in request_headers:
+            request_headers['User-Agent'] = os.getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT",
+                                                      'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36')
+
+        proxies = {}
+
+        # Allows override the proxy on a per-request basis
+        if self.proxy_override:
+            proxies = {'http': self.proxy_override, 'https': self.proxy_override, 'ftp': self.proxy_override}
+        else:
+            if self.system_http_proxy:
+                proxies['http'] = self.system_http_proxy
+            if self.system_https_proxy:
+                proxies['https'] = self.system_https_proxy
+
+        r = requests.request(method=request_method,
+                             data=request_body,
+                             url=url,
+                             headers=request_headers,
+                             timeout=timeout,
+                             proxies=proxies,
+                             verify=False)
+
+        # If the response did not tell us what encoding format to expect, Then use chardet to override what `requests` thinks.
+        # For example - some sites don't tell us it's utf-8, but return utf-8 content
+        # This seems to not occur when using webdriver/selenium, it seems to detect the text encoding more reliably.
+        # https://github.com/psf/requests/issues/1604 good info about requests encoding detection
+        if not is_binary:
+            # Don't run this for PDF (and requests identified as binary) takes a _long_ time
+            if not r.headers.get('content-type') or not 'charset=' in r.headers.get('content-type'):
+                encoding = chardet.detect(r.content)['encoding']
+                if encoding:
+                    r.encoding = encoding
+
+        if not r.content or not len(r.content):
+            raise exceptions.EmptyReply(url=url, status_code=r.status_code)
+
+        # @todo test this
+        # @todo maybe you really want to test zero-byte return pages?
+        if r.status_code != 200 and not ignore_status_codes:
+            # maybe check with content works?
+            raise exceptions.Non200ErrorCodeReceived(url=url, status_code=r.status_code, page_html=r.text)
+
+        self.status_code = r.status_code
+        if is_binary:
+            # Binary files just return their checksum until we add something smarter
+            self.content = hashlib.md5(r.content).hexdigest()
+        else:
+            self.content = r.text
+
+        self.headers = r.headers
+        self.raw_content = r.content

changedetectionio/fetchers/playwright.py

@@ -0,0 +1,208 @@
+from . import Fetcher
+from . import exceptions
+from . import visualselector_xpath_selectors
+
+import os
+import logging
+import time
+
+class fetcher(Fetcher):
+    fetcher_description = "Playwright {}/Javascript".format(
+        os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
+    )
+    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
+        fetcher_description += " via '{}'".format(os.getenv("PLAYWRIGHT_DRIVER_URL"))
+
+    browser_type = ''
+    command_executor = ''
+
+    # Configs for Proxy setup
+    # In the ENV vars, is prefixed with "playwright_proxy_", so it is for example "playwright_proxy_server"
+    playwright_proxy_settings_mappings = ['bypass', 'server', 'username', 'password']
+
+    proxy = None
+
+    def __init__(self, proxy_override=None):
+        super().__init__()
+        import json
+
+        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+        self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
+        self.command_executor = os.getenv(
+            "PLAYWRIGHT_DRIVER_URL",
+            'ws://playwright-chrome:3000'
+        ).strip('"')
+
+        # If any proxy settings are enabled, then we should setup the proxy object
+        proxy_args = {}
+        for k in self.playwright_proxy_settings_mappings:
+            v = os.getenv('playwright_proxy_' + k, False)
+            if v:
+                proxy_args[k] = v.strip('"')
+
+        if proxy_args:
+            self.proxy = proxy_args
+
+        # allow per-watch proxy selection override
+        if proxy_override:
+            self.proxy = {'server': proxy_override}
+
+        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
+                self.proxy['password'] = parsed.password
+
+    def screenshot_step(self, step_n=''):
+        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=85)
+
+        if self.browser_steps_screenshot_path is not None:
+            destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.jpeg'.format(step_n))
+            logging.debug("Saving step screenshot to {}".format(destination))
+            with open(destination, 'wb') as f:
+                f.write(screenshot)
+
+    def save_step_html(self, step_n):
+        content = self.page.content()
+        destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.html'.format(step_n))
+        logging.debug("Saving step HTML to {}".format(destination))
+        with open(destination, 'w') as f:
+            f.write(content)
+
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None,
+            is_binary=False):
+
+        from playwright.sync_api import sync_playwright
+        import playwright._impl._api_types
+        import json
+
+        self.delete_browser_steps_screenshots()
+        response = None
+        with sync_playwright() as p:
+            browser_type = getattr(p, self.browser_type)
+
+            # Seemed to cause a connection Exception even tho I can see it connect
+            # self.browser = browser_type.connect(self.command_executor, timeout=timeout*1000)
+            # 60,000 connection timeout only
+            browser = browser_type.connect_over_cdp(self.command_executor, timeout=60000)
+
+            # 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(
+                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
+                proxy=self.proxy,
+                # This is needed to enable JavaScript execution on GitHub and others
+                bypass_csp=True,
+                # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
+                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
+                # Should never be needed
+                accept_downloads=False
+            )
+
+            self.page = context.new_page()
+            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}"))
+
+            # 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')
+
+            except Exception as e:
+                print ("Content Fetcher > Other exception when page.goto", str(e))
+                context.close()
+                browser.close()
+                raise exceptions.PageUnloadable(url=url, status_code=None, message=str(e))
+
+            # 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)
+
+            except playwright._impl._api_types.TimeoutError as e:
+                context.close()
+                browser.close()
+                # This can be ok, we will try to grab what we could retrieve
+                pass
+            except Exception as e:
+                print ("Content Fetcher > Other exception when executing custom JS code", str(e))
+                context.close()
+                browser.close()
+                raise exceptions.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 exceptions.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.content = self.page.content()
+            self.status_code = response.status
+            if len(self.page.content().strip()) == 0:
+                context.close()
+                browser.close()
+                print ("Content Fetcher > Content was empty")
+                raise exceptions.EmptyReply(url=url, status_code=response.status)
+
+            self.status_code = response.status
+            self.headers = response.all_headers()
+
+            # 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:
+                self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
+            else:
+                self.page.evaluate("var include_filters=''")
+
+            self.xpath_data = self.page.evaluate("async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
+            self.instock_data = self.page.evaluate("async () => {" + self.instock_data_js + "}")
+
+            # 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
+
+            # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
+            # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
+            # acceptable screenshot quality here
+            try:
+                # The actual screenshot
+                self.screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+            except Exception as e:
+                context.close()
+                browser.close()
+                raise exceptions.ScreenshotUnavailable(url=url, status_code=None)
+
+            context.close()
+            browser.close()

changedetectionio/fetchers/webdriver.py

@@ -0,0 +1,103 @@
+from . import Fetcher
+import os
+import time
+
+class fetcher(Fetcher):
+    if os.getenv("WEBDRIVER_URL"):
+        fetcher_description = "WebDriver Chrome/Javascript via '{}'".format(os.getenv("WEBDRIVER_URL"))
+    else:
+        fetcher_description = "WebDriver Chrome/Javascript"
+
+    command_executor = ''
+
+    # Configs for Proxy setup
+    # In the ENV vars, is prefixed with "webdriver_", so it is for example "webdriver_sslProxy"
+    selenium_proxy_settings_mappings = ['proxyType', 'ftpProxy', 'httpProxy', 'noProxy',
+                                        'proxyAutoconfigUrl', 'sslProxy', 'autodetect',
+                                        'socksProxy', 'socksVersion', 'socksUsername', 'socksPassword']
+    proxy = None
+
+    def __init__(self, proxy_override=None, command_executor=None):
+        super().__init__()
+        from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
+
+        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+        if command_executor:
+            self.command_executor = command_executor
+        else:
+            self.command_executor = os.getenv("WEBDRIVER_URL", 'http://browser-chrome:4444/wd/hub').strip('"')
+
+        # If any proxy settings are enabled, then we should setup the proxy object
+        proxy_args = {}
+        for k in self.selenium_proxy_settings_mappings:
+            v = os.getenv('webdriver_' + k, False)
+            if v:
+                proxy_args[k] = v.strip('"')
+
+        # Map back standard HTTP_ and HTTPS_PROXY to webDriver httpProxy/sslProxy
+        if not proxy_args.get('webdriver_httpProxy') and self.system_http_proxy:
+            proxy_args['httpProxy'] = self.system_http_proxy
+        if not proxy_args.get('webdriver_sslProxy') and self.system_https_proxy:
+            proxy_args['httpsProxy'] = self.system_https_proxy
+
+        # Allows override the proxy on a per-request basis
+        if proxy_override is not None:
+            proxy_args['httpProxy'] = proxy_override
+
+        if proxy_args:
+            self.proxy = SeleniumProxy(raw=proxy_args)
+
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None,
+            is_binary=False):
+
+        from selenium import webdriver
+        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+        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
+        self.driver = webdriver.Remote(
+            command_executor=self.command_executor,
+            desired_capabilities=DesiredCapabilities.CHROME,
+            proxy=self.proxy
+        )
+
+        try:
+            self.driver.get(url)
+        except WebDriverException as e:
+            # Be sure we close the session window
+            self.quit()
+            raise
+
+        self.driver.set_window_size(1280, 1024)
+        self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+
+        if self.webdriver_js_execute_code is not None:
+            self.driver.execute_script(self.webdriver_js_execute_code)
+            # Selenium doesn't automatically wait for actions as good as Playwright, so wait again
+            self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+
+        # @todo - how to check this? is it possible?
+        self.status_code = 200
+        # @todo somehow we should try to get this working for WebDriver
+        # raise EmptyReply(url=url, status_code=r.status_code)
+
+        # @todo - dom wait loaded?
+        time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay)
+        self.content = self.driver.page_source
+        self.headers = {}
+
+        self.screenshot = self.driver.get_screenshot_as_png()
+
+    # Try something with requests?
+    def is_ready(self):
+        return True
+
+

changedetectionio/forms.py

@@ -21,7 +21,6 @@ from wtforms.validators import ValidationError
 # 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.notification import (
     valid_notification_formats,
 )
@@ -135,30 +134,31 @@ class ValidateContentFetcherIsReady(object):
 
     def __call__(self, form, field):
         import urllib3.exceptions
-        from changedetectionio import content_fetcher
+        import importlib
 
         # Better would be a radiohandler that keeps a reference to each class
         if field.data is not None and field.data != 'system':
-            klass = getattr(content_fetcher, field.data)
-            some_object = klass()
-            try:
-                ready = some_object.is_ready()
+            from . import fetchers
+            if fetchers.html_webdriver is not None:
+                try:
+                    driver = fetchers.html_webdriver()
+                    driver.is_ready()
 
-            except urllib3.exceptions.MaxRetryError as e:
-                driver_url = some_object.command_executor
-                message = field.gettext('Content fetcher \'%s\' did not respond.' % (field.data))
-                message += '<br>' + field.gettext(
-                    'Be sure that the selenium/webdriver runner is running and accessible via network from this container/host.')
-                message += '<br>' + field.gettext('Did you follow the instructions in the wiki?')
-                message += '<br><br>' + field.gettext('WebDriver Host: %s' % (driver_url))
-                message += '<br><a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">Go here for more information</a>'
-                message += '<br>'+field.gettext('Content fetcher did not respond properly, unable to use it.\n %s' % (str(e)))
+                except urllib3.exceptions.MaxRetryError as e:
+                    driver_url = fetchers.html_webdriver.command_executor
+                    message = field.gettext('Content fetcher \'%s\' did not respond.' % (field.data))
+                    message += '<br>' + field.gettext(
+                        'Be sure that the selenium/webdriver runner is running and accessible via network from this container/host.')
+                    message += '<br>' + field.gettext('Did you follow the instructions in the wiki?')
+                    message += '<br><br>' + field.gettext('WebDriver Host: %s' % (driver_url))
+                    message += '<br><a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">Go here for more information</a>'
+                    message += '<br>'+field.gettext('Content fetcher did not respond properly, unable to use it.\n %s' % (str(e)))
 
-                raise ValidationError(message)
+                    raise ValidationError(message)
 
-            except Exception as e:
-                message = field.gettext('Content fetcher \'%s\' did not respond properly, unable to use it.\n %s')
-                raise ValidationError(message % (field.data, e))
+                except Exception as e:
+                    message = field.gettext('Content fetcher \'%s\' did not respond properly, unable to use it.\n %s')
+                    raise ValidationError(message % (field.data, e))
 
 
 class ValidateNotificationBodyAndTitleWhenURLisSet(object):
@@ -355,11 +355,12 @@ class quickWatchForm(Form):
 
 # Common to a single watch and the global settings
 class commonSettingsForm(Form):
+    from .fetchers import available_fetchers
     notification_urls = StringListField('Notification URL List', validators=[validators.Optional(), ValidateAppRiseServers()])
     notification_title = StringField('Notification Title', default='ChangeDetection.io Notification - {{ watch_url }}', validators=[validators.Optional(), ValidateJinja2Template()])
     notification_body = TextAreaField('Notification Body', default='{{ watch_url }} had a change.', validators=[validators.Optional(), ValidateJinja2Template()])
     notification_format = SelectField('Notification format', choices=valid_notification_formats.keys())
-    fetch_backend = RadioField(u'Fetch Method', choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    fetch_backend = RadioField(u'Fetch Method', choices=available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     extract_title_as_title = BooleanField('Extract <title> from document and use as watch title', default=False)
     webdriver_delay = IntegerField('Wait seconds before extracting text', validators=[validators.Optional(), validators.NumberRange(min=1,
                                                                                                                                     message="Should contain one or more seconds")])
@@ -472,19 +473,15 @@ class globalSettingsRequestForm(Form):
 
