tweak test

Co-authored-by: bwees <branonwees@gmail.com>

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,9 +1,9 @@
 ---
 name: Bug report
-about: Create a report to help us improve
+about: Create a bug report, if you don't follow this template, your report will be DELETED
 title: ''
-labels: ''
-assignees: ''
+labels: 'triage'
+assignees: 'dgtlmoon'
 
 ---
 
@@ -11,15 +11,18 @@ assignees: ''
 A clear and concise description of what the bug is.
 
 **Version**
-In the top right area: 0....
+*Exact version* in the top right area: 0....
 
 **To Reproduce**
+
 Steps to reproduce the behavior:
 1. Go to '...'
 2. Click on '....'
 3. Scroll down to '....'
 4. See error
 
+! ALWAYS INCLUDE AN EXAMPLE URL WHERE IT IS POSSIBLE TO RE-CREATE THE ISSUE - USE THE 'SHARE WATCH' FEATURE AND PASTE IN THE SHARE-LINK!
+
 **Expected behavior**
 A clear and concise description of what you expected to happen.
 

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,8 +1,8 @@
 ---
 name: Feature request
 about: Suggest an idea for this project
-title: ''
-labels: ''
+title: '[feature]'
+labels: 'enhancement'
 assignees: ''
 
 ---

.github/workflows/containers.yml

@@ -85,8 +85,8 @@ jobs:
           version: latest
           driver-opts: image=moby/buildkit:master
 
-      # master always builds :latest
-      - name: Build and push :latest
+      # master branch -> :dev container tag
+      - name: Build and push :dev
         id: docker_build
         if: ${{ github.ref }} == "refs/heads/master"
         uses: docker/build-push-action@v2
@@ -95,12 +95,12 @@ jobs:
           file: ./Dockerfile
           push: true
           tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest,ghcr.io/${{ github.repository }}:latest
+            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
 
-      # A new tagged release is required, which builds :tag
+      # A new tagged release is required, which builds :tag and :latest
       - name: Build and push :tag
         id: docker_build_tag_release
         if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
@@ -110,7 +110,10 @@ jobs:
           file: ./Dockerfile
           push: true
           tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:${{ github.event.release.tag_name }},ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
+            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:${{ github.event.release.tag_name }}
+            ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
+            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest
+            ghcr.io/dgtlmoon/changedetection.io:latest
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
@@ -125,5 +128,3 @@ jobs:
           key: ${{ runner.os }}-buildx-${{ github.sha }}
           restore-keys: |
             ${{ runner.os }}-buildx-
-
-

.gitignore

@@ -8,5 +8,6 @@ __pycache__
 build
 dist
 venv
+test-datastore
 *.egg-info*
 .vscode/settings.json

MANIFEST.in

@@ -1,5 +1,7 @@
+recursive-include changedetectionio/api *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/static *
+recursive-include changedetectionio/model *
 include changedetection.py
 global-exclude *.pyc
 global-exclude node_modules

README-pip.md

@@ -16,6 +16,13 @@ Live your data-life *pro-actively* instead of *re-actively*, do not rely on mani
 
 <img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />
 
+
+**Get your own private instance now! Let us host it for you!**
+
+[**Try our $6.99/month subscription - unlimited checks, watches and notifications!**](https://lemonade.changedetection.io/start), choose from different geographical locations, let us handle everything for you. 
+
+
+
 #### Example use cases
 
 Know when ...
@@ -58,14 +65,3 @@ Then visit http://127.0.0.1:5000 , You should now be able to access the UI.
 
 See https://github.com/dgtlmoon/changedetection.io for more information.
 
-
-
-### Support us
-
-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.
-
-Please support us, even small amounts help a LOT.
-
-BTC `1PLFN327GyUarpJd7nVe7Reqg9qHx5frNn`
-
-<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/btc-support.png" style="max-width:50%;" alt="Support us!"  />

README.md

@@ -3,16 +3,16 @@
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
-## Self-Hosted, Open Source, Change Monitoring of Web Pages
+## Web Site Change Detection, Monitoring and Notification - Self-Hosted or SaaS.
 
-_Know when web pages change! Stay ontop of new information!_ 
+_Know when web pages change! Stay ontop of new information! get notifications when important website content changes_ 
 
 Live your data-life *pro-actively* instead of *re-actively*.
 
 Free, Open-source web page monitoring, notification and change detection. Don't have time? [**Try our $6.99/month subscription - unlimited checks and watches!**](https://lemonade.changedetection.io/start)
 
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/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)
+[<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)
 
 
 **Get your own private instance now! Let us host it for you!**
@@ -33,6 +33,7 @@ Free, Open-source web page monitoring, notification and change detection. Don't
 - New software releases, security advisories when you're not on their mailing list.
 - Festivals with changes
 - Realestate listing changes
+- Know when your favourite whiskey is on sale, or other special deals are announced before anyone else
 - COVID related news from government websites
 - University/organisation news from their website
 - Detect and monitor changes in JSON API responses 
@@ -48,26 +49,37 @@ _Need an actual Chrome runner with Javascript support? We support fetching via W
 
 ## Screenshots
 
-Examining differences in content.
+### Examine differences in content.
 
-<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/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 " />
+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 " />
 
 Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
 
+### Filter by elements using the Visual Selector tool.
+
+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 " />
 
 ## Installation
 
 ### Docker
 
 With Docker composer, just clone this repository and..
+
 ```bash
 $ docker-compose up -d
 ```
+
 Docker standalone
 ```bash
 $ docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/datastore --name changedetection.io dgtlmoon/changedetection.io
 ```
 
+`:latest` tag is our latest stable release, `:dev` tag is our bleeding edge `master` branch.
+
 ### Windows
 
 See the install instructions at the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Microsoft-Windows
@@ -107,7 +119,7 @@ See the wiki for more information https://github.com/dgtlmoon/changedetection.io
 ## Filters
 XPath, JSONPath 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:math and re:replace.)
+(We support LXML `re:test`, `re:math` and `re:replace`.)
 
 ## Notifications
 
@@ -129,7 +141,7 @@ Just some examples
  
 <a href="https://github.com/caronc/apprise#popular-notification-services">And everything else in this list!</a>
 
-<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/screenshot-notifications.png" style="max-width:100%;" alt="Self-hosted web page change monitoring notifications"  title="Self-hosted web page change monitoring notifications"  />
+<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-notifications.png" style="max-width:100%;" alt="Self-hosted web page change monitoring notifications"  title="Self-hosted web page change monitoring notifications"  />
 
 Now you can also customise your notification content!
 
@@ -137,11 +149,11 @@ Now you can also customise your notification content!
 
 Detect changes and monitor data in JSON API's by using the built-in JSONPath selectors as a filter / selector.
 
-![image](https://user-images.githubusercontent.com/275001/125165842-0ce01980-e1dc-11eb-9e73-d8137dd162dc.png)
+![image](https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/json-filter-field-example.png)
 
 This will re-parse the JSON and apply formatting to the text, making it super easy to monitor and detect changes in JSON API results
 
-![image](https://user-images.githubusercontent.com/275001/125165995-d9ea5580-e1dc-11eb-8030-f0deced2661a.png)
+![image](https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/json-diff-example.png)
 
 ### Parse JSON embedded in HTML!
 
@@ -177,7 +189,7 @@ Or directly donate an amount PayPal [![Donate](https://img.shields.io/badge/Dona
 
 Or BTC `1PLFN327GyUarpJd7nVe7Reqg9qHx5frNn`
 
-<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/btc-support.png" style="max-width:50%;" alt="Support us!"  />
+<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/btc-support.png" style="max-width:50%;" alt="Support us!"  />
 
 ## Commercial Support
 

changedetectionio/__init__.py

@@ -20,6 +20,7 @@ from copy import deepcopy
 from threading import Event
 
 import flask_login
+import logging
 import pytz
 import timeago
 from feedgen.feed import FeedGenerator
@@ -36,11 +37,14 @@ from flask import (
     url_for,
 )
 from flask_login import login_required
+from flask_restful import abort, Api
+
 from flask_wtf import CSRFProtect
 
 from changedetectionio import html_tools
+from changedetectionio.api import api_v1
 
-__version__ = '0.39.12'
+__version__ = '0.39.16'
 
 datastore = None
 
@@ -78,6 +82,8 @@ csrf.init_app(app)
 
 notification_debug_log=[]
 
+watch_api = Api(app, decorators=[csrf.exempt])
+
 def init_app_secret(datastore_path):
     secret = ""
 
@@ -102,7 +108,7 @@ def _jinja2_filter_datetime(watch_obj, format="%Y-%m-%d %H:%M:%S"):
     # Worker thread tells us which UUID it is currently processing.
     for t in running_update_threads:
         if t.current_uuid == watch_obj['uuid']:
-            return "Checking now.."
+            return '<span class="loader"></span><span> Checking now</span>'
 
     if watch_obj['last_checked'] == 0:
         return 'Not yet'
@@ -173,12 +179,35 @@ def changedetection_app(config=None, datastore_o=None):
     global datastore
     datastore = datastore_o
 
+    # so far just for read-only via tests, but this will be moved eventually to be the main source
+    # (instead of the global var)
+    app.config['DATASTORE']=datastore_o
+
     #app.config.update(config or {})
 
     login_manager = flask_login.LoginManager(app)
     login_manager.login_view = 'login'
     app.secret_key = init_app_secret(config['datastore_path'])
 
+
+    watch_api.add_resource(api_v1.WatchSingleHistory,
+                           '/api/v1/watch/<string:uuid>/history/<string:timestamp>',
+                           resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
+
+    watch_api.add_resource(api_v1.WatchHistory,
+                           '/api/v1/watch/<string:uuid>/history',
+                           resource_class_kwargs={'datastore': datastore})
+
+    watch_api.add_resource(api_v1.CreateWatch, '/api/v1/watch',
+                           resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
+
+    watch_api.add_resource(api_v1.Watch, '/api/v1/watch/<string:uuid>',
+                           resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
+
+
+
+
+
     # Setup cors headers to allow all domains
     # https://flask-cors.readthedocs.io/en/latest/
     #    CORS(app)
@@ -269,7 +298,7 @@ def changedetection_app(config=None, datastore_o=None):
         # Sort by last_changed and add the uuid which is usually the key..
         sorted_watches = []
 
-        # @todo needs a .itemsWithTag() or something
+        # @todo needs a .itemsWithTag() or something - then we can use that in Jinaj2 and throw this away
         for uuid, watch in datastore.data['watching'].items():
 
             if limit_tag != None:
@@ -293,25 +322,19 @@ def changedetection_app(config=None, datastore_o=None):
 
         for watch in sorted_watches:
 
-            dates = list(watch['history'].keys())
+            dates = list(watch.history.keys())
             # Re #521 - Don't bother processing this one if theres less than 2 snapshots, means we never had a change detected.
             if len(dates) < 2:
                 continue
 
-            # Convert to int, sort and back to str again
-            # @todo replace datastore getter that does this automatically
-            dates = [int(i) for i in dates]
-            dates.sort(reverse=True)
-            dates = [str(i) for i in dates]
-            prev_fname = watch['history'][dates[1]]
+            prev_fname = watch.history[dates[-2]]
 
-            if not watch['viewed']:
+            if not watch.viewed:
                 # Re #239 - GUID needs to be individual for each event
                 # @todo In the future make this a configurable link back (see work on BASE_URL https://github.com/dgtlmoon/changedetection.io/pull/228)
                 guid = "{}/{}".format(watch['uuid'], watch['last_changed'])
                 fe = fg.add_entry()
 
-
                 # Include a link to the diff page, they will have to login here to see if password protection is enabled.
                 # Description is the page you watch, link takes you to the diff JS UI page
                 base_url = datastore.data['settings']['application']['base_url']
@@ -326,18 +349,19 @@ def changedetection_app(config=None, datastore_o=None):
 
                 watch_title = watch.get('title') if watch.get('title') else watch.get('url')
                 fe.title(title=watch_title)
-                latest_fname = watch['history'][dates[0]]
+                latest_fname = watch.history[dates[-1]]
 
                 html_diff = diff.render_diff(prev_fname, latest_fname, include_equal=False, line_feed_sep="</br>")
-                fe.description(description="<![CDATA[<html><body><h4>{}</h4>{}</body></html>".format(watch_title, html_diff))
+                fe.content(content="<html><body><h4>{}</h4>{}</body></html>".format(watch_title, html_diff),
+                           type='CDATA')
 
                 fe.guid(guid, permalink=False)
-                dt = datetime.datetime.fromtimestamp(int(watch['newest_history_key']))
+                dt = datetime.datetime.fromtimestamp(int(watch.newest_history_key))
                 dt = dt.replace(tzinfo=pytz.UTC)
                 fe.pubDate(dt)
 
         response = make_response(fg.rss_str())
-        response.headers.set('Content-Type', 'application/rss+xml')
+        response.headers.set('Content-Type', 'application/rss+xml;charset=utf-8')
         return response
 
     @app.route("/", methods=['GET'])
@@ -367,6 +391,8 @@ def changedetection_app(config=None, datastore_o=None):
 
             if limit_tag != None:
                 # Support for comma separated list of tags.
+                if watch['tag'] is None:
+                    continue
                 for tag_in_watch in watch['tag'].split(','):
                     tag_in_watch = tag_in_watch.strip()
                     if tag_in_watch == limit_tag:
@@ -377,8 +403,6 @@ def changedetection_app(config=None, datastore_o=None):
                 watch['uuid'] = uuid
                 sorted_watches.append(watch)
 
-        sorted_watches.sort(key=lambda x: x['last_changed'], reverse=True)
-
         existing_tags = datastore.get_all_tags()
 
         form = forms.quickWatchForm(request.form)
@@ -389,11 +413,13 @@ def changedetection_app(config=None, datastore_o=None):
                                  tags=existing_tags,
                                  active_tag=limit_tag,
                                  app_rss_token=datastore.data['settings']['application']['rss_access_token'],
-                                 has_unviewed=datastore.data['has_unviewed'],
+                                 has_unviewed=datastore.has_unviewed,
                                  # Don't link to hosting when we're on the hosting environment
                                  hosted_sticky=os.getenv("SALTED_PASS", False) == False,
                                  guid=datastore.data['app_guid'],
                                  queued_uuids=update_q.queue)
+
+
         if session.get('share-link'):
             del(session['share-link'])
         return output
@@ -405,7 +431,9 @@ def changedetection_app(config=None, datastore_o=None):
     def ajax_callback_send_notification_test():
 
         import apprise
-        apobj = apprise.Apprise()
+        from .apprise_asset import asset
+        apobj = apprise.Apprise(asset=asset)
+
 
         # validate URLS
         if not len(request.form['notification_urls'].strip()):
@@ -430,25 +458,39 @@ def changedetection_app(config=None, datastore_o=None):
 
         return 'OK'
 
-    @app.route("/scrub", methods=['GET', 'POST'])
+
+    @app.route("/clear_history/<string:uuid>", methods=['GET'])
     @login_required
-    def scrub_page():
+    def clear_watch_history(uuid):
+        try:
+            datastore.clear_watch_history(uuid)
+        except KeyError:
+            flash('Watch not found', 'error')
+        else:
+            flash("Cleared snapshot history for watch {}".format(uuid))
+
+        return redirect(url_for('index'))
+
+    @app.route("/clear_history", methods=['GET', 'POST'])
+    @login_required
+    def clear_all_history():
 
         if request.method == 'POST':
             confirmtext = request.form.get('confirmtext')
 
-            if confirmtext == 'scrub':
+            if confirmtext == 'clear':
                 changes_removed = 0
                 for uuid in datastore.data['watching'].keys():
-                    datastore.scrub_watch(uuid)
+                    datastore.clear_watch_history(uuid)
+                    #TODO: KeyError not checked, as it is above
 
-                flash("Cleared all snapshot history")
+                flash("Cleared snapshot history for all watches")
             else:
                 flash('Incorrect confirmation text.', 'error')
 
             return redirect(url_for('index'))
 
-        output = render_template("scrub.html")
+        output = render_template("clear_all_history.html")
         return output
 
 
@@ -465,10 +507,10 @@ def changedetection_app(config=None, datastore_o=None):
 
         # 0 means that theres only one, so that there should be no 'unviewed' history available
         if newest_history_key == 0:
-            newest_history_key = list(datastore.data['watching'][uuid]['history'].keys())[0]
+            newest_history_key = list(datastore.data['watching'][uuid].history.keys())[0]
 
         if newest_history_key:
-            with open(datastore.data['watching'][uuid]['history'][newest_history_key],
+            with open(datastore.data['watching'][uuid].history[newest_history_key],
                       encoding='utf-8') as file:
                 raw_content = file.read()
 
@@ -518,10 +560,22 @@ def changedetection_app(config=None, datastore_o=None):
         if all(value == 0 or value == None for value in datastore.data['watching'][uuid]['time_between_check'].values()):
             default['time_between_check'] = deepcopy(datastore.data['settings']['requests']['time_between_check'])
 
-        form = forms.watchForm(formdata=request.form if request.method == 'POST' else None,
-                                        data=default
-                                        )
+        # Defaults for proxy choice
+        if datastore.proxy_list is not None:  # When enabled
+            # Radio needs '' not None, or incase that the chosen one no longer exists
+            if default['proxy'] is None or not any(default['proxy'] in tup for tup in datastore.proxy_list):
+                default['proxy'] = ''
 
+        # proxy_override set to the json/text list of the items
+        form = forms.watchForm(formdata=request.form if request.method == 'POST' else None,
+                               data=default,
+                               )
+
+        if datastore.proxy_list is None:
+            # @todo - Couldn't get setattr() etc dynamic addition working, so remove it instead
+            del form.proxy
+        else:
+            form.proxy.choices = [('', 'Default')] + datastore.proxy_list
 
         if request.method == 'POST' and form.validate():
             extra_update_obj = {}
@@ -550,14 +604,18 @@ def changedetection_app(config=None, datastore_o=None):
 
             # Reset the previous_md5 so we process a new snapshot including stripping ignore text.
             if form_ignore_text:
-                if len(datastore.data['watching'][uuid]['history']):
+                if len(datastore.data['watching'][uuid].history):
                     extra_update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
 
             # Reset the previous_md5 so we process a new snapshot including stripping ignore text.
             if form.css_filter.data.strip() != datastore.data['watching'][uuid]['css_filter']:
-                if len(datastore.data['watching'][uuid]['history']):
+                if len(datastore.data['watching'][uuid].history):
                     extra_update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
 
+            # Be sure proxy value is None
+            if datastore.proxy_list is not None and form.data['proxy'] == '':
+                extra_update_obj['proxy'] = None
+
             datastore.data['watching'][uuid].update(form.data)
             datastore.data['watching'][uuid].update(extra_update_obj)
 
@@ -584,14 +642,23 @@ def changedetection_app(config=None, datastore_o=None):
             if request.method == 'POST' and not form.validate():
                 flash("An error occurred, please see below.", "error")
 
+            visualselector_data_is_ready = datastore.visualselector_data_is_ready(uuid)
+
+            # Only works reliably with Playwright
+            visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and default['fetch_backend'] == 'html_webdriver'
+
 
             output = render_template("edit.html",
                                      uuid=uuid,
                                      watch=datastore.data['watching'][uuid],
                                      form=form,
                                      has_empty_checktime=using_default_check_time,
+                                     using_global_webdriver_wait=default['webdriver_delay'] is None,
                                      current_base_url=datastore.data['settings']['application']['base_url'],
-                                     emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False)
+                                     emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
+                                     visualselector_data_is_ready=visualselector_data_is_ready,
+                                     visualselector_enabled=visualselector_enabled,
+                                     playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False)
                                      )
 
         return output
@@ -601,10 +668,28 @@ def changedetection_app(config=None, datastore_o=None):
     def settings_page():
         from changedetectionio import content_fetcher, forms
 
+        default = deepcopy(datastore.data['settings'])
+        if datastore.proxy_list is not None:
+            # When enabled
+            system_proxy = datastore.data['settings']['requests']['proxy']
+            # In the case it doesnt exist anymore
+            if not any([system_proxy in tup for tup in datastore.proxy_list]):
+                system_proxy = None
+
+            default['requests']['proxy'] = system_proxy if system_proxy is not None else datastore.proxy_list[0][0]
+            # Used by the form handler to keep or remove the proxy settings
+            default['proxy_list'] = datastore.proxy_list
+
+
         # Don't use form.data on POST so that it doesnt overrid the checkbox status from the POST status
         form = forms.globalSettingsForm(formdata=request.form if request.method == 'POST' else None,
-                                        data=datastore.data['settings']
+                                        data=default
                                         )
+        if datastore.proxy_list is None:
+            # @todo - Couldn't get setattr() etc dynamic addition working, so remove it instead
+            del form.requests.form.proxy
+        else:
+            form.requests.form.proxy.choices = datastore.proxy_list
 
         if request.method == 'POST':
             # Password unset is a GET, but we can lock the session to a salted env password to always need the password
@@ -637,6 +722,7 @@ def changedetection_app(config=None, datastore_o=None):
                                  form=form,
                                  current_base_url = datastore.data['settings']['application']['base_url'],
                                  hide_remove_pass=os.getenv("SALTED_PASS", False),
+                                 api_key=datastore.data['settings']['application'].get('api_access_token'),
                                  emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False))
 
         return output
@@ -644,57 +730,49 @@ def changedetection_app(config=None, datastore_o=None):
     @app.route("/import", methods=['GET', "POST"])
     @login_required
     def import_page():
-        import validators
         remaining_urls = []
-
-        good = 0
-
         if request.method == 'POST':
-            now=time.time()
-            urls = request.values.get('urls').split("\n")
+            from .importer import import_url_list, import_distill_io_json
 
-            if (len(urls) > 5000):
-                flash("Importing 5,000 of the first URLs from your list, the rest can be imported again.")
+            # URL List import
+            if request.values.get('urls') and len(request.values.get('urls').strip()):
+                # Import and push into the queue for immediate update check
+                importer = import_url_list()
+                importer.run(data=request.values.get('urls'), flash=flash, datastore=datastore)
+                for uuid in importer.new_uuids:
+                    update_q.put(uuid)
 
-            for url in urls:
-                url = url.strip()
-                url, *tags = url.split(" ")
-                # Flask wtform validators wont work with basic auth, use validators package
-                # Up to 5000 per batch so we dont flood the server
-                if len(url) and validators.url(url.replace('source:', '')) and good < 5000:
-                    new_uuid = datastore.add_watch(url=url.strip(), tag=" ".join(tags), write_to_disk_now=False)
-                    if new_uuid:
-                        # Straight into the queue.
-                        update_q.put(new_uuid)
-                        good += 1
-                        continue
+                if len(importer.remaining_data) == 0:
+                    return redirect(url_for('index'))
+                else:
+                    remaining_urls = importer.remaining_data
 
-                if len(url.strip()):
-                    remaining_urls.append(url)
+            # Distill.io import
+            if request.values.get('distill-io') and len(request.values.get('distill-io').strip()):
+                # Import and push into the queue for immediate update check
+                d_importer = import_distill_io_json()
+                d_importer.run(data=request.values.get('distill-io'), flash=flash, datastore=datastore)
+                for uuid in d_importer.new_uuids:
+                    update_q.put(uuid)
 
-            flash("{} Imported in {:.2f}s, {} Skipped.".format(good, time.time()-now,len(remaining_urls)))
-            datastore.needs_write = True
 
-            if len(remaining_urls) == 0:
-                # Looking good, redirect to index.
-                return redirect(url_for('index'))
 
         # Could be some remaining, or we could be on GET
         output = render_template("import.html",
-                                 remaining="\n".join(remaining_urls)
+                                 import_url_list_remaining="\n".join(remaining_urls),
+                                 original_distill_json=''
                                  )
         return output
 
     # Clear all statuses, so we do not see the 'unviewed' class
-    @app.route("/api/mark-all-viewed", methods=['GET'])
+    @app.route("/form/mark-all-viewed", methods=['GET'])
     @login_required
     def mark_all_viewed():
 
         # Save the current newest history as the most recently viewed
         for watch_uuid, watch in datastore.data['watching'].items():
-            datastore.set_last_viewed(watch_uuid, watch['newest_history_key'])
+            datastore.set_last_viewed(watch_uuid, int(time.time()))
 
-        flash("Cleared all statuses.")
         return redirect(url_for('index'))
 
     @app.route("/diff/<string:uuid>", methods=['GET'])
@@ -712,20 +790,17 @@ def changedetection_app(config=None, datastore_o=None):
             flash("No history found for the specified link, bad link?", "error")
             return redirect(url_for('index'))
 
-        dates = list(watch['history'].keys())
-        # Convert to int, sort and back to str again
-        # @todo replace datastore getter that does this automatically
-        dates = [int(i) for i in dates]
-        dates.sort(reverse=True)
-        dates = [str(i) for i in dates]
+        history = watch.history
+        dates = list(history.keys())
 
         if len(dates) < 2:
             flash("Not enough saved change detection snapshots to produce a report.", "error")
             return redirect(url_for('index'))
 
         # Save the current newest history as the most recently viewed
-        datastore.set_last_viewed(uuid, dates[0])
-        newest_file = watch['history'][dates[0]]
+        datastore.set_last_viewed(uuid, time.time())
+
+        newest_file = history[dates[-1]]
 
         try:
             with open(newest_file, 'r') as f:
@@ -735,10 +810,10 @@ def changedetection_app(config=None, datastore_o=None):
 
         previous_version = request.args.get('previous_version')
         try:
-            previous_file = watch['history'][previous_version]
+            previous_file = history[previous_version]
         except KeyError:
             # Not present, use a default value, the second one in the sorted list.
-            previous_file = watch['history'][dates[1]]
+            previous_file = history[dates[-2]]
 
         try:
             with open(previous_file, 'r') as f:
@@ -749,18 +824,25 @@ def changedetection_app(config=None, datastore_o=None):
 
         screenshot_url = datastore.get_screenshot(uuid)
 
