Merge branch 'master' into hours-day-schedule

.github/ISSUE_TEMPLATE/bug_report.md

@@ -7,6 +7,20 @@ assignees: 'dgtlmoon'
 
 ---
 
+**DO NOT USE THIS FORM TO REPORT THAT A PARTICULAR WEBSITE IS NOT SCRAPING/WATCHING AS EXPECTED**
+
+This form is only for direct bugs and feature requests todo directly with the software.
+
+Please report watched websites (full URL and _any_ settings) that do not work with changedetection.io as expected [**IN THE DISCUSSION FORUMS**](https://github.com/dgtlmoon/changedetection.io/discussions) or your report will be deleted
+
+CONSIDER TAKING OUT A SUBSCRIPTION FOR A SMALL PRICE PER MONTH, YOU GET THE BENEFIT OF USING OUR PAID PROXIES AND FURTHERING THE DEVELOPMENT OF CHANGEDETECTION.IO
+
+THANK YOU
+
+
+
+
+
 **Describe the bug**
 A clear and concise description of what the bug is.
 

.github/test/Dockerfile-alpine

@@ -0,0 +1,31 @@
+# Taken from https://github.com/linuxserver/docker-changedetection.io/blob/main/Dockerfile
+# Test that we can still build on Alpine (musl modified libc https://musl.libc.org/)
+# Some packages wont install via pypi because they dont have a wheel available under this architecture.
+
+FROM ghcr.io/linuxserver/baseimage-alpine:3.16
+ENV PYTHONUNBUFFERED=1
+
+COPY requirements.txt /requirements.txt
+
+RUN \
+  apk add --update --no-cache --virtual=build-dependencies \
+    cargo \
+    g++ \
+    gcc \
+    libc-dev \
+    libffi-dev \
+    libxslt-dev \
+    make \
+    openssl-dev \
+    py3-wheel \
+    python3-dev \
+    zlib-dev && \
+  apk add --update --no-cache \
+    libxslt \
+    python3 \
+    py3-pip && \
+  echo "**** pip3 install test of changedetection.io ****" && \
+  pip3 install -U pip wheel setuptools && \
+  pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.16/ -r /requirements.txt && \
+  apk del --purge \
+    build-dependencies

.github/workflows/test-container-build.yml

@@ -0,0 +1,66 @@
+name: ChangeDetection.io Container Build Test
+
+# Triggers the workflow on push or pull request events
+
+# This line doesnt work, even tho it is the documented one
+#on: [push, pull_request]
+
+on:
+  push:
+    paths:
+      - requirements.txt
+      - Dockerfile
+
+  pull_request:
+    paths:
+      - requirements.txt
+      - Dockerfile
+
+  # Changes to requirements.txt packages and Dockerfile may or may not always be compatible with arm etc, so worth testing
+  # @todo: some kind of path filter for requirements.txt and Dockerfile
+jobs:
+  test-container-build:
+    runs-on: ubuntu-latest
+    steps:
+        - uses: actions/checkout@v2
+        - name: Set up Python 3.9
+          uses: actions/setup-python@v2
+          with:
+            python-version: 3.9
+
+        # Just test that the build works, some libraries won't compile on ARM/rPi etc
+        - name: Set up QEMU
+          uses: docker/setup-qemu-action@v1
+          with:
+            image: tonistiigi/binfmt:latest
+            platforms: all
+
+        - name: Set up Docker Buildx
+          id: buildx
+          uses: docker/setup-buildx-action@v1
+          with:
+            install: true
+            version: latest
+            driver-opts: image=moby/buildkit:master
+
+        # https://github.com/dgtlmoon/changedetection.io/pull/1067
+        # Check we can still build under alpine/musl
+        - name: Test that the docker containers can build (musl via alpine check)
+          id: docker_build_musl
+          uses: docker/build-push-action@v2
+          with:
+            context: ./
+            file: ./.github/test/Dockerfile-alpine
+            platforms: linux/amd64,linux/arm64
+
+        - name: Test that the docker containers can build
+          id: docker_build
+          uses: docker/build-push-action@v2
+          # https://github.com/docker/build-push-action#customizing
+          with:
+            context: ./
+            file: ./Dockerfile
+            platforms: linux/arm/v7,linux/arm/v6,linux/amd64,linux/arm64,
+            cache-from: type=local,src=/tmp/.buildx-cache
+            cache-to: type=local,dest=/tmp/.buildx-cache
+

.github/workflows/test-only.yml

@@ -1,28 +1,25 @@
-name: ChangeDetection.io Test
+name: ChangeDetection.io App Test
 
 # Triggers the workflow on push or pull request events
 on: [push, pull_request]
 
 jobs:
-  test-build:
+  test-application:
     runs-on: ubuntu-latest
     steps:
-
       - uses: actions/checkout@v2
       - name: Set up Python 3.9
         uses: actions/setup-python@v2
         with:
           python-version: 3.9
 
-      - name: Show env vars
-        run: set
-
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
           pip install flake8 pytest
           if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
           if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
+
       - name: Lint with flake8
         run: |
           # stop the build if there are Python syntax errors or undefined names
@@ -39,7 +36,4 @@ jobs:
           # Each test is totally isolated and performs its own cleanup/reset
           cd changedetectionio; ./run_all_tests.sh
 
-      # https://github.com/docker/build-push-action/blob/master/docs/advanced/test-before-push.md ?
-      # https://github.com/docker/buildx/issues/59 ? Needs to be one platform?
 
-      # https://github.com/docker/buildx/issues/495#issuecomment-918925854

CONTRIBUTING.md

@@ -6,7 +6,7 @@ Otherwise, it's always best to PR into the `dev` branch.
 
 Please be sure that all new functionality has a matching test!
 
-Use `pytest` to validate/test, you can run the existing tests as `pytest tests/test_notifications.py` for example
+Use `pytest` to validate/test, you can run the existing tests as `pytest tests/test_notification.py` for example
 
 ```
 pip3 install -r requirements-dev

Dockerfile

@@ -5,13 +5,14 @@ FROM python:3.8-slim as builder
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    libssl-dev \
+    g++ \
-    libffi-dev \
     gcc \
     libc-dev \
+    libffi-dev \
+    libssl-dev \
     libxslt-dev \
-    zlib1g-dev \
+    make \
-    g++
+    zlib1g-dev
 
 RUN mkdir /install
 WORKDIR /install
@@ -22,7 +23,8 @@ RUN pip install --target=/dependencies -r /requirements.txt
 
 # Playwright is an alternative to Selenium
 # Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
-RUN pip install --target=/dependencies playwright~=1.24 \
+# https://github.com/dgtlmoon/changedetection.io/pull/1067 also musl/alpine (not supported)
+RUN pip install --target=/dependencies playwright~=1.26 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
@@ -58,6 +60,7 @@ EXPOSE 5000
 
 # The actual flask app
 COPY changedetectionio /app/changedetectionio
+
 # The eventlet server wrapper
 COPY changedetection.py /app/changedetection.py
 

MANIFEST.in

@@ -2,6 +2,7 @@ recursive-include changedetectionio/api *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/static *
 recursive-include changedetectionio/model *
+recursive-include changedetectionio/tests *
 include changedetection.py
 global-exclude *.pyc
 global-exclude node_modules

README-pip.md

@@ -1,45 +1,48 @@
-#  changedetection.io
+## Web Site Change Detection, Monitoring and Notification.
-![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
-<a href="https://hub.docker.com/r/dgtlmoon/changedetection.io" target="_blank" title="Change detection docker hub">
-  <img src="https://img.shields.io/docker/pulls/dgtlmoon/changedetection.io" alt="Docker Pulls"/>
-</a>
-<a href="https://hub.docker.com/r/dgtlmoon/changedetection.io" target="_blank" title="Change detection docker hub">
-  <img src="https://img.shields.io/github/v/release/dgtlmoon/changedetection.io" alt="Change detection latest tag version"/> 
-</a>
 
-## Self-hosted open source change monitoring of web pages.
+Live your data-life pro-actively, track website content changes and receive notifications via Discord, Email, Slack, Telegram and 70+ more
 
-_Know when web pages change! Stay ontop of new information!_ 
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=pip)
-
-Live your data-life *pro-actively* instead of *re-actively*, do not rely on manipulative social media for consuming important information.
 
 
-<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"  />
+[**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://lemonade.changedetection.io/start) 
-
-
-**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 ...
+- Products and services have a change in pricing
-
+- _Out of stock notification_ and _Back In stock notification_
-- Government department updates (changes are often only on their websites)
+- Governmental department updates (changes are often only on their websites)
-- Local government news (changes are often only on their websites)
 - 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 
-- API monitoring and alerting
+- JSON API monitoring and alerting
+- Changes in legal and other documents
+- Trigger API calls via notifications when text appears on a website
+- Glue together APIs using the JSON filter and JSON notifications
+- Create RSS feeds based on changes in web content
+- Monitor HTML source code for unexpected changes, strengthen your PCI compliance
+- You have a very sensitive list of URLs to watch and you do _not_ want to use the paid alternatives. (Remember, _you_ are the product)
+
+_Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
+
+#### Key Features
+
+- Lots of trigger filters, such as "Trigger on text", "Remove text by selector", "Ignore text", "Extract text", also using regular-expressions!
+- Target elements with xPath and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
+- Switch between fast non-JS and Chrome JS based "fetchers"
+- Easily specify how often a site should be checked
+- Execute JS before extracting text (Good for logging in, see examples in the UI!)
+- Override Request Headers, Specify `POST` or `GET` and other methods
+- Use the "Visual Selector" to help target specific elements
 
-**Get monitoring now!**
 
 ```bash
-$ pip3 install changedetection.io   
+$ pip3 install changedetection.io
 ```
 
 Specify a target for the *datastore path* with `-d` (required) and a *listening port* with `-p` (defaults to `5000`)
@@ -51,17 +54,5 @@ $ changedetection.io -d /path/to/empty/data/dir -p 5000
 
 Then visit http://127.0.0.1:5000 , You should now be able to access the UI.
 
-### Features
-- Website monitoring
-- Change detection of content and analyses
-- Filters on change (Select by CSS or JSON)
-- Triggers (Wait for text, wait for regex)
-- Notification support
-- JSON API Monitoring
-- Parse JSON embedded in HTML
-- (Reverse) Proxy support
-- Javascript support via WebDriver
-- RaspberriPi (arm v6/v7/64 support)
-
 See https://github.com/dgtlmoon/changedetection.io for more information.
 

README.md

@@ -1,29 +1,24 @@
-#  changedetection.io
+## Web Site Change Detection, Monitoring and Notification.
+
+_Live your data-life pro-actively, Detect website changes and perform meaningful actions, trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._
+
+
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=github)
+
 [![Release Version][release-shield]][release-link] [![Docker Pulls][docker-pulls]][docker-link] [![License][license-shield]](LICENSE.md)
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
-## Web Site Change Detection, Monitoring and Notification - Self-Hosted or SaaS.
+[**Don't have time? Let us host it for you! try our $6.99/month subscription - use our proxies and support!**](https://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
 
-_Know when web pages change! Stay ontop of new information! get notifications when important website content changes_ 
+- Chrome browser included.
-
+- Super fast, no registration needed setup.
-Live your data-life *pro-actively* instead of *re-actively*.
+- Start watching and receiving change notifications instantly.
-
-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/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)
+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 " />
-**Get your own private instance now! Let us host it for you!**
-
-[**Try our $6.99/month subscription - unlimited checks and watches!**](https://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
-
-
-
-- Automatic Updates, Automatic Backups, No Heroku "paused application", don't miss a change!
-- Javascript browser included
-- Unlimited checks and watches!
 
 
 #### Example use cases
@@ -46,16 +41,23 @@ Free, Open-source web page monitoring, notification and change detection. Don't
 - Monitor HTML source code for unexpected changes, strengthen your PCI compliance
 - You have a very sensitive list of URLs to watch and you do _not_ want to use the paid alternatives. (Remember, _you_ are the product)
 
-_Need an actual Chrome runner with Javascript support? We support fetching via WebDriver!</a>_
+_Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
+
+#### Key Features
+
+- Lots of trigger filters, such as "Trigger on text", "Remove text by selector", "Ignore text", "Extract text", also using regular-expressions!
+- Target elements with xPath and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
+- Switch between fast non-JS and Chrome JS based "fetchers"
+- Easily specify how often a site should be checked
+- Execute JS before extracting text (Good for logging in, see examples in the UI!)
+- Override Request Headers, Specify `POST` or `GET` and other methods
+- Use the "Visual Selector" to help target specific elements
+- Configurable [proxy per watch](https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration)
+
+We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) global proxy services, Bright Data will match any first deposit up to $100 using our signup link.
 
 ## Screenshots
 
-### Examine differences in content.
-
-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.
@@ -118,8 +120,8 @@ 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.
 
+XPath, JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools. 
 (We support LXML `re:test`, `re:math` and `re:replace`.)
 
 ## Notifications
@@ -148,7 +150,7 @@ Now you can also customise your notification content!
 
 ## JSON API Monitoring
 
-Detect changes and monitor data in JSON API's by using the built-in JSONPath selectors as a filter / selector.
+Detect changes and monitor data in JSON API's by using either JSONPath or jq to filter, parse, and restructure JSON as needed.
 
 ![image](https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/json-filter-field-example.png)
 
@@ -156,9 +158,17 @@ This will re-parse the JSON and apply formatting to the text, making it super ea
 
 ![image](https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/json-diff-example.png)
 
+### JSONPath or jq?
+
+For more complex parsing, filtering, and modifying of JSON data, jq is recommended due to the built-in operators and functions. Refer to the [documentation](https://stedolan.github.io/jq/manual/) for more specifc information on jq.
+
+One big advantage of `jq` is that you can use logic in your JSON filter, such as filters to only show items that have a value greater than/less than etc.
+
+See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/JSON-Selector-Filter-help for more information and examples
+
 ### Parse JSON embedded in HTML!
 
-When you enable a `json:` filter, you can even automatically extract and parse embedded JSON inside a HTML page! Amazingly handy for sites that build content based on JSON, such as many e-commerce websites. 
+When you enable a `json:` or `jq:` filter, you can even automatically extract and parse embedded JSON inside a HTML page! Amazingly handy for sites that build content based on JSON, such as many e-commerce websites. 
 