 # datastore.data['settings']['application']..
 class globalSettingsApplicationForm(commonSettingsForm):
-
+    from .fetchers import available_fetchers
     api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
     base_url = StringField('Base URL', validators=[validators.Optional()])
     empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
-    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
     global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
     ignore_whitespace = BooleanField('Ignore whitespace')
     password = SaltyPasswordField()
-    pager_size = IntegerField('Pager size',
-                              render_kw={"style": "width: 5em;"},
-                              validators=[validators.NumberRange(min=0,
-                                                                 message="Should be atleast zero (disabled)")])
     removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
     render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
     shared_diff_access = BooleanField('Allow access to view diff page when password is enabled', default=False, validators=[validators.Optional()])

changedetectionio/html_tools.py

@@ -137,13 +137,12 @@ def _get_stripped_text_from_json_match(match):
 def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None):
     stripped_text_from_html = False
 
-    # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded within HTML tags
+    # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded <script type=ldjson>
     try:
         stripped_text_from_html = _parse_json(json.loads(content), json_filter)
     except json.JSONDecodeError:
 
         # Foreach <script json></script> blob.. just return the first that matches json_filter
-        # As a last resort, try to parse the whole <body>
         s = []
         soup = BeautifulSoup(content, 'html.parser')
 
@@ -151,34 +150,32 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
             bs_result = soup.findAll('script', {"type": "application/ld+json"})
         else:
             bs_result = soup.findAll('script')
-        bs_result += soup.findAll('body')
 
-        bs_jsons = []
+
+        if not bs_result:
+            raise JSONNotFound("No parsable JSON found in this document")
+
         for result in bs_result:
             # Skip empty tags, and things that dont even look like JSON
-            if not result.text or '{' not in result.text:
+            if not result.string or not '{' in result.string:
                 continue
+                
             try:
-                json_data = json.loads(result.text)
-                bs_jsons.append(json_data)
+                json_data = json.loads(result.string)
             except json.JSONDecodeError:
-                # Skip objects which cannot be parsed
+                # Just skip it
                 continue
-
-        if not bs_jsons:
-            raise JSONNotFound("No parsable JSON found in this document")
-        
-        for json_data in bs_jsons:
-            stripped_text_from_html = _parse_json(json_data, json_filter)
-            if ensure_is_ldjson_info_type:
-                # Could sometimes be list, string or something else random
-                if isinstance(json_data, dict):
-                    # If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
-                    # (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
-                    if json_data.get('@type', False) and json_data.get('@type','').lower() == ensure_is_ldjson_info_type.lower() and stripped_text_from_html:
-                        break
-            elif stripped_text_from_html:
-                break
+            else:
+                stripped_text_from_html = _parse_json(json_data, json_filter)
+                if ensure_is_ldjson_info_type:
+                    # Could sometimes be list, string or something else random
+                    if isinstance(json_data, dict):
+                        # If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
+                        # (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
+                        if json_data.get('@type', False) and json_data.get('@type','').lower() == ensure_is_ldjson_info_type.lower() and stripped_text_from_html:
+                            break
+                elif stripped_text_from_html:
+                    break
 
     if not stripped_text_from_html:
         # Re 265 - Just return an empty string when filter not found

changedetectionio/importer.py

@@ -52,8 +52,7 @@ class import_url_list(Importer):
 
             # Flask wtform validators wont work with basic auth, use validators package
             # Up to 5000 per batch so we dont flood the server
-            # @todo validators.url failed on local hostnames (such as referring to ourself when using browserless)
-            if len(url) and 'http' in url.lower() and good < 5000:
+            if len(url) and validators.url(url.replace('source:', '')) and good < 5000:
                 extras = None
                 if processor:
                     extras = {'processor': processor}

changedetectionio/model/App.py

@@ -23,26 +23,25 @@ class model(dict):
                     'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "10")),  # Number of threads, lower is better for slow connections
                 },
                 'application': {
-                    # Custom notification content
                     'api_access_token_enabled': True,
+                    'password': False,
                     'base_url' : None,
-                    'empty_pages_are_a_change': False,
                     'extract_title_as_title': False,
+                    'empty_pages_are_a_change': False,
                     'fetch_backend': getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
                     'filter_failure_notification_threshold_attempts': _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT,
                     'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
                     'global_subtractive_selectors': [],
                     'ignore_whitespace': True,
+                    'render_anchor_tag_content': False,
+                    'notification_urls': [], # Apprise URL list
+                    # Custom notification content
+                    'notification_title': default_notification_title,
                     'notification_body': default_notification_body,
                     'notification_format': default_notification_format,
-                    'notification_title': default_notification_title,
-                    'notification_urls': [], # Apprise URL list
-                    'pager_size': 50,
-                    'password': False,
-                    'render_anchor_tag_content': False,
                     'schema_version' : 0,
                     'shared_diff_access': False,
-                    'webdriver_delay': None , # Extra delay in seconds before extracting text
+                    'webdriver_delay': None  # Extra delay in seconds before extracting text
                 }
             }
         }
@@ -50,15 +49,3 @@ class model(dict):
     def __init__(self, *arg, **kw):
         super(model, self).__init__(*arg, **kw)
         self.update(self.base_config)
-
-
-def parse_headers_from_text_file(filepath):
-    headers = {}
-    with open(filepath, 'r') as f:
-        for l in f.readlines():
-            l = l.strip()
-            if not l.startswith('#') and ':' in l:
-                (k, v) = l.split(':')
-                headers[k.strip()] = v.strip()
-
-    return headers

changedetectionio/model/Watch.py

@@ -20,7 +20,6 @@ base_config = {
     'body': None,
     'check_unique_lines': False,  # On change-detected, compare against all history if its something new
     'check_count': 0,
-    'date_created': None,
     'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
     'extract_text': [],  # Extract text by regex after filters
     'extract_title_as_title': False,
@@ -473,40 +472,6 @@ class model(dict):
         # None is set
         return False
 
-    @property
-    def has_extra_headers_file(self):
-        if os.path.isfile(os.path.join(self.watch_data_dir, 'headers.txt')):
-            return True
-
-        for f in self.all_tags:
-            fname = "headers-"+re.sub(r'[\W_]', '', f).lower().strip() + ".txt"
-            filepath = os.path.join(self.__datastore_path, fname)
-            if os.path.isfile(filepath):
-                return True
-
-        return False
-
-    def get_all_headers(self):
-        from .App import parse_headers_from_text_file
-        headers = self.get('headers', {}).copy()
-        # Available headers on the disk could 'headers.txt' in the watch data dir
-        filepath = os.path.join(self.watch_data_dir, 'headers.txt')
-        try:
-            if os.path.isfile(filepath):
-                headers.update(parse_headers_from_text_file(filepath))
-        except Exception as e:
-            print(f"ERROR reading headers.txt at {filepath}", str(e))
-
-        # Or each by tag, as tagname.txt in the main datadir
-        for f in self.all_tags:
-            fname = "headers-"+re.sub(r'[\W_]', '', f).lower().strip() + ".txt"
-            filepath = os.path.join(self.__datastore_path, fname)
-            try:
-                if os.path.isfile(filepath):
-                    headers.update(parse_headers_from_text_file(filepath))
-            except Exception as e:
-                print(f"ERROR reading headers.txt at {filepath}", str(e))
-        return headers
 
     def get_last_fetched_before_filters(self):
         import brotli

changedetectionio/notification.py

@@ -89,7 +89,7 @@ def process_notification(n_object, datastore):
     n_body = jinja2_env.from_string(n_object.get('notification_body', default_notification_body)).render(**notification_parameters)
     n_title = jinja2_env.from_string(n_object.get('notification_title', default_notification_title)).render(**notification_parameters)
     n_format = valid_notification_formats.get(
-        n_object.get('notification_format', default_notification_format),
+        n_object['notification_format'],
         valid_notification_formats[default_notification_format],
     )
     

changedetectionio/processors/restock_diff.py

@@ -4,20 +4,14 @@ import os
 import re
 import urllib3
 from . import difference_detection_processor
-from changedetectionio import content_fetcher
 from copy import deepcopy
+from .. import fetchers
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 name = 'Re-stock detection for single product pages'
 description = 'Detects if the product goes back to in-stock'
 
-class UnableToExtractRestockData(Exception):
-    def __init__(self, status_code):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        return
-
 class perform_site_check(difference_detection_processor):
     screenshot = None
     xpath_data = None
@@ -67,11 +61,12 @@ class perform_site_check(difference_detection_processor):
         if not prefer_backend or prefer_backend == 'system':
             prefer_backend = self.datastore.data['settings']['application']['fetch_backend']
 
-        if hasattr(content_fetcher, prefer_backend):
-            klass = getattr(content_fetcher, prefer_backend)
+        if prefer_backend == 'html_webdriver':
+            preferred_fetcher = fetchers.html_webdriver
         else:
-            # If the klass doesnt exist, just use a default
-            klass = getattr(content_fetcher, "html_requests")
+            from ..fetchers import html_requests
+            preferred_fetcher = html_requests
+
 
         proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=uuid)
         proxy_url = None
@@ -79,7 +74,7 @@ class perform_site_check(difference_detection_processor):
             proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
             print("UUID {} Using proxy {}".format(uuid, proxy_url))
 
-        fetcher = klass(proxy_override=proxy_url)
+        fetcher = preferred_fetcher(proxy_override=proxy_url)
 
         # Configurable per-watch or global extra delay before extracting text (for webDriver types)
         system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
@@ -111,8 +106,7 @@ class perform_site_check(difference_detection_processor):
             fetched_md5 = hashlib.md5(fetcher.instock_data.encode('utf-8')).hexdigest()
             # 'Possibly in stock' comes from stock-not-in-stock.js when no string found above the fold.
             update_obj["in_stock"] = True if fetcher.instock_data == 'Possibly in stock' else False
-        else:
-            raise UnableToExtractRestockData(status_code=fetcher.status_code)
+
 
         # The main thing that all this at the moment comes down to :)
         changed_detected = False

changedetectionio/processors/text_json_diff.py

@@ -7,10 +7,11 @@ import os
 import re
 import urllib3
 
-from changedetectionio import content_fetcher, html_tools
+from changedetectionio import 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 .. import fetchers
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
@@ -70,9 +71,10 @@ class perform_site_check(difference_detection_processor):
         # Unset any existing notification error
         update_obj = {'last_notification_error': False, 'last_error': False}
 
+        extra_headers = watch.get('headers', [])
+
         # Tweak the base config with the per-watch ones
-        extra_headers = watch.get_all_headers()
-        request_headers = self.datastore.get_all_headers()
+        request_headers = deepcopy(self.datastore.data['settings']['headers'])
         request_headers.update(extra_headers)
 
         # https://github.com/psf/requests/issues/4525
@@ -100,11 +102,12 @@ class perform_site_check(difference_detection_processor):
         if not prefer_backend or prefer_backend == 'system':
             prefer_backend = self.datastore.data['settings']['application']['fetch_backend']
 
-        if hasattr(content_fetcher, prefer_backend):
-            klass = getattr(content_fetcher, prefer_backend)
+        if prefer_backend == 'html_webdriver':
+            preferred_fetcher = fetchers.html_webdriver
         else:
-            # If the klass doesnt exist, just use a default
-            klass = getattr(content_fetcher, "html_requests")
+            from ..fetchers import html_requests
+            preferred_fetcher = html_requests
+
 
         proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=uuid)
         proxy_url = None
@@ -112,7 +115,7 @@ class perform_site_check(difference_detection_processor):
             proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
             print("UUID {} Using proxy {}".format(uuid, proxy_url))
 
-        fetcher = klass(proxy_override=proxy_url)
+        fetcher = preferred_fetcher(proxy_override=proxy_url)
 
         # Configurable per-watch or global extra delay before extracting text (for webDriver types)
         system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
@@ -139,14 +142,14 @@ class perform_site_check(difference_detection_processor):
         self.xpath_data = fetcher.xpath_data
 
         # Track the content type
-        update_obj['content_type'] = fetcher.get_all_headers().get('content-type', '').lower()
+        update_obj['content_type'] = fetcher.headers.get('Content-Type', '')
 
         # Watches added automatically in the queue manager will skip if its the same checksum as the previous run
         # Saves a lot of CPU
         update_obj['previous_md5_before_filters'] = hashlib.md5(fetcher.content.encode('utf-8')).hexdigest()
         if skip_when_checksum_same:
             if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
-                raise content_fetcher.checksumFromPreviousCheckWasTheSame()
+                raise fetchers.exceptions.checksumFromPreviousCheckWasTheSame()
 
 
         # Fetching complete, now filters
@@ -159,7 +162,7 @@ class perform_site_check(difference_detection_processor):
         # https://stackoverflow.com/questions/41817578/basic-method-chaining ?
         # return content().textfilter().jsonextract().checksumcompare() ?
 
