Extra validation

.github/workflows/containers.yml

@@ -50,6 +50,7 @@ jobs:
           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: Create release metadata
         run: |
@@ -98,8 +99,6 @@ jobs:
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
-# Looks like this was disabled
-#          provenance: false
 
       # A new tagged release is required, which builds :tag and :latest
       - name: Build and push :tag
@@ -118,8 +117,6 @@ jobs:
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
-# Looks like this was disabled
-#          provenance: false
 
       - name: Image digest
         run: echo step SHA ${{ steps.vars.outputs.sha_short }} tag ${{steps.vars.outputs.tag}} branch ${{steps.vars.outputs.branch}} digest ${{ steps.docker_build.outputs.digest }}

.github/workflows/pypi.yml

@@ -0,0 +1,44 @@
+name: PyPi Test and Push tagged release
+
+# Triggers the workflow on push or pull request events
+on:
+  workflow_run:
+    workflows: ["ChangeDetection.io Test"]
+    tags: '*.*'
+    types: [completed]
+
+
+jobs:
+  test-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
+
+#      - 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: Test that pip builds without error
+        run: |
+          pip3 --version
+          python3 -m pip install wheel
+          python3 setup.py bdist_wheel
+          python3 -m pip install dist/changedetection.io-*-none-any.whl --force
+          changedetection.io -d /tmp -p 10000 &
+          sleep 3
+          curl http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
+          killall -9 changedetection.io
+
+      # 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
+#if: ${{ github.event_name == 'release'}}

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

@@ -10,13 +10,11 @@ on:
     paths:
       - requirements.txt
       - Dockerfile
-      - .github/workflows/*
 
   pull_request:
     paths:
       - requirements.txt
       - Dockerfile
-      - .github/workflows/*
 
   # 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

.github/workflows/test-only.yml

@@ -8,73 +8,32 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
-
-      # Mainly just for link/flake8
-      - name: Set up Python 3.10
+      - name: Set up Python 3.9
         uses: actions/setup-python@v2
         with:
-          python-version: '3.10'
+          python-version: 3.9
+
+      - 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: |
-          pip3 install flake8
           # stop the build if there are Python syntax errors or undefined names
           flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
           # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
           flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
 
-      - name: Spin up ancillary testable services
+      - name: Unit tests
         run: |
-          
-          docker network create changedet-network
+          python3 -m unittest changedetectionio.tests.unit.test_notification_diff
 
-          # Selenium+browserless
-          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome-debug:3.141.59
-          docker run --network changedet-network -d --hostname browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
-
-      - name: Build changedetection.io container for testing
-        run: |         
-          # Build a changedetection.io container and start testing inside
-          docker build . -t test-changedetectionio
-
-      - name: Test built container with pytest
+      - name: Test with pytest
         run: |
-          
-          # Unit tests
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
-          
-          # All tests
-          docker run --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio && ./run_basic_tests.sh'
+          # Each test is totally isolated and performs its own cleanup/reset
+          cd changedetectionio; ./run_all_tests.sh
 
-      - name: Test built container selenium+browserless/playwright
-        run: |
-          
-          # Selenium fetch
-          docker run --rm -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py'
-          
-          # Playwright/Browserless fetch
-          docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
-          
-          # restock detection via playwright - added name=changedet here so that playwright/browserless can connect to it
-          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
 
-      - name: Test proxy interaction
-        run: |
-          cd changedetectionio
-          ./run_proxy_tests.sh
-          cd ..
-
-      - name: Test changedetection.io container starts+runs basically without error
-        run: |
-          docker run -p 5556:5000 -d test-changedetectionio
-          sleep 3
-          # Should return 0 (no error) when grep finds it
-          curl -s http://localhost:5556 |grep -q checkbox-uuid
-          
-          # and IPv6
-          curl -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
-          
-
-#export WEBDRIVER_URL=http://localhost:4444/wd/hub
-#pytest tests/fetchers/test_content.py
-#pytest tests/test_errorhandling.py

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

@@ -1,36 +0,0 @@
-name: ChangeDetection.io PIP package 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]
-
-  # 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-pip-build-basics:
-    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: Test that the basic pip built package runs without error
-          run: |
-            set -e
-            mkdir dist
-            pip3 install wheel
-            python3 setup.py bdist_wheel            
-            pip3 install -r requirements.txt
-            rm ./changedetection.py
-            rm -rf changedetectio
-            
-            pip3 install dist/changedetection.io*.whl
-            changedetection.io -d /tmp -p 10000 &
-            sleep 3
-            curl http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
-            killall -9 changedetection.io

CONTRIBUTING.md

@@ -7,3 +7,9 @@ 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_notification.py` for example
+
+```
+pip3 install -r requirements-dev
+```
+
+this is from https://github.com/dgtlmoon/changedetection.io/blob/master/requirements-dev.txt

Dockerfile

@@ -1,7 +1,7 @@
 # pip dependencies install stage
-FROM python:3.10-slim as builder
+FROM python:3.8-slim as builder
 
-# See `cryptography` pin comment in requirements.txt
+# rustc compiler would be needed on ARM type devices but theres an issue with some deps not building..
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
@@ -29,16 +29,22 @@ RUN pip install --target=/dependencies playwright~=1.27.1 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
-FROM python:3.10-slim
+FROM python:3.8-slim
 
+# Actual packages needed at runtime, usually due to the notification (apprise) backend
+# rustc compiler would be needed on ARM type devices but theres an issue with some deps not building..
+ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
+
+# Re #93, #73, excluding rustc (adds another 430Mb~)
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    libssl1.1 \
-    libxslt1.1 \
-    # For pdftohtml
-    poppler-utils \
-    zlib1g \
-    && apt-get clean && rm -rf /var/lib/apt/lists/*
-
+    g++ \
+    gcc \
+    libc-dev \
+    libffi-dev \
+    libjpeg-dev \
+    libssl-dev \
+    libxslt-dev \
+    zlib1g-dev
 
 # https://stackoverflow.com/questions/58701233/docker-logs-erroneously-appears-empty-until-container-stops
 ENV PYTHONUNBUFFERED=1

MANIFEST.in

@@ -1,11 +1,9 @@
 recursive-include changedetectionio/api *
-recursive-include changedetectionio/blueprint *
-recursive-include changedetectionio/model *
-recursive-include changedetectionio/processors *
-recursive-include changedetectionio/res *
-recursive-include changedetectionio/static *
 recursive-include changedetectionio/templates *
+recursive-include changedetectionio/static *
+recursive-include changedetectionio/model *
 recursive-include changedetectionio/tests *
+recursive-include changedetectionio/res *
 prune changedetectionio/static/package-lock.json
 prune changedetectionio/static/styles/node_modules
 prune changedetectionio/static/styles/package-lock.json

README.md

@@ -1,8 +1,6 @@
-## Web Site Change Detection, Restock monitoring and notifications.
+## Web Site Change Detection, Monitoring and Notification.
 
-**_Detect website content changes and perform meaningful actions - trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._**
-
-_Live your data-life pro-actively._ 
+_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)
@@ -11,7 +9,7 @@ _Live your data-life pro-actively._
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
-[**Don't have time? Let us host it for you! try our $8.99/month subscription - use our proxies and support!**](https://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
+[**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!_
 
 - Chrome browser included.
 - Super fast, no registration needed setup.
@@ -45,11 +43,9 @@ Requires Playwright to be enabled.
 
 - Products and services have a change in pricing
 - _Out of stock notification_ and _Back In stock notification_
-- Monitor and track PDF file changes, know when a PDF file has text changes.
 - Governmental department updates (changes are often only on their websites)
 - New software releases, security advisories when you're not on their mailing list.
 - Festivals with changes
-- Discogs restock alerts and monitoring
 - 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
@@ -64,8 +60,6 @@ Requires Playwright to be enabled.
 - 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)
 - Get notified when certain keywords appear in Twitter search results
 - Proactively search for jobs, get notified when companies update their careers page, search job portals for keywords.
-- Get alerts when new job positions are open on Bamboo HR and other job platforms
-- Website defacement monitoring
 
 _Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
 
@@ -74,7 +68,6 @@ _Need an actual Chrome runner with Javascript support? We support fetching via W
 - 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"
-- Track changes in PDF files (Monitor text changed in the PDF, Also monitor PDF filesize and checksums)
 - 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
@@ -103,8 +96,6 @@ $ docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/d
 
 `:latest` tag is our latest stable release, `:dev` tag is our bleeding edge `master` branch.
 
-Alternative docker repository over at ghcr - [ghcr.io/dgtlmoon/changedetection.io](https://ghcr.io/dgtlmoon/changedetection.io)
-
 ### Windows
 
 See the install instructions at the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Microsoft-Windows
@@ -168,7 +159,7 @@ Just some examples
 
 <img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-notifications.png" style="max-width:100%;" alt="Self-hosted web page change monitoring notifications"  title="Self-hosted web page change monitoring notifications"  />
 
-Now you can also customise your notification content and use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2 templating</a> for their title and body!
+Now you can also customise your notification content!
 