 ```
 <html>
@@ -168,11 +178,11 @@ When you enable a `json:` filter, you can even automatically extract and parse e
 </script>
 ```  
 
-`json:$.price` would give `23.50`, or you can extract the whole structure
+`json:$.price` or `jq:.price` would give `23.50`, or you can extract the whole structure
 
-## Proxy configuration
+## Proxy Configuration
 
-See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration
+See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [BrightData proxy services where possible]( https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support)
 
 ## Raspberry Pi support?
 

changedetectionio/__init__.py

@@ -1,16 +1,5 @@
 #!/usr/bin/python3
 
-
-# @todo logging
-# @todo extra options for url like , verify=False etc.
-# @todo enable https://urllib3.readthedocs.io/en/latest/user-guide.html#ssl as option?
-# @todo option for interval day/6 hour/etc
-# @todo on change detected, config for calling some API
-# @todo fetch title into json
-# https://distill.io/features
-# proxy per check
-#  - flask_cors, itsdangerous,MarkupSafe
-
 import datetime
 import os
 import queue
@@ -44,7 +33,7 @@ from flask_wtf import CSRFProtect
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.39.17.2'
+__version__ = '0.39.21.1'
 
 datastore = None
 
@@ -205,7 +194,8 @@ def changedetection_app(config=None, datastore_o=None):
     watch_api.add_resource(api_v1.Watch, '/api/v1/watch/<string:uuid>',
                            resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
 
-
+    watch_api.add_resource(api_v1.SystemInfo, '/api/v1/systeminfo',
+                           resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
 
 
 
@@ -503,7 +493,7 @@ def changedetection_app(config=None, datastore_o=None):
         from changedetectionio import fetch_site_status
 
         # Get the most recent one
-        newest_history_key = datastore.get_val(uuid, 'newest_history_key')
+        newest_history_key = datastore.data['watching'][uuid].get('newest_history_key')
 
         # 0 means that theres only one, so that there should be no 'unviewed' history available
         if newest_history_key == 0:
@@ -552,16 +542,13 @@ def changedetection_app(config=None, datastore_o=None):
         # be sure we update with a copy instead of accidently editing the live object by reference
         default = deepcopy(datastore.data['watching'][uuid])
 
-        # Show system wide default if nothing configured
-        if datastore.data['watching'][uuid]['fetch_backend'] is None:
-            default['fetch_backend'] = datastore.data['settings']['application']['fetch_backend']
-
         # Show system wide default if nothing configured
         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'])
 
         # Defaults for proxy choice
         if datastore.proxy_list is not None:  # When enabled
+            # @todo
             # 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'] = ''
@@ -575,7 +562,9 @@ def changedetection_app(config=None, datastore_o=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
+            form.proxy.choices = [('', 'Default')]
+            for p in datastore.proxy_list:
+                form.proxy.choices.append(tuple((p, datastore.proxy_list[p]['label'])))
 
         if request.method == 'POST' and form.validate():
             extra_update_obj = {}
@@ -583,25 +572,13 @@ def changedetection_app(config=None, datastore_o=None):
             if request.args.get('unpause_on_save'):
                 extra_update_obj['paused'] = False
 
-            # Re #110, if they submit the same as the default value, set it to None, so we continue to follow the default
-            # Assume we use the default value, unless something relevant is different, then use the form value
-            # values could be None, 0 etc.
-            # Set to None unless the next for: says that something is different
-            extra_update_obj['time_between_check'] = dict.fromkeys(form.time_between_check.data)
-            for k, v in form.time_between_check.data.items():
-                if v and v != datastore.data['settings']['requests']['time_between_check'][k]:
-                    extra_update_obj['time_between_check'] = form.time_between_check.data
-                    using_default_check_time = False
-                    break
 
             # Use the default if its the same as system wide
             if form.fetch_backend.data == datastore.data['settings']['application']['fetch_backend']:
                 extra_update_obj['fetch_backend'] = None
 
-            # Notification URLs
-            datastore.data['watching'][uuid]['notification_urls'] = form.notification_urls.data
 
-            # Ignore text
+             # Ignore text
             form_ignore_text = form.ignore_text.data
             datastore.data['watching'][uuid]['ignore_text'] = form_ignore_text
 
@@ -611,7 +588,7 @@ def changedetection_app(config=None, datastore_o=None):
                     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 form.include_filters.data != datastore.data['watching'][uuid].get('include_filters', []):
                 if len(datastore.data['watching'][uuid].history):
                     extra_update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
 
@@ -649,18 +626,27 @@ def changedetection_app(config=None, datastore_o=None):
             # Only works reliably with Playwright
             visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and default['fetch_backend'] == 'html_webdriver'
 
+            # JQ is difficult to install on windows and must be manually added (outside requirements.txt)
+            jq_support = True
+            try:
+                import jq
+            except ModuleNotFoundError:
+                jq_support = False
 
             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),
+                                     form=form,
+                                     has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
+                                     has_empty_checktime=using_default_check_time,
+                                     jq_support=jq_support,
+                                     playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False),
+                                     settings_application=datastore.data['settings']['application'],
+                                     using_global_webdriver_wait=default['webdriver_delay'] is None,
+                                     uuid=uuid,
                                      visualselector_data_is_ready=visualselector_data_is_ready,
                                      visualselector_enabled=visualselector_enabled,
-                                     playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False)
+                                     watch=datastore.data['watching'][uuid],
                                      )
 
         return output
@@ -672,26 +658,34 @@ def changedetection_app(config=None, datastore_o=None):
 
         default = deepcopy(datastore.data['settings'])
         if datastore.proxy_list is not None:
+            available_proxies = list(datastore.proxy_list.keys())
             # 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]):
+            if not system_proxy in available_proxies:
                 system_proxy = None
 
-            default['requests']['proxy'] = system_proxy if system_proxy is not None else datastore.proxy_list[0][0]
+            default['requests']['proxy'] = system_proxy if system_proxy is not None else available_proxies[0]
             # Used by the form handler to keep or remove the proxy settings
-            default['proxy_list'] = datastore.proxy_list
+            default['proxy_list'] = available_proxies[0]
 
 
         # 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=default
                                         )
+
+        # Remove the last option 'System default'
+        form.application.form.notification_format.choices.pop()
+
         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
+            form.requests.form.proxy.choices = []
+            for p in datastore.proxy_list:
+                form.requests.form.proxy.choices.append(tuple((p, datastore.proxy_list[p]['label'])))
+
 
         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
@@ -727,12 +721,19 @@ def changedetection_app(config=None, datastore_o=None):
             else:
                 flash("An error occurred, please see below.", "error")
 
+        import datetime
+        datetime = datetime.datetime.now(pytz.timezone(datastore.data['settings']['application'].get('timezone')))
+
         output = render_template("settings.html",
-                                 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))
+                                 current_base_url=datastore.data['settings']['application']['base_url'],
+                                 datetime=str(datetime),
+                                 emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
+                                 form=form,
+                                 hide_remove_pass=os.getenv("SALTED_PASS", False),
+                                 settings_application=datastore.data['settings']['application'],
+                                 timezone=datastore.data['settings']['application'].get('timezone')
+                                 )
 
         return output
 
@@ -811,8 +812,10 @@ def changedetection_app(config=None, datastore_o=None):
 
         newest_file = history[dates[-1]]
 
+        # Read as binary and force decode as UTF-8
+        # Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
         try:
-            with open(newest_file, 'r') as f:
+            with open(newest_file, 'r', encoding='utf-8', errors='ignore') as f:
                 newest_version_file_contents = f.read()
         except Exception as e:
             newest_version_file_contents = "Unable to read {}.\n".format(newest_file)
@@ -825,7 +828,7 @@ def changedetection_app(config=None, datastore_o=None):
             previous_file = history[dates[-2]]
 
         try:
-            with open(previous_file, 'r') as f:
+            with open(previous_file, 'r', encoding='utf-8', errors='ignore') as f:
                 previous_version_file_contents = f.read()
         except Exception as e:
             previous_version_file_contents = "Unable to read {}.\n".format(previous_file)
@@ -902,7 +905,7 @@ def changedetection_app(config=None, datastore_o=None):
         timestamp = list(watch.history.keys())[-1]
         filename = watch.history[timestamp]
         try:
-            with open(filename, 'r') as f:
+            with open(filename, 'r', encoding='utf-8', errors='ignore') as f:
                 tmp = f.readlines()
 
                 # Get what needs to be highlighted
@@ -977,9 +980,6 @@ def changedetection_app(config=None, datastore_o=None):
 
         # create a ZipFile object
         backupname = "changedetection-backup-{}.zip".format(int(time.time()))
-
-        # We only care about UUIDS from the current index file
-        uuids = list(datastore.data['watching'].keys())
         backup_filepath = os.path.join(datastore_o.datastore_path, backupname)
 
         with zipfile.ZipFile(backup_filepath, "w",
@@ -995,12 +995,12 @@ def changedetection_app(config=None, datastore_o=None):
             # Add the flask app secret
             zipObj.write(os.path.join(datastore_o.datastore_path, "secret.txt"), arcname="secret.txt")
 
-            # Add any snapshot data we find, use the full path to access the file, but make the file 'relative' in the Zip.
+            # Add any data in the watch data directory.
-            for txt_file_path in Path(datastore_o.datastore_path).rglob('*.txt'):
+            for uuid, w in datastore.data['watching'].items():
-                parent_p = txt_file_path.parent
+                for f in Path(w.watch_data_dir).glob('*'):
-                if parent_p.name in uuids:
+                    zipObj.write(f,
-                    zipObj.write(txt_file_path,
+                                 # Use the full path to access the file, but make the file 'relative' in the Zip.
-                                 arcname=str(txt_file_path).replace(datastore_o.datastore_path, ''),
+                                 arcname=os.path.join(f.parts[-2], f.parts[-1]),
                                  compress_type=zipfile.ZIP_DEFLATED,
                                  compresslevel=8)
 
@@ -1186,6 +1186,63 @@ def changedetection_app(config=None, datastore_o=None):
         flash("{} watches are queued for rechecking.".format(i))
         return redirect(url_for('index', tag=tag))
 
+    @app.route("/form/checkbox-operations", methods=['POST'])
+    @login_required
+    def form_watch_list_checkbox_operations():
+        op = request.form['op']
+        uuids = request.form.getlist('uuids')
+
+        if (op == 'delete'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.delete(uuid.strip())
+            flash("{} watches deleted".format(len(uuids)))
+
+        elif (op == 'pause'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid.strip()]['paused'] = True
+
+            flash("{} watches paused".format(len(uuids)))
+
+        elif (op == 'unpause'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid.strip()]['paused'] = False
+            flash("{} watches unpaused".format(len(uuids)))
+
+        elif (op == 'mute'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid.strip()]['notification_muted'] = True
+            flash("{} watches muted".format(len(uuids)))
+
+        elif (op == 'unmute'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid.strip()]['notification_muted'] = False
+            flash("{} watches un-muted".format(len(uuids)))
+
+        elif (op == 'notification-default'):
+            from changedetectionio.notification import (
+                default_notification_format_for_watch
+            )
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid.strip()]['notification_title'] = None
+                    datastore.data['watching'][uuid.strip()]['notification_body'] = None
+                    datastore.data['watching'][uuid.strip()]['notification_urls'] = []
+                    datastore.data['watching'][uuid.strip()]['notification_format'] = default_notification_format_for_watch
+            flash("{} watches set to use default notification settings".format(len(uuids)))
+
+        return redirect(url_for('index'))
+
     @app.route("/api/share-url", methods=['GET'])
     @login_required
     def form_share_put_watch():
@@ -1245,8 +1302,8 @@ def changedetection_app(config=None, datastore_o=None):
 
     threading.Thread(target=notification_runner).start()
 
-    # Check for new release version, but not when running in test/build
+    # Check for new release version, but not when running in test/build or pytest
-    if not os.getenv("GITHUB_REF", False):
+    if not os.getenv("GITHUB_REF", False) and not config.get('disable_checkver') == True:
         threading.Thread(target=check_for_new_version).start()
 
     return app
@@ -1321,6 +1378,8 @@ def ticker_thread_check_time_launch_checks():
     import random
     from changedetectionio import update_worker
 
+    proxy_last_called_time = {}
+
     recheck_time_minimum_seconds = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 20))
     print("System env MINIMUM_SECONDS_RECHECK_TIME", recheck_time_minimum_seconds)
 
@@ -1381,17 +1440,46 @@ def ticker_thread_check_time_launch_checks():
                 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 watch.is_schedule_permitted:
+                    # Skip if the schedule (day of week and time) isnt permitted
+                    continue
+
                 if not uuid in running_uuids and uuid not in [q_uuid for p,q_uuid 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,
+                    # Proxies can be set to have a limit on seconds between which they can be called
-                                                                                                         watch['last_checked'],
+                    watch_proxy = datastore.get_preferred_proxy_for_watch(uuid=uuid)
-                                                                                                         now,
+                    if watch_proxy and watch_proxy in list(datastore.proxy_list.keys()):
-                                                                                                         watch.jitter_seconds,
+                        # Proxy may also have some threshold minimum
-                                                                                                         now - watch['last_checked']))
+                        proxy_list_reuse_time_minimum = int(datastore.proxy_list.get(watch_proxy, {}).get('reuse_time_minimum', 0))
+                        if proxy_list_reuse_time_minimum:
+                            proxy_last_used_time = proxy_last_called_time.get(watch_proxy, 0)
+                            time_since_proxy_used = int(time.time() - proxy_last_used_time)
+                            if time_since_proxy_used < proxy_list_reuse_time_minimum:
+                                # Not enough time difference reached, skip this watch
+                                print("> Skipped UUID {} using proxy '{}', not enough time between proxy requests {}s/{}s".format(uuid,
+                                                                                                                         watch_proxy,
+                                                                                                                         time_since_proxy_used,
+                                                                                                                         proxy_list_reuse_time_minimum))
+                                continue
+                            else:
+                                # Record the last used time
+                                proxy_last_called_time[watch_proxy] = int(time.time())
+
+                    # Use Epoch time as priority, so we get a "sorted" PriorityQueue, but we can still push a priority 1 into it.
+                    priority = int(time.time())
+                    print(
+                        "> Queued watch UUID {} last checked at {} queued at {:0.2f} priority {} jitter {:0.2f}s, {:0.2f}s since last checked".format(
+                            uuid,
+                            watch['last_checked'],
+                            now,
+                            priority,
+                            watch.jitter_seconds,
+                            now - watch['last_checked']))
                     # Into the queue with you
-                    update_q.put((5, uuid))
+                    update_q.put((priority, uuid))
 
                     # Reset for next time
                     watch.jitter_seconds = 0

changedetectionio/api/api_v1.py

@@ -122,3 +122,37 @@ class CreateWatch(Resource):
             return {'status': "OK"}, 200
 
         return list, 200
+
+class SystemInfo(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 get(self):
+        import time
+        overdue_watches = []
+
+        # Check all watches and report which have not been checked but should have been
+
+        for uuid, watch in self.datastore.data.get('watching', {}).items():
+            # see if now - last_checked is greater than the time that should have been
+            # this is not super accurate (maybe they just edited it) but better than nothing
+            t = watch.threshold_seconds()
+            if not t:
+                # Use the system wide default
+                t = self.datastore.threshold_seconds
+
+            time_since_check = time.time() - watch.get('last_checked')
+
+            # Allow 5 minutes of grace time before we decide it's overdue
+            if time_since_check - (5 * 60) > t:
+                overdue_watches.append(uuid)
+
+        return {
+                   'queue_size': self.update_q.qsize(),
+                   'overdue_watches': overdue_watches,
+                   'uptime': round(time.time() - self.datastore.start_time, 2),
+                   'watch_count': len(self.datastore.data.get('watching', {}))
+               }, 200

changedetectionio/changedetection.py

@@ -102,6 +102,14 @@ def main():
                     has_password=datastore.data['settings']['application']['password'] != False
                     )
 
+    # Monitored websites will not receive a Referer header when a user clicks on an outgoing link.
+    # @Note: Incompatible with password login (and maybe other features) for now, submit a PR!
+    @app.after_request
+    def hide_referrer(response):
+        if os.getenv("HIDE_REFERER", False):
+            response.headers["Referrer-Policy"] = "no-referrer"
+        return response
+
     # Proxy sub-directory support
     # Set environment var USE_X_SETTINGS=1 on this script
     # And then in your proxy_pass settings

changedetectionio/content_fetcher.py

@@ -31,11 +31,12 @@ class JSActionExceptions(Exception):
         return
 
 class PageUnloadable(Exception):
-    def __init__(self, status_code, url, screenshot=False):
+    def __init__(self, status_code, url, screenshot=False, message=False):
         # Set this so we can use it in other parts of the app
         self.status_code = status_code
         self.url = url
         self.screenshot = screenshot
+        self.message = message
         return
 
 class EmptyReply(Exception):
@@ -163,16 +164,16 @@ class Fetcher():
                 }
 
 
-                // inject the current one set in the css_filter, which may be a CSS rule
+                // inject the current one set in the include_filters, which may be a CSS rule
                 // used for displaying the current one in VisualSelector, where its not one we generated.
-                if (css_filter.length) {
+                if (include_filters.length) {
                    q=false;                   
                    try {
                        // is it xpath?
-                       if (css_filter.startsWith('/') || css_filter.startsWith('xpath:')) {
+                       if (include_filters.startsWith('/') || include_filters.startsWith('xpath:')) {
-                         q=document.evaluate(css_filter.replace('xpath:',''), document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
+                         q=document.evaluate(include_filters.replace('xpath:',''), document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
                        } else {
-                         q=document.querySelector(css_filter);
+                         q=document.querySelector(include_filters);
                        }                       
                    } catch (e) {
                     // Maybe catch DOMException and alert? 
@@ -185,7 +186,7 @@ class Fetcher():
                                    
                    if (bbox && bbox['width'] >0 && bbox['height']>0) {                       
                        size_pos.push({
-                           xpath: css_filter,
+                           xpath: include_filters,
                            width: bbox['width'], 