-        is_json = 'application/json' in fetcher.get_all_headers().get('content-type', '').lower()
+        is_json = 'application/json' in fetcher.headers.get('Content-Type', '')
         is_html = not is_json
 
         # source: support, basically treat it as plaintext
@@ -167,7 +170,7 @@ class perform_site_check(difference_detection_processor):
             is_html = False
             is_json = False
 
-        if watch.is_pdf or 'application/pdf' in fetcher.get_all_headers().get('content-type', '').lower():
+        if watch.is_pdf or 'application/pdf' in fetcher.headers.get('Content-Type', '').lower():
             from shutil import which
             tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
             if not which(tool):
@@ -235,7 +238,7 @@ class perform_site_check(difference_detection_processor):
             html_content = fetcher.content
 
             # If not JSON,  and if it's not text/plain..
-            if 'text/plain' in fetcher.get_all_headers().get('content-type', '').lower():
+            if 'text/plain' in fetcher.headers.get('Content-Type', '').lower():
                 # Don't run get_text or xpath/css filters on plaintext
                 stripped_text_from_html = html_content
             else:
@@ -309,7 +312,7 @@ class perform_site_check(difference_detection_processor):
         # Treat pages with no renderable text content as a change? No by default
         empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
         if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
-            raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot)
+            raise fetchers.exceptions.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot)
 
         # We rely on the actual text in the html output.. many sites have random script vars etc,
         # in the future we'll implement other mechanisms.

changedetectionio/res/puppeteer_fetch.js

@@ -1,183 +0,0 @@
-module.exports = async ({page, context}) => {
-
-    var {
-        url,
-        execute_js,
-        user_agent,
-        extra_wait_ms,
-        req_headers,
-        include_filters,
-        xpath_element_js,
-        screenshot_quality,
-        proxy_username,
-        proxy_password,
-        disk_cache_dir,
-        no_cache_list,
-        block_url_list,
-    } = context;
-
-    await page.setBypassCSP(true)
-    await page.setExtraHTTPHeaders(req_headers);
-    await page.setUserAgent(user_agent);
-    // https://ourcodeworld.com/articles/read/1106/how-to-solve-puppeteer-timeouterror-navigation-timeout-of-30000-ms-exceeded
-
-    await page.setDefaultNavigationTimeout(0);
-
-    if (proxy_username) {
-        await page.authenticate({
-            username: proxy_username,
-            password: proxy_password
-        });
-    }
-
-    await page.setViewport({
-        width: 1024,
-        height: 768,
-        deviceScaleFactor: 1,
-    });
-
-    await page.setRequestInterception(true);
-    if (disk_cache_dir) {
-        console.log(">>>>>>>>>>>>>>> LOCAL DISK CACHE ENABLED <<<<<<<<<<<<<<<<<<<<<");
-    }
-    const fs = require('fs');
-    const crypto = require('crypto');
-
-    function file_is_expired(file_path) {
-        if (!fs.existsSync(file_path)) {
-            return true;
-        }
-        var stats = fs.statSync(file_path);
-        const now_date = new Date();
-        const expire_seconds = 300;
-        if ((now_date / 1000) - (stats.mtime.getTime() / 1000) > expire_seconds) {
-            console.log("CACHE EXPIRED: " + file_path);
-            return true;
-        }
-        return false;
-
-    }
-
-    page.on('request', async (request) => {
-        // General blocking of requests that waste traffic
-        if (block_url_list.some(substring => request.url().toLowerCase().includes(substring))) return request.abort();
-
-        if (disk_cache_dir) {
-            const url = request.url();
-            const key = crypto.createHash('md5').update(url).digest("hex");
-            const dir_path = disk_cache_dir + key.slice(0, 1) + '/' + key.slice(1, 2) + '/' + key.slice(2, 3) + '/';
-
-            // https://stackoverflow.com/questions/4482686/check-synchronously-if-file-directory-exists-in-node-js
-
-            if (fs.existsSync(dir_path + key)) {
-                console.log("* CACHE HIT , using - " + dir_path + key + " - " + url);
-                const cached_data = fs.readFileSync(dir_path + key);
-                // @todo headers can come from dir_path+key+".meta" json file
-                request.respond({
-                    status: 200,
-                    //contentType: 'text/html', //@todo
-                    body: cached_data
-                });
-                return;
-            }
-        }
-        request.continue();
-    });
-
-
-    if (disk_cache_dir) {
-        page.on('response', async (response) => {
-            const url = response.url();
-            // Basic filtering for sane responses
-            if (response.request().method() != 'GET' || response.request().resourceType() == 'xhr' || response.request().resourceType() == 'document' || response.status() != 200) {
-                console.log("Skipping (not useful) - Status:" + response.status() + " Method:" + response.request().method() + " ResourceType:" + response.request().resourceType() + " " + url);
-                return;
-            }
-            if (no_cache_list.some(substring => url.toLowerCase().includes(substring))) {
-                console.log("Skipping (no_cache_list) - " + url);
-                return;
-            }
-            if (url.toLowerCase().includes('data:')) {
-                console.log("Skipping (embedded-data) - " + url);
-                return;
-            }
-            response.buffer().then(buffer => {
-                if (buffer.length > 100) {
-                    console.log("Cache - Saving " + response.request().method() + " - " + url + " - " + response.request().resourceType());
-
-                    const key = crypto.createHash('md5').update(url).digest("hex");
-                    const dir_path = disk_cache_dir + key.slice(0, 1) + '/' + key.slice(1, 2) + '/' + key.slice(2, 3) + '/';
-
-                    if (!fs.existsSync(dir_path)) {
-                        fs.mkdirSync(dir_path, {recursive: true})
-                    }
-
-                    if (fs.existsSync(dir_path + key)) {
-                        if (file_is_expired(dir_path + key)) {
-                            fs.writeFileSync(dir_path + key, buffer);
-                        }
-                    } else {
-                        fs.writeFileSync(dir_path + key, buffer);
-                    }
-                }
-            });
-        });
-    }
-
-    const r = await page.goto(url, {
-        waitUntil: 'load'
-    });
-
-    await page.waitForTimeout(1000);
-    await page.waitForTimeout(extra_wait_ms);
-
-    if (execute_js) {
-        await page.evaluate(execute_js);
-        await page.waitForTimeout(200);
-    }
-
-    var xpath_data;
-    var instock_data;
-    try {
-        // Not sure the best way here, in the future this should be a new package added to npm then run in browserless
-        // (Once the old playwright is removed)
-        xpath_data = await page.evaluate((include_filters) => {%xpath_scrape_code%}, include_filters);
-        instock_data = await page.evaluate(() => {%instock_scrape_code%});
-    } catch (e) {
-        console.log(e);
-    }
-
-    // Protocol error (Page.captureScreenshot): Cannot take screenshot with 0 width can come from a proxy auth failure
-    // Wrap it here (for now)
-
-    var b64s = false;
-    try {
-        b64s = await page.screenshot({encoding: "base64", fullPage: true, quality: screenshot_quality, type: 'jpeg'});
-    } catch (e) {
-        console.log(e);
-    }
-
-    // May fail on very large pages with 'WARNING: tile memory limits exceeded, some content may not draw'
-    if (!b64s) {
-        // @todo after text extract, we can place some overlay text with red background to say 'croppped'
-        console.error('ERROR: content-fetcher page was maybe too large for a screenshot, reverting to viewport only screenshot');
-        try {
-            b64s = await page.screenshot({encoding: "base64", quality: screenshot_quality, type: 'jpeg'});
-        } catch (e) {
-            console.log(e);
-        }
-    }
-
-    var html = await page.content();
-    return {
-        data: {
-            'content': html,
-            'headers': r.headers(),
-            'instock_data': instock_data,
-            'screenshot': b64s,
-            'status_code': r.status(),
-            'xpath_data': xpath_data
-        },
-        type: 'application/json',
-    };
-};

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

@@ -10,7 +10,6 @@ function isItemInStock() {
     'brak na stanie',
     'brak w magazynie',
     'coming soon',
-    'currently have any tickets for this',
     'currently unavailable',
     'en rupture de stock',
     'item is no longer available',
@@ -21,9 +20,7 @@ function isItemInStock() {
     'nicht zur verfügung',
     'no disponible temporalmente',
     'no longer in stock',
-    'no tickets available',
     'not available',
-    'not currently available',
     'not in stock',
     'notify me when available',
     'não estamos a aceitar encomendas',
@@ -33,8 +30,6 @@ function isItemInStock() {
     'sold out',
     'temporarily out of stock',
     'temporarily unavailable',
-    'tickets unavailable',
-    'unavailable tickets',
     'we do not currently have an estimate of when this product will be back in stock.',
     'zur zeit nicht an lager',
   ];

changedetectionio/res/xpath_element_scraper.js

@@ -8,14 +8,8 @@
 // Some pages like https://www.londonstockexchange.com/stock/NCCL/ncondezi-energy-limited/analysis
 // will automatically force a scroll somewhere, so include the position offset
 // Lets hope the position doesnt change while we iterate the bbox's, but this is better than nothing
-var scroll_y = 0;
-try {
-    scroll_y = +document.documentElement.scrollTop || document.body.scrollTop
-} catch (e) {
-    console.log(e);
-}
-
 
+var scroll_y=+document.documentElement.scrollTop || document.body.scrollTop
 
 // Include the getXpath script directly, easier than fetching
 function getxpath(e) {
@@ -44,15 +38,15 @@ const findUpTag = (el) => {
     if (el.name !== undefined && el.name.length) {
         var proposed = el.tagName + "[name=" + el.name + "]";
         var proposed_element = window.document.querySelectorAll(proposed);
-        if (proposed_element.length) {
+        if(proposed_element.length) {
             if (proposed_element.length === 1) {
                 return proposed;
             } else {
                 // Some sites change ID but name= stays the same, we can hit it if we know the index
                 // Find all the elements that match and work out the input[n]
-                var n = Array.from(proposed_element).indexOf(el);
+                var n=Array.from(proposed_element).indexOf(el);
                 // Return a Playwright selector for nthinput[name=zipcode]
-                return proposed + " >> nth=" + n;
+                return proposed+" >> nth="+n;
             }
         }
     }

changedetectionio/static/images/email.svg

@@ -1,37 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!-- Uploaded to: SVG Repo, www.svgrepo.com, Generator: SVG Repo Mixer Tools -->
-
-<svg
-   fill="#FFFFFF"
-   height="7.5005589"
-   width="11.248507"
-   version="1.1"
-   id="Layer_1"
-   viewBox="0 0 7.1975545 4.7993639"
-   xml:space="preserve"
-   xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg"><defs
-   id="defs19" />
-<g
-   id="g14"
-   transform="matrix(-0.01406065,0,0,0.01406065,7.1975543,-1.1990922)">
-	<g
-   id="g12">
-		<g
-   id="g10">
-			<path
-   d="M 468.373,85.28 H 45.333 C 21.227,85.28 0,105.76 0,129.014 V 383.2 c 0,23.147 21.227,43.413 45.333,43.413 h 422.933 c 23.68,0 43.627,-19.84 43.627,-43.413 V 129.014 C 512,105.334 492.053,85.28 468.373,85.28 Z m 0,320 H 45.333 c -12.373,0 -24,-10.773 -24,-22.08 V 129.014 c 0,-11.307 11.84,-22.4 24,-22.4 h 422.933 c 11.733,0 22.293,10.667 22.293,22.4 V 383.2 h 0.107 c 10e-4,11.734 -10.453,22.08 -22.293,22.08 z"
-   id="path2" />
-			<path
-   d="m 440.853,153.974 c -3.307,-4.907 -9.92,-6.187 -14.827,-2.987 L 256,264.48 85.973,151.094 c -4.907,-3.2 -11.52,-1.707 -14.72,3.2 -3.093,4.8 -1.813,11.307 2.88,14.507 l 176,117.333 c 3.627,2.347 8.213,2.347 11.84,0 l 176,-117.333 c 4.8,-3.201 6.187,-9.921 2.88,-14.827 z"
-   id="path4" />
-			<path
-   d="m 143.573,257.654 c -0.107,0.107 -0.32,0.213 -0.427,0.32 L 68.48,311.307 c -4.907,3.307 -6.187,9.92 -2.88,14.827 3.307,4.907 9.92,6.187 14.827,2.88 0.107,-0.107 0.32,-0.213 0.427,-0.32 l 74.667,-53.333 c 4.907,-3.307 6.187,-9.92 2.88,-14.827 -3.308,-4.907 -9.921,-6.187 -14.828,-2.88 z"
-   id="path6" />
-			<path
-   d="m 443.947,311.627 c -0.107,-0.107 -0.32,-0.213 -0.427,-0.32 l -74.667,-53.333 c -4.693,-3.52 -11.413,-2.56 -14.933,2.133 -3.52,4.693 -2.56,11.413 2.133,14.933 0.107,0.107 0.32,0.213 0.427,0.32 l 74.667,53.333 c 4.693,3.52 11.413,2.56 14.933,-2.133 3.52,-4.693 2.56,-11.413 -2.133,-14.933 z"
-   id="path8" />
-		</g>
-	</g>
-</g>
-</svg>