 ## JSON API Monitoring
 
@@ -196,29 +187,11 @@ When you enable a `json:` or `jq:` filter, you can even automatically extract an
 <html>
 ...
 <script type="application/ld+json">
-
-{
-   "@context":"http://schema.org/",
-   "@type":"Product",
-   "offers":{
-      "@type":"Offer",
-      "availability":"http://schema.org/InStock",
-      "price":"3949.99",
-      "priceCurrency":"USD",
-      "url":"https://www.newegg.com/p/3D5-000D-001T1"
-   },
-   "description":"Cobratype King Cobra Hero Desktop Gaming PC",
-   "name":"Cobratype King Cobra Hero Desktop Gaming PC",
-   "sku":"3D5-000D-001T1",
-   "itemCondition":"NewCondition"
-}
+  {"@context":"http://schema.org","@type":"Product","name":"Nan Optipro Stage 1 Baby Formula  800g","price": 23.50 }
 </script>
 ```  
 
-`json:$..price` or `jq:..price` would give `3949.99`, or you can extract the whole structure (use a JSONpath test website to validate with)
-
-The application also supports notifying you that it can follow this information automatically
-
+`json:$.price` or `jq:.price` would give `23.50`, or you can extract the whole structure
 
 ## Proxy Configuration
 
@@ -228,9 +201,6 @@ See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configura
 
 Raspberry Pi and linux/arm/v6 linux/arm/v7 arm64 devices are supported! See the wiki for [details](https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver)
 
-## API Support
-
-Supports managing the website watch list [via our API](https://changedetection.io/docs/api_v1/index.html)
 
 ## Support us
 
@@ -255,5 +225,5 @@ I offer commercial support, this software is depended on by network security, ae
 [test-shield]: https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master
 
 [license-shield]: https://img.shields.io/github/license/dgtlmoon/changedetection.io.svg?style=for-the-badge
-[release-link]: https://github.com/dgtlmoon/changedetection.io/releases
+[release-link]: https://github.com/dgtlmoon.com/changedetection.io/releases
 [docker-link]: https://hub.docker.com/r/dgtlmoon/changedetection.io

changedetection.py

@@ -7,7 +7,7 @@
 
 from changedetectionio import changedetection
 import multiprocessing
-import sys
+import signal
 import os
 
 def sigchld_handler(_signo, _stack_frame):
@@ -35,9 +35,6 @@ if __name__ == '__main__':
     try:
         while True:
             time.sleep(1)
-            if not parse_process.is_alive():
-                # Process died/crashed for some reason, exit with error set
-                sys.exit(1)
 
     except KeyboardInterrupt:
         #parse_process.terminate() not needed, because this process will issue it to the sub-process anyway

changedetectionio/__init__.py

@@ -1,15 +1,5 @@
 #!/usr/bin/python3
 
-from changedetectionio import queuedWatchMetaData
-from copy import deepcopy
-from distutils.util import strtobool
-from feedgen.feed import FeedGenerator
-from flask_compress import Compress as FlaskCompress
-from flask_login import current_user
-from flask_restful import abort, Api
-from flask_wtf import CSRFProtect
-from functools import wraps
-from threading import Event
 import datetime
 import flask_login
 import logging
@@ -20,6 +10,11 @@ import threading
 import time
 import timeago
 
+from copy import deepcopy
+from distutils.util import strtobool
+from feedgen.feed import FeedGenerator
+from threading import Event
+
 from flask import (
     Flask,
     abort,
@@ -32,11 +27,15 @@ from flask import (
     session,
     url_for,
 )
+from flask_compress import Compress as FlaskCompress
+from flask_login import login_required
+from flask_restful import abort, Api
+from flask_wtf import CSRFProtect
 
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.41.1'
+__version__ = '0.39.22.1'
 
 datastore = None
 
@@ -53,6 +52,7 @@ app = Flask(__name__,
             static_url_path="",
             static_folder="static",
             template_folder="templates")
+from flask_compress import Compress
 
 # Super handy for compressing large BrowserSteps responses and others
 FlaskCompress(app)
@@ -64,8 +64,7 @@ app.config.exit = Event()
 
 app.config['NEW_VERSION_AVAILABLE'] = False
 
-if os.getenv('FLASK_SERVER_NAME'):
-    app.config['SERVER_NAME'] = os.getenv('FLASK_SERVER_NAME')
+app.config['LOGIN_DISABLED'] = False
 
 #app.config["EXPLAIN_TEMPLATE_LOADING"] = True
 
@@ -74,6 +73,7 @@ app.config['TEMPLATES_AUTO_RELOAD'] = True
 app.jinja_env.add_extension('jinja2.ext.loopcontrols')
 csrf = CSRFProtect()
 csrf.init_app(app)
+
 notification_debug_log=[]
 
 watch_api = Api(app, decorators=[csrf.exempt])
@@ -95,12 +95,6 @@ def init_app_secret(datastore_path):
 
     return secret
 
-
-@app.template_global()
-def get_darkmode_state():
-    css_dark_mode = request.cookies.get('css_dark_mode', 'false')
-    return 'true' if css_dark_mode and strtobool(css_dark_mode) else 'false'
-
 # We use the whole watch object from the store/JSON so we can see if there's some related status in terms of a thread
 # running or something similar.
 @app.template_filter('format_last_checked_time')
@@ -148,6 +142,7 @@ class User(flask_login.UserMixin):
 
     # Compare given password against JSON store or Env var
     def check_password(self, password):
+
         import base64
         import hashlib
 
@@ -155,9 +150,11 @@ class User(flask_login.UserMixin):
         raw_salt_pass = os.getenv("SALTED_PASS", False)
 
         if not raw_salt_pass:
-            raw_salt_pass = datastore.data['settings']['application'].get('password')
+            raw_salt_pass = datastore.data['settings']['application']['password']
 
         raw_salt_pass = base64.b64decode(raw_salt_pass)
+
+
         salt_from_storage = raw_salt_pass[:32]  # 32 is the length of the salt
 
         # Use the exact same setup you used to generate the key, but this time put in the password to check
@@ -167,44 +164,21 @@ class User(flask_login.UserMixin):
             salt_from_storage,
             100000
         )
-        new_key = salt_from_storage + new_key
+        new_key =  salt_from_storage + new_key
 
         return new_key == raw_salt_pass
 
     pass
 
-
-def login_optionally_required(func):
-    @wraps(func)
-    def decorated_view(*args, **kwargs):
-
-        has_password_enabled = datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False)
-
-        # Permitted
-        if request.endpoint == 'static_content' and request.view_args['group'] == 'styles':
-            return func(*args, **kwargs)
-        # Permitted
-        elif request.endpoint == 'diff_history_page' and datastore.data['settings']['application'].get('shared_diff_access'):
-            return func(*args, **kwargs)
-
-        elif request.method in flask_login.config.EXEMPT_METHODS:
-            return func(*args, **kwargs)
-        elif app.config.get('LOGIN_DISABLED'):
-            return func(*args, **kwargs)
-        elif has_password_enabled and not current_user.is_authenticated:
-            return app.login_manager.unauthorized()
-
-        return func(*args, **kwargs)
-
-    return decorated_view
-
 def changedetection_app(config=None, datastore_o=None):
     global datastore
     datastore = datastore_o
 
     # so far just for read-only via tests, but this will be moved eventually to be the main source
     # (instead of the global var)
-    app.config['DATASTORE'] = datastore_o
+    app.config['DATASTORE']=datastore_o
+
+    #app.config.update(config or {})
 
     login_manager = flask_login.LoginManager(app)
     login_manager.login_view = 'login'
@@ -228,12 +202,14 @@ def changedetection_app(config=None, datastore_o=None):
     watch_api.add_resource(api_v1.SystemInfo, '/api/v1/systeminfo',
                            resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
 
+    def getDarkModeSetting():
+      css_dark_mode = request.cookies.get('css_dark_mode')
+      return True if (css_dark_mode == 'true' or css_dark_mode == True) else False
+
     # Setup cors headers to allow all domains
     # https://flask-cors.readthedocs.io/en/latest/
     #    CORS(app)
 
-
-
     @login_manager.user_loader
     def user_loader(email):
         user = User()
@@ -242,7 +218,7 @@ def changedetection_app(config=None, datastore_o=None):
 
     @login_manager.unauthorized_handler
     def unauthorized_handler():
-        flash("You must be logged in, please log in.", 'error')
+        # @todo validate its a URL of this host and use that
         return redirect(url_for('login', next=url_for('index')))
 
     @app.route('/logout')
@@ -255,6 +231,10 @@ def changedetection_app(config=None, datastore_o=None):
     @app.route('/login', methods=['GET', 'POST'])
     def login():
 
+        if not datastore.data['settings']['application']['password'] and not os.getenv("SALTED_PASS", False):
+            flash("Login not required, no password enabled.", "notice")
+            return redirect(url_for('index'))
+
         if request.method == 'GET':
             if flask_login.current_user.is_authenticated:
                 flash("Already logged in")
@@ -289,22 +269,27 @@ def changedetection_app(config=None, datastore_o=None):
         return redirect(url_for('login'))
 
     @app.before_request
-    def before_request_handle_cookie_x_settings():
+    def do_something_whenever_a_request_comes_in():
+
+        # Disable password login if there is not one set
+        # (No password in settings or env var)
+        app.config['LOGIN_DISABLED'] = datastore.data['settings']['application']['password'] == False and os.getenv("SALTED_PASS", False) == False
+
         # Set the auth cookie path if we're running as X-settings/X-Forwarded-Prefix
         if os.getenv('USE_X_SETTINGS') and 'X-Forwarded-Prefix' in request.headers:
             app.config['REMEMBER_COOKIE_PATH'] = request.headers['X-Forwarded-Prefix']
             app.config['SESSION_COOKIE_PATH'] = request.headers['X-Forwarded-Prefix']
 
-        return None
+        # For the RSS path, allow access via a token
+        if request.path == '/rss' and request.args.get('token'):
+            app_rss_token = datastore.data['settings']['application']['rss_access_token']
+            rss_url_token = request.args.get('token')
+            if app_rss_token == rss_url_token:
+                app.config['LOGIN_DISABLED'] = True
 
     @app.route("/rss", methods=['GET'])
+    @login_required
     def rss():
-        # Always requires token set
-        app_rss_token = datastore.data['settings']['application'].get('rss_access_token')
-        rss_url_token = request.args.get('token')
-        if rss_url_token != app_rss_token:
-            return "Access denied, bad token", 403
-
         from . import diff
         limit_tag = request.args.get('tag')
 
@@ -340,6 +325,8 @@ def changedetection_app(config=None, datastore_o=None):
             if len(dates) < 2:
                 continue
 
+            prev_fname = watch.history[dates[-2]]
+
             if not watch.viewed:
                 # Re #239 - GUID needs to be individual for each event
                 # @todo In the future make this a configurable link back (see work on BASE_URL https://github.com/dgtlmoon/changedetection.io/pull/228)
@@ -360,12 +347,9 @@ def changedetection_app(config=None, datastore_o=None):
 
                 watch_title = watch.get('title') if watch.get('title') else watch.get('url')
                 fe.title(title=watch_title)
+                latest_fname = watch.history[dates[-1]]
 
-                html_diff = diff.render_diff(previous_version_file_contents=watch.get_history_snapshot(dates[-2]),
-                                             newest_version_file_contents=watch.get_history_snapshot(dates[-1]),
-                                             include_equal=False,
-                                             line_feed_sep="<br>")
-
+                html_diff = diff.render_diff(prev_fname, latest_fname, include_equal=False, line_feed_sep="</br>")
                 fe.content(content="<html><body><h4>{}</h4>{}</body></html>".format(watch_title, html_diff),
                            type='CDATA')
 
@@ -379,7 +363,7 @@ def changedetection_app(config=None, datastore_o=None):
         return response
 
     @app.route("/", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def index():
         from changedetectionio import forms
 
@@ -392,9 +376,9 @@ def changedetection_app(config=None, datastore_o=None):
         if op:
             uuid = request.args.get('uuid')
             if op == 'pause':
-                datastore.data['watching'][uuid].toggle_pause()
+                datastore.data['watching'][uuid]['paused'] ^= True
             elif op == 'mute':
-                datastore.data['watching'][uuid].toggle_mute()
+                datastore.data['watching'][uuid]['notification_muted'] ^= True
 
             datastore.needs_write = True
             return redirect(url_for('index', tag = limit_tag))
@@ -418,22 +402,20 @@ def changedetection_app(config=None, datastore_o=None):
                 sorted_watches.append(watch)
 
         existing_tags = datastore.get_all_tags()
+
         form = forms.quickWatchForm(request.form)
-        output = render_template(
-            "watch-overview.html",
-                                 # Don't link to hosting when we're on the hosting environment
+        output = render_template("watch-overview.html",
+                                 dark_mode=getDarkModeSetting(),
+                                 form=form,
+                                 watches=sorted_watches,
+                                 tags=existing_tags,
                                  active_tag=limit_tag,
                                  app_rss_token=datastore.data['settings']['application']['rss_access_token'],
-                                 form=form,
-                                 guid=datastore.data['app_guid'],
-                                 has_proxies=datastore.proxy_list,
                                  has_unviewed=datastore.has_unviewed,
+                                 # Don't link to hosting when we're on the hosting environment
                                  hosted_sticky=os.getenv("SALTED_PASS", False) == False,
-                                 queued_uuids=[q_uuid.item['uuid'] for q_uuid in update_q.queue],
-                                 system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),
-                                 tags=existing_tags,
-                                 watches=sorted_watches
-                                 )
+                                 guid=datastore.data['app_guid'],
+                                 queued_uuids=[uuid for p,uuid in update_q.queue])
 
 
         if session.get('share-link'):
@@ -443,7 +425,7 @@ def changedetection_app(config=None, datastore_o=None):
 
     # AJAX endpoint for sending a test
     @app.route("/notification/send-test", methods=['POST'])
-    @login_optionally_required
+    @login_required
     def ajax_callback_send_notification_test():
 
         import apprise
@@ -476,7 +458,7 @@ def changedetection_app(config=None, datastore_o=None):
 
 
     @app.route("/clear_history/<string:uuid>", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def clear_watch_history(uuid):
         try:
             datastore.clear_watch_history(uuid)
@@ -488,7 +470,7 @@ def changedetection_app(config=None, datastore_o=None):
         return redirect(url_for('index'))
 
     @app.route("/clear_history", methods=['GET', 'POST'])
-    @login_optionally_required
+    @login_required
     def clear_all_history():
 
         if request.method == 'POST':
@@ -509,15 +491,49 @@ def changedetection_app(config=None, datastore_o=None):
         output = render_template("clear_all_history.html")
         return output
 
+
+    # If they edited an existing watch, we need to know to reset the current/previous md5 to include
+    # the excluded text.
+    def get_current_checksum_include_ignore_text(uuid):
+
+        import hashlib
+
+        from changedetectionio import fetch_site_status
+
+        # Get the most recent one
+        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:
+            newest_history_key = list(datastore.data['watching'][uuid].history.keys())[0]
+
+        if newest_history_key:
+            with open(datastore.data['watching'][uuid].history[newest_history_key],
+                      encoding='utf-8') as file:
+                raw_content = file.read()
+
+                handler = fetch_site_status.perform_site_check(datastore=datastore)
+                stripped_content = html_tools.strip_ignore_text(raw_content,
+                                                             datastore.data['watching'][uuid]['ignore_text'])
+
+                if datastore.data['settings']['application'].get('ignore_whitespace', False):
+                    checksum = hashlib.md5(stripped_content.translate(None, b'\r\n\t ')).hexdigest()
+                else:
+                    checksum = hashlib.md5(stripped_content).hexdigest()
+
+                return checksum
+
+        return datastore.data['watching'][uuid]['previous_md5']
+
+
     @app.route("/edit/<string:uuid>", methods=['GET', 'POST'])
-    @login_optionally_required
+    @login_required
     # https://stackoverflow.com/questions/42984453/wtforms-populate-form-with-data-if-data-exists
     # https://wtforms.readthedocs.io/en/3.0.x/forms/#wtforms.form.Form.populate_obj ?
 
     def edit_page(uuid):
-        from . import forms
-        from .blueprint.browser_steps.browser_steps import browser_step_ui_config
-        from . import processors
+        from changedetectionio import forms
+        from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
 
         using_default_check_time = True
         # More for testing, possible to return the first/only
@@ -532,15 +548,6 @@ def changedetection_app(config=None, datastore_o=None):
             flash("No watch with the UUID %s found." % (uuid), "error")
             return redirect(url_for('index'))
 
-        switch_processor = request.args.get('switch_processor')
-        if switch_processor:
-            for p in processors.available_processors():
-                if p[0] == switch_processor:
-                    datastore.data['watching'][uuid]['processor'] = switch_processor
-                    flash(f"Switched to mode - {p[1]}.")
-                    datastore.clear_watch_history(uuid)
-                    redirect(url_for('edit_page', uuid=uuid))
-
         # be sure we update with a copy instead of accidently editing the live object by reference
         default = deepcopy(datastore.data['watching'][uuid])
 
@@ -560,8 +567,6 @@ def changedetection_app(config=None, datastore_o=None):
                                data=default,
                                )
 
-        form.fetch_backend.choices.append(("system", 'System settings default'))
-
         # form.browser_steps[0] can be assumed that we 'goto url' first
 
         if datastore.proxy_list is None:
@@ -574,7 +579,6 @@ def changedetection_app(config=None, datastore_o=None):
 
 
         if request.method == 'POST' and form.validate():
-
             extra_update_obj = {}
 
             if request.args.get('unpause_on_save'):
@@ -591,26 +595,29 @@ def changedetection_app(config=None, datastore_o=None):
                     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
 
 
              # Ignore text
             form_ignore_text = form.ignore_text.data
             datastore.data['watching'][uuid]['ignore_text'] = form_ignore_text
 
+            # Reset the previous_md5 so we process a new snapshot including stripping ignore text.
+            if form_ignore_text:
+                if len(datastore.data['watching'][uuid].history):
+                    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.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)
+
             # Be sure proxy value is None
             if datastore.proxy_list is not None and form.data['proxy'] == '':
                 extra_update_obj['proxy'] = None
 
-            # Unsetting all filter_text methods should make it go back to default
-            # This particularly affects tests running
-            if 'filter_text_added' in form.data and not form.data.get('filter_text_added') \
-                    and 'filter_text_replaced' in form.data and not form.data.get('filter_text_replaced') \
-                    and 'filter_text_removed' in form.data and not form.data.get('filter_text_removed'):
-                extra_update_obj['filter_text_added'] = True
-                extra_update_obj['filter_text_replaced'] = True
-                extra_update_obj['filter_text_removed'] = True
-
-
             datastore.data['watching'][uuid].update(form.data)
             datastore.data['watching'][uuid].update(extra_update_obj)
 
@@ -624,7 +631,7 @@ def changedetection_app(config=None, datastore_o=None):
             datastore.needs_write_urgent = True
 
             # Queue the watch for immediate recheck, with a higher priority
-            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+            update_q.put((1, uuid))
 
             # Diff page [edit] link should go back to diff page
             if request.args.get("next") and request.args.get("next") == 'diff':
@@ -638,6 +645,8 @@ def changedetection_app(config=None, datastore_o=None):
 
             visualselector_data_is_ready = datastore.visualselector_data_is_ready(uuid)
 
+            # Only works reliably with Playwright
+            visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and default['fetch_backend'] == 'html_webdriver'
 
             # JQ is difficult to install on windows and must be manually added (outside requirements.txt)
             jq_support = True
@@ -648,19 +657,14 @@ def changedetection_app(config=None, datastore_o=None):
 
             watch = datastore.data['watching'].get(uuid)
             system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
-
-            is_html_webdriver = False
-            if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
-                is_html_webdriver = True
-
-            # Only works reliably with Playwright
-            visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and is_html_webdriver
+            is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
+                    watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
 
             output = render_template("edit.html",
-                                     available_processors=processors.available_processors(),
                                      browser_steps_config=browser_step_ui_config,
                                      current_base_url=datastore.data['settings']['application']['base_url'],
                                      emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
+                                     dark_mode=getDarkModeSetting(),
                                      form=form,
                                      has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
                                      has_empty_checktime=using_default_check_time,
@@ -677,9 +681,9 @@ def changedetection_app(config=None, datastore_o=None):
         return output
 
     @app.route("/settings", methods=['GET', "POST"])
-    @login_optionally_required
+    @login_required
     def settings_page():
-        from . import forms
+        from changedetectionio import content_fetcher, forms
 
         default = deepcopy(datastore.data['settings'])
         if datastore.proxy_list is not None:
@@ -748,6 +752,7 @@ def changedetection_app(config=None, datastore_o=None):
 
         output = render_template("settings.html",
                                  form=form,
+                                 dark_mode=getDarkModeSetting(),
                                  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'),
@@ -757,11 +762,9 @@ def changedetection_app(config=None, datastore_o=None):
         return output
 
     @app.route("/import", methods=['GET', "POST"])
-    @login_optionally_required
+    @login_required
     def import_page():
         remaining_urls = []
-        from . import forms
-
         if request.method == 'POST':
             from .importer import import_url_list, import_distill_io_json
 
@@ -769,9 +772,9 @@ def changedetection_app(config=None, datastore_o=None):
             if request.values.get('urls') and len(request.values.get('urls').strip()):
                 # Import and push into the queue for immediate update check
                 importer = import_url_list()
-                importer.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor'))
+                importer.run(data=request.values.get('urls'), flash=flash, datastore=datastore)
                 for uuid in importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put((1, uuid))
 
                 if len(importer.remaining_data) == 0:
                     return redirect(url_for('index'))
@@ -784,15 +787,13 @@ def changedetection_app(config=None, datastore_o=None):
                 d_importer = import_distill_io_json()
                 d_importer.run(data=request.values.get('distill-io'), flash=flash, datastore=datastore)
                 for uuid in d_importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put((1, uuid))
+
 
 
-        form = forms.importForm(formdata=request.form if request.method == 'POST' else None,
-#                               data=default,
-                               )
         # Could be some remaining, or we could be on GET
         output = render_template("import.html",
-                                 form=form,
+                                 dark_mode=getDarkModeSetting(),
                                  import_url_list_remaining="\n".join(remaining_urls),
                                  original_distill_json=''
                                  )
@@ -800,7 +801,7 @@ def changedetection_app(config=None, datastore_o=None):
 
     # Clear all statuses, so we do not see the 'unviewed' class
     @app.route("/form/mark-all-viewed", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def mark_all_viewed():
 
         # Save the current newest history as the most recently viewed
@@ -810,7 +811,7 @@ def changedetection_app(config=None, datastore_o=None):
         return redirect(url_for('index'))
 
     @app.route("/diff/<string:uuid>", methods=['GET', 'POST'])
-    @login_optionally_required
+    @login_required
     def diff_history_page(uuid):
 
         from changedetectionio import forms
@@ -858,39 +859,41 @@ def changedetection_app(config=None, datastore_o=None):
         # Save the current newest history as the most recently viewed
         datastore.set_last_viewed(uuid, time.time())
 
+        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:
-            newest_version_file_contents = watch.get_history_snapshot(dates[-1])
+            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(dates[-1])
+            newest_version_file_contents = "Unable to read {}.\n".format(newest_file)
 
         previous_version = request.args.get('previous_version')
-        previous_timestamp = dates[-2]
-        if previous_version:
-            previous_timestamp = previous_version
+        try:
+            previous_file = history[previous_version]
+        except KeyError:
+            # Not present, use a default value, the second one in the sorted list.
+            previous_file = history[dates[-2]]
 
         try:
-            previous_version_file_contents = watch.get_history_snapshot(previous_timestamp)
+            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_timestamp)
+            previous_version_file_contents = "Unable to read {}.\n".format(previous_file)
 
 
         screenshot_url = watch.get_screenshot()
 
         system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
 
-        is_html_webdriver = False
-        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
-            is_html_webdriver = True
-
-        password_enabled_and_share_is_off = False
-        if datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False):
-            password_enabled_and_share_is_off = not datastore.data['settings']['application'].get('shared_diff_access')
+        is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
+                    watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
 
         output = render_template("diff.html",
                                  current_diff_url=watch['url'],
                                  current_previous_version=str(previous_version),
+                                 dark_mode=getDarkModeSetting(),
                                  extra_stylesheets=extra_stylesheets,
                                  extra_title=" - Diff - {}".format(watch['title'] if watch['title'] else watch['url']),
                                  extract_form=extract_form,
@@ -901,7 +904,6 @@ def changedetection_app(config=None, datastore_o=None):
                                  left_sticky=True,
                                  newest=newest_version_file_contents,
                                  newest_version_timestamp=dates[-1],
-                                 password_enabled_and_share_is_off=password_enabled_and_share_is_off,
                                  previous=previous_version_file_contents,
                                  screenshot=screenshot_url,
                                  uuid=uuid,
@@ -912,7 +914,7 @@ def changedetection_app(config=None, datastore_o=None):
         return output
 
     @app.route("/preview/<string:uuid>", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def preview_page(uuid):
         content = []
         ignored_line_numbers = []
@@ -932,9 +934,8 @@ def changedetection_app(config=None, datastore_o=None):
         extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
 
 
-        is_html_webdriver = False
-        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
-            is_html_webdriver = True
+        is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
+                watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
 
         # Never requested successfully, but we detected a fetch error
         if datastore.data['watching'][uuid].history_n == 0 and (watch.get_error_text() or watch.get_error_snapshot()):
@@ -943,6 +944,7 @@ def changedetection_app(config=None, datastore_o=None):
                                      content=content,
                                      history_n=watch.history_n,
                                      extra_stylesheets=extra_stylesheets,
+                                     dark_mode=getDarkModeSetting(),
 #                                     current_diff_url=watch['url'],
                                      watch=watch,
                                      uuid=uuid,
@@ -953,40 +955,43 @@ def changedetection_app(config=None, datastore_o=None):
             return output
 
         timestamp = list(watch.history.keys())[-1]
+        filename = watch.history[timestamp]
         try:
-            tmp = watch.get_history_snapshot(timestamp).splitlines()
+            with open(filename, 'r', encoding='utf-8', errors='ignore') as f:
+                tmp = f.readlines()
 
-            # Get what needs to be highlighted
-            ignore_rules = watch.get('ignore_text', []) + datastore.data['settings']['application']['global_ignore_text']
+                # Get what needs to be highlighted
+                ignore_rules = watch.get('ignore_text', []) + datastore.data['settings']['application']['global_ignore_text']
 
-            # .readlines will keep the \n, but we will parse it here again, in the future tidy this up
-            ignored_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
-                                                                wordlist=ignore_rules,
-                                                                mode='line numbers'
-                                                                )
+                # .readlines will keep the \n, but we will parse it here again, in the future tidy this up
+                ignored_line_numbers = html_tools.strip_ignore_text(content="".join(tmp),
+                                                                    wordlist=ignore_rules,
+                                                                    mode='line numbers'
+                                                                    )
 
-            trigger_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
-                                                                wordlist=watch['trigger_text'],
-                                                                mode='line numbers'
-                                                                )
-            # Prepare the classes and lines used in the template
-            i=0
-            for l in tmp:
-                classes=[]
-                i+=1
-                if i in ignored_line_numbers:
-                    classes.append('ignored')
-                if i in trigger_line_numbers:
-                    classes.append('triggered')
-                content.append({'line': l, 'classes': ' '.join(classes)})
+                trigger_line_numbers = html_tools.strip_ignore_text(content="".join(tmp),
+                                                                    wordlist=watch['trigger_text'],
+                                                                    mode='line numbers'
+                                                                    )
+                # Prepare the classes and lines used in the template
+                i=0
+                for l in tmp:
+                    classes=[]
+                    i+=1
+                    if i in ignored_line_numbers:
+                        classes.append('ignored')
+                    if i in trigger_line_numbers:
+                        classes.append('triggered')
+                    content.append({'line': l, 'classes': ' '.join(classes)})
 
         except Exception as e:
-            content.append({'line': f"File doesnt exist or unable to read timestamp {timestamp}", 'classes': ''})
+            content.append({'line': "File doesnt exist or unable to read file {}".format(filename), 'classes': ''})
 
         output = render_template("preview.html",
                                  content=content,
                                  history_n=watch.history_n,
                                  extra_stylesheets=extra_stylesheets,
+                                 dark_mode=getDarkModeSetting(),
                                  ignored_line_numbers=ignored_line_numbers,
                                  triggered_line_numbers=trigger_line_numbers,
                                  current_diff_url=watch['url'],
@@ -1001,17 +1006,22 @@ def changedetection_app(config=None, datastore_o=None):
         return output
 
     @app.route("/settings/notification-logs", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def notification_logs():
         global notification_debug_log
         output = render_template("notification-log.html",
+                                 dark_mode=getDarkModeSetting(),
                                  logs=notification_debug_log if len(notification_debug_log) else ["Notification logs are empty - no notifications sent yet."])
 
         return output
 
+    @app.route("/favicon.ico", methods=['GET'])
+    def favicon():
+        return send_from_directory("static/images", path="favicon.ico")
+
     # We're good but backups are even better!
     @app.route("/backup", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def get_backup():
 
         import zipfile
@@ -1023,8 +1033,7 @@ def changedetection_app(config=None, datastore_o=None):
             os.unlink(previous_backup_filename)
 
         # create a ZipFile object
-        timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
-        backupname = "changedetection-backup-{}.zip".format(timestamp)
+        backupname = "changedetection-backup-{}.zip".format(int(time.time()))
         backup_filepath = os.path.join(datastore_o.datastore_path, backupname)
 
         with zipfile.ZipFile(backup_filepath, "w",
@@ -1132,14 +1141,13 @@ def changedetection_app(config=None, datastore_o=None):
             abort(404)
 
     @app.route("/form/add/quickwatch", methods=['POST'])
-    @login_optionally_required
+    @login_required
     def form_quick_watch_add():
         from changedetectionio import forms
         form = forms.quickWatchForm(request.form)
 
         if not form.validate():
-            for widget, l in form.errors.items():
-                flash(','.join(l), 'error')
+            flash("Error")
             return redirect(url_for('index'))
 
         url = request.form.get('url').strip()
@@ -1148,24 +1156,24 @@ def changedetection_app(config=None, datastore_o=None):
             return redirect(url_for('index'))
 
         add_paused = request.form.get('edit_and_watch_submit_button') != None
-        processor = request.form.get('processor', 'text_json_diff')
-        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tag').strip(), extras={'paused': add_paused, 'processor': processor})
+        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tag').strip(), extras={'paused': add_paused})
 
-        if new_uuid:
-            if add_paused:
-                flash('Watch added in Paused state, saving will unpause.')
-                return redirect(url_for('edit_page', uuid=new_uuid, unpause_on_save=1))
-            else:
-                # Straight into the queue.
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
-                flash("Watch added.")
+
+        if not add_paused and new_uuid:
+            # Straight into the queue.
+            update_q.put((1, new_uuid))
+            flash("Watch added.")
+
+        if add_paused:
+            flash('Watch added in Paused state, saving will unpause.')
+            return redirect(url_for('edit_page', uuid=new_uuid, unpause_on_save=1))
 
         return redirect(url_for('index'))
 
 
 
     @app.route("/api/delete", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def form_delete():
         uuid = request.args.get('uuid')
 
@@ -1182,7 +1190,7 @@ def changedetection_app(config=None, datastore_o=None):
         return redirect(url_for('index'))
 
     @app.route("/api/clone", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def form_clone():
         uuid = request.args.get('uuid')
         # More for testing, possible to return the first/only
@@ -1190,17 +1198,15 @@ def changedetection_app(config=None, datastore_o=None):
             uuid = list(datastore.data['watching'].keys()).pop()
 
         new_uuid = datastore.clone(uuid)
-        if new_uuid:
-            if not datastore.data['watching'].get(uuid).get('paused'):
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
-            flash('Cloned.')
+        update_q.put((5, new_uuid))
+        flash('Cloned.')
 
         return redirect(url_for('index'))
 
     @app.route("/api/checknow", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def form_watch_checknow():
-        # Forced recheck will skip the 'skip if content is the same' rule (, 'reprocess_existing_data': True})))
+
         tag = request.args.get('tag')
         uuid = request.args.get('uuid')
         i = 0
@@ -1209,9 +1215,11 @@ def changedetection_app(config=None, datastore_o=None):
         for t in running_update_threads:
             running_uuids.append(t.current_uuid)
 
+        # @todo check thread is running and skip
+
         if uuid:
             if uuid not in running_uuids:
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+                update_q.put((1, uuid))
             i = 1
 
         elif tag != None:
@@ -1219,20 +1227,20 @@ def changedetection_app(config=None, datastore_o=None):
             for watch_uuid, watch in datastore.data['watching'].items():
                 if (tag != None and tag in watch['tag']):
                     if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
-                        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False}))
+                        update_q.put((1, watch_uuid))
                         i += 1
 
         else:
             # No tag, no uuid, add everything.
             for watch_uuid, watch in datastore.data['watching'].items():
                 if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False}))
+                    update_q.put((1, watch_uuid))
                     i += 1
-        flash("{} watches queued for rechecking.".format(i))
+        flash("{} watches are queued for rechecking.".format(i))
         return redirect(url_for('index', tag=tag))
 
     @app.route("/form/checkbox-operations", methods=['POST'])
-    @login_optionally_required
+    @login_required
     def form_watch_list_checkbox_operations():
         op = request.form['op']
         uuids = request.form.getlist('uuids')
@@ -1249,6 +1257,7 @@ def changedetection_app(config=None, datastore_o=None):
                 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'):
@@ -1272,14 +1281,6 @@ def changedetection_app(config=None, datastore_o=None):
                     datastore.data['watching'][uuid.strip()]['notification_muted'] = False
             flash("{} watches un-muted".format(len(uuids)))
 
-        elif (op == 'recheck'):
-            for uuid in uuids:
-                uuid = uuid.strip()
-                if datastore.data['watching'].get(uuid):
-                    # Recheck and require a full reprocessing
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
-            flash("{} watches queued for rechecking".format(len(uuids)))
-
         elif (op == 'notification-default'):
             from changedetectionio.notification import (
                 default_notification_format_for_watch
@@ -1296,7 +1297,7 @@ def changedetection_app(config=None, datastore_o=None):
         return redirect(url_for('index'))
 
     @app.route("/api/share-url", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def form_share_put_watch():
         """Given a watch UUID, upload the info and return a share-link
            the share-link can be imported/added"""
@@ -1352,10 +1353,6 @@ def changedetection_app(config=None, datastore_o=None):
     import changedetectionio.blueprint.browser_steps as browser_steps
     app.register_blueprint(browser_steps.construct_blueprint(datastore), url_prefix='/browser-steps')
 
-    import changedetectionio.blueprint.price_data_follower as price_data_follower
-    app.register_blueprint(price_data_follower.construct_blueprint(datastore, update_q), url_prefix='/price_data_follower')
-
-
     # @todo handle ctrl break
     ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks).start()
     threading.Thread(target=notification_runner).start()
@@ -1461,11 +1458,7 @@ def ticker_thread_check_time_launch_checks():
         watch_uuid_list = []
         while True:
             try:
-                # Get a list of watches sorted by last_checked, [1] because it gets passed a tuple
-                # This is so we examine the most over-due first
-                for k in sorted(datastore.data['watching'].items(), key=lambda item: item[1].get('last_checked',0)):
-                    watch_uuid_list.append(k[0])
-
+                watch_uuid_list = datastore.data['watching'].keys()
             except RuntimeError as e:
                 # RuntimeError: dictionary changed size during iteration
                 time.sleep(0.1)
@@ -1505,7 +1498,7 @@ def ticker_thread_check_time_launch_checks():
             seconds_since_last_recheck = now - watch['last_checked']
 
             if seconds_since_last_recheck >= (threshold + watch.jitter_seconds) and seconds_since_last_recheck >= recheck_time_minimum_seconds:
-                if not uuid in running_uuids and uuid not in [q_uuid.item['uuid'] for q_uuid in update_q.queue]:
+                if not uuid in running_uuids and uuid not in [q_uuid for p,q_uuid in update_q.queue]:
 
                     # Proxies can be set to have a limit on seconds between which they can be called
                     watch_proxy = datastore.get_preferred_proxy_for_watch(uuid=uuid)
@@ -1536,9 +1529,8 @@ def ticker_thread_check_time_launch_checks():
                             priority,
                             watch.jitter_seconds,
                             now - watch['last_checked']))
-
                     # Into the queue with you
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=priority, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put((priority, uuid))
 
                     # Reset for next time
                     watch.jitter_seconds = 0

changedetectionio/api/api_schema.py

@@ -1,117 +0,0 @@
-# Responsible for building the storage dict into a set of rules ("JSON Schema") acceptable via the API
-# Probably other ways to solve this when the backend switches to some ORM
-
-def build_time_between_check_json_schema():
-    # Setup time between check schema
-    schema_properties_time_between_check = {
-        "type": "object",
-        "additionalProperties": False,
-        "properties": {}
-    }
-    for p in ['weeks', 'days', 'hours', 'minutes', 'seconds']:
-        schema_properties_time_between_check['properties'][p] = {
-            "anyOf": [
-                {
-                    "type": "integer"
-                },
-                {
-                    "type": "null"
-                }
-            ]
-        }
-
-    return schema_properties_time_between_check
-
-def build_watch_json_schema(d):
-    # Base JSON schema
-    schema = {
-        'type': 'object',
-        'properties': {},
-    }
-
-    for k, v in d.items():
-        # @todo 'integer' is not covered here because its almost always for internal usage
-
-        if isinstance(v, type(None)):
-            schema['properties'][k] = {
-                "anyOf": [
-                    {"type": "null"},
-                ]
-            }
-        elif isinstance(v, list):
-            schema['properties'][k] = {
-                "anyOf": [
-                    {"type": "array",
-                     # Always is an array of strings, like text or regex or something
-                     "items": {
-                         "type": "string",
-                         "maxLength": 5000
-                     }
-                     },
-                ]
-            }
-        elif isinstance(v, bool):
-            schema['properties'][k] = {
-                "anyOf": [
-                    {"type": "boolean"},
-                ]
-            }
-        elif isinstance(v, str):
-            schema['properties'][k] = {
-                "anyOf": [
-                    {"type": "string",
-                     "maxLength": 5000},
-                ]
-            }
-
-    # Can also be a string (or None by default above)
-    for v in ['body',
-              'notification_body',
-              'notification_format',
-              'notification_title',
-              'proxy',
-              'tag',
-              'title',
-              'webdriver_js_execute_code'
-              ]:
-        schema['properties'][v]['anyOf'].append({'type': 'string', "maxLength": 5000})
-
-    # None or Boolean
-    schema['properties']['track_ldjson_price_data']['anyOf'].append({'type': 'boolean'})
-
-    schema['properties']['method'] = {"type": "string",
-                                      "enum": ["GET", "POST", "DELETE", "PUT"]
-                                      }
-
-    schema['properties']['fetch_backend']['anyOf'].append({"type": "string",
-                                                           "enum": ["html_requests", "html_webdriver"]
-                                                           })
-
-
-
-    # All headers must be key/value type dict
-    schema['properties']['headers'] = {
-        "type": "object",
-        "patternProperties": {
-            # Should always be a string:string type value
-            ".*": {"type": "string"},
-        }
-    }
-
-    from changedetectionio.notification import valid_notification_formats
-
-    schema['properties']['notification_format'] = {'type': 'string',
-                                                   'enum': list(valid_notification_formats.keys())
-                                                   }
-
-    # Stuff that shouldn't be available but is just state-storage
-    for v in ['previous_md5', 'last_error', 'has_ldjson_price_data', 'previous_md5_before_filters', 'uuid']:
-        del schema['properties'][v]
-
-    schema['properties']['webdriver_delay']['anyOf'].append({'type': 'integer'})
-
-    schema['properties']['time_between_check'] = build_time_between_check_json_schema()
-
-    # headers ?
-    return schema
-

changedetectionio/api/api_v1.py

@@ -1,24 +1,11 @@
-from flask_expects_json import expects_json
-from changedetectionio import queuedWatchMetaData
 from flask_restful import abort, Resource
 from flask import request, make_response
 import validators
 from . import auth
-import copy
 
-# See docs/README.md for rebuilding the docs/apidoc information
 
-from . import api_schema
 
-# Build a JSON Schema atleast partially based on our Watch model
-from changedetectionio.model.Watch import base_config as watch_base_config
-schema = api_schema.build_watch_json_schema(watch_base_config)
-
-schema_create_watch = copy.deepcopy(schema)
-schema_create_watch['required'] = ['url']
-
-schema_update_watch = copy.deepcopy(schema)
-schema_update_watch['additionalProperties'] = False
+# https://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html
 
 class Watch(Resource):
     def __init__(self, **kwargs):
@@ -28,100 +15,30 @@ class Watch(Resource):
 
     # Get information about a single watch, excluding the history list (can be large)
     # curl http://localhost:4000/api/v1/watch/<string:uuid>
-    # @todo - version2 - ?muted and ?paused should be able to be called together, return the watch struct not "OK"
     # ?recheck=true
     @auth.check_token
     def get(self, uuid):
-        """
-        @api {get} /api/v1/watch/:uuid Get a single watch data
-        @apiDescription Retrieve watch information and set muted/paused status
-        @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?muted=unmuted"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?paused=unpaused"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiName Watch
-        @apiGroup Watch
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiQuery {Boolean} [recheck] Recheck this watch `recheck=1`
-        @apiQuery {String} [paused] =`paused` or =`unpaused` , Sets the PAUSED state
-        @apiQuery {String} [muted] =`muted` or =`unmuted` , Sets the MUTE NOTIFICATIONS state
-        @apiSuccess (200) {String} OK When paused/muted/recheck operation OR full JSON object of the watch
-        @apiSuccess (200) {JSON} WatchJSON JSON Full JSON object of the watch
-        """
         from copy import deepcopy
         watch = deepcopy(self.datastore.data['watching'].get(uuid))
         if not watch:
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
 
         if request.args.get('recheck'):
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
-            return "OK", 200
-        if request.args.get('paused', '') == 'paused':
-            self.datastore.data['watching'].get(uuid).pause()
-            return "OK", 200
-        elif request.args.get('paused', '') == 'unpaused':
-            self.datastore.data['watching'].get(uuid).unpause()
-            return "OK", 200
-        if request.args.get('muted', '') == 'muted':
-            self.datastore.data['watching'].get(uuid).mute()
-            return "OK", 200
-        elif request.args.get('muted', '') == 'unmuted':
-            self.datastore.data['watching'].get(uuid).unmute()
+            self.update_q.put((1, uuid))
             return "OK", 200
 
         # Return without history, get that via another API call
-        # Properties are not returned as a JSON, so add the required props manually
         watch['history_n'] = watch.history_n
-        watch['last_changed'] = watch.last_changed
-
         return watch
 
     @auth.check_token
     def delete(self, uuid):
-        """
-        @api {delete} /api/v1/watch/:uuid Delete a watch and related history
-        @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiName Delete
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was deleted
-        """
         if not self.datastore.data['watching'].get(uuid):
             abort(400, message='No watch exists with the UUID of {}'.format(uuid))
 
         self.datastore.delete(uuid)
         return 'OK', 204
 
-    @auth.check_token
-    @expects_json(schema_update_watch)
-    def put(self, uuid):
-        """
-        @api {put} /api/v1/watch/:uuid Update watch information
-        @apiExample {curl} Example usage:
-            Update (PUT)
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X PUT -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "new list"}'
-
-        @apiDescription Updates an existing watch using JSON, accepts the same structure as returned in <a href="#api-Watch-Watch">get single watch information</a>
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiName Update a watch
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was updated
-        @apiSuccess (500) {String} ERR Some other error
-        """
-        watch = self.datastore.data['watching'].get(uuid)