-        output = render_template("diff.html", watch_a=watch,
+        system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
+
+        is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
+                    watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
+
+        output = render_template("diff.html",
+                                 watch_a=watch,
                                  newest=newest_version_file_contents,
                                  previous=previous_version_file_contents,
                                  extra_stylesheets=extra_stylesheets,
-                                 versions=dates[1:],
+                                 versions=dates[:-1], # All except current/last
                                  uuid=uuid,
-                                 newest_version_timestamp=dates[0],
+                                 newest_version_timestamp=dates[-1],
                                  current_previous_version=str(previous_version),
                                  current_diff_url=watch['url'],
                                  extra_title=" - Diff - {}".format(watch['title'] if watch['title'] else watch['url']),
                                  left_sticky=True,
-                                 screenshot=screenshot_url)
+                                 screenshot=screenshot_url,
+                                 is_html_webdriver=is_html_webdriver)
 
         return output
 
@@ -775,6 +857,12 @@ def changedetection_app(config=None, datastore_o=None):
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
 
+        # Normally you would never reach this, because the 'preview' button is not available when there's no history
+        # However they may try to clear snapshots and reload the page
+        if datastore.data['watching'][uuid].history_n == 0:
+            flash("Preview unavailable - No fetch/check completed or triggers not reached", "error")
+            return redirect(url_for('index'))
+
         extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
 
         try:
@@ -783,9 +871,9 @@ def changedetection_app(config=None, datastore_o=None):
             flash("No history found for the specified link, bad link?", "error")
             return redirect(url_for('index'))
 
-        if len(watch['history']):
-            timestamps = sorted(watch['history'].keys(), key=lambda x: int(x))
-            filename = watch['history'][timestamps[-1]]
+        if watch.history_n >0:
+            timestamps = sorted(watch.history.keys(), key=lambda x: int(x))
+            filename = watch.history[timestamps[-1]]
             try:
                 with open(filename, 'r') as f:
                     tmp = f.readlines()
@@ -821,6 +909,11 @@ def changedetection_app(config=None, datastore_o=None):
             content.append({'line': "No history found", 'classes': ''})
 
         screenshot_url = datastore.get_screenshot(uuid)
+        system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
+
+        is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
+                watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
+
         output = render_template("preview.html",
                                  content=content,
                                  extra_stylesheets=extra_stylesheets,
@@ -829,8 +922,9 @@ def changedetection_app(config=None, datastore_o=None):
                                  current_diff_url=watch['url'],
                                  screenshot=screenshot_url,
                                  watch=watch,
-                                 uuid=uuid)
-        
+                                 uuid=uuid,
+                                 is_html_webdriver=is_html_webdriver)
+
         return output
 
     @app.route("/settings/notification-logs", methods=['GET'])
@@ -838,31 +932,10 @@ def changedetection_app(config=None, datastore_o=None):
     def notification_logs():
         global notification_debug_log
         output = render_template("notification-log.html",
-                                 logs=notification_debug_log if len(notification_debug_log) else ["No errors or warnings detected"])
+                                 logs=notification_debug_log if len(notification_debug_log) else ["Notification logs are empty - no notifications sent yet."])
 
         return output
 
-    @app.route("/api/<string:uuid>/snapshot/current", methods=['GET'])
-    @login_required
-    def api_snapshot(uuid):
-
-        # More for testing, possible to return the first/only
-        if uuid == 'first':
-            uuid = list(datastore.data['watching'].keys()).pop()
-
-        try:
-            watch = datastore.data['watching'][uuid]
-        except KeyError:
-            return abort(400, "No history found for the specified link, bad link?")
-
-        newest = list(watch['history'].keys())[-1]
-        with open(watch['history'][newest], 'r') as f:
-            content = f.read()
-
-        resp = make_response(content)
-        resp.headers['Content-Type'] = 'text/plain'
-        return resp
-
     @app.route("/favicon.ico", methods=['GET'])
     def favicon():
         return send_from_directory("static/images", path="favicon.ico")
@@ -943,10 +1016,9 @@ def changedetection_app(config=None, datastore_o=None):
 
     @app.route("/static/<string:group>/<string:filename>", methods=['GET'])
     def static_content(group, filename):
+        from flask import make_response
+
         if group == 'screenshot':
-
-            from flask import make_response
-
             # Could be sensitive, follow password requirements
             if datastore.data['settings']['application']['password'] and not flask_login.current_user.is_authenticated:
                 abort(403)
@@ -965,6 +1037,26 @@ def changedetection_app(config=None, datastore_o=None):
             except FileNotFoundError:
                 abort(404)
 
+
+        if group == 'visual_selector_data':
+            # Could be sensitive, follow password requirements
+            if datastore.data['settings']['application']['password'] and not flask_login.current_user.is_authenticated:
+                abort(403)
+
+            # These files should be in our subdirectory
+            try:
+                # set nocache, set content-type
+                watch_dir = datastore_o.datastore_path + "/" + filename
+                response = make_response(send_from_directory(filename="elements.json", directory=watch_dir, path=watch_dir + "/elements.json"))
+                response.headers['Content-type'] = 'application/json'
+                response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+                response.headers['Pragma'] = 'no-cache'
+                response.headers['Expires'] = 0
+                return response
+
+            except FileNotFoundError:
+                abort(404)
+
         # These files should be in our subdirectory
         try:
             return send_from_directory("static/{}".format(group), path=filename)
@@ -973,7 +1065,7 @@ def changedetection_app(config=None, datastore_o=None):
 
     @app.route("/api/add", methods=['POST'])
     @login_required
-    def api_watch_add():
+    def form_watch_add():
         from changedetectionio import forms
         form = forms.quickWatchForm(request.form)
 
@@ -999,7 +1091,7 @@ def changedetection_app(config=None, datastore_o=None):
 
     @app.route("/api/delete", methods=['GET'])
     @login_required
-    def api_delete():
+    def form_delete():
         uuid = request.args.get('uuid')
 
         if uuid != 'all' and not uuid in datastore.data['watching'].keys():
@@ -1016,7 +1108,7 @@ def changedetection_app(config=None, datastore_o=None):
 
     @app.route("/api/clone", methods=['GET'])
     @login_required
-    def api_clone():
+    def form_clone():
         uuid = request.args.get('uuid')
         # More for testing, possible to return the first/only
         if uuid == 'first':
@@ -1030,7 +1122,7 @@ def changedetection_app(config=None, datastore_o=None):
 
     @app.route("/api/checknow", methods=['GET'])
     @login_required
-    def api_watch_checknow():
+    def form_watch_checknow():
 
         tag = request.args.get('tag')
         uuid = request.args.get('uuid')
@@ -1067,7 +1159,7 @@ def changedetection_app(config=None, datastore_o=None):
 
     @app.route("/api/share-url", methods=['GET'])
     @login_required
-    def api_share_put_watch():
+    def form_share_put_watch():
         """Given a watch UUID, upload the info and return a share-link
            the share-link can be imported/added"""
         import requests
@@ -1081,6 +1173,7 @@ def changedetection_app(config=None, datastore_o=None):
 
         # copy it to memory as trim off what we dont need (history)
         watch = deepcopy(datastore.data['watching'][uuid])
+        # For older versions that are not a @property
         if (watch.get('history')):
             del (watch['history'])
 
@@ -1110,14 +1203,14 @@ def changedetection_app(config=None, datastore_o=None):
 
 
         except Exception as e:
-            flash("Could not share, something went wrong while communicating with the share server.", 'error')
+            logging.error("Error sharing -{}".format(str(e)))
+            flash("Could not share, something went wrong while communicating with the share server - {}".format(str(e)), 'error')
 
         # https://changedetection.io/share/VrMv05wpXyQa
         # in the browser - should give you a nice info page - wtf
         # paste in etc
         return redirect(url_for('index'))
 
-
     # @todo handle ctrl break
     ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks).start()
 
@@ -1159,6 +1252,9 @@ def check_for_new_version():
 
 def notification_runner():
     global notification_debug_log
+    from datetime import datetime
+    import json
+
     while not app.config.exit.is_set():
         try:
             # At the moment only one thread runs (single runner)
@@ -1167,13 +1263,17 @@ def notification_runner():
             time.sleep(1)
 
         else:
-            # Process notifications
+
+            now = datetime.now()
+            sent_obj = None
+
             try:
                 from changedetectionio import notification
-                notification.process_notification(n_object, datastore)
+
+                sent_obj = notification.process_notification(n_object, datastore)
 
             except Exception as e:
-                print("Watch URL: {}  Error {}".format(n_object['watch_url'], str(e)))
+                logging.error("Watch URL: {}  Error {}".format(n_object['watch_url'], str(e)))
 
                 # UUID wont be present when we submit a 'test' from the global settings
                 if 'uuid' in n_object:
@@ -1183,14 +1283,19 @@ def notification_runner():
                 log_lines = str(e).splitlines()
                 notification_debug_log += log_lines
 
-                # Trim the log length
-                notification_debug_log = notification_debug_log[-100:]
-
+            # Process notifications
+            notification_debug_log+= ["{} - SENDING - {}".format(now.strftime("%Y/%m/%d %H:%M:%S,000"), json.dumps(sent_obj))]
+            # Trim the log length
+            notification_debug_log = notification_debug_log[-100:]
 
 # Thread runner to check every minute, look for new watches to feed into the Queue.
 def ticker_thread_check_time_launch_checks():
+    import random
     from changedetectionio import update_worker
 
+    recheck_time_minimum_seconds = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 20))
+    print("System env MINIMUM_SECONDS_RECHECK_TIME", recheck_time_minimum_seconds)
+
     # Spin up Workers that do the fetching
     # Can be overriden by ENV or use the default settings
     n_workers = int(os.getenv("FETCH_WORKERS", datastore.data['settings']['requests']['workers']))
@@ -1208,9 +1313,10 @@ def ticker_thread_check_time_launch_checks():
                 running_uuids.append(t.current_uuid)
 
         # Re #232 - Deepcopy the data incase it changes while we're iterating through it all
+        watch_uuid_list = []
         while True:
             try:
-                copied_datastore = deepcopy(datastore)
+                watch_uuid_list = datastore.data['watching'].keys()
             except RuntimeError as e:
                 # RuntimeError: dictionary changed size during iteration
                 time.sleep(0.1)
@@ -1221,33 +1327,49 @@ def ticker_thread_check_time_launch_checks():
         while update_q.qsize() >= 2000:
             time.sleep(1)
 
+
+        recheck_time_system_seconds = int(datastore.threshold_seconds)
+
         # Check for watches outside of the time threshold to put in the thread queue.
-        now = time.time()
-
-        recheck_time_minimum_seconds = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
-        recheck_time_system_seconds = datastore.threshold_seconds
-
-        for uuid, watch in copied_datastore.data['watching'].items():
+        for uuid in watch_uuid_list:
+            now = time.time()
+            watch = datastore.data['watching'].get(uuid)
+            if not watch:
+                logging.error("Watch: {} no longer present.".format(uuid))
+                continue
 
             # No need todo further processing if it's paused
             if watch['paused']:
                 continue
 
             # If they supplied an individual entry minutes to threshold.
-            threshold = now
-            watch_threshold_seconds = watch.threshold_seconds()
-            if watch_threshold_seconds:
-                threshold -= watch_threshold_seconds
-            else:
-                threshold -= recheck_time_system_seconds
 
-            # Yeah, put it in the queue, it's more than time
-            if watch['last_checked'] <= max(threshold, recheck_time_minimum_seconds):
+            watch_threshold_seconds = watch.threshold_seconds()
+            threshold = watch_threshold_seconds if watch_threshold_seconds > 0 else recheck_time_system_seconds
+
+            # #580 - Jitter plus/minus amount of time to make the check seem more random to the server
+            jitter = datastore.data['settings']['requests'].get('jitter_seconds', 0)
+            if jitter > 0:
+                if watch.jitter_seconds == 0:
+                    watch.jitter_seconds = random.uniform(-abs(jitter), jitter)
+
+
+            seconds_since_last_recheck = now - watch['last_checked']
+            if seconds_since_last_recheck >= (threshold + watch.jitter_seconds) and seconds_since_last_recheck >= recheck_time_minimum_seconds:
                 if not uuid in running_uuids and uuid not in update_q.queue:
+                    print("Queued watch UUID {} last checked at {} queued at {:0.2f} jitter {:0.2f}s, {:0.2f}s since last checked".format(uuid,
+                                                                                                         watch['last_checked'],
+                                                                                                         now,
+                                                                                                         watch.jitter_seconds,
+                                                                                                         now - watch['last_checked']))
+                    # Into the queue with you
                     update_q.put(uuid)
 
-        # Wait a few seconds before checking the list again
-        time.sleep(3)
+                    # Reset for next time
+                    watch.jitter_seconds = 0
+
+        # Wait before checking the list again - saves CPU
+        time.sleep(1)
 
         # Should be low so we can break this out in testing
-        app.config.exit.wait(1)
+        app.config.exit.wait(1)

changedetectionio/api/api_v1.py

@@ -0,0 +1,124 @@
+from flask_restful import abort, Resource
+from flask import request, make_response
+import validators
+from . import auth
+
+
+
+# https://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html
+
+class Watch(Resource):
+    def __init__(self, **kwargs):
+        # datastore is a black box dependency
+        self.datastore = kwargs['datastore']
+        self.update_q = kwargs['update_q']
+
+    # Get information about a single watch, excluding the history list (can be large)
+    # curl http://localhost:4000/api/v1/watch/<string:uuid>
+    # ?recheck=true
+    @auth.check_token
+    def get(self, uuid):
+        from copy import deepcopy
+        watch = deepcopy(self.datastore.data['watching'].get(uuid))
+        if not watch:
+            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
+
+        if request.args.get('recheck'):
+            self.update_q.put(uuid)
+            return "OK", 200
+
+        # Return without history, get that via another API call
+        watch['history_n'] = watch.history_n
+        return watch
+
+    @auth.check_token
+    def delete(self, uuid):
+        if not self.datastore.data['watching'].get(uuid):
+            abort(400, message='No watch exists with the UUID of {}'.format(uuid))
+
+        self.datastore.delete(uuid)
+        return 'OK', 204
+
+
+class WatchHistory(Resource):
+    def __init__(self, **kwargs):
+        # datastore is a black box dependency
+        self.datastore = kwargs['datastore']
+
+    # Get a list of available history for a watch by UUID
+    # curl http://localhost:4000/api/v1/watch/<string:uuid>/history
+    def get(self, uuid):
+        watch = self.datastore.data['watching'].get(uuid)
+        if not watch:
+            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
+        return watch.history, 200
+
+
+class WatchSingleHistory(Resource):
+    def __init__(self, **kwargs):
+        # datastore is a black box dependency
+        self.datastore = kwargs['datastore']
+
+    # Read a given history snapshot and return its content
+    # <string:timestamp> or "latest"
+    # curl http://localhost:4000/api/v1/watch/<string:uuid>/history/<int:timestamp>
+    @auth.check_token
+    def get(self, uuid, timestamp):
+        watch = self.datastore.data['watching'].get(uuid)
+        if not watch:
+            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
+
+        if not len(watch.history):
+            abort(404, message='Watch found but no history exists for the UUID {}'.format(uuid))
+
+        if timestamp == 'latest':
+            timestamp = list(watch.history.keys())[-1]
+
+        with open(watch.history[timestamp], 'r') as f:
+            content = f.read()
+
+        response = make_response(content, 200)
+        response.mimetype = "text/plain"
+        return response
+
+
+class CreateWatch(Resource):
+    def __init__(self, **kwargs):
+        # datastore is a black box dependency
+        self.datastore = kwargs['datastore']
+        self.update_q = kwargs['update_q']
+
+    @auth.check_token
+    def post(self):
+        # curl http://localhost:4000/api/v1/watch -H "Content-Type: application/json" -d '{"url": "https://my-nice.com", "tag": "one, two" }'
+        json_data = request.get_json()
+        tag = json_data['tag'].strip() if json_data.get('tag') else ''
+
+        if not validators.url(json_data['url'].strip()):
+            return "Invalid or unsupported URL", 400
+
+        extras = {'title': json_data['title'].strip()} if json_data.get('title') else {}
+
+        new_uuid = self.datastore.add_watch(url=json_data['url'].strip(), tag=tag, extras=extras)
+        self.update_q.put(new_uuid)
+        return {'uuid': new_uuid}, 201
+
+    # Return concise list of available watches and some very basic info
+    # curl http://localhost:4000/api/v1/watch|python -mjson.tool
+    # ?recheck_all=1 to recheck all
+    @auth.check_token
+    def get(self):
+        list = {}
+        for k, v in self.datastore.data['watching'].items():
+            list[k] = {'url': v['url'],
+                       'title': v['title'],
+                       'last_checked': v['last_checked'],
+                       'last_changed': v['last_changed'],
+                       'last_error': v['last_error']}
+
+        if request.args.get('recheck_all'):
+            for uuid in self.datastore.data['watching'].keys():
+                self.update_q.put(uuid)
+            return {'status': "OK"}, 200
+
+        return list, 200

changedetectionio/api/auth.py

@@ -0,0 +1,33 @@
+from flask import request, make_response, jsonify
+from functools import wraps
+
+
+# Simple API auth key comparison
+# @todo - Maybe short lived token in the future?
+
+def check_token(f):
+    @wraps(f)
+    def decorated(*args, **kwargs):
+        datastore = args[0].datastore
+
+        config_api_token_enabled = datastore.data['settings']['application'].get('api_access_token_enabled')
+        if not config_api_token_enabled:
+            return
+
+        try:
+            api_key_header = request.headers['x-api-key']
+        except KeyError:
+            return make_response(
+                jsonify("No authorization x-api-key header."), 403
+            )
+
+        config_api_token = datastore.data['settings']['application'].get('api_access_token')
+
+        if api_key_header != config_api_token:
+            return make_response(
+                jsonify("Invalid access - API key invalid."), 403
+            )
+
+        return f(*args, **kwargs)
+
+    return decorated

changedetectionio/apprise_asset.py

@@ -0,0 +1,11 @@
+import apprise
+
+# Create our AppriseAsset and populate it with some of our new values:
+# https://github.com/caronc/apprise/wiki/Development_API#the-apprise-asset-object
+asset = apprise.AppriseAsset(
+   image_url_logo='https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
+)
+
+asset.app_id = "changedetection.io"
+asset.app_desc = "ChangeDetection.io best and simplest website monitoring and change detection"
+asset.app_url = "https://changedetection.io"

changedetectionio/changedetection.py

@@ -35,7 +35,7 @@ def main():
     create_datastore_dir = False
 
     for opt, arg in opts:
-        #        if opt == '--purge':
+        #        if opt == '--clear-all-history':
         # Remove history, the actual files you need to delete manually.
         #            for uuid, watch in datastore.data['watching'].items():
         #                watch.update({'history': {}, 'last_checked': 0, 'last_changed': 0, 'previous_md5': None})

changedetectionio/content_fetcher.py

@@ -1,11 +1,18 @@
 from abc import ABC, abstractmethod
 import chardet
+import json
 import os
 import requests
 import time
-import urllib3.exceptions
 import sys
 
+class PageUnloadable(Exception):
+    def __init__(self, status_code, url):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        return
+    pass
 
 class EmptyReply(Exception):
     def __init__(self, status_code, url):
@@ -13,7 +20,22 @@ class EmptyReply(Exception):
         self.status_code = status_code
         self.url = url
         return
+    pass
 
+class ScreenshotUnavailable(Exception):
+    def __init__(self, status_code, url):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        return
+    pass
+
+class ReplyWithContentButNoText(Exception):
+    def __init__(self, status_code, url):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        return
     pass
 
 
@@ -22,9 +44,143 @@ class Fetcher():
     status_code = None
     content = None
     headers = None
+
+    fetcher_description = "No description"
+    webdriver_js_execute_code = None
+    xpath_element_js = """               
+                // Include the getXpath script directly, easier than fetching
+                !function(e,n){"object"==typeof exports&&"undefined"!=typeof module?module.exports=n():"function"==typeof define&&define.amd?define(n):(e=e||self).getXPath=n()}(this,function(){return function(e){var n=e;if(n&&n.id)return'//*[@id="'+n.id+'"]';for(var o=[];n&&Node.ELEMENT_NODE===n.nodeType;){for(var i=0,r=!1,d=n.previousSibling;d;)d.nodeType!==Node.DOCUMENT_TYPE_NODE&&d.nodeName===n.nodeName&&i++,d=d.previousSibling;for(d=n.nextSibling;d;){if(d.nodeName===n.nodeName){r=!0;break}d=d.nextSibling}o.push((n.prefix?n.prefix+":":"")+n.localName+(i||r?"["+(i+1)+"]":"")),n=n.parentNode}return o.length?"/"+o.reverse().join("/"):""}});
+
+
+                const findUpTag = (el) => {
+                  let r = el
+                  chained_css = [];
+                  depth=0;
+            
+                // Strategy 1: Keep going up until we hit an ID tag, imagine it's like  #list-widget div h4
+                  while (r.parentNode) {
+                    if(depth==5) {
+                      break;
+                    }
+                    if('' !==r.id) {
+                      chained_css.unshift("#"+r.id);
+                      final_selector= chained_css.join('>');
+                      // Be sure theres only one, some sites have multiples of the same ID tag :-(
+                      if (window.document.querySelectorAll(final_selector).length ==1 ) {
+                        return final_selector;
+                      }
+                      return null;
+                    } else {
+                      chained_css.unshift(r.tagName.toLowerCase());
+                    }
+                    r=r.parentNode;
+                    depth+=1;
+                  }
+                  return null;
+                }
+
+
+                // @todo - if it's SVG or IMG, go into image diff mode
+                var elements = window.document.querySelectorAll("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");
+                var size_pos=[];
+                // after page fetch, inject this JS
+                // build a map of all elements and their positions (maybe that only include text?)
+                var bbox;
+                for (var i = 0; i < elements.length; i++) {   
+                 bbox = elements[i].getBoundingClientRect();
+
+                 // forget really small ones
+                 if (bbox['width'] <20 && bbox['height'] < 20 ) {
+                   continue;
+                 }
+
+                 // @todo the getXpath kind of sucks, it doesnt know when there is for example just one ID sometimes
+                 // it should not traverse when we know we can anchor off just an ID one level up etc..
+                 // maybe, get current class or id, keep traversing up looking for only class or id until there is just one match 
+
+                 // 1st primitive - if it has class, try joining it all and select, if theres only one.. well thats us.
+                 xpath_result=false;
+                 
+                 try {
+                   var d= findUpTag(elements[i]);
+                   if (d) {
+                     xpath_result =d;
+                   }                
+                 } catch (e) {
+                   console.log(e);
+                 }
+                 
+                 // You could swap it and default to getXpath and then try the smarter one
+                 // default back to the less intelligent one
+                 if (!xpath_result) {
+                    try {
+                       // I've seen on FB and eBay that this doesnt work
+                       // ReferenceError: getXPath is not defined at eval (eval at evaluate (:152:29), <anonymous>:67:20) at UtilityScript.evaluate (<anonymous>:159:18) at UtilityScript.<anonymous> (<anonymous>:1:44)
+                       xpath_result = getXPath(elements[i]);
+                     } catch (e) {
+                       console.log(e);
+                       continue;
+                     }            
+                 }
+                 
+                 if(window.getComputedStyle(elements[i]).visibility === "hidden") {
+                   continue;
+                 }
+
+                 size_pos.push({
+                   xpath: xpath_result,
+                   width: Math.round(bbox['width']), 
+                   height: Math.round(bbox['height']), 
+                   left: Math.floor(bbox['left']), 
+                   top: Math.floor(bbox['top']), 
+                   childCount: elements[i].childElementCount
+                 });                 
+                }
+
+
+                // inject the current one set in the css_filter, which may be a CSS rule
+                // used for displaying the current one in VisualSelector, where its not one we generated.
+                if (css_filter.length) {
+                   q=false;                   
+                   try {
+                       // is it xpath?
+                       if (css_filter.startsWith('/') || css_filter.startsWith('xpath:')) {
+                         q=document.evaluate(css_filter.replace('xpath:',''), document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
+                       } else {
+                         q=document.querySelector(css_filter);
+                       }                       
+                   } catch (e) {
+                    // Maybe catch DOMException and alert? 
+                     console.log(e);                       
+                   }
+                   bbox=false;
+                   if(q) {
+                     bbox = q.getBoundingClientRect();
+                   }
+                                   
+                   if (bbox && bbox['width'] >0 && bbox['height']>0) {                       
+                       size_pos.push({
+                           xpath: css_filter,
+                           width: bbox['width'], 
+                           height: bbox['height'],
+                           left: bbox['left'],
+                           top: bbox['top'],
+                           childCount: q.childElementCount
+                         });
+                     }
+                }
+                // Window.width required for proper scaling in the frontend
+                return {'size_pos':size_pos, 'browser_width': window.innerWidth};
+    """
+    xpath_data = None
+
     # Will be needed in the future by the VisualSelector, always get this where possible.
     screenshot = False
-    fetcher_description = "No description"
+    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
 
     @abstractmethod
     def get_error(self):
@@ -37,7 +193,8 @@ class Fetcher():
             request_headers,
             request_body,
             request_method,
-            ignore_status_codes=False):
+            ignore_status_codes=False,
+            current_css_filter=None):
         # Should set self.error, self.status_code and self.content
         pass
 
@@ -80,26 +237,22 @@ class base_html_playwright(Fetcher):
     if os.getenv("PLAYWRIGHT_DRIVER_URL"):
         fetcher_description += " via '{}'".format(os.getenv("PLAYWRIGHT_DRIVER_URL"))
 
-#    try:
-#        from playwright.sync_api import sync_playwright
-#    except ModuleNotFoundError:
-#        fetcher_enabled = False
-
     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 = ['server', 'bypass', 'username', 'password']
+    playwright_proxy_settings_mappings = ['bypass', 'server', 'username', 'password']
 
     proxy = None
 
-    def __init__(self):
+    def __init__(self, proxy_override=None):
+
         # .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/playwright'
+            'ws://playwright-chrome:3000'
         ).strip('"')
 
         # If any proxy settings are enabled, then we should setup the proxy object
@@ -112,46 +265,120 @@ class base_html_playwright(Fetcher):
         if proxy_args:
             self.proxy = proxy_args
 