changedetectionio/static/images/generic-icon.svg

@@ -1,3 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!-- Created with Inkscape (http://www.inkscape.org/) -->
-<svg width="61.649mm" height="61.649mm" version="1.1" viewBox="0 0 61.649 61.649" xml:space="preserve" xmlns="http://www.w3.org/2000/svg"><g transform="translate(66.269 -15.463)" fill="#3056d3"><g transform="matrix(1.423 0 0 1.423 101.16 69.23)" fill="#3056d3"><g transform="matrix(.8229 0 0 .8229 -23.378 -2.3935)" fill="#3056d3"><path d="m-88.248-43.007a26.323 26.323 0 0 0-26.323 26.323 26.323 26.323 0 0 0 26.323 26.323 26.323 26.323 0 0 0 26.323-26.323 26.323 26.323 0 0 0-26.323-26.323zm0 2.8417a23.482 23.482 0 0 1 23.482 23.482 23.482 23.482 0 0 1-23.482 23.482 23.482 23.482 0 0 1-23.482-23.482 23.482 23.482 0 0 1 23.482-23.482z"/><g transform="matrix(.26458 0 0 .26458 -115.65 -44.085)"><path d="m33.02 64.43c0.35-0.05 2.04-0.13 2.04-0.13h25.53s3.17 0.32 3.67 0.53c2.5 1.05 3.98 1.89 6.04 3.57 0.72 0.58 4.12 4.01 4.12 4.01l51.67 57.39s1.61 1.65 1.97 1.94c1.2 0.97 2.48 1.96 3.98 2.32 0.5 0.12 2.72 0.21 2.72 0.21h27.32l-8.83-9.04s-1.31-1.65-1.44-1.94c-0.45-0.93-0.59-2.59-0.13-3.51 0.35-0.69 1.46-1.87 2.23-1.98 1.03-0.14 2.12-0.39 3.02 0.14 0.33 0.2 1.64 1.32 1.64 1.32l17.49 17.49s1.35 1.09 1.6 1.6c0.17 0.34 0.29 0.82 0.15 1.18-0.17 0.42-1.42 1.63-1.42 1.63l-0.94 0.98-15.69 16.37s-1.44 1.4-1.79 1.67c-0.76 0.6-1.99 0.89-2.96 0.9-1.03 0-2.62-1.11-3.26-1.91-0.6-0.76-1.1-2.22-0.77-3.13 0.16-0.45 1.28-1.85 1.28-1.85l11.36-11.3-29.47-0.02-1.68 0.09s-4.16-0.66-5.26-1.03c-1.63-0.56-3.44-1.82-4.75-2.93-0.39-0.33-1.8-1.92-1.8-1.92l-51.7-59.28s-2-2.06-2.43-2.43c-1.37-1.17-2-1.62-3.76-2.34-0.44-0.18-3.45-0.55-3.45-0.55l-24.13-0.22s-2.23-0.15-2.61-0.22c-1.08-0.21-2.16-1.07-2.81-1.83-0.79-0.92-0.59-3.06 0.06-4.09 0.57-0.89 2.14-1.52 3.19-1.66z"/><path d="m86.1 109.7-17.13 19.65s-2 2.06-2.43 2.43c-1.37 1.17-2 1.62-3.76 2.34-0.44 0.18-3.45 0.55-3.45 0.55l-24.13 0.22s-2.23 0.15-2.61 0.22c-1.08 0.21-2.16 1.07-2.81 1.83-0.79 0.92-0.59 3.06 0.06 4.09 0.57 0.89 2.14 1.52 3.19 1.66 0.35 0.05 2.04 0.13 2.04 0.13h25.53s3.17-0.32 3.67-0.53c2.5-1.05 3.98-1.89 6.04-3.57 0.72-0.58 4.12-4.01 4.12-4.01l17.38-19.3z"/><path d="m177.81 67.6c-0.17-0.42-1.42-1.63-1.42-1.63l-0.94-0.98-15.69-16.37s-1.44-1.4-1.79-1.67c-0.76-0.6-1.99-0.89-2.96-0.9-1.03 0-2.62 1.11-3.26 1.91-0.6 0.76-1.1 2.22-0.77 3.13 0.16 0.45 1.28 1.85 1.28 1.85l11.36 11.3-29.47 0.02-1.68-0.09s-4.16 0.66-5.26 1.03c-1.63 0.56-3.44 1.82-4.75 2.93-0.39 0.33-1.8 1.92-1.8 1.92l-18.91 21.69 5.98 5.98 18.38-20.41s1.61-1.65 1.97-1.94c1.2-0.97 2.48-1.96 3.98-2.32 0.5-0.12 2.72-0.21 2.72-0.21h27.32l-8.83 9.04s-1.31 1.65-1.44 1.94c-0.45 0.93-0.59 2.59-0.13 3.51 0.35 0.69 1.46 1.87 2.23 1.98 1.03 0.14 2.12 0.39 3.02-0.14 0.33-0.2 1.64-1.32 1.64-1.32l17.49-17.49s1.35-1.09 1.6-1.6c0.17-0.34 0.29-0.82 0.15-1.18z"/></g></g></g></g></svg>

changedetectionio/static/js/browser-steps.js

@@ -114,11 +114,11 @@ $(document).ready(function () {
             e.preventDefault()
         });
 
-        // When the mouse moves we know which element it should be above
-        // mousedown will link that to the UI (select the right action, highlight etc)
         $('#browsersteps-selector-canvas').bind('mousedown', function (e) {
             // https://developer.mozilla.org/en-US/docs/Web/API/MouseEvent
             e.preventDefault()
+            console.log(e);
+            console.log("current xpath in index is " + current_selected_i);
             last_click_xy = {'x': parseInt((1 / x_scale) * e.offsetX), 'y': parseInt((1 / y_scale) * e.offsetY)}
             process_selected(current_selected_i);
             current_selected_i = false;
@@ -132,7 +132,6 @@ $(document).ready(function () {
             }
         });
 
-        // Debounce and find the current most 'interesting' element we are hovering above
         $('#browsersteps-selector-canvas').bind('mousemove', function (e) {
             if (!xpath_data) {
                 return;
@@ -152,40 +151,41 @@ $(document).ready(function () {
             current_selected_i = false;
             // Reverse order - the most specific one should be deeper/"laster"
             // Basically, find the most 'deepest'
-            var possible_elements = [];
-            xpath_data['size_pos'].forEach(function (item, index) {
+            //$('#browsersteps-selector-canvas').css('cursor', 'pointer');
+            for (var i = xpath_data['size_pos'].length; i !== 0; i--) {
+                // draw all of them? let them choose somehow?
+                var sel = xpath_data['size_pos'][i - 1];
                 // If we are in a bounding-box
-                if (e.offsetY > item.top * y_scale && e.offsetY < item.top * y_scale + item.height * y_scale
+                if (e.offsetY > sel.top * y_scale && e.offsetY < sel.top * y_scale + sel.height * y_scale
                     &&
-                    e.offsetX > item.left * y_scale && e.offsetX < item.left * y_scale + item.width * y_scale
+                    e.offsetX > sel.left * y_scale && e.offsetX < sel.left * y_scale + sel.width * y_scale
 
                 ) {
-                    // There could be many elements here, record them all and then we'll find out which is the most 'useful'
-                    // (input, textarea, button, A etc)
-                    if (item.width < xpath_data['browser_width']) {
-                        possible_elements.push(item);
+                    // Only highlight these interesting types
+                    if (1) {
+                        ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+                        ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+                        current_selected_i = i - 1;
+                        break;
+
+                        // find the smallest one at this x,y
+                        // does it mean sort the xpath list by size (w*h) i think so!
+                    } else {
+
+                        if (include_text_elements[0].checked === true) {
+                            // blue one with background instead?
+                            ctx.fillStyle = 'rgba(0,0,255, 0.1)';
+                            ctx.strokeStyle = 'rgba(0,0,200, 0.7)';
+                            $('#browsersteps-selector-canvas').css('cursor', 'grab');
+                            ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+                            ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+                            current_selected_i = i - 1;
+                            break;
+                        }
                     }
                 }
-            });
-
-            // Find the best one
-            if (possible_elements.length) {
-                possible_elements.forEach(function (item, index) {
-                  if (["a", "input", "textarea", "button"].includes(item['tagName'])) {
-                      current_selected_i = item;
-                  }
-                });
-
-                if (!current_selected_i) {
-                    current_selected_i = possible_elements[0];
-                }
-
-                sel = xpath_data['size_pos'][current_selected_i];
-                ctx.strokeRect(current_selected_i.left * x_scale, current_selected_i.top * y_scale, current_selected_i.width * x_scale, current_selected_i.height * y_scale);
-                ctx.fillRect(current_selected_i.left * x_scale, current_selected_i.top * y_scale, current_selected_i.width * x_scale, current_selected_i.height * y_scale);
             }
 
-
         }.debounce(10));
     });
 
@@ -195,16 +195,16 @@ $(document).ready(function () {
 
 
     // callback for clicking on an xpath on the canvas
-    function process_selected(selected_in_xpath_list) {
+    function process_selected(xpath_data_index) {
         found_something = false;
         var first_available = $("ul#browser_steps li.empty").first();
 
 
-        if (selected_in_xpath_list !== false) {
+        if (xpath_data_index !== false) {
             // Nothing focused, so fill in a new one
             // if inpt type button or <button>
             // from the top, find the next not used one and use it
-            var x = selected_in_xpath_list;
+            var x = xpath_data['size_pos'][xpath_data_index];
             console.log(x);
             if (x && first_available.length) {
                 // @todo will it let you click shit that has a layer ontop? probably not.
@@ -214,18 +214,26 @@ $(document).ready(function () {
                     $('input[placeholder="Value"]', first_available).addClass('ok').click().focus();
                     found_something = true;
                 } else {
-                    // There's no good way (that I know) to find if this
-                    // see https://stackoverflow.com/questions/446892/how-to-find-event-listeners-on-a-dom-node-in-javascript-or-in-debugging
-                    // https://codepen.io/azaslavsky/pen/DEJVWv
-
-                    // So we dont know if its really a clickable element or not :-(
-                    // Assume it is - then we dont fill the pages with unreliable "Click X,Y" selections
-                    // If you switch to "Click X,y" after an element here is setup, it will give the last co-ords anyway
-                    //if (x['isClickable'] || x['tagName'].startsWith('h') || x['tagName'] === 'a' || x['tagName'] === 'button' || x['tagtype'] === 'submit' || x['tagtype'] === 'checkbox' || x['tagtype'] === 'radio' || x['tagtype'] === 'li') {
+                    if (x['isClickable'] || x['tagName'].startsWith('h') || x['tagName'] === 'a' || x['tagName'] === 'button' || x['tagtype'] === 'submit' || x['tagtype'] === 'checkbox' || x['tagtype'] === 'radio' || x['tagtype'] === 'li') {
                         $('select', first_available).val('Click element').change();
                         $('input[type=text]', first_available).first().val(x['xpath']);
                         found_something = true;
-                    //}
+                    }
+                }
+
+                first_available.xpath_data_index = xpath_data_index;
+
+                if (!found_something) {
+                    if (include_text_elements[0].checked === true) {
+                        // Suggest that we use as filter?
+                        // @todo filters should always be in the last steps, nothing non-filter after it
+                        found_something = true;
+                        ctx.strokeStyle = 'rgba(0,0,255, 0.9)';
+                        ctx.fillStyle = 'rgba(0,0,255, 0.1)';
+                        $('select', first_available).val('Extract text and use as filter').change();
+                        $('input[type=text]', first_available).first().val(x['xpath']);
+                        include_text_elements[0].checked = false;
+                    }
                 }
             }
         }
@@ -240,7 +248,7 @@ $(document).ready(function () {
 
     function start() {
         console.log("Starting browser-steps UI");
-        browsersteps_session_id = false;
+        browsersteps_session_id = Date.now();
         // @todo This setting of the first one should be done at the datalayer but wtforms doesnt wanna play nice
         $('#browser_steps >li:first-child').removeClass('empty');
         set_first_gotosite_disabled();
@@ -248,7 +256,7 @@ $(document).ready(function () {
         $('.clear,.remove', $('#browser_steps >li:first-child')).hide();
         $.ajax({
             type: "GET",
-            url: browser_steps_start_url,
+            url: browser_steps_sync_url + "&browsersteps_session_id=" + browsersteps_session_id,
             statusCode: {
                 400: function () {
                     // More than likely the CSRF token was lost when the server restarted
@@ -256,12 +264,12 @@ $(document).ready(function () {
                 }
             }
         }).done(function (data) {
+            xpath_data = data.xpath_data;
             $("#loading-status-text").fadeIn();
-            browsersteps_session_id = data.browsersteps_session_id;
             // This should trigger 'Goto site'
             console.log("Got startup response, requesting Goto-Site (first) step fake click");
             $('#browser_steps >li:first-child .apply').click();
-            browserless_seconds_remaining = 500;
+            browserless_seconds_remaining = data.browser_time_remaining;
             set_first_gotosite_disabled();
         }).fail(function (data) {
             console.log(data);
@@ -422,6 +430,7 @@ $(document).ready(function () {
             apply_buttons_disabled = false;
             $("#browsersteps-img").css('opacity', 1);
             $('ul#browser_steps li .control .apply').css('opacity', 1);
+            browserless_seconds_remaining = data.browser_time_remaining;
             $("#loading-status-text").hide();
             set_first_gotosite_disabled();
         }).fail(function (data) {

changedetectionio/static/js/notifications.js

@@ -26,6 +26,9 @@ $(document).ready(function() {
     data = {
         window_url : window.location.href,
         notification_urls : $('.notification-urls').val(),
+        notification_title : $('.notification-title').val(),
+        notification_body : $('.notification-body').val(),
+        notification_format : $('.notification-format').val(),
     }
     for (key in data) {
       if (!data[key].length) {