-        if not watch:
-            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
-
-        if request.json.get('proxy'):
-            plist = self.datastore.proxy_list
-            if not request.json.get('proxy') in plist:
-                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
-
-        watch.update(request.json)
-
-        return "OK", 200
-
 
 class WatchHistory(Resource):
     def __init__(self, **kwargs):
@@ -131,21 +48,6 @@ class WatchHistory(Resource):
     # Get a list of available history for a watch by UUID
     # curl http://localhost:4000/api/v1/watch/<string:uuid>/history
     def get(self, uuid):
-        """
-        @api {get} /api/v1/watch/<string:uuid>/history Get a list of all historical snapshots available for a watch
-        @apiDescription Requires `uuid`, returns list
-        @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
-            {
-                "1676649279": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/cb7e9be8258368262246910e6a2a4c30.txt",
-                "1677092785": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/e20db368d6fc633e34f559ff67bb4044.txt",
-                "1677103794": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/02efdd37dacdae96554a8cc85dc9c945.txt"
-            }
-        @apiName Get list of available stored snapshots for watch
-        @apiGroup Watch History
-        @apiSuccess (200) {String} OK
-        @apiSuccess (404) {String} ERR Not found
-        """
         watch = self.datastore.data['watching'].get(uuid)
         if not watch:
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
@@ -157,18 +59,11 @@ class WatchSingleHistory(Resource):
         # datastore is a black box dependency
         self.datastore = kwargs['datastore']
 
+    # Read a given history snapshot and return its content
+    # <string:timestamp> or "latest"
+    # curl http://localhost:4000/api/v1/watch/<string:uuid>/history/<int:timestamp>
     @auth.check_token
     def get(self, uuid, timestamp):
-        """
-        @api {get} /api/v1/watch/<string:uuid>/history/<int:timestamp> Get single snapshot from watch
-        @apiDescription Requires watch `uuid` and `timestamp`. `timestamp` of "`latest`" for latest available snapshot, or <a href="#api-Watch_History-Get_list_of_available_stored_snapshots_for_watch">use the list returned here</a>
-        @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history/1677092977 -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
-        @apiName Get single snapshot content
-        @apiGroup Watch History
-        @apiSuccess (200) {String} OK
-        @apiSuccess (404) {String} ERR Not found
-        """
         watch = self.datastore.data['watching'].get(uuid)
         if not watch:
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
@@ -179,7 +74,8 @@ class WatchSingleHistory(Resource):
         if timestamp == 'latest':
             timestamp = list(watch.history.keys())[-1]
 
-        content = watch.get_history_snapshot(timestamp)
+        with open(watch.history[timestamp], 'r') as f:
+            content = f.read()
 
         response = make_response(content, 200)
         response.mimetype = "text/plain"
@@ -193,87 +89,36 @@ class CreateWatch(Resource):
         self.update_q = kwargs['update_q']
 
     @auth.check_token
-    @expects_json(schema_create_watch)
     def post(self):
-        """
-        @api {post} /api/v1/watch Create a single watch
-        @apiDescription Requires atleast `url` set, can accept the same structure as <a href="#api-Watch-Watch">get single watch information</a> to create.
-        @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "nice list"}'
-        @apiName Create
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was created
-        @apiSuccess (500) {String} ERR Some other error
-        """
-
+        # curl http://localhost:4000/api/v1/watch -H "Content-Type: application/json" -d '{"url": "https://my-nice.com", "tag": "one, two" }'
         json_data = request.get_json()
-        url = json_data['url'].strip()
+        tag = json_data['tag'].strip() if json_data.get('tag') else ''
 
         if not validators.url(json_data['url'].strip()):
             return "Invalid or unsupported URL", 400
 
-        if json_data.get('proxy'):
-            plist = self.datastore.proxy_list
-            if not json_data.get('proxy') in plist:
-                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
+        extras = {'title': json_data['title'].strip()} if json_data.get('title') else {}
 
-        extras = copy.deepcopy(json_data)
-        del extras['url']
-
-        new_uuid = self.datastore.add_watch(url=url, extras=extras)
-        if new_uuid:
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
-            return {'uuid': new_uuid}, 201
-        else:
-            return "Invalid or unsupported URL", 400
+        new_uuid = self.datastore.add_watch(url=json_data['url'].strip(), tag=tag, extras=extras)
+        self.update_q.put((1, new_uuid))
+        return {'uuid': new_uuid}, 201
 
+    # Return concise list of available watches and some very basic info
+    # curl http://localhost:4000/api/v1/watch|python -mjson.tool
+    # ?recheck_all=1 to recheck all
     @auth.check_token
     def get(self):
-        """
-        @api {get} /api/v1/watch List watches
-        @apiDescription Return concise list of available watches and some very basic info
-        @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            {
-                "6a4b7d5c-fee4-4616-9f43-4ac97046b595": {
-                    "last_changed": 1677103794,
-                    "last_checked": 1677103794,
-                    "last_error": false,
-                    "title": "",
-                    "url": "http://www.quotationspage.com/random.php"
-                },
-                "e6f5fd5c-dbfe-468b-b8f3-f9d6ff5ad69b": {
-                    "last_changed": 0,
-                    "last_checked": 1676662819,
-                    "last_error": false,
-                    "title": "QuickLook",
-                    "url": "https://github.com/QL-Win/QuickLook/tags"
-                }
-            }
-
-        @apiParam {String} [recheck_all]       Optional Set to =1 to force recheck of all watches
-        @apiParam {String} [tag]               Optional name of tag to limit results
-        @apiName ListWatches
-        @apiGroup Watch Management
-        @apiSuccess (200) {String} OK JSON dict
-        """
         list = {}
-
-        tag_limit = request.args.get('tag', None)
-        for k, watch in self.datastore.data['watching'].items():
-            if tag_limit:
-                if not tag_limit.lower() in watch.all_tags:
-                    continue
-
-            list[k] = {'url': watch['url'],
-                       'title': watch['title'],
-                       'last_checked': watch['last_checked'],
-                       'last_changed': watch.last_changed,
-                       'last_error': watch['last_error']}
+        for k, v in self.datastore.data['watching'].items():
+            list[k] = {'url': v['url'],
+                       'title': v['title'],
+                       'last_checked': v['last_checked'],
+                       'last_changed': v.last_changed,
+                       'last_error': v['last_error']}
 
         if request.args.get('recheck_all'):
             for uuid in self.datastore.data['watching'].keys():
-                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                self.update_q.put((1, uuid))
             return {'status': "OK"}, 200
 
         return list, 200
@@ -286,22 +131,6 @@ class SystemInfo(Resource):
 
     @auth.check_token
     def get(self):
-        """
-        @api {get} /api/v1/systeminfo Return system info
-        @apiDescription Return some info about the current system state
-        @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/systeminfo -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            HTTP/1.0 200
-            {
-                'queue_size': 10 ,
-                'overdue_watches': ["watch-uuid-list"],
-                'uptime': 38344.55,
-                'watch_count': 800,
-                'version': "0.40.1"
-            }
-        @apiName Get Info
-        @apiGroup System Information
-        """
         import time
         overdue_watches = []
 
@@ -320,11 +149,10 @@ class SystemInfo(Resource):
             # Allow 5 minutes of grace time before we decide it's overdue
             if time_since_check - (5 * 60) > t:
                 overdue_watches.append(uuid)
-        from changedetectionio import __version__ as main_version
+
         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', {})),
-                   'version': main_version
+                   'watch_count': len(self.datastore.data.get('watching', {}))
                }, 200

changedetectionio/blueprint/browser_steps/__init__.py

@@ -23,10 +23,11 @@
 
 from distutils.util import strtobool
 from flask import Blueprint, request, make_response
+from flask_login import login_required
 import os
 import logging
 from changedetectionio.store import ChangeDetectionStore
-from changedetectionio import login_optionally_required
+
 browsersteps_live_ui_o = {}
 browsersteps_playwright_browser_interface = None
 browsersteps_playwright_browser_interface_browser = None
@@ -64,7 +65,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
     browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
 
-    @login_optionally_required
+    @login_required
     @browser_steps_blueprint.route("/browsersteps_update", methods=['GET', 'POST'])
     def browsersteps_ui_update():
         import base64
@@ -106,8 +107,8 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
             if step_operation == 'Goto site':
                 step_operation = 'goto_url'
-                step_optional_value = datastore.data['watching'][uuid].get('url')
-                step_selector = None
+                step_optional_value = None
+                step_selector = datastore.data['watching'][uuid].get('url')
 
             # @todo try.. accept.. nice errors not popups..
             try:

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -25,14 +25,12 @@ browser_step_ui_config = {'Choose one': '0 0',
                           'Execute JS': '0 1',
 #                          'Extract text and use as filter': '1 0',
                           'Goto site': '0 0',
-                          'Goto URL': '0 1',
                           'Press Enter': '0 0',
                           'Select by label': '1 1',
                           'Scroll down': '0 0',
                           'Uncheck checkbox': '1 0',
                           'Wait for seconds': '0 1',
                           'Wait for text': '0 1',
-                          'Wait for text in element': '1 1',
                           #                          'Press Page Down': '0 0',
                           #                          'Press Page Up': '0 0',
                           # weird bug, come back to it later
@@ -55,7 +53,7 @@ class steppable_browser_interface():
 
         print("> action calling", call_action_name)
         # https://playwright.dev/python/docs/selectors#xpath-selectors
-        if selector and selector.startswith('/') and not selector.startswith('//'):
+        if selector.startswith('/') and not selector.startswith('//'):
             selector = "xpath=" + selector
 
         action_handler = getattr(self, "action_" + call_action_name)
@@ -74,16 +72,18 @@ class steppable_browser_interface():
         self.page.wait_for_timeout(3 * 1000)
         print("Call action done in", time.time() - now)
 
-    def action_goto_url(self, selector, value):
+    def action_goto_url(self, url, optional_value):
         # self.page.set_viewport_size({"width": 1280, "height": 5000})
         now = time.time()
-        response = self.page.goto(value, timeout=0, wait_until='commit')
+        response = self.page.goto(url, timeout=0, wait_until='domcontentloaded')
+        print("Time to goto URL", time.time() - now)
 
         # Wait_until = commit
         # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
         # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
         # This seemed to solve nearly all 'TimeoutErrors'
-        print("Time to goto URL ", time.time() - now)
+        extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5))
+        self.page.wait_for_timeout(extra_wait * 1000)
 
     def action_click_element_containing_text(self, selector=None, value=''):
         if not len(value.strip()):
@@ -134,17 +134,6 @@ class steppable_browser_interface():
     def action_wait_for_seconds(self, selector, value):
         self.page.wait_for_timeout(int(value) * 1000)
 
-    def action_wait_for_text(self, selector, value):
-        import json
-        v = json.dumps(value)
-        self.page.wait_for_function(f'document.querySelector("body").innerText.includes({v});', timeout=30000)
-
-    def action_wait_for_text_in_element(self, selector, value):
-        import json
-        s = json.dumps(selector)
-        v = json.dumps(value)
-        self.page.wait_for_function(f'document.querySelector({s}).innerText.includes({v});', timeout=30000)
-
     # @todo - in the future make some popout interface to capture what needs to be set
     # https://playwright.dev/python/docs/api/class-keyboard
     def action_press_enter(self, selector, value):
@@ -237,7 +226,7 @@ class browsersteps_live_ui(steppable_browser_interface):
     def get_current_state(self):
         """Return the screenshot and interactive elements mapping, generally always called after action_()"""
         from pkg_resources import resource_string
-        xpath_element_js = resource_string(__name__, "../res/xpath_element_scraper.js").decode('utf-8')
+        xpath_element_js = resource_string(__name__, "../../res/xpath_element_scraper.js").decode('utf-8')
         now = time.time()
         self.page.wait_for_timeout(1 * 1000)
 
@@ -272,8 +261,8 @@ class browsersteps_live_ui(steppable_browser_interface):
         self.page.evaluate("var include_filters=''")
         from pkg_resources import resource_string
         # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
-        xpath_element_js = resource_string(__name__, "../res/xpath_element_scraper.js").decode('utf-8')
-        from changedetectionio.fetchers import visualselector_xpath_selectors
+        xpath_element_js = resource_string(__name__, "../../res/xpath_element_scraper.js").decode('utf-8')
+        from changedetectionio.content_fetcher import visualselector_xpath_selectors
         xpath_element_js = xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
         xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")
         screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -1,33 +0,0 @@
-
-from distutils.util import strtobool
-from flask import Blueprint, flash, redirect, url_for
-from flask_login import login_required
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio import queuedWatchMetaData
-from queue import PriorityQueue
-
-PRICE_DATA_TRACK_ACCEPT = 'accepted'
-PRICE_DATA_TRACK_REJECT = 'rejected'
-
-def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue):
-
-    price_data_follower_blueprint = Blueprint('price_data_follower', __name__)
-
-    @login_required
-    @price_data_follower_blueprint.route("/<string:uuid>/accept", methods=['GET'])
-    def accept(uuid):
-        datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_ACCEPT
-        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
-        return redirect(url_for("form_watch_checknow", uuid=uuid))
-
-
-    @login_required
-    @price_data_follower_blueprint.route("/<string:uuid>/reject", methods=['GET'])
-    def reject(uuid):
-        datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_REJECT
-        return redirect(url_for("index"))
-
-
-    return price_data_follower_blueprint
-
-

changedetectionio/changedetection.py

@@ -3,17 +3,14 @@
 # Launch as a eventlet.wsgi server instance.
 
 from distutils.util import strtobool
-from json.decoder import JSONDecodeError
-
 import eventlet
 import eventlet.wsgi
 import getopt
 import os
 import signal
-import socket
 import sys
 
-from . import store, changedetection_app
+from . import store, changedetection_app, content_fetcher
 from . import __version__
 
 # Only global so we can access it in the signal handler
@@ -31,13 +28,11 @@ def sigterm_handler(_signo, _stack_frame):
 def main():
     global datastore
     global app
-
-    datastore_path = None
-    do_cleanup = False
-    host = ''
-    ipv6_enabled = False
-    port = os.environ.get('PORT') or 5000
     ssl_mode = False
+    host = ''
+    port = os.environ.get('PORT') or 5000
+    do_cleanup = False
+    datastore_path = None
 
     # On Windows, create and use a default path.
     if os.name == 'nt':
@@ -48,7 +43,7 @@ def main():
         datastore_path = os.path.join(os.getcwd(), "../datastore")
 
     try:
-        opts, args = getopt.getopt(sys.argv[1:], "6Ccsd:h:p:", "port")
+        opts, args = getopt.getopt(sys.argv[1:], "Ccsd:h:p:", "port")
     except getopt.GetoptError:
         print('backend.py -s SSL enable -h [host] -p [port] -d [datastore path]')
         sys.exit(2)
@@ -68,10 +63,6 @@ def main():
         if opt == '-d':
             datastore_path = arg
 
-        if opt == '-6':
-            print ("Enabling IPv6 listen support")
-            ipv6_enabled = True
-
         # Cleanup (remove text files that arent in the index)
         if opt == '-c':
             do_cleanup = True
@@ -92,14 +83,8 @@ def main():
                 "Or use the -C parameter to create the directory.".format(app_config['datastore_path']), file=sys.stderr)
             sys.exit(2)
 
-    try:
-        datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], version_tag=__version__)
-    except JSONDecodeError as e:
-        # Dont' start if the JSON DB looks corrupt
-        print ("ERROR: JSON DB or Proxy List JSON at '{}' appears to be corrupt, aborting".format(app_config['datastore_path']))
-        print(str(e))
-        return
 
+    datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], version_tag=__version__)
     app = changedetection_app(app_config, datastore)
 
     signal.signal(signal.SIGTERM, sigterm_handler)
@@ -139,15 +124,13 @@ def main():
         from werkzeug.middleware.proxy_fix import ProxyFix
         app.wsgi_app = ProxyFix(app.wsgi_app, x_prefix=1, x_host=1)
 
-    s_type = socket.AF_INET6 if ipv6_enabled else socket.AF_INET
-
     if ssl_mode:
         # @todo finalise SSL config, but this should get you in the right direction if you need it.
-        eventlet.wsgi.server(eventlet.wrap_ssl(eventlet.listen((host, port), s_type),
+        eventlet.wsgi.server(eventlet.wrap_ssl(eventlet.listen((host, port)),
                                                certfile='cert.pem',
                                                keyfile='privkey.pem',
                                                server_side=True), app)
 
     else:
-        eventlet.wsgi.server(eventlet.listen((host, int(port)), s_type), app)
+        eventlet.wsgi.server(eventlet.listen((host, int(port))), app)
 

changedetectionio/content_fetcher.py

@@ -0,0 +1,573 @@
+from abc import abstractmethod
+import chardet
+import json
+import logging
+import os
+import requests
+import sys
+import time
+
+visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4, header, footer, section, article, aside, details, main, nav, section, summary'
+
+class Non200ErrorCodeReceived(Exception):
+    def __init__(self, status_code, url, screenshot=None, xpath_data=None, page_html=None):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        self.xpath_data = xpath_data
+        self.page_text = None
+
+        if page_html:
+            from changedetectionio import html_tools
+            self.page_text = html_tools.html_to_text(page_html)
+        return
+
+
+class JSActionExceptions(Exception):
+    def __init__(self, status_code, url, screenshot, message=''):
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        self.message = message
+        return
+
+class BrowserStepsStepTimout(Exception):
+    def __init__(self, step_n):
+        self.step_n = step_n
+        return
+
+
+class PageUnloadable(Exception):
+    def __init__(self, status_code, url, 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):
+    def __init__(self, status_code, url, screenshot=None):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        return
+
+class ScreenshotUnavailable(Exception):
+    def __init__(self, status_code, url, page_html=None):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        if page_html:
+            from html_tools import html_to_text
+            self.page_text = html_to_text(page_html)
+        return
+
+class ReplyWithContentButNoText(Exception):
+    def __init__(self, status_code, url, screenshot=None):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        return
+
+class Fetcher():
+    error = None
+    status_code = None
+    content = None
+    headers = None
+    browser_steps = None
+    browser_steps_screenshot_path = None
+
+    fetcher_description = "No description"
+    webdriver_js_execute_code = None
+    xpath_element_js = ""
+
+    xpath_data = None
+
+    # Will be needed in the future by the VisualSelector, always get this where possible.
+    screenshot = False
+    system_http_proxy = os.getenv('HTTP_PROXY')
+    system_https_proxy = os.getenv('HTTPS_PROXY')
+
+    # Time ONTOP of the system defined env minimum time
+    render_extract_delay = 0
+
+    def __init__(self):
+        from pkg_resources import resource_string
+        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
+        self.xpath_element_js = resource_string(__name__, "res/xpath_element_scraper.js").decode('utf-8')
+
+
+    @abstractmethod
+    def get_error(self):
+        return self.error
+
+    @abstractmethod
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None):
+        # Should set self.error, self.status_code and self.content
+        pass
+
+    @abstractmethod
+    def quit(self):
+        return
+
+    @abstractmethod
+    def get_last_status_code(self):
+        return self.status_code
+
+    @abstractmethod
+    def screenshot_step(self, step_n):
+        return None
+
+    @abstractmethod
+    # Return true/false if this checker is ready to run, in the case it needs todo some special config check etc
+    def is_ready(self):
+        return True
+
+    def iterate_browser_steps(self):
+        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+        from playwright._impl._api_types import TimeoutError
+        from jinja2 import Environment
+        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
+
+        step_n = 0
+
+        if self.browser_steps is not None and len(self.browser_steps):
+            interface = steppable_browser_interface()
+            interface.page = self.page
+
+            valid_steps = filter(lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'), self.browser_steps)
+
+            for step in valid_steps:
+                step_n += 1
+                print(">> Iterating check - browser Step n {} - {}...".format(step_n, step['operation']))
+                self.screenshot_step("before-"+str(step_n))
+                self.save_step_html("before-"+str(step_n))
+                try:
+                    optional_value = step['optional_value']
+                    selector = step['selector']
+                    # Support for jinja2 template in step values, with date module added
+                    if '{%' in step['optional_value'] or '{{' in step['optional_value']:
+                        optional_value = str(jinja2_env.from_string(step['optional_value']).render())
+                    if '{%' in step['selector'] or '{{' in step['selector']:
+                        selector = str(jinja2_env.from_string(step['selector']).render())
+
+                    getattr(interface, "call_action")(action_name=step['operation'],
+                                                      selector=selector,
+                                                      optional_value=optional_value)
+                    self.screenshot_step(step_n)
+                    self.save_step_html(step_n)
+                except TimeoutError:
+                    # Stop processing here
+                    raise BrowserStepsStepTimout(step_n=step_n)
+
+
+
+    # It's always good to reset these
+    def delete_browser_steps_screenshots(self):
+        import glob
+        if self.browser_steps_screenshot_path is not None:
+            dest = os.path.join(self.browser_steps_screenshot_path, 'step_*.jpeg')
+            files = glob.glob(dest)
+            for f in files:
+                os.unlink(f)
+
+#   Maybe for the future, each fetcher provides its own diff output, could be used for text, image
+#   the current one would return javascript output (as we use JS to generate the diff)
+#
+def available_fetchers():
+    # See the if statement at the bottom of this file for how we switch between playwright and webdriver
+    import inspect
+    p = []
+    for name, obj in inspect.getmembers(sys.modules[__name__], inspect.isclass):
+        if inspect.isclass(obj):
+            # @todo html_ is maybe better as fetcher_ or something
+            # In this case, make sure to edit the default one in store.py and fetch_site_status.py
+            if name.startswith('html_'):
+                t = tuple([name, obj.fetcher_description])
+                p.append(t)
+
+    return p
+
+class base_html_playwright(Fetcher):
+    fetcher_description = "Playwright {}/Javascript".format(
+        os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
+    )
+    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
+        fetcher_description += " via '{}'".format(os.getenv("PLAYWRIGHT_DRIVER_URL"))
+
+    browser_type = ''
+    command_executor = ''
+
+    # Configs for Proxy setup
+    # In the ENV vars, is prefixed with "playwright_proxy_", so it is for example "playwright_proxy_server"
+    playwright_proxy_settings_mappings = ['bypass', 'server', 'username', 'password']
+
+    proxy = None
+
+    def __init__(self, proxy_override=None):
+        super().__init__()
+        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+        self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
+        self.command_executor = os.getenv(
+            "PLAYWRIGHT_DRIVER_URL",
+            'ws://playwright-chrome:3000'
+        ).strip('"')
+