                            height: bbox['height'],
                            left: bbox['left'],
@@ -219,7 +220,7 @@ class Fetcher():
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_css_filter=None):
+            current_include_filters=None):
         # Should set self.error, self.status_code and self.content
         pass
 
@@ -292,7 +293,15 @@ class base_html_playwright(Fetcher):
 
         # allow per-watch proxy selection override
         if proxy_override:
-            self.proxy = {'server': proxy_override}
+            # https://playwright.dev/docs/network#http-proxy
+            from urllib.parse import urlparse
+            parsed = urlparse(proxy_override)
+            proxy_url = "{}://{}:{}".format(parsed.scheme, parsed.hostname, parsed.port)
+            self.proxy = {'server': proxy_url}
+            if parsed.username:
+                self.proxy['username'] = parsed.username
+            if parsed.password:
+                self.proxy['password'] = parsed.password
 
     def run(self,
             url,
@@ -301,12 +310,13 @@ class base_html_playwright(Fetcher):
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_css_filter=None):
+            current_include_filters=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)
 
@@ -356,7 +366,7 @@ class base_html_playwright(Fetcher):
                 print(str(e))
                 context.close()
                 browser.close()
-                raise PageUnloadable(url=url, status_code=None)
+                raise PageUnloadable(url=url, status_code=None, message=e.message)
 
             if response is None:
                 context.close()
@@ -364,8 +374,11 @@ class base_html_playwright(Fetcher):
                 print("response object was none")
                 raise EmptyReply(url=url, status_code=None)
 
-            # Bug 2(?) Set the viewport size AFTER loading the page
+
-            page.set_viewport_size({"width": 1280, "height": 1024})
+            # Removed browser-set-size, seemed to be needed to make screenshots work reliably in older playwright versions
+            # Was causing exceptions like 'waiting for page but content is changing' etc
+            # https://www.browserstack.com/docs/automate/playwright/change-browser-window-size 1280x720 should be the default
+                        
             extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
             time.sleep(extra_wait)
 
@@ -389,14 +402,21 @@ class base_html_playwright(Fetcher):
 
                     raise JSActionExceptions(status_code=response.status, screenshot=error_screenshot, message=str(e), url=url)
 
+                else:
+                    # JS eval was run, now we also wait some time if possible to let the page settle
+                    if self.render_extract_delay:
+                        page.wait_for_timeout(self.render_extract_delay * 1000)
+
+            page.wait_for_timeout(500)
+
             self.content = page.content()
             self.status_code = response.status
             self.headers = response.all_headers()
 
-            if current_css_filter is not None:
+            if current_include_filters is not None:
-                page.evaluate("var css_filter={}".format(json.dumps(current_css_filter)))
+                page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
             else:
-                page.evaluate("var css_filter=''")
+                page.evaluate("var include_filters=''")
 
             self.xpath_data = page.evaluate("async () => {" + self.xpath_element_js + "}")
 
@@ -477,7 +497,7 @@ class base_html_webdriver(Fetcher):
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_css_filter=None):
+            current_include_filters=None):
 
         from selenium import webdriver
         from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
@@ -505,8 +525,6 @@ class base_html_webdriver(Fetcher):
             # 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
@@ -517,6 +535,8 @@ class base_html_webdriver(Fetcher):
         self.content = self.driver.page_source
         self.headers = {}
 
+        self.screenshot = self.driver.get_screenshot_as_png()
+
     # Does the connection to the webdriver work? run a test connection.
     def is_ready(self):
         from selenium import webdriver
@@ -553,7 +573,12 @@ class html_requests(Fetcher):
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_css_filter=None):
+            current_include_filters=None):
+
+        # Make requests use a more modern looking user-agent
+        if not 'User-Agent' in request_headers:
+            request_headers['User-Agent'] = os.getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT",
+                                                      'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36')
 
         proxies = {}
 

changedetectionio/fetch_site_status.py

@@ -10,42 +10,22 @@ from changedetectionio import content_fetcher, html_tools
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 
+class FilterNotFoundInResponse(ValueError):
+    def __init__(self, msg):
+        ValueError.__init__(self, msg)
+
+
+
 # Some common stuff here that can be moved to a base class
 # (set_proxy_from_list)
 class perform_site_check():
+    screenshot = None
+    xpath_data = None
 
     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):
@@ -61,13 +41,13 @@ class perform_site_check():
 
 
     def run(self, uuid):
-        timestamp = int(time.time())  # used for storage etc too
-
         changed_detected = False
         screenshot = False  # as bytes
         stripped_text_from_html = ""
 
-        watch = self.datastore.data['watching'][uuid]
+        watch = self.datastore.data['watching'].get(uuid)
+        if not watch:
+            return
 
         # Protect against file:// access
         if re.search(r'^file', watch['url'], re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
@@ -78,7 +58,7 @@ class perform_site_check():
         # Unset any existing notification error
         update_obj = {'last_notification_error': False, 'last_error': False}
 
-        extra_headers = self.datastore.get_val(uuid, 'headers')
+        extra_headers =self.datastore.data['watching'][uuid].get('headers')
 
         # Tweak the base config with the per-watch ones
         request_headers = self.datastore.data['settings']['headers'].copy()
@@ -90,10 +70,12 @@ class perform_site_check():
         if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
             request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
 
-        timeout = self.datastore.data['settings']['requests']['timeout']
+        timeout = self.datastore.data['settings']['requests'].get('timeout')
-        url = self.datastore.get_val(uuid, 'url')
+
-        request_body = self.datastore.get_val(uuid, 'body')
+        url = watch.link
-        request_method = self.datastore.get_val(uuid, 'method')
+
+        request_body = self.datastore.data['watching'][uuid].get('body')
+        request_method = self.datastore.data['watching'][uuid].get('method')
         ignore_status_codes = self.datastore.data['watching'][uuid].get('ignore_status_codes', False)
 
         # source: support
@@ -110,9 +92,13 @@ class perform_site_check():
             # If the klass doesnt exist, just use a default
             klass = getattr(content_fetcher, "html_requests")
 
+        proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=uuid)
+        proxy_url = None
+        if proxy_id:
+            proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
+            print ("UUID {} Using proxy {}".format(uuid, proxy_url))
 
-        proxy_args = self.set_proxy_from_list(watch)
+        fetcher = klass(proxy_override=proxy_url)
-        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)
@@ -124,9 +110,12 @@ class perform_site_check():
         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_codes, watch['css_filter'])
+        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch['include_filters'])
         fetcher.quit()
 
+        self.screenshot = fetcher.screenshot
+        self.xpath_data = fetcher.xpath_data
+
         # Fetching complete, now filters
         # @todo move to class / maybe inside of fetcher abstract base?
 
@@ -145,24 +134,26 @@ class perform_site_check():
             is_html = False
             is_json = False
 
-        css_filter_rule = watch['css_filter']
+        include_filters_rule = watch['include_filters']
         subtractive_selectors = watch.get(
             "subtractive_selectors", []
         ) + self.datastore.data["settings"]["application"].get(
             "global_subtractive_selectors", []
         )
 
-        has_filter_rule = css_filter_rule and len(css_filter_rule.strip())
+        has_filter_rule = include_filters_rule and len("".join(include_filters_rule).strip())
         has_subtractive_selectors = subtractive_selectors and len(subtractive_selectors[0].strip())
 
         if is_json and not has_filter_rule:
-            css_filter_rule = "json:$"
+            include_filters_rule.append("json:$")
             has_filter_rule = True
 
         if has_filter_rule:
-            if 'json:' in css_filter_rule:
+            json_filter_prefixes = ['json:', 'jq:']
-                stripped_text_from_html = html_tools.extract_json_as_string(content=fetcher.content, jsonpath_filter=css_filter_rule)
+            for filter in include_filters_rule:
-                is_html = False
+                if any(prefix in filter for prefix in json_filter_prefixes):
+                    stripped_text_from_html += html_tools.extract_json_as_string(content=fetcher.content, json_filter=filter)
+                    is_html = False
 
         if is_html or is_source:
             
@@ -177,18 +168,28 @@ class perform_site_check():
             else:
                 # Then we assume HTML
                 if has_filter_rule:
-                    # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
+                    html_content = ""
-                    if css_filter_rule[0] == '/' or css_filter_rule.startswith('xpath:'):
+                    for filter_rule in include_filters_rule:
-                        html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule.replace('xpath:', ''),
+                        # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
-                                                               html_content=fetcher.content)
+                        if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
-                    else:
+                            html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
-                        # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
+                                                                    html_content=fetcher.content,
-                        html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content)
+                                                                    append_pretty_line_formatting=not is_source)
+                        else:
+                            # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
+                            html_content += html_tools.include_filters(include_filters=filter_rule,
+                                                                  html_content=fetcher.content,
+                                                                  append_pretty_line_formatting=not is_source)
+
+                    if not html_content.strip():
+                        raise FilterNotFoundInResponse(include_filters_rule)
 
                 if has_subtractive_selectors:
                     html_content = html_tools.element_removal(subtractive_selectors, html_content)
 
-                if not is_source:
+                if is_source:
+                    stripped_text_from_html = html_content
+                else:
                     # extract text
                     stripped_text_from_html = \
                         html_tools.html_to_text(
@@ -198,12 +199,6 @@ class perform_site_check():
                                 "render_anchor_tag_content", False)
                         )
 
-                elif is_source:
-                    stripped_text_from_html = html_content
-
-            # 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')
 
@@ -312,4 +307,4 @@ class perform_site_check():
         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
+        return changed_detected, update_obj, text_content_before_ignored_filter

changedetectionio/forms.py

@@ -1,5 +1,5 @@
 import re
-
+import pytz
 from wtforms import (
     BooleanField,
     Field,
@@ -8,9 +8,11 @@ from wtforms import (
     PasswordField,
     RadioField,
     SelectField,
+    SelectMultipleField,
     StringField,
     SubmitField,
     TextAreaField,
+    TimeField,
     fields,
     validators,
     widgets,
@@ -97,6 +99,44 @@ class TimeBetweenCheckForm(Form):
     seconds = IntegerField('Seconds', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
     # @todo add total seconds minimum validatior = minimum_seconds_recheck_time
 
+class MultiCheckboxDayOfWeekField(SelectMultipleField):
+    widget = widgets.ListWidget(prefix_label=False)
+    option_widget = widgets.CheckboxInput()
+
+class TimeScheduleCheckLimitForm(Form):
+    # @todo must be a better python way todo this c/i list
+    c=[]
+    i=0
+    for d in ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']:
+        c.append((i, d))
+        i+=1
+    day_of_week = MultiCheckboxDayOfWeekField('',coerce=int, choices=c)
+    from_time = TimeField('From', validators=[validators.Optional()])
+    until_time = TimeField('Until', validators=[validators.Optional()])
+
+    def validate(self, **kwargs):
+        if not super().validate():
+            return False
+
+        result = True
+
+        f = self.data.get('from_time')
+        u = self.data.get('until_time')
+        if f and u:
+            import time
+            f = time.strptime(str(f), '%H:%M:%S')
+            u = time.strptime(str(u), '%H:%M:%S')
+            if f >= u:
+                #@todo doesnt present
+                self.from_time.errors.append('From time must be LESS than the until/end time')
+                result = False
+
+        if len(self.data.get('day_of_week', [])) == 0:
+            self.day_of_week.errors.append('No day selected')
+            result = False
+
+        return result
+
 # Separated by  key:value
 class StringDictKeyValue(StringField):
     widget = widgets.TextArea()
@@ -303,6 +343,25 @@ class ValidateCSSJSONXPATHInput(object):
 
                 # Re #265 - maybe in the future fetch the page and offer a
                 # warning/notice that its possible the rule doesnt yet match anything?
+                if not self.allow_json:
+                    raise ValidationError("jq not permitted in this field!")
+
+            if 'jq:' in line:
+                try:
+                    import jq
+                except ModuleNotFoundError:
+                    # `jq` requires full compilation in windows and so isn't generally available
+                    raise ValidationError("jq not support not found")
+
+                input = line.replace('jq:', '')
+
+                try:
+                    jq.compile(input)
+                except (ValueError) as e:
+                    message = field.gettext('\'%s\' is not a valid jq expression. (%s)')
+                    raise ValidationError(message % (input, str(e)))
+                except:
+                    raise ValidationError("A system-error occurred when validating your jq expression")
 
 
 class quickWatchForm(Form):
@@ -314,47 +373,44 @@ class quickWatchForm(Form):
 
 # Common to a single watch and the global settings
 class commonSettingsForm(Form):
-
+    notification_urls = StringListField('Notification URL list', validators=[validators.Optional(), ValidateAppRiseServers()])
-    notification_urls = StringListField('Notification URL list', validators=[validators.Optional(), ValidateNotificationBodyAndTitleWhenURLisSet(), ValidateAppRiseServers()])
+    notification_title = StringField('Notification title', validators=[validators.Optional(), ValidateTokensList()])
-    notification_title = StringField('Notification title', default=default_notification_title, validators=[validators.Optional(), ValidateTokensList()])
+    notification_body = TextAreaField('Notification body', validators=[validators.Optional(), ValidateTokensList()])
-    notification_body = TextAreaField('Notification body', default=default_notification_body, validators=[validators.Optional(), ValidateTokensList()])
+    notification_format = SelectField('Notification format', choices=valid_notification_formats.keys())
-    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")] )
+    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()], 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()])
-    headers = StringDictKeyValue('Request headers')
     body = TextAreaField('Request body', [validators.Optional()])
-    method = SelectField('Request method', choices=valid_method, default=default_method)
-    ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
     check_unique_lines = BooleanField('Only trigger when new lines appear', default=False)
-    trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
+    extract_text = StringListField('Extract text', [ValidateListRegex()])
+    headers = StringDictKeyValue('Request headers')
+    ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
+    ignore_text = StringListField('Ignore text', [ValidateListRegex()])
+    include_filters = StringListField('CSS/JSONPath/JQ/XPath Filters', [ValidateCSSJSONXPATHInput()], default='')
+    method = SelectField('Request method', choices=valid_method, default=default_method)
+    subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
     text_should_not_be_present = StringListField('Block change-detection if text matches', [validators.Optional(), ValidateListRegex()])
-
+    time_between_check = FormField(TimeBetweenCheckForm)
+    time_schedule_check_limit = FormField(TimeScheduleCheckLimitForm)
+    time_use_system_default = BooleanField('Use system/default check time', default=False, validators=[validators.Optional()])
+    title = StringField('Title', default='')
+    trigger_text = StringListField('Trigger/wait for text', [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"})
 
     proxy = RadioField('Proxy')
     filter_failure_notification_send = BooleanField(
         'Send a notification when the filter can no longer be found on the page', default=False)
 
+    notification_muted = BooleanField('Notifications Muted / Off', default=False)
+
     def validate(self, **kwargs):
         if not super().validate():
             return False
@@ -368,10 +424,10 @@ class watchForm(commonSettingsForm):
 
         return result
 
-
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
     time_between_check = FormField(TimeBetweenCheckForm)
+    time_schedule_check_limit = FormField(TimeScheduleCheckLimitForm)
     proxy = RadioField('Proxy')
     jitter_seconds = IntegerField('Random jitter seconds ± check',
                                   render_kw={"style": "width: 5em;"},
@@ -380,22 +436,21 @@ class globalSettingsRequestForm(Form):
 # datastore.data['settings']['application']..
 class globalSettingsApplicationForm(commonSettingsForm):
 
-    base_url = StringField('Base URL', validators=[validators.Optional()])
-    global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
-    global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
-    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()
+    base_url = StringField('Base URL', validators=[validators.Optional()])
-
+    empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
+    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     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")])
+    global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
+    global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
+    ignore_whitespace = BooleanField('Ignore whitespace')
+    password = SaltyPasswordField()
+    removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
+    render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
+    timezone = SelectField('Timezone', choices=pytz.all_timezones)
 
 
 class globalSettingsForm(Form):

changedetectionio/html_tools.py

@@ -1,32 +1,36 @@
-import json
-from typing import List
 
 from bs4 import BeautifulSoup
-from jsonpath_ng.ext import parse
-import re
 from inscriptis import get_text
 from inscriptis.model.config import ParserConfig
+from jsonpath_ng.ext import parse
+from typing import List
+import json
+import re
 
-class FilterNotFoundInResponse(ValueError):
+# HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
-    def __init__(self, msg):
+TEXT_FILTER_LIST_LINE_SUFFIX = "<br/>"
-        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):
+def include_filters(include_filters, html_content, append_pretty_line_formatting=False):
     soup = BeautifulSoup(html_content, "html.parser")
     html_block = ""
-    r = soup.select(css_filter, separator="")
+    r = soup.select(include_filters, 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"
+    for element in r:
+        # When there's more than 1 match, then add the suffix to separate each line
+        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
+        # (This way each 'match' reliably has a new-line in the diff)
+        # Divs are converted to 4 whitespaces by inscriptis
+        if append_pretty_line_formatting and len(html_block) and not element.name in (['br', 'hr', 'div', 'p']):
+            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
+
+        html_block += str(element)
+
+    return html_block
 
 def subtractive_css_selector(css_selector, html_content):
     soup = BeautifulSoup(html_content, "html.parser")
@@ -42,25 +46,29 @@ def element_removal(selectors: List[str], html_content):
 
 
 # Return str Utf-8 of matched rules
-def xpath_filter(xpath_filter, html_content):
+def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False):
     from lxml import etree, html
 
     tree = html.fromstring(bytes(html_content, encoding='utf-8'))
     html_block = ""
 
     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)
-
     #@note: //title/text() wont work where <title>CDATA..
 
     for element in r:
+        # When there's more than 1 match, then add the suffix to separate each line
+        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
+        # (This way each 'match' reliably has a new-line in the diff)
+        # Divs are converted to 4 whitespaces by inscriptis
+        if append_pretty_line_formatting and len(html_block) and (not hasattr( element, 'tag' ) or not element.tag in (['br', 'hr', 'div', 'p'])):
+            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
+
         if type(element) == etree._ElementStringResult:
-            html_block += str(element) + "<br/>"
+            html_block += str(element)
         elif type(element) == etree._ElementUnicodeResult:
-            html_block += str(element) + "<br/>"
+            html_block += str(element)
         else:
-            html_block += etree.tostring(element, pretty_print=True).decode('utf-8') + "<br/>"
+            html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
 
     return html_block
 
@@ -79,19 +87,35 @@ def extract_element(find='title', html_content=''):
     return element_text
 
 #
-def _parse_json(json_data, jsonpath_filter):
+def _parse_json(json_data, json_filter):
-    s=[]
+    if 'json:' in json_filter:
-    jsonpath_expression = parse(jsonpath_filter.replace('json:', ''))
+        jsonpath_expression = parse(json_filter.replace('json:', ''))
-    match = jsonpath_expression.find(json_data)
+        match = jsonpath_expression.find(json_data)
+        return _get_stripped_text_from_json_match(match)
 
+    if 'jq:' in json_filter:
+
+        try:
+            import jq
+        except ModuleNotFoundError:
+            # `jq` requires full compilation in windows and so isn't generally available
+            raise Exception("jq not support not found")
+
+        jq_expression = jq.compile(json_filter.replace('jq:', ''))
+        match = jq_expression.input(json_data).all()
+
+        return _get_stripped_text_from_json_match(match)
+
+def _get_stripped_text_from_json_match(match):
+    s = []
     # More than one result, we will return it as a JSON list.
     if len(match) > 1:
         for i in match:
-            s.append(i.value)
+            s.append(i.value if hasattr(i, 'value') else i)
 
     # Single value, use just the value, as it could be later used in a token in notifications.
     if len(match) == 1:
-        s = match[0].value
+        s = match[0].value if hasattr(match[0], 'value') else match[0]
 
     # Re #257 - Better handling where it does not exist, in the case the original 's' value was False..
     if not match:
@@ -103,16 +127,16 @@ def _parse_json(json_data, jsonpath_filter):
 
     return stripped_text_from_html
 
-def extract_json_as_string(content, jsonpath_filter):
+def extract_json_as_string(content, json_filter):
 
     stripped_text_from_html = False
 
     # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded <script type=ldjson>
     try:
-        stripped_text_from_html = _parse_json(json.loads(content), jsonpath_filter)
+        stripped_text_from_html = _parse_json(json.loads(content), json_filter)
     except json.JSONDecodeError:
 
-        # Foreach <script json></script> blob.. just return the first that matches jsonpath_filter
+        # Foreach <script json></script> blob.. just return the first that matches json_filter
         s = []
         soup = BeautifulSoup(content, 'html.parser')
         bs_result = soup.findAll('script')
@@ -131,7 +155,7 @@ def extract_json_as_string(content, jsonpath_filter):
                 # Just skip it
                 continue
             else:
-                stripped_text_from_html = _parse_json(json_data, jsonpath_filter)
+                stripped_text_from_html = _parse_json(json_data, json_filter)
                 if stripped_text_from_html:
                     break
 

changedetectionio/importer.py

@@ -103,12 +103,12 @@ class import_distill_io_json(Importer):
                     pass
                 except IndexError:
                     pass
-
+                extras['include_filters'] = []
                 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']
+                        extras['include_filters'].append('xpath:' + d_config['selections'][0]['frames'][0]['includes'][0]['expr'])
-
+                    else:
+                        extras['include_filters'].append(d_config['selections'][0]['frames'][0]['includes'][0]['expr'])
                 except KeyError:
                     pass
                 except IndexError:

changedetectionio/model/App.py

@@ -13,38 +13,35 @@ class model(dict):
             'watching': {},
             'settings': {
                 'headers': {
-                    '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': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
                     'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
+                    'time_schedule_check_limit': {'day_of_week': [0, 1, 2, 3, 4, 5, 6], 'time_from': '', 'time_until': ''},
                     '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': {
+                    # Custom notification content
                     'api_access_token_enabled': True,
-                    'password': False,
                     'base_url' : None,
-                    'extract_title_as_title': False,
                     'empty_pages_are_a_change': False,
+                    'extract_title_as_title': False,
                     'fetch_backend': getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
                     'filter_failure_notification_threshold_attempts': _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT,
                     'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
                     'global_subtractive_selectors': [],
                     'ignore_whitespace': True,
-                    'render_anchor_tag_content': False,
-                    'notification_urls': [], # Apprise URL list
-                    # Custom notification content
-                    'notification_title': default_notification_title,
                     'notification_body': default_notification_body,
                     'notification_format': default_notification_format,
-                    'real_browser_save_screenshot': True,
+                    'notification_title': default_notification_title,
+                    'notification_urls': [], # Apprise URL list
+                    'password': False,
+                    'render_anchor_tag_content': False,
                     'schema_version' : 0,
-                    'webdriver_delay': None  # Extra delay in seconds before extracting text
+                    'timezone': 'UTC',
+                    'webdriver_delay': None,  # Extra delay in seconds before extracting text
                 }
             }
         }

changedetectionio/model/Watch.py

@@ -1,14 +1,14 @@
-import os
-import uuid as uuid_builder
 from distutils.util import strtobool
+import logging
+import os
+import time
+import uuid
 
 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,
+    default_notification_format_for_watch
-    default_notification_format,
-    default_notification_title,
 )
 
 
@@ -16,42 +16,44 @@ class model(dict):
     __newest_history_key = None
     __history_n=0
     __base_config = {
-            'url': None,
+            #'history': {},  # Dict of timestamp and output stripped filename (removed)
-            'tag': None,
+            #'newest_history_key': 0, (removed, taken from history.txt index)
-            'last_checked': 0,
-            'paused': False,
-            'last_viewed': 0,  # history key value of the last viewed via the [diff] link
-            #'newest_history_key': 0,
-            'title': None,
-            'previous_md5': False,
-            'uuid': str(uuid_builder.uuid4()),
-            'headers': {},  # Extra headers to send
             'body': None,
-            'method': 'GET',
+            'check_unique_lines': False, # On change-detected, compare against all history if its something new
-            #'history': {},  # Dict of timestamp and output stripped filename
+            'check_count': 0,
-            'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+            'consecutive_filter_failures': 0, # Every time the CSS/xPath filter cannot be located, reset when all is fine.
-            # 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,
-            'notification_muted': False,
-            'css_filter': '',
-            'last_error': False,
             'extract_text': [],  # Extract text by regex after filters
-            'subtractive_selectors': [],
+            'extract_title_as_title': False,
-            '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': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
-            'consecutive_filter_failures': 0, # Every time the CSS/xPath filter cannot be located, reset when all is fine.
+            'headers': {},  # Extra headers to send
-            'extract_title_as_title': False,
+            'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
-            'check_unique_lines': False, # On change-detected, compare against all history if its something new
+            'include_filters': [],
+            'last_checked': 0,
+            'last_error': False,
+            'last_viewed': 0,  # history key value of the last viewed via the [diff] link
+            'method': 'GET',
+             # Custom notification content
+            'notification_body': None,
+            'notification_format': default_notification_format_for_watch,
+            'notification_muted': False,
+            'notification_title': None,
+            'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
+            'paused': False,
+            'previous_md5': False,
             'proxy': None, # Preferred proxy connection
+            'subtractive_selectors': [],
+            'tag': None,
+            'text_should_not_be_present': [], # Text that should not present
             # 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_schedule_check_limit': {'day_of_week': [0, 1, 2, 3, 4, 5, 6], 'time_from': '', 'time_until': ''},
+            'title': None,
+            'trigger_text': [],  # List of text or regex to wait for until a change is detected
+            'url': None,
+            'uuid': str(uuid.uuid4()),
             'webdriver_delay': None,
             'webdriver_js_execute_code': None, # Run before change-detection
         }
@@ -62,7 +64,7 @@ class model(dict):
         self.update(self.__base_config)
         self.__datastore_path = kw['datastore_path']
 
-        self['uuid'] = str(uuid_builder.uuid4())
+        self['uuid'] = str(uuid.uuid4())
 
         del kw['datastore_path']
 
@@ -83,6 +85,21 @@ class model(dict):
 
         return False
 
+    def ensure_data_dir_exists(self):
+        if not os.path.isdir(self.watch_data_dir):
+            print ("> Creating data dir {}".format(self.watch_data_dir))
+            os.mkdir(self.watch_data_dir)
+
+    @property
+    def link(self):
+        url = self.get('url', '')
+        if '{%' in url or '{{' in url:
+            from jinja2 import Environment
+            # Jinja2 available in URLs along with https://pypi.org/project/jinja2-time/
+            jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
+            return str(jinja2_env.from_string(url).render())
+        return url
+
     @property
     def label(self):
         # Used for sorting
@@ -105,16 +122,40 @@ class model(dict):
 
     @property
     def history(self):
+        """History index is just a text file as a list
+            {watch-uuid}/history.txt
+
+            contains a list like
+
+            {epoch-time},{filename}\n
+
+            We read in this list as the history information
+
+        """
         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")
+        fname = os.path.join(self.watch_data_dir, "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())
+                for i in f.readlines():
+                    if ',' in i:
+                        k, v = i.strip().split(',', 2)
+
+                        # The index history could contain a relative path, so we need to make the fullpath
+                        # so that python can read it
+                        if not '/' in v and not '\'' in v:
+                            v = os.path.join(self.watch_data_dir, v)
+                        else:
+                            # It's possible that they moved the datadir on older versions
+                            # So the snapshot exists but is in a different path
+                            snapshot_fname = v.split('/')[-1]
+                            proposed_new_path = os.path.join(self.watch_data_dir, snapshot_fname)
+                            if not os.path.exists(v) and os.path.exists(proposed_new_path):
+                                v = proposed_new_path
+
+                        tmp_history[k] = v
 
         if len(tmp_history):
             self.__newest_history_key = list(tmp_history.keys())[-1]
@@ -125,7 +166,7 @@ class model(dict):
 
     @property
     def has_history(self):
-        fname = os.path.join(self.__datastore_path, self.get('uuid'), "history.txt")
+        fname = os.path.join(self.watch_data_dir, "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.
@@ -144,33 +185,33 @@ class model(dict):
     # 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
-        import logging
 
-        output_path = "{}/{}".format(self.__datastore_path, self['uuid'])
+        self.ensure_data_dir_exists()
 
-        # Incase the operator deleted it, check and create.
+        # Small hack so that we sleep just enough to allow 1 second  between history snapshots
-        if not os.path.isdir(output_path):
+        # this is because history.txt indexes/keys snapshots by epoch seconds and we dont want dupe keys
-            os.mkdir(output_path)
+        if self.__newest_history_key and int(timestamp) == int(self.__newest_history_key):
+            time.sleep(timestamp - self.__newest_history_key)
 
-        snapshot_fname = "{}/{}.stripped.txt".format(output_path, uuid.uuid4())
+        snapshot_fname = "{}.txt".format(str(uuid.uuid4()))
-        logging.debug("Saving history text {}".format(snapshot_fname))
 
-        with open(snapshot_fname, 'wb') as f:
+        # in /diff/ and /preview/ we are going to assume for now that it's UTF-8 when reading
+        # most sites are utf-8 and some are even broken utf-8
+        with open(os.path.join(self.watch_data_dir, 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)
+        index_fname = os.path.join(self.watch_data_dir, "history.txt")
         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
+        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
+        # @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
@@ -188,6 +229,11 @@ class model(dict):
                 seconds += x * n
         return seconds
 
+    def is_schedule_permitted(self):
+        """According to the current day of week and time, is this watch queueable?"""
+
+        return True
+
     # Iterate over all history texts and see if something new exists
     def lines_contain_something_unique_compared_to_history(self, lines: list):
         local_lines = set([l.decode('utf-8').strip().lower() for l in lines])
@@ -203,14 +249,14 @@ class model(dict):
         return not local_lines.issubset(existing_history)
 
     def get_screenshot(self):
-        fname = os.path.join(self.__datastore_path, self['uuid'], "last-screenshot.png")
+        fname = os.path.join(self.watch_data_dir, "last-screenshot.png")
         if os.path.isfile(fname):
             return fname
 
         return False
 
     def __get_file_ctime(self, filename):
-        fname = os.path.join(self.__datastore_path, self['uuid'], filename)
+        fname = os.path.join(self.watch_data_dir, filename)
         if os.path.isfile(fname):
             return int(os.path.getmtime(fname))
         return False
@@ -235,9 +281,14 @@ class model(dict):
     def snapshot_error_screenshot_ctime(self):
         return self.__get_file_ctime('last-error-screenshot.png')
 
+    @property
+    def watch_data_dir(self):
+        # The base dir of the watch data
+        return os.path.join(self.__datastore_path, self['uuid'])
+    
     def get_error_text(self):
         """Return the text saved from a previous request that resulted in a non-200 error"""
-        fname = os.path.join(self.__datastore_path, self['uuid'], "last-error.txt")
+        fname = os.path.join(self.watch_data_dir, "last-error.txt")
         if os.path.isfile(fname):
             with open(fname, 'r') as f:
                 return f.read()
@@ -245,7 +296,7 @@ class model(dict):
 
     def get_error_snapshot(self):
         """Return path to the screenshot that resulted in a non-200 error"""
-        fname = os.path.join(self.__datastore_path, self['uuid'], "last-error-screenshot.png")
+        fname = os.path.join(self.watch_data_dir, "last-error-screenshot.png")
         if os.path.isfile(fname):
             return fname
         return False

changedetectionio/notification.py

@@ -14,16 +14,19 @@ valid_tokens = {
     'current_snapshot': ''
 }
 
+default_notification_format_for_watch = 'System default'
+default_notification_format = 'Text'
+default_notification_body = '{watch_url} had a change.\n---\n{diff}\n---\n'
+default_notification_title = 'ChangeDetection.io Notification - {watch_url}'
+
 valid_notification_formats = {
     'Text': NotifyFormat.TEXT,
     'Markdown': NotifyFormat.MARKDOWN,
     'HTML': NotifyFormat.HTML,
+    # Used only for editing a watch (not for global)
+    default_notification_format_for_watch: default_notification_format_for_watch
 }
 
-default_notification_format = 'Text'
-default_notification_body = '{watch_url} had a change.\n---\n{diff}\n---\n'
-default_notification_title = 'ChangeDetection.io Notification - {watch_url}'
-
 def process_notification(n_object, datastore):
 
     # Get the notification body from datastore

changedetectionio/run_all_tests.sh

@@ -9,6 +9,8 @@
 # exit when any command fails
 set -e
 
+SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+
 find tests/test_*py -type f|while read test_name
 do
   echo "TEST RUNNING $test_name"
@@ -22,7 +24,6 @@ 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
 
@@ -38,13 +39,60 @@ 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
+PLAYWRIGHT_VERSION=$(grep -i -E "RUN pip install.+" "$SCRIPT_DIR/../Dockerfile" | grep --only-matching -i -E "playwright[=><~+]+[0-9\.]+")
+echo "using $PLAYWRIGHT_VERSION"
+pip3 install "$PLAYWRIGHT_VERSION"
 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
 pytest tests/test_errorhandling.py
+pytest tests/visualselector/test_fetch_data.py
 
 unset PLAYWRIGHT_DRIVER_URL
-docker kill $$-test_browserless
+docker kill $$-test_browserless
+
+# Test proxy list handling, starting two squids on different ports
+# Each squid adds a different header to the response, which is the main thing we test for.
+docker run -d --name $$-squid-one --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf -p 3128:3128 ubuntu/squid:4.13-21.10_edge
+docker run -d --name $$-squid-two --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf -p 3129:3128 ubuntu/squid:4.13-21.10_edge
+
+
+# So, basic HTTP as env var test
+export HTTP_PROXY=http://localhost:3128
+export HTTPS_PROXY=http://localhost:3128
+pytest tests/proxy_list/test_proxy.py
+docker logs $$-squid-one 2>/dev/null|grep one.changedetection.io
+if [ $? -ne 0 ]
+then
+  echo "Did not see a request to one.changedetection.io in the squid logs (while checking env vars HTTP_PROXY/HTTPS_PROXY)"
+fi
+unset HTTP_PROXY
+unset HTTPS_PROXY
+
+
+# 2nd test actually choose the preferred proxy from proxies.json
+cp tests/proxy_list/proxies.json-example ./test-datastore/proxies.json
+# Makes a watch use a preferred proxy
+pytest tests/proxy_list/test_multiple_proxy.py
+
+# Should be a request in the default "first" squid
+docker logs $$-squid-one 2>/dev/null|grep chosen.changedetection.io
+if [ $? -ne 0 ]
+then
+  echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy)"
+fi
+
+# And one in the 'second' squid (user selects this as preferred)
+docker logs $$-squid-two 2>/dev/null|grep chosen.changedetection.io
+if [ $? -ne 0 ]
+then
+  echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy)"
+fi
+
+# @todo - test system override proxy selection and watch defaults, setup a 3rd squid?
+docker kill $$-squid-one
+docker kill $$-squid-two
+
+

changedetectionio/static/images/notice.svg

@@ -0,0 +1,51 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   width="20.108334mm"
+   height="21.43125mm"
+   viewBox="0 0 20.108334 21.43125"
+   version="1.1"
+   id="svg5"
+   xmlns:xlink="http://www.w3.org/1999/xlink"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg">
+  <defs
+     id="defs2" />
+  <g
+     id="layer1"
+     transform="translate(-141.05873,-76.816635)">
+    <image
+       width="20.108334"
+       height="21.43125"
+       preserveAspectRatio="none"
+       style="image-rendering:optimizeQuality"
+       xlink:href="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAEwAAABRCAYAAAB430BuAAAABHNCSVQICAgIfAhkiAAABLxJREFU
+eJztnN2Z2jgUhl8Z7petIGwF0WMXsFBBoIKwFWS2gmQryKSCJRXsTAUDBTDRVBCmgkAB9tkLexh+
+bIONLGwP7xU2RjafpaOjoyNBCxHNQAJEfG5sl+3ZLrAWeAyST5/sF91mFH3bRbZbsAq4ClaQq2B7
+iKYnmg9Z318F20ICRnj8pMOd6E3HscNVsATxmQD/oeghPCnDLO26q2AkYin+TQ7XREyyrn3zgu2J
+BSEjZTBZ179pwQ7EEv7KaoovvFnBUsV6ZHrsd+0WTHhKPV1SLGivYEsA1KEtEs2grFitRjQ65VxP
+fH5JgEjAKsvXupKwFfYxaYJeSeHcWqVSCuwD7/HQQD8lRHLWDStBWG3slbAElkTc5/lTZdkIJhpN
+h6/UUZDyzAgZK8PKVoEKErE8HlD0bBVcI2ZqwdBWYbFgAT+g1UZwrBbcvRyIpofHJ1Sh1rQCZt1k
+lN5msQAm8CoYoFF8KVHOsFtQ5aayExBUhpnopJl6J/3/FREGWCrxmaH40/4z1oyQ320Yf5dDozXC
+P4QMCRkCY4S5w/tbMTtd4L2Ngo6wJmSQ4hfdScAU+OjgGazgOXEl8oJyof3Z6Spx0iTzgnLKsMoK
+w9SRuoR3rHniVVMXwRpDXQR7d+kHOJV6CFZB0khVOBGsTcE6VzWsNVGQizfJptU+N4LlD3AbVfsu
+XsOahhvB8nrB08IrtcGNYNIct+EYl2+S6mr0D8kLUMrV6BfFRTzOGs4Ey8p1aNrUnssaliaMO/vV
+sfNi3AmW5j54DgUTO/dyJ1hab9iwHhLcNskP23ZMND0kewFBXek6vZvHg/hMiUPSN00z+OBasFig
+y8wSRfnZ0adSBz+sUVwFK4jbJhnPP06To1ETczpcCnavHhltHd82LU0AXDbJMGXBU8PSBAA8Jxk0
+wnNaqlGSJuAyg+dsXIV38iZqXU3iWsmodhetSNlDQgJGriZxbWVSe1hS/gQ+S/C6j4QEfES21vxU
+icXsoC4vC5mqJvbybyXgduucG/YWaYmmj+IdHvpoxFdt8ltRP5h3iZjRqfBh60C4t1rNY7rxAU95
+aYnhEp+/u8pgxGfeRCfyJIR5SkLfFOHYXMMzu63PEDF9WQnSo8MUmhduyUWYEzGyvnRmU3683ugG
+GAG/2bqJU4RnFDNCpsfWb5chswUnwb5Xg+hxiyo9w7MGJoSVpmYulam+A8scS+5nPYtf+s9mpZw7
+J1nayDnCVuu4Ck+E6DqIBYDHHR1+is/n8kVUhfBExMBFMzm4taafkXcWL9BSfBG/nNN8sutYcE3S
+d7XI3o6lSpIe/xcAIX/svzDxMVu22BAyLNKL2q9hwrdLiZWwXbP6B99GDLaGSpoOD6JPn4yxK1i8
+B0StY1zKsCJiQNxzQ0HRbAm2BsZN2TBDGVaE5USzIVjsNix2VrzWHmUwB6J5fD32uyKCzQ7OxG5D
+vzZuQ0E2osXjRlBMjvWe5WtYPE4b2BynXQJlMEToTUegmEiwM1mzQ1nBvqvH5ov1wlZHcA+AZHdc
+xQW7vNuQS9kBtzKs1IIRMM7b0q/YvGTzto4qbFutdV5FnLtLk2x3JVWUfXKTbIu9Opc2J6Osj19S
+HLfJKO64r6rg/wFBX3+2ZapW8wAAAABJRU5ErkJggg==
+"
+       id="image832"
+       x="141.05873"
+       y="76.816635" />
+  </g>
+</svg>

changedetectionio/static/images/play.svg

@@ -0,0 +1,122 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   version="1.1"
+   id="Capa_1"
+   x="0px"
+   y="0px"
+   viewBox="0 0 15 14.998326"
+   xml:space="preserve"
+   width="15"
+   height="14.998326"
+   sodipodi:docname="play.svg"
+   inkscape:version="1.1.1 (1:1.1+202109281949+c3084ef5ed)"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:dc="http://purl.org/dc/elements/1.1/"><sodipodi:namedview
+   id="namedview21"
+   pagecolor="#ffffff"
+   bordercolor="#666666"
+   borderopacity="1.0"
+   inkscape:pageshadow="2"
+   inkscape:pageopacity="0.0"
+   inkscape:pagecheckerboard="0"
+   showgrid="false"
+   inkscape:zoom="45.47174"
+   inkscape:cx="7.4991632"
+   inkscape:cy="7.4991632"
+   inkscape:window-width="1554"
+   inkscape:window-height="896"
+   inkscape:window-x="3048"
+   inkscape:window-y="227"
+   inkscape:window-maximized="0"
+   inkscape:current-layer="Capa_1" /><metadata
+   id="metadata39"><rdf:RDF><cc:Work
+       rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type