+        # allow per-watch proxy selection override
+        if proxy_override:
+            self.proxy = {'server': proxy_override}
+
     def run(self,
             url,
             timeout,
             request_headers,
             request_body,
             request_method,
-            ignore_status_codes=False):
+            ignore_status_codes=False,
+            current_css_filter=None):
 
         from playwright.sync_api import sync_playwright
-
+        import playwright._impl._api_types
+        from playwright._impl._api_types import Error, TimeoutError
+        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)
-            browser = browser_type.connect_over_cdp(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="Mozilla/5.0",
-                proxy=self.proxy
+                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 never be needed
+                accept_downloads=False
             )
-            page = context.new_page()
-            page.set_viewport_size({"width": 1280, "height": 1024})
-            response = page.goto(url, timeout=timeout * 1000)
 
-            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5))
-            page.wait_for_timeout(extra_wait * 1000)
+            if len(request_headers):
+                context.set_extra_http_headers(request_headers)
+
+            page = context.new_page()
+            try:
+                page.set_default_navigation_timeout(90000)
+                page.set_default_timeout(90000)
+
+                # Listen for all console events and handle errors
+                page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
+
+                # Bug - never set viewport size BEFORE page.goto
+
+                # Waits for the next navigation. Using Python context manager
+                # prevents a race condition between clicking and waiting for a navigation.
+                with page.expect_navigation():
+                    response = page.goto(url, wait_until='load')
+
+                if self.webdriver_js_execute_code is not None:
+                    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 ("other exception when page.goto")
+                print (str(e))
+                context.close()
+                browser.close()
+                raise PageUnloadable(url=url, status_code=None)
 
             if response is None:
+                context.close()
+                browser.close()
+                print ("response object was none")
                 raise EmptyReply(url=url, status_code=None)
 
-            self.status_code = response.status
+            # Bug 2(?) Set the viewport size AFTER loading the page
+            page.set_viewport_size({"width": 1280, "height": 1024})            
+            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+            time.sleep(extra_wait)
             self.content = page.content()
+            self.status_code = response.status
+
+            if len(self.content.strip()) == 0:
+                context.close()
+                browser.close()
+                print ("Content was empty")
+                raise EmptyReply(url=url, status_code=None)
+            
             self.headers = response.all_headers()
 
+            if current_css_filter is not None:
+                page.evaluate("var css_filter={}".format(json.dumps(current_css_filter)))
+            else:
+                page.evaluate("var css_filter=''")
+
+            self.xpath_data = page.evaluate("async () => {" + self.xpath_element_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
-            page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024})
-            self.screenshot = page.screenshot(type='jpeg', full_page=True, quality=90)
+
+            # 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:
+                # Quality set to 1 because it's not used, just used as a work-around for a bug, no need to change this.
+                page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024}, quality=1)
+                # The actual screenshot
+                self.screenshot = 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()
 
@@ -171,7 +398,7 @@ class base_html_webdriver(Fetcher):
                                         'socksProxy', 'socksVersion', 'socksUsername', 'socksPassword']
     proxy = None
 
-    def __init__(self):
+    def __init__(self, proxy_override=None):
         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
@@ -184,6 +411,16 @@ class base_html_webdriver(Fetcher):
             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)
 
@@ -193,7 +430,8 @@ class base_html_webdriver(Fetcher):
             request_headers,
             request_body,
             request_method,
-            ignore_status_codes=False):
+            ignore_status_codes=False,
+            current_css_filter=None):
 
         from selenium import webdriver
         from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
@@ -213,17 +451,25 @@ class base_html_webdriver(Fetcher):
             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)))
+
+        self.screenshot = self.driver.get_screenshot_as_png()
+
         # @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)))
+        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()
-        self.quit()
 
     # Does the connection to the webdriver work? run a test connection.
     def is_ready(self):
@@ -251,19 +497,35 @@ class base_html_webdriver(Fetcher):
 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):
+            ignore_status_codes=False,
+            current_css_filter=None):
+
+        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.

changedetectionio/fetch_site_status.py

@@ -1,4 +1,5 @@
 import hashlib
+import logging
 import os
 import re
 import time
@@ -10,12 +11,55 @@ urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 
 # Some common stuff here that can be moved to a base class
+# (set_proxy_from_list)
 class perform_site_check():
 
     def __init__(self, *args, datastore, **kwargs):
         super().__init__(*args, **kwargs)
         self.datastore = datastore
 
+    # If there was a proxy list enabled, figure out what proxy_args/which proxy to use
+    # if watch.proxy use that
+    # fetcher.proxy_override = watch.proxy or main config proxy
+    # Allows override the proxy on a per-request basis
+    # ALWAYS use the first one is nothing selected
+
+    def set_proxy_from_list(self, watch):
+        proxy_args = None
+        if self.datastore.proxy_list is None:
+            return None
+
+        # If its a valid one
+        if any([watch['proxy'] in p for p in self.datastore.proxy_list]):
+            proxy_args = watch['proxy']
+
+        # not valid (including None), try the system one
+        else:
+            system_proxy = self.datastore.data['settings']['requests']['proxy']
+            # Is not None and exists
+            if any([system_proxy in p for p in self.datastore.proxy_list]):
+                proxy_args = system_proxy
+
+        # Fallback - Did not resolve anything, use the first available
+        if proxy_args is None:
+            proxy_args = self.datastore.proxy_list[0][0]
+
+        return proxy_args
+
+    # Doesn't look like python supports forward slash auto enclosure in re.findall
+    # So convert it to inline flag "foobar(?i)" type configuration
+    def forward_slash_enclosed_regex_to_options(self, regex):
+        res = re.search(r'^/(.*?)/(\w+)$', regex, re.IGNORECASE)
+
+        if res:
+            regex = res.group(1)
+            regex += '(?{})'.format(res.group(2))
+        else:
+            regex += '(?{})'.format('i')
+
+        return regex
+
+
     def run(self, uuid):
         timestamp = int(time.time())  # used for storage etc too
 
@@ -66,8 +110,22 @@ class perform_site_check():
             # If the klass doesnt exist, just use a default
             klass = getattr(content_fetcher, "html_requests")
 
-        fetcher = klass()
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_code)
+
+        proxy_args = self.set_proxy_from_list(watch)
+        fetcher = klass(proxy_override=proxy_args)
+
+        # 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)
+        if watch['webdriver_delay'] is not None:
+            fetcher.render_extract_delay = watch['webdriver_delay']
+        elif system_webdriver_delay is not None:
+            fetcher.render_extract_delay = system_webdriver_delay
+
+        if watch['webdriver_js_execute_code'] is not None and watch['webdriver_js_execute_code'].strip():
+            fetcher.webdriver_js_execute_code = watch['webdriver_js_execute_code']
+
+        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_code, watch['css_filter'])
+        fetcher.quit()
 
         # Fetching complete, now filters
         # @todo move to class / maybe inside of fetcher abstract base?
@@ -107,7 +165,9 @@ class perform_site_check():
                 is_html = False
 
         if is_html or is_source:
+            
             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
+            fetcher.content = html_tools.workarounds_for_obfuscations(fetcher.content)
             html_content = fetcher.content
 
             # If not JSON,  and if it's not text/plain..
@@ -118,11 +178,13 @@ class perform_site_check():
                 # Then we assume HTML
                 if has_filter_rule:
                     # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
-                    if css_filter_rule[0] == '/':
-                        html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule, html_content=fetcher.content)
+                    if css_filter_rule[0] == '/' or css_filter_rule.startswith('xpath:'):
+                        html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule.replace('xpath:', ''),
+                                                               html_content=fetcher.content)
                     else:
                         # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
                         html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content)
+
                 if has_subtractive_selectors:
                     html_content = html_tools.element_removal(subtractive_selectors, html_content)
 
@@ -142,10 +204,14 @@ class perform_site_check():
             # Re #340 - return the content before the 'ignore text' was applied
             text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
-
         # Re #340 - return the content before the 'ignore text' was applied
         text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
+        # 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=200)
+
         # 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.
 
@@ -159,33 +225,69 @@ class perform_site_check():
         else:
             stripped_text_from_html = stripped_text_from_html.encode('utf8')
 
+        # 615 Extract text by regex
+        extract_text = watch.get('extract_text', [])
+        if len(extract_text) > 0:
+            regex_matched_output = []
+            for s_re in extract_text:
+                # incase they specified something in '/.../x'
+                regex = self.forward_slash_enclosed_regex_to_options(s_re)
+                result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
+
+                for l in result:
+                    if type(l) is tuple:
+                        #@todo - some formatter option default (between groups)
+                        regex_matched_output += list(l) + [b'\n']
+                    else:
+                        # @todo - some formatter option default (between each ungrouped result)
+                        regex_matched_output += [l] + [b'\n']
+
+            # Now we will only show what the regex matched
+            stripped_text_from_html = b''
+            text_content_before_ignored_filter = b''
+            if regex_matched_output:
+                # @todo some formatter for presentation?
+                stripped_text_from_html = b''.join(regex_matched_output)
+                text_content_before_ignored_filter = stripped_text_from_html
+
+
         # Re #133 - if we should strip whitespaces from triggering the change detected comparison
         if self.datastore.data['settings']['application'].get('ignore_whitespace', False):
             fetched_md5 = hashlib.md5(stripped_text_from_html.translate(None, b'\r\n\t ')).hexdigest()
         else:
             fetched_md5 = hashlib.md5(stripped_text_from_html).hexdigest()
 
-        # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
-        if not watch.get('previous_md5'):
-            watch['previous_md5'] = fetched_md5
-            update_obj["previous_md5"] = fetched_md5
-
-        blocked_by_not_found_trigger_text = False
+        ############ Blocking rules, after checksum #################
+        blocked = False
 
         if len(watch['trigger_text']):
-            # Yeah, lets block first until something matches
-            blocked_by_not_found_trigger_text = True
+            # Assume blocked
+            blocked = True
             # Filter and trigger works the same, so reuse it
+            # It should return the line numbers that match
             result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
                                                   wordlist=watch['trigger_text'],
                                                   mode="line numbers")
+            # Unblock if the trigger was found
             if result:
-                blocked_by_not_found_trigger_text = False
+                blocked = False
 
-        if not blocked_by_not_found_trigger_text and watch['previous_md5'] != fetched_md5:
+
+        if len(watch['text_should_not_be_present']):
+            # If anything matched, then we should block a change from happening
+            result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
+                                                  wordlist=watch['text_should_not_be_present'],
+                                                  mode="line numbers")
+            if result:
+                blocked = True
+
+        # The main thing that all this at the moment comes down to :)
+        if watch['previous_md5'] != fetched_md5:
             changed_detected = True
-            update_obj["previous_md5"] = fetched_md5
-            update_obj["last_changed"] = timestamp
+
+        # Looks like something changed, but did it match all the rules?
+        if blocked:
+            changed_detected = False
 
         # Extract title as title
         if is_html:
@@ -193,4 +295,21 @@ class perform_site_check():
                 if not watch['title'] or not len(watch['title']):
                     update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
 
-        return changed_detected, update_obj, text_content_before_ignored_filter, fetcher.screenshot
+        if changed_detected:
+            if watch.get('check_unique_lines', False):
+                has_unique_lines = watch.lines_contain_something_unique_compared_to_history(lines=stripped_text_from_html.splitlines())
+                # One or more lines? unsure?
+                if not has_unique_lines:
+                    logging.debug("check_unique_lines: UUID {} didnt have anything new setting change_detected=False".format(uuid))
+                    changed_detected = False
+                else:
+                    logging.debug("check_unique_lines: UUID {} had unique content".format(uuid))
+
+        # Always record the new checksum
+        update_obj["previous_md5"] = fetched_md5
+
+        # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
+        if not watch.get('previous_md5'):
+            watch['previous_md5'] = fetched_md5
+
+        return changed_detected, update_obj, text_content_before_ignored_filter, fetcher.screenshot, fetcher.xpath_data

changedetectionio/forms.py

@@ -223,7 +223,7 @@ class validateURL(object):
         except validators.ValidationFailure:
             message = field.gettext('\'%s\' is not a valid URL.' % (field.data.strip()))
             raise ValidationError(message)
-        
+
 class ValidateListRegex(object):
     """
     Validates that anything that looks like a regex passes as a regex
@@ -307,7 +307,7 @@ class ValidateCSSJSONXPATHInput(object):
 
 class quickWatchForm(Form):
     url = fields.URLField('URL', validators=[validateURL()])
-    tag = StringField('Group tag', [validators.Optional(), validators.Length(max=35)])
+    tag = StringField('Group tag', [validators.Optional()])
 
 # Common to a single watch and the global settings
 class commonSettingsForm(Form):
@@ -318,17 +318,21 @@ class commonSettingsForm(Form):
     notification_format = SelectField('Notification format', choices=valid_notification_formats.keys(), default=default_notification_format)
     fetch_backend = RadioField(u'Fetch method', choices=content_fetcher.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")] )
 
 class watchForm(commonSettingsForm):
 
     url = fields.URLField('URL', validators=[validateURL()])
-    tag = StringField('Group tag', [validators.Optional(), validators.Length(max=35)], default='')
+    tag = StringField('Group tag', [validators.Optional()], default='')
 
     time_between_check = FormField(TimeBetweenCheckForm)
 
     css_filter = StringField('CSS/JSON/XPATH Filter', [ValidateCSSJSONXPATHInput()], default='')
 
     subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
+
+    extract_text = StringListField('Extract text', [ValidateListRegex()])
+
     title = StringField('Title', default='')
 
     ignore_text = StringListField('Ignore text', [ValidateListRegex()])
@@ -336,10 +340,17 @@ class watchForm(commonSettingsForm):
     body = TextAreaField('Request body', [validators.Optional()])
     method = SelectField('Request method', choices=valid_method, default=default_method)
     ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
+    check_unique_lines = BooleanField('Only trigger when new lines appear', default=False)
     trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
+    text_should_not_be_present = StringListField('Block change-detection if text matches', [validators.Optional(), ValidateListRegex()])
+
+    webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
 
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
     save_and_preview_button = SubmitField('Save & Preview', render_kw={"class": "pure-button pure-button-primary"})
+    proxy = RadioField('Proxy')
+    filter_failure_notification_send = BooleanField(
+        'Send a notification when the filter can no longer be found on the page', default=False)
 
     def validate(self, **kwargs):
         if not super().validate():
@@ -358,7 +369,10 @@ class watchForm(commonSettingsForm):
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
     time_between_check = FormField(TimeBetweenCheckForm)
-
+    proxy = RadioField('Proxy')
+    jitter_seconds = IntegerField('Random jitter seconds ± check',
+                                  render_kw={"style": "width: 5em;"},
+                                  validators=[validators.NumberRange(min=0, message="Should contain zero or more seconds")])
 
 # datastore.data['settings']['application']..
 class globalSettingsApplicationForm(commonSettingsForm):
@@ -369,10 +383,17 @@ class globalSettingsApplicationForm(commonSettingsForm):
     ignore_whitespace = BooleanField('Ignore whitespace')
     real_browser_save_screenshot = BooleanField('Save last screenshot when using Chrome?')
     removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
+    empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
     render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
     fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
     password = SaltyPasswordField()
 
+    filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',
+                                                                  render_kw={"style": "width: 5em;"},
+                                                                  validators=[validators.NumberRange(min=0,
+                                                                                                     message="Should contain zero or more attempts")])
+
 
 class globalSettingsForm(Form):
     # Define these as FormFields/"sub forms", this way it matches the JSON storage
@@ -382,4 +403,3 @@ class globalSettingsForm(Form):
     requests = FormField(globalSettingsRequestForm)
     application = FormField(globalSettingsApplicationForm)
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
-

changedetectionio/html_tools.py

@@ -1,5 +1,4 @@
 import json
-import re
 from typing import List
 
 from bs4 import BeautifulSoup
@@ -8,16 +7,23 @@ import re
 from inscriptis import get_text
 from inscriptis.model.config import ParserConfig
 
+class FilterNotFoundInResponse(ValueError):
+    def __init__(self, msg):
+        ValueError.__init__(self, msg)
 
 class JSONNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
 
+
 # Given a CSS Rule, and a blob of HTML, return the blob of HTML that matches
 def css_filter(css_filter, html_content):
     soup = BeautifulSoup(html_content, "html.parser")
     html_block = ""
-    for item in soup.select(css_filter, separator=""):
+    r = soup.select(css_filter, separator="")
+    if len(html_content) > 0 and len(r) == 0:
+        raise FilterNotFoundInResponse(css_filter)
+    for item in r:
         html_block += str(item)
 
     return html_block + "\n"
@@ -39,11 +45,15 @@ def element_removal(selectors: List[str], html_content):
 def xpath_filter(xpath_filter, html_content):
     from lxml import etree, html
 
-    tree = html.fromstring(html_content)
+    tree = html.fromstring(bytes(html_content, encoding='utf-8'))
     html_block = ""
 
-    for item in tree.xpath(xpath_filter.strip(), namespaces={'re':'http://exslt.org/regular-expressions'}):
-        html_block+= etree.tostring(item, pretty_print=True).decode('utf-8')+"<br/>"
+    r = tree.xpath(xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'})
+    if len(html_content) > 0 and len(r) == 0:
+        raise FilterNotFoundInResponse(xpath_filter)
+
+    for item in r:
+        html_block += etree.tostring(item, pretty_print=True).decode('utf-8') + "<br/>"
 
     return html_block
 
@@ -202,3 +212,17 @@ def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
 
     return text_content
 
+def workarounds_for_obfuscations(content):
+    """
+    Some sites are using sneaky tactics to make prices and other information un-renderable by Inscriptis
+    This could go into its own Pip package in the future, for faster updates
+    """
+
+    # HomeDepot.com style <span>$<!-- -->90<!-- -->.<!-- -->74</span>
+    # https://github.com/weblyzard/inscriptis/issues/45
+    if not content:
+        return content
+
+    content = re.sub('<!--\s+-->', '', content)
+
+    return content

changedetectionio/importer.py

@@ -0,0 +1,130 @@
+from abc import ABC, abstractmethod
+import time
+import validators
+
+
+class Importer():
+    remaining_data = []
+    new_uuids = []
+    good = 0
+
+    def __init__(self):
+        self.new_uuids = []
+        self.good = 0
+        self.remaining_data = []
+
+    @abstractmethod
+    def run(self,
+            data,
+            flash,
+            datastore):
+        pass
+
+
+class import_url_list(Importer):
+    """
+    Imports a list, can be in <code>https://example.com tag1, tag2, last tag</code> format
+    """
+    def run(self,
+            data,
+            flash,
+            datastore,
+            ):
+
+        urls = data.split("\n")
+        good = 0
+        now = time.time()
+
+        if (len(urls) > 5000):
+            flash("Importing 5,000 of the first URLs from your list, the rest can be imported again.")
+
+        for url in urls:
+            url = url.strip()
+            if not len(url):
+                continue
+
+            tags = ""
+
+            # 'tags' should be a csv list after the URL
+            if ' ' in url:
+                url, tags = url.split(" ", 1)
+
+            # Flask wtform validators wont work with basic auth, use validators package
+            # Up to 5000 per batch so we dont flood the server
+            if len(url) and validators.url(url.replace('source:', '')) and good < 5000:
+                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False)
+                if new_uuid:
+                    # Straight into the queue.
+                    self.new_uuids.append(new_uuid)
+                    good += 1
+                    continue
+
+            # Worked past the 'continue' above, append it to the bad list
+            if self.remaining_data is None:
+                self.remaining_data = []
+            self.remaining_data.append(url)
+
+        flash("{} Imported from list in {:.2f}s, {} Skipped.".format(good, time.time() - now, len(self.remaining_data)))
+
+
+class import_distill_io_json(Importer):
+    def run(self,
+            data,
+            flash,
+            datastore,
+            ):
+
+        import json
+        good = 0
+        now = time.time()
+        self.new_uuids=[]
+
+
+        try:
+            data = json.loads(data.strip())
+        except json.decoder.JSONDecodeError:
+            flash("Unable to read JSON file, was it broken?", 'error')
+            return
+
+        if not data.get('data'):
+            flash("JSON structure looks invalid, was it broken?", 'error')
+            return
+
+        for d in data.get('data'):
+            d_config = json.loads(d['config'])
+            extras = {'title': d.get('name', None)}
+
+            if len(d['uri']) and good < 5000:
+                try:
+                    # @todo we only support CSS ones at the moment
+                    if d_config['selections'][0]['frames'][0]['excludes'][0]['type'] == 'css':
+                        extras['subtractive_selectors'] = d_config['selections'][0]['frames'][0]['excludes'][0]['expr']
+                except KeyError:
+                    pass
+                except IndexError:
+                    pass
+
+                try:
+                    extras['css_filter'] = d_config['selections'][0]['frames'][0]['includes'][0]['expr']
+                    if d_config['selections'][0]['frames'][0]['includes'][0]['type'] == 'xpath':
+                        extras['css_filter'] = 'xpath:' + extras['css_filter']
+
+                except KeyError:
+                    pass
+                except IndexError:
+                    pass
+
+
+                if d.get('tags', False):
+                    extras['tag'] = ", ".join(d['tags'])
+
+                new_uuid = datastore.add_watch(url=d['uri'].strip(),
+                                               extras=extras,
+                                               write_to_disk_now=False)
+
+                if new_uuid:
+                    # Straight into the queue.
+                    self.new_uuids.append(new_uuid)
+                    good += 1
+
+        flash("{} Imported from Distill.io in {:.2f}s, {} Skipped.".format(len(self.new_uuids), time.time() - now, len(self.remaining_data)))

changedetectionio/model/App.py

@@ -1,38 +1,41 @@
-import collections
-import os
-
-import uuid as uuid_builder
-
+from os import getenv
 from changedetectionio.notification import (
     default_notification_body,
     default_notification_format,
     default_notification_title,
 )
 
+_FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT = 6
+
 class model(dict):
     base_config = {
             'note': "Hello! If you change this file manually, please be sure to restart your changedetection.io instance!",
             'watching': {},
             'settings': {
                 'headers': {
-                    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36',
+                    'User-Agent': 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'),
                     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
                     'Accept-Encoding': 'gzip, deflate',  # No support for brolti in python requests yet.
                     'Accept-Language': 'en-GB,en-US;q=0.9,en;'
                 },
                 'requests': {
-                    'timeout': 15,  # Default 15 seconds
+                    'timeout': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
                     'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
-                    'workers': 10  # Number of threads, lower is better for slow connections
+                    'jitter_seconds': 0,
+                    'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "10")),  # Number of threads, lower is better for slow connections
+                    'proxy': None # Preferred proxy connection
                 },
                 'application': {
+                    'api_access_token_enabled': True,
                     'password': False,
                     'base_url' : None,
                     'extract_title_as_title': False,
-                    'fetch_backend': os.getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
+                    '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': False,
+                    'ignore_whitespace': True,
                     'render_anchor_tag_content': False,
                     'notification_urls': [], # Apprise URL list
                     # Custom notification content
@@ -40,7 +43,8 @@ class model(dict):
                     'notification_body': default_notification_body,
                     'notification_format': default_notification_format,
                     'real_browser_save_screenshot': True,
-                    'schema_version' : 0
+                    'schema_version' : 0,
+                    'webdriver_delay': None  # Extra delay in seconds before extracting text
                 }
             }
         }

changedetectionio/model/Watch.py

@@ -1,8 +1,8 @@
 import os
-
 import uuid as uuid_builder
 
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
+mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
 
 from changedetectionio.notification import (
     default_notification_body,
@@ -12,44 +12,147 @@ from changedetectionio.notification import (
 
 
 class model(dict):
-    base_config = {
+    __newest_history_key = None
+    __history_n=0
+    __base_config = {
             'url': None,
             'tag': None,
             'last_checked': 0,
             'last_changed': 0,
             'paused': False,
             'last_viewed': 0,  # history key value of the last viewed via the [diff] link
-            'newest_history_key': 0,
+            #'newest_history_key': 0,
             'title': None,
             'previous_md5': False,
-#           UUID not needed, should be generated only as a key
-#            'uuid':
+            'uuid': str(uuid_builder.uuid4()),
             'headers': {},  # Extra headers to send
             'body': None,
             'method': 'GET',
-            'history': {},  # Dict of timestamp and output stripped filename
+            #'history': {},  # Dict of timestamp and output stripped filename
             'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
             # Custom notification content
             'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
             'notification_title': default_notification_title,
             'notification_body': default_notification_body,
             'notification_format': default_notification_format,
-            'css_filter': "",
+            'css_filter': '',
+            'extract_text': [],  # Extract text by regex after filters
             'subtractive_selectors': [],
             'trigger_text': [],  # List of text or regex to wait for until a change is detected
+            'text_should_not_be_present': [], # Text that should not present
             'fetch_backend': None,
+            'filter_failure_notification_send': True,
+            'consecutive_filter_failures': 0, # Every time the CSS/xPath filter cannot be located, reset when all is fine.
             'extract_title_as_title': False,
+            'check_unique_lines': False, # On change-detected, compare against all history if its something new
+            'proxy': None, # Preferred proxy connection
             # Re #110, so then if this is set to None, we know to use the default value instead
             # Requires setting to None on submit if it's the same as the default
             # Should be all None by default, so we use the system default in this case.
-            'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None}
+            'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
+            'webdriver_delay': None,
+            'webdriver_js_execute_code': None, # Run before change-detection
         }
+    jitter_seconds = 0
 
     def __init__(self, *arg, **kw):
-        self.update(self.base_config)
+        import uuid
+        self.update(self.__base_config)
+        self.__datastore_path = kw['datastore_path']
+
+        self['uuid'] = str(uuid.uuid4())
+
+        del kw['datastore_path']
+
+        if kw.get('default'):
+            self.update(kw['default'])
+            del kw['default']
+
         # goes at the end so we update the default object with the initialiser
         super(model, self).__init__(*arg, **kw)
 