+        # If any proxy settings are enabled, then we should setup the proxy object
+        proxy_args = {}
+        for k in self.playwright_proxy_settings_mappings:
+            v = os.getenv('playwright_proxy_' + k, False)
+            if v:
+                proxy_args[k] = v.strip('"')
+
+        if proxy_args:
+            self.proxy = proxy_args
+
+        # allow per-watch proxy selection override
+        if proxy_override:
+            self.proxy = {'server': proxy_override}
+
+    def screenshot_step(self, step_n=''):
+
+        # There's a bug where we need to do it twice or it doesnt take the whole page, dont know why.
+        self.page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024})
+        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=85)
+
+        if self.browser_steps_screenshot_path is not None:
+            destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.jpeg'.format(step_n))
+            logging.debug("Saving step screenshot to {}".format(destination))
+            with open(destination, 'wb') as f:
+                f.write(screenshot)
+
+    def save_step_html(self, step_n):
+        content = self.page.content()
+        destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.html'.format(step_n))
+        logging.debug("Saving step HTML to {}".format(destination))
+        with open(destination, 'w') as f:
+            f.write(content)
+
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None):
+
+        from playwright.sync_api import sync_playwright
+        import playwright._impl._api_types
+
+        self.delete_browser_steps_screenshots()
+        response = None
+        with sync_playwright() as p:
+            browser_type = getattr(p, self.browser_type)
+
+            # Seemed to cause a connection Exception even tho I can see it connect
+            # self.browser = browser_type.connect(self.command_executor, timeout=timeout*1000)
+            # 60,000 connection timeout only
+            browser = browser_type.connect_over_cdp(self.command_executor, timeout=60000)
+
+            # Set user agent to prevent Cloudflare from blocking the browser
+            # Use the default one configured in the App.py model that's passed from fetch_site_status.py
+            context = browser.new_context(
+                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
+                proxy=self.proxy,
+                # This is needed to enable JavaScript execution on GitHub and others
+                bypass_csp=True,
+                # Should never be needed
+                accept_downloads=False
+            )
+
+            self.page = context.new_page()
+            if len(request_headers):
+                context.set_extra_http_headers(request_headers)
+
+            try:
+                self.page.set_default_navigation_timeout(90000)
+                self.page.set_default_timeout(90000)
+
+                # Listen for all console events and handle errors
+                self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
+
+                # Bug - never set viewport size BEFORE page.goto
+
+
+                # Waits for the next navigation. Using Python context manager
+                # prevents a race condition between clicking and waiting for a navigation.
+                with self.page.expect_navigation():
+                    response = self.page.goto(url, wait_until='load')
+                # Wait_until = commit
+                # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
+                # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
+                # This seemed to solve nearly all 'TimeoutErrors'
+                extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+                self.page.wait_for_timeout(extra_wait * 1000)
+
+                if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
+                    self.page.evaluate(self.webdriver_js_execute_code)
+
+            except playwright._impl._api_types.TimeoutError as e:
+                context.close()
+                browser.close()
+                # This can be ok, we will try to grab what we could retrieve
+                pass
+            except Exception as e:
+                print ("other exception when page.goto")
+                print (str(e))
+                context.close()
+                browser.close()
+                raise PageUnloadable(url=url, status_code=None)
+
+
+            if response is None:
+                context.close()
+                browser.close()
+                print ("response object was none")
+                raise EmptyReply(url=url, status_code=None)
+
+            # Bug 2(?) Set the viewport size AFTER loading the page
+            self.page.set_viewport_size({"width": 1280, "height": 1024})
+
+            # Run Browser Steps here
+            self.iterate_browser_steps()
+
+            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+            time.sleep(extra_wait)
+
+
+            self.content = self.page.content()
+            self.status_code = response.status
+
+            if len(self.page.content().strip()) == 0:
+                context.close()
+                browser.close()
+                print ("Content was empty")
+                raise EmptyReply(url=url, status_code=None)
+
+            # Bug 2(?) Set the viewport size AFTER loading the page
+            self.page.set_viewport_size({"width": 1280, "height": 1024})
+
+            self.status_code = response.status
+            self.content = self.page.content()
+            self.headers = response.all_headers()
+
+            # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
+            if current_include_filters is not None:
+                self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
+            else:
+                self.page.evaluate("var include_filters=''")
+
+            self.xpath_data = self.page.evaluate("async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
+
+            # Bug 3 in Playwright screenshot handling
+            # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
+            # JPEG is better here because the screenshots can be very very large
+
+            # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
+            # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
+            # acceptable screenshot quality here
+            try:
+                # Quality set to 1 because it's not used, just used as a work-around for a bug, no need to change this.
+                self.page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024}, quality=1)
+                # The actual screenshot
+                self.screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+            except Exception as e:
+                context.close()
+                browser.close()
+                raise ScreenshotUnavailable(url=url, status_code=None)
+
+            context.close()
+            browser.close()
+
+class base_html_webdriver(Fetcher):
+    if os.getenv("WEBDRIVER_URL"):
+        fetcher_description = "WebDriver Chrome/Javascript via '{}'".format(os.getenv("WEBDRIVER_URL"))
+    else:
+        fetcher_description = "WebDriver Chrome/Javascript"
+
+    command_executor = ''
+
+    # Configs for Proxy setup
+    # In the ENV vars, is prefixed with "webdriver_", so it is for example "webdriver_sslProxy"
+    selenium_proxy_settings_mappings = ['proxyType', 'ftpProxy', 'httpProxy', 'noProxy',
+                                        'proxyAutoconfigUrl', 'sslProxy', 'autodetect',
+                                        'socksProxy', 'socksVersion', 'socksUsername', 'socksPassword']
+    proxy = None
+
+    def __init__(self, proxy_override=None):
+        super().__init__()
+        from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
+
+        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+        self.command_executor = os.getenv("WEBDRIVER_URL", 'http://browser-chrome:4444/wd/hub').strip('"')
+
+        # If any proxy settings are enabled, then we should setup the proxy object
+        proxy_args = {}
+        for k in self.selenium_proxy_settings_mappings:
+            v = os.getenv('webdriver_' + k, False)
+            if v:
+                proxy_args[k] = v.strip('"')
+
+        # Map back standard HTTP_ and HTTPS_PROXY to webDriver httpProxy/sslProxy
+        if not proxy_args.get('webdriver_httpProxy') and self.system_http_proxy:
+            proxy_args['httpProxy'] = self.system_http_proxy
+        if not proxy_args.get('webdriver_sslProxy') and self.system_https_proxy:
+            proxy_args['httpsProxy'] = self.system_https_proxy
+
+        # Allows override the proxy on a per-request basis
+        if proxy_override is not None:
+            proxy_args['httpProxy'] = proxy_override
+
+        if proxy_args:
+            self.proxy = SeleniumProxy(raw=proxy_args)
+
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None):
+
+        from selenium import webdriver
+        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+        from selenium.common.exceptions import WebDriverException
+        # request_body, request_method unused for now, until some magic in the future happens.
+
+        # check env for WEBDRIVER_URL
+        self.driver = webdriver.Remote(
+            command_executor=self.command_executor,
+            desired_capabilities=DesiredCapabilities.CHROME,
+            proxy=self.proxy)
+
+        try:
+            self.driver.get(url)
+        except WebDriverException as e:
+            # Be sure we close the session window
+            self.quit()
+            raise
+
+        self.driver.set_window_size(1280, 1024)
+        self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+
+        if self.webdriver_js_execute_code is not None:
+            self.driver.execute_script(self.webdriver_js_execute_code)
+            # Selenium doesn't automatically wait for actions as good as Playwright, so wait again
+            self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
+
+        # @todo - how to check this? is it possible?
+        self.status_code = 200
+        # @todo somehow we should try to get this working for WebDriver
+        # raise EmptyReply(url=url, status_code=r.status_code)
+
+        # @todo - dom wait loaded?
+        time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay)
+        self.content = self.driver.page_source
+        self.headers = {}
+
+        self.screenshot = self.driver.get_screenshot_as_png()
+
+    # Does the connection to the webdriver work? run a test connection.
+    def is_ready(self):
+        from selenium import webdriver
+        from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+
+        self.driver = webdriver.Remote(
+            command_executor=self.command_executor,
+            desired_capabilities=DesiredCapabilities.CHROME)
+
+        # driver.quit() seems to cause better exceptions
+        self.quit()
+        return True
+
+    def quit(self):
+        if self.driver:
+            try:
+                self.driver.quit()
+            except Exception as e:
+                print("Exception in chrome shutdown/quit" + str(e))
+
+
+# "html_requests" is listed as the default fetcher in store.py!
+class html_requests(Fetcher):
+    fetcher_description = "Basic fast Plaintext/HTTP Client"
+
+    def __init__(self, proxy_override=None):
+        self.proxy_override = proxy_override
+
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None):
+
+        # Make requests use a more modern looking user-agent
+        if not 'User-Agent' in request_headers:
+            request_headers['User-Agent'] = os.getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT",
+                                                      'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36')
+
+        proxies = {}
+
+        # Allows override the proxy on a per-request basis
+        if self.proxy_override:
+            proxies = {'http': self.proxy_override, 'https': self.proxy_override, 'ftp': self.proxy_override}
+        else:
+            if self.system_http_proxy:
+                proxies['http'] = self.system_http_proxy
+            if self.system_https_proxy:
+                proxies['https'] = self.system_https_proxy
+
+        r = requests.request(method=request_method,
+                             data=request_body,
+                             url=url,
+                             headers=request_headers,
+                             timeout=timeout,
+                             proxies=proxies,
+                             verify=False)
+
+        # If the response did not tell us what encoding format to expect, Then use chardet to override what `requests` thinks.
+        # For example - some sites don't tell us it's utf-8, but return utf-8 content
+        # This seems to not occur when using webdriver/selenium, it seems to detect the text encoding more reliably.
+        # https://github.com/psf/requests/issues/1604 good info about requests encoding detection
+        if not r.headers.get('content-type') or not 'charset=' in r.headers.get('content-type'):
+            encoding = chardet.detect(r.content)['encoding']
+            if encoding:
+                r.encoding = encoding
+
+        if not r.content or not len(r.content):
+            raise EmptyReply(url=url, status_code=r.status_code)
+
+        # @todo test this
+        # @todo maybe you really want to test zero-byte return pages?
+        if r.status_code != 200 and not ignore_status_codes:
+            # maybe check with content works?
+            raise Non200ErrorCodeReceived(url=url, status_code=r.status_code, page_html=r.text)
+
+        self.status_code = r.status_code
+        self.content = r.text
+        self.headers = r.headers
+
+
+# Decide which is the 'real' HTML webdriver, this is more a system wide config
+# rather than site-specific.
+use_playwright_as_chrome_fetcher = os.getenv('PLAYWRIGHT_DRIVER_URL', False)
+if use_playwright_as_chrome_fetcher:
+    html_webdriver = base_html_playwright
+else:
+    html_webdriver = base_html_webdriver

changedetectionio/dev-docker/Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.8-slim
+
+# https://stackoverflow.com/questions/58701233/docker-logs-erroneously-appears-empty-until-container-stops
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+RUN [ ! -d "/datastore" ] && mkdir /datastore
+
+COPY sleep.py /
+CMD [ "python", "/sleep.py" ]
+
+
+

changedetectionio/dev-docker/sleep.py

@@ -0,0 +1,7 @@
+import time
+
+print ("Sleep loop, you should run your script from the console")
+
+while True: 
+    # Wait for 5 seconds
+    time.sleep(2)

changedetectionio/diff.py

@@ -10,7 +10,7 @@ def same_slicer(l, a, b):
         return l[a:b]
 
 # like .compare but a little different output
-def customSequenceMatcher(before, after, include_equal=False, include_removed=True, include_added=True, include_replaced=True, include_change_type_prefix=True):
+def customSequenceMatcher(before, after, include_equal=False):
     cruncher = difflib.SequenceMatcher(isjunk=lambda x: x in " \\t", a=before, b=after)
 
     # @todo Line-by-line mode instead of buncghed, including `after` that is not in `before` (maybe unset?)
@@ -18,39 +18,34 @@ def customSequenceMatcher(before, after, include_equal=False, include_removed=Tr
         if include_equal and tag == 'equal':
             g = before[alo:ahi]
             yield g
-        elif include_removed and tag == 'delete':
-            row_prefix = "(removed) " if include_change_type_prefix else ''
-            g = [ row_prefix + i for i in same_slicer(before, alo, ahi)]
+        elif tag == 'delete':
+            g = ["(removed) " + i for i in same_slicer(before, alo, ahi)]
             yield g
-        elif include_replaced and tag == 'replace':
-            row_prefix = "(changed) " if include_change_type_prefix else ''
-            g = [row_prefix + i for i in same_slicer(before, alo, ahi)]
-            row_prefix = "(into) " if include_change_type_prefix else ''
-            g += [row_prefix + i for i in same_slicer(after, blo, bhi)]
+        elif tag == 'replace':
+            g = ["(changed) " + i for i in same_slicer(before, alo, ahi)]
+            g += ["(into   ) " + i for i in same_slicer(after, blo, bhi)]
             yield g
-        elif include_added and tag == 'insert':
-            row_prefix = "(added) " if include_change_type_prefix else ''
-            g = [row_prefix + i for i in same_slicer(after, blo, bhi)]
+        elif tag == 'insert':
+            g = ["(added  ) " + i for i in same_slicer(after, blo, bhi)]
             yield g
 
 # only_differences - only return info about the differences, no context
-# line_feed_sep could be "<br>" or "<li>" or "\n" etc
-def render_diff(previous_version_file_contents, newest_version_file_contents, include_equal=False, include_removed=True, include_added=True, include_replaced=True, line_feed_sep="\n", include_change_type_prefix=True):
+# line_feed_sep could be "<br/>" or "<li>" or "\n" etc
+def render_diff(previous_file, newest_file, include_equal=False, line_feed_sep="\n"):
+    with open(newest_file, 'r') as f:
+        newest_version_file_contents = f.read()
+        newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
 
-    newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
-
-    if previous_version_file_contents:
+    if previous_file:
+        with open(previous_file, 'r') as f:
+            previous_version_file_contents = f.read()
             previous_version_file_contents = [line.rstrip() for line in previous_version_file_contents.splitlines()]
     else:
         previous_version_file_contents = ""
 
-    rendered_diff = customSequenceMatcher(before=previous_version_file_contents,
-                                          after=newest_version_file_contents,
-                                          include_equal=include_equal,
-                                          include_removed=include_removed,
-                                          include_added=include_added,
-                                          include_replaced=include_replaced,
-                                          include_change_type_prefix=include_change_type_prefix)
+    rendered_diff = customSequenceMatcher(previous_version_file_contents,
+                                          newest_version_file_contents,
+                                          include_equal)
 
     # Recursively join lists
     f = lambda L: line_feed_sep.join([f(x) if type(x) is list else x for x in L])

changedetectionio/fetch_site_status.py

@@ -1,36 +1,23 @@
-# HTML to TEXT/JSON DIFFERENCE FETCHER
-
 import hashlib
-import json
 import logging
 import os
 import re
+import time
 import urllib3
 
-from changedetectionio import html_tools
-from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
-from copy import deepcopy
-from . import difference_detection_processor
-from .. import fetchers
+from changedetectionio import content_fetcher, html_tools
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 
-name =  'Webpage Text/HTML, JSON and PDF changes'
-description = 'Detects all text changes where possible'
-
 class FilterNotFoundInResponse(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
 
-class PDFToHTMLToolNotFound(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(difference_detection_processor):
+class perform_site_check():
     screenshot = None
     xpath_data = None
 
@@ -51,7 +38,8 @@ class perform_site_check(difference_detection_processor):
 
         return regex
 
-    def run(self, uuid, skip_when_checksum_same=True):
+    def run(self, uuid):
+        from copy import deepcopy
         changed_detected = False
         screenshot = False  # as bytes
         stripped_text_from_html = ""
@@ -60,7 +48,7 @@ class perform_site_check(difference_detection_processor):
         watch = deepcopy(self.datastore.data['watching'].get(uuid))
 
         if not watch:
-            raise Exception("Watch no longer exists.")
+            return
 
         # Protect against file:// access
         if re.search(r'^file', watch.get('url', ''), re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
@@ -98,16 +86,12 @@ class perform_site_check(difference_detection_processor):
             is_source = True
 
         # Pluggable content fetcher
-        prefer_backend = watch.get_fetch_backend
-        if not prefer_backend or prefer_backend == 'system':
-            prefer_backend = self.datastore.data['settings']['application']['fetch_backend']
-
-        if prefer_backend == 'html_webdriver':
-            preferred_fetcher = fetchers.html_webdriver
+        prefer_backend = watch.get('fetch_backend')
+        if hasattr(content_fetcher, prefer_backend):
+            klass = getattr(content_fetcher, prefer_backend)
         else:
-            from ..fetchers import html_requests
-            preferred_fetcher = html_requests
-
+            # 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
@@ -115,7 +99,7 @@ class perform_site_check(difference_detection_processor):
             proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
             print("UUID {} Using proxy {}".format(uuid, proxy_url))
 
-        fetcher = preferred_fetcher(proxy_override=proxy_url)
+        fetcher = klass(proxy_override=proxy_url)
 
         # Configurable per-watch or global extra delay before extracting text (for webDriver types)
         system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
@@ -132,26 +116,12 @@ class perform_site_check(difference_detection_processor):
         if watch.get('webdriver_js_execute_code') is not None and watch.get('webdriver_js_execute_code').strip():
             fetcher.webdriver_js_execute_code = watch.get('webdriver_js_execute_code')
 
-        # requests for PDF's, images etc should be passwd the is_binary flag
-        is_binary = watch.is_pdf
-
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'), is_binary=is_binary)
+        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'))
         fetcher.quit()
 
         self.screenshot = fetcher.screenshot
         self.xpath_data = fetcher.xpath_data
 
-        # Track the content type
-        update_obj['content_type'] = fetcher.headers.get('Content-Type', '')
-
-        # Watches added automatically in the queue manager will skip if its the same checksum as the previous run
-        # Saves a lot of CPU
-        update_obj['previous_md5_before_filters'] = hashlib.md5(fetcher.content.encode('utf-8')).hexdigest()
-        if skip_when_checksum_same:
-            if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
-                raise fetchers.exceptions.checksumFromPreviousCheckWasTheSame()
-
-
         # Fetching complete, now filters
         # @todo move to class / maybe inside of fetcher abstract base?
 
@@ -170,32 +140,7 @@ class perform_site_check(difference_detection_processor):
             is_html = False
             is_json = False
 
-        if watch.is_pdf or 'application/pdf' in fetcher.headers.get('Content-Type', '').lower():
-            from shutil import which
-            tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
-            if not which(tool):
-                raise PDFToHTMLToolNotFound("Command-line `{}` tool was not found in system PATH, was it installed?".format(tool))
-
-            import subprocess
-            proc = subprocess.Popen(
-                [tool, '-stdout', '-', '-s', 'out.pdf', '-i'],
-                stdout=subprocess.PIPE,
-                stdin=subprocess.PIPE)
-            proc.stdin.write(fetcher.raw_content)
-            proc.stdin.close()
-            fetcher.content = proc.stdout.read().decode('utf-8')
-            proc.wait(timeout=60)
-
-            # Add a little metadata so we know if the file changes (like if an image changes, but the text is the same
-            # @todo may cause problems with non-UTF8?
-            metadata = "<p>Added by changedetection.io: Document checksum - {} Filesize - {} bytes</p>".format(
-                hashlib.md5(fetcher.raw_content).hexdigest().upper(),
-                len(fetcher.content))
-
-            fetcher.content = fetcher.content.replace('</body>', metadata + '</body>')
-
-
-        include_filters_rule = deepcopy(watch.get('include_filters', []))
+        include_filters_rule = watch.get('include_filters', [])
         # include_filters_rule = watch['include_filters']
         subtractive_selectors = watch.get(
             "subtractive_selectors", []
@@ -203,10 +148,6 @@ class perform_site_check(difference_detection_processor):
             "global_subtractive_selectors", []
         )
 
-        # Inject a virtual LD+JSON price tracker rule
-        if watch.get('track_ldjson_price_data', '') == PRICE_DATA_TRACK_ACCEPT:
-            include_filters_rule.append(html_tools.LD_JSON_PRODUCT_OFFER_SELECTOR)
-
         has_filter_rule = include_filters_rule and len("".join(include_filters_rule).strip())
         has_subtractive_selectors = subtractive_selectors and len(subtractive_selectors[0].strip())
 
@@ -214,14 +155,6 @@ class perform_site_check(difference_detection_processor):
             include_filters_rule.append("json:$")
             has_filter_rule = True
 
-        if is_json:
-            # Sort the JSON so we dont get false alerts when the content is just re-ordered
-            try:
-                fetcher.content = json.dumps(json.loads(fetcher.content), sort_keys=True)
-            except Exception as e:
-                # Might have just been a snippet, or otherwise bad JSON, continue
-                pass
-
         if has_filter_rule:
             json_filter_prefixes = ['json:', 'jq:']
             for filter in include_filters_rule:
@@ -229,8 +162,6 @@ class perform_site_check(difference_detection_processor):
                     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:
 
             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
@@ -242,13 +173,9 @@ class perform_site_check(difference_detection_processor):
                 # Don't run get_text or xpath/css filters on plaintext
                 stripped_text_from_html = html_content
             else:
-                # Does it have some ld+json price data? used for easier monitoring
-                update_obj['has_ldjson_price_data'] = html_tools.has_ldjson_product_info(fetcher.content)
-
                 # Then we assume HTML
                 if has_filter_rule:
                     html_content = ""
-
                     for filter_rule in include_filters_rule:
                         # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
                         if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