+         rdf:resource="http://purl.org/dc/dcmitype/StillImage" /></cc:Work></rdf:RDF></metadata><defs
+   id="defs37" />
+<path
+   id="path2"
+   style="fill:#1b98f8;fill-opacity:1;stroke-width:0.0292893"
+   d="M 7.4980469,0 C 4.5496028,-0.04093755 1.7047721,1.8547661 0.58789062,4.5800781 -0.57819305,7.2574082 0.02636631,10.583252 2.0703125,12.671875 4.0368718,14.788335 7.2754393,15.560096 9.9882812,14.572266 12.800219,13.617028 14.874915,10.855516 14.986328,7.8847656 15.172991,4.9968456 13.497714,2.109448 10.910156,0.8203125 9.858961,0.28011352 8.6796569,-0.00179908 7.4980469,0 Z"
+   sodipodi:nodetypes="ccccccc" />
+<g
+   id="g4"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g6"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g8"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g10"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g12"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g14"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g16"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g18"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g20"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g22"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g24"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g26"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g28"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g30"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<g
+   id="g32"
+   transform="translate(-0.01903604,0.02221043)">
+</g>
+<path
+   sodipodi:type="star"
+   style="fill:#ffffff;fill-opacity:1;stroke-width:37.7953;paint-order:stroke fill markers"
+   id="path1203"
+   inkscape:flatsided="false"
+   sodipodi:sides="3"
+   sodipodi:cx="7.2964563"
+   sodipodi:cy="7.3240671"
+   sodipodi:r1="3.805218"
+   sodipodi:r2="1.9026089"
+   sodipodi:arg1="-0.0017436774"
+   sodipodi:arg2="1.0454539"
+   inkscape:rounded="0"
+   inkscape:randomized="0"
+   d="M 11.101669,7.317432 8.2506324,8.9701135 5.3995964,10.622795 5.3938504,7.3273846 5.3881041,4.0319742 8.2448863,5.6747033 Z"
+   inkscape:transform-center-x="-0.94843001"
+   inkscape:transform-center-y="0.0033175346" /></svg>

changedetectionio/static/js/visual-selector.js

@@ -50,7 +50,7 @@ $(document).ready(function() {
         state_clicked=false;
         ctx.clearRect(0, 0, c.width, c.height);
         xctx.clearRect(0, 0, c.width, c.height);
-        $("#css_filter").val('');
+        $("#include_filters").val('');
     });
 
 
@@ -68,7 +68,7 @@ $(document).ready(function() {
                xctx = c.getContext("2d");
                 // redline highlight context
                ctx = c.getContext("2d");
-               current_default_xpath =$("#css_filter").val();
+               current_default_xpath =$("#include_filters").val();
                fetch_data();
                $('#selector-canvas').off("mousemove mousedown");
                // screenshot_url defined in the edit.html template
@@ -205,9 +205,9 @@ $(document).ready(function() {
         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);
+            $("#include_filters").val('xpath:'+sel.xpath);
         } else {
-            $("#css_filter").val(sel.xpath);
+            $("#include_filters").val(sel.xpath);
         }
         xctx.fillStyle = 'rgba(205,205,205,0.95)';
         xctx.strokeStyle = 'rgba(225,0,0,0.9)';

changedetectionio/static/js/watch-overview.js

@@ -22,5 +22,18 @@ $(function () {
       });
   });
 
+    // checkboxes - check all
+    $("#check-all").click(function (e) {
+        $('input[type=checkbox]').not(this).prop('checked', this.checked);
+    });
+    // checkboxes - show/hide buttons
+    $("input[type=checkbox]").click(function (e) {
+        if ($('input[type=checkbox]:checked').length) {
+            $('#checkbox-operations').slideDown();
+        } else {
+            $('#checkbox-operations').slideUp();
+        }
+    });
+
 });
 

changedetectionio/static/js/watch-settings.js

@@ -30,4 +30,11 @@ $(document).ready(function() {
     });
     toggle();
 
+    $('#notification-setting-reset-to-default').click(function (e) {
+        $('#notification_title').val('');
+        $('#notification_body').val('');
+        $('#notification_format').val('System default');
+        $('#notification_urls').val('');
+        e.preventDefault();
+    });
 });

changedetectionio/static/styles/parts/_arrows.scss

@@ -0,0 +1,26 @@
+.arrow {
+  border: solid #1b98f8;
+  border-width: 0 2px 2px 0;
+  display: inline-block;
+  padding: 3px;
+
+  &.right {
+    transform: rotate(-45deg);
+    -webkit-transform: rotate(-45deg);
+  }
+
+  &.left {
+    transform: rotate(135deg);
+    -webkit-transform: rotate(135deg);
+  }
+
+  &.up, &.asc {
+    transform: rotate(-135deg);
+    -webkit-transform: rotate(-135deg);
+  }
+
+  &.down, &.desc {
+    transform: rotate(45deg);
+    -webkit-transform: rotate(45deg);
+  }
+}

changedetectionio/static/styles/styles.css

@@ -4,6 +4,24 @@
  * nvm use v14.18.1 && npm install && npm run build
  * or npm run watch
  */
+.arrow {
+  border: solid #1b98f8;
+  border-width: 0 2px 2px 0;
+  display: inline-block;
+  padding: 3px; }
+  .arrow.right {
+    transform: rotate(-45deg);
+    -webkit-transform: rotate(-45deg); }
+  .arrow.left {
+    transform: rotate(135deg);
+    -webkit-transform: rotate(135deg); }
+  .arrow.up, .arrow.asc {
+    transform: rotate(-135deg);
+    -webkit-transform: rotate(-135deg); }
+  .arrow.down, .arrow.desc {
+    transform: rotate(45deg);
+    -webkit-transform: rotate(45deg); }
+
 body {
   color: #333;
   background: #262626; }
@@ -53,6 +71,12 @@ code {
     white-space: normal; }
   .watch-table th {
     white-space: nowrap; }
+    .watch-table th a {
+      font-weight: normal; }
+      .watch-table th a.active {
+        font-weight: bolder; }
+      .watch-table th a.inactive .arrow {
+        display: none; }
   .watch-table .title-col a[target="_blank"]::after, .watch-table .current-diff-url::after {
     content: url(data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAQElEQVR42qXKwQkAIAxDUUdxtO6/RBQkQZvSi8I/pL4BoGw/XPkh4XigPmsUgh0626AjRsgxHTkUThsG2T/sIlzdTsp52kSS1wAAAABJRU5ErkJggg==);
     margin: 0 3px 0 5px; }
@@ -103,30 +127,12 @@ body:after, body:before {
   -webkit-clip-path: polygon(100% 0, 0 0, 0 77.5%, 1% 77.4%, 2% 77.1%, 3% 76.6%, 4% 75.9%, 5% 75.05%, 6% 74.05%, 7% 72.95%, 8% 71.75%, 9% 70.55%, 10% 69.3%, 11% 68.05%, 12% 66.9%, 13% 65.8%, 14% 64.8%, 15% 64%, 16% 63.35%, 17% 62.85%, 18% 62.6%, 19% 62.5%, 20% 62.65%, 21% 63%, 22% 63.5%, 23% 64.2%, 24% 65.1%, 25% 66.1%, 26% 67.2%, 27% 68.4%, 28% 69.65%, 29% 70.9%, 30% 72.15%, 31% 73.3%, 32% 74.35%, 33% 75.3%, 34% 76.1%, 35% 76.75%, 36% 77.2%, 37% 77.45%, 38% 77.5%, 39% 77.3%, 40% 76.95%, 41% 76.4%, 42% 75.65%, 43% 74.75%, 44% 73.75%, 45% 72.6%, 46% 71.4%, 47% 70.15%, 48% 68.9%, 49% 67.7%, 50% 66.55%, 51% 65.5%, 52% 64.55%, 53% 63.75%, 54% 63.15%, 55% 62.75%, 56% 62.55%, 57% 62.5%, 58% 62.7%, 59% 63.1%, 60% 63.7%, 61% 64.45%, 62% 65.4%, 63% 66.45%, 64% 67.6%, 65% 68.8%, 66% 70.05%, 67% 71.3%, 68% 72.5%, 69% 73.6%, 70% 74.65%, 71% 75.55%, 72% 76.35%, 73% 76.9%, 74% 77.3%, 75% 77.5%, 76% 77.45%, 77% 77.25%, 78% 76.8%, 79% 76.2%, 80% 75.4%, 81% 74.45%, 82% 73.4%, 83% 72.25%, 84% 71.05%, 85% 69.8%, 86% 68.55%, 87% 67.35%, 88% 66.2%, 89% 65.2%, 90% 64.3%, 91% 63.55%, 92% 63%, 93% 62.65%, 94% 62.5%, 95% 62.55%, 96% 62.8%, 97% 63.3%, 98% 63.9%, 99% 64.75%, 100% 65.7%);
   clip-path: polygon(100% 0, 0 0, 0 77.5%, 1% 77.4%, 2% 77.1%, 3% 76.6%, 4% 75.9%, 5% 75.05%, 6% 74.05%, 7% 72.95%, 8% 71.75%, 9% 70.55%, 10% 69.3%, 11% 68.05%, 12% 66.9%, 13% 65.8%, 14% 64.8%, 15% 64%, 16% 63.35%, 17% 62.85%, 18% 62.6%, 19% 62.5%, 20% 62.65%, 21% 63%, 22% 63.5%, 23% 64.2%, 24% 65.1%, 25% 66.1%, 26% 67.2%, 27% 68.4%, 28% 69.65%, 29% 70.9%, 30% 72.15%, 31% 73.3%, 32% 74.35%, 33% 75.3%, 34% 76.1%, 35% 76.75%, 36% 77.2%, 37% 77.45%, 38% 77.5%, 39% 77.3%, 40% 76.95%, 41% 76.4%, 42% 75.65%, 43% 74.75%, 44% 73.75%, 45% 72.6%, 46% 71.4%, 47% 70.15%, 48% 68.9%, 49% 67.7%, 50% 66.55%, 51% 65.5%, 52% 64.55%, 53% 63.75%, 54% 63.15%, 55% 62.75%, 56% 62.55%, 57% 62.5%, 58% 62.7%, 59% 63.1%, 60% 63.7%, 61% 64.45%, 62% 65.4%, 63% 66.45%, 64% 67.6%, 65% 68.8%, 66% 70.05%, 67% 71.3%, 68% 72.5%, 69% 73.6%, 70% 74.65%, 71% 75.55%, 72% 76.35%, 73% 76.9%, 74% 77.3%, 75% 77.5%, 76% 77.45%, 77% 77.25%, 78% 76.8%, 79% 76.2%, 80% 75.4%, 81% 74.45%, 82% 73.4%, 83% 72.25%, 84% 71.05%, 85% 69.8%, 86% 68.55%, 87% 67.35%, 88% 66.2%, 89% 65.2%, 90% 64.3%, 91% 63.55%, 92% 63%, 93% 62.65%, 94% 62.5%, 95% 62.55%, 96% 62.8%, 97% 63.3%, 98% 63.9%, 99% 64.75%, 100% 65.7%); }
 
-.arrow {
-  border: solid black;
-  border-width: 0 3px 3px 0;
-  display: inline-block;
-  padding: 3px; }
-  .arrow.right {
-    transform: rotate(-45deg);
-    -webkit-transform: rotate(-45deg); }
-  .arrow.left {
-    transform: rotate(135deg);
-    -webkit-transform: rotate(135deg); }
-  .arrow.up {
-    transform: rotate(-135deg);
-    -webkit-transform: rotate(-135deg); }
-  .arrow.down {
-    transform: rotate(45deg);
-    -webkit-transform: rotate(45deg); }
-
 .button-small {
   font-size: 85%; }
 
 .fetch-error {
   padding-top: 1em;
-  font-size: 60%;
+  font-size: 80%;
   max-width: 400px;
   display: block; }
 
@@ -474,6 +480,22 @@ ul {
   .time-check-widget tr input[type="number"] {
     width: 5em; }
 
+.pure-control-group table label {
+  color: #333;
+  font-weight: normal; }
+
+.time-schedule-check-limit-widget tr {
+  display: inline-block; }
+
+.time-schedule-check-limit-widget li {
+  text-decoration: none; }
+
+.time-schedule-check-limit-widget ul {
+  padding-left: 0px; }
+  .time-schedule-check-limit-widget ul li {
+    display: inline-block;
+    width: 3em; }
+
 #selector-wrapper {
   height: 600px;
   overflow-y: scroll;
@@ -549,3 +571,26 @@ ul {
   .snapshot-age.error {
     background-color: #ff0000;
     color: #fff; }
+
+#checkbox-operations {
+  background: rgba(0, 0, 0, 0.05);
+  padding: 1em;
+  border-radius: 10px;
+  margin-bottom: 1em;
+  display: none; }
+
+.checkbox-uuid > * {
+  vertical-align: middle; }
+
+.inline-warning {
+  border: 1px solid #ff3300;
+  padding: 0.5rem;
+  border-radius: 5px;
+  color: #ff3300; }
+  .inline-warning > span {
+    display: inline-block;
+    vertical-align: middle; }
+  .inline-warning img.inline-warning-icon {
+    display: inline;
+    height: 26px;
+    vertical-align: middle; }

changedetectionio/static/styles/styles.scss

@@ -4,6 +4,8 @@
  * nvm use v14.18.1 && npm install && npm run build
  * or npm run watch
  */
+@import "parts/_arrows.scss";
+
 body {
   color: #333;
   background: #262626;
@@ -68,6 +70,17 @@ code {
 
   th {
     white-space: nowrap;
+    a {
+      font-weight: normal;
+      &.active {
+        font-weight: bolder;
+      }
+      &.inactive {
+        .arrow {
+          display: none;
+        }
+      }
+    }
   }
 
   .title-col a[target="_blank"]::after, .current-diff-url::after {
@@ -137,36 +150,13 @@ body:after, body:before {
   clip-path: polygon(100% 0, 0 0, 0 77.5%, 1% 77.4%, 2% 77.1%, 3% 76.6%, 4% 75.9%, 5% 75.05%, 6% 74.05%, 7% 72.95%, 8% 71.75%, 9% 70.55%, 10% 69.3%, 11% 68.05%, 12% 66.9%, 13% 65.8%, 14% 64.8%, 15% 64%, 16% 63.35%, 17% 62.85%, 18% 62.6%, 19% 62.5%, 20% 62.65%, 21% 63%, 22% 63.5%, 23% 64.2%, 24% 65.1%, 25% 66.1%, 26% 67.2%, 27% 68.4%, 28% 69.65%, 29% 70.9%, 30% 72.15%, 31% 73.3%, 32% 74.35%, 33% 75.3%, 34% 76.1%, 35% 76.75%, 36% 77.2%, 37% 77.45%, 38% 77.5%, 39% 77.3%, 40% 76.95%, 41% 76.4%, 42% 75.65%, 43% 74.75%, 44% 73.75%, 45% 72.6%, 46% 71.4%, 47% 70.15%, 48% 68.9%, 49% 67.7%, 50% 66.55%, 51% 65.5%, 52% 64.55%, 53% 63.75%, 54% 63.15%, 55% 62.75%, 56% 62.55%, 57% 62.5%, 58% 62.7%, 59% 63.1%, 60% 63.7%, 61% 64.45%, 62% 65.4%, 63% 66.45%, 64% 67.6%, 65% 68.8%, 66% 70.05%, 67% 71.3%, 68% 72.5%, 69% 73.6%, 70% 74.65%, 71% 75.55%, 72% 76.35%, 73% 76.9%, 74% 77.3%, 75% 77.5%, 76% 77.45%, 77% 77.25%, 78% 76.8%, 79% 76.2%, 80% 75.4%, 81% 74.45%, 82% 73.4%, 83% 72.25%, 84% 71.05%, 85% 69.8%, 86% 68.55%, 87% 67.35%, 88% 66.2%, 89% 65.2%, 90% 64.3%, 91% 63.55%, 92% 63%, 93% 62.65%, 94% 62.5%, 95% 62.55%, 96% 62.8%, 97% 63.3%, 98% 63.9%, 99% 64.75%, 100% 65.7%)
 }
 
-.arrow {
-  border: solid black;
-  border-width: 0 3px 3px 0;
-  display: inline-block;
-  padding: 3px;
-    &.right {
-      transform: rotate(-45deg);
-      -webkit-transform: rotate(-45deg);
-    }
-    &.left {
-      transform: rotate(135deg);
-      -webkit-transform: rotate(135deg);
-    }
-    &.up {
-      transform: rotate(-135deg);
-      -webkit-transform: rotate(-135deg);
-    }
-    &.down {
-      transform: rotate(45deg);
-      -webkit-transform: rotate(45deg);
-    }
-}
-
 .button-small {
   font-size: 85%;
 }
 
 .fetch-error {
   padding-top: 1em;
-  font-size: 60%;
+  font-size: 80%;
   max-width: 400px;
   display: block;
 }
@@ -512,6 +502,7 @@ and also iPads specifically.
         vertical-align: middle;
       }
     }
+
     .last-checked::before {
       color: #555;
       content: "Last Checked ";
@@ -686,6 +677,29 @@ ul {
         }
     }
 }
+.pure-control-group table  label {
+  color: #333;
+  font-weight: normal;
+}
+
+.time-schedule-check-limit-widget {
+  tr {
+    display: inline-block;
+  }
+
+  li {
+    text-decoration: none;
+  }
+
+  ul {
+    padding-left: 0px;
+    li {
+      display: inline-block;
+      width: 3em;
+    }
+  }
+}
+
 
 #selector-wrapper {
  height: 600px;
@@ -783,3 +797,33 @@ ul {
   }
 }
 
+#checkbox-operations {
+  background: rgba(0, 0, 0, 0.05);
+  padding: 1em;
+  border-radius: 10px;
+  margin-bottom: 1em;
+  display: none;
+}
+.checkbox-uuid {
+  > * {
+    vertical-align: middle;
+  }
+}
+
+.inline-warning {
+  > span {
+    display: inline-block;
+    vertical-align: middle;
+  }
+
+  img.inline-warning-icon {
+    display: inline;
+    height: 26px;
+    vertical-align: middle;
+  }
+
+  border: 1px solid #ff3300;
+  padding: 0.5rem;
+  border-radius: 5px;
+  color: #ff3300;
+}

changedetectionio/store.py

@@ -8,7 +8,7 @@ import threading
 import time
 import uuid as uuid_builder
 from copy import deepcopy
-from os import mkdir, path, unlink
+from os import path, unlink
 from threading import Lock
 import re
 import requests
@@ -27,17 +27,18 @@ class ChangeDetectionStore:
     # For when we edit, we should write to disk
     needs_write_urgent = False
 
+    __version_check = True
+
     def __init__(self, datastore_path="/datastore", include_default_watches=True, version_tag="0.0.0"):
         # Should only be active for docker
         # logging.basicConfig(filename='/dev/stdout', level=logging.INFO)
-        self.needs_write = False
+        self.__data = App.model()
         self.datastore_path = datastore_path
         self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
+        self.needs_write = False
         self.proxy_list = None
+        self.start_time = time.time()
         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(datastore_path = datastore_path, default={}))
@@ -81,10 +82,13 @@ class ChangeDetectionStore:
         except (FileNotFoundError, json.decoder.JSONDecodeError):
             if include_default_watches:
                 print("Creating JSON store at", self.datastore_path)
+                self.add_watch(url='https://news.ycombinator.com/',
+                               tag='Tech news',
+                               extras={'fetch_backend': 'html_requests'})
 
-                self.add_watch(url='http://www.quotationspage.com/random.php', tag='test')
+                self.add_watch(url='https://changedetection.io/CHANGELOG.txt',
-                self.add_watch(url='https://news.ycombinator.com/', tag='Tech news')
+                               tag='changedetection.io',
-                self.add_watch(url='https://changedetection.io/CHANGELOG.txt', tag='changedetection.io')
+                               extras={'fetch_backend': 'html_requests'})
 
         self.__data['version_tag'] = version_tag
 
@@ -113,9 +117,7 @@ class ChangeDetectionStore:
             self.__data['settings']['application']['api_access_token'] = secret
 
         # Proxy list support - available as a selection in settings when text file is imported
-        # CSV list
+        proxy_list_file = "{}/proxies.json".format(self.datastore_path)
-        # "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)
 
@@ -244,10 +246,6 @@ class ChangeDetectionStore:
 
         return False
 
-    def get_val(self, uuid, val):
-        # Probably their should be dict...
-        return self.data['watching'][uuid].get(val)
-
     # Remove a watchs data but keep the entry (URL etc)
     def clear_watch_history(self, uuid):
         import pathlib
@@ -274,7 +272,7 @@ class ChangeDetectionStore:
             extras = {}
         # should always be str
         if tag is None or not tag:
-            tag=''
+            tag = ''
 
         # Incase these are copied across, assume it's a reference and deepcopy()
         apply_extras = deepcopy(extras)
@@ -289,17 +287,31 @@ class ChangeDetectionStore:
                 res = r.json()
 
                 # List of permissible attributes we accept from the wild internet
-                for k in ['url', 'tag',
+                for k in [
-                          'paused', 'title',
+                    'body',
-                          'previous_md5', 'headers',
+                    'css_filter',
-                          'body', 'method',
+                    'extract_text',
-                          'ignore_text', 'css_filter',
+                    'extract_title_as_title',
-                          'subtractive_selectors', 'trigger_text',
+                    'headers',
-                          'extract_title_as_title', 'extract_text',
+                    'ignore_text',
-                          'text_should_not_be_present',
+                    'include_filters',
-                          'webdriver_js_execute_code']:
+                    'method',
+                    'paused',
+                    'previous_md5',
+                    'subtractive_selectors',
+                    'tag',
+                    'text_should_not_be_present',
+                    'title',
+                    'trigger_text',
+                    'webdriver_js_execute_code',
+                    'url',
+                ]:
                     if res.get(k):
-                        apply_extras[k] = res[k]
+                        if k != 'css_filter':
+                            apply_extras[k] = res[k]
+                        else:
+                            # We renamed the field and made it a list
+                            apply_extras['include_filters'] = [res['css_filter']]
 
             except Exception as e:
                 logging.error("Error fetching metadata for shared watch link", url, str(e))
@@ -322,17 +334,13 @@ class ChangeDetectionStore:
                     del apply_extras[k]
 
             new_watch.update(apply_extras)
-            self.__data['watching'][new_uuid]=new_watch
+            self.__data['watching'][new_uuid] = new_watch
 
-        # Get the directory ready
+        self.__data['watching'][new_uuid].ensure_data_dir_exists()
-        output_path = "{}/{}".format(self.datastore_path, new_uuid)
-        try:
-            mkdir(output_path)
-        except FileExistsError:
-            print(output_path, "already exists.")
 
         if write_to_disk_now:
             self.sync_to_json()
+
         return new_uuid
 
     def visualselector_data_is_ready(self, watch_uuid):
@@ -346,29 +354,35 @@ class ChangeDetectionStore:
 
     # Save as PNG, PNG is larger but better for doing visual diff in the future
     def save_screenshot(self, watch_uuid, screenshot: bytes, as_error=False):
+        if not self.data['watching'].get(watch_uuid):
+            return
 
         if as_error:
             target_path = os.path.join(self.datastore_path, watch_uuid, "last-error-screenshot.png")
         else:
             target_path = os.path.join(self.datastore_path, watch_uuid, "last-screenshot.png")
 
+        self.data['watching'][watch_uuid].ensure_data_dir_exists()
+
         with open(target_path, 'wb') as f:
             f.write(screenshot)
             f.close()
 
     def save_error_text(self, watch_uuid, contents):
-
+        if not self.data['watching'].get(watch_uuid):
+            return
         target_path = os.path.join(self.datastore_path, watch_uuid, "last-error.txt")
 
         with open(target_path, 'w') as f:
             f.write(contents)
 
     def save_xpath_data(self, watch_uuid, data, as_error=False):
-
+        if not self.data['watching'].get(watch_uuid):
+            return
         if as_error:
-            target_path = os.path.join(self.datastore_path, watch_uuid, "elements.json")
-        else:
             target_path = os.path.join(self.datastore_path, watch_uuid, "elements-error.json")
+        else:
+            target_path = os.path.join(self.datastore_path, watch_uuid, "elements.json")
 
         with open(target_path, 'w') as f:
             f.write(json.dumps(data))
@@ -440,20 +454,42 @@ class ChangeDetectionStore:
                     unlink(item)
 
     def import_proxy_list(self, filename):
-        import csv
+        with open(filename) as f:
-        with open(filename, newline='') as f:
+            self.proxy_list = json.load(f)
-            reader = csv.reader(f, skipinitialspace=True)
+            print ("Registered proxy list", list(self.proxy_list.keys()))
-            # @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
 
 
+    def get_preferred_proxy_for_watch(self, uuid):
+        """
+        Returns the preferred proxy by ID key
+        :param uuid: UUID
+        :return: proxy "key" id
+        """
+
+        proxy_id = None
+        if self.proxy_list is None:
+            return None
+
+        # If its a valid one
+        watch = self.data['watching'].get(uuid)
+
+        if watch.get('proxy') and watch.get('proxy') in list(self.proxy_list.keys()):
+            return watch.get('proxy')
+
+        # not valid (including None), try the system one
+        else:
+            system_proxy_id = self.data['settings']['requests'].get('proxy')
+            # Is not None and exists
+            if self.proxy_list.get(system_proxy_id):
+                return system_proxy_id
+
+        # Fallback - Did not resolve anything, use the first available
+        if system_proxy_id is None:
+            first_default = list(self.proxy_list)[0]
+            return first_default
+
+        return 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
@@ -538,4 +574,44 @@ class ChangeDetectionStore:
                 del(watch['last_changed'])
             except:
                 continue
+        return
+
+    def update_5(self):
+        # If the watch notification body, title look the same as the global one, unset it, so the watch defaults back to using the main settings
+        # In other words - the watch notification_title and notification_body are not needed if they are the same as the default one
+        current_system_body = self.data['settings']['application']['notification_body'].translate(str.maketrans('', '', "\r\n "))
+        current_system_title = self.data['settings']['application']['notification_body'].translate(str.maketrans('', '', "\r\n "))