changedetectionio/static/js/tabs.js

@@ -12,7 +12,7 @@ window.addEventListener('hashchange', function () {
 var has_errors = document.querySelectorAll(".messages .error");
 if (!has_errors.length) {
     if (document.location.hash == "") {
-        location.replace(document.querySelector(".tabs ul li:first-child a").hash);
+        document.querySelector(".tabs ul li:first-child a").click();
     } else {
         set_active_tab();
     }

changedetectionio/static/js/toggle-theme.js

@@ -3,7 +3,7 @@
  * Toggles theme between light and dark mode.
  */
 $(document).ready(function () {
-  const button = document.getElementById("toggle-light-mode");
+  const button = document.getElementsByClassName("toggle-theme")[0];
 
   button.onclick = () => {
     const htmlElement = document.getElementsByTagName("html");
@@ -21,33 +21,4 @@ $(document).ready(function () {
   const setCookieValue = (value) => {
     document.cookie = `css_dark_mode=${value};max-age=31536000;path=/`
   }
-
-  // Search input box behaviour
-    const toggle_search = document.getElementById("toggle-search");
-  const search_q = document.getElementById("search-q");
-  window.addEventListener('keydown', function (e) {
-
-    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();
-    }
-  };
-  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();
-    }
-  };
-
 });

changedetectionio/static/js/visual-selector.js

@@ -61,12 +61,7 @@ $(document).ready(function () {
     function bootstrap_visualselector() {
         if (1) {
             // bootstrap it, this will trigger everything else
-            $("img#selector-background").on("error", function () {
-                $('.fetching-update-notice').html("<strong>Ooops!</strong> The VisualSelector tool needs atleast one fetched page, please unpause the watch and/or wait for the watch to complete fetching and then reload this page.");
-                $('.fetching-update-notice').css('color','#bb0000');
-                $('#selector-current-xpath').hide();
-                $('#clear-selector').hide();
-            }).bind('load', function () {
+            $("img#selector-background").bind('load', function () {
                 console.log("Loaded background...");
                 c = document.getElementById("selector-canvas");
                 // greyed out fill context
@@ -84,11 +79,10 @@ $(document).ready(function () {
             }).attr("src", screenshot_url);
         }
         // Tell visualSelector that the image should update
-        var s = $("img#selector-background").attr('src') + "?" + new Date().getTime();
-        $("img#selector-background").attr('src', s)
+        var s = $("img#selector-background").attr('src')+"?"+ new Date().getTime();
+        $("img#selector-background").attr('src',s)
     }
 
-    // This is fired once the img src is loaded in bootstrap_visualselector()
     function fetch_data() {
         // Image is ready
         $('.fetching-update-notice').html("Fetching element data..");
@@ -105,8 +99,7 @@ $(document).ready(function () {
             reflow_selector();
             $('.fetching-update-notice').fadeOut();
         });
-
-    }
+    };
 
 
     function set_scale() {

changedetectionio/static/styles/scss/parts/_pagination.scss

@@ -1,37 +0,0 @@
-.pagination-page-info {
-  color: #fff;
-  font-size: 0.85rem;
-  text-transform: capitalize;
-}
-
-.pagination.menu {
-  > * {
-    display: inline-block;
-  }
-
-  li {
-    display: inline-block;
-  }
-
-  a {
-    padding: 0.65rem;
-    margin: 3px;
-    border: none;
-    background: #444;
-    border-radius: 2px;
-    color: var(--color-text-button);
-    &.disabled {
-      display: none;
-    }
-    &.active {
-      font-weight: bold;
-      background: #888;
-    }
-
-    &:hover {
-      background: #999;
-    }
-  }
-
-
-}

changedetectionio/static/styles/scss/styles.scss

@@ -5,7 +5,6 @@
 @import "parts/_arrows";
 @import "parts/_browser-steps";
 @import "parts/_extra_proxies";
-@import "parts/_pagination";
 @import "parts/_spinners";
 @import "parts/_variables";
 
@@ -54,47 +53,8 @@ a.github-link {
   }
 }
 
-#toggle-light-mode {
-  width: 3rem;
-  .icon-dark {
-    display: none;
-  }
-
-  &.dark {
-    .icon-light {
-      display: none;
-    }
-
-    .icon-dark {
-      display: block;
-    }
-  }
-}
-
-#toggle-search {
-  width: 2rem;
-}
-
-#search-q {
-  opacity: 0;
-  -webkit-transition: all .9s ease;
-  -moz-transition: all .9s ease;
-  transition: all .9s ease;
-  width: 0;
-  display: none;
-  &.expanded {
-    width: auto;
-    display: inline-block;
-
-    opacity: 1;
-  }
-}
-#search-result-info {
-  color: #fff;
-}
-
-button.toggle-button {
-  vertical-align: middle;
+button.toggle-theme {
+  width: 4rem;
   background: transparent;
   border: none;
   cursor: pointer;
@@ -113,7 +73,19 @@ button.toggle-button {
     display: block;
   }
 
+  .icon-dark {
+    display: none;
+  }
 
+  &.dark {
+    .icon-light {
+      display: none;
+    }
+
+    .icon-dark {
+      display: block;
+    }
+  }
 }
 
 .pure-menu-horizontal {

changedetectionio/static/styles/styles.css

@@ -95,32 +95,6 @@ ul#requests-extra_proxies {
   ul#requests-extra_proxies table tr {
     display: inline; }
 
-.pagination-page-info {
-  color: #fff;
-  font-size: 0.85rem;
-  text-transform: capitalize; }
-
-.pagination.menu > * {
-  display: inline-block; }
-
-.pagination.menu li {
-  display: inline-block; }
-
-.pagination.menu a {
-  padding: 0.65rem;
-  margin: 3px;
-  border: none;
-  background: #444;
-  border-radius: 2px;
-  color: var(--color-text-button); }
-  .pagination.menu a.disabled {
-    display: none; }
-  .pagination.menu a.active {
-    font-weight: bold;
-    background: #888; }
-  .pagination.menu a:hover {
-    background: #999; }
-
 /* spinner */
 .spinner,
 .spinner:after {
@@ -331,44 +305,23 @@ a.github-link {
   a.github-link:hover {
     color: var(--color-icon-github-hover); }
 
-#toggle-light-mode {
-  width: 3rem; }
-  #toggle-light-mode .icon-dark {
-    display: none; }
-  #toggle-light-mode.dark .icon-light {
-    display: none; }
-  #toggle-light-mode.dark .icon-dark {
-    display: block; }
-
-#toggle-search {
-  width: 2rem; }
-
-#search-q {
-  opacity: 0;
-  -webkit-transition: all .9s ease;
-  -moz-transition: all .9s ease;
-  transition: all .9s ease;
-  width: 0;
-  display: none; }
-  #search-q.expanded {
-    width: auto;
-    display: inline-block;
-    opacity: 1; }
-
-#search-result-info {
-  color: #fff; }
-
-button.toggle-button {
-  vertical-align: middle;
+button.toggle-theme {
+  width: 4rem;
   background: transparent;
   border: none;
   cursor: pointer;
   color: var(--color-icon-github); }
-  button.toggle-button:hover {
+  button.toggle-theme:hover {
     color: var(--color-icon-github-hover); }
-  button.toggle-button svg {
+  button.toggle-theme svg {
     fill: currentColor; }
-  button.toggle-button .icon-light {
+  button.toggle-theme .icon-light {
+    display: block; }
+  button.toggle-theme .icon-dark {
+    display: none; }
+  button.toggle-theme.dark .icon-light {
+    display: none; }
+  button.toggle-theme.dark .icon-dark {
     display: block; }
 
 .pure-menu-horizontal {

changedetectionio/store.py

@@ -3,7 +3,7 @@ from flask import (
 )
 
 from . model import App, Watch
-from copy import deepcopy, copy
+from copy import deepcopy
 from os import path, unlink
 from threading import Lock
 import json
@@ -204,16 +204,15 @@ class ChangeDetectionStore:
                 # GitHub #30 also delete history records
                 for uuid in self.data['watching']:
                     path = pathlib.Path(os.path.join(self.datastore_path, uuid))
-                    if os.path.exists(path):
-                        shutil.rmtree(path)
+                    shutil.rmtree(path)
+                    self.needs_write_urgent = True
 
             else:
                 path = pathlib.Path(os.path.join(self.datastore_path, uuid))
-                if os.path.exists(path):
-                    shutil.rmtree(path)
+                shutil.rmtree(path)
                 del self.data['watching'][uuid]
 
-        self.needs_write_urgent = True
+            self.needs_write_urgent = True
 
     # Clone a watch by UUID
     def clone(self, uuid):
@@ -317,8 +316,7 @@ class ChangeDetectionStore:
             # #Re 569
             new_watch = Watch.model(datastore_path=self.datastore_path, default={
                 'url': url,
-                'tag': tag,
-                'date_created': int(time.time())
+                'tag': tag
             })
 
             new_uuid = new_watch['uuid']
@@ -367,21 +365,19 @@ class ChangeDetectionStore:
     def save_error_text(self, watch_uuid, contents):
         if not self.data['watching'].get(watch_uuid):
             return
-
-        self.data['watching'][watch_uuid].ensure_data_dir_exists()
         target_path = os.path.join(self.datastore_path, watch_uuid, "last-error.txt")
+
         with open(target_path, 'w') as f:
             f.write(contents)
 
     def save_xpath_data(self, watch_uuid, data, as_error=False):
-
         if not self.data['watching'].get(watch_uuid):
             return
         if as_error:
             target_path = os.path.join(self.datastore_path, watch_uuid, "elements-error.json")
         else:
             target_path = os.path.join(self.datastore_path, watch_uuid, "elements.json")
-        self.data['watching'][watch_uuid].ensure_data_dir_exists()
+
         with open(target_path, 'w') as f:
             f.write(json.dumps(data))
             f.close()
@@ -475,6 +471,8 @@ class ChangeDetectionStore:
         return proxy_list if len(proxy_list) else None
 
 
+
+
     def get_preferred_proxy_for_watch(self, uuid):
         """
         Returns the preferred proxy by ID key
@@ -506,25 +504,6 @@ class ChangeDetectionStore:
 
         return None
 
-    @property
-    def has_extra_headers_file(self):
-        filepath = os.path.join(self.datastore_path, 'headers.txt')
-        return os.path.isfile(filepath)
-
-    def get_all_headers(self):
-        from .model.App import parse_headers_from_text_file
-        headers = copy(self.data['settings'].get('headers', {}))
-
-        filepath = os.path.join(self.datastore_path, 'headers.txt')
-        try:
-            if os.path.isfile(filepath):
-                headers.update(parse_headers_from_text_file(filepath))
-        except Exception as e:
-            print(f"ERROR reading headers.txt at {filepath}", str(e))
-
-        return headers
-
-
     # 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
@@ -700,13 +679,3 @@ class ChangeDetectionStore:
             except:
                 continue
         return
-
-    # We don't know when the date_created was in the past until now, so just add an index number for now.
-    def update_11(self):
-        i = 0
-        for uuid, watch in self.data['watching'].items():
-            if not watch.get('date_created'):
-                watch['date_created'] = i
-            i+=1
-        return
-

changedetectionio/templates/_common_fields.jinja

@@ -23,7 +23,7 @@
                             <div class="notifications-wrapper">
                               <a id="send-test-notification" class="pure-button button-secondary button-xsmall" >Send test notification</a>
                             {% if emailprefix %}
-                              <a id="add-email-helper" class="pure-button button-secondary button-xsmall" >Add email <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='email.svg')}}" alt="Add an email address"> </a>
+                              <a id="add-email-helper" class="pure-button button-secondary button-xsmall" >Add email</a>
                             {% endif %}
                               <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" >Notification debug logs</a>
                             </div>
@@ -115,7 +115,7 @@
                                     URLs generated by changedetection.io (such as <code>{{ '{{diff_url}}' }}</code>) require the <code>BASE_URL</code> environment variable set.<br>
                                     Your <code>BASE_URL</code> var is currently "{{settings_application['current_base_url']}}"
 									<br>
-									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removed%7D%7D-notification-tokens">More Here</a> <br>
+									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removal%7D%7D-notification-tokens">More Here</a> </br>
                                 </div>
                             </div>
                         </div>

changedetectionio/templates/_pagination.jinja

@@ -0,0 +1,7 @@
+{% macro pagination(sorted_watches, total_per_page, current_page) %}
+  {{ sorted_watches|length }}
+
+  {% for row in sorted_watches|batch(total_per_page, ' ') %}
+    {{ loop.index}}
+  {% endfor %}
+{% endmacro %}

changedetectionio/templates/base.html

@@ -2,35 +2,35 @@
 <html lang="en" data-darkmode="{{ get_darkmode_state() }}">
 
   <head>
-    <meta charset="utf-8" >
-    <meta name="viewport" content="width=device-width, initial-scale=1.0" >
-    <meta name="description" content="Self hosted website change detection." >
+    <meta charset="utf-8"/>
+    <meta name="viewport" content="width=device-width, initial-scale=1.0"/>
+    <meta name="description" content="Self hosted website change detection."/>
     <title>Change Detection{{extra_title}}</title>
-    <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}" >
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}" >
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}" >
+    <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"/>
+    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}"/>
+    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}"/>
     {% if extra_stylesheets %}
       {% for m in extra_stylesheets %}
-        <link rel="stylesheet" href="{{ m }}?ver=1000" >
+        <link rel="stylesheet" href="{{ m }}?ver=1000"/>
       {% endfor %}
     {% endif %}
 