+    @property
+    def viewed(self):
+        if int(self['last_viewed']) >= int(self.newest_history_key) :
+            return True
+
+        return False
+
+    @property
+    def history_n(self):
+        return self.__history_n
+
+    @property
+    def history(self):
+        tmp_history = {}
+        import logging
+        import time
+
+        # Read the history file as a dict
+        fname = os.path.join(self.__datastore_path, self.get('uuid'), "history.txt")
+        if os.path.isfile(fname):
+            logging.debug("Reading history index " + str(time.time()))
+            with open(fname, "r") as f:
+                tmp_history = dict(i.strip().split(',', 2) for i in f.readlines())
+
+        if len(tmp_history):
+            self.__newest_history_key = list(tmp_history.keys())[-1]
+
+        self.__history_n = len(tmp_history)
+
+        return tmp_history
+
+    @property
+    def has_history(self):
+        fname = os.path.join(self.__datastore_path, self.get('uuid'), "history.txt")
+        return os.path.isfile(fname)
+
+    # Returns the newest key, but if theres only 1 record, then it's counted as not being new, so return 0.
+    @property
+    def newest_history_key(self):
+        if self.__newest_history_key is not None:
+            return self.__newest_history_key
+
+        if len(self.history) <= 1:
+            return 0
+
+
+        bump = self.history
+        return self.__newest_history_key
+
+
+    # Save some text file to the appropriate path and bump the history
+    # result_obj from fetch_site_status.run()
+    def save_history_text(self, contents, timestamp):
+        import uuid
+        from os import mkdir, path, unlink
+        import logging
+
+        output_path = "{}/{}".format(self.__datastore_path, self['uuid'])
+
+        # Incase the operator deleted it, check and create.
+        if not os.path.isdir(output_path):
+            mkdir(output_path)
+
+        snapshot_fname = "{}/{}.stripped.txt".format(output_path, uuid.uuid4())
+        logging.debug("Saving history text {}".format(snapshot_fname))
+
+        with open(snapshot_fname, 'wb') as f:
+            f.write(contents)
+            f.close()
+
+        # Append to index
+        # @todo check last char was \n
+        index_fname = "{}/history.txt".format(output_path)
+        with open(index_fname, 'a') as f:
+            f.write("{},{}\n".format(timestamp, snapshot_fname))
+            f.close()
+
+        self.__newest_history_key = timestamp
+        self.__history_n+=1
+
+        #@todo bump static cache of the last timestamp so we dont need to examine the file to set a proper ''viewed'' status
+        return snapshot_fname
 
     @property
     def has_empty_checktime(self):
@@ -60,9 +163,21 @@ class model(dict):
 
     def threshold_seconds(self):
         seconds = 0
-        mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
         for m, n in mtable.items():
             x = self.get('time_between_check', {}).get(m, None)
             if x:
                 seconds += x * n
         return seconds
+
+    # Iterate over all history texts and see if something new exists
+    def lines_contain_something_unique_compared_to_history(self, lines=[]):
+        local_lines = [l.decode('utf-8').strip().lower() for l in lines]
+
+        # Compare each lines (set) against each history text file (set) looking for something new..
+        for k, v in self.history.items():
+            alist = [line.decode('utf-8').strip().lower() for line in open(v, 'rb')]
+            res = set(alist) != set(local_lines)
+            if res:
+                return True
+
+        return False

changedetectionio/notification.py

@@ -34,7 +34,6 @@ def process_notification(n_object, datastore):
         valid_notification_formats[default_notification_format],
     )
 
-
     # Insert variables into the notification content
     notification_parameters = create_notification_parameters(n_object, datastore)
 
@@ -48,9 +47,10 @@ def process_notification(n_object, datastore):
     # Anything higher than or equal to WARNING (which covers things like Connection errors)
     # raise it as an exception
     apobjs=[]
+    sent_objs=[]
+    from .apprise_asset import asset
     for url in n_object['notification_urls']:
-
-        apobj = apprise.Apprise(debug=True)
+        apobj = apprise.Apprise(debug=True, asset=asset)
         url = url.strip()
         if len(url):
             print(">> Process Notification: AppRise notifying {}".format(url))
@@ -63,23 +63,36 @@ def process_notification(n_object, datastore):
 
                 # So if no avatar_url is specified, add one so it can be correctly calculated into the total payload
                 k = '?' if not '?' in url else '&'
-                if not 'avatar_url' in url:
+                if not 'avatar_url' in url and not url.startswith('mail'):
                     url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
 
                 if url.startswith('tgram://'):
+                    # Telegram only supports a limit subset of HTML, remove the '<br/>' we place in.
+                    # re https://github.com/dgtlmoon/changedetection.io/issues/555
+                    # @todo re-use an existing library we have already imported to strip all non-allowed tags
+                    n_body = n_body.replace('<br/>', '\n')
+                    n_body = n_body.replace('</br>', '\n')
                     # real limit is 4096, but minus some for extra metadata
                     payload_max_size = 3600
                     body_limit = max(0, payload_max_size - len(n_title))
                     n_title = n_title[0:payload_max_size]
                     n_body = n_body[0:body_limit]
 
-                elif url.startswith('discord://'):
+                elif url.startswith('discord://') or url.startswith('https://discordapp.com/api/webhooks'):
                     # real limit is 2000, but minus some for extra metadata
                     payload_max_size = 1700
                     body_limit = max(0, payload_max_size - len(n_title))
                     n_title = n_title[0:payload_max_size]
                     n_body = n_body[0:body_limit]
 
+                elif url.startswith('mailto'):
+                    # Apprise will default to HTML, so we need to override it
+                    # So that whats' generated in n_body is in line with what is going to be sent.
+                    # https://github.com/caronc/apprise/issues/633#issuecomment-1191449321
+                    if not 'format=' in url and (n_format == 'text' or n_format == 'markdown'):
+                        prefix = '?' if not '?' in url else '&'
+                        url = "{}{}format={}".format(url, prefix, n_format)
+
                 apobj.add(url)
 
                 apobj.notify(
@@ -96,6 +109,15 @@ def process_notification(n_object, datastore):
                 log_value = logs.getvalue()
                 if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
                     raise Exception(log_value)
+                
+                sent_objs.append({'title': n_title,
+                                  'body': n_body,
+                                  'url' : url,
+                                  'body_format': n_format})
+
+    # Return what was sent for better logging - after the for loop
+    return sent_objs
+
 
 # Notification title + body content parameters get created here.
 def create_notification_parameters(n_object, datastore):

changedetectionio/run_all_tests.sh

@@ -22,3 +22,26 @@ echo "RUNNING WITH BASE_URL SET"
 export BASE_URL="https://really-unique-domain.io"
 pytest tests/test_notification.py
 
+
+# Now for the selenium and playwright/browserless fetchers
+# Note - this is not UI functional tests - just checking that each one can fetch the content
+
+echo "TESTING WEBDRIVER FETCH > SELENIUM/WEBDRIVER..."
+docker run -d --name $$-test_selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome-debug:3.141.59
+# takes a while to spin up
+sleep 5
+export WEBDRIVER_URL=http://localhost:4444/wd/hub
+pytest tests/fetchers/test_content.py
+unset WEBDRIVER_URL
+docker kill $$-test_selenium
+
+echo "TESTING WEBDRIVER FETCH > PLAYWRIGHT/BROWSERLESS..."
+# Not all platforms support playwright (not ARM/rPI), so it's not packaged in requirements.txt
+pip3 install playwright~=1.22
+docker run -d --name $$-test_browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
+# takes a while to spin up
+sleep 5
+export PLAYWRIGHT_DRIVER_URL=ws://127.0.0.1:3000
+pytest tests/fetchers/test_content.py
+unset PLAYWRIGHT_DRIVER_URL
+docker kill $$-test_browserless

changedetectionio/static/images/spread-white.svg

@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   width="18"
+   height="19.92"
+   viewBox="0 0 18 19.92"
+   version="1.1"
+   id="svg6"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg">
+  <defs
+     id="defs10" />
+  <path
+     d="M -3,-2 H 21 V 22 H -3 Z"
+     fill="none"
+     id="path2" />
+  <path
+     d="m 15,14.08 c -0.76,0 -1.44,0.3 -1.96,0.77 L 5.91,10.7 C 5.96,10.47 6,10.24 6,10 6,9.76 5.96,9.53 5.91,9.3 L 12.96,5.19 C 13.5,5.69 14.21,6 15,6 16.66,6 18,4.66 18,3 18,1.34 16.66,0 15,0 c -1.66,0 -3,1.34 -3,3 0,0.24 0.04,0.47 0.09,0.7 L 5.04,7.81 C 4.5,7.31 3.79,7 3,7 1.34,7 0,8.34 0,10 c 0,1.66 1.34,3 3,3 0.79,0 1.5,-0.31 2.04,-0.81 l 7.12,4.16 c -0.05,0.21 -0.08,0.43 -0.08,0.65 0,1.61 1.31,2.92 2.92,2.92 1.61,0 2.92,-1.31 2.92,-2.92 0,-1.61 -1.31,-2.92 -2.92,-2.92 z"
+     id="path4"
+     style="fill:#ffffff;fill-opacity:1" />
+</svg>

changedetectionio/static/js/diff-overview.js

@@ -0,0 +1,17 @@
+$(document).ready(function () {
+    // Load it when the #screenshot tab is in use, so we dont give a slow experience when waiting for the text diff to load
+    window.addEventListener('hashchange', function (e) {
+        toggle(location.hash);
+    }, false);
+
+    toggle(location.hash);
+
+    function toggle(hash_name) {
+        if (hash_name === '#screenshot') {
+            $("img#screenshot-img").attr('src', screenshot_url);
+            $("#settings").hide();
+        } else {
+            $("#settings").show();
+        }
+    }
+});

changedetectionio/static/js/global-settings.js

@@ -0,0 +1,36 @@
+$(document).ready(function () {
+    function toggle() {
+        if ($('input[name="application-fetch_backend"]:checked').val() != 'html_requests') {
+            $('#requests-override-options').hide();
+            $('#webdriver-override-options').show();
+        } else {
+            $('#requests-override-options').show();
+            $('#webdriver-override-options').hide();
+        }
+    }
+
+    $('input[name="application-fetch_backend"]').click(function (e) {
+        toggle();
+    });
+    toggle();
+
+    $("#api-key").hover(
+        function () {
+            $("#api-key-copy").html('copy').fadeIn();
+        },
+        function () {
+            $("#api-key-copy").hide();
+        }
+    ).click(function (e) {
+        $("#api-key-copy").html('copied');
+        var range = document.createRange();
+        var n = $("#api-key")[0];
+        range.selectNode(n);
+        window.getSelection().removeAllRanges();
+        window.getSelection().addRange(range);
+        document.execCommand("copy");
+        window.getSelection().removeAllRanges();
+
+    });
+});
+

changedetectionio/static/js/limit.js

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

changedetectionio/static/js/notifications.js

@@ -40,13 +40,19 @@ $(document).ready(function() {
     $.ajax({
       type: "POST",
       url: notification_base_url,
-      data : data
+      data : data,
+        statusCode: {
+        400: function() {
+            // More than likely the CSRF token was lost when the server restarted
+          alert("There was a problem processing the request, please reload the page.");
+        }
+      }
     }).done(function(data){
       console.log(data);
       alert('Sent');
     }).fail(function(data){
       console.log(data);
-      alert('Error: '+data.responseJSON.error);
+      alert('There was an error communicating with the server.');
     })
   });
 });

changedetectionio/static/js/settings.js

@@ -1,13 +0,0 @@
-window.addEventListener("load", (event) => {
-  // just an example for now
-  function toggleVisible(elem) {
-    // theres better ways todo this
-    var x = document.getElementById(elem);
-    if (x.style.display === "block") {
-      x.style.display = "none";
-    } else {
-      x.style.display = "block";
-    }
-  }
-});
-

changedetectionio/static/js/visual-selector.js

@@ -0,0 +1,230 @@
+// Horrible proof of concept code :)
+// yes - this is really a hack, if you are a front-ender and want to help, please get in touch!
+
+$(document).ready(function() {
+
+    var current_selected_i;
+    var state_clicked=false;
+
+    var c;
+
+    // greyed out fill context
+    var xctx;
+    // redline highlight context
+    var ctx;
+
+    var current_default_xpath;
+    var x_scale=1;
+    var y_scale=1;
+    var selector_image;
+    var selector_image_rect;
+    var selector_data;
+
+    $('#visualselector-tab').click(function () {
+        $("img#selector-background").off('load');
+        state_clicked = false;
+        current_selected_i = false;
+        bootstrap_visualselector();
+    });
+
+    $(document).on('keydown', function(event) {
+        if ($("img#selector-background").is(":visible")) {
+            if (event.key == "Escape") {
+                state_clicked=false;
+                ctx.clearRect(0, 0, c.width, c.height);
+            }
+        }
+    });
+
+    // For when the page loads
+    if(!window.location.hash || window.location.hash != '#visualselector') {
+        $("img#selector-background").attr('src','');
+        return;
+    }
+
+    // Handle clearing button/link
+    $('#clear-selector').on('click', function(event) {
+        if(!state_clicked) {
+            alert('Oops, Nothing selected!');
+        }
+        state_clicked=false;
+        ctx.clearRect(0, 0, c.width, c.height);
+        xctx.clearRect(0, 0, c.width, c.height);
+        $("#css_filter").val('');
+    });
+
+
+    bootstrap_visualselector();
+
+
+
+    function bootstrap_visualselector() {
+        if ( 1 ) {
+            // bootstrap it, this will trigger everything else
+            $("img#selector-background").bind('load', function () {
+                console.log("Loaded background...");
+               c = document.getElementById("selector-canvas");
+                // greyed out fill context
+               xctx = c.getContext("2d");
+                // redline highlight context
+               ctx = c.getContext("2d");
+               current_default_xpath =$("#css_filter").val();
+               fetch_data();
+               $('#selector-canvas').off("mousemove mousedown");
+               // screenshot_url defined in the edit.html template
+            }).attr("src", screenshot_url);
+        }
+    }
+
+    function fetch_data() {
+      // Image is ready
+      $('.fetching-update-notice').html("Fetching element data..");
+
+      $.ajax({
+        url: watch_visual_selector_data_url,
+        context: document.body
+      }).done(function (data) {
+        $('.fetching-update-notice').html("Rendering..");
+        selector_data = data;
+        console.log("Reported browser width from backend: "+data['browser_width']);
+        state_clicked=false;
+        set_scale();
+        reflow_selector();
+        $('.fetching-update-notice').fadeOut();
+      });
+    };
+
+
+
+    function set_scale() {
+
+      // some things to check if the scaling doesnt work
+      // - that the widths/sizes really are about the actual screen size cat elements.json |grep -o width......|sort|uniq
+      selector_image = $("img#selector-background")[0];
+      selector_image_rect = selector_image.getBoundingClientRect();
+
+      // make the canvas the same size as the image
+      $('#selector-canvas').attr('height', selector_image_rect.height);
+      $('#selector-canvas').attr('width', selector_image_rect.width);
+      $('#selector-wrapper').attr('width', selector_image_rect.width);
+      x_scale = selector_image_rect.width / selector_data['browser_width'];
+      y_scale = selector_image_rect.height / selector_image.naturalHeight;
+      ctx.strokeStyle = 'rgba(255,0,0, 0.9)';
+      ctx.fillStyle = 'rgba(255,0,0, 0.1)';
+      ctx.lineWidth = 3;
+      console.log("scaling set  x: "+x_scale+" by y:"+y_scale);
+      $("#selector-current-xpath").css('max-width', selector_image_rect.width);
+    }
+
+    function reflow_selector() {
+        $(window).resize(function() {
+            set_scale();
+            highlight_current_selected_i();
+        });
+      var selector_currnt_xpath_text=$("#selector-current-xpath span");
+
+      set_scale();
+
+      console.log(selector_data['size_pos'].length + " selectors found");
+
+      // highlight the default one if we can find it in the xPath list
+      // or the xpath matches the default one
+      found = false;
+      if(current_default_xpath.length) {
+          for (var i = selector_data['size_pos'].length; i!==0; i--) {
+            var sel = selector_data['size_pos'][i-1];
+            if(selector_data['size_pos'][i - 1].xpath == current_default_xpath) {
+            console.log("highlighting "+current_default_xpath);
+              current_selected_i = i-1;
+              highlight_current_selected_i();
+              found = true;
+              break;
+            }
+          }
+        if(!found) {
+          alert("Unfortunately your existing CSS/xPath Filter was no longer found!");
+        }
+      }
+
+
+      $('#selector-canvas').bind('mousemove', function (e) {
+        if(state_clicked) {
+          return;
+        }
+        ctx.clearRect(0, 0, c.width, c.height);
+        current_selected_i=null;
+
+        // Add in offset
+        if ((typeof e.offsetX === "undefined" || typeof e.offsetY === "undefined") || (e.offsetX === 0 && e.offsetY === 0)) {
+          var targetOffset = $(e.target).offset();
+          e.offsetX = e.pageX - targetOffset.left;
+          e.offsetY = e.pageY - targetOffset.top;
+        }
+
+        // Reverse order - the most specific one should be deeper/"laster"
+        // Basically, find the most 'deepest'
+        var found=0;
+        ctx.fillStyle = 'rgba(205,0,0,0.35)';
+        for (var i = selector_data['size_pos'].length; i!==0; i--) {
+          // draw all of them? let them choose somehow?
+          var sel = selector_data['size_pos'][i-1];
+          // If we are in a bounding-box
+          if (e.offsetY > sel.top * y_scale && e.offsetY < sel.top * y_scale + sel.height * y_scale
+              &&
+              e.offsetX > sel.left * y_scale && e.offsetX < sel.left * y_scale + sel.width * y_scale
+
+          ) {
+
+            // FOUND ONE
+            set_current_selected_text(sel.xpath);
+            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);
+
+            // no need to keep digging
+            // @todo or, O to go out/up, I to go in
+            // or double click to go up/out the selector?
+            current_selected_i=i-1;
+            found+=1;
+            break;
+          }
+        }
+
+      }.debounce(5));
+
+      function set_current_selected_text(s) {
+        selector_currnt_xpath_text[0].innerHTML=s;
+      }
+
+      function highlight_current_selected_i() {
+        if(state_clicked) {
+          state_clicked=false;
+          xctx.clearRect(0,0,c.width, c.height);
+          return;
+        }
+
+        var sel = selector_data['size_pos'][current_selected_i];
+        if (sel[0] == '/') {
+        // @todo - not sure just checking / is right
+            $("#css_filter").val('xpath:'+sel.xpath);
+        } else {
+            $("#css_filter").val(sel.xpath);
+        }
+        xctx.fillStyle = 'rgba(205,205,205,0.95)';
+        xctx.strokeStyle = 'rgba(225,0,0,0.9)';
+        xctx.lineWidth = 3;
+        xctx.fillRect(0,0,c.width, c.height);
+        // Clear out what only should be seen (make a clear/clean spot)
+        xctx.clearRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+        xctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+        state_clicked=true;
+        set_current_selected_text(sel.xpath);
+
+      }
+
+
+      $('#selector-canvas').bind('mousedown', function (e) {
+        highlight_current_selected_i();
+      });
+    }
+
+});

changedetectionio/static/js/watch-overview.js

@@ -4,6 +4,7 @@ $(function () {
     $(this).closest('.unviewed').removeClass('unviewed');
   });
 
+
   $('.with-share-link > *').click(function () {
       $("#copied-clipboard").remove();
 
@@ -20,5 +21,6 @@ $(function () {
        $(this).remove();
       });
   });
+
 });
 

changedetectionio/static/js/watch-settings.js

@@ -0,0 +1,33 @@
+$(document).ready(function() {
+    function toggle() {
+        if ($('input[name="fetch_backend"]:checked').val() == 'html_webdriver') {
+            if(playwright_enabled) {
+                // playwright supports headers, so hide everything else
+                // See #664
+                $('#requests-override-options #request-method').hide();
+                $('#requests-override-options #request-body').hide();
+
+                // @todo connect this one up
+                $('#ignore-status-codes-option').hide();
+            } else {
+                // selenium/webdriver doesnt support anything afaik, hide it all
+                $('#requests-override-options').hide();
+            }
+
+
+            $('#webdriver-override-options').show();
+
+        } else {
+
+            $('#requests-override-options').show();
+            $('#requests-override-options *:hidden').show();
+            $('#webdriver-override-options').hide();
+        }
+    }
+
+    $('input[name="fetch_backend"]').click(function (e) {
+        toggle();
+    });
+    toggle();
+
+});

changedetectionio/static/styles/.gitignore

@@ -1 +1,3 @@
 node_modules
+package-lock.json
+

changedetectionio/static/styles/styles.css

@@ -284,6 +284,11 @@ footer {
 .pure-form {
   /* The input fields with errors */
   /* The list of errors */ }
+  .pure-form fieldset {
+    padding-top: 0px; }
+    .pure-form fieldset ul {
+      padding-bottom: 0px;
+      margin-bottom: 0px; }
   .pure-form .pure-control-group, .pure-form .pure-group, .pure-form .pure-controls {
     padding-bottom: 1em; }
     .pure-form .pure-control-group div, .pure-form .pure-group div, .pure-form .pure-controls div {
@@ -309,10 +314,10 @@ footer {
     font-weight: bold; }
   .pure-form textarea {
     width: 100%; }
-  .pure-form ul.fetch-backend {
+  .pure-form .inline-radio ul {
     margin: 0px;
     list-style: none; }
-    .pure-form ul.fetch-backend li > * {
+    .pure-form .inline-radio ul li > * {
       display: inline-block; }
 
 @media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 1024px) {
@@ -333,7 +338,8 @@ footer {
     padding-top: 110px; }
   div.tabs.collapsable ul li {
     display: block;
-    border-radius: 0px; }
+    border-radius: 0px;
+    margin-right: 0px; }
   input[type='text'] {
     width: 100%; }
   /*
@@ -347,6 +353,8 @@ and also iPads specifically.
     /* Hide table headers (but not display: none;, for accessibility) */ }
     .watch-table thead, .watch-table tbody, .watch-table th, .watch-table td, .watch-table tr {
       display: block; }
+    .watch-table .last-checked > span {
+      vertical-align: middle; }
     .watch-table .last-checked::before {
       color: #555;
       content: "Last Checked "; }
@@ -364,7 +372,8 @@ and also iPads specifically.
     .watch-table td {
       /* Behave  like a "row" */
       border: none;
-      border-bottom: 1px solid #eee; }
+      border-bottom: 1px solid #eee;
+      vertical-align: middle; }
       .watch-table td:before {
         /* Top/left values mimic padding */
         top: 6px;
@@ -424,6 +433,15 @@ and also iPads specifically.
   .tab-pane-inner:target {
     display: block; }
 
+#beta-logo {
+  height: 50px;
+  right: -3px;
+  top: -3px;
+  position: absolute; }
+
+#selector-header {
+  padding-bottom: 1em; }
+
 .edit-form {
   min-width: 70%;
   /* so it cant overflow */
@@ -447,4 +465,70 @@ ul {
 .time-check-widget tr {
   display: inline; }
   .time-check-widget tr input[type="number"] {
-    width: 4em; }
+    width: 5em; }
+
+#selector-wrapper {
+  height: 600px;
+  overflow-y: scroll;
+  position: relative; }
+  #selector-wrapper > img {
+    position: absolute;
+    z-index: 4;
+    max-width: 100%; }
+  #selector-wrapper > canvas {
+    position: relative;
+    z-index: 5;
+    max-width: 100%; }
+    #selector-wrapper > canvas:hover {
+      cursor: pointer; }
+
+#selector-current-xpath {
+  font-size: 80%; }
+
+#webdriver-override-options input[type="number"] {
+  width: 5em; }
+
+#api-key:hover {
+  cursor: pointer; }
+
+#api-key-copy {
+  color: #0078e7; }
+
+/* spinner */
+.loader,
+.loader:after {
+  border-radius: 50%;
+  width: 10px;
+  height: 10px; }
+
+.loader {
+  margin: 0px auto;
+  font-size: 3px;
+  vertical-align: middle;
+  display: inline-block;
+  text-indent: -9999em;
+  border-top: 1.1em solid rgba(38, 104, 237, 0.2);
+  border-right: 1.1em solid rgba(38, 104, 237, 0.2);
+  border-bottom: 1.1em solid rgba(38, 104, 237, 0.2);
+  border-left: 1.1em solid #2668ed;
+  -webkit-transform: translateZ(0);
+  -ms-transform: translateZ(0);
+  transform: translateZ(0);
+  -webkit-animation: load8 1.1s infinite linear;
+  animation: load8 1.1s infinite linear; }
+
+@-webkit-keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg); }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg); } }
+
+@keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg); }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg); } }

changedetectionio/static/styles/styles.scss

@@ -375,6 +375,13 @@ footer {
 
 
 .pure-form {
+    fieldset {
+        padding-top: 0px;
+        ul {
+            padding-bottom: 0px;
+            margin-bottom: 0px;
+        }
+    }
     .pure-control-group, .pure-group, .pure-controls {
         padding-bottom: 1em;
         div {
@@ -418,14 +425,16 @@ footer {
   textarea {
     width: 100%;
   }
-  ul.fetch-backend {
-    margin: 0px;
-    list-style: none;
-    li {
-        > * {
-            display: inline-block;
+  .inline-radio {
+      ul {
+        margin: 0px;
+        list-style: none;
+        li {
+            > * {
+                display: inline-block;
+            }
         }
-    }
+      }
   }
 }
 
@@ -460,6 +469,7 @@ footer {
   div.tabs.collapsable ul li {
     display: block;
     border-radius: 0px;
+    margin-right: 0px;
   }
 
   input[type='text'] {
@@ -477,6 +487,11 @@ and also iPads specifically.
       display: block;
     }
 
+    .last-checked {
+      > span {
+        vertical-align: middle;
+      }
+    }
     .last-checked::before {
       color: #555;
       content: "Last Checked ";
@@ -507,7 +522,7 @@ and also iPads specifically.
       /* Behave  like a "row" */
       border: none;
       border-bottom: 1px solid #eee;
-
+      vertical-align: middle;
       &:before {
         /* Top/left values mimic padding */
         top: 6px;
@@ -604,6 +619,18 @@ $form-edge-padding: 20px;
     padding: 0px;
 }
 