+        for uuid, watch in self.data['watching'].items():
+            try:
+                watch_body = watch.get('notification_body', '')
+                if watch_body and watch_body.translate(str.maketrans('', '', "\r\n ")) == current_system_body:
+                    # Looks the same as the default one, so unset it
+                    watch['notification_body'] = None
+
+                watch_title = watch.get('notification_title', '')
+                if watch_title and watch_title.translate(str.maketrans('', '', "\r\n ")) == current_system_title:
+                    # Looks the same as the default one, so unset it
+                    watch['notification_title'] = None
+            except Exception as e:
+                continue
+        return
+
+
+    # We incorrectly used common header overrides that should only apply to Requests
+    # These are now handled in content_fetcher::html_requests and shouldnt be passed to Playwright/Selenium
+    def update_7(self):
+        # These were hard-coded in early versions
+        for v in ['User-Agent', 'Accept', 'Accept-Encoding', 'Accept-Language']:
+            if self.data['settings']['headers'].get(v):
+                del self.data['settings']['headers'][v]
+
+    # Convert filters to a list of filters css_filter -> include_filters
+    def update_8(self):
+        for uuid, watch in self.data['watching'].items():
+            try:
+                existing_filter = watch.get('css_filter', '')
+                if existing_filter:
+                    watch['include_filters'] = [existing_filter]
+            except:
+                continue
         return

changedetectionio/templates/_common_fields.jinja

@@ -1,13 +1,14 @@
 
 {% from '_helpers.jinja' import render_field %}
 
-{% macro render_common_settings_form(form, current_base_url, emailprefix) %}
+{% macro render_common_settings_form(form, emailprefix, settings_application) %}
                         <div class="pure-control-group">
                             {{ render_field(form.notification_urls, rows=5, placeholder="Examples:
     Gitter - gitter://token/room
     Office365 - o365://TenantID:AccountEmail/ClientID/ClientSecret/TargetEmail
     AWS SNS - sns://AccessKeyID/AccessSecretKey/RegionName/+PhoneNo
-    SMTPS - mailtos://user:pass@mail.domain.com?to=receivingAddress@example.com", class="notification-urls")
+    SMTPS - mailtos://user:pass@mail.domain.com?to=receivingAddress@example.com",
+    class="notification-urls" )
                             }}
                             <div class="pure-form-message-inline">
                               <ul>
@@ -26,15 +27,16 @@
                         </div>
                         <div id="notification-customisation" class="pure-control-group">
                             <div class="pure-control-group">
-                                {{ render_field(form.notification_title, class="m-d notification-title") }}
+                                {{ render_field(form.notification_title, class="m-d notification-title", placeholder=settings_application['notification_title']) }}
                                 <span class="pure-form-message-inline">Title for all notifications</span>
                             </div>
                             <div class="pure-control-group">
-                                {{ render_field(form.notification_body , rows=5, class="notification-body") }}
+                                {{ render_field(form.notification_body , rows=5, class="notification-body", placeholder=settings_application['notification_body']) }}
                                 <span class="pure-form-message-inline">Body for all notifications</span>
                             </div>
                             <div class="pure-control-group">
-                                {{ render_field(form.notification_format , rows=5, class="notification-format") }}
+                            <!-- unsure -->
+                                {{ render_field(form.notification_format , class="notification-format") }}
                                 <span class="pure-form-message-inline">Format for all notifications</span>
                             </div>
                             <div class="pure-controls">
@@ -94,7 +96,7 @@
                                 </table>
                                 <br/>
                                 URLs generated by changedetection.io (such as <code>{diff_url}</code>) require the <code>BASE_URL</code> environment variable set.<br/>
-                                Your <code>BASE_URL</code> var is currently "{{current_base_url}}"
+                                Your <code>BASE_URL</code> var is currently "{{settings_application['current_base_url']}}"
                             </span>
                             </div>
                         </div>

changedetectionio/templates/edit.html

@@ -40,7 +40,8 @@
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.url, placeholder="https://...", required=true, class="m-d") }}
-                        <span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span>
+                        <span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span><br/>
+                        <span class="pure-form-message-inline">You can use variables in the URL, perfect for inserting the current date and other logic, <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a></span><br/>
                     </div>
                     <div class="pure-control-group">
                         {{ render_field(form.title, class="m-d") }}
@@ -50,14 +51,15 @@
                         <span class="pure-form-message-inline">Organisational tag/group name used in the main listing page</span>
                     </div>
                     <div class="pure-control-group">
+                        {{ render_checkbox_field(form.time_use_system_default) }}
+                        <div style="opacity: 0.5">
                         {{ render_field(form.time_between_check, class="time-check-widget") }}
+                        {{ render_field(form.time_schedule_check_limit, class="time-schedule-check-limit-widget") }}
+@todo - add 'use default' checkbox
+                        </div>
                         {% if has_empty_checktime %}
-                        <span class="pure-form-message-inline">Currently using the <a
-                                href="{{ url_for('settings_page', uuid=uuid) }}">default global settings</a>, change to another value if you want to be specific.</span>
-                        {% else %}
-                        <span class="pure-form-message-inline">Set to blank to use the <a
-                                href="{{ url_for('settings_page', uuid=uuid) }}">default global settings</a>.</span>
                         {% endif %}
+
                     </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.extract_title_as_title) }}
@@ -77,6 +79,7 @@
                         <span class="pure-form-message-inline">
                             <p>Use the <strong>Basic</strong> method (default) where your watched site doesn't need Javascript to render.</p>
                             <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
+                            Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using BrightData Proxies, find out more here.</a>
                         </span>
                     </div>
                 {% if form.proxy %}
@@ -135,10 +138,20 @@ User-Agent: wonderbra 1.0") }}
             </div>
 
             <div class="tab-pane-inner" id="notifications">
-                <strong>Note: <i>These settings override the global settings for this watch.</i></strong>
                 <fieldset>
-                    <div class="field-group">
+                    <div  class="pure-control-group inline-radio">
-                        {{ render_common_settings_form(form, current_base_url, emailprefix) }}
+                      {{ render_checkbox_field(form.notification_muted) }}
+                    </div>
+                    <div class="field-group" id="notification-field-group">
+                        {% if has_default_notification_urls %}
+                        <div class="inline-warning">
+                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!"/>
+                            There are <a href="{{ url_for('settings_page')}}#notifications">system-wide notification URLs enabled</a>, this form will override notification settings for this watch only &dash; an empty Notification URL list here will still send notifications.
+                        </div>
+                        {% endif %}
+                        <a href="#notifications" id="notification-setting-reset-to-default" class="pure-button button-xsmall" style="right: 20px; top: 20px; position: absolute; background-color: #5f42dd; border-radius: 4px; font-size: 70%; color: #fff">Use system defaults</a>
+
+                        {{ render_common_settings_form(form, emailprefix, settings_application) }}
                     </div>
                 </fieldset>
             </div>
@@ -162,19 +175,29 @@ User-Agent: wonderbra 1.0") }}
                         </div>
                     </fieldset>
                     <div class="pure-control-group">
-                        {% set field = render_field(form.css_filter,
+                        {% set field = render_field(form.include_filters,
-                            placeholder=".class-name or #some-id, or other CSS selector rule.",
+                            rows=5,
+                            placeholder="#example
+xpath://body/div/span[contains(@class, 'example-class')]",
                             class="m-d")
                         %}
                         {{ field }}
                         {% if '/text()' in  field %}
                           <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br/>
                         {% endif %}
-                        <span class="pure-form-message-inline">
+                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br/>
                     <ul>
                         <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:$</code> to force re-formatting if required,  <a
+                        <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
-                                href="https://jsonpath.com/" target="new">test your JSONPath here</a></li>
+                            <ul>
+                                <li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required,  <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
+                                {% if jq_support %}
+                                <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>.</li>
+                                {% else %}
+                                <li>jq support not installed</li>
+                                {% endif %}
+                            </ul>
+                        </li>
                         <li>XPath - Limit text to this XPath rule, simply start with a forward-slash,
                             <ul>
                                 <li>Example:  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath://*[contains(@class, 'sametext')]</code>, <a
@@ -183,7 +206,7 @@ User-Agent: wonderbra 1.0") }}
                             </ul>
                             </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
+                    Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
                                 href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br/>
                 </span>
                     </div>

changedetectionio/templates/preview.html

@@ -57,6 +57,7 @@
          </br>
          {% if is_html_webdriver %}
            {% if screenshot %}
+             <div class="snapshot-age">{{watch.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
              <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
            {% else %}
               No screenshot available just yet! Try rechecking the page.

changedetectionio/templates/settings.html

@@ -21,6 +21,7 @@
             <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>
+            <li class="tab"><a href="#date-time">Date &amp; Time</a></li>
         </ul>
     </div>
     <div class="box-wrap inner">
@@ -30,6 +31,7 @@
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.requests.form.time_between_check, class="time-check-widget") }}
+                        {{ render_field(form.requests.form.time_schedule_check_limit, class="time-schedule-check-limit-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">
@@ -60,7 +62,7 @@
                         {{ render_field(form.application.form.base_url, placeholder="http://yoursite.com:5000/",
                         class="m-d") }}
                         <span class="pure-form-message-inline">
-                            Base URL used for the {base_url} token in notifications and RSS links.<br/>Default value is the ENV var 'BASE_URL' (Currently "{{current_base_url}}"),
+                            Base URL used for the <code>{base_url}</code> token in notifications and RSS links.<br/>Default value is the ENV var 'BASE_URL' (Currently "{{settings_application['current_base_url']}}"),
                             <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">read more here</a>.
                         </span>
                     </div>
@@ -69,12 +71,6 @@
                         {{ render_checkbox_field(form.application.form.extract_title_as_title) }}
                         <span class="pure-form-message-inline">Note: This will automatically apply to all existing watches.</span>
                     </div>
-
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.application.form.real_browser_save_screenshot) }}
-                        <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>
@@ -93,11 +89,10 @@
             <div class="tab-pane-inner" id="notifications">
                 <fieldset>
                     <div class="field-group">
-                        {{ render_common_settings_form(form.application.form, current_base_url, emailprefix) }}
+                        {{ render_common_settings_form(form.application.form, emailprefix, settings_application) }}
                     </div>
                 </fieldset>
             </div>
-
             <div class="tab-pane-inner" id="fetching">
                 <div class="pure-control-group inline-radio">
                     {{ render_field(form.application.form.fetch_backend, class="fetch-backend") }}
@@ -105,6 +100,8 @@
                         <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>
+                    <br/>
+                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using BrightData Proxies, find out more here.</a>
                 </div>
                 <fieldset class="pure-group" id="webdriver-override-options">
                     <div class="pure-form-message-inline">
@@ -174,6 +171,19 @@ nav
                     </div>
                 </div>
             </div>
+            <div class="tab-pane-inner" id="date-time">
+                <fieldset>
+                    <div class="field-group">
+                        {{ render_field(form.application.form.timezone) }}
+                    </div>
+                    <div class="field-group">
+                        <p>
+                        <label>Local time</label> {{ datetime }}<br/>
+                        <label>Configured timezone:</label> {{ timezone }}<br/>
+                        </p>
+                    </div>
+                </fieldset>
+            </div>
 
             <div id="actions">
                 <div class="pure-control-group">

changedetectionio/templates/watch-overview.html

@@ -24,6 +24,17 @@
         </fieldset>
         <span style="color:#eee; font-size: 80%;"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" /> Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></a></span>
     </form>
+
+    <form class="pure-form" action="{{ url_for('form_watch_list_checkbox_operations') }}" method="POST" id="watch-list-form">
+    <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+    <div id="checkbox-operations">
+        <button class="pure-button button-secondary button-xsmall" style="font-size: 70%"  name="op" value="pause">Pause</button>
+        <button class="pure-button button-secondary button-xsmall" style="font-size: 70%"  name="op" value="unpause">UnPause</button>
+        <button class="pure-button button-secondary button-xsmall" style="font-size: 70%"  name="op" value="mute">Mute</button>
+        <button class="pure-button button-secondary button-xsmall" style="font-size: 70%"  name="op" value="unmute">UnMute</button>
+        <button class="pure-button button-secondary button-xsmall" style="font-size: 70%" name="op" value="notification-default">Use default notification</button>
+        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242; font-size: 70%" name="op" value="delete">Delete</button>
+    </div>
     <div>
         <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag }}">All</a>
         {% for tag in tags %}
@@ -33,7 +44,7 @@
         {% endfor %}
     </div>
 
-    {% set sort_order = request.args.get('order', 'desc') == 'desc' %}
+    {% set sort_order = request.args.get('order', 'asc') == 'asc' %}
     {% set sort_attribute = request.args.get('sort', 'last_changed')   %}
     {% set pagination_page = request.args.get('page', 0) %}
 
@@ -41,12 +52,13 @@
         <table class="pure-table pure-table-striped watch-table">
             <thead>
             <tr>
-                <th>#</th>
+                <th><input style="vertical-align: middle" type="checkbox" id="check-all"/> #</th>
                 <th></th>
-                {% set link_order = "asc" if sort_order else "desc" %}
+                {% set link_order = "desc" if sort_order else "asc" %}
-                <th><a href="{{url_for('index', sort='label', order=link_order)}}">Website</a></th>
+                {% set arrow_span = "" %}
-                <th><a href="{{url_for('index', sort='last_checked', order=link_order)}}">Last Checked</a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('index', sort='label', order=link_order)}}">Website <span class='arrow {{link_order}}'></span></a></th>
-                <th><a href="{{url_for('index', sort='last_changed', order=link_order)}}">Last Changed</a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order)}}">Last Checked <span class='arrow {{link_order}}'></span></a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
                 <th></th>
             </tr>
             </thead>
@@ -65,13 +77,17 @@
                 {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
                 {% if watch.newest_history_key| int > watch.last_viewed and watch.history_n>=2 %}unviewed{% endif %}
                 {% if watch.uuid in queued_uuids %}queued{% endif %}">
-                <td class="inline">{{ loop.index }}</td>
+                <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} "/> <span>{{ loop.index }}</span></td>
                 <td class="inline watch-controls">
-                    <a class="state-{{'on' if watch.paused }}" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks"/></a>
+                    {% if not watch.paused %}
+                    <a class="state-off" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks"/></a>
+                    {% else %}
+                    <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks"/></a>
+                    {% endif %}
                     <a class="state-{{'on' if watch.notification_muted}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications"/></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 class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></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 %}
@@ -128,5 +144,6 @@
          #}
 
     </div>
+    </form>
 </div>
 {% endblock %}

changedetectionio/tests/conftest.py

@@ -41,7 +41,7 @@ def app(request):
 
     cleanup(datastore_path)
 
-    app_config = {'datastore_path': datastore_path}
+    app_config = {'datastore_path': datastore_path, 'disable_checkver' : True}
     cleanup(app_config['datastore_path'])
     datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], include_default_watches=False)
     app = changedetection_app(app_config, datastore)

changedetectionio/tests/fetchers/test_content.py

@@ -2,7 +2,7 @@
 
 import time
 from flask import url_for
-from ..util import live_server_setup
+from ..util import live_server_setup, wait_for_all_checks
 import logging
 
 
@@ -29,14 +29,8 @@ def test_fetch_webdriver_content(client, live_server):
 
     assert b"1 Imported" in res.data
     time.sleep(3)
-    attempt = 0
+
-    while attempt < 20:
+    wait_for_all_checks(client)
-        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(

changedetectionio/tests/proxy_list/__init__.py

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

changedetectionio/tests/proxy_list/conftest.py

@@ -0,0 +1,14 @@
+#!/usr/bin/python3
+
+from .. import conftest
+
+#def pytest_addoption(parser):
+#    parser.addoption("--url_suffix", action="store", default="identifier for request")
+
+
+#def pytest_generate_tests(metafunc):
+#    # This is called for every test. Only get/set command line arguments
+#    # if the argument is specified in the list of test "fixturenames".
+#    option_value = metafunc.config.option.url_suffix
+#    if 'url_suffix' in metafunc.fixturenames and option_value is not None:
+#        metafunc.parametrize("url_suffix", [option_value])

changedetectionio/tests/proxy_list/proxies.json-example

@@ -0,0 +1,10 @@
+{
+  "proxy-one": {
+    "label": "One",
+    "url": "http://127.0.0.1:3128"
+  },
+  "proxy-two": {
+    "label": "two",
+    "url": "http://127.0.0.1:3129"
+  }
+}

changedetectionio/tests/proxy_list/squid.conf

@@ -0,0 +1,41 @@
+acl localnet src 0.0.0.1-0.255.255.255  # RFC 1122 "this" network (LAN)
+acl localnet src 10.0.0.0/8             # RFC 1918 local private network (LAN)
+acl localnet src 100.64.0.0/10          # RFC 6598 shared address space (CGN)
+acl localnet src 169.254.0.0/16         # RFC 3927 link-local (directly plugged) machines
+acl localnet src 172.16.0.0/12          # RFC 1918 local private network (LAN)
+acl localnet src 192.168.0.0/16         # RFC 1918 local private network (LAN)
+acl localnet src fc00::/7               # RFC 4193 local private network range
+acl localnet src fe80::/10              # RFC 4291 link-local (directly plugged) machines
+acl localnet src 159.65.224.174
+acl SSL_ports port 443
+acl Safe_ports port 80          # http
+acl Safe_ports port 21          # ftp
+acl Safe_ports port 443         # https
+acl Safe_ports port 70          # gopher
+acl Safe_ports port 210         # wais
+acl Safe_ports port 1025-65535  # unregistered ports
+acl Safe_ports port 280         # http-mgmt
+acl Safe_ports port 488         # gss-http
+acl Safe_ports port 591         # filemaker
+acl Safe_ports port 777         # multiling http
+acl CONNECT method CONNECT
+
+http_access deny !Safe_ports