@@ -281,38 +208,10 @@ class perform_site_check(difference_detection_processor):
         # Re #340 - return the content before the 'ignore text' was applied
         text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
-
-        # @todo whitespace coming from missing rtrim()?
-        # stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
-        # Rewrite's the processing text based on only what diff result they want to see
-        if watch.has_special_diff_filter_options_set() and len(watch.history.keys()):
-            # Now the content comes from the diff-parser and not the returned HTTP traffic, so could be some differences
-            from .. import diff
-            # needs to not include (added) etc or it may get used twice
-            # Replace the processed text with the preferred result
-            rendered_diff = diff.render_diff(previous_version_file_contents=watch.get_last_fetched_before_filters(),
-                                                       newest_version_file_contents=stripped_text_from_html,
-                                                       include_equal=False,  # not the same lines
-                                                       include_added=watch.get('filter_text_added', True),
-                                                       include_removed=watch.get('filter_text_removed', True),
-                                                       include_replaced=watch.get('filter_text_replaced', True),
-                                                       line_feed_sep="\n",
-                                                       include_change_type_prefix=False)
-
-            watch.save_last_fetched_before_filters(text_content_before_ignored_filter)
-
-            if not rendered_diff and stripped_text_from_html:
-                # We had some content, but no differences were found
-                # Store our new file as the MD5 so it will trigger in the future
-                c = hashlib.md5(text_content_before_ignored_filter.translate(None, b'\r\n\t ')).hexdigest()
-                return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8')
-            else:
-                stripped_text_from_html = rendered_diff
-
         # Treat pages with no renderable text content as a change? No by default
         empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
         if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
-            raise fetchers.exceptions.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot)
+            raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot)
 
         # We rely on the actual text in the html output.. many sites have random script vars etc,
         # in the future we'll implement other mechanisms.
@@ -367,7 +266,6 @@ class perform_site_check(difference_detection_processor):
             blocked = True
             # Filter and trigger works the same, so reuse it
             # It should return the line numbers that match
-            # Unblock flow if the trigger was found (some text remained after stripped what didnt match)
             result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
                                                   wordlist=trigger_text,
                                                   mode="line numbers")

changedetectionio/fetchers/__init__.py

@@ -1,150 +0,0 @@
-from abc import abstractmethod
-import os
-from . import exceptions
-
-visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4, header, footer, section, article, aside, details, main, nav, section, summary'
-
-
-class Fetcher():
-    browser_steps = None
-    browser_steps_screenshot_path = None
-    content = None
-    error = None
-    fetcher_description = "No description"
-    headers = None
-    status_code = None
-    webdriver_js_execute_code = None
-    xpath_data = None
-    xpath_element_js = ""
-    instock_data = None
-    instock_data_js = ""
-
-    # Will be needed in the future by the VisualSelector, always get this where possible.
-    screenshot = False
-    system_http_proxy = os.getenv('HTTP_PROXY')
-    system_https_proxy = os.getenv('HTTPS_PROXY')
-
-    # Time ONTOP of the system defined env minimum time
-    render_extract_delay = 0
-
-    def __init__(self):
-        from pkg_resources import resource_string
-        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
-        self.xpath_element_js = resource_string(__name__, "../res/xpath_element_scraper.js").decode('utf-8')
-        self.instock_data_js = resource_string(__name__, "../res/stock-not-in-stock.js").decode('utf-8')
-
-
-    @abstractmethod
-    def get_error(self):
-        return self.error
-
-    @abstractmethod
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-        # Should set self.error, self.status_code and self.content
-        pass
-
-    @abstractmethod
-    def quit(self):
-        return
-
-    @abstractmethod
-    def get_last_status_code(self):
-        return self.status_code
-
-    @abstractmethod
-    def screenshot_step(self, step_n):
-        return None
-
-    @abstractmethod
-    # Return true/false if this checker is ready to run, in the case it needs todo some special config check etc
-    def is_ready(self):
-        return True
-
-    def iterate_browser_steps(self):
-        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
-        from playwright._impl._api_types import TimeoutError
-        from jinja2 import Environment
-        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
-
-        step_n = 0
-
-        if self.browser_steps is not None and len(self.browser_steps):
-            interface = steppable_browser_interface()
-            interface.page = self.page
-
-            valid_steps = filter(lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'), self.browser_steps)
-
-            for step in valid_steps:
-                step_n += 1
-                print(">> Iterating check - browser Step n {} - {}...".format(step_n, step['operation']))
-                self.screenshot_step("before-"+str(step_n))
-                self.save_step_html("before-"+str(step_n))
-                try:
-                    optional_value = step['optional_value']
-                    selector = step['selector']
-                    # Support for jinja2 template in step values, with date module added
-                    if '{%' in step['optional_value'] or '{{' in step['optional_value']:
-                        optional_value = str(jinja2_env.from_string(step['optional_value']).render())
-                    if '{%' in step['selector'] or '{{' in step['selector']:
-                        selector = str(jinja2_env.from_string(step['selector']).render())
-
-                    getattr(interface, "call_action")(action_name=step['operation'],
-                                                      selector=selector,
-                                                      optional_value=optional_value)
-                    self.screenshot_step(step_n)
-                    self.save_step_html(step_n)
-                except TimeoutError:
-                    # Stop processing here
-                    raise exceptions.BrowserStepsStepTimout(step_n=step_n)
-
-
-
-    # It's always good to reset these
-    def delete_browser_steps_screenshots(self):
-        import glob
-        if self.browser_steps_screenshot_path is not None:
-            dest = os.path.join(self.browser_steps_screenshot_path, 'step_*.jpeg')
-            files = glob.glob(dest)
-            for f in files:
-                os.unlink(f)
-
-#   Maybe for the future, each fetcher provides its own diff output, could be used for text, image
-#   the current one would return javascript output (as we use JS to generate the diff)
-#
-
-
-def available_fetchers():
-    from . import playwright, html_requests, webdriver
-
-    p = []
-    p.append(tuple(['html_requests', html_requests.fetcher.fetcher_description]))
-
-    # Prefer playwright
-    if os.getenv('PLAYWRIGHT_DRIVER_URL', False):
-        p.append(tuple(['html_webdriver', playwright.fetcher.fetcher_description]))
-
-    elif os.getenv('WEBDRIVER_URL'):
-        p.append(tuple(['html_webdriver', webdriver.fetcher.fetcher_description]))
-
-
-    return p
-
-html_webdriver = None
-# Decide which is the 'real' HTML webdriver, this is more a system wide config rather than site-specific.
-use_playwright_as_chrome_fetcher = os.getenv('PLAYWRIGHT_DRIVER_URL', False)
-if use_playwright_as_chrome_fetcher:
-    from . import playwright
-    html_webdriver = getattr(playwright, "fetcher")
-
-else:
-    from . import webdriver
-    html_webdriver = getattr(webdriver, "fetcher")
-

changedetectionio/fetchers/browserless.py

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

changedetectionio/fetchers/exceptions.py

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

changedetectionio/fetchers/html_requests.py

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

changedetectionio/fetchers/playwright.py

@@ -1,208 +0,0 @@
-from . import Fetcher
-from . import exceptions
-from . import visualselector_xpath_selectors
-
-import os
-import logging
-import time
-
-class fetcher(Fetcher):
-    fetcher_description = "Playwright {}/Javascript".format(
-        os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
-    )
-    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
-        fetcher_description += " via '{}'".format(os.getenv("PLAYWRIGHT_DRIVER_URL"))
-
-    browser_type = ''
-    command_executor = ''
-
-    # Configs for Proxy setup
-    # In the ENV vars, is prefixed with "playwright_proxy_", so it is for example "playwright_proxy_server"
-    playwright_proxy_settings_mappings = ['bypass', 'server', 'username', 'password']
-
-    proxy = None
-
-    def __init__(self, proxy_override=None):
-        super().__init__()
-        import json
-
-        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
-        self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
-        self.command_executor = os.getenv(
-            "PLAYWRIGHT_DRIVER_URL",
-            'ws://playwright-chrome:3000'
-        ).strip('"')
-
-        # If any proxy settings are enabled, then we should setup the proxy object
-        proxy_args = {}
-        for k in self.playwright_proxy_settings_mappings:
-            v = os.getenv('playwright_proxy_' + k, False)
-            if v:
-                proxy_args[k] = v.strip('"')
-
-        if proxy_args:
-            self.proxy = proxy_args
-
-        # allow per-watch proxy selection override
-        if proxy_override:
-            self.proxy = {'server': proxy_override}
-
-        if self.proxy:
-            # Playwright needs separate username and password values
-            from urllib.parse import urlparse
-            parsed = urlparse(self.proxy.get('server'))
-            if parsed.username:
-                self.proxy['username'] = parsed.username
-                self.proxy['password'] = parsed.password
-
-    def screenshot_step(self, step_n=''):
-        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=85)
-
-        if self.browser_steps_screenshot_path is not None:
-            destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.jpeg'.format(step_n))
-            logging.debug("Saving step screenshot to {}".format(destination))
-            with open(destination, 'wb') as f:
-                f.write(screenshot)
-
-    def save_step_html(self, step_n):
-        content = self.page.content()
-        destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.html'.format(step_n))
-        logging.debug("Saving step HTML to {}".format(destination))
-        with open(destination, 'w') as f:
-            f.write(content)
-
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-
-        from playwright.sync_api import sync_playwright
-        import playwright._impl._api_types
-        import json
-
-        self.delete_browser_steps_screenshots()
-        response = None
-        with sync_playwright() as p:
-            browser_type = getattr(p, self.browser_type)
-
-            # Seemed to cause a connection Exception even tho I can see it connect
-            # self.browser = browser_type.connect(self.command_executor, timeout=timeout*1000)
-            # 60,000 connection timeout only
-            browser = browser_type.connect_over_cdp(self.command_executor, timeout=60000)
-
-            # Set user agent to prevent Cloudflare from blocking the browser
-            # Use the default one configured in the App.py model that's passed from fetch_site_status.py
-            context = browser.new_context(
-                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
-                proxy=self.proxy,
-                # This is needed to enable JavaScript execution on GitHub and others
-                bypass_csp=True,
-                # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
-                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
-                # Should never be needed
-                accept_downloads=False
-            )
-
-            self.page = context.new_page()
-            if len(request_headers):
-                context.set_extra_http_headers(request_headers)
-
-                self.page.set_default_navigation_timeout(90000)
-                self.page.set_default_timeout(90000)
-
-                # Listen for all console events and handle errors
-                self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
-
-            # Goto page
-            try:
-                # Wait_until = commit
-                # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
-                # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
-                # This seemed to solve nearly all 'TimeoutErrors'
-                response = self.page.goto(url, wait_until='commit')
-            except playwright._impl._api_types.Error as e:
-                # Retry once - https://github.com/browserless/chrome/issues/2485
-                # Sometimes errors related to invalid cert's and other can be random
-                print ("Content Fetcher > retrying request got error - ", str(e))
-                time.sleep(1)
-                response = self.page.goto(url, wait_until='commit')
-
-            except Exception as e:
-                print ("Content Fetcher > Other exception when page.goto", str(e))
-                context.close()
-                browser.close()
-                raise exceptions.PageUnloadable(url=url, status_code=None, message=str(e))
-
-            # Execute any browser steps
-            try:
-                extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-                self.page.wait_for_timeout(extra_wait * 1000)
-
-                if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
-                    self.page.evaluate(self.webdriver_js_execute_code)
-
-            except playwright._impl._api_types.TimeoutError as e:
-                context.close()
-                browser.close()
-                # This can be ok, we will try to grab what we could retrieve
-                pass
-            except Exception as e:
-                print ("Content Fetcher > Other exception when executing custom JS code", str(e))
-                context.close()
-                browser.close()
-                raise exceptions.PageUnloadable(url=url, status_code=None, message=str(e))
-
-            if response is None:
-                context.close()
-                browser.close()
-                print ("Content Fetcher > Response object was none")
-                raise exceptions.EmptyReply(url=url, status_code=None)
-
-            # Run Browser Steps here
-            self.iterate_browser_steps()
-
-            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-            time.sleep(extra_wait)
-
-            self.content = self.page.content()
-            self.status_code = response.status
-            if len(self.page.content().strip()) == 0:
-                context.close()
-                browser.close()
-                print ("Content Fetcher > Content was empty")
-                raise exceptions.EmptyReply(url=url, status_code=response.status)
-
-            self.status_code = response.status
-            self.headers = response.all_headers()
-
-            # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
-            if current_include_filters is not None:
-                self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
-            else:
-                self.page.evaluate("var include_filters=''")
-
-            self.xpath_data = self.page.evaluate("async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
-            self.instock_data = self.page.evaluate("async () => {" + self.instock_data_js + "}")
-
-            # Bug 3 in Playwright screenshot handling
-            # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
-            # JPEG is better here because the screenshots can be very very large
-
-            # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
-            # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
-            # acceptable screenshot quality here
-            try:
-                # The actual screenshot
-                self.screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
-            except Exception as e:
-                context.close()
-                browser.close()
-                raise exceptions.ScreenshotUnavailable(url=url, status_code=None)
-
-            context.close()
-            browser.close()

changedetectionio/fetchers/webdriver.py

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

changedetectionio/forms.py

@@ -21,6 +21,7 @@ from wtforms.validators import ValidationError
 # each select <option data-enabled="enabled-0-0"
 from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
 
+from changedetectionio import content_fetcher
 from changedetectionio.notification import (
     valid_notification_formats,
 )
@@ -134,31 +135,30 @@ class ValidateContentFetcherIsReady(object):
 
     def __call__(self, form, field):
         import urllib3.exceptions
-        import importlib
+        from changedetectionio import content_fetcher
 
         # Better would be a radiohandler that keeps a reference to each class
-        if field.data is not None and field.data != 'system':
-            from . import fetchers
-            if fetchers.html_webdriver is not None:
-                try:
-                    driver = fetchers.html_webdriver()
-                    driver.is_ready()
+        if field.data is not None:
+            klass = getattr(content_fetcher, field.data)
+            some_object = klass()
+            try:
+                ready = some_object.is_ready()
 
-                except urllib3.exceptions.MaxRetryError as e:
-                    driver_url = fetchers.html_webdriver.command_executor
-                    message = field.gettext('Content fetcher \'%s\' did not respond.' % (field.data))
-                    message += '<br>' + field.gettext(
-                        'Be sure that the selenium/webdriver runner is running and accessible via network from this container/host.')
-                    message += '<br>' + field.gettext('Did you follow the instructions in the wiki?')
-                    message += '<br><br>' + field.gettext('WebDriver Host: %s' % (driver_url))
-                    message += '<br><a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">Go here for more information</a>'
-                    message += '<br>'+field.gettext('Content fetcher did not respond properly, unable to use it.\n %s' % (str(e)))
+            except urllib3.exceptions.MaxRetryError as e:
+                driver_url = some_object.command_executor
+                message = field.gettext('Content fetcher \'%s\' did not respond.' % (field.data))
+                message += '<br/>' + field.gettext(
+                    'Be sure that the selenium/webdriver runner is running and accessible via network from this container/host.')
+                message += '<br/>' + field.gettext('Did you follow the instructions in the wiki?')
+                message += '<br/><br/>' + field.gettext('WebDriver Host: %s' % (driver_url))
+                message += '<br/><a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">Go here for more information</a>'
+                message += '<br/>'+field.gettext('Content fetcher did not respond properly, unable to use it.\n %s' % (str(e)))
 
-                    raise ValidationError(message)
+                raise ValidationError(message)
 
-                except Exception as e:
-                    message = field.gettext('Content fetcher \'%s\' did not respond properly, unable to use it.\n %s')
-                    raise ValidationError(message % (field.data, e))
+            except Exception as e:
+                message = field.gettext('Content fetcher \'%s\' did not respond properly, unable to use it.\n %s')
+                raise ValidationError(message % (field.data, e))
 
 
 class ValidateNotificationBodyAndTitleWhenURLisSet(object):
@@ -193,7 +193,7 @@ class ValidateAppRiseServers(object):
                 message = field.gettext('\'%s\' is not a valid AppRise URL.' % (server_url))
                 raise ValidationError(message)
 
-class ValidateJinja2Template(object):
+class ValidateTokensList(object):
     """
     Validates that a {token} is from a valid set
     """
@@ -202,24 +202,11 @@ class ValidateJinja2Template(object):
 
     def __call__(self, form, field):
         from changedetectionio import notification
-
-        from jinja2 import Environment, BaseLoader, TemplateSyntaxError
-        from jinja2.meta import find_undeclared_variables
-
-
-        try:
-            jinja2_env = Environment(loader=BaseLoader)
-            jinja2_env.globals.update(notification.valid_tokens)
-            rendered = jinja2_env.from_string(field.data).render()
-        except TemplateSyntaxError as e:
-            raise ValidationError(f"This is not a valid Jinja2 template: {e}") from e
-
-        ast = jinja2_env.parse(field.data)
-        undefined = ", ".join(find_undeclared_variables(ast))
-        if undefined:
-            raise ValidationError(
-                f"The following tokens used in the notification are not valid: {undefined}"
-            )
+        regex = re.compile('{.*?}')
+        for p in re.findall(regex, field.data):
+            if not p.strip('{}') in notification.valid_tokens:
+                message = field.gettext('Token \'%s\' is not a valid token.')
+                raise ValidationError(message % (p))
 
 class validateURL(object):
 
@@ -232,18 +219,12 @@ class validateURL(object):
 
     def __call__(self, form, field):
         import validators
-
         try:
             validators.url(field.data.strip())
         except validators.ValidationFailure:
             message = field.gettext('\'%s\' is not a valid URL.' % (field.data.strip()))
             raise ValidationError(message)
 
-        from .model.Watch import is_safe_url
-        if not is_safe_url(field.data):
-            raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX')
-
-
 class ValidateListRegex(object):
     """
     Validates that anything that looks like a regex passes as a regex
@@ -344,30 +325,22 @@ class ValidateCSSJSONXPATHInput(object):
                     raise ValidationError("A system-error occurred when validating your jq expression")
 
 class quickWatchForm(Form):
-    from . import processors
-
     url = fields.URLField('URL', validators=[validateURL()])
     tag = StringField('Group tag', [validators.Optional()])
     watch_submit_button = SubmitField('Watch', render_kw={"class": "pure-button pure-button-primary"})
-    processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
     edit_and_watch_submit_button = SubmitField('Edit > Watch', render_kw={"class": "pure-button pure-button-primary"})
 
 
 # Common to a single watch and the global settings
 class commonSettingsForm(Form):
-    from .fetchers import available_fetchers
-    notification_urls = StringListField('Notification URL List', validators=[validators.Optional(), ValidateAppRiseServers()])
-    notification_title = StringField('Notification Title', default='ChangeDetection.io Notification - {{ watch_url }}', validators=[validators.Optional(), ValidateJinja2Template()])
-    notification_body = TextAreaField('Notification Body', default='{{ watch_url }} had a change.', validators=[validators.Optional(), ValidateJinja2Template()])
+    notification_urls = StringListField('Notification URL list', validators=[validators.Optional(), ValidateAppRiseServers()])
+    notification_title = StringField('Notification title', validators=[validators.Optional(), ValidateTokensList()])
+    notification_body = TextAreaField('Notification body', validators=[validators.Optional(), ValidateTokensList()])
     notification_format = SelectField('Notification format', choices=valid_notification_formats.keys())
-    fetch_backend = RadioField(u'Fetch Method', choices=available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    fetch_backend = RadioField(u'Fetch method', choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     extract_title_as_title = BooleanField('Extract <title> from document and use as watch title', default=False)
     webdriver_delay = IntegerField('Wait seconds before extracting text', validators=[validators.Optional(), validators.NumberRange(min=1,
                                                                                                                                     message="Should contain one or more seconds")])
-class importForm(Form):
-    from . import processors
-    processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
-    urls = TextAreaField('URLs')
 
 class SingleBrowserStep(Form):
 
@@ -400,19 +373,11 @@ class watchForm(commonSettingsForm):
     body = TextAreaField('Request body', [validators.Optional()])
     method = SelectField('Request method', choices=valid_method, default=default_method)
     ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
-    check_unique_lines = BooleanField('Only trigger when unique lines appear', default=False)
-
-    filter_text_added = BooleanField('Added lines', default=True)
-    filter_text_replaced = BooleanField('Replaced/changed lines', default=True)
-    filter_text_removed = BooleanField('Removed lines', default=True)
-
-    # @todo this class could be moved to its own text_json_diff_watchForm and this goes to restock_diff_Watchform perhaps
-    in_stock_only = BooleanField('Only trigger when product goes BACK to in-stock', default=True)
-