+#beta-logo {
+    height: 50px;
+    // looks better when it's hanging off a little
+    right: -3px;
+    top: -3px;
+    position: absolute;
+}
+
+#selector-header {
+    padding-bottom: 1em;
+}
+
 .edit-form {
   min-width: 70%;
   /* so it cant overflow */
@@ -635,7 +662,92 @@ ul {
     tr {
         display: inline;
         input[type="number"] {
-            width: 4em;
+            width: 5em;
         }
     }
-}
+}
+
+#selector-wrapper {
+ height: 600px;
+ overflow-y: scroll;
+ position: relative;
+    //width: 100%;
+ > img {
+    position: absolute;
+    z-index: 4;
+    max-width: 100%;
+ }
+ >canvas {
+    position: relative;
+    z-index: 5;
+     max-width: 100%;
+     &:hover {
+     cursor: pointer;
+     }
+ }
+}
+
+#selector-current-xpath {
+  font-size: 80%;
+}
+
+#webdriver-override-options {
+        input[type="number"] {
+            width: 5em;
+        }
+}
+
+#api-key {
+  &:hover {
+    cursor: pointer;
+  }
+}
+
+#api-key-copy {
+  color: #0078e7;
+}
+
+/* spinner */
+.loader,
+.loader:after {
+  border-radius: 50%;
+  width: 10px;
+  height: 10px;
+}
+.loader {
+  margin: 0px auto;
+  font-size: 3px;
+  vertical-align: middle;
+  display: inline-block;
+  text-indent: -9999em;
+  border-top: 1.1em solid rgba(38,104,237, 0.2);
+  border-right: 1.1em solid rgba(38,104,237, 0.2);
+  border-bottom: 1.1em solid rgba(38,104,237, 0.2);
+  border-left: 1.1em solid #2668ed;
+  -webkit-transform: translateZ(0);
+  -ms-transform: translateZ(0);
+  transform: translateZ(0);
+  -webkit-animation: load8 1.1s infinite linear;
+  animation: load8 1.1s infinite linear;
+}
+@-webkit-keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg);
+  }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg);
+  }
+}
+@keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg);
+  }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg);
+  }
+}
+

changedetectionio/store.py

@@ -12,9 +12,9 @@ from os import mkdir, path, unlink
 from threading import Lock
 import re
 import requests
+import secrets
 
-from changedetectionio.model import Watch, App
-
+from . model import App, Watch
 
 # Is there an existing library to ensure some data store (JSON etc) is in sync with CRUD methods?
 # Open a github issue if you know something :)
@@ -33,13 +33,14 @@ class ChangeDetectionStore:
         self.needs_write = False
         self.datastore_path = datastore_path
         self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
+        self.proxy_list = None
         self.stop_thread = False
 
         self.__data = App.model()
 
         # Base definition for all watchers
         # deepcopy part of #569 - not sure why its needed exactly
-        self.generic_definition = deepcopy(Watch.model())
+        self.generic_definition = deepcopy(Watch.model(datastore_path = datastore_path, default={}))
 
         if path.isfile('changedetectionio/source.txt'):
             with open('changedetectionio/source.txt') as f:
@@ -70,13 +71,10 @@ class ChangeDetectionStore:
                     if 'application' in from_disk['settings']:
                         self.__data['settings']['application'].update(from_disk['settings']['application'])
 
-                # Reinitialise each `watching` with our generic_definition in the case that we add a new var in the future.
-                # @todo pretty sure theres a python we todo this with an abstracted(?) object!
+                # Convert each existing watch back to the Watch.model object
                 for uuid, watch in self.__data['watching'].items():
-                    _blank = deepcopy(self.generic_definition)
-                    _blank.update(watch)
-                    self.__data['watching'].update({uuid: _blank})
-                    self.__data['watching'][uuid]['newest_history_key'] = self.get_newest_history_key(uuid)
+                    watch['uuid']=uuid
+                    self.__data['watching'][uuid] = Watch.model(datastore_path=self.datastore_path, default=watch)
                     print("Watching:", uuid, self.__data['watching'][uuid]['url'])
 
         # First time ran, doesnt exist.
@@ -86,8 +84,7 @@ class ChangeDetectionStore:
 
                 self.add_watch(url='http://www.quotationspage.com/random.php', tag='test')
                 self.add_watch(url='https://news.ycombinator.com/', tag='Tech news')
-                self.add_watch(url='https://www.gov.uk/coronavirus', tag='Covid')
-                self.add_watch(url='https://changedetection.io/CHANGELOG.txt')
+                self.add_watch(url='https://changedetection.io/CHANGELOG.txt', tag='changedetection.io')
 
         self.__data['version_tag'] = version_tag
 
@@ -107,10 +104,21 @@ class ChangeDetectionStore:
 
         # Generate the URL access token for RSS feeds
         if not 'rss_access_token' in self.__data['settings']['application']:
-            import secrets
             secret = secrets.token_hex(16)
             self.__data['settings']['application']['rss_access_token'] = secret
 
+        # Generate the API access token
+        if not 'api_access_token' in self.__data['settings']['application']:
+            secret = secrets.token_hex(16)
+            self.__data['settings']['application']['api_access_token'] = secret
+
+        # Proxy list support - available as a selection in settings when text file is imported
+        # CSV list
+        # "name, address", or just "name"
+        proxy_list_file = "{}/proxies.txt".format(self.datastore_path)
+        if path.isfile(proxy_list_file):
+            self.import_proxy_list(proxy_list_file)
+
         # Bump the update version by running updates
         self.run_updates()
 
@@ -119,23 +127,8 @@ class ChangeDetectionStore:
         # Finally start the thread that will manage periodic data saves to JSON
         save_data_thread = threading.Thread(target=self.save_datastore).start()
 
-    # Returns the newest key, but if theres only 1 record, then it's counted as not being new, so return 0.
-    def get_newest_history_key(self, uuid):
-        if len(self.__data['watching'][uuid]['history']) == 1:
-            return 0
-
-        dates = list(self.__data['watching'][uuid]['history'].keys())
-        # Convert to int, sort and back to str again
-        # @todo replace datastore getter that does this automatically
-        dates = [int(i) for i in dates]
-        dates.sort(reverse=True)
-        if len(dates):
-            # always keyed as str
-            return str(dates[0])
-
-        return 0
-
     def set_last_viewed(self, uuid, timestamp):
+        logging.debug("Setting watch UUID: {} last viewed to {}".format(uuid, int(timestamp)))
         self.data['watching'][uuid].update({'last_viewed': int(timestamp)})
         self.needs_write = True
 
@@ -159,35 +152,32 @@ class ChangeDetectionStore:
                         del (update_obj[dict_key])
 
             self.__data['watching'][uuid].update(update_obj)
-            self.__data['watching'][uuid]['newest_history_key'] = self.get_newest_history_key(uuid)
 
         self.needs_write = True
 
     @property
     def threshold_seconds(self):
         seconds = 0
-        mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
-        minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
-        for m, n in mtable.items():
+        for m, n in Watch.mtable.items():
             x = self.__data['settings']['requests']['time_between_check'].get(m)
             if x:
                 seconds += x * n
-        return max(seconds, minimum_seconds_recheck_time)
+        return seconds
+
+    @property
+    def has_unviewed(self):
+        for uuid, watch in self.__data['watching'].items():
+            if watch.viewed == False:
+                return True
+        return False
 
     @property
     def data(self):
         has_unviewed = False
-        for uuid, v in self.__data['watching'].items():
-            self.__data['watching'][uuid]['newest_history_key'] = self.get_newest_history_key(uuid)
-            if int(v['newest_history_key']) <= int(v['last_viewed']):
-                self.__data['watching'][uuid]['viewed'] = True
-
-            else:
-                self.__data['watching'][uuid]['viewed'] = False
-                has_unviewed = True
-
+        for uuid, watch in self.__data['watching'].items():
             # #106 - Be sure this is None on empty string, False, None, etc
             # Default var for fetch_backend
+            # @todo this may not be needed anymore, or could be easily removed
             if not self.__data['watching'][uuid]['fetch_backend']:
                 self.__data['watching'][uuid]['fetch_backend'] = self.__data['settings']['application']['fetch_backend']
 
@@ -196,14 +186,13 @@ class ChangeDetectionStore:
         if not self.__data['settings']['application']['base_url']:
           self.__data['settings']['application']['base_url'] = env_base_url.strip('" ')
 
-        self.__data['has_unviewed'] = has_unviewed
-
         return self.__data
 
     def get_all_tags(self):
         tags = []
         for uuid, watch in self.data['watching'].items():
-
+            if watch['tag'] is None:
+                continue
             # Support for comma separated list of tags.
             for tag in watch['tag'].split(','):
                 tag = tag.strip()
@@ -227,11 +216,11 @@ class ChangeDetectionStore:
 
                 # GitHub #30 also delete history records
                 for uuid in self.data['watching']:
-                    for path in self.data['watching'][uuid]['history'].values():
+                    for path in self.data['watching'][uuid].history.values():
                         self.unlink_history_file(path)
 
             else:
-                for path in self.data['watching'][uuid]['history'].values():
+                for path in self.data['watching'][uuid].history.values():
                     self.unlink_history_file(path)
 
                 del self.data['watching'][uuid]
@@ -260,18 +249,34 @@ class ChangeDetectionStore:
         return self.data['watching'][uuid].get(val)
 
     # Remove a watchs data but keep the entry (URL etc)
-    def scrub_watch(self, uuid):
+    def clear_watch_history(self, uuid):
         import pathlib
 
-        self.__data['watching'][uuid].update({'history': {}, 'last_checked': 0, 'last_changed': 0, 'newest_history_key': 0, 'previous_md5': False})
-        self.needs_write_urgent = True
+        self.__data['watching'][uuid].update(
+            {'last_checked': 0,
+             'last_changed': 0,
+             'last_viewed': 0,
+             'previous_md5': False,
+             'last_notification_error': False,
+             'last_error': False})
 
-        for item in pathlib.Path(self.datastore_path).rglob(uuid+"/*.txt"):
+        # JSON Data, Screenshots, Textfiles (history index and snapshots), HTML in the future etc
+        for item in pathlib.Path(os.path.join(self.datastore_path, uuid)).rglob("*.*"):
             unlink(item)
 
+        # Force the attr to recalculate
+        bump = self.__data['watching'][uuid].history
+
+        self.needs_write_urgent = True
+
     def add_watch(self, url, tag="", extras=None, write_to_disk_now=True):
+
         if extras is None:
             extras = {}
+        # should always be str
+        if tag is None or not tag:
+            tag=''
+
         # Incase these are copied across, assume it's a reference and deepcopy()
         apply_extras = deepcopy(extras)
 
@@ -284,14 +289,16 @@ class ChangeDetectionStore:
                                      headers={'App-Guid': self.__data['app_guid']})
                 res = r.json()
 
-                # List of permisable stuff we accept from the wild internet
+                # List of permissible attributes we accept from the wild internet
                 for k in ['url', 'tag',
-                                   'paused', 'title',
-                                   'previous_md5', 'headers',
-                                   'body', 'method',
-                                   'ignore_text', 'css_filter',
-                                   'subtractive_selectors', 'trigger_text',
-                                   'extract_title_as_title']:
+                          'paused', 'title',
+                          'previous_md5', 'headers',
+                          'body', 'method',
+                          'ignore_text', 'css_filter',
+                          'subtractive_selectors', 'trigger_text',
+                          'extract_title_as_title', 'extract_text',
+                          'text_should_not_be_present',
+                          'webdriver_js_execute_code']:
                     if res.get(k):
                         apply_extras[k] = res[k]
 
@@ -301,16 +308,15 @@ class ChangeDetectionStore:
                 return False
 
         with self.lock:
-            # @todo use a common generic version of this
-            new_uuid = str(uuid_builder.uuid4())
+
             # #Re 569
-            # Not sure why deepcopy was needed here, sometimes new watches would appear to already have 'history' set
-            # I assumed this would instantiate a new object but somehow an existing dict was getting used
-            new_watch = deepcopy(Watch.model({
+            new_watch = Watch.model(datastore_path=self.datastore_path, default={
                 'url': url,
                 'tag': tag
-            }))
+            })
 
+            new_uuid = new_watch['uuid']
+            logging.debug("Added URL {} - {}".format(url, new_uuid))
 
             for k in ['uuid', 'history', 'last_checked', 'last_changed', 'newest_history_key', 'previous_md5', 'viewed']:
                 if k in apply_extras:
@@ -330,23 +336,6 @@ class ChangeDetectionStore:
             self.sync_to_json()
         return new_uuid
 
-    # Save some text file to the appropriate path and bump the history
-    # result_obj from fetch_site_status.run()
-    def save_history_text(self, watch_uuid, contents):
-        import uuid
-
-        output_path = "{}/{}".format(self.datastore_path, watch_uuid)
-        # Incase the operator deleted it, check and create.
-        if not os.path.isdir(output_path):
-            mkdir(output_path)
-
-        fname = "{}/{}.stripped.txt".format(output_path, uuid.uuid4())
-        with open(fname, 'wb') as f:
-            f.write(contents)
-            f.close()
-
-        return fname
-
     def get_screenshot(self, watch_uuid):
         output_path = "{}/{}".format(self.datastore_path, watch_uuid)
         fname = "{}/last-screenshot.png".format(output_path)
@@ -355,6 +344,15 @@ class ChangeDetectionStore:
 
         return False
 
+    def visualselector_data_is_ready(self, watch_uuid):
+        output_path = "{}/{}".format(self.datastore_path, watch_uuid)
+        screenshot_filename = "{}/last-screenshot.png".format(output_path)
+        elements_index_filename = "{}/elements.json".format(output_path)
+        if path.isfile(screenshot_filename) and  path.isfile(elements_index_filename) :
+            return True
+
+        return False
+
     # Save as PNG, PNG is larger but better for doing visual diff in the future
     def save_screenshot(self, watch_uuid, screenshot: bytes):
         output_path = "{}/{}".format(self.datastore_path, watch_uuid)
@@ -363,6 +361,14 @@ class ChangeDetectionStore:
             f.write(screenshot)
             f.close()
 
+    def save_xpath_data(self, watch_uuid, data):
+        output_path = "{}/{}".format(self.datastore_path, watch_uuid)
+        fname = "{}/elements.json".format(output_path)
+        with open(fname, 'w') as f:
+            f.write(json.dumps(data))
+            f.close()
+
+
     def sync_to_json(self):
         logging.info("Saving JSON..")
         print("Saving JSON..")
@@ -415,8 +421,8 @@ class ChangeDetectionStore:
 
         index=[]
         for uuid in self.data['watching']:
-            for id in self.data['watching'][uuid]['history']:
-                index.append(self.data['watching'][uuid]['history'][str(id)])
+            for id in self.data['watching'][uuid].history:
+                index.append(self.data['watching'][uuid].history[str(id)])
 
         import pathlib
 
@@ -427,6 +433,21 @@ class ChangeDetectionStore:
                     print ("Removing",item)
                     unlink(item)
 
+    def import_proxy_list(self, filename):
+        import csv
+        with open(filename, newline='') as f:
+            reader = csv.reader(f, skipinitialspace=True)
+            # @todo This loop can could be improved
+            l = []
+            for row in reader:
+                if len(row):
+                    if len(row)>=2:
+                        l.append(tuple(row[:2]))
+                    else:
+                        l.append(tuple([row[0], row[0]]))
+            self.proxy_list = l if len(l) else None
+
+
     # 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
@@ -472,3 +493,36 @@ class ChangeDetectionStore:
                 # Only upgrade individual watch time if it was set
                 if watch.get('minutes_between_check', False):
                     self.data['watching'][uuid]['time_between_check']['minutes'] = watch['minutes_between_check']
+
+    # Move the history list to a flat text file index
+    # Better than SQLite because this list is only appended to, and works across NAS / NFS type setups
+    def update_2(self):
+        # @todo test running this on a newly updated one (when this already ran)
+        for uuid, watch in self.data['watching'].items():
+            history = []
+
+            if watch.get('history', False):
+                for d, p in watch['history'].items():
+                    d = int(d)  # Used to be keyed as str, we'll fix this now too
+                    history.append("{},{}\n".format(d,p))
+
+                if len(history):
+                    target_path = os.path.join(self.datastore_path, uuid)
+                    if os.path.exists(target_path):
+                        with open(os.path.join(target_path, "history.txt"), "w") as f:
+                            f.writelines(history)
+                    else:
+                        logging.warning("Datastore history directory {} does not exist, skipping history import.".format(target_path))
+
+                # No longer needed, dynamically pulled from the disk when needed.
+                # But we should set it back to a empty dict so we don't break if this schema runs on an earlier version.
+                # In the distant future we can remove this entirely
+                self.data['watching'][uuid]['history'] = {}
+
+    # We incorrectly stored last_changed when there was not a change, and then confused the output list table
+    def update_3(self):
+        for uuid, watch in self.data['watching'].items():
+            # Be sure it's recalculated
+            p = watch.history
+            if watch.history_n < 2:
+                watch['last_changed'] = 0

changedetectionio/templates/_common_fields.jinja

@@ -2,7 +2,6 @@
 {% from '_helpers.jinja' import render_field %}
 
 {% macro render_common_settings_form(form, current_base_url, emailprefix) %}
-
                         <div class="pure-control-group">
                             {{ render_field(form.notification_urls, rows=5, placeholder="Examples:
     Gitter - gitter://token/room
@@ -15,7 +14,7 @@
                                 <li>Use <a target=_new href="https://github.com/caronc/apprise">AppRise URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.</li>
                                 <li><code>discord://</code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
                                 <li><code>tgram://</code> bots cant send messages to other bots, so you should specify chat ID of non-bot user.</li>
-                                <li>Go here for <a href="{{url_for('notification_logs')}}">notification debug logs</a></li>
+                                <li><code>tgram://</code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
                               </ul>
                             </div>
                             <br/>
@@ -23,6 +22,7 @@
 {% if emailprefix %}
                             <a id="add-email-helper" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Add email</a>
 {% endif %}
+                            <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Notification debug logs</a>
                         </div>
                         <div id="notification-customisation" class="pure-control-group">
                             <div class="pure-control-group">

changedetectionio/templates/clear_all_history.html

@@ -3,22 +3,22 @@
 {% block content %}
 <div class="edit-form">
     <div class="box-wrap inner">
-    <form class="pure-form pure-form-stacked" action="{{url_for('scrub_page')}}" method="POST">
+    <form class="pure-form pure-form-stacked" action="{{url_for('clear_all_history')}}" method="POST">
         <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
         <fieldset>
             <div class="pure-control-group">
-                This will remove ALL version snapshots/data, but keep your list of URLs. <br/>
+                This will remove version history (snapshots) for ALL watches, but keep your list of URLs! <br/>
                 You may like to use the <strong>BACKUP</strong> link first.<br/>
             </div>
             <br/>
             <div class="pure-control-group">
                 <label for="confirmtext">Confirmation text</label>
                 <input type="text" id="confirmtext" required="" name="confirmtext" value="" size="10"/>
-                <span class="pure-form-message-inline">Type in the word <strong>scrub</strong> to confirm that you understand!</span>
+                <span class="pure-form-message-inline">Type in the word <strong>clear</strong> to confirm that you understand.</span>
             </div>
             <br/>
             <div class="pure-control-group">
-                <button type="submit" class="pure-button pure-button-primary">Scrub!</button>
+                <button type="submit" class="pure-button pure-button-primary">Clear History!</button>
             </div>
             <br/>
             <div class="pure-control-group">

changedetectionio/templates/diff.html

@@ -1,6 +1,11 @@
 {% extends 'base.html' %}
 
 {% block content %}
+<script>
+    const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
+</script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
+
 <div id="settings">
     <h1>Differences</h1>
     <form class="pure-form " action="" method="GET">
@@ -17,7 +22,7 @@
             {% if versions|length >= 1 %}
             <label for="diff-version">Compare newest (<span id="current-v-date"></span>) with</label>
             <select id="diff-version" name="previous_version">
-                {% for version in versions %}
+                {% for version in versions|reverse %}
                 <option value="{{version}}" {% if version== current_previous_version %} selected="" {% endif %}>
                     {{version}}
                 </option>
@@ -39,9 +44,7 @@
 <div class="tabs">
     <ul>
         <li class="tab" id="default-tab"><a href="#text">Text</a></li>
-{% if screenshot %}
-        <li class="tab"><a href="#screenshot">Current screenshot</a></li>
-{% endif %}
+        <li class="tab" id="screenshot-tab"><a href="#screenshot">Screenshot</a></li>
     </ul>
 </div>
 
@@ -63,17 +66,21 @@
          </table>
          Diff algorithm from the amazing <a href="https://github.com/kpdecker/jsdiff">github.com/kpdecker/jsdiff</a>
      </div>
-
-{% if screenshot %}
      <div class="tab-pane-inner" id="screenshot">
-         <p>
-         <i>For now, only the most recent screenshot is saved and displayed.</i>
-             </p>
-
-        <img src="{{url_for('static_content', group='screenshot', filename=uuid)}}">
+         <div class="tip">
+             For now, Differences are performed on text, not graphically, only the latest screenshot is available.
+         </div>
+         </br>
+         {% if is_html_webdriver %}
+           {% if screenshot %}
+             <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 %}
+         {% else %}
+           <strong>Screenshot requires Playwright/WebDriver enabled</strong>
+         {% endif %}
      </div>
-{% endif %}
-
 </div>
 
 

changedetectionio/templates/edit.html

@@ -5,11 +5,19 @@
 <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)}}";
+    const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
+    const playwright_enabled={% if playwright_enabled %} true {% else %} false {% endif %};
+
 {% if emailprefix %}
     const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');
 {% endif %}
+
 </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='notifications.js')}}" defer></script>
+<script type="text/javascript" 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='limit.js')}}" defer></script>
 
 <div class="edit-form monospaced-textarea">
 
@@ -17,6 +25,7 @@
         <ul>
             <li class="tab" id="default-tab"><a href="#general">General</a></li>
             <li class="tab"><a href="#request">Request</a></li>
+            <li class="tab"><a id="visualselector-tab" href="#visualselector">Visual Filter Selector</a></li>
             <li class="tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
             <li class="tab"><a href="#notifications">Notifications</a></li>
         </ul>
@@ -53,33 +62,65 @@
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.extract_title_as_title) }}
                     </div>
+                    <div class="pure-control-group">
+                        {{ render_checkbox_field(form.filter_failure_notification_send) }}
+                        <span class="pure-form-message-inline">
+                         Sends a notification when the filter can no longer be seen on the page, good for knowing when the page changed and your filter will not work anymore.
+                        </span>
+                    </div>
                 </fieldset>
             </div>
 
             <div class="tab-pane-inner" id="request">
-                    <div class="pure-control-group">
+                    <div class="pure-control-group inline-radio">
                         {{ render_field(form.fetch_backend, class="fetch-backend") }}
                         <span class="pure-form-message-inline">
                             <p>Use the <strong>Basic</strong> method (default) where your watched site doesn't need Javascript to render.</p>
                             <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
                         </span>
                     </div>
-
-                <hr/>
-                <fieldset class="pure-group">
-
-                    <span class="pure-form-message-inline">
-                        <strong>Request override is currently only used by the <i>Basic fast Plaintext/HTTP Client</i> method.</strong>
-                    </span>
+                {% if form.proxy %}
+                    <div class="pure-control-group inline-radio">
+                        {{ render_field(form.proxy, class="fetch-backend-proxy") }}
+                        <span class="pure-form-message-inline">
+                        Choose a proxy for this watch
+                        </span>
+                    </div>
+                {% endif %}
+                <fieldset id="webdriver-override-options">
                     <div class="pure-control-group">
-                        {{ render_field(form.method) }}
+                        {{ render_field(form.webdriver_delay) }}
+                        <div class="pure-form-message-inline">
+                            <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
+                            <br/>
+                            This will wait <i>n</i> seconds before extracting the text.
+                            {% if using_global_webdriver_wait %}
+                            <br/><strong>Using the current global default settings</strong>
+                            {% endif %}
+                        </div>
                     </div>
                     <div class="pure-control-group">
+                        {{ render_field(form.webdriver_js_execute_code) }}
+                        <div class="pure-form-message-inline">
+                            Run this code before performing change detection, handy for filling in fields and other actions <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Run-JavaScript-before-change-detection">More help and examples here</a>
+                        </div>
+                    </div>
+                </fieldset>
+                <fieldset class="pure-group" id="requests-override-options">
+                    {% if not playwright_enabled %}
+                        <div class="pure-form-message-inline">
+                            <strong>Request override is currently only used by the <i>Basic fast Plaintext/HTTP Client</i> method.</strong>
+                        </div>
+                    {% endif %}
+                    <div class="pure-control-group" id="request-method">
+                        {{ render_field(form.method) }}
+                    </div>
+                    <div class="pure-control-group" id="request-headers">
 {{ render_field(form.headers, rows=5, placeholder="Example
 Cookie: foobar
 User-Agent: wonderbra 1.0") }}
                     </div>
-                    <div class="pure-control-group">
+                    <div class="pure-control-group" id="request-body">
                                         {{ render_field(form.body, rows=5, placeholder="Example
 {
    \"name\":\"John\",
@@ -87,7 +128,7 @@ User-Agent: wonderbra 1.0") }}
    \"car\":null
 }") }}
                     </div>
-                    <div>
+                    <div id="ignore-status-codes-option">
                         {{ render_checkbox_field(form.ignore_status_codes) }}
                     </div>
                 </fieldset>
@@ -104,8 +145,7 @@ User-Agent: wonderbra 1.0") }}
             </div>
 