-    <link rel="apple-touch-icon" sizes="180x180" href="{{url_for('static_content', group='favicons', filename='apple-touch-icon.png')}}">
-    <link rel="icon" type="image/png" sizes="32x32" href="{{url_for('static_content', group='favicons', filename='favicon-32x32.png')}}">
-    <link rel="icon" type="image/png" sizes="16x16" href="{{url_for('static_content', group='favicons', filename='favicon-16x16.png')}}">
-    <link rel="manifest" href="{{url_for('static_content', group='favicons', filename='site.webmanifest')}}">
-    <link rel="mask-icon" href="{{url_for('static_content', group='favicons', filename='safari-pinned-tab.svg')}}" color="#5bbad5">
-    <link rel="shortcut icon" href="{{url_for('static_content', group='favicons', filename='favicon.ico')}}">
-    <meta name="msapplication-TileColor" content="#da532c">
-    <meta name="msapplication-config" content="favicons/browserconfig.xml">
-    <meta name="theme-color" content="#ffffff">
+    <link rel="apple-touch-icon" sizes="180x180" href="{{url_for('static_content', group='favicons', filename='apple-touch-icon.png')}}"/>
+    <link rel="icon" type="image/png" sizes="32x32" href="{{url_for('static_content', group='favicons', filename='favicon-32x32.png')}}"/>
+    <link rel="icon" type="image/png" sizes="16x16" href="{{url_for('static_content', group='favicons', filename='favicon-16x16.png')}}"/>
+    <link rel="manifest" href="{{url_for('static_content', group='favicons', filename='site.webmanifest')}}"/>
+    <link rel="mask-icon" href="{{url_for('static_content', group='favicons', filename='safari-pinned-tab.svg')}}" color="#5bbad5"/>
+    <link rel="shortcut icon" href="{{url_for('static_content', group='favicons', filename='favicon.ico')}}"/>
+    <meta name="msapplication-TileColor" content="#da532c"/>
+    <meta name="msapplication-config" content="favicons/browserconfig.xml"/>
+    <meta name="theme-color" content="#ffffff"/>
 
     <style>
       body::before {
         background-image: url({{url_for('static_content', group='images', filename='gradient-border.png') }});
       }
     </style>
-    <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
+    <script type="text/javascript" src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
   </head>
 
   <body>
@@ -82,21 +82,11 @@
               <a href="{{url_for('logout')}}" class="pure-menu-link">LOG OUT</a>
             </li>
           {% endif %}
-          <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">
-              <input id="search-q" class="" name="q" placeholder="URL or Title {% if active_tag %}in '{{ active_tag }}'{% endif %}" required="" type="text" value="">
-              <input name="tag" type="hidden" value="{% if active_tag %}{{active_tag}}{% endif %}">
-              <button class="toggle-button " id="toggle-search" type="button" title="Search, or Use Alt+S Key" >
-                {% include "svgs/search-icon.svg" %}
-              </button>
-            </form>
-          </li>
           <li class="pure-menu-item">
             {% if dark_mode %}
             {% set darkClass = 'dark' %}
             {% endif %}
-            <button class="toggle-button {{darkClass}}"  id ="toggle-light-mode" type="button" title="Toggle Light/Dark Mode">
+            <button class="toggle-theme {{darkClass}}" type="button" title="Toggle Light/Dark Mode">
               <span class="visually-hidden">Toggle light/dark mode</span>
               <span class="icon-light">
                 {% include "svgs/light-mode-toggle-icon.svg" %}
@@ -116,7 +106,7 @@
     </div>
     {% if hosted_sticky %}
       <div class="sticky-tab" id="hosted-sticky">
-        <a href="https://changedetection.io/?ref={{guid}}">Let us host your instance!</a>
+        <a href="https://lemonade.changedetection.io/start?ref={{guid}}">Let us host your instance!</a>
       </div>
     {% endif %}
     {% if left_sticky %}
@@ -147,13 +137,16 @@
           <li class="message">
             Share this link:
             <span id="share-link">{{ session['share-link'] }}</span>
-            <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='copy.svg')}}" >
+            <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='copy.svg')}}"/>
           </li>
         </ul>
       {% endif %}
       {% block content %}{% endblock %}
     </section>
-    <script src="{{url_for('static_content', group='js', filename='toggle-theme.js')}}" defer></script>
+    <script
+      type="text/javascript"
+      src="{{url_for('static_content', group='js', filename='toggle-theme.js')}}"
+      defer></script>
   </body>
 
 </html>

changedetectionio/templates/clear_all_history.html

@@ -6,7 +6,7 @@
       action="{{url_for('clear_all_history')}}"
       method="POST"
     >
-      <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
+      <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" />
       <fieldset>
         <div class="pure-control-group">
           This will remove version history (snapshots) for ALL watches, but keep

changedetectionio/templates/diff.html

@@ -7,7 +7,7 @@
     const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
     {% endif %}
 </script>
-<script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
 <div id="settings">
     <h1>Differences</h1>
@@ -15,15 +15,15 @@
         <fieldset>
 
             <label for="diffWords" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffWords" value="diffWords"> Words</label>
+                <input type="radio" name="diff_type" id="diffWords" value="diffWords"/> Words</label>
             <label for="diffLines" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffLines" value="diffLines" checked=""> Lines</label>
+                <input type="radio" name="diff_type" id="diffLines" value="diffLines" checked=""/> Lines</label>
 
             <label for="diffChars" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffChars" value="diffChars"> Chars</label>
+                <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>
@@ -43,7 +43,7 @@
     <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>
 </div>
 
@@ -51,7 +51,7 @@
     <a onclick="next_diff();">Jump</a>
 </div>
 
-<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="tabs">
     <ul>
         {% if last_error_text %}<li class="tab" id="error-text-tab"><a href="#error-text">Error Text</a></li> {% endif %}
@@ -72,7 +72,7 @@
 
     <div class="tab-pane-inner" id="error-screenshot">
         <div class="snapshot-age error">{{watch_a.snapshot_error_screenshot_ctime|format_seconds_ago}} seconds ago</div>
-        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current error-ing screenshot from most recent request" >
+        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current error-ing screenshot from most recent request"/>
     </div>
 
      <div class="tab-pane-inner" id="text">
@@ -105,7 +105,7 @@
          {% if is_html_webdriver %}
            {% if screenshot %}
             <div class="snapshot-age">{{watch_a.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
-            <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request" >
+            <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
            {% else %}
               No screenshot available just yet! Try rechecking the page.
            {% endif %}
@@ -117,7 +117,7 @@
         <form id="extract-data-form" class="pure-form pure-form-stacked edit-form"
               action="{{ url_for('diff_history_page', uuid=uuid) }}#extract"
               method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
+            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
 
             <p>This tool will extract text data from all of the watch history.</p>
 
@@ -149,9 +149,9 @@
 <script>
     const newest_version_timestamp = {{newest_version_timestamp}};
 </script>
-<script src="{{url_for('static_content', group='js', filename='diff.min.js')}}"></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff.min.js')}}"></script>
 
-<script src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
 
 
 {% endblock %}

changedetectionio/templates/edit.html

@@ -2,7 +2,7 @@
 {% block content %}
 {% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
-<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <script>
     const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
     const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
@@ -14,17 +14,15 @@
 {% endif %}
 
     const browser_steps_config=JSON.parse('{{ browser_steps_config|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)}}";
-
 </script>
 
-<script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
-<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
-<script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
-<script src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
 {% if playwright_enabled %}
-<script src="{{url_for('static_content', group='js', filename='browser-steps.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='browser-steps.js')}}" defer></script>
 {% endif %}
 
 <div class="edit-form monospaced-textarea">
@@ -52,7 +50,7 @@
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked"
               action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next'), unpause_on_save = request.args.get('unpause_on_save')) }}" method="POST">
-             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
+             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
 
             <div class="tab-pane-inner" id="general">
                 <fieldset>
@@ -152,17 +150,6 @@
 {{ render_field(form.headers, rows=5, placeholder="Example
 Cookie: foobar
 User-Agent: wonderbra 1.0") }}
-
-                        <div class="pure-form-message-inline">
-                            {% if has_extra_headers_file %}
-                                <strong>Alert! Extra headers file found and will be added to this watch!</strong>
-                            {% else %}
-                                Headers can be also read from a file in your data-directory <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Adding-headers-from-an-external-file">Read more here</a>
-                            {% endif %}
-                            <br>
-                            (Not supported by Selenium browser)
-                        </div>
-
                     </div>
                     <div class="pure-control-group" id="request-body">
                                         {{ render_field(form.body, rows=5, placeholder="Example
@@ -176,7 +163,7 @@ User-Agent: wonderbra 1.0") }}
             </div>
             {% if playwright_enabled %}
             <div class="tab-pane-inner" id="browser-steps">
-                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
+                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
                 <fieldset>
                     <div class="pure-control-group">
                         <!--
@@ -199,12 +186,11 @@ User-Agent: wonderbra 1.0") }}
                                     <span class="loader" >
                                         <span id="browsersteps-click-start">
                                             <h2 >Click here to Start</h2>
-                                            <svg style="height: 3.5rem;" version="1.1" viewBox="0 0 32 32"  xml:space="preserve" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g id="Layer_1"/><g id="play_x5F_alt"><path d="M16,0C7.164,0,0,7.164,0,16s7.164,16,16,16s16-7.164,16-16S24.836,0,16,0z M10,24V8l16.008,8L10,24z" style="fill: var(--color-grey-400);"/></g></svg><br>
-                                            Please allow 10-15 seconds for the browser to connect.<br>
+                                            Please allow 10-15 seconds for the browser to connect.
                                         </span>
                                         <div class="spinner"  style="display: none;"></div>
                                     </span>
-                                    <img class="noselect" id="browsersteps-img" src="" style="max-width: 100%; width: 100%;" >
+                                    <img  class="noselect" id="browsersteps-img" src="" style="max-width: 100%; width: 100%;" />
                                     <canvas  class="noselect" id="browsersteps-selector-canvas" style="max-width: 100%; width: 100%;"></canvas>
                                 </div>
                             </div>
@@ -234,7 +220,7 @@ User-Agent: wonderbra 1.0") }}
                     <div class="field-group" id="notification-field-group">
                         {% if has_default_notification_urls %}
                         <div class="inline-warning">
-                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!" >
+                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!"/>
                             There are <a href="{{ url_for('settings_page')}}#notifications">system-wide notification URLs enabled</a>, this form will override notification settings for this watch only &dash; an empty Notification URL list here will still send notifications.
                         </div>
                         {% endif %}
@@ -404,7 +390,7 @@ Unavailable") }}
 
             {% if watch['processor'] == 'text_json_diff' %}
             <div class="tab-pane-inner visual-selector-ui" id="visualselector">
-                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
+                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
 
                 <fieldset>
                     <div class="pure-control-group">
@@ -421,7 +407,7 @@ Unavailable") }}
                                 <!-- request the screenshot and get the element offset info ready -->
                                 <!-- use img src ready load to know everything is ready to map out -->
                                 <!-- @todo: maybe something interesting like a field to select 'elements that contain text... and their parents n' -->
-                                <img id="selector-background" >
+                                <img id="selector-background" />
                                 <canvas id="selector-canvas"></canvas>
                             </div>
                             <div id="selector-current-xpath" style="overflow-x: hidden"><strong>Currently:</strong>&nbsp;<span class="text">Loading...</span></div>

changedetectionio/templates/import.html

@@ -1,7 +1,7 @@
 {% extends 'base.html' %}
 {% block content %}
 {% from '_helpers.jinja' import render_field %}
-<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="edit-form monospaced-textarea">
 
     <div class="tabs collapsable">
@@ -13,7 +13,7 @@
 
     <div class="box-wrap inner">
         <form class="pure-form pure-form-aligned" action="{{url_for('import_page')}}" method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
+            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
             <div class="tab-pane-inner" id="url-list">
                     <legend>
                         Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma

changedetectionio/templates/login.html

@@ -4,13 +4,13 @@
 <div class="login-form">
  <div class="inner">
     <form class="pure-form pure-form-stacked" action="{{url_for('login')}}" method="POST">
-        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
+        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
         <fieldset>
             <div class="pure-control-group">
                 <label for="password">Password</label>
                 <input type="password" id="password" required="" name="password" value=""
                        size="15" autofocus />
-                <input type="hidden" id="email" name="email" value="defaultuser@changedetection.io" >
+                <input type="hidden" id="email" name="email" value="defaultuser@changedetection.io" />
             </div>
             <div class="pure-control-group">
                 <button type="submit" class="pure-button pure-button-primary">Login</button>

changedetectionio/templates/preview.html

@@ -7,9 +7,9 @@
     const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
     {% endif %}
 </script>
-<script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
-<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="tabs">
     <ul>
         {% if last_error_text %}<li class="tab" id="error-text-tab"><a href="#error-text">Error Text</a></li> {% endif %}
@@ -31,7 +31,7 @@
 