+    check_unique_lines = BooleanField('Only trigger when new lines appear', default=False)
     trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
     if os.getenv("PLAYWRIGHT_DRIVER_URL"):
         browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
-    text_should_not_be_present = StringListField('Block change-detection while text matches', [validators.Optional(), ValidateListRegex()])
+    text_should_not_be_present = StringListField('Block change-detection if text matches', [validators.Optional(), ValidateListRegex()])
     webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
 
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
@@ -447,13 +412,6 @@ class watchForm(commonSettingsForm):
         return result
 
 
-class SingleExtraProxy(Form):
-
-    # maybe better to set some <script>var..
-    proxy_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
-    proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "http://user:pass@...:3128", "size":50})
-    # @todo do the validation here instead
-
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
     time_between_check = FormField(TimeBetweenCheckForm)
@@ -461,30 +419,21 @@ class globalSettingsRequestForm(Form):
     jitter_seconds = IntegerField('Random jitter seconds ± check',
                                   render_kw={"style": "width: 5em;"},
                                   validators=[validators.NumberRange(min=0, message="Should contain zero or more seconds")])
-    extra_proxies = FieldList(FormField(SingleExtraProxy), min_entries=5)
-
-    def validate_extra_proxies(self, extra_validators=None):
-        for e in self.data['extra_proxies']:
-            if e.get('proxy_name') or e.get('proxy_url'):
-                if not e.get('proxy_name','').strip() or not e.get('proxy_url','').strip():
-                    self.extra_proxies.errors.append('Both a name, and a Proxy URL is required.')
-                    return False
-
 
 # datastore.data['settings']['application']..
 class globalSettingsApplicationForm(commonSettingsForm):
-    from .fetchers import available_fetchers
-    api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
+
     base_url = StringField('Base URL', validators=[validators.Optional()])
-    empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
-    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=available_fetchers(), validators=[ValidateContentFetcherIsReady()])
-    global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
     global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
+    global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
     ignore_whitespace = BooleanField('Ignore whitespace')
-    password = SaltyPasswordField()
     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)
-    shared_diff_access = BooleanField('Allow access to view diff page when password is enabled', default=False, validators=[validators.Optional()])
+    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
+    password = SaltyPasswordField()
+
     filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',
                                                                   render_kw={"style": "width: 5em;"},
                                                                   validators=[validators.NumberRange(min=0,

changedetectionio/html_tools.py

@@ -8,11 +8,7 @@ import json
 import re
 
 # HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
-TEXT_FILTER_LIST_LINE_SUFFIX = "<br>"
-
-# 'price' , 'lowPrice', 'highPrice' are usually under here
-# all of those may or may not appear on different websites
-LD_JSON_PRODUCT_OFFER_SELECTOR = "json:$..offers"
+TEXT_FILTER_LIST_LINE_SUFFIX = "<br/>"
 
 class JSONNotFound(ValueError):
     def __init__(self, msg):
@@ -131,10 +127,8 @@ def _get_stripped_text_from_json_match(match):
 
     return stripped_text_from_html
 
-# content - json
-# json_filter - ie json:$..price
-# ensure_is_ldjson_info_type - str "product", optional, "@type == product" (I dont know how to do that as a json selector)
-def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None):
+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>
@@ -145,12 +139,7 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
         # Foreach <script json></script> blob.. just return the first that matches json_filter
         s = []
         soup = BeautifulSoup(content, 'html.parser')
-
-        if ensure_is_ldjson_info_type:
-            bs_result = soup.findAll('script', {"type": "application/ld+json"})
-        else:
-            bs_result = soup.findAll('script')
-
+        bs_result = soup.findAll('script')
 
         if not bs_result:
             raise JSONNotFound("No parsable JSON found in this document")
@@ -167,14 +156,7 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
                 continue
             else:
                 stripped_text_from_html = _parse_json(json_data, json_filter)
-                if ensure_is_ldjson_info_type:
-                    # Could sometimes be list, string or something else random
-                    if isinstance(json_data, dict):
-                        # If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
-                        # (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
-                        if json_data.get('@type', False) and json_data.get('@type','').lower() == ensure_is_ldjson_info_type.lower() and stripped_text_from_html:
-                            break
-                elif stripped_text_from_html:
+                if stripped_text_from_html:
                     break
 
     if not stripped_text_from_html:
@@ -261,18 +243,6 @@ def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
 
     return text_content
 
-
-# Does LD+JSON exist with a @type=='product' and a .price set anywhere?
-def has_ldjson_product_info(content):
-    try:
-        pricing_data = extract_json_as_string(content=content, json_filter=LD_JSON_PRODUCT_OFFER_SELECTOR, ensure_is_ldjson_info_type="product")
-    except JSONNotFound as e:
-        # Totally fine
-        return False
-    x=bool(pricing_data)
-    return x
-
-
 def workarounds_for_obfuscations(content):
     """
     Some sites are using sneaky tactics to make prices and other information un-renderable by Inscriptis
@@ -287,18 +257,3 @@ def workarounds_for_obfuscations(content):
     content = re.sub('<!--\s+-->', '', content)
 
     return content
-
-
-def get_triggered_text(content, trigger_text):
-    triggered_text = []
-    result = strip_ignore_text(content=content,
-                               wordlist=trigger_text,
-                               mode="line numbers")
-
-    i = 1
-    for p in content.splitlines():
-        if i in result:
-            triggered_text.append(p)
-        i += 1
-
-    return triggered_text

changedetectionio/importer.py

@@ -29,7 +29,6 @@ class import_url_list(Importer):
             data,
             flash,
             datastore,
-            processor=None
             ):
 
         urls = data.split("\n")
@@ -53,11 +52,7 @@ class import_url_list(Importer):
             # Flask wtform validators wont work with basic auth, use validators package
             # Up to 5000 per batch so we dont flood the server
             if len(url) and validators.url(url.replace('source:', '')) and good < 5000:
-                extras = None
-                if processor:
-                    extras = {'processor': processor}
-                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False, extras=extras)
-
+                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False)
                 if new_uuid:
                     # Straight into the queue.
                     self.new_uuids.append(new_uuid)

changedetectionio/model/App.py

@@ -15,12 +15,11 @@ class model(dict):
                 'headers': {
                 },
                 'requests': {
-                    'extra_proxies': [], # Configurable extra proxies via the UI
-                    'jitter_seconds': 0,
-                    'proxy': None, # Preferred proxy connection
-                    'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
                     'timeout': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
+                    'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
+                    'jitter_seconds': 0,
                     'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "10")),  # Number of threads, lower is better for slow connections
+                    'proxy': None # Preferred proxy connection
                 },
                 'application': {
                     'api_access_token_enabled': True,
@@ -28,6 +27,7 @@ class model(dict):
                     'base_url' : None,
                     'extract_title_as_title': False,
                     'empty_pages_are_a_change': False,
+                    'css_dark_mode': 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
@@ -40,7 +40,6 @@ class model(dict):
                     'notification_body': default_notification_body,
                     'notification_format': default_notification_format,
                     'schema_version' : 0,
-                    'shared_diff_access': False,
                     'webdriver_delay': None  # Extra delay in seconds before extracting text
                 }
             }

changedetectionio/model/Watch.py

@@ -1,14 +1,9 @@
 from distutils.util import strtobool
 import logging
 import os
-import re
 import time
 import uuid
 
-# Allowable protocols, protects against javascript: etc
-# file:// is further checked by ALLOW_FILE_URI
-SAFE_PROTOCOL_REGEX='^(http|https|ftp|file):'
-
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
 mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
 
@@ -16,79 +11,57 @@ from changedetectionio.notification import (
     default_notification_format_for_watch
 )
 
-base_config = {
-    'body': None,
-    'check_unique_lines': False,  # On change-detected, compare against all history if its something new
-    'check_count': 0,
-    'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
-    'extract_text': [],  # Extract text by regex after filters
-    'extract_title_as_title': False,
-    'fetch_backend': 'system', # plaintext, playwright etc
-    'processor': 'text_json_diff', # could be restock_diff or others from .processors
-    'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
-    'filter_text_added': True,
-    'filter_text_replaced': True,
-    'filter_text_removed': True,
-    'has_ldjson_price_data': None,
-    'track_ldjson_price_data': None,
-    'headers': {},  # Extra headers to send
-    'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
-    'in_stock_only' : True, # Only trigger change on going to instock from out-of-stock
-    '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_screenshot': False,  # Include the latest screenshot if available and supported by the apprise URL
-    'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
-    'paused': False,
-    'previous_md5': False,
-    'previous_md5_before_filters': False,  # Used for skipping changedetection entirely
-    '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},
-    'title': None,
-    'trigger_text': [],  # List of text or regex to wait for until a change is detected
-    'url': '',
-    'uuid': str(uuid.uuid4()),
-    'webdriver_delay': None,
-    'webdriver_js_execute_code': None,  # Run before change-detection
-}
-
-
-def is_safe_url(test_url):
-    # See https://github.com/dgtlmoon/changedetection.io/issues/1358
-
-    # Remove 'source:' prefix so we dont get 'source:javascript:' etc
-    # 'source:' is a valid way to tell us to return the source
-
-    r = re.compile(re.escape('source:'), re.IGNORECASE)
-    test_url = r.sub('', test_url)
-
-    pattern = re.compile(os.getenv('SAFE_PROTOCOL_REGEX', SAFE_PROTOCOL_REGEX), re.IGNORECASE)
-    if not pattern.match(test_url.strip()):
-        return False
-
-    return True
 
 class model(dict):
     __newest_history_key = None
-    __history_n = 0
+    __history_n=0
+    __base_config = {
+            #'history': {},  # Dict of timestamp and output stripped filename (removed)
+            #'newest_history_key': 0, (removed, taken from history.txt index)
+            'body': None,
+            'check_unique_lines': False, # On change-detected, compare against all history if its something new
+            'check_count': 0,
+            'consecutive_filter_failures': 0, # Every time the CSS/xPath filter cannot be located, reset when all is fine.
+            'extract_text': [],  # Extract text by regex after filters
+            'extract_title_as_title': False,
+            'fetch_backend': None,
+            'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
+            'headers': {},  # Extra headers to send
+            'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+            '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_screenshot': False, # Include the latest screenshot if available and supported by the apprise URL
+            '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},
+            '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
+        }
     jitter_seconds = 0
 
     def __init__(self, *arg, **kw):
 
-        self.update(base_config)
+        self.update(self.__base_config)
         self.__datastore_path = kw['datastore_path']
 
         self['uuid'] = str(uuid.uuid4())
@@ -119,11 +92,7 @@ class model(dict):
 
     @property
     def link(self):
-
         url = self.get('url', '')
-        if not is_safe_url(url):
-            return 'DISABLED'
-
         ready_url = url
         if '{%' in url or '{{' in url:
             from jinja2 import Environment
@@ -142,26 +111,6 @@ class model(dict):
 
         return ready_url
 
-    @property
-    def get_fetch_backend(self):
-        """
-        Like just using the `fetch_backend` key but there could be some logic
-        :return:
-        """
-        # Maybe also if is_image etc?
-        # This is because chrome/playwright wont render the PDF in the browser and we will just fetch it and use pdf2html to see the text.
-        if self.is_pdf:
-            return 'html_requests'
-
-        return self.get('fetch_backend')
-
-    @property
-    def is_pdf(self):
-        # content_type field is set in the future
-        # https://github.com/dgtlmoon/changedetection.io/issues/1392
-        # Not sure the best logic here
-        return self.get('url', '').lower().endswith('.pdf') or 'pdf' in self.get('content_type', '').lower()
-
     @property
     def label(self):
         # Used for sorting
@@ -244,32 +193,9 @@ class model(dict):
         bump = self.history
         return self.__newest_history_key
 
-    def get_history_snapshot(self, timestamp):
-        import brotli
-        filepath = self.history[timestamp]
-
-        # See if a brotli versions exists and switch to that
-        if not filepath.endswith('.br') and os.path.isfile(f"{filepath}.br"):
-            filepath = f"{filepath}.br"
-
-        # OR in the backup case that the .br does not exist, but the plain one does
-        if filepath.endswith('.br') and not os.path.isfile(filepath):
-            if os.path.isfile(filepath.replace('.br', '')):
-                filepath = filepath.replace('.br', '')
-
-        if filepath.endswith('.br'):
-            # Brotli doesnt have a fileheader to detect it, so we rely on filename
-            # https://www.rfc-editor.org/rfc/rfc7932
-            with open(filepath, 'rb') as f:
-                return(brotli.decompress(f.read()).decode('utf-8'))
-
-        with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
-            return f.read()
-
     # 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, snapshot_id):
-        import brotli
+    def save_history_text(self, contents, timestamp):
 
         self.ensure_data_dir_exists()
 
@@ -278,21 +204,13 @@ class model(dict):
         if self.__newest_history_key and int(timestamp) == int(self.__newest_history_key):
             time.sleep(timestamp - self.__newest_history_key)
 
-        threshold = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
-        skip_brotli = strtobool(os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False'))
+        snapshot_fname = "{}.txt".format(str(uuid.uuid4()))
 
-        if not skip_brotli and len(contents) > threshold:
-            snapshot_fname = f"{snapshot_id}.txt.br"
-            dest = os.path.join(self.watch_data_dir, snapshot_fname)
-            if not os.path.exists(dest):
-                with open(dest, 'wb') as f:
-                    f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
-        else:
-            snapshot_fname = f"{snapshot_id}.txt"
-            dest = os.path.join(self.watch_data_dir, snapshot_fname)
-            if not os.path.exists(dest):
-                with open(dest, 'wb') as f:
-                    f.write(contents)
+        # 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
@@ -329,8 +247,7 @@ class model(dict):
         # Compare each lines (set) against each history text file (set) looking for something new..
         existing_history = set({})
         for k, v in self.history.items():
-            content = self.get_history_snapshot(k)
-            alist = set([line.strip().lower() for line in content.splitlines()])
+            alist = set([line.decode('utf-8').strip().lower() for line in open(v, 'rb')])
             existing_history = existing_history.union(alist)
 
         # Check that everything in local_lines(new stuff) already exists in existing_history - it should
@@ -345,6 +262,17 @@ class model(dict):
         # False is not an option for AppRise, must be type None
         return None
 
+    def get_screenshot_as_jpeg(self):
+
+        # Created by save_screenshot()
+        fname = os.path.join(self.watch_data_dir, "last-screenshot.jpg")
+        if os.path.isfile(fname):
+            return fname
+
+        # False is not an option for AppRise, must be type None
+        return None
+
+
     def __get_file_ctime(self, filename):
         fname = os.path.join(self.watch_data_dir, filename)
         if os.path.isfile(fname):
@@ -391,25 +319,6 @@ class model(dict):
             return fname
         return False
 
-
-    def pause(self):
-        self['paused'] = True
-
-    def unpause(self):
-        self['paused'] = False
-
-    def toggle_pause(self):
-        self['paused'] ^= True
-
-    def mute(self):
-        self['notification_muted'] = True
-
-    def unmute(self):
-        self['notification_muted'] = False
-
-    def toggle_mute(self):
-        self['notification_muted'] ^= True
-
     def extract_regex_from_all_history(self, regex):
         import csv
         import re
@@ -421,8 +330,8 @@ class model(dict):
         # self.history will be keyed with the full path
         for k, fname in self.history.items():
             if os.path.isfile(fname):
-                if True:
-                    contents = self.get_history_snapshot(k)
+                with open(fname, "r") as f:
+                    contents = f.read()
                     res = re.findall(regex, contents, re.MULTILINE)
                     if res:
                         if not csv_writer:
@@ -453,43 +362,3 @@ class model(dict):
             f.close()
 
         return csv_output_filename
-
-    @property
-    # Return list of tags, stripped and lowercase, used for searching
-    def all_tags(self):
-        return [s.strip().lower() for s in self.get('tag','').split(',')]
-
-    def has_special_diff_filter_options_set(self):
-
-        # All False - nothing would be done, so act like it's not processable
-        if not self.get('filter_text_added', True) and not self.get('filter_text_replaced', True) and not self.get('filter_text_removed', True):
-            return False
-
-        # Or one is set
-        if not self.get('filter_text_added', True) or not self.get('filter_text_replaced', True) or not self.get('filter_text_removed', True):
-            return True
-
-        # None is set
-        return False
-
-
-    def get_last_fetched_before_filters(self):
-        import brotli
-        filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
-
-        if not os.path.isfile(filepath):
-            # If a previous attempt doesnt yet exist, just snarf the previous snapshot instead
-            dates = list(self.history.keys())
-            if len(dates):
-                return self.get_history_snapshot(dates[-1])
-            else:
-                return ''
-
-        with open(filepath, 'rb') as f:
-            return(brotli.decompress(f.read()).decode('utf-8'))
-
-    def save_last_fetched_before_filters(self, contents):
-        import brotli
-        filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
-        with open(filepath, 'wb') as f:
-            f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))

changedetectionio/notification.py

@@ -1,28 +1,23 @@
 import apprise
-from jinja2 import Environment, BaseLoader
 from apprise import NotifyFormat
-import json
 
 valid_tokens = {
     'base_url': '',
-    'current_snapshot': '',
-    'diff': '',
-    'diff_added': '',
-    'diff_full': '',
-    'diff_removed': '',
-    'diff_url': '',
-    'preview_url': '',
-    'triggered_text': '',
-    'watch_tag': '',
-    'watch_title': '',
     'watch_url': '',
     'watch_uuid': '',
+    'watch_title': '',
+    'watch_tag': '',
+    'diff': '',
+    'diff_full': '',
+    'diff_url': '',
+    'preview_url': '',
+    '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}}'
+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,
@@ -32,67 +27,25 @@ valid_notification_formats = {
     default_notification_format_for_watch: default_notification_format_for_watch
 }
 
-# include the decorator
-from apprise.decorators import notify
-
-@notify(on="delete")
-@notify(on="deletes")
-@notify(on="get")
-@notify(on="gets")
-@notify(on="post")
-@notify(on="posts")
-@notify(on="put")
-@notify(on="puts")
-def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
-    import requests
-    url = kwargs['meta'].get('url')
-
-    if url.startswith('post'):
-        r = requests.post
-    elif url.startswith('get'):
-        r = requests.get
-    elif url.startswith('put'):
-        r = requests.put
-    elif url.startswith('delete'):
-        r = requests.delete
-
-    url = url.replace('post://', 'http://')
-    url = url.replace('posts://', 'https://')
-    url = url.replace('put://', 'http://')
-    url = url.replace('puts://', 'https://')
-    url = url.replace('get://', 'http://')
-    url = url.replace('gets://', 'https://')
-    url = url.replace('put://', 'http://')
-    url = url.replace('puts://', 'https://')
-    url = url.replace('delete://', 'http://')
-    url = url.replace('deletes://', 'https://')
-
-    # Try to auto-guess if it's JSON
-    headers = {}
-    try:
-        json.loads(body)
-        headers = {'Content-Type': 'application/json; charset=utf-8'}
-    except ValueError as e:
-        pass
-
-
-    r(url, headers=headers, data=body)
-
-
 def process_notification(n_object, datastore):
 
-    # Insert variables into the notification content
-    notification_parameters = create_notification_parameters(n_object, datastore)
-
     # Get the notification body from datastore
-    jinja2_env = Environment(loader=BaseLoader)
-    n_body = jinja2_env.from_string(n_object.get('notification_body', default_notification_body)).render(**notification_parameters)
-    n_title = jinja2_env.from_string(n_object.get('notification_title', default_notification_title)).render(**notification_parameters)
+    n_body = n_object.get('notification_body', default_notification_body)
+    n_title = n_object.get('notification_title', default_notification_title)
     n_format = valid_notification_formats.get(
         n_object['notification_format'],
         valid_notification_formats[default_notification_format],
     )
-    
+
+    # Insert variables into the notification content
+    notification_parameters = create_notification_parameters(n_object, datastore)
+
+    for n_k in notification_parameters:
+        token = '{' + n_k + '}'
+        val = notification_parameters[n_k]
+        n_title = n_title.replace(token, val)
+        n_body = n_body.replace(token, val)
+
     # https://github.com/caronc/apprise/wiki/Development_LogCapture
     # Anything higher than or equal to WARNING (which covers things like Connection errors)
     # raise it as an exception
@@ -100,7 +53,6 @@ def process_notification(n_object, datastore):
     sent_objs=[]
     from .apprise_asset import asset
     for url in n_object['notification_urls']:
-        url = jinja2_env.from_string(url).render(**notification_parameters)
         apobj = apprise.Apprise(debug=True, asset=asset)
         url = url.strip()
         if len(url):
@@ -114,19 +66,14 @@ def process_notification(n_object, datastore):
 
                 # So if no avatar_url is specified, add one so it can be correctly calculated into the total payload
                 k = '?' if not '?' in url else '&'
-                if not 'avatar_url' in url \
-                        and not url.startswith('mail') \
-                        and not url.startswith('post') \
-                        and not url.startswith('get') \
-                        and not url.startswith('delete') \
-                        and not url.startswith('put'):
+                if not 'avatar_url' in url and not url.startswith('mail'):
                     url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
 
                 if url.startswith('tgram://'):
-                    # Telegram only supports a limit subset of HTML, remove the '<br>' we place in.
+                    # Telegram only supports a limit subset of HTML, remove the '<br/>' we place in.
                     # re https://github.com/dgtlmoon/changedetection.io/issues/555
                     # @todo re-use an existing library we have already imported to strip all non-allowed tags
-                    n_body = n_body.replace('<br>', '\n')
+                    n_body = n_body.replace('<br/>', '\n')
                     n_body = n_body.replace('</br>', '\n')
                     # real limit is 4096, but minus some for extra metadata
                     payload_max_size = 3600
@@ -197,7 +144,7 @@ def create_notification_parameters(n_object, datastore):
 
     watch_url = n_object['watch_url']
 
-    # Re #148 - Some people have just {{ base_url }} in the body or title, but this may break some notification services
+    # Re #148 - Some people have just {base_url} in the body or title, but this may break some notification services
     #           like 'Join', so it's always best to atleast set something obvious so that they are not broken.