             <div class="tab-pane-inner" id="filters-and-triggers">
-                <fieldset>
-                        <div class="pure-control-group">
+                    <div class="pure-control-group">
                             <strong>Pro-tips:</strong><br/>
                             <ul>
                                 <li>
@@ -116,7 +156,12 @@ User-Agent: wonderbra 1.0") }}
                                 </li>
                             </ul>
                     </div>
-
+                    <fieldset>
+                        <div class="pure-control-group">
+                            {{ render_checkbox_field(form.check_unique_lines) }}
+                            <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
+                        </div>
+                    </fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.css_filter, placeholder=".class-name or #some-id, or other CSS selector rule.",
                         class="m-d") }}
@@ -125,14 +170,14 @@ User-Agent: wonderbra 1.0") }}
                         <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
                         <li>JSON - Limit text to this JSON rule, using <a href="https://pypi.org/project/jsonpath-ng/">JSONPath</a>, prefix with <code>"json:"</code>, use <code>json:$</code> to force re-formatting if required,  <a
                                 href="https://jsonpath.com/" target="new">test your JSONPath here</a></li>
-                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash, example  <code>//*[contains(@class, 'sametext')]</code>, <a
+                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash, example  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath://*[contains(@class, 'sametext')]</code>, <a
                                 href="http://xpather.com/" target="new">test your XPath here</a></li>
                     </ul>
                     Please be sure that you thoroughly understand how to write CSS or JSONPath, XPath selector rules before filing an issue on GitHub! <a
                                 href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br/>
                 </span>
                     </div>
-                    <fieldset class="pure-group">
+                    <div class="pure-control-group">
                       {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
 footer
 nav
@@ -143,8 +188,7 @@ nav
                           <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
-                    </fieldset>
-                </fieldset>
+                    </div>
                 <fieldset class="pure-group">
                     {{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
 /some.regex\d{2}/ for case-INsensitive regex
@@ -152,7 +196,7 @@ nav
                     <span class="pure-form-message-inline">
                         <ul>
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                            <li>Regular Expression support, wrap the line in forward slash <code>/regex/</code></li>
+                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
                             <li>Changing this will affect the comparison checksum which may trigger an alert</li>
                             <li>Use the preview/show current tab to see ignores</li>
                         </ul>
@@ -174,6 +218,80 @@ nav
                         </span>
                     </div>
                 </fieldset>
+                <fieldset>
+                    <div class="pure-control-group">
+                        {{ render_field(form.text_should_not_be_present, rows=5, placeholder="For example: Out of stock
+Sold out
+Not in stock
+Unavailable") }}
+                        <span class="pure-form-message-inline">
+                            <ul>
+                                <li>Block change-detection while this text is on the page, all text and regex are tested <i>case-insensitive</i>, good for waiting for when a product is available again</li>
+                                <li>Block text is processed from the result-text that comes out of any CSS/JSON Filters for this watch</li>
+                                <li>All lines here must not exist (think of each line as "OR")</li>
+                                <li>Note: Wrap in forward slash / to use regex  example: <code>/foo\d/</code></li>
+                            </ul>
+                        </span>
+                    </div>
+                </fieldset>
+                <fieldset>
+                    <div class="pure-control-group">
+                        {{ render_field(form.extract_text, rows=5, placeholder="\d+ online") }}
+                        <span class="pure-form-message-inline">
+                    <ul>
+                        <li>Extracts text in the final output (line by line) after other filters using regular expressions;
+                            <ul>
+                                <li>Regular expression &dash; example <code>/reports.+?2022/i</code></li>
+                                <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br/></li>
+                                <li>Keyword example &dash; example <code>Out of stock</code></li>
+                                <li>Use groups to extract just that text &dash; example <code>/reports.+?(\d+)/i</code> returns a list of years only</li>
+                            </ul>
+                        </li>
+                        <li>One line per regular-expression/ string match</li>
+                    </ul>
+                        </span>
+                    </div>
+                </fieldset>
+            </div>
+
+            <div class="tab-pane-inner visual-selector-ui" id="visualselector">
+                <img id="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
+                <strong>Pro-tip:</strong> This tool is only for limiting which elements will be included on a change-detection, not for interacting with browser directly.
+                <fieldset>
+                    <div class="pure-control-group">
+                        {% if visualselector_enabled %}
+                            {% if visualselector_data_is_ready %}
+                                <div id="selector-header">
+                                    <a id="clear-selector" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Clear selection</a>
+                                    <i class="fetching-update-notice" style="font-size: 80%;">One moment, fetching screenshot and element information..</i>
+                                </div>
+                                <div id="selector-wrapper">
+                                    <!-- 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" />
+                                    <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>
+
+                            <span class="pure-form-message-inline">
+                                <p><span style="font-weight: bold">Beta!</span> The Visual Selector is new and there may be minor bugs, please report pages that dont work, help us to improve this software!</p>
+                            </span>
+
+                            {% else %}
+                                <span class="pure-form-message-inline">Screenshot and element data is not available or not yet ready.</span>
+                            {% endif %}
+                        {% else %}
+                            <span class="pure-form-message-inline">
+                                <p>Sorry, this functionality only works with Playwright/Chrome enabled watches.</p>
+                                <p>Enable the Playwright Chrome fetcher, or alternatively try our <a href="https://lemonade.changedetection.io/start">very affordable subscription based service</a>.</p>
+                                <p>This is because Selenium/WebDriver can not extract full page screenshots reliably.</p>
+
+                            </span>
+                        {% endif %}
+                    </div>
+                </fieldset>
             </div>
 
             <div id="actions">
@@ -181,9 +299,11 @@ nav
 
                       {{ render_button(form.save_button) }} {{ render_button(form.save_and_preview_button) }}
 
-                    <a href="{{url_for('api_delete', uuid=uuid)}}"
+                    <a href="{{url_for('form_delete', uuid=uuid)}}"
                        class="pure-button button-small button-error ">Delete</a>
-                    <a href="{{url_for('api_clone', uuid=uuid)}}"
+                    <a href="{{url_for('clear_watch_history', uuid=uuid)}}"
+                       class="pure-button button-small button-error ">Clear History</a>
+                    <a href="{{url_for('form_clone', uuid=uuid)}}"
                        class="pure-button button-small ">Create Copy</a>
                 </div>
             </div>

changedetectionio/templates/import.html

@@ -1,30 +1,86 @@
 {% extends 'base.html' %}
-
 {% block content %}
-<div class="edit-form">
-     <div class="inner">
+<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">
+        <ul>
+            <li class="tab" id="default-tab"><a href="#url-list">URL List</a></li>
+            <li class="tab"><a href="#distill-io">Distill.io</a></li>
+        </ul>
+    </div>
+
+    <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() }}"/>
-            <fieldset class="pure-group">
-              <legend>
-                Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma (,):
-                <br>
-                <code>https://example.com tag1, tag2, last tag</code>
-                <br>
-                URLs which do not pass validation will stay in the textarea.
-              </legend>
-              
+            <div class="tab-pane-inner" id="url-list">
+                <fieldset class="pure-group">
+                    <legend>
+                        Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma
+                        (,):
+                        <br>
+                        <code>https://example.com tag1, tag2, last tag</code>
+                        <br>
+                        URLs which do not pass validation will stay in the textarea.
+                    </legend>
 
-                <textarea name="urls" class="pure-input-1-2" placeholder="https://"
-                          style="width: 100%;
+
+                    <textarea name="urls" class="pure-input-1-2" placeholder="https://"
+                              style="width: 100%;
                                 font-family:monospace;
                                 white-space: pre;
                                 overflow-wrap: normal;
-                                overflow-x: scroll;" rows="25">{{ remaining }}</textarea>
-            </fieldset>
+                                overflow-x: scroll;" rows="25">{{ import_url_list_remaining }}</textarea>
+                </fieldset>
+
+
+            </div>
+
+            <div class="tab-pane-inner" id="distill-io">
+
+
+                <fieldset class="pure-group">
+                    <legend>
+                        Copy and Paste your Distill.io watch 'export' file, this should be a JSON file.</br>
+                        This is <i>experimental</i>, supported fields are <code>name</code>, <code>uri</code>, <code>tags</code>, <code>config:selections</code>, the rest (including <code>schedule</code>) are ignored.
+                        <br/>
+                        <p>
+                        How to export? <a href="https://distill.io/docs/web-monitor/how-export-and-import-monitors/">https://distill.io/docs/web-monitor/how-export-and-import-monitors/</a><br/>
+                        Be sure to set your default fetcher to Chrome if required.</br>
+                        </p>
+                    </legend>
+
+
+                    <textarea name="distill-io" class="pure-input-1-2" style="width: 100%;
+                                font-family:monospace;
+                                white-space: pre;
+                                overflow-wrap: normal;
+                                overflow-x: scroll;" placeholder="Example Distill.io JSON export file
+
+{
+    &quot;client&quot;: {
+        &quot;local&quot;: 1
+    },
+    &quot;data&quot;: [
+        {
+            &quot;name&quot;: &quot;Unraid | News&quot;,
+            &quot;uri&quot;: &quot;https://unraid.net/blog&quot;,
+            &quot;config&quot;: &quot;{\&quot;selections\&quot;:[{\&quot;frames\&quot;:[{\&quot;index\&quot;:0,\&quot;excludes\&quot;:[],\&quot;includes\&quot;:[{\&quot;type\&quot;:\&quot;xpath\&quot;,\&quot;expr\&quot;:\&quot;(//div[@id='App']/div[contains(@class,'flex')]/main[contains(@class,'relative')]/section[contains(@class,'relative')]/div[@class='container']/div[contains(@class,'flex')]/div[contains(@class,'w-full')])[1]\&quot;}]}],\&quot;dynamic\&quot;:true,\&quot;delay\&quot;:2}],\&quot;ignoreEmptyText\&quot;:true,\&quot;includeStyle\&quot;:false,\&quot;dataAttr\&quot;:\&quot;text\&quot;}&quot;,
+            &quot;tags&quot;: [],
+            &quot;content_type&quot;: 2,
+            &quot;state&quot;: 40,
+            &quot;schedule&quot;: &quot;{\&quot;type\&quot;:\&quot;INTERVAL\&quot;,\&quot;params\&quot;:{\&quot;interval\&quot;:4447}}&quot;,
+            &quot;ts&quot;: &quot;2022-03-27T15:51:15.667Z&quot;
+        }
+    ]
+}
+" rows="25">{{ original_distill_json }}</textarea>
+                </fieldset>
+            </div>
             <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">Import</button>
         </form>
-     </div>
+
+    </div>
 </div>
 
 {% endblock %}

changedetectionio/templates/notification-log.html

@@ -4,7 +4,7 @@
 <div class="edit-form">
      <div class="inner">
 
-         <h4 style="margin-top: 0px;">The following issues were detected when sending notifications</h4>
+         <h4 style="margin-top: 0px;">Notification debug log</h4>
                 <div id="notification-error-log">
                 <ul style="font-size: 80%; margin:0px; padding: 0 0 0 7px">
                 {% for log in logs|reverse %}

changedetectionio/templates/preview.html

@@ -1,6 +1,10 @@
 {% extends 'base.html' %}
 
 {% block content %}
+<script>
+    const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
+</script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
 <div id="settings">
     <h1>Current - {{watch.last_checked|format_timestamp_timeago}}</h1>
@@ -10,9 +14,7 @@
 <div class="tabs">
     <ul>
         <li class="tab" id="default-tab"><a href="#text">Text</a></li>
-{% if screenshot %}
-        <li class="tab"><a href="#screenshot">Current screenshot</a></li>
-{% endif %}
+        <li class="tab" id="screenshot-tab"><a href="#screenshot">Screenshot</a></li>
     </ul>
 </div>
 
@@ -31,15 +33,20 @@
             </tbody>
         </table>
     </div>
-
-{% if screenshot %}
      <div class="tab-pane-inner" id="screenshot">
-         <p>
-         <i>For now, only the most recent screenshot is saved and displayed.</i>
-             </p>
-
-        <img src="{{url_for('static_content', group='screenshot', filename=uuid)}}">
+         <div class="tip">
+             For now, Differences are performed on text, not graphically, only the latest screenshot is available.
+         </div>
+         </br>
+         {% if is_html_webdriver %}
+           {% if screenshot %}
+             <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 %}
+         {% else %}
+           <strong>Screenshot requires Playwright/WebDriver enabled</strong>
+         {% endif %}
      </div>
-{% endif %}
 </div>
 {% endblock %}

changedetectionio/templates/settings.html

@@ -9,10 +9,10 @@
     const email_notification_prefix=JSON.parse('{{emailprefix|tojson}}');
 {% endif %}
 </script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='settings.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 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>
@@ -20,6 +20,7 @@
             <li class="tab"><a href="#notifications">Notifications</a></li>
             <li class="tab"><a href="#fetching">Fetching</a></li>
             <li class="tab"><a href="#filters">Global Filters</a></li>
+            <li class="tab"><a href="#api">API</a></li>
         </ul>
     </div>
     <div class="box-wrap inner">
@@ -31,6 +32,17 @@
                         {{ render_field(form.requests.form.time_between_check, class="time-check-widget") }}
                         <span class="pure-form-message-inline">Default time for all watches, when the watch does not have a specific time setting.</span>
                     </div>
+                    <div class="pure-control-group">
+                        {{ render_field(form.requests.form.jitter_seconds, class="jitter_seconds") }}
+                        <span class="pure-form-message-inline">Example - 3 seconds random jitter could trigger up to 3 seconds earlier or up to 3 seconds later</span>
+                    </div>
+                    <div class="pure-control-group">
+                        {{ render_field(form.application.form.filter_failure_notification_threshold_attempts, class="filter_failure_notification_threshold_attempts") }}
+                        <span class="pure-form-message-inline">After this many consecutive times that the CSS/xPath filter is missing, send a notification
+                            <br/>
+                        Set to <strong>0</strong> to disable
+                        </span>
+                    </div>
                     <div class="pure-control-group">
                         {% if not hide_remove_pass %}
                             {% if current_user.is_authenticated %}
@@ -43,6 +55,7 @@
                             <span class="pure-form-message-inline">Password is locked.</span>
                         {% endif %}
                     </div>
+
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.base_url, placeholder="http://yoursite.com:5000/",
                         class="m-d") }}
@@ -62,6 +75,18 @@
                         <span class="pure-form-message-inline">When using a Chrome browser, a screenshot from the last check will be available on the Diff page</span>
                     </div>
 
+                    <div class="pure-control-group">
+                        {{ render_checkbox_field(form.application.form.empty_pages_are_a_change) }}
+                        <span class="pure-form-message-inline">When a page contains HTML, but no renderable text appears (empty page), is this considered a change?</span>
+                    </div>
+                {% if form.requests.proxy %}
+                    <div class="pure-control-group inline-radio">
+                        {{ render_field(form.requests.form.proxy, class="fetch-backend-proxy") }}
+                        <span class="pure-form-message-inline">
+                        Choose a default proxy for all watches
+                        </span>
+                    </div>
+                {% endif %}
                 </fieldset>
             </div>
 
@@ -74,16 +99,25 @@
             </div>
 
             <div class="tab-pane-inner" id="fetching">
-                <div class="pure-control-group">
+                <div class="pure-control-group inline-radio">
                     {{ render_field(form.application.form.fetch_backend, class="fetch-backend") }}
                     <span class="pure-form-message-inline">
                         <p>Use the <strong>Basic</strong> method (default) where your watched sites don't need Javascript to render.</p>
                         <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
                     </span>
                 </div>
+                <fieldset class="pure-group" id="webdriver-override-options">
+                    <div class="pure-form-message-inline">
+                        <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
+                        <br/>
+                        This will wait <i>n</i> seconds before extracting the text.
+                    </div>
+                    <div class="pure-control-group">
+                        {{ render_field(form.application.form.webdriver_delay) }}
+                    </div>
+                </fieldset>
             </div>
 
-
             <div class="tab-pane-inner" id="filters">
 
                     <fieldset class="pure-group">
@@ -120,7 +154,7 @@ nav
                         <ul>
                             <li>Note: This is applied globally in addition to the per-watch rules.</li>
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                            <li>Regular Expression support, wrap the line in forward slash <code>/regex/</code></li>
+                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
                             <li>Changing this will affect the comparison checksum which may trigger an alert</li>
                             <li>Use the preview/show current tab to see ignores</li>
                         </ul>
@@ -128,12 +162,26 @@ nav
                     </fieldset>
            </div>
 
+            <div class="tab-pane-inner" id="api">
+
+                <p>Drive your changedetection.io via API, More about <a href="https://github.com/dgtlmoon/changedetection.io/wiki/API-Reference">API access here</a></p>
+
+                <div class="pure-control-group">
+                    {{ render_checkbox_field(form.application.form.api_access_token_enabled) }}
+                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header</div><br/>
+                    <div class="pure-form-message-inline"><br/>API Key <span id="api-key">{{api_key}}</span>
+                        <span style="display:none;" id="api-key-copy" >copy</span>
+                    </div>
+                </div>
+            </div>
+
             <div id="actions">
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}
                     <a href="{{url_for('index')}}" class="pure-button button-small button-cancel">Back</a>
-                    <a href="{{url_for('scrub_page')}}" class="pure-button button-small button-cancel">Delete History Snapshot Data</a>
+                    <a href="{{url_for('clear_all_history')}}" class="pure-button button-small button-cancel">Clear Snapshot History</a>
                 </div>
+
             </div>
         </form>
     </div>

changedetectionio/templates/watch-overview.html

@@ -3,9 +3,10 @@
 {% from '_helpers.jinja' import render_simple_field %}
 <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('api_watch_add') }}" method="POST" id="new-watch-form">
+    <form class="pure-form" action="{{ url_for('form_watch_add') }}" method="POST" id="new-watch-form">
         <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
         <fieldset>
             <legend>Add a new change detection watch</legend>
@@ -13,7 +14,7 @@
                 {{ render_simple_field(form.tag, value=active_tag if active_tag else '', placeholder="watch group") }}
             <button type="submit" class="pure-button pure-button-primary">Watch</button>
         </fieldset>
-        <span style="color:#eee; font-size: 80%;"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread.svg')}}" /> Tip: You can also add 'shared' watches. <a href="#">More info</a></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>
     <div>
         <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag }}">All</a>
@@ -39,20 +40,20 @@
             <tbody>
 
 
-            {% for watch in watches %}
+            {% for watch in watches|sort(attribute='last_changed', reverse=True) %}
             <tr id="{{ watch.uuid }}"
                 class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }}
                 {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
                 {% if watch.last_notification_error is defined and watch.last_notification_error != False %}error{% endif %}
                 {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
-                {% if watch.newest_history_key| int > watch.last_viewed| int %}unviewed{% 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">{{ loop.index }}</td>
                 <td class="inline paused-state state-{{watch.paused}}"><a href="{{url_for('index', pause=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause" title="Pause"/></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.url.replace('source:','') }}"></a>
-                    <a href="{{url_for('api_share_put_watch', uuid=watch.uuid)}}"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread.svg')}}" /></a>
+                    <a href="{{url_for('form_share_put_watch', uuid=watch.uuid)}}"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread.svg')}}" /></a>
 
                     {%if watch.fetch_backend == "html_webdriver" %}<img style="height: 1em; display:inline-block;" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" />{% endif %}
 
@@ -66,21 +67,21 @@
                     <span class="watch-tag-list">{{ watch.tag}}</span>
                     {% endif %}
                 </td>
-                <td class="last-checked">{{watch|format_last_checked_time}}</td>
-                <td class="last-changed">{% if watch.history|length >= 2 and watch.last_changed %}
+                <td class="last-checked">{{watch|format_last_checked_time|safe}}</td>
+                <td class="last-changed">{% if watch.history_n >=2 and watch.last_changed >0 %}
                     {{watch.last_changed|format_timestamp_timeago}}
                     {% else %}
                     Not yet
                     {% endif %}
                 </td>
                 <td>
-                    <a {% if watch.uuid in queued_uuids %}disabled="true"{% endif %} href="{{ url_for('api_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}"
+                    <a {% if watch.uuid in queued_uuids %}disabled="true"{% endif %} href="{{ url_for('form_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}"
                        class="recheck pure-button button-small pure-button-primary">{% if watch.uuid in queued_uuids %}Queued{% else %}Recheck{% endif %}</a>
                     <a href="{{ url_for('edit_page', uuid=watch.uuid)}}" class="pure-button button-small pure-button-primary">Edit</a>
-                    {% if watch.history|length >= 2 %}
+                    {% if watch.history_n >= 2 %}
                     <a href="{{ url_for('diff_history_page', uuid=watch.uuid) }}" target="{{watch.uuid}}" class="pure-button button-small pure-button-primary diff-link">Diff</a>
                     {% else %}
-                        {% if watch.history|length == 1 %}
+                        {% if watch.history_n == 1 %}
                             <a href="{{ url_for('preview_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button button-small pure-button-primary">Preview</a>
                         {% endif %}
                     {% endif %}
@@ -96,7 +97,7 @@
             </li>
             {% endif %}
             <li>
-               <a href="{{ url_for('api_watch_checknow', tag=active_tag) }}" class="pure-button button-tag ">Recheck
+               <a href="{{ url_for('form_watch_checknow', tag=active_tag) }}" class="pure-button button-tag ">Recheck
                 all {% if active_tag%}in "{{active_tag}}"{%endif%}</a>
             </li>
             <li>

changedetectionio/tests/conftest.py

@@ -32,6 +32,8 @@ def app(request):
     """Create application for the tests."""
     datastore_path = "./test-datastore"
 
+    # So they don't delay in fetching
+    os.environ["MINIMUM_SECONDS_RECHECK_TIME"] = "0"
     try:
         os.mkdir(datastore_path)
     except FileExistsError:

changedetectionio/tests/fetchers/__init__.py

@@ -0,0 +1,2 @@
+"""Tests for the app."""
+

changedetectionio/tests/fetchers/conftest.py

@@ -0,0 +1,3 @@
+#!/usr/bin/python3
+
+from .. import conftest

changedetectionio/tests/fetchers/test_content.py

@@ -0,0 +1,48 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from ..util import live_server_setup
+import logging
+
+
+def test_fetch_webdriver_content(client, live_server):
+    live_server_setup(live_server)
+
+    #####################
+    res = client.post(
+        url_for("settings_page"),
+        data={"application-empty_pages_are_a_change": "",
+              "requests-time_between_check-minutes": 180,
+              'application-fetch_backend': "html_webdriver"},
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." in res.data
+
+    # Add our URL to the import page
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": "https://changedetection.io/ci-test.html"},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+    time.sleep(3)
+    attempt = 0
+    while attempt < 20:
+        res = client.get(url_for("index"))
+        if not b'Checking now' in res.data:
+            break
+        logging.getLogger().info("Waiting for check to not say 'Checking now'..")
+        time.sleep(3)
+        attempt += 1
+
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+    logging.getLogger().info("Looking for correct fetched HTML (text) from server")
+
+    assert b'cool it works' in res.data

changedetectionio/tests/test_api.py

@@ -2,73 +2,194 @@
 
 import time
 from flask import url_for
-from . util import live_server_setup
+from .util import live_server_setup, extract_api_key_from_UI
 
-def test_setup(live_server):
-    live_server_setup(live_server)
+import json
+import uuid
 
 
-def set_response_data(test_return_data):
+def set_original_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+     <div id="sametext">Some text thats the same</div>
+     <div id="changetext">Some text that will change</div>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+    return None
+
+
+def set_modified_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <p>which has this one new line</p>
+     </br>
+     So let's see what happens.  </br>
+     <div id="sametext">Some text thats the same</div>
+     <div id="changetext">Some text that changes</div>
+     </body>
+     </html>
+    """
+
     with open("test-datastore/endpoint-content.txt", "w") as f:
         f.write(test_return_data)
 
+    return None
 
-def test_snapshot_api_detects_change(client, live_server):
-    test_return_data = "Some initial text"
 
-    test_return_data_modified = "Some NEW nice initial text"
+def is_valid_uuid(val):
+    try:
+        uuid.UUID(str(val))
+        return True
+    except ValueError:
+        return False
 
-    sleep_time_for_fetch_thread = 3
 
-    set_response_data(test_return_data)
+def test_api_simple(client, live_server):
+    live_server_setup(live_server)
 
-    # Give the endpoint time to spin up
-    time.sleep(1)
+    api_key = extract_api_key_from_UI(client)
 
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', content_type="text/plain",
-                       _external=True)
+    # Create a watch
+    set_original_response()
+    watch_uuid = None
+
+    # Validate bad URL
+    test_url = url_for('test_endpoint', _external=True,
+                       headers={'x-api-key': api_key}, )
     res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
+        url_for("createwatch"),
+        data=json.dumps({"url": "h://xxxxxxxxxom"}),
+        headers={'content-type': 'application/json', 'x-api-key': api_key},
         follow_redirects=True
     )
-    assert b"1 Imported" in res.data
-
-    # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
-    res = client.get(
-        url_for("api_snapshot", uuid="first"),
-        follow_redirects=True
-    )
-
-    assert test_return_data.encode() == res.data
-
-    #  Make a change
-    set_response_data(test_return_data_modified)
-
-    # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
-    res = client.get(
-        url_for("api_snapshot", uuid="first"),
-        follow_redirects=True
-    )
-
-    assert test_return_data_modified.encode() == res.data
-
-def test_snapshot_api_invalid_uuid(client, live_server):
-
-    res = client.get(
-        url_for("api_snapshot", uuid="invalid"),
-        follow_redirects=True
-    )
-
     assert res.status_code == 400
 