     <div class="tab-pane-inner" id="error-screenshot">
         <div class="snapshot-age error">{{watch.snapshot_error_screenshot_ctime|format_seconds_ago}} seconds ago</div>
-        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current erroring screenshot from most recent request" >
+        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current erroring screenshot from most recent request"/>
     </div>
 
     <div class="tab-pane-inner" id="text">
@@ -58,7 +58,7 @@
          {% if is_html_webdriver %}
            {% if screenshot %}
              <div class="snapshot-age">{{watch.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
-             <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request" >
+             <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
            {% else %}
               No screenshot available just yet! Try rechecking the page.
            {% endif %}

changedetectionio/templates/settings.html

@@ -9,10 +9,10 @@
     const email_notification_prefix=JSON.parse('{{emailprefix|tojson}}');
 {% endif %}
 </script>
-<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
-<script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 
-<script src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
 <div class="edit-form">
     <div class="tabs collapsable">
         <ul>
@@ -26,7 +26,7 @@
     </div>
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked settings" action="{{url_for('settings_page')}}" method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
+            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
             <div class="tab-pane-inner" id="general">
                 <fieldset>
                     <div class="pure-control-group">
@@ -70,10 +70,6 @@
                             <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">read more here</a>.
                         </span>
                     </div>
-                    <div class="pure-control-group">
-                        {{ render_field(form.application.form.pager_size) }}
-                        <span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
-                    </div>
 
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.extract_title_as_title) }}

changedetectionio/templates/svgs/search-icon.svg

@@ -1 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?><svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0 0 122.879 119.799" enable-background="new 0 0 122.879 119.799" xml:space="preserve"><g><path d="M49.988,0h0.016v0.007C63.803,0.011,76.298,5.608,85.34,14.652c9.027,9.031,14.619,21.515,14.628,35.303h0.007v0.033v0.04 h-0.007c-0.005,5.557-0.917,10.905-2.594,15.892c-0.281,0.837-0.575,1.641-0.877,2.409v0.007c-1.446,3.66-3.315,7.12-5.547,10.307 l29.082,26.139l0.018,0.016l0.157,0.146l0.011,0.011c1.642,1.563,2.536,3.656,2.649,5.78c0.11,2.1-0.543,4.248-1.979,5.971 l-0.011,0.016l-0.175,0.203l-0.035,0.035l-0.146,0.16l-0.016,0.021c-1.565,1.642-3.654,2.534-5.78,2.646 c-2.097,0.111-4.247-0.54-5.971-1.978l-0.015-0.011l-0.204-0.175l-0.029-0.024L78.761,90.865c-0.88,0.62-1.778,1.209-2.687,1.765 c-1.233,0.755-2.51,1.466-3.813,2.115c-6.699,3.342-14.269,5.222-22.272,5.222v0.007h-0.016v-0.007 c-13.799-0.004-26.296-5.601-35.338-14.645C5.605,76.291,0.016,63.805,0.007,50.021H0v-0.033v-0.016h0.007 c0.004-13.799,5.601-26.296,14.645-35.338C23.683,5.608,36.167,0.016,49.955,0.007V0H49.988L49.988,0z M50.004,11.21v0.007h-0.016 h-0.033V11.21c-10.686,0.007-20.372,4.35-27.384,11.359C15.56,29.578,11.213,39.274,11.21,49.973h0.007v0.016v0.033H11.21 c0.007,10.686,4.347,20.367,11.359,27.381c7.009,7.012,16.705,11.359,27.403,11.361v-0.007h0.016h0.033v0.007 c10.686-0.007,20.368-4.348,27.382-11.359c7.011-7.009,11.358-16.702,11.36-27.4h-0.006v-0.016v-0.033h0.006 c-0.006-10.686-4.35-20.372-11.358-27.384C70.396,15.56,60.703,11.213,50.004,11.21L50.004,11.21z"/></g></svg>

changedetectionio/templates/watch-overview.html

@@ -1,13 +1,14 @@
 {% extends 'base.html' %}
 {% block content %}
 {% from '_helpers.jinja' import render_simple_field, render_field %}
-<script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
-<script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
+{% from '_pagination.jinja' import pagination %}
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
 
 <div class="box">
 
     <form class="pure-form" action="{{ url_for('form_quick_watch_add') }}" method="POST" id="new-watch-form">
-        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
+        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
         <fieldset>
             <legend>Add a new change detection watch</legend>
             <div id="watch-add-wrapper-zone">
@@ -25,26 +26,20 @@
             </div>
 
         </fieldset>
-        <span style="color:#eee; font-size: 80%;"><img alt="Create a shareable link" style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" > Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></span>
+        <span style="color:#eee; font-size: 80%;"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" /> Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></a></span>
     </form>
 
     <form class="pure-form" action="{{ url_for('form_watch_list_checkbox_operations') }}" method="POST" id="watch-list-form">
-    <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
+    <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
     <div id="checkbox-operations">
         <button class="pure-button button-secondary button-xsmall"  name="op" value="pause">Pause</button>
         <button class="pure-button button-secondary button-xsmall"  name="op" value="unpause">UnPause</button>
         <button class="pure-button button-secondary button-xsmall"  name="op" value="mute">Mute</button>
         <button class="pure-button button-secondary button-xsmall"  name="op" value="unmute">UnMute</button>
         <button class="pure-button button-secondary button-xsmall" name="op" value="recheck">Recheck</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="mark-viewed">Mark viewed</button>
         <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default">Use default notification</button>
-        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="clear-history">Clear/reset history</button>
-        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="delete">Delete</button>
+        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242; font-size: 70%" name="op" value="delete">Delete</button>
     </div>
-    {% if watches|length >= pagination.per_page %}
-        {{ pagination.info }}
-    {% endif %}
-    {% if search_q %}<div id="search-result-info">Searching "<strong><i>{{search_q}}</i></strong>"</div>{% endif %}
     <div>
         <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag }}">All</a>
         {% for tag in tags %}
@@ -54,19 +49,18 @@
         {% endfor %}
     </div>
 
-    {% set sort_order = sort_order or 'asc' %}
-    {% set sort_attribute = sort_attribute or 'last_changed'  %}
+    {% set sort_order = request.args.get('order', 'asc') == 'asc' %}
+    {% set sort_attribute = request.args.get('sort', 'last_changed')   %}
     {% set pagination_page = request.args.get('page', 0) %}
 
     <div id="watch-table-wrapper">
-
         <table class="pure-table pure-table-striped watch-table">
             <thead>
             <tr>
-                {% set link_order = "desc" if sort_order  == 'asc' else "asc" %}
-                {% set arrow_span = "" %}
-                <th><input style="vertical-align: middle" type="checkbox" id="check-all" > <a class="{{ 'active '+link_order if sort_attribute == 'date_created' else 'inactive' }}"  href="{{url_for('index', sort='date_created', order=link_order, tag=active_tag)}}"># <span class='arrow {{link_order}}'></span></a></th>
+                <th><input style="vertical-align: middle" type="checkbox" id="check-all"/> #</th>
                 <th></th>
+                {% set link_order = "desc" if sort_order else "asc" %}
+                {% set arrow_span = "" %}
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('index', sort='label', order=link_order, tag=active_tag)}}">Website <span class='arrow {{link_order}}'></span></a></th>
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag)}}">Last Checked <span class='arrow {{link_order}}'></span></a></th>
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
@@ -74,12 +68,13 @@
             </tr>
             </thead>
             <tbody>
-            {% if not watches|length %}
-            <tr>
-                <td colspan="6">No website watches configured, please add a URL in the box above, or <a href="{{ url_for('import_page')}}" >import a list</a>.</td>
-            </tr>
-            {% endif %}
-            {% for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))|pagination_slice(skip=pagination.skip) %}
+
+            {% set sorted_watches = watches|sort(attribute=sort_attribute, reverse=sort_order) %}
+            {% for watch in sorted_watches %}
+
+            {# WIP for pagination, disabled for now
+              {% if not ( loop.index >= 3 and loop.index <=4) %}{% continue %}{% endif %} -->
+             #}
             <tr id="{{ watch.uuid }}"
                 class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }} processor-{{ watch['processor'] }}
                 {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
@@ -87,26 +82,26 @@
                 {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
                 {% if watch.newest_history_key| int > watch.last_viewed and watch.history_n>=2 %}unviewed{% endif %}
                 {% if watch.uuid in queued_uuids %}queued{% endif %}">
-                <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span>{{ loop.index+pagination.skip }}</span></td>
+                <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} "/> <span>{{ loop.index }}</span></td>
                 <td class="inline watch-controls">
                     {% if not watch.paused %}
-                    <a class="state-off" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause" ></a>
+                    <a class="state-off" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause"/></a>
                     {% else %}
-                    <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause" ></a>
+                    <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause"/></a>
                     {% endif %}
-                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute" ></a>
+                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute"/></a>
                 </td>
                 <td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
                     <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
-                    <a class="link-spread" href="{{url_for('form_share_put_watch', uuid=watch.uuid)}}"><img src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" ></a>
+                    <a class="link-spread" href="{{url_for('form_share_put_watch', uuid=watch.uuid)}}"><img class="status-icon"  src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" /></a>
 
                     {% if watch.get_fetch_backend == "html_webdriver"
                          or (  watch.get_fetch_backend == "system" and system_default_fetcher == 'html_webdriver'  )
                     %}
-                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a chrome browser" >
+                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a chrome browser" />
                     {% endif %}
 
-                    {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" >{% endif %}
+                    {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" />{% endif %}
                     {% if watch.last_error is defined and watch.last_error != False %}
                     <div class="fetch-error">{{ watch.last_error }}
 
@@ -128,7 +123,7 @@
                         <div class="ldjson-price-track-offer">Embedded price data detected, follow only price data? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
                         {% endif %}
                         {% if watch['track_ldjson_price_data'] == 'accepted' %}
-                        <span class="tracking-ldjson-price-data" title="Automatically following embedded price information"><img src="{{url_for('static_content', group='images', filename='price-tag-icon.svg')}}"  class="status-icon price-follow-tag-icon" > Price</span>
+                        <span class="tracking-ldjson-price-data" title="Automatically following embedded price information"><img src="{{url_for('static_content', group='images', filename='price-tag-icon.svg')}}"  class="status-icon price-follow-tag-icon"/> Price</span>
                         {% endif %}
                     {% endif %}
 
@@ -140,7 +135,6 @@
                         {% else %}
                             Not yet checked
                         {% endif %}
-                    </span>
                     {% endif %}
 
                     {% if not active_tag %}
@@ -184,7 +178,10 @@
                 <a href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='Generic_Feed-icon.svg')}}" height="15"></a>
             </li>
         </ul>
-        {{ pagination.links }}
+        {# WIP for pagination, disabled for now
+         {{ pagination(sorted_watches,3, pagination_page) }}
+         #}
+
     </div>
     </form>
 </div>

changedetectionio/tests/conftest.py

@@ -14,16 +14,13 @@ global app
 
 def cleanup(datastore_path):
     # Unlink test output files
-    files = [
-        'count.txt',
-        'endpoint-content.txt'
-        'headers.txt',
-        'headers-testtag.txt',
-        'notification.txt',
-        'secret.txt',
-        'url-watches.json',
-        'output.txt',
-    ]
+    files = ['output.txt',
+             'url-watches.json',
+             'secret.txt',
+             'notification.txt',
+             'count.txt',
+             'endpoint-content.txt'
+                 ]
     for file in files:
         try:
             os.unlink("{}/{}".format(datastore_path, file))

changedetectionio/tests/test_jsonpath_jq_selector.py

@@ -3,7 +3,7 @@
 
 import time
 from flask import url_for, escape
-from . util import live_server_setup, wait_for_all_checks
+from . util import live_server_setup
 import pytest
 jq_support = True
 
@@ -64,24 +64,6 @@ and it can also be repeated
         with pytest.raises(html_tools.JSONNotFound) as e_info:
             html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "jq:.id")
 
-
-def test_unittest_inline_extract_body():
-    content = """
-    <html>
-        <head></head>
-        <body>
-            <pre style="word-wrap: break-word; white-space: pre-wrap;">
-                {"testKey": 42}
-            </pre>
-        </body>
-    </html>
-    """
-    from .. import html_tools
-
-    # See that we can find the second <script> one, which is not broken, and matches our filter
-    text = html_tools.extract_json_as_string(content, "json:$.testKey")
-    assert text == '42'
-
 def set_original_ext_response():
     data = """
         [
@@ -454,37 +436,6 @@ def test_ignore_json_order(client, live_server):
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
-def test_correct_header_detect(client, live_server):
-    # Like in https://github.com/dgtlmoon/changedetection.io/pull/1593
-    # Specify extra html that JSON is sometimes wrapped in - when using Browserless/Puppeteer etc
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write('<html><body>{"hello" : 123, "world": 123}')
-
-    # Add our URL to the import page
-    # Check weird casing is cleaned up and detected also
-    test_url = url_for('test_endpoint', content_type="aPPlication/JSon", uppercase_headers=True, _external=True)
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-    wait_for_all_checks(client)
-    res = client.get(url_for("index"))
-
-    # Fixed in #1593
-    assert b'No parsable JSON found in this document' not in res.data
-
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-    assert b'&#34;world&#34;:' in res.data
-    assert res.data.count(b'{') >= 2
-
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
-
 def test_check_jsonpath_ext_filter(client, live_server):
     check_json_ext_filter('json:$[?(@.status==Sold)]', client, live_server)
 

changedetectionio/tests/test_request.py

@@ -1,8 +1,7 @@
 import json
-import os
 import time
 from flask import url_for
-from . util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_UUID_from_client
+from . util import set_original_response, set_modified_response, live_server_setup
 
 def test_setup(live_server):
     live_server_setup(live_server)
@@ -10,12 +9,8 @@ def test_setup(live_server):
 # Hard to just add more live server URLs when one test is already running (I think)
 # So we add our test here (was in a different file)
 def test_headers_in_request(client, live_server):
-    #live_server_setup(live_server)
     # Add our URL to the import page
     test_url = url_for('test_headers', _external=True)
-    if os.getenv('PLAYWRIGHT_DRIVER_URL'):
-        # Because its no longer calling back to localhost but from browserless, set in test-only.yml
-        test_url = test_url.replace('localhost', 'changedet')
 