+http_access deny CONNECT !SSL_ports
+http_access allow localhost manager
+http_access deny manager
+http_access allow localhost
+http_access allow localnet
+http_access deny all
+http_port 3128
+coredump_dir /var/spool/squid
+refresh_pattern ^ftp:           1440    20%     10080
+refresh_pattern ^gopher:        1440    0%      1440
+refresh_pattern -i (/cgi-bin/|\?) 0     0%      0
+refresh_pattern \/(Packages|Sources)(|\.bz2|\.gz|\.xz)$ 0 0% 0 refresh-ims
+refresh_pattern \/Release(|\.gpg)$ 0 0% 0 refresh-ims
+refresh_pattern \/InRelease$ 0 0% 0 refresh-ims
+refresh_pattern \/(Translation-.*)(|\.bz2|\.gz|\.xz)$ 0 0% 0 refresh-ims
+refresh_pattern .               0       20%     4320
+logfile_rotate 0
+

changedetectionio/tests/proxy_list/test_multiple_proxy.py

@@ -0,0 +1,38 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from ..util import live_server_setup
+
+def test_preferred_proxy(client, live_server):
+    time.sleep(1)
+    live_server_setup(live_server)
+    time.sleep(1)
+    url = "http://chosen.changedetection.io"
+
+    res = client.post(
+        url_for("import_page"),
+        # Because a URL wont show in squid/proxy logs due it being SSLed
+        # Use plain HTTP or a specific domain-name here
+        data={"urls": url},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+
+    time.sleep(2)
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={
+                "include_filters": "",
+                "fetch_backend": "html_requests",
+                "headers": "",
+                "proxy": "proxy-two",
+                "tag": "",
+                "url": url,
+              },
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    time.sleep(2)
+    # Now the request should appear in the second-squid logs

changedetectionio/tests/proxy_list/test_proxy.py

@@ -0,0 +1,19 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+
+# just make a request, we will grep in the docker logs to see it actually got called
+def test_check_basic_change_detection_functionality(client, live_server):
+    live_server_setup(live_server)
+    res = client.post(
+        url_for("import_page"),
+        # Because a URL wont show in squid/proxy logs due it being SSLed
+        # Use plain HTTP or a specific domain-name here
+        data={"urls": "http://one.changedetection.io"},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+    time.sleep(3)

changedetectionio/tests/test_api.py

@@ -147,6 +147,16 @@ def test_api_simple(client, live_server):
     # @todo how to handle None/default global values?
     assert watch['history_n'] == 2, "Found replacement history section, which is in its own API"
 
+    # basic systeminfo check
+    res = client.get(
+        url_for("systeminfo"),
+        headers={'x-api-key': api_key},
+    )
+    info = json.loads(res.data)
+    assert info.get('watch_count') == 1
+    assert info.get('uptime') > 0.5
+
+
     # Finally delete the watch
     res = client.delete(
         url_for("watch", uuid=watch_uuid),

changedetectionio/tests/test_auth.py

@@ -23,7 +23,7 @@ def test_basic_auth(client, live_server):
     # Check form validation
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": "", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"include_filters": "", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data

changedetectionio/tests/test_backend.py

@@ -3,7 +3,7 @@
 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, wait_for_all_checks
 
 sleep_time_for_fetch_thread = 3
 
@@ -36,7 +36,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
         client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
         # Give the thread time to pick it up
-        time.sleep(sleep_time_for_fetch_thread)
+        wait_for_all_checks(client)
 
         # It should report nothing found (no new 'unviewed' class)
         res = client.get(url_for("index"))
@@ -69,7 +69,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
     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)
+    wait_for_all_checks(client)
 
     # Now something should be ready, indicated by having a 'unviewed' class
     res = client.get(url_for("index"))
@@ -98,14 +98,14 @@ def test_check_basic_change_detection_functionality(client, live_server):
     assert b'which has this one new line' in res.data
     assert b'Which is across multiple lines' not in res.data
 
-    time.sleep(2)
+    wait_for_all_checks(client)
 
     # Do this a few times.. ensures we dont accidently set the status
     for n in range(2):
         client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
         # Give the thread time to pick it up
-        time.sleep(sleep_time_for_fetch_thread)
+        wait_for_all_checks(client)
 
         # It should report nothing found (no new 'unviewed' class)
         res = client.get(url_for("index"))
@@ -125,7 +125,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
     )
 
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data

changedetectionio/tests/test_backup.py

@@ -1,18 +1,31 @@
 #!/usr/bin/python3
 
-import time
+from .util import set_original_response, set_modified_response, live_server_setup
 from flask import url_for
 from urllib.request import urlopen
-from . util import set_original_response, set_modified_response, live_server_setup
+from zipfile import ZipFile
+import re
+import time
 
 
 def test_backup(client, live_server):
-
     live_server_setup(live_server)
 
+    set_original_response()
+
     # Give the endpoint time to spin up
     time.sleep(1)
 
+    # Add our URL to the import page
+    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(3)
+
     res = client.get(
         url_for("get_backup"),
         follow_redirects=True
@@ -20,6 +33,19 @@ def test_backup(client, live_server):
 
     # Should get the right zip content type
     assert res.content_type == "application/zip"
+
     # Should be PK/ZIP stream
     assert res.data.count(b'PK') >= 2
 
+    # ZipFile from buffer seems non-obvious, just save it instead
+    with open("download.zip", 'wb') as f:
+        f.write(res.data)
+
+    zip = ZipFile('download.zip')
+    l = zip.namelist()
+    uuid4hex = re.compile('^[a-f0-9]{8}-?[a-f0-9]{4}-?4[a-f0-9]{3}-?[89ab][a-f0-9]{3}-?[a-f0-9]{12}.*txt', re.I)
+    newlist = list(filter(uuid4hex.match, l))  # Read Note below
+
+    # Should be two txt files in the archive (history and the snapshot)
+    assert len(newlist) == 2
+

changedetectionio/tests/test_css_selector.py

@@ -46,22 +46,23 @@ def set_modified_response():
 
 
 # Test that the CSS extraction works how we expect, important here is the right placing of new lines \n's
-def test_css_filter_output():
+def test_include_filters_output():
-    from changedetectionio import fetch_site_status
     from inscriptis import get_text
 
     # Check text with sub-parts renders correctly
     content = """<html> <body><div id="thingthing" >  Some really <b>bold</b> text  </div> </body> </html>"""
-    html_blob = css_filter(css_filter="#thingthing", html_content=content)
+    html_blob = include_filters(include_filters="#thingthing", html_content=content)
     text = get_text(html_blob)
     assert text == "  Some really bold text"
 
     content = """<html> <body>
     <p>foo bar blah</p>
-    <div class="parts">Block A</div> <div class="parts">Block B</div></body> 
+    <DIV class="parts">Block A</DiV> <div class="parts">Block B</DIV></body> 
     </html>
 """
-    html_blob = css_filter(css_filter=".parts", html_content=content)
+
+    # in xPath this would be //*[@class='parts']
+    html_blob = include_filters(include_filters=".parts", html_content=content)
     text = get_text(html_blob)
 
     # Divs are converted to 4 whitespaces by inscriptis
@@ -69,10 +70,10 @@ def test_css_filter_output():
 
 
 # Tests the whole stack works with the CSS Filter
-def test_check_markup_css_filter_restriction(client, live_server):
+def test_check_markup_include_filters_restriction(client, live_server):
     sleep_time_for_fetch_thread = 3
 
-    css_filter = "#sametext"
+    include_filters = "#sametext"
 
     set_original_response()
 
@@ -98,7 +99,7 @@ def test_check_markup_css_filter_restriction(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": css_filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"include_filters": include_filters, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -107,7 +108,7 @@ def test_check_markup_css_filter_restriction(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
-    assert bytes(css_filter.encode('utf-8')) in res.data
+    assert bytes(include_filters.encode('utf-8')) in res.data
 
     # Trigger a check
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
@@ -126,3 +127,58 @@ def test_check_markup_css_filter_restriction(client, live_server):
     # Because it should be looking at only that 'sametext' id
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
+
+
+# Tests the whole stack works with the CSS Filter
+def test_check_multiple_filters(client, live_server):
+    sleep_time_for_fetch_thread = 3
+
+    include_filters = "#blob-a\r\nxpath://*[contains(@id,'blob-b')]"
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write("""<html><body>
+     <div id="blob-a">Blob A</div>
+     <div id="blob-b">Blob B</div>
+     <div id="blob-c">Blob C</div>
+     </body>
+     </html>
+    """)
+
+    # 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)
+
+    # 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={"include_filters": include_filters,
+              "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)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    # Only the two blobs should be here
+    assert b"Blob A" in res.data # CSS was ok
+    assert b"Blob B" in res.data # xPath was ok
+    assert b"Blob C" not in res.data # Should not be included

changedetectionio/tests/test_extract_regex.py

@@ -88,7 +88,7 @@ def test_check_filter_multiline(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": '',
+        data={"include_filters": '',
               'extract_text': '/something.+?6 billion.+?lines/si',
               "url": test_url,
               "tag": "",
@@ -116,7 +116,7 @@ def test_check_filter_multiline(client, live_server):
 
 def test_check_filter_and_regex_extract(client, live_server):
     sleep_time_for_fetch_thread = 3
-    css_filter = ".changetext"
+    include_filters = ".changetext"
 
     set_original_response()
 
@@ -143,7 +143,7 @@ def test_check_filter_and_regex_extract(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": css_filter,
+        data={"include_filters": include_filters,
               '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": "",

changedetectionio/tests/test_filter_exist_changes.py

@@ -92,7 +92,7 @@ def test_filter_doesnt_exist_then_exists_should_get_notification(client, live_se
         "tag": "my tag",
         "title": "my title",
         "headers": "",
-        "css_filter": '.ticket-available',
+        "include_filters": '.ticket-available',
         "fetch_backend": "html_requests"})
 
     res = client.post(

changedetectionio/tests/test_filter_failure_notification.py

@@ -76,7 +76,7 @@ def run_filter_test(client, content_filter):
         "title": "my title",
         "headers": "",
         "filter_failure_notification_send": 'y',
-        "css_filter": content_filter,
+        "include_filters": content_filter,
         "fetch_backend": "html_requests"})
 
     res = client.post(
@@ -95,7 +95,7 @@ def run_filter_test(client, content_filter):
         time.sleep(3)
 
     # We should see something in the frontend
-    assert b'Warning, filter' in res.data
+    assert b'Warning, no filters were found' in res.data
 
     # Now it should exist and contain our "filter not found" alert
     assert os.path.isfile("test-datastore/notification.txt")
@@ -131,7 +131,7 @@ def run_filter_test(client, content_filter):
 def test_setup(live_server):
     live_server_setup(live_server)
 
-def test_check_css_filter_failure_notification(client, live_server):
+def test_check_include_filters_failure_notification(client, live_server):
     set_original_response()
     time.sleep(1)
     run_filter_test(client, '#nope-doesnt-exist')

changedetectionio/tests/test_jinja2.py

@@ -0,0 +1,33 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from .util import live_server_setup
+
+
+# If there was only a change in the whitespacing, then we shouldnt have a change detected
+def test_jinja2_in_url_query(client, live_server):
+    live_server_setup(live_server)
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # Add our URL to the import page
+    test_url = url_for('test_return_query', _external=True)
+
+    # because url_for() will URL-encode the var, but we dont here
+    full_url = "{}?{}".format(test_url,
+                              "date={% now 'Europe/Berlin', '%Y' %}.{% now 'Europe/Berlin', '%m' %}.{% now 'Europe/Berlin', '%d' %}", )
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": full_url, "tag": "test"},
+        follow_redirects=True
+    )
+    assert b"Watch added" in res.data
+    time.sleep(3)
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+    assert b'date=2' in res.data

changedetectionio/tests/test_jsonpath_jq_selector.py

@@ -2,10 +2,15 @@
 # coding=utf-8
 
 import time
-from flask import url_for
+from flask import url_for, escape
 from . util import live_server_setup
 import pytest
+jq_support = True
 
+try:
+    import jq
+except ModuleNotFoundError:
+    jq_support = False
 
 def test_setup(live_server):
     live_server_setup(live_server)
@@ -36,16 +41,28 @@ and it can also be repeated
     from .. import html_tools
 
     # See that we can find the second <script> one, which is not broken, and matches our filter
-    text = html_tools.extract_json_as_string(content, "$.offers.price")
+    text = html_tools.extract_json_as_string(content, "json:$.offers.price")
     assert text == "23.5"
 
-    text = html_tools.extract_json_as_string('{"id":5}', "$.id")
+    # also check for jq
+    if jq_support:
+        text = html_tools.extract_json_as_string(content, "jq:.offers.price")
+        assert text == "23.5"
+
+        text = html_tools.extract_json_as_string('{"id":5}', "jq:.id")
+        assert text == "5"
+
+    text = html_tools.extract_json_as_string('{"id":5}', "json:$.id")
     assert text == "5"
 
     # When nothing at all is found, it should throw JSONNOTFound
     # Which is caught and shown to the user in the watch-overview table
     with pytest.raises(html_tools.JSONNotFound) as e_info:
-        html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "$.id")
+        html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "json:$.id")
+
+    if jq_support:
+        with pytest.raises(html_tools.JSONNotFound) as e_info:
+            html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "jq:.id")
 
 def set_original_ext_response():
     data = """
@@ -66,6 +83,7 @@ def set_original_ext_response():
 
     with open("test-datastore/endpoint-content.txt", "w") as f:
         f.write(data)
+    return None
 
 def set_modified_ext_response():
     data = """
@@ -86,6 +104,7 @@ def set_modified_ext_response():
 
     with open("test-datastore/endpoint-content.txt", "w") as f:
         f.write(data)
+    return None
 
 def set_original_response():
     test_return_data = """
@@ -113,7 +132,7 @@ def set_original_response():
     return None
 
 
-def set_response_with_html():
+def set_json_response_with_html():
     test_return_data = """
     {
       "test": [
@@ -157,7 +176,7 @@ def set_modified_response():
 def test_check_json_without_filter(client, live_server):
     # Request a JSON document from a application/json source containing HTML
     # and be sure it doesn't get chewed up by instriptis
-    set_response_with_html()
+    set_json_response_with_html()
 
     # Give the endpoint time to spin up
     time.sleep(1)
@@ -170,9 +189,6 @@ def test_check_json_without_filter(client, live_server):
         follow_redirects=True
     )
 
-    # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-
     # Give the thread time to pick it up
     time.sleep(3)
 
@@ -181,13 +197,14 @@ def test_check_json_without_filter(client, live_server):
         follow_redirects=True
     )
 
+    # Should still see '"html": "<b>"'
     assert b'&#34;&lt;b&gt;' in res.data
     assert res.data.count(b'{\n') >= 2
 
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
 
-def test_check_json_filter(client, live_server):
+def check_json_filter(json_filter, client, live_server):
-    json_filter = 'json:boss.name'
-
     set_original_response()
 
     # Give the endpoint time to spin up
@@ -202,9 +219,6 @@ def test_check_json_filter(client, live_server):
     )
     assert b"1 Imported" 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(3)
 
@@ -212,7 +226,7 @@ def test_check_json_filter(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": json_filter,
+        data={"include_filters": json_filter,
               "url": test_url,
               "tag": "",
               "headers": "",
@@ -226,10 +240,7 @@ def test_check_json_filter(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
-    assert bytes(json_filter.encode('utf-8')) in res.data
+    assert bytes(escape(json_filter).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(3)
@@ -252,10 +263,17 @@ def test_check_json_filter(client, live_server):
     # And #462 - check we see the proper utf-8 string there
     assert "Örnsköldsvik".encode('utf-8') in res.data
 
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
 
-def test_check_json_filter_bool_val(client, live_server):
+def test_check_jsonpath_filter(client, live_server):
-    json_filter = "json:$['available']"
+    check_json_filter('json:boss.name', client, live_server)
 
+def test_check_jq_filter(client, live_server):
+    if jq_support:
+        check_json_filter('jq:.boss.name', client, live_server)
+
+def check_json_filter_bool_val(json_filter, client, live_server):
     set_original_response()
 
     # Give the endpoint time to spin up
@@ -275,7 +293,7 @@ def test_check_json_filter_bool_val(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": json_filter,
+        data={"include_filters": json_filter,
               "url": test_url,
               "tag": "",
               "headers": "",
@@ -285,11 +303,6 @@ def test_check_json_filter_bool_val(client, live_server):
     )
     assert b"Updated watch." in res.data
 
-    time.sleep(3)
-
-    # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-
     # Give the thread time to pick it up
     time.sleep(3)
     #  Make a change
@@ -304,14 +317,22 @@ def test_check_json_filter_bool_val(client, live_server):
     # But the change should be there, tho its hard to test the change was detected because it will show old and new versions
     assert b'false' in res.data
 
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+def test_check_jsonpath_filter_bool_val(client, live_server):
+    check_json_filter_bool_val("json:$['available']", client, live_server)
+
+def test_check_jq_filter_bool_val(client, live_server):
+    if jq_support:
+        check_json_filter_bool_val("jq:.available", client, live_server)
+
 # Re #265 - Extended JSON selector test
 # Stuff to consider here
 # - Selector should be allowed to return empty when it doesnt match (people might wait for some condition)
 # - The 'diff' tab could show the old and new content
 # - Form should let us enter a selector that doesnt (yet) match anything
-def test_check_json_ext_filter(client, live_server):
+def check_json_ext_filter(json_filter, client, live_server):
-    json_filter = 'json:$[?(@.status==Sold)]'
-
     set_original_ext_response()
 
     # Give the endpoint time to spin up
@@ -326,9 +347,6 @@ def test_check_json_ext_filter(client, live_server):
     )
     assert b"1 Imported" 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(3)
 
@@ -336,7 +354,7 @@ def test_check_json_ext_filter(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": json_filter,
+        data={"include_filters": json_filter,
               "url": test_url,
               "tag": "",
               "headers": "",
@@ -350,10 +368,7 @@ def test_check_json_ext_filter(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
-    assert bytes(json_filter.encode('utf-8')) in res.data
+    assert bytes(escape(json_filter).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(3)
@@ -376,3 +391,12 @@ def test_check_json_ext_filter(client, live_server):
     assert b'ForSale' not in res.data
     assert b'Sold' in res.data
 
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+def test_check_jsonpath_ext_filter(client, live_server):
+    check_json_ext_filter('json:$[?(@.status==Sold)]', client, live_server)
+
+def test_check_jq_ext_filter(client, live_server):
+    if jq_support:
+        check_json_ext_filter('jq:.[] | select(.status | contains("Sold"))', client, live_server)

changedetectionio/tests/test_notification.py

@@ -4,7 +4,13 @@ import re
 from flask import url_for
 from . util import set_original_response, set_modified_response, set_more_modified_response, live_server_setup
 import logging
-from changedetectionio.notification import default_notification_body, default_notification_title
+
+from changedetectionio.notification import (
+    default_notification_body,
+    default_notification_format,
+    default_notification_title,
+    valid_notification_formats,
+)
 
 def test_setup(live_server):
     live_server_setup(live_server)
@@ -20,9 +26,26 @@ def test_check_notification(client, live_server):
 
     # Re 360 - new install should have defaults set
     res = client.get(url_for("settings_page"))
+    notification_url = url_for('test_notification_endpoint', _external=True).replace('http', 'json')
+
     assert default_notification_body.encode() in res.data
     assert default_notification_title.encode() in res.data
 
+    #####################
+    # Set this up for when we remove the notification from the watch, it should fallback with these details
+    res = client.post(
+        url_for("settings_page"),
+        data={"application-notification_urls": notification_url,
+              "application-notification_title": "fallback-title "+default_notification_title,
+              "application-notification_body": "fallback-body "+default_notification_body,
+              "application-notification_format": default_notification_format,
+              "requests-time_between_check-minutes": 180,
+              'application-fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+
+    assert b"Settings updated." in res.data
+
     # When test mode is in BASE_URL env mode, we should see this already configured
     env_base_url = os.getenv('BASE_URL', '').strip()
     if len(env_base_url):
@@ -47,8 +70,6 @@ def test_check_notification(client, live_server):
 
     # 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)
 
@@ -158,6 +179,30 @@ def test_check_notification(client, live_server):
     # be sure we see it in the output log
     assert b'New ChangeDetection.io Notification - ' + test_url.encode('utf-8') in res.data
 
+    set_original_response()
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={
+        "url": test_url,
+        "tag": "my tag",
+        "title": "my title",