+    # Create new
+    res = client.post(
+        url_for("createwatch"),
+        data=json.dumps({"url": test_url, 'tag': "One, Two", "title": "My test URL"}),
+        headers={'content-type': 'application/json', 'x-api-key': api_key},
+        follow_redirects=True
+    )
+    s = json.loads(res.data)
+    assert is_valid_uuid(s['uuid'])
+    watch_uuid = s['uuid']
+    assert res.status_code == 201
+
+    time.sleep(3)
+
+    # Verify its in the list and that recheck worked
+    res = client.get(
+        url_for("createwatch"),
+        headers={'x-api-key': api_key}
+    )
+    assert watch_uuid in json.loads(res.data).keys()
+    before_recheck_info = json.loads(res.data)[watch_uuid]
+    assert before_recheck_info['last_checked'] != 0
+    #705 `last_changed` should be zero on the first check
+    assert before_recheck_info['last_changed'] == 0
+    assert before_recheck_info['title'] == 'My test URL'
+
+    set_modified_response()
+    # Trigger recheck of all ?recheck_all=1
+    client.get(
+        url_for("createwatch", recheck_all='1'),
+        headers={'x-api-key': api_key},
+    )
+    time.sleep(3)
+
+    # Did the recheck fire?
+    res = client.get(
+        url_for("createwatch"),
+        headers={'x-api-key': api_key},
+    )
+    after_recheck_info = json.loads(res.data)[watch_uuid]
+    assert after_recheck_info['last_checked'] != before_recheck_info['last_checked']
+    assert after_recheck_info['last_changed'] != 0
+
+    # Check history index list
+    res = client.get(
+        url_for("watchhistory", uuid=watch_uuid),
+        headers={'x-api-key': api_key},
+    )
+    history = json.loads(res.data)
+    assert len(history) == 2, "Should have two history entries (the original and the changed)"
+
+    # Fetch a snapshot by timestamp, check the right one was found
+    res = client.get(
+        url_for("watchsinglehistory", uuid=watch_uuid, timestamp=list(history.keys())[-1]),
+        headers={'x-api-key': api_key},
+    )
+    assert b'which has this one new line' in res.data
+
+    # Fetch a snapshot by 'latest'', check the right one was found
+    res = client.get(
+        url_for("watchsinglehistory", uuid=watch_uuid, timestamp='latest'),
+        headers={'x-api-key': api_key},
+    )
+    assert b'which has this one new line' in res.data
+
+    # Fetch the whole watch
+    res = client.get(
+        url_for("watch", uuid=watch_uuid),
+        headers={'x-api-key': api_key}
+    )
+    watch = json.loads(res.data)
+    # @todo how to handle None/default global values?
+    assert watch['history_n'] == 2, "Found replacement history section, which is in its own API"
+
+    # Finally delete the watch
+    res = client.delete(
+        url_for("watch", uuid=watch_uuid),
+        headers={'x-api-key': api_key},
+    )
+    assert res.status_code == 204
+
+    # Check via a relist
+    res = client.get(
+        url_for("createwatch"),
+        headers={'x-api-key': api_key}
+    )
+    watch_list = json.loads(res.data)
+    assert len(watch_list) == 0, "Watch list should be empty"
+
+
+def test_access_denied(client, live_server):
+    # `config_api_token_enabled` Should be On by default
+    res = client.get(
+        url_for("createwatch")
+    )
+    assert res.status_code == 403
+
+    res = client.get(
+        url_for("createwatch"),
+        headers={'x-api-key': "something horrible"}
+    )
+    assert res.status_code == 403
+
+    # Disable config_api_token_enabled and it should work
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "requests-time_between_check-minutes": 180,
+            "application-fetch_backend": "html_requests",
+            "application-api_access_token_enabled": ""
+        },
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." in res.data
+
+    res = client.get(
+        url_for("createwatch")
+    )
+    assert res.status_code == 200

changedetectionio/tests/test_auth.py

@@ -29,7 +29,7 @@ def test_basic_auth(client, live_server):
     assert b"Updated watch." in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(1)
     res = client.get(
         url_for("preview_page", uuid="first"),

changedetectionio/tests/test_backend.py

@@ -3,14 +3,15 @@
 import time
 from flask import url_for
 from urllib.request import urlopen
-from . util import set_original_response, set_modified_response, live_server_setup
+from .util import set_original_response, set_modified_response, live_server_setup
 
 sleep_time_for_fetch_thread = 3
 
+
 # Basic test to check inscriptus is not adding return line chars, basically works etc
 def test_inscriptus():
     from inscriptis import get_text
-    html_content="<html><body>test!<br/>ok man</body></html>"
+    html_content = "<html><body>test!<br/>ok man</body></html>"
     stripped_text_from_html = get_text(html_content)
     assert stripped_text_from_html == 'test!\nok man'
 
@@ -32,7 +33,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
 
     # Do this a few times.. ensures we dont accidently set the status
     for n in range(3):
-        client.get(url_for("api_watch_checknow"), follow_redirects=True)
+        client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
         # Give the thread time to pick it up
         time.sleep(sleep_time_for_fetch_thread)
@@ -65,7 +66,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
     assert b'which has this one new line' in res.read()
 
     # Force recheck
-    res = client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
     assert b'1 watches are queued for rechecking.' in res.data
 
     time.sleep(sleep_time_for_fetch_thread)
@@ -82,7 +83,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
     # re #16 should have the diff in here too
     assert b'(into   ) which has this one new line' in res.data
     assert b'CDATA' in res.data
-    
+
     assert expected_url.encode('utf-8') in res.data
 
     # Following the 'diff' link, it should no longer display as 'unviewed' even after we recheck it a few times
@@ -93,7 +94,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
 
     # Do this a few times.. ensures we dont accidently set the status
     for n in range(2):
-        client.get(url_for("api_watch_checknow"), follow_redirects=True)
+        client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
         # Give the thread time to pick it up
         time.sleep(sleep_time_for_fetch_thread)
@@ -101,7 +102,8 @@ def test_check_basic_change_detection_functionality(client, live_server):
         # It should report nothing found (no new 'unviewed' class)
         res = client.get(url_for("index"))
         assert b'unviewed' not in res.data
-        assert b'head title' not in res.data # Should not be present because this is off by default
+        assert b'Mark all viewed' not in res.data
+        assert b'head title' not in res.data  # Should not be present because this is off by default
         assert b'test-endpoint' in res.data
 
     set_original_response()
@@ -109,20 +111,28 @@ def test_check_basic_change_detection_functionality(client, live_server):
     # Enable auto pickup of <title> in settings
     res = client.post(
         url_for("settings_page"),
-        data={"application-extract_title_as_title": "1", "requests-time_between_check-minutes": 180, 'application-fetch_backend': "html_requests"},
+        data={"application-extract_title_as_title": "1", "requests-time_between_check-minutes": 180,
+              'application-fetch_backend': "html_requests"},
         follow_redirects=True
     )
 
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
 
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
+    assert b'Mark all viewed' in res.data
+
     # It should have picked up the <title>
     assert b'head title' in res.data
 
+    # hit the mark all viewed link
+    res = client.get(url_for("mark_all_viewed"), follow_redirects=True)
+
+    assert b'Mark all viewed' not in res.data
+    assert b'unviewed' not in res.data
+
     #
     # Cleanup everything
-    res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
-

changedetectionio/tests/test_block_while_text_present.py

@@ -0,0 +1,137 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from . util import live_server_setup
+from changedetectionio import html_tools
+
+def set_original_ignore_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+     </body>
+     </html>
+
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def set_modified_original_ignore_response():
+    test_return_data = """<html>
+       <body>
+     Some NEW nice initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+     <p>new ignore stuff</p>
+     <p>out of stock</p>
+     <p>blah</p>
+     </body>
+     </html>
+
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+# Is the same but includes ZZZZZ, 'ZZZZZ' is the last line in ignore_text
+def set_modified_response_minus_block_text():
+    test_return_data = """<html>
+       <body>
+     Some NEW nice initial text</br>
+     <p>Which is across multiple lines</p>
+     <p>now on sale $2/p>
+     </br>
+     So let's see what happens.  </br>
+     <p>new ignore stuff</p>
+     <p>blah</p>
+     </body>
+     </html>
+
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def test_check_block_changedetection_text_NOT_present(client, live_server):
+    sleep_time_for_fetch_thread = 3
+    live_server_setup(live_server)
+    # Use a mix of case in ZzZ to prove it works case-insensitive.
+    ignore_text = "out of stoCk\r\nfoobar"
+
+    set_original_ignore_response()
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # Goto the edit page, add our ignore text
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"text_should_not_be_present": ignore_text, "url": test_url, 'fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+    # Check it saved
+    res = client.get(
+        url_for("edit_page", uuid="first"),
+    )
+    assert bytes(ignore_text.encode('utf-8')) in res.data
+
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+    assert b'/test-endpoint' in res.data
+
+    # The page changed, BUT the text is still there, just the rest of it changes, we should not see a change
+    set_modified_original_ignore_response()
+
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+    assert b'/test-endpoint' in res.data
+
+
+    # Now we set a change where the text is gone, it should now trigger
+    set_modified_response_minus_block_text()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    time.sleep(sleep_time_for_fetch_thread)
+
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_clone.py

@@ -23,7 +23,7 @@ def test_trigger_functionality(client, live_server):
 
 
     res = client.get(
-        url_for("api_clone", uuid="first"),
+        url_for("form_clone", uuid="first"),
         follow_redirects=True
     )
 

changedetectionio/tests/test_css_selector.py

@@ -89,7 +89,7 @@ def test_check_markup_css_filter_restriction(client, live_server):
     assert b"1 Imported" in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -110,7 +110,7 @@ def test_check_markup_css_filter_restriction(client, live_server):
     assert bytes(css_filter.encode('utf-8')) in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -118,7 +118,7 @@ def test_check_markup_css_filter_restriction(client, live_server):
     set_modified_response()
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 

changedetectionio/tests/test_element_removal.py

@@ -145,20 +145,19 @@ def test_element_removal_full(client, live_server):
     assert bytes(subtractive_selectors_data.encode("utf-8")) in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 
-    # No change yet - first check
-    res = client.get(url_for("index"))
-    assert b"unviewed" not in res.data
+    # so that we set the state to 'unviewed' after all the edits
+    client.get(url_for("diff_history_page", uuid="first"))
 
     #  Make a change to header/footer/nav
     set_modified_response()
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)

changedetectionio/tests/test_encoding.py

@@ -39,7 +39,7 @@ def test_check_encoding_detection(client, live_server):
     )
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(2)
@@ -71,7 +71,7 @@ def test_check_encoding_detection_missing_content_type_header(client, live_serve
     )
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(2)

changedetectionio/tests/test_errorhandling.py

@@ -29,7 +29,7 @@ def test_error_handler(client, live_server):
     assert b"1 Imported" in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(3)
@@ -54,7 +54,7 @@ def test_error_text_handler(client, live_server):
     assert b"1 Imported" in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(3)

changedetectionio/tests/test_extract_regex.py

@@ -0,0 +1,198 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from .util import live_server_setup
+
+from ..html_tools import *
+
+
+def set_original_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+     <div id="sametext">Some text thats the same</div>
+     <div class="changetext">Some text that will change</div>     
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+    return None
+
+
+def set_modified_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <p>which has this one new line</p>
+     </br>
+     So let's see what happens.  </br>
+     <div id="sametext">Some text thats the same</div>
+     <div class="changetext">Some text that did change ( 1000 online <br/> 80 guests<br/>  2000 online )</div>
+     <div class="changetext">SomeCase insensitive 3456</div>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+    return None
+
+
+def set_multiline_response():
+    test_return_data = """<html>
+       <body>
+     
+     <p>Something <br/>
+        across 6 billion multiple<br/>
+        lines
+     </p>
+     
+     <div>aaand something lines</div>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+    return None
+
+
+def test_setup(client, live_server):
+
+    live_server_setup(live_server)
+
+def test_check_filter_multiline(client, live_server):
+
+    set_multiline_response()
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    time.sleep(3)
+
+    # Goto the edit page, add our ignore text
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"css_filter": '',
+              'extract_text': '/something.+?6 billion.+?lines/si',
+              "url": test_url,
+              "tag": "",
+              "headers": "",
+              'fetch_backend': "html_requests"
+              },
+        follow_redirects=True
+    )
+
+    assert b"Updated watch." in res.data
+    time.sleep(3)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+
+    assert b'<div class="">Something' in res.data
+    assert b'<div class="">across 6 billion multiple' in res.data
+    assert b'<div class="">lines' in res.data
+
+    # but the last one, which also says 'lines' shouldnt be here (non-greedy match checking)
+    assert b'aaand something lines' not in res.data
+
+def test_check_filter_and_regex_extract(client, live_server):
+    sleep_time_for_fetch_thread = 3
+    css_filter = ".changetext"
+
+    set_original_response()
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    time.sleep(1)
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # Goto the edit page, add our ignore text
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"css_filter": css_filter,
+              'extract_text': '\d+ online\r\n\d+ guests\r\n/somecase insensitive \d+/i\r\n/somecase insensitive (345\d)/i',
+              "url": test_url,
+              "tag": "",
+              "headers": "",
+              'fetch_backend': "html_requests"
+              },
+        follow_redirects=True
+    )
+
+    assert b"Updated watch." in res.data
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    #  Make a change
+    set_modified_response()
+
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # It should have 'unviewed' still
+    # Because it should be looking at only that 'sametext' id
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    # Check HTML conversion detected and workd
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    # Class will be blank for now because the frontend didnt apply the diff
+    assert b'<div class="">1000 online' in res.data
+
+    # All regex matching should be here
+    assert b'<div class="">2000 online' in res.data
+
+    # Both regexs should be here
+    assert b'<div class="">80 guests' in res.data
+
+    # Regex with flag handling should be here
+    assert b'<div class="">SomeCase insensitive 3456' in res.data
+
+    # Singular group from /somecase insensitive (345\d)/i
+    assert b'<div class="">3456' in res.data
+
+    # Regex with multiline flag handling should be here
+
+    # Should not be here
+    assert b'Some text that did change' not in res.data

changedetectionio/tests/test_filter_failure_notification.py

@@ -0,0 +1,134 @@
+import os
+import time
+import re
+from flask import url_for
+from .util import set_original_response, live_server_setup
+from changedetectionio.model import App
+
+
+def set_response_with_filter():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+     <div id="nope-doesnt-exist">Some text thats the same</div>     
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+    return None
+
+def run_filter_test(client, content_filter):
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("form_watch_add"),
+        data={"url": test_url, "tag": ''},
+        follow_redirects=True
+    )
+    assert b"Watch added" in res.data
+
+    # Give the thread time to pick up the first version
+    time.sleep(3)
+
+    # Goto the edit page, add our ignore text
+    # Add our URL to the import page
+    url = url_for('test_notification_endpoint', _external=True)
+    notification_url = url.replace('http', 'json')
+
+    print(">>>> Notification URL: " + notification_url)
+
+    # Just a regular notification setting, this will be used by the special 'filter not found' notification
+    notification_form_data = {"notification_urls": notification_url,
+                              "notification_title": "New ChangeDetection.io Notification - {watch_url}",
+                              "notification_body": "BASE URL: {base_url}\n"
+                                                   "Watch URL: {watch_url}\n"
+                                                   "Watch UUID: {watch_uuid}\n"
+                                                   "Watch title: {watch_title}\n"
+                                                   "Watch tag: {watch_tag}\n"
+                                                   "Preview: {preview_url}\n"
+                                                   "Diff URL: {diff_url}\n"
+                                                   "Snapshot: {current_snapshot}\n"
+                                                   "Diff: {diff}\n"
+                                                   "Diff Full: {diff_full}\n"
+                                                   ":-)",
+                              "notification_format": "Text"}
+
+    notification_form_data.update({
+        "url": test_url,
+        "tag": "my tag",
+        "title": "my title",
+        "headers": "",
+        "css_filter": content_filter,
+        "fetch_backend": "html_requests"})
+
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data=notification_form_data,
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    time.sleep(3)
+
+    # Now the notification should not exist, because we didnt reach the threshold
+    assert not os.path.isfile("test-datastore/notification.txt")
+
+    for i in range(0, App._FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT):
+        res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+        time.sleep(3)
+
+    # We should see something in the frontend
+    assert b'Did the page change its layout' in res.data
+
+    # Now it should exist and contain our "filter not found" alert
+    assert os.path.isfile("test-datastore/notification.txt")
+    notification = False
+    with open("test-datastore/notification.txt", 'r') as f:
+        notification = f.read()
+    assert 'CSS/xPath filter was not present in the page' in notification
+    assert content_filter.replace('"', '\\"') in notification
+
+    # Remove it and prove that it doesnt trigger when not expected
+    os.unlink("test-datastore/notification.txt")
+    set_response_with_filter()
+
+    for i in range(0, App._FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT):
+        client.get(url_for("form_watch_checknow"), follow_redirects=True)
+        time.sleep(3)
+
+    # It should have sent a notification, but..
+    assert os.path.isfile("test-datastore/notification.txt")
+    # but it should not contain the info about the failed filter
+    with open("test-datastore/notification.txt", 'r') as f:
+        notification = f.read()
+    assert not 'CSS/xPath filter was not present in the page' in notification
+
+    # cleanup for the next
+    client.get(
+        url_for("form_delete", uuid="all"),
+        follow_redirects=True
+    )
+    os.unlink("test-datastore/notification.txt")
+
+
+def test_setup(live_server):
+    live_server_setup(live_server)
+
+def test_check_css_filter_failure_notification(client, live_server):
+    set_original_response()
+    time.sleep(1)
+    run_filter_test(client, '#nope-doesnt-exist')
+
+def test_check_xpath_filter_failure_notification(client, live_server):
+    set_original_response()
+    time.sleep(1)
+    run_filter_test(client, '//*[@id="nope-doesnt-exist"]')
+

changedetectionio/tests/test_history_consistency.py

@@ -0,0 +1,84 @@
+#!/usr/bin/python3
+
+import time
+import os
+import json
+import logging
+from flask import url_for
+from .util import live_server_setup
+from urllib.parse import urlparse, parse_qs
+
+def test_consistent_history(client, live_server):
+    live_server_setup(live_server)
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+    r = range(1, 50)
+
+    for one in r:
+        test_url = url_for('test_endpoint', content_type="text/html", content=str(one), _external=True)
+        res = client.post(
+            url_for("import_page"),
+            data={"urls": test_url},
+            follow_redirects=True
+        )
+
+        assert b"1 Imported" in res.data
+
+    time.sleep(3)
+    while True:
+        res = client.get(url_for("index"))
+        logging.debug("Waiting for 'Checking now' to go away..")
+        if b'Checking now' not in res.data:
+            break
+        time.sleep(0.5)
+
+    time.sleep(3)
+    # Essentially just triggers the DB write/update
+    res = client.post(
+        url_for("settings_page"),
+        data={"application-empty_pages_are_a_change": "",
+              "requests-time_between_check-minutes": 180,
+              'application-fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Settings updated." in res.data
+
+    # Give it time to write it out
+    time.sleep(3)
+    json_db_file = os.path.join(live_server.app.config['DATASTORE'].datastore_path, 'url-watches.json')
+
+    json_obj = None
+    with open(json_db_file, 'r') as f:
+        json_obj = json.load(f)
+
+    # assert the right amount of watches was found in the JSON
+    assert len(json_obj['watching']) == len(r), "Correct number of watches was found in the JSON"
+
+    # each one should have a history.txt containing just one line
+    for w in json_obj['watching'].keys():
+        history_txt_index_file = os.path.join(live_server.app.config['DATASTORE'].datastore_path, w, 'history.txt')
+        assert os.path.isfile(history_txt_index_file), "History.txt should exist where I expect it - {}".format(history_txt_index_file)
+
+        # Same like in model.Watch
+        with open(history_txt_index_file, "r") as f:
+            tmp_history = dict(i.strip().split(',', 2) for i in f.readlines())
+            assert len(tmp_history) == 1, "History.txt should contain 1 line"
+
+        # Should be two files,. the history.txt , and the snapshot.txt
+        files_in_watch_dir = os.listdir(os.path.join(live_server.app.config['DATASTORE'].datastore_path,
+                                                     w))
+        # Find the snapshot one
+        for fname in files_in_watch_dir:
+            if fname != 'history.txt':
+                # contents should match what we requested as content returned from the test url
+                with open(os.path.join(live_server.app.config['DATASTORE'].datastore_path, w, fname), 'r') as snapshot_f:
+                    contents = snapshot_f.read()
+                    watch_url = json_obj['watching'][w]['url']
+                    u = urlparse(watch_url)
+                    q = parse_qs(u[4])
+                    assert q['content'][0] == contents.strip(), "Snapshot file {} should contain {}".format(fname, q['content'][0])
+
+
+
+        assert len(files_in_watch_dir) == 2, "Should be just two files in the dir, history.txt and the snapshot"

changedetectionio/tests/test_ignore_text.py

@@ -102,7 +102,7 @@ def test_check_ignore_text_functionality(client, live_server):
     assert b"1 Imported" in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -123,7 +123,7 @@ def test_check_ignore_text_functionality(client, live_server):
     assert bytes(ignore_text.encode('utf-8')) in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -137,7 +137,7 @@ def test_check_ignore_text_functionality(client, live_server):
     set_modified_ignore_response()
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 
@@ -152,7 +152,7 @@ def test_check_ignore_text_functionality(client, live_server):
 
     # Just to be sure.. set a regular modified change..
     set_modified_original_ignore_response()
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
 
     res = client.get(url_for("index"))
@@ -165,7 +165,7 @@ def test_check_ignore_text_functionality(client, live_server):
     # We should be able to see what we ignored
     assert b'<div class="ignored">new ignore stuff' in res.data
 
-    res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
 def test_check_global_ignore_text_functionality(client, live_server):
@@ -200,7 +200,7 @@ def test_check_global_ignore_text_functionality(client, live_server):
     assert b"1 Imported" in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -222,7 +222,7 @@ def test_check_global_ignore_text_functionality(client, live_server):
     assert bytes(ignore_text.encode('utf-8')) in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -240,7 +240,7 @@ def test_check_global_ignore_text_functionality(client, live_server):
     set_modified_ignore_response()
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 
@@ -251,10 +251,10 @@ def test_check_global_ignore_text_functionality(client, live_server):
 
     # Just to be sure.. set a regular modified change that will trigger it
     set_modified_original_ignore_response()
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
-    res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/test_ignorehyperlinks.py

@@ -72,14 +72,14 @@ def test_render_anchor_tag_content_true(client, live_server):
 
     time.sleep(sleep_time_for_fetch_thread)
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # set a new html text with a modified link
     set_modified_ignore_response()
     time.sleep(sleep_time_for_fetch_thread)
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -101,7 +101,7 @@ def test_render_anchor_tag_content_true(client, live_server):
     assert b"Settings updated." in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -119,7 +119,7 @@ def test_render_anchor_tag_content_true(client, live_server):
     assert b"/test-endpoint" in res.data
 
     # Cleanup everything
-    res = client.get(url_for("api_delete", uuid="all"),
+    res = client.get(url_for("form_delete", uuid="all"),
                      follow_redirects=True)
     assert b'Deleted' in res.data
 

changedetectionio/tests/test_ignorestatuscode.py

@@ -70,12 +70,12 @@ def test_normal_page_check_works_with_ignore_status_code(client, live_server):
 
     time.sleep(sleep_time_for_fetch_thread)
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     set_some_changed_response()
     time.sleep(sleep_time_for_fetch_thread)
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -105,7 +105,7 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server):
     assert b"1 Imported" in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -120,7 +120,7 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server):
     assert b"Updated watch." in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -128,7 +128,7 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server):
     set_some_changed_response()
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 
@@ -157,7 +157,7 @@ def test_403_page_check_fails_without_ignore_status_code(client, live_server):
     assert b"1 Imported" in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -172,7 +172,7 @@ def test_403_page_check_fails_without_ignore_status_code(client, live_server):
     assert b"Updated watch." in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -180,7 +180,7 @@ def test_403_page_check_fails_without_ignore_status_code(client, live_server):
     set_some_changed_response()
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 

changedetectionio/tests/test_ignorewhitespace.py

@@ -80,12 +80,12 @@ def test_check_ignore_whitespace(client, live_server):
 
     time.sleep(sleep_time_for_fetch_thread)
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     set_original_ignore_response_but_with_whitespace()
     time.sleep(sleep_time_for_fetch_thread)
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)

changedetectionio/tests/test_import.py

@@ -5,18 +5,17 @@ import time
 from flask import url_for
 
 from .util import live_server_setup
-
-
-def test_import(client, live_server):
-
+def test_setup(client, live_server):
     live_server_setup(live_server)
 
+def test_import(client, live_server):
     # Give the endpoint time to spin up
     time.sleep(1)
 
     res = client.post(
         url_for("import_page"),
         data={
+            "distill-io": "",
             "urls": """https://example.com
 https://example.com tag1
 https://example.com tag1, other tag"""
@@ -26,3 +25,96 @@ https://example.com tag1, other tag"""
     assert b"3 Imported" in res.data
     assert b"tag1" in res.data
     assert b"other tag" in res.data
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+
+    # Clear flask alerts
+    res = client.get( url_for("index"))
+    res = client.get( url_for("index"))
+
+def xtest_import_skip_url(client, live_server):
+
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    res = client.post(
+        url_for("import_page"),
+        data={
+            "distill-io": "",
+            "urls": """https://example.com
+:ht000000broken
+"""
+        },
+        follow_redirects=True,
+    )
+    assert b"1 Imported" in res.data
+    assert b"ht000000broken" in res.data
+    assert b"1 Skipped" in res.data
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    # Clear flask alerts
+    res = client.get( url_for("index"))
+
+def test_import_distillio(client, live_server):
+
+    distill_data='''
+{
+    "client": {
+        "local": 1
+    },
+    "data": [
+        {
+            "name": "Unraid | News",
+            "uri": "https://unraid.net/blog",
+            "config": "{\\"selections\\":[{\\"frames\\":[{\\"index\\":0,\\"excludes\\":[],\\"includes\\":[{\\"type\\":\\"xpath\\",\\"expr\\":\\"(//div[@id='App']/div[contains(@class,'flex')]/main[contains(@class,'relative')]/section[contains(@class,'relative')]/div[@class='container']/div[contains(@class,'flex')]/div[contains(@class,'w-full')])[1]\\"}]}],\\"dynamic\\":true,\\"delay\\":2}],\\"ignoreEmptyText\\":true,\\"includeStyle\\":false,\\"dataAttr\\":\\"text\\"}",
+            "tags": ["nice stuff", "nerd-news"],
+            "content_type": 2,
+            "state": 40,
+            "schedule": "{\\"type\\":\\"INTERVAL\\",\\"params\\":{\\"interval\\":4447}}",
+            "ts": "2022-03-27T15:51:15.667Z"
+        }
+    ]
+}		   
+
+'''
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    res = client.post(
+        url_for("import_page"),
+        data={
+            "distill-io": distill_data,
+            "urls" : ''
+        },
+        follow_redirects=True,
+    )
+
+
+    assert b"Unable to read JSON file, was it broken?" not in res.data
+    assert b"1 Imported from Distill.io" in res.data
+
+    res = client.get( url_for("edit_page", uuid="first"))
+
+    assert b"https://unraid.net/blog" in res.data
+    assert b"Unraid | News" in res.data
+
+
+    # flask/wtforms should recode this, check we see it
+    # wtforms encodes it like id=&#39 ,but html.escape makes it like id=&#x27
+    # - so just check it manually :(
+    #import json
+    #import html
+    #d = json.loads(distill_data)
+    # embedded_d=json.loads(d['data'][0]['config'])
+    # x=html.escape(embedded_d['selections'][0]['frames'][0]['includes'][0]['expr']).encode('utf-8')
+    assert b"xpath:(//div[@id='App']/div[contains(@class,'flex')]/main[contains(@class,'relative')]/section[contains(@class,'relative')]/div[@class='container']/div[contains(@class,'flex')]/div[contains(@class,'w-full')])[1]" in res.data
+
+    # did the tags work?
+    res = client.get( url_for("index"))
+
+    assert b"nice stuff" in res.data
+    assert b"nerd-news" in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    # Clear flask alerts
+    res = client.get(url_for("index"))

changedetectionio/tests/test_jsonpath_selector.py

@@ -171,7 +171,7 @@ def test_check_json_without_filter(client, live_server):
     )
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(3)
@@ -203,7 +203,7 @@ def test_check_json_filter(client, live_server):
     assert b"1 Imported" in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(3)
@@ -229,7 +229,7 @@ def test_check_json_filter(client, live_server):
     assert bytes(json_filter.encode('utf-8')) in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(3)
@@ -237,7 +237,7 @@ def test_check_json_filter(client, live_server):
     set_modified_response()
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     # Give the thread time to pick it up
     time.sleep(4)
 