     # Add the test URL twice, we will check
     res = client.post(
@@ -34,7 +29,7 @@ def test_headers_in_request(client, live_server):
     )
     assert b"1 Imported" in res.data
 
-    wait_for_all_checks(client)
+    time.sleep(3)
     cookie_header = '_ga=GA1.2.1022228332; cookie-preferences=analytics:accepted;'
 
 
@@ -44,7 +39,7 @@ def test_headers_in_request(client, live_server):
         data={
               "url": test_url,
               "tag": "",
-              "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
+              "fetch_backend": "html_requests",
               "headers": "xxx:ooo\ncool:yeah\r\ncookie:"+cookie_header},
         follow_redirects=True
     )
@@ -52,7 +47,7 @@ def test_headers_in_request(client, live_server):
 
 
     # Give the thread time to pick up the first version
-    wait_for_all_checks(client)
+    time.sleep(5)
 
     # The service should echo back the request headers
     res = client.get(
@@ -68,7 +63,7 @@ def test_headers_in_request(client, live_server):
     from html import escape
     assert escape(cookie_header).encode('utf-8') in res.data
 
-    wait_for_all_checks(client)
+    time.sleep(5)
 
     # Re #137 -  Examine the JSON index file, it should have only one set of headers entered
     watches_with_headers = 0
@@ -84,9 +79,6 @@ def test_headers_in_request(client, live_server):
 def test_body_in_request(client, live_server):
     # Add our URL to the import page
     test_url = url_for('test_body', _external=True)
-    if os.getenv('PLAYWRIGHT_DRIVER_URL'):
-        # Because its no longer calling back to localhost but from browserless, set in test-only.yml
-        test_url = test_url.replace('localhost', 'cdio')
 
     res = client.post(
         url_for("import_page"),
@@ -175,9 +167,6 @@ def test_body_in_request(client, live_server):
 def test_method_in_request(client, live_server):
     # Add our URL to the import page
     test_url = url_for('test_method', _external=True)
-    if os.getenv('PLAYWRIGHT_DRIVER_URL'):
-        # Because its no longer calling back to localhost but from browserless, set in test-only.yml
-        test_url = test_url.replace('localhost', 'cdio')
 
     # Add the test URL twice, we will check
     res = client.post(
@@ -245,76 +234,3 @@ def test_method_in_request(client, live_server):
     # Should be only one with method set to PATCH
     assert watches_with_method == 1
 
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
-
-def test_headers_textfile_in_request(client, live_server):
-    #live_server_setup(live_server)
-    # Add our URL to the import page
-    test_url = url_for('test_headers', _external=True)
-    if os.getenv('PLAYWRIGHT_DRIVER_URL'):
-        # Because its no longer calling back to localhost but from browserless, set in test-only.yml
-        test_url = test_url.replace('localhost', 'cdio')
-
-    print ("TEST URL IS ",test_url)
-    # Add the test URL twice, we will check
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-
-    time.sleep(1)
-
-
-    # Add some headers to a request
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={
-              "url": test_url,
-              "tag": "testtag",
-              "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
-              "headers": "xxx:ooo\ncool:yeah\r\n"},
-        follow_redirects=True
-    )
-    assert b"Updated watch." in res.data
-    wait_for_all_checks(client)
-
-    with open('test-datastore/headers-testtag.txt', 'w') as f:
-        f.write("tag-header: test")
-
-    with open('test-datastore/headers.txt', 'w') as f:
-        f.write("global-header: nice\r\nnext-global-header: nice")
-
-    with open('test-datastore/'+extract_UUID_from_client(client)+'/headers.txt', 'w') as f:
-        f.write("watch-header: nice")
-
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
-    wait_for_all_checks(client)
-
-    res = client.get(url_for("edit_page", uuid="first"))
-    assert b"Extra headers file found and will be added to this watch" in res.data
-
-    # Not needed anymore
-    os.unlink('test-datastore/headers.txt')
-    os.unlink('test-datastore/headers-testtag.txt')
-    os.unlink('test-datastore/'+extract_UUID_from_client(client)+'/headers.txt')
-    # The service should echo back the request verb
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-
-    assert b"Global-Header:nice" in res.data
-    assert b"Next-Global-Header:nice" in res.data
-    assert b"Xxx:ooo" in res.data
-    assert b"Watch-Header:nice" in res.data
-    assert b"Tag-Header:test" in res.data
-
-
-    #unlink headers.txt on start/stop
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data

changedetectionio/tests/test_search.py

@@ -1,74 +0,0 @@
-from flask import url_for
-from .util import set_original_response, set_modified_response, live_server_setup
-import time
-
-def test_setup(live_server):
-    live_server_setup(live_server)
-
-def test_basic_search(client, live_server):
-    #live_server_setup(live_server)
-
-    urls = ['https://localhost:12300?first-result=1',
-            'https://localhost:5000?second-result=1'
-            ]
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": "\r\n".join(urls)},
-        follow_redirects=True
-    )
-
-    assert b"2 Imported" in res.data
-
-    # By URL
-    res = client.get(url_for("index") + "?q=first-res")
-    assert urls[0].encode('utf-8') in res.data
-    assert urls[1].encode('utf-8') not in res.data
-
-    # By Title
-
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={"title": "xxx-title", "url": urls[0], "tag": "", "headers": "", 'fetch_backend': "html_requests"},
-        follow_redirects=True
-    )
-    assert b"Updated watch." in res.data
-
-    res = client.get(url_for("index") + "?q=xxx-title")
-    assert urls[0].encode('utf-8') in res.data
-    assert urls[1].encode('utf-8') not in res.data
-
-
-def test_search_in_tag_limit(client, live_server):
-    #live_server_setup(live_server)
-
-    urls = ['https://localhost:12300?first-result=1 tag-one',
-            'https://localhost:5000?second-result=1 tag-two'
-            ]
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": "\r\n".join(urls)},
-        follow_redirects=True
-    )
-
-    assert b"2 Imported" in res.data
-
-    # By URL
-
-    res = client.get(url_for("index") + "?q=first-res")
-    # Split because of the import tag separation
-    assert urls[0].split(' ')[0].encode('utf-8') in res.data, urls[0].encode('utf-8')
-    assert urls[1].split(' ')[0].encode('utf-8') not in res.data, urls[0].encode('utf-8')
-
-    # By Title
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={"title": "xxx-title", "url": urls[0].split(' ')[0], "tag": urls[0].split(' ')[1], "headers": "",
-              'fetch_backend': "html_requests"},
-        follow_redirects=True
-    )
-    assert b"Updated watch." in res.data
-
-    res = client.get(url_for("index") + "?q=xxx-title")
-    assert urls[0].split(' ')[0].encode('utf-8') in res.data, urls[0].encode('utf-8')
-    assert urls[1].split(' ')[0].encode('utf-8') not in res.data, urls[0].encode('utf-8')
-

changedetectionio/tests/util.py

@@ -119,26 +119,16 @@ def live_server_setup(live_server):
         status_code = request.args.get('status_code')
         content = request.args.get('content') or None
 
-        # Used to just try to break the header detection
-        uppercase_headers = request.args.get('uppercase_headers')
-
         try:
             if content is not None:
                 resp = make_response(content, status_code)
-                if uppercase_headers:
-                    ctype=ctype.upper()
-                    resp.headers['CONTENT-TYPE'] = ctype if ctype else 'text/html'
-                else:
-                    resp.headers['Content-Type'] = ctype if ctype else 'text/html'
+                resp.headers['Content-Type'] = ctype if ctype else 'text/html'
                 return resp
 
             # Tried using a global var here but didn't seem to work, so reading from a file instead.
             with open("test-datastore/endpoint-content.txt", "r") as f:
                 resp = make_response(f.read(), status_code)
-                if uppercase_headers:
-                    resp.headers['CONTENT-TYPE'] = ctype if ctype else 'text/html'
-                else:
-                    resp.headers['Content-Type'] = ctype if ctype else 'text/html'
+                resp.headers['Content-Type'] = ctype if ctype else 'text/html'
                 return resp
         except FileNotFoundError:
             return make_response('', status_code)

changedetectionio/update_worker.py

@@ -3,9 +3,8 @@ import threading
 import queue
 import time
 
-from changedetectionio import content_fetcher
 from .processors.text_json_diff import FilterNotFoundInResponse
-from .processors.restock_diff import UnableToExtractRestockData
+from .fetchers import exceptions
 
 # A single update worker
 #
@@ -190,6 +189,7 @@ class update_worker(threading.Thread):
                         processor = self.datastore.data['watching'][uuid].get('processor','text_json_diff')
 
                         # @todo some way to switch by name
+                        update_handler = None
                         if processor == 'restock_diff':
                             update_handler = restock_diff.perform_site_check(datastore=self.datastore)
                         else:
@@ -205,7 +205,7 @@ class update_worker(threading.Thread):
                     except PermissionError as e:
                         self.app.logger.error("File permission error updating", uuid, str(e))
                         process_changedetection_results = False
-                    except content_fetcher.ReplyWithContentButNoText as e:
+                    except exceptions.ReplyWithContentButNoText as e:
                         # Totally fine, it's by choice - just continue on, nothing more to care about
                         # Page had elements/content but no renderable text
                         # Backend (not filters) gave zero output
@@ -214,7 +214,7 @@ class update_worker(threading.Thread):
                             self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot)
                         process_changedetection_results = False
 
-                    except content_fetcher.Non200ErrorCodeReceived as e:
+                    except exceptions.Non200ErrorCodeReceived as e:
                         if e.status_code == 403:
                             err_text = "Error - 403 (Access denied) received"
                         elif e.status_code == 404:
@@ -238,7 +238,7 @@ class update_worker(threading.Thread):
                         if not self.datastore.data['watching'].get(uuid):
                             continue
 
-                        err_text = "Warning, no filters were found, no change detection ran - Did the page change layout? update your Visual Filter if necessary."
+                        err_text = "Warning, no filters were found, no change detection ran."
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
 
                         # Only when enabled, send the notification
@@ -258,13 +258,12 @@ class update_worker(threading.Thread):
 
                         process_changedetection_results = False
 
-                    except content_fetcher.checksumFromPreviousCheckWasTheSame as e:
+                    except exceptions.checksumFromPreviousCheckWasTheSame as e:
                         # Yes fine, so nothing todo, don't continue to process.
                         process_changedetection_results = False
                         changed_detected = False
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': False})
 
-                    except content_fetcher.BrowserStepsStepTimout as e:
+                    except exceptions.BrowserStepsStepTimout as e:
 
                         if not self.datastore.data['watching'].get(uuid):
                             continue
@@ -289,25 +288,25 @@ class update_worker(threading.Thread):
 
                         process_changedetection_results = False
 
-                    except content_fetcher.EmptyReply as e:
+                    except exceptions.EmptyReply as e:
                         # Some kind of custom to-str handler in the exception handler that does this?
                         err_text = "EmptyReply - try increasing 'Wait seconds before extracting text', Status Code {}".format(e.status_code)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetcher.ScreenshotUnavailable as e:
+                    except exceptions.ScreenshotUnavailable as e:
                         err_text = "Screenshot unavailable, page did not render fully in the expected time - try increasing 'Wait seconds before extracting text'"
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetcher.JSActionExceptions as e:
+                    except exceptions.JSActionExceptions as e:
                         err_text = "Error running JS Actions - Page request - "+e.message
                         if e.screenshot:
                             self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot, as_error=True)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetcher.PageUnloadable as e:
+                    except exceptions.PageUnloadable as e:
                         err_text = "Page request from server didnt respond correctly"
                         if e.message:
                             err_text = "{} - {}".format(err_text, e.message)
@@ -316,13 +315,7 @@ class update_worker(threading.Thread):
                             self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot, as_error=True)
 
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
-                                                                           'last_check_status': e.status_code,
-                                                                           'has_ldjson_price_data': None})
-                        process_changedetection_results = False
-                    except UnableToExtractRestockData as e:
-                        # Usually when fetcher.instock_data returns empty
-                        self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': f"Unable to extract restock data for this page unfortunately. (Got code {e.status_code} from server)"})
+                                                                           'last_check_status': e.status_code})
                         process_changedetection_results = False
                     except Exception as e:
                         self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))

requirements.txt

@@ -2,7 +2,6 @@ eventlet>=0.31.0
 feedgen~=0.9
 flask-compress
 flask-login~=0.5
-flask-paginate
 flask_expects_json~=1.7
 flask_restful
 flask_wtf