+        "notification_urls": '',
+        "notification_title": '',
+        "notification_body": '',
+        "notification_format": default_notification_format,
+        "fetch_backend": "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+
+    time.sleep(2)
+
+    # Verify what was sent as a notification, this file should exist
+    with open("test-datastore/notification.txt", "r") as f:
+        notification_submission = f.read()
+    assert "fallback-title" in notification_submission
+    assert "fallback-body" in notification_submission
+
     # cleanup for the next
     client.get(
         url_for("form_delete", uuid="all"),
@@ -180,20 +225,20 @@ def test_notification_validation(client, live_server):
     assert b"Watch added" in res.data
 
     # Re #360 some validation
-    res = client.post(
+#    res = client.post(
-        url_for("edit_page", uuid="first"),
+#        url_for("edit_page", uuid="first"),
-        data={"notification_urls": 'json://localhost/foobar',
+#        data={"notification_urls": 'json://localhost/foobar',
-              "notification_title": "",
+#              "notification_title": "",
-              "notification_body": "",
+#              "notification_body": "",
-              "notification_format": "Text",
+#              "notification_format": "Text",
-              "url": test_url,
+#              "url": test_url,
-              "tag": "my tag",
+#              "tag": "my tag",
-              "title": "my title",
+#              "title": "my title",
-              "headers": "",
+#              "headers": "",
-              "fetch_backend": "html_requests"},
+#              "fetch_backend": "html_requests"},
-        follow_redirects=True
+#        follow_redirects=True
-    )
+#    )
-    assert b"Notification Body and Title is required when a Notification URL is used" in res.data
+#    assert b"Notification Body and Title is required when a Notification URL is used" in res.data
 
     # Now adding a wrong token should give us an error
     res = client.post(
@@ -215,3 +260,5 @@ def test_notification_validation(client, live_server):
         url_for("form_delete", uuid="all"),
         follow_redirects=True
     )
+
+

changedetectionio/tests/test_share_watch.py

@@ -14,7 +14,7 @@ def test_share_watch(client, live_server):
     live_server_setup(live_server)
 
     test_url = url_for('test_endpoint', _external=True)
-    css_filter = ".nice-filter"
+    include_filters = ".nice-filter"
 
     # Add our URL to the import page
     res = client.post(
@@ -29,7 +29,7 @@ def test_share_watch(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": css_filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"include_filters": include_filters, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -37,7 +37,7 @@ def test_share_watch(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
-    assert bytes(css_filter.encode('utf-8')) in res.data
+    assert bytes(include_filters.encode('utf-8')) in res.data
 
     # click share the link
     res = client.get(
@@ -73,4 +73,8 @@ def test_share_watch(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
-    assert bytes(css_filter.encode('utf-8')) in res.data
+    assert bytes(include_filters.encode('utf-8')) in res.data
+
+    # Check it saved the URL
+    res = client.get(url_for("index"))
+    assert bytes(test_url.encode('utf-8')) in res.data

changedetectionio/tests/test_source.py

@@ -57,10 +57,9 @@ def test_check_basic_change_detection_functionality_source(client, live_server):
 
 
 
-
+# `subtractive_selectors` should still work in `source:` type requests
 def test_check_ignore_elements(client, live_server):
     set_original_response()
-
     time.sleep(2)
     test_url = 'source:'+url_for('test_endpoint', _external=True)
     # Add our URL to the import page
@@ -77,9 +76,9 @@ def test_check_ignore_elements(client, live_server):
     #####################
     # We want <span> and <p> ONLY, but ignore span with .foobar-detection
 
-    res = client.post(
+    client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": 'span,p', "url": test_url, "tag": "", "subtractive_selectors": ".foobar-detection", 'fetch_backend': "html_requests"},
+        data={"include_filters": 'span,p', "url": test_url, "tag": "", "subtractive_selectors": ".foobar-detection", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
 
@@ -89,7 +88,6 @@ def test_check_ignore_elements(client, live_server):
         url_for("preview_page", uuid="first"),
         follow_redirects=True
     )
-
     assert b'foobar-detection' not in res.data
     assert b'&lt;br' not in res.data
     assert b'&lt;p' in res.data

changedetectionio/tests/test_trigger_regex_with_filter.py

@@ -49,7 +49,7 @@ def test_trigger_regex_functionality_with_filter(client, live_server):
         url_for("edit_page", uuid="first"),
         data={"trigger_text": "/cool.stuff/",
               "url": test_url,
-              "css_filter": '#in-here',
+              "include_filters": '#in-here',
               "fetch_backend": "html_requests"},
         follow_redirects=True
     )

changedetectionio/tests/test_watch_fields_storage.py

@@ -22,7 +22,7 @@ def test_check_watch_field_storage(client, live_server):
         url_for("edit_page", uuid="first"),
         data={ "notification_urls": "json://127.0.0.1:30000\r\njson://128.0.0.1\r\n",
                "time_between_check-minutes": 126,
-               "css_filter" : ".fooclass",
+               "include_filters" : ".fooclass",
                "title" : "My title",
                "ignore_text" : "ignore this",
                "url": test_url,

changedetectionio/tests/test_xpath_selector.py

@@ -89,7 +89,7 @@ def test_check_xpath_filter_utf8(client, live_server):
     time.sleep(1)
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"include_filters": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -143,7 +143,7 @@ def test_check_xpath_text_function_utf8(client, live_server):
     time.sleep(1)
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"include_filters": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -182,9 +182,6 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
     )
     assert b"1 Imported" 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)
 
@@ -192,7 +189,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": xpath_filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"include_filters": xpath_filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -230,10 +227,11 @@ def test_xpath_validation(client, live_server):
         follow_redirects=True
     )
     assert b"1 Imported" in res.data
+    time.sleep(2)
 
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"css_filter": "/something horrible", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"include_filters": "/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
@@ -242,7 +240,7 @@ def test_xpath_validation(client, live_server):
 
 
 # actually only really used by the distll.io importer, but could be handy too
-def test_check_with_prefix_css_filter(client, live_server):
+def test_check_with_prefix_include_filters(client, live_server):
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
@@ -263,7 +261,7 @@ def test_check_with_prefix_css_filter(client, live_server):
 
     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"},
+        data={"include_filters":  "xpath://*[contains(@class, 'sametext')]", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
 

changedetectionio/tests/util.py

@@ -2,6 +2,8 @@
 
 from flask import make_response, request
 from flask import url_for
+import logging
+import time
 
 def set_original_response():
     test_return_data = """<html>
@@ -68,6 +70,32 @@ def extract_api_key_from_UI(client):
     api_key = m.group(1)
     return api_key.strip()
 
+
+# kinda funky, but works for now
+def extract_UUID_from_client(client):
+    import re
+    res = client.get(
+        url_for("index"),
+    )
+    # <span id="api-key">{{api_key}}</span>
+
+    m = re.search('edit/(.+?)"', str(res.data))
+    uuid = m.group(1)
+    return uuid.strip()
+
+def wait_for_all_checks(client):
+    # Loop waiting until done..
+    attempt=0
+    time.sleep(0.1)
+    while attempt < 60:
+        time.sleep(1)
+        res = client.get(url_for("index"))
+        if not b'Checking now' in res.data:
+            break
+        logging.getLogger().info("Waiting for watch-list to not say 'Checking now'.. {}".format(attempt))
+
+        attempt += 1
+
 def live_server_setup(live_server):
 
     @live_server.app.route('/test-endpoint')
@@ -132,4 +160,10 @@ def live_server_setup(live_server):
         ret = " ".join([auth.username, auth.password, auth.type])
         return ret
 
+    # Just return some GET var
+    @live_server.app.route('/test-return-query', methods=['GET'])
+    def test_return_query():
+        return request.query_string
+
     live_server.start()
+

changedetectionio/tests/visualselector/__init__.py

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

changedetectionio/tests/visualselector/conftest.py

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

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -0,0 +1,54 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+
+# Add a site in paused mode, add an invalid filter, we should still have visual selector data ready
+def test_visual_selector_content_ready(client, live_server):
+    import os
+    import json
+
+    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
+    live_server_setup(live_server)
+    time.sleep(1)
+
+    # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
+    test_url = "https://changedetection.io/ci-test/test-runjs.html"
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tag": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+        data={
+              "url": test_url,
+              "tag": "",
+              "headers": "",
+              'fetch_backend': "html_webdriver",
+              'webdriver_js_execute_code': 'document.querySelector("button[name=test-button]").click();'
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    time.sleep(1)
+    wait_for_all_checks(client)
+    uuid = extract_UUID_from_client(client)
+
+    # Check the JS execute code before extract worked
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+    assert b'I smell JavaScript' in res.data
+
+    assert os.path.isfile(os.path.join('test-datastore', uuid, 'last-screenshot.png')), "last-screenshot.png should exist"
+    assert os.path.isfile(os.path.join('test-datastore', uuid, 'elements.json')), "xpath elements.json data should exist"
+
+    # Open it and see if it roughly looks correct
+    with open(os.path.join('test-datastore', uuid, 'elements.json'), 'r') as f:
+        json.load(f)

changedetectionio/update_worker.py

@@ -4,18 +4,21 @@ import queue
 import time
 
 from changedetectionio import content_fetcher
-from changedetectionio.html_tools import FilterNotFoundInResponse
+from changedetectionio.fetch_site_status import FilterNotFoundInResponse
 
 # A single update worker
 #
 # Requests for checking on a single site(watch) from a queue of watches
 # (another process inserts watches into the queue that are time-ready for checking)
 
+import logging
+import sys
 
 class update_worker(threading.Thread):
     current_uuid = None
 
     def __init__(self, q, notification_q, app, datastore, *args, **kwargs):
+        logging.basicConfig(stream=sys.stderr, level=logging.DEBUG)
         self.q = q
         self.app = app
         self.notification_q = notification_q
@@ -26,6 +29,10 @@ class update_worker(threading.Thread):
 
         from changedetectionio import diff
 
+        from changedetectionio.notification import (
+            default_notification_format_for_watch
+        )
+
         n_object = {}
         watch = self.datastore.data['watching'].get(watch_uuid, False)
         if not watch:
@@ -40,33 +47,27 @@ class update_worker(threading.Thread):
                 "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?"
             )
 
-        # Did it have any notification alerts to hit?
+        n_object['notification_urls'] = watch['notification_urls'] if len(watch['notification_urls']) else \
-        if len(watch['notification_urls']):
+            self.datastore.data['settings']['application']['notification_urls']
-            print(">>> Notifications queued for UUID from watch {}".format(watch_uuid))
+
-            n_object['notification_urls'] = watch['notification_urls']
+        n_object['notification_title'] = watch['notification_title'] if watch['notification_title'] else \
-            n_object['notification_title'] = watch['notification_title']
+            self.datastore.data['settings']['application']['notification_title']
-            n_object['notification_body'] = watch['notification_body']
+
-            n_object['notification_format'] = watch['notification_format']
+        n_object['notification_body'] = watch['notification_body'] if watch['notification_body'] else \
+            self.datastore.data['settings']['application']['notification_body']
+
+        n_object['notification_format'] = watch['notification_format'] if watch['notification_format'] != default_notification_format_for_watch else \
+            self.datastore.data['settings']['application']['notification_format']
 
-        # No? maybe theres a global setting, queue them all
-        elif len(self.datastore.data['settings']['application']['notification_urls']):
-            print(">>> Watch notification URLs were empty, using GLOBAL notifications for UUID: {}".format(watch_uuid))
-            n_object['notification_urls'] = self.datastore.data['settings']['application']['notification_urls']
-            n_object['notification_title'] = self.datastore.data['settings']['application']['notification_title']
-            n_object['notification_body'] = self.datastore.data['settings']['application']['notification_body']
-            n_object['notification_format'] = self.datastore.data['settings']['application']['notification_format']
-        else:
-            print(">>> NO notifications queued, watch and global notification URLs were empty.")
 
         # Only prepare to notify if the rules above matched
-        if 'notification_urls' in n_object:
+        if 'notification_urls' in n_object and n_object['notification_urls']:
             # HTML needs linebreak, but MarkDown and Text can use a linefeed
             if n_object['notification_format'] == 'HTML':
                 line_feed_sep = "</br>"
             else:
                 line_feed_sep = "\n"
 
-            snapshot_contents = ''
             with open(watch_history[dates[-1]], 'rb') as f:
                 snapshot_contents = f.read()
 
@@ -77,8 +78,10 @@ class update_worker(threading.Thread):
                 'diff': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], line_feed_sep=line_feed_sep),
                 'diff_full': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], True, line_feed_sep=line_feed_sep)
             })
-
+            logging.info (">> SENDING NOTIFICATION")
             self.notification_q.put(n_object)
+        else:
+            logging.info (">> NO Notification sent, notification_url was empty in both watch and system")
 
     def send_filter_failure_notification(self, watch_uuid):
 
@@ -88,8 +91,8 @@ class update_worker(threading.Thread):
             return
 
         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(
+                    'notification_body': "Your configured CSS/xPath filters 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'],
+                        ", ".join(watch['include_filters']),
                         threshold),
                     'notification_format': 'text'}
 
@@ -142,7 +145,7 @@ class update_worker(threading.Thread):
                     now = time.time()
 
                     try:
-                        changed_detected, update_obj, contents, screenshot, xpath_data = update_handler.run(uuid)
+                        changed_detected, update_obj, contents = 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
@@ -183,7 +186,10 @@ class update_worker(threading.Thread):
                         process_changedetection_results = False
 
                     except FilterNotFoundInResponse as e:
-                        err_text = "Warning, filter '{}' not found".format(str(e))
+                        if not self.datastore.data['watching'].get(uuid):
+                            continue
+
+                        err_text = "Warning, no filters were found, no change detection ran."
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            # So that we get a trigger when the content is added again
                                                                            'previous_md5': ''})
@@ -223,6 +229,9 @@ class update_worker(threading.Thread):
                                                                            'last_check_status': e.status_code})
                     except content_fetcher.PageUnloadable as e:
                         err_text = "Page request from server didnt respond correctly"
+                        if e.message:
+                            err_text = "{} - {}".format(err_text, e.message)
+
                         if e.screenshot:
                             self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot, as_error=True)
 
@@ -234,6 +243,9 @@ class update_worker(threading.Thread):
                         # Other serious error
                         process_changedetection_results = False
                     else:
+                        # Crash protection, the watch entry could have been removed by this point (during a slow chrome fetch etc)
+                        if not self.datastore.data['watching'].get(uuid):
+                            continue
 
                         # Mark that we never had any failures
                         if not self.datastore.data['watching'][uuid].get('ignore_status_codes'):
@@ -241,10 +253,6 @@ class update_worker(threading.Thread):
 
                         self.cleanup_error_artifacts(uuid)
 
-                    # Crash protection, the watch entry could have been removed by this point (during a slow chrome fetch etc)
-                    if not self.datastore.data['watching'].get(uuid):
-                        continue
-
                     # Different exceptions mean that we may or may not want to bump the snapshot, trigger notifications etc
                     if process_changedetection_results:
                         try:
@@ -274,16 +282,18 @@ class update_worker(threading.Thread):
                             self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
                             self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
 
-
                     # Always record that we atleast tried
+                    count = self.datastore.data['watching'][uuid].get('check_count', 0) + 1
                     self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
-                                                                       'last_checked': round(time.time())})
+                                                                       'last_checked': round(time.time()),
+                                                                       'check_count': count
+                                                                       })
 
                     # Always save the screenshot if it's available
-                    if screenshot:
+                    if update_handler.screenshot:
-                        self.datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
+                        self.datastore.save_screenshot(watch_uuid=uuid, screenshot=update_handler.screenshot)
-                    if xpath_data:
+                    if update_handler.xpath_data:
-                        self.datastore.save_xpath_data(watch_uuid=uuid, data=xpath_data)
+                        self.datastore.save_xpath_data(watch_uuid=uuid, data=update_handler.xpath_data)
 
 
                 self.current_uuid = None  # Done

docker-compose.yml

@@ -6,6 +6,8 @@ services:
       hostname: changedetection
       volumes:
         - changedetection-data:/datastore
+# Configurable proxy list support, see https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#proxy-list-support
+#        - ./proxies.json:/datastore/proxies.json
 
   #    environment:
   #        Default listening port, can also be changed with the -p option
@@ -30,7 +32,7 @@ services:
   #
   #             https://playwright.dev/python/docs/api/class-browsertype#browser-type-launch-option-proxy
   #
-  #        Plain requsts - proxy support example.
+  #        Plain requests - proxy support example.
   #      - HTTP_PROXY=socks5h://10.10.1.10:1080
   #      - HTTPS_PROXY=socks5h://10.10.1.10:1080
   #
@@ -43,6 +45,9 @@ services:
   #        Respect proxy_pass type settings, `proxy_set_header Host "localhost";` and `proxy_set_header X-Forwarded-Prefix /app;`
   #        More here https://github.com/dgtlmoon/changedetection.io/wiki/Running-changedetection.io-behind-a-reverse-proxy-sub-directory
   #      - USE_X_SETTINGS=1
+  #
+  #        Hides the `Referer` header so that monitored websites can't see the changedetection.io hostname.
+  #      - HIDE_REFERER=true
 
       # Comment out ports: when using behind a reverse proxy , enable networks: etc.
       ports:

requirements.txt

@@ -1,31 +1,36 @@
-flask~= 2.0
+flask~=2.0
 flask_wtf
 eventlet>=0.31.0
 validators
-timeago ~=1.0
+timeago~=1.0
-inscriptis ~= 2.2
+inscriptis~=2.2
-feedgen ~= 0.9
+feedgen~=0.9
-flask-login ~= 0.5
+flask-login~=0.5
 flask_restful
 pytz
 
 # Set these versions together to avoid a RequestsDependencyWarning
-requests[socks] ~= 2.26
+# >= 2.26 also adds Brotli support if brotli is installed
-urllib3 > 1.26
+brotli~=1.0
-chardet > 2.3.0
+requests[socks] ~=2.28
 
-wtforms ~= 3.0
+urllib3>1.26
-jsonpath-ng ~= 1.5.3
+chardet>2.3.0
+
+wtforms~=3.0
+jsonpath-ng~=1.5.3
+
+# jq not available on Windows so must be installed manually
 
 # Notification library
-apprise ~= 1.0.0
+apprise~=1.1.0
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 paho-mqtt
 
 # Pinned version of cryptography otherwise
 # ERROR: Could not build wheels for cryptography which use PEP 517 and cannot be installed directly
-cryptography ~= 3.4
+cryptography~=3.4
 
 # Used for CSS filtering
 bs4
@@ -34,11 +39,20 @@ bs4
 lxml
 
 # 3.141 was missing socksVersion, 3.150 was not in pypi, so we try 4.1.0
-selenium ~= 4.1.0
+selenium~=4.1.0
 
 # https://stackoverflow.com/questions/71652965/importerror-cannot-import-name-safe-str-cmp-from-werkzeug-security/71653849#71653849
 # ImportError: cannot import name 'safe_str_cmp' from 'werkzeug.security'
 # need to revisit flask login versions
-werkzeug ~= 2.0.0
+werkzeug~=2.0.0
+
+# Templating, so far just in the URLs but in the future can be for the notifications also
+jinja2~=3.1
+jinja2-time
+
+# https://peps.python.org/pep-0508/#environment-markers
+# https://github.com/dgtlmoon/changedetection.io/pull/1009
+jq~=1.3 ;python_version >= "3.8" and sys_platform == "linux"
 
 # playwright is installed at Dockerfile build time because it's not available on all platforms
+