@@ -288,7 +288,7 @@ def test_check_json_filter_bool_val(client, live_server):
     time.sleep(3)
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(3)
@@ -296,7 +296,7 @@ def test_check_json_filter_bool_val(client, live_server):
     set_modified_response()
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     # Give the thread time to pick it up
     time.sleep(3)
 
@@ -327,7 +327,7 @@ def test_check_json_ext_filter(client, live_server):
     assert b"1 Imported" in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(3)
@@ -353,7 +353,7 @@ def test_check_json_ext_filter(client, live_server):
     assert bytes(json_filter.encode('utf-8')) in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(3)
@@ -361,7 +361,7 @@ def test_check_json_ext_filter(client, live_server):
     set_modified_ext_response()
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     # Give the thread time to pick it up
     time.sleep(4)
 

changedetectionio/tests/test_nonrenderable_pages.py

@@ -0,0 +1,102 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from urllib.request import urlopen
+from .util import set_original_response, set_modified_response, live_server_setup
+
+sleep_time_for_fetch_thread = 3
+
+
+def set_nonrenderable_response():
+    test_return_data = """<html>
+    <head><title>modified head title</title></head>
+    <!-- like when some angular app was broken and doesnt render or whatever -->
+    <body>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+    return None
+
+def test_check_basic_change_detection_functionality(client, live_server):
+    set_original_response()
+    live_server_setup(live_server)
+
+    # Add our URL to the import page
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": url_for('test_endpoint', _external=True)},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # Do this a few times.. ensures we dont accidently set the status
+    for n in range(3):
+        client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
+        # Give the thread time to pick it up
+        time.sleep(sleep_time_for_fetch_thread)
+
+        # It should report nothing found (no new 'unviewed' class)
+        res = client.get(url_for("index"))
+        assert b'unviewed' not in res.data
+
+
+    #####################
+    client.post(
+        url_for("settings_page"),
+        data={"application-empty_pages_are_a_change": "",
+              "requests-time_between_check-minutes": 180,
+              'application-fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+
+    # this should not trigger a change, because no good text could be converted from the HTML
+    set_nonrenderable_response()
+
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+
+
+    # ok now do the opposite
+
+    client.post(
+        url_for("settings_page"),
+        data={"application-empty_pages_are_a_change": "y",
+              "requests-time_between_check-minutes": 180,
+              'application-fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    set_modified_response()
+
+
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+
+
+
+    #
+    # Cleanup everything
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+

changedetectionio/tests/test_notification.py

@@ -36,7 +36,7 @@ def test_check_notification(client, live_server):
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(
-        url_for("api_watch_add"),
+        url_for("form_watch_add"),
         data={"url": test_url, "tag": ''},
         follow_redirects=True
     )
@@ -98,7 +98,7 @@ def test_check_notification(client, live_server):
     notification_submission = None
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(3)
     # Verify what was sent as a notification, this file should exist
     with open("test-datastore/notification.txt", "r") as f:
@@ -133,7 +133,7 @@ def test_check_notification(client, live_server):
 
     # This should insert the {current_snapshot}
     set_more_modified_response()
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(3)
     # Verify what was sent as a notification, this file should exist
     with open("test-datastore/notification.txt", "r") as f:
@@ -146,17 +146,21 @@ def test_check_notification(client, live_server):
     os.unlink("test-datastore/notification.txt")
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(1)
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(1)
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(1)
     assert os.path.exists("test-datastore/notification.txt") == False
 
+    res = client.get(url_for("notification_logs"))
+    # be sure we see it in the output log
+    assert b'New ChangeDetection.io Notification - ' + test_url.encode('utf-8') in res.data
+
     # cleanup for the next
     client.get(
-        url_for("api_delete", uuid="all"),
+        url_for("form_delete", uuid="all"),
         follow_redirects=True
     )
 
@@ -168,7 +172,7 @@ def test_notification_validation(client, live_server):
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(
-        url_for("api_watch_add"),
+        url_for("form_watch_add"),
         data={"url": test_url, "tag": 'nice one'},
         follow_redirects=True
     )
@@ -208,6 +212,6 @@ def test_notification_validation(client, live_server):
 
     # cleanup for the next
     client.get(
-        url_for("api_delete", uuid="all"),
+        url_for("form_delete", uuid="all"),
         follow_redirects=True
     )

changedetectionio/tests/test_notification_errors.py

@@ -16,7 +16,7 @@ def test_check_notification_error_handling(client, live_server):
     # use a different URL so that it doesnt interfere with the actual check until we are ready
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(
-        url_for("api_watch_add"),
+        url_for("form_watch_add"),
         data={"url": "https://changedetection.io/CHANGELOG.txt", "tag": ''},
         follow_redirects=True
     )

changedetectionio/tests/test_obfuscations.py

@@ -0,0 +1,43 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from .util import live_server_setup
+
+
+def set_original_ignore_response():
+    test_return_data = """<html>
+       <body>
+     <span>The price is</span><span>$<!-- -->90<!-- -->.<!-- -->74</span>
+     </body>
+     </html>
+
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def test_obfuscations(client, live_server):
+    set_original_ignore_response()
+    live_server_setup(live_server)
+    time.sleep(1)
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    # Give the thread time to pick it up
+    time.sleep(3)
+
+    # Check HTML conversion detected and workd
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert b'$90.74' in res.data

changedetectionio/tests/test_share_watch.py

@@ -41,7 +41,7 @@ def test_share_watch(client, live_server):
 
     # click share the link
     res = client.get(
-        url_for("api_share_put_watch", uuid="first"),
+        url_for("form_share_put_watch", uuid="first"),
         follow_redirects=True
     )
 
@@ -54,7 +54,7 @@ def test_share_watch(client, live_server):
 
     # Now delete what we have, we will try to re-import it
     # Cleanup everything
-    res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
     # Add our URL to the import page

changedetectionio/tests/test_source.py

@@ -39,7 +39,7 @@ def test_check_basic_change_detection_functionality_source(client, live_server):
     set_modified_response()
 
     # Force recheck
-    res = client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
     assert b'1 watches are queued for rechecking.' in res.data
 
     time.sleep(5)

changedetectionio/tests/test_trigger.py

@@ -43,7 +43,7 @@ def set_modified_with_trigger_text_response():
      Some NEW nice initial text</br>
      <p>Which is across multiple lines</p>
      </br>
-     foobar123
+     Add to cart
      <br/>
      So let's see what happens.  </br>
      </body>
@@ -60,7 +60,7 @@ def test_trigger_functionality(client, live_server):
     live_server_setup(live_server)
 
     sleep_time_for_fetch_thread = 3
-    trigger_text = "foobar123"
+    trigger_text = "Add to cart"
     set_original_ignore_response()
 
     # Give the endpoint time to spin up
@@ -76,10 +76,7 @@ def test_trigger_functionality(client, live_server):
     assert b"1 Imported" in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Goto the edit page, add our ignore text
     # Add our URL to the import page
@@ -98,8 +95,14 @@ def test_trigger_functionality(client, live_server):
     )
     assert bytes(trigger_text.encode('utf-8')) in res.data
 
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+    
+    # so that we set the state to 'unviewed' after all the edits
+    client.get(url_for("diff_history_page", uuid="first"))
+
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -113,7 +116,7 @@ def test_trigger_functionality(client, live_server):
     set_modified_original_ignore_response()
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 
@@ -121,16 +124,22 @@ def test_trigger_functionality(client, live_server):
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
 
-    # Just to be sure.. set a regular modified change..
+    # Now set the content which contains the trigger text
     time.sleep(sleep_time_for_fetch_thread)
     set_modified_with_trigger_text_response()
 
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
+    
+    # https://github.com/dgtlmoon/changedetection.io/issues/616
+    # Apparently the actual snapshot that contains the trigger never shows
+    res = client.get(url_for("diff_history_page", uuid="first"))
+    assert b'Add to cart' in res.data
 
     # Check the preview/highlighter, we should be able to see what we triggered on, but it should be highlighted
     res = client.get(url_for("preview_page", uuid="first"))
-    # We should be able to see what we ignored
-    assert b'<div class="triggered">foobar' in res.data
+
+    # We should be able to see what we triggered on
+    assert b'<div class="triggered">Add to cart' in res.data

changedetectionio/tests/test_trigger_regex.py

@@ -42,9 +42,6 @@ def test_trigger_regex_functionality(client, live_server):
     )
     assert b"1 Imported" in res.data
 
-    # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 
@@ -60,12 +57,14 @@ def test_trigger_regex_functionality(client, live_server):
               "fetch_backend": "html_requests"},
         follow_redirects=True
     )
-
+    time.sleep(sleep_time_for_fetch_thread)
+    # so that we set the state to 'unviewed' after all the edits
+    client.get(url_for("diff_history_page", uuid="first"))
 
     with open("test-datastore/endpoint-content.txt", "w") as f:
         f.write("some new noise")
 
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
 
     # It should report nothing found (nothing should match the regex)
@@ -75,7 +74,11 @@ def test_trigger_regex_functionality(client, live_server):
     with open("test-datastore/endpoint-content.txt", "w") as f:
         f.write("regex test123<br/>\nsomething 123")
 
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
     res = client.get(url_for("index"))
-    assert b'unviewed' in res.data
+    assert b'unviewed' in res.data
+
+    # Cleanup everything
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_trigger_regex_with_filter.py

@@ -22,10 +22,9 @@ def set_original_ignore_response():
 
 
 
-def test_trigger_regex_functionality(client, live_server):
+def test_trigger_regex_functionality_with_filter(client, live_server):
 
     live_server_setup(live_server)
-
     sleep_time_for_fetch_thread = 3
 
     set_original_ignore_response()
@@ -42,43 +41,44 @@ def test_trigger_regex_functionality(client, live_server):
     )
     assert b"1 Imported" in res.data
 
-    # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
+    # it needs time to save the original version
     time.sleep(sleep_time_for_fetch_thread)
 
-    # It should report nothing found (just a new one shouldnt have anything)
-    res = client.get(url_for("index"))
-    assert b'unviewed' not in res.data
-
     ### test regex with filter
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"trigger_text": "/cool.stuff\d/",
+        data={"trigger_text": "/cool.stuff/",
               "url": test_url,
               "css_filter": '#in-here',
               "fetch_backend": "html_requests"},
         follow_redirects=True
     )
 
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    client.get(url_for("diff_history_page", uuid="first"))
+
     # Check that we have the expected text.. but it's not in the css filter we want
     with open("test-datastore/endpoint-content.txt", "w") as f:
         f.write("<html>some new noise with cool stuff2 ok</html>")
 
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
 
     # It should report nothing found (nothing should match the regex and filter)
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
 
+    # now this should trigger something
     with open("test-datastore/endpoint-content.txt", "w") as f:
         f.write("<html>some new noise with <span id=in-here>cool stuff6</span> ok</html>")
 
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
-
+# Cleanup everything
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_unique_lines.py

@@ -0,0 +1,104 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from .util import live_server_setup
+
+
+def set_original_ignore_response():
+    test_return_data = """<html>
+     <body>
+     <p>Some initial text</p>
+     <p>Which is across multiple lines</p>
+     <p>So let's see what happens.</p>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+# The same but just re-ordered the text
+def set_modified_swapped_lines():
+    # Re-ordered and with some whitespacing, should get stripped() too.
+    test_return_data = """<html>
+     <body>
+     <p>Some initial text</p>
+     <p>   So let's see what happens.</p>
+     <p>&nbsp;Which is across multiple lines</p>     
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def set_modified_with_trigger_text_response():
+    test_return_data = """<html>
+     <body>
+     <p>Some initial text</p>
+     <p>So let's see what happens.</p>
+     <p>and a new line!</p>
+     <p>Which is across multiple lines</p>     
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def test_unique_lines_functionality(client, live_server):
+    live_server_setup(live_server)
+
+    sleep_time_for_fetch_thread = 3
+
+    set_original_ignore_response()
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"check_unique_lines": "y",
+              "url": test_url,
+              "fetch_backend": "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    assert b'unviewed' not in res.data
+
+    #  Make a change
+    set_modified_swapped_lines()
+
+    time.sleep(sleep_time_for_fetch_thread)
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+
+
+    # Now set the content which contains the new text and re-ordered existing text
+    set_modified_with_trigger_text_response()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    time.sleep(sleep_time_for_fetch_thread)
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+

changedetectionio/tests/test_xpath_selector.py

@@ -44,6 +44,61 @@ def set_modified_response():
 
     return None
 
+# Handle utf-8 charset replies https://github.com/dgtlmoon/changedetection.io/pull/613
+def test_check_xpath_filter_utf8(client, live_server):
+    filter='//item/*[self::description]'
+
+    d='''<?xml version="1.0" encoding="UTF-8"?>
+<rss xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
+	<channel>
+		<title>rpilocator.com</title>
+		<link>https://rpilocator.com</link>
+		<description>Find Raspberry Pi Computers in Stock</description>
+		<lastBuildDate>Thu, 19 May 2022 23:27:30 GMT</lastBuildDate>
+		<image>
+			<url>https://rpilocator.com/favicon.png</url>
+			<title>rpilocator.com</title>
+			<link>https://rpilocator.com/</link>
+			<width>32</width>
+			<height>32</height>
+		</image>
+		<item>
+			<title>Stock Alert (UK): RPi CM4 - 1GB RAM, No MMC, No Wifi is In Stock at Pimoroni</title>
+			<description>Stock Alert (UK): RPi CM4 - 1GB RAM, No MMC, No Wifi is In Stock at Pimoroni</description>
+			<link>https://rpilocator.com?vendor=pimoroni&amp;utm_source=feed&amp;utm_medium=rss</link>
+			<category>pimoroni</category>
+			<category>UK</category>
+			<category>CM4</category>
+			<guid isPermaLink="false">F9FAB0D9-DF6F-40C8-8DEE5FC0646BB722</guid>
+			<pubDate>Thu, 19 May 2022 14:32:32 GMT</pubDate>
+		</item>
+	</channel>
+</rss>'''
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(d)
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True, content_type="application/rss+xml;charset=UTF-8")
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"css_filter": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    time.sleep(3)
+    res = client.get(url_for("index"))
+    assert b'Unicode strings with encoding declaration are not supported.' not in res.data
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+
 
 def test_check_markup_xpath_filter_restriction(client, live_server):
     sleep_time_for_fetch_thread = 3
@@ -65,7 +120,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
     assert b"1 Imported" in res.data
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
@@ -89,12 +144,14 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
     set_modified_response()
 
     # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
 
 
 def test_xpath_validation(client, live_server):
@@ -116,4 +173,46 @@ def test_xpath_validation(client, live_server):
         data={"css_filter": "/something horrible", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
-    assert b"is not a valid XPath expression" in res.data
+    assert b"is not a valid XPath expression" in res.data
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+
+# actually only really used by the distll.io importer, but could be handy too
+def test_check_with_prefix_css_filter(client, live_server):
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    set_original_response()
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+    time.sleep(3)
+
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"css_filter":  "xpath://*[contains(@class, 'sametext')]", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+
+    assert b"Updated watch." in res.data
+    time.sleep(3)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert b"Some text thats the same" in res.data #in selector
+    assert b"Some text that will change" not in res.data #not in selector
+
+    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

changedetectionio/tests/util.py

@@ -1,6 +1,7 @@
 #!/usr/bin/python3
 
 from flask import make_response, request
+from flask import url_for
 
 def set_original_response():
     test_return_data = """<html>
@@ -55,14 +56,32 @@ def set_more_modified_response():
     return None
 
 
+# kinda funky, but works for now
+def extract_api_key_from_UI(client):
+    import re
+    res = client.get(
+        url_for("settings_page"),
+    )
+    # <span id="api-key">{{api_key}}</span>
+
+    m = re.search('<span id="api-key">(.+?)</span>', str(res.data))
+    api_key = m.group(1)
+    return api_key.strip()
+
 def live_server_setup(live_server):
 
     @live_server.app.route('/test-endpoint')
     def test_endpoint():
         ctype = request.args.get('content_type')
         status_code = request.args.get('status_code')
+        content = request.args.get('content') or None
 
         try:
+            if content is not None:
+                resp = make_response(content, status_code)
+                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)

changedetectionio/update_worker.py

@@ -3,6 +3,8 @@ import queue
 import time
 
 from changedetectionio import content_fetcher
+from changedetectionio.html_tools import FilterNotFoundInResponse
+
 # A single update worker
 #
 # Requests for checking on a single site(watch) from a queue of watches
@@ -19,6 +21,32 @@ class update_worker(threading.Thread):
         self.datastore = datastore
         super().__init__(*args, **kwargs)
 
+    def send_filter_failure_notification(self, uuid):
+
+        threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts')
+        watch = self.datastore.data['watching'].get(uuid, False)
+
+        n_object = {'notification_title': 'Changedetection.io - Alert - CSS/xPath filter was not present in the page',
+                    'notification_body': "Your configured CSS/xPath filter of '{}' for {{watch_url}} did not appear on the page after {} attempts, did the page change layout?\n\nLink: {{base_url}}/edit/{{watch_uuid}}\n\nThanks - Your omniscient changedetection.io installation :)\n".format(
+                        watch['css_filter'],
+                        threshold),
+                    'notification_format': 'text'}
+
+        if len(watch['notification_urls']):
+            n_object['notification_urls'] = watch['notification_urls']
+
+        elif len(self.datastore.data['settings']['application']['notification_urls']):
+            n_object['notification_urls'] = self.datastore.data['settings']['application']['notification_urls']
+
+        # Only prepare to notify if the rules above matched
+        if 'notification_urls' in n_object:
+            n_object.update({
+                'watch_url': watch['url'],
+                'uuid': uuid
+            })
+            self.notification_q.put(n_object)
+            print("Sent filter not found notification for {}".format(uuid))
+
     def run(self):
         from changedetectionio import fetch_site_status
 
@@ -40,11 +68,11 @@ class update_worker(threading.Thread):
                     contents = ""
                     screenshot = False
                     update_obj= {}
+                    xpath_data = False
                     now = time.time()
 
                     try:
-                        changed_detected, update_obj, contents, screenshot = update_handler.run(uuid)
-
+                        changed_detected, update_obj, contents, screenshot, xpath_data = update_handler.run(uuid)
                         # Re #342
                         # In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.
                         # We then convert/.decode('utf-8') for the notification etc
@@ -52,9 +80,37 @@ class update_worker(threading.Thread):
                             raise Exception("Error - returned data from the fetch handler SHOULD be bytes")
                     except PermissionError as e:
                         self.app.logger.error("File permission error updating", uuid, str(e))
+                    except content_fetcher.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
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found."})
+                    except FilterNotFoundInResponse as e:
+                        err_text = "Filter '{}' not found - Did the page change its layout?".format(str(e))
+                        c = 0
+                        if self.datastore.data['watching'].get(uuid, False):
+                            c = self.datastore.data['watching'][uuid].get('consecutive_filter_failures', 5)
+                        c += 1
+
+                        # Send notification if we reached the threshold?
+                        threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts', 0)
+                        print("Filter for {} not found, consecutive_filter_failures: {}".format(uuid, c))
+                        if threshold >0 and c >= threshold:
+                            self.send_filter_failure_notification(uuid)
+                            c = 0
+
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                                                                           'consecutive_filter_failures': c})
                     except content_fetcher.EmptyReply as e:
                         # Some kind of custom to-str handler in the exception handler that does this?
-                        err_text = "EmptyReply: Status Code {}".format(e.status_code)
+                        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})
+                    except content_fetcher.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})
+                    except content_fetcher.PageUnloadable as e:
+                        err_text = "Page request from server didnt respond correctly"
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                     except Exception as e:
@@ -69,11 +125,10 @@ class update_worker(threading.Thread):
                             # For the FIRST time we check a site, or a change detected, save the snapshot.
                             if changed_detected or not watch['last_checked']:
                                 # A change was detected
-                                fname = self.datastore.save_history_text(watch_uuid=uuid, contents=contents)
-                                # Should always be keyed by string(timestamp)
-                                self.datastore.update_watch(uuid, {"history": {str(round(time.time())): fname}})
+                                fname = watch.save_history_text(contents=contents, timestamp=str(round(time.time())))
 
                             # Generally update anything interesting returned
+                            update_obj['consecutive_filter_failures'] = 0
                             self.datastore.update_watch(uuid=uuid, update_obj=update_obj)
 
                             # A change was detected
@@ -82,17 +137,19 @@ class update_worker(threading.Thread):
                                 print (">> Change detected in UUID {} - {}".format(uuid, watch['url']))
 
                                 # Notifications should only trigger on the second time (first time, we gather the initial snapshot)
-                                if len(watch['history']) > 1:
-
-                                    dates = list(watch['history'].keys())
-                                    # Convert to int, sort and back to str again
-                                    # @todo replace datastore getter that does this automatically
-                                    dates = [int(i) for i in dates]
-                                    dates.sort(reverse=True)
-                                    dates = [str(i) for i in dates]
-
-                                    prev_fname = watch['history'][dates[1]]
+                                if watch.history_n >= 2:
+                                    # Atleast 2, means there really was a change
+                                    self.datastore.update_watch(uuid=uuid, update_obj={'last_changed': round(now)})
 
+                                    watch_history = watch.history
+                                    dates = list(watch_history.keys())
+                                    # Theoretically it's possible that this could be just 1 long,
+                                    # - In the case that the timestamp key was not unique
+                                    if len(dates) == 1:
+                                        raise ValueError(
+                                            "History index had 2 or more, but only 1 date loaded, timestamps were not unique? maybe two of the same timestamps got written, needs more delay?"
+                                        )
+                                    prev_fname = watch_history[dates[-2]]
 
                                     # Did it have any notification alerts to hit?
                                     if len(watch['notification_urls']):
@@ -141,9 +198,13 @@ class update_worker(threading.Thread):
                         # Always record that we atleast tried
                         self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
                                                                            'last_checked': round(time.time())})
+
                         # Always save the screenshot if it's available
                         if screenshot:
                             self.datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
+                        if xpath_data:
+                            self.datastore.save_xpath_data(watch_uuid=uuid, data=xpath_data)
+
 
                 self.current_uuid = None  # Done
                 self.q.task_done()

docker-compose.yml

@@ -17,14 +17,14 @@ services:
   #       Alternative WebDriver/selenium URL, do not use "'s or 's!
   #      - WEBDRIVER_URL=http://browser-chrome:4444/wd/hub
   #
-  #       WebDriver proxy settings webdriver_proxyType, webdriver_ftpProxy, webdriver_httpProxy, webdriver_noProxy,
-  #                                webdriver_proxyAutoconfigUrl, webdriver_sslProxy, webdriver_autodetect,
+  #       WebDriver proxy settings webdriver_proxyType, webdriver_ftpProxy, webdriver_noProxy,
+  #                                webdriver_proxyAutoconfigUrl, webdriver_autodetect,
   #                                webdriver_socksProxy, webdriver_socksUsername, webdriver_socksVersion, webdriver_socksPassword
   #
   #             https://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.common.proxy
   #
   #       Alternative Playwright URL, do not use "'s or 's!
-  #      - PLAYWRIGHT_DRIVER_URL=ws://playwright-chrome:3000/playwright
+  #      - PLAYWRIGHT_DRIVER_URL=ws://playwright-chrome:3000/?stealth=1&--disable-web-security=true
   #
   #       Playwright proxy settings playwright_proxy_server, playwright_proxy_bypass, playwright_proxy_username, playwright_proxy_password
   #
@@ -73,6 +73,17 @@ services:
 #        hostname: playwright-chrome
 #        image: browserless/chrome
 #        restart: unless-stopped
+#        environment:
+#            - SCREEN_WIDTH=1920
+#            - SCREEN_HEIGHT=1024
+#            - SCREEN_DEPTH=16
+#            - ENABLE_DEBUGGER=false
+#            - PREBOOT_CHROME=true
+#            - CONNECTION_TIMEOUT=300000
+#            - MAX_CONCURRENT_SESSIONS=10
+#            - CHROME_REFRESH_TIME=600000
+#            - DEFAULT_BLOCK_ADS=true
+#            - DEFAULT_STEALTH=true
 
 volumes:
   changedetection-data:

requirements.txt

@@ -6,6 +6,7 @@ timeago ~=1.0
 inscriptis ~= 2.2
 feedgen ~= 0.9
 flask-login ~= 0.5
+flask_restful
 pytz
 
 # Set these versions together to avoid a RequestsDependencyWarning
@@ -17,7 +18,7 @@ wtforms ~= 3.0
 jsonpath-ng ~= 1.5.3
 
 # Notification library
-apprise ~= 0.9.8.3
+apprise ~= 0.9.9
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 paho-mqtt