     if base_url == '':
         base_url = "<base-url-env-var-not-set>"
@@ -212,18 +159,15 @@ def create_notification_parameters(n_object, datastore):
     tokens.update(
         {
             'base_url': base_url if base_url is not None else '',
-            'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else '',
-            'diff': n_object.get('diff', ''),  # Null default in the case we use a test
-            'diff_added': n_object.get('diff_added', ''),  # Null default in the case we use a test
-            'diff_full': n_object.get('diff_full', ''),  # Null default in the case we use a test
-            'diff_removed': n_object.get('diff_removed', ''),  # Null default in the case we use a test
-            'diff_url': diff_url,
-            'preview_url': preview_url,
-            'triggered_text': n_object.get('triggered_text', ''),
-            'watch_tag': watch_tag if watch_tag is not None else '',
-            'watch_title': watch_title if watch_title is not None else '',
             'watch_url': watch_url,
             'watch_uuid': uuid,
+            'watch_title': watch_title if watch_title is not None else '',
+            'watch_tag': watch_tag if watch_tag is not None else '',
+            'diff_url': diff_url,
+            'diff': n_object.get('diff', ''),  # Null default in the case we use a test
+            'diff_full': n_object.get('diff_full', ''),  # Null default in the case we use a test
+            'preview_url': preview_url,
+            'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else ''
         })
 
     return tokens

changedetectionio/processors/README.md

@@ -1,11 +0,0 @@
-# Change detection post-processors
-
-The concept here is to be able to switch between different domain specific problems to solve.
-
-- `text_json_diff` The traditional text and JSON comparison handler
-- `restock_diff` Only cares about detecting if a product looks like it has some text that suggests that it's out of stock, otherwise assumes that it's in stock.
-
-Some suggestions for the future
-
-- `graphical` 
-- `restock_and_price` - extract price AND stock text

changedetectionio/processors/__init__.py

@@ -1,24 +0,0 @@
-from abc import abstractmethod
-import hashlib
-
-
-class difference_detection_processor():
-
-
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-
-    @abstractmethod
-    def run(self, uuid, skip_when_checksum_same=True):
-        update_obj = {'last_notification_error': False, 'last_error': False}
-        some_data = 'xxxxx'
-        update_obj["previous_md5"] = hashlib.md5(some_data.encode('utf-8')).hexdigest()
-        changed_detected = False
-        return changed_detected, update_obj, ''.encode('utf-8')
-
-
-def available_processors():
-    from . import restock_diff, text_json_diff
-    x=[('text_json_diff', text_json_diff.name), ('restock_diff', restock_diff.name)]
-    # @todo Make this smarter with introspection of sorts.
-    return x

changedetectionio/processors/restock_diff.py

@@ -1,126 +0,0 @@
-
-import hashlib
-import os
-import re
-import urllib3
-from . import difference_detection_processor
-from copy import deepcopy
-from .. import fetchers
-
-urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
-
-name = 'Re-stock detection for single product pages'
-description = 'Detects if the product goes back to in-stock'
-
-class perform_site_check(difference_detection_processor):
-    screenshot = None
-    xpath_data = None
-
-    def __init__(self, *args, datastore, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.datastore = datastore
-
-    def run(self, uuid, skip_when_checksum_same=True):
-
-        # DeepCopy so we can be sure we don't accidently change anything by reference
-        watch = deepcopy(self.datastore.data['watching'].get(uuid))
-
-        if not watch:
-            raise Exception("Watch no longer exists.")
-
-        # Protect against file:// access
-        if re.search(r'^file', watch.get('url', ''), re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
-            raise Exception(
-                "file:// type access is denied for security reasons."
-            )
-
-        # Unset any existing notification error
-        update_obj = {'last_notification_error': False, 'last_error': False}
-        extra_headers = watch.get('headers', [])
-
-        # Tweak the base config with the per-watch ones
-        request_headers = deepcopy(self.datastore.data['settings']['headers'])
-        request_headers.update(extra_headers)
-
-        # https://github.com/psf/requests/issues/4525
-        # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
-        # do this by accident.
-        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'].get('timeout')
-
-        url = watch.link
-
-        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)
-
-        # Pluggable content fetcher
-        prefer_backend = watch.get_fetch_backend
-        if not prefer_backend or prefer_backend == 'system':
-            prefer_backend = self.datastore.data['settings']['application']['fetch_backend']
-
-        if prefer_backend == 'html_webdriver':
-            preferred_fetcher = fetchers.html_webdriver
-        else:
-            from ..fetchers import html_requests
-            preferred_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))
-
-        fetcher = preferred_fetcher(proxy_override=proxy_url)
-
-        # Configurable per-watch or global extra delay before extracting text (for webDriver types)
-        system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
-        if watch['webdriver_delay'] is not None:
-            fetcher.render_extract_delay = watch.get('webdriver_delay')
-        elif system_webdriver_delay is not None:
-            fetcher.render_extract_delay = system_webdriver_delay
-
-        # Could be removed if requests/plaintext could also return some info?
-        if prefer_backend != 'html_webdriver':
-            raise Exception("Re-stock detection requires Chrome or compatible webdriver/playwright fetcher to work")
-
-        if watch.get('webdriver_js_execute_code') is not None and watch.get('webdriver_js_execute_code').strip():
-            fetcher.webdriver_js_execute_code = watch.get('webdriver_js_execute_code')
-
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'))
-        fetcher.quit()
-
-        self.screenshot = fetcher.screenshot
-        self.xpath_data = fetcher.xpath_data
-
-        # Track the content type
-        update_obj['content_type'] = fetcher.headers.get('Content-Type', '')
-        update_obj["last_check_status"] = fetcher.get_last_status_code()
-
-        # Main detection method
-        fetched_md5 = None
-        if fetcher.instock_data:
-            fetched_md5 = hashlib.md5(fetcher.instock_data.encode('utf-8')).hexdigest()
-            # 'Possibly in stock' comes from stock-not-in-stock.js when no string found above the fold.
-            update_obj["in_stock"] = True if fetcher.instock_data == 'Possibly in stock' else False
-
-
-        # The main thing that all this at the moment comes down to :)
-        changed_detected = False
-
-        if watch.get('previous_md5') and watch.get('previous_md5') != fetched_md5:
-            # Yes if we only care about it going to instock, AND we are in stock
-            if watch.get('in_stock_only') and update_obj["in_stock"]:
-                changed_detected = True
-
-            if not watch.get('in_stock_only'):
-                # All cases
-                changed_detected = True
-
-        # Always record the new checksum
-        update_obj["previous_md5"] = fetched_md5
-
-        return changed_detected, update_obj, fetcher.instock_data.encode('utf-8')

changedetectionio/queuedWatchMetaData.py

@@ -1,10 +0,0 @@
-from dataclasses import dataclass, field
-from typing import Any
-
-# So that we can queue some metadata in `item`
-# https://docs.python.org/3/library/queue.html#queue.PriorityQueue
-#
-@dataclass(order=True)
-class PrioritizedItem:
-    priority: int
-    item: Any=field(compare=False)

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

@@ -1,97 +0,0 @@
-function isItemInStock() {
-  // @todo Pass these in so the same list can be used in non-JS fetchers
-  const outOfStockTexts = [
-    '0 in stock',
-    'agotado',
-    'artikel zurzeit vergriffen',
-    'as soon as stock is available',
-    'available for back order',
-    'backordered',
-    'brak na stanie',
-    'brak w magazynie',
-    'coming soon',
-    'currently unavailable',
-    'en rupture de stock',
-    'item is no longer available',
-    'message if back in stock',
-    'nachricht bei',
-    'nicht auf lager',
-    'nicht lieferbar',
-    'nicht zur verfügung',
-    'no disponible temporalmente',
-    'no longer in stock',
-    'not available',
-    'not in stock',
-    'notify me when available',
-    'não estamos a aceitar encomendas',
-    'out of stock',
-    'out-of-stock',
-    'produkt niedostępny',
-    'sold out',
-    'temporarily out of stock',
-    'temporarily unavailable',
-    'we do not currently have an estimate of when this product will be back in stock.',
-    'zur zeit nicht an lager',
-  ];
-
-
-  const negateOutOfStockRegexs = [
-      '[0-9] in stock'
-  ]
-  var negateOutOfStockRegexs_r = [];
-  for (let i = 0; i < negateOutOfStockRegexs.length; i++) {
-    negateOutOfStockRegexs_r.push(new RegExp(negateOutOfStockRegexs[0], 'g'));
-  }
-
-
-  const elementsWithZeroChildren = Array.from(document.getElementsByTagName('*')).filter(element => element.children.length === 0);
-
-  // REGEXS THAT REALLY MEAN IT'S IN STOCK
-  for (let i = elementsWithZeroChildren.length - 1; i >= 0; i--) {
-    const element = elementsWithZeroChildren[i];
-    if (element.offsetWidth > 0 || element.offsetHeight > 0 || element.getClientRects().length > 0) {
-      var elementText="";
-      if (element.tagName.toLowerCase() === "input") {
-        elementText = element.value.toLowerCase();
-      } else {
-        elementText = element.textContent.toLowerCase();
-      }
-
-      if (elementText.length) {
-        // try which ones could mean its in stock
-        for (let i = 0; i < negateOutOfStockRegexs.length; i++) {
-          if (negateOutOfStockRegexs_r[i].test(elementText)) {
-            return 'Possibly in stock';
-          }
-        }
-      }
-    }
-  }
-
-  // OTHER STUFF THAT COULD BE THAT IT'S OUT OF STOCK
-  for (let i = elementsWithZeroChildren.length - 1; i >= 0; i--) {
-    const element = elementsWithZeroChildren[i];
-    if (element.offsetWidth > 0 || element.offsetHeight > 0 || element.getClientRects().length > 0) {
-      var elementText="";
-      if (element.tagName.toLowerCase() === "input") {
-        elementText = element.value.toLowerCase();
-      } else {
-        elementText = element.textContent.toLowerCase();
-      }
-
-      if (elementText.length) {
-        // and these mean its out of stock
-        for (const outOfStockText of outOfStockTexts) {
-          if (elementText.includes(outOfStockText)) {
-            return elementText; // item is out of stock
-          }
-        }
-      }
-    }
-  }
-
-  return 'Possibly in stock'; // possibly in stock, cant decide otherwise.
-}
-
-// returns the element text that makes it think it's out of stock
-return isItemInStock();

changedetectionio/res/xpath_element_scraper.js

@@ -1,6 +1,3 @@
-// Copyright (C) 2021 Leigh Morresi (dgtlmoon@gmail.com)
-// All rights reserved.
-
 // @file Scrape the page looking for elements of concern (%ELEMENTS%)
 // http://matatk.agrip.org.uk/tests/position-and-width/
 // https://stackoverflow.com/questions/26813480/when-is-element-getboundingclientrect-guaranteed-to-be-updated-accurate
@@ -84,16 +81,8 @@ var bbox;
 for (var i = 0; i < elements.length; i++) {
     bbox = elements[i].getBoundingClientRect();
 
-    // Exclude items that are not interactable or visible
-    if(elements[i].style.opacity === "0") {
-        continue
-    }
-    if(elements[i].style.display === "none" || elements[i].style.pointerEvents === "none" ) {
-        continue
-    }
-
-    // Skip really small ones, and where width or height ==0
-    if (bbox['width'] * bbox['height'] < 100) {
+    // Forget really small ones
+    if (bbox['width'] < 10 && bbox['height'] < 10) {
         continue;
     }
 
@@ -149,6 +138,7 @@ for (var i = 0; i < elements.length; i++) {
 
 }
 
+
 // 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 (include_filters.length) {
@@ -176,23 +166,10 @@ if (include_filters.length) {
         }
 
         if (q) {
-            // #1231 - IN the case XPath attribute filter is applied, we will have to traverse up and find the element.
-            if (q.hasOwnProperty('getBoundingClientRect')) {
-                bbox = q.getBoundingClientRect();
-                console.log("xpath_element_scraper: Got filter element, scroll from top was " + scroll_y)
-            } else {
-                try {
-                    // Try and see we can find its ownerElement
-                    bbox = q.ownerElement.getBoundingClientRect();
-                    console.log("xpath_element_scraper: Got filter by ownerElement element, scroll from top was " + scroll_y)
-                } catch (e) {
-                    console.log("xpath_element_scraper: error looking up ownerElement")
-                }
-            }
-        }
-        
-        if(!q) {
-            console.log("xpath_element_scraper: filter element " + f + " was not found");
+            bbox = q.getBoundingClientRect();
+            console.log("xpath_element_scraper: Got filter element, scroll from top was "+scroll_y)
+        } else {
+            console.log("xpath_element_scraper: filter element "+f+" was not found");
         }
 
         if (bbox && bbox['width'] > 0 && bbox['height'] > 0) {
@@ -207,9 +184,5 @@ if (include_filters.length) {
     }
 }
 
-// Sort the elements so we find the smallest one first, in other words, we find the smallest one matching in that area
-// so that we dont select the wrapping element by mistake and be unable to select what we want
-size_pos.sort((a, b) => (a.width*a.height > b.width*b.height) ? 1 : -1)
-
 // Window.width required for proper scaling in the frontend
 return {'size_pos': size_pos, 'browser_width': window.innerWidth};

changedetectionio/run_all_tests.sh

@@ -0,0 +1,104 @@
+#!/bin/bash
+
+
+# live_server will throw errors even with live_server_scope=function if I have the live_server setup in different functions
+# and I like to restart the server for each test (and have the test cleanup after each test)
+# merge request welcome :)
+
+
+# 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"
+  pytest $test_name
+done
+
+echo "RUNNING WITH BASE_URL SET"
+
+# Now re-run some tests with BASE_URL enabled
+# Re #65 - Ability to include a link back to the installation, in the notification.
+export BASE_URL="https://really-unique-domain.io"
+pytest tests/test_notification.py
+
+
+# Re-run with HIDE_REFERER set - could affect login
+export HIDE_REFERER=True
+pytest tests/test_access_control.py
+
+
+# Now for the selenium and playwright/browserless fetchers
+# Note - this is not UI functional tests - just checking that each one can fetch the content
+
+echo "TESTING WEBDRIVER FETCH > SELENIUM/WEBDRIVER..."
+docker run -d --name $$-test_selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome-debug:3.141.59
+# takes a while to spin up
+sleep 5
+export WEBDRIVER_URL=http://localhost:4444/wd/hub
+pytest tests/fetchers/test_content.py
+pytest tests/test_errorhandling.py
+unset WEBDRIVER_URL
+docker kill $$-test_selenium
+
+echo "TESTING WEBDRIVER FETCH > PLAYWRIGHT/BROWSERLESS..."
+# Not all platforms support playwright (not ARM/rPI), so it's not packaged in requirements.txt
+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
+
+# 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/run_basic_tests.sh

@@ -1,38 +0,0 @@
-#!/bin/bash
-
-
-# live_server will throw errors even with live_server_scope=function if I have the live_server setup in different functions
-# and I like to restart the server for each test (and have the test cleanup after each test)
-# merge request welcome :)
-
-
-# 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"
-  pytest $test_name
-done
-
-echo "RUNNING WITH BASE_URL SET"
-
-# Now re-run some tests with BASE_URL enabled
-# Re #65 - Ability to include a link back to the installation, in the notification.
-export BASE_URL="https://really-unique-domain.io"
-pytest tests/test_notification.py
-
-
-# Re-run with HIDE_REFERER set - could affect login
-export HIDE_REFERER=True
-pytest tests/test_access_control.py
-
-# Re-run a few tests that will trigger brotli based storage
-export SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD=5
-pytest tests/test_access_control.py
-pytest tests/test_notification.py
-pytest tests/test_backend.py
-pytest tests/test_rss.py
-pytest tests/test_unique_lines.py

changedetectionio/run_proxy_tests.sh

@@ -1,61 +0,0 @@
-#!/bin/bash
-
-# exit when any command fails
-set -e
-
-# 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 --network changedet-network -d --name squid-one --hostname squid-one --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
-docker run --network changedet-network -d --name squid-two --hostname squid-two --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
-
-# Used for configuring a custom proxy URL via the UI
-docker run --network changedet-network -d \
-  --name squid-custom \
-  --hostname squid-custom \
-  --rm \
-  -v `pwd`/tests/proxy_list/squid-auth.conf:/etc/squid/conf.d/debian.conf \
-  -v `pwd`/tests/proxy_list/squid-passwords.txt:/etc/squid3/passwords \
-  ubuntu/squid:4.13-21.10_edge
-
-
-## 2nd test actually choose the preferred proxy from proxies.json
-
-docker run --network changedet-network \
-  -v `pwd`/tests/proxy_list/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
-  test-changedetectionio \
-  bash -c 'cd changedetectionio && 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 - squid one)"
-  exit 1
-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 - squid two)"
-  exit 1
-fi
-
-
-# Test the UI configurable proxies
-
-docker run --network changedet-network \
-  test-changedetectionio \
-  bash -c 'cd changedetectionio && pytest tests/proxy_list/test_select_custom_proxy.py'
-
-
-# Should see a request for one.changedetection.io in there
-docker logs squid-custom 2>/dev/null|grep "TCP_TUNNEL.200.*changedetection.io"
-if [ $? -ne 0 ]
-then
-  echo "Did not see a valid request to changedetection.io in the squid logs (while checking preferred proxy - squid two)"
-  exit 1
-fi
-
-docker kill squid-one squid-two squid-custom

changedetectionio/static/images/pdf-icon.svg

@@ -1,9 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<svg xmlns="http://www.w3.org/2000/svg" width="75.320129mm" height="92.604164mm" viewBox="0 0 75.320129 92.604164">
-  <g transform="translate(53.548057 -183.975276) scale(1.4843)">
-    <path fill="#ff2116" d="M-29.632812 123.94727c-3.551967 0-6.44336 2.89347-6.44336 6.44531v49.49804c0 3.55185 2.891393 6.44532 6.44336 6.44532H8.2167969c3.5519661 0 6.4433591-2.89335 6.4433591-6.44532v-40.70117s.101353-1.19181-.416015-2.35156c-.484969-1.08711-1.275391-1.84375-1.275391-1.84375a1.0584391 1.0584391 0 0 0-.0059-.008l-9.3906254-9.21094a1.0584391 1.0584391 0 0 0-.015625-.0156s-.8017392-.76344-1.9902344-1.27344c-1.39939552-.6005-2.8417968-.53711-2.8417968-.53711l.021484-.002z" color="#000" font-family="sans-serif" overflow="visible" paint-order="markers fill stroke" style="line-height:normal;font-variant-ligatures:normal;font-variant-position:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-alternates:normal;font-feature-settings:normal;text-indent:0;text-align:start;text-decoration-line:none;text-decoration-style:solid;text-decoration-color:#000000;text-transform:none;text-orientation:mixed;white-space:normal;shape-padding:0;isolation:auto;mix-blend-mode:normal;solid-color:#000000;solid-opacity:1"/>
-    <path fill="#f5f5f5" d="M-29.632812 126.06445h28.3789058a1.0584391 1.0584391 0 0 0 .021484 0s1.13480448.011 1.96484378.36719c.79889772.34282 1.36536982.86176 1.36914062.86524.0000125.00001.00391.004.00391.004l9.3671868 9.18945s.564354.59582.837891 1.20899c.220779.49491.234375 1.40039.234375 1.40039a1.0584391 1.0584391 0 0 0-.002.0449v40.74609c0 2.41592-1.910258 4.32813-4.3261717 4.32813H-29.632812c-2.415914 0-4.326172-1.91209-4.326172-4.32813v-49.49804c0-2.41603 1.910258-4.32813 4.326172-4.32813z" color="#000" font-family="sans-serif" overflow="visible" paint-order="markers fill stroke" style="line-height:normal;font-variant-ligatures:normal;font-variant-position:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-alternates:normal;font-feature-settings:normal;text-indent:0;text-align:start;text-decoration-line:none;text-decoration-style:solid;text-decoration-color:#000000;text-transform:none;text-orientation:mixed;white-space:normal;shape-padding:0;isolation:auto;mix-blend-mode:normal;solid-color:#000000;solid-opacity:1"/>
-    <path fill="#ff2116" d="M-23.40766 161.09299c-1.45669-1.45669.11934-3.45839 4.39648-5.58397l2.69124-1.33743 1.04845-2.29399c.57665-1.26169 1.43729-3.32036 1.91254-4.5748l.8641-2.28082-.59546-1.68793c-.73217-2.07547-.99326-5.19438-.52872-6.31588.62923-1.51909 2.69029-1.36323 3.50626.26515.63727 1.27176.57212 3.57488-.18329 6.47946l-.6193 2.38125.5455.92604c.30003.50932 1.1764 1.71867 1.9475 2.68743l1.44924 1.80272 1.8033728-.23533c5.72900399-.74758 7.6912472.523 7.6912472 2.34476 0 2.29921-4.4984914 2.48899-8.2760865-.16423-.8499666-.59698-1.4336605-1.19001-1.4336605-1.19001s-2.3665326.48178-3.531704.79583c-1.202707.32417-1.80274.52719-3.564509 1.12186 0 0-.61814.89767-1.02094 1.55026-1.49858 2.4279-3.24833 4.43998-4.49793 5.1723-1.3991.81993-2.86584.87582-3.60433.13733zm2.28605-.81668c.81883-.50607 2.47616-2.46625 3.62341-4.28553l.46449-.73658-2.11497 1.06339c-3.26655 1.64239-4.76093 3.19033-3.98386 4.12664.43653.52598.95874.48237 2.01093-.16792zm21.21809-5.95578c.80089-.56097.68463-1.69142-.22082-2.1472-.70466-.35471-1.2726074-.42759-3.1031574-.40057-1.1249.0767-2.9337647.3034-3.2403347.37237 0 0 .993716.68678 1.434896.93922.58731.33544 2.0145161.95811 3.0565161 1.27706 1.02785.31461 1.6224.28144 2.0729-.0409zm-8.53152-3.54594c-.4847-.50952-1.30889-1.57296-1.83152-2.3632-.68353-.89643-1.02629-1.52887-1.02629-1.52887s-.4996 1.60694-.90948 2.57394l-1.27876 3.16076-.37075.71695s1.971043-.64627 2.97389-.90822c1.0621668-.27744 3.21787-.70134 3.21787-.70134zm-2.74938-11.02573c.12363-1.0375.1761-2.07346-.15724-2.59587-.9246-1.01077-2.04057-.16787-1.85154 2.23517.0636.8084.26443 2.19033.53292 3.04209l.48817 1.54863.34358-1.16638c.18897-.64151.47882-2.02015.64411-3.06364z"/>
-    <path fill="#2c2c2c" d="M-20.930423 167.83862h2.364986q1.133514 0 1.840213.2169.706698.20991 1.189489.9446.482795.72769.482795 1.75625 0 .94459-.391832 1.6233-.391833.67871-1.056548.97958-.65772.30087-2.02913.30087h-.818651v3.72941h-1.581322zm1.581322 1.22447v3.33058h.783664q1.049552 0 1.44838-.39184.405826-.39183.405826-1.27345 0-.65772-.265887-1.06355-.265884-.41282-.587747-.50378-.314866-.098-1.000572-.098zm5.50664-1.22447h2.148082q1.560333 0 2.4909318.55276.9375993.55276 1.4133973 1.6443.482791 1.09153.482791 2.42096 0 1.3994-.4338151 2.49793-.4268149 1.09153-1.3154348 1.76324-.8816233.67172-2.5189212.67172h-2.267031zm1.581326 1.26645v7.018h.657715q1.378411 0 2.001144-.9516.6227329-.95858.6227329-2.5539 0-3.5125-2.6238769-3.5125zm6.4722254-1.26645h5.30372941v1.26645H-4.2075842v2.85478h2.9807225v1.26646h-2.9807225v4.16322h-1.5813254z" font-family="Franklin Gothic Medium Cond" letter-spacing="0" style="line-height:125%;-inkscape-font-specification:'Franklin Gothic Medium Cond'" word-spacing="4.26000023"/>
-  </g>
-</svg>

changedetectionio/static/images/price-tag-icon.svg

@@ -1,2 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<svg width="83.39" height="89.648" enable-background="new 0 0 122.406 122.881" version="1.1" viewBox="0 0 83.39 89.648" xml:space="preserve" xmlns="http://www.w3.org/2000/svg"><g transform="translate(5e-4 -33.234)"><path d="m44.239 42.946-39.111 39.896 34.908 34.91 39.09-39.876-1.149-34.931zm-0.91791 42.273c0.979-0.979 1.507-1.99 1.577-3.027 0.077-1.043-0.248-2.424-0.967-4.135-0.725-1.717-1.348-3.346-1.87-4.885s-0.814-3.014-0.897-4.432c-0.07-1.42 0.134-2.768 0.624-4.045 0.477-1.279 1.348-2.545 2.607-3.804 2.099-2.099 4.535-3.123 7.314-3.065 2.773 0.063 5.457 1.158 8.04 3.294l2.881 3.034c1.946 2.607 2.799 5.33 2.557 8.166-0.235 2.83-1.532 5.426-3.893 7.785l-6.296-6.297c1.291-1.291 2.035-2.531 2.238-3.727 0.191-1.197-0.165-2.252-1.081-3.168-0.821-0.82-1.717-1.195-2.69-1.139-0.967 0.064-1.908 0.547-2.817 1.457-0.922 0.922-1.393 1.914-1.412 2.977s0.306 2.416 0.973 4.064c0.661 1.652 1.24 3.25 1.736 4.801 0.496 1.553 0.782 3.035 0.858 4.445 0.076 1.426-0.127 2.787-0.591 4.104-0.477 1.316-1.336 2.596-2.588 3.848-2.125 2.125-4.522 3.186-7.212 3.18s-5.311-1.063-7.855-3.16l-3.747 3.746-2.964-2.965 3.766-3.764c-2.423-2.996-3.568-5.998-3.447-9.02 0.127-3.014 1.476-5.813 4.045-8.383l6.278 6.277c-1.412 1.412-2.175 2.799-2.277 4.16-0.108 1.367 0.414 2.627 1.571 3.783 0.839 0.84 1.755 1.26 2.741 1.242 0.985-0.017 1.92-0.47 2.798-1.347zm21.127-46.435h17.457c-0.0269 2.2368 0.69936 16.025 0.69936 16.025l0.785 23.858c0.019 0.609-0.221 1.164-0.619 1.564l5e-3 4e-3 -41.236 42.022c-0.82213 0.8378-2.175 0.83-3.004 0l-37.913-37.91c-0.83-0.83-0.83-2.176 0-3.006l41.236-42.021c0.39287-0.42671 1.502-0.53568 1.502-0.53568zm18.011 11.59c-59.392-29.687-29.696-14.843 0 0z"/></g></svg>

changedetectionio/static/js/visual-selector.js

@@ -1,5 +1,4 @@
-// Copyright (C) 2021 Leigh Morresi (dgtlmoon@gmail.com)
-// All rights reserved.
+// Horrible proof of concept code :)
 // yes - this is really a hack, if you are a front-ender and want to help, please get in touch!
 
 $(document).ready(function () {
@@ -178,10 +177,9 @@ $(document).ready(function () {
             // Basically, find the most 'deepest'
             var found = 0;
             ctx.fillStyle = 'rgba(205,0,0,0.35)';
-            // Will be sorted by smallest width*height first
-            for (var i = 0; i <= selector_data['size_pos'].length; i++) {
+            for (var i = selector_data['size_pos'].length; i !== 0; i--) {
                 // draw all of them? let them choose somehow?
-                var sel = selector_data['size_pos'][i];
+                var sel = selector_data['size_pos'][i - 1];
                 // If we are in a bounding-box
                 if (e.offsetY > sel.top * y_scale && e.offsetY < sel.top * y_scale + sel.height * y_scale
                     &&
@@ -197,7 +195,7 @@ $(document).ready(function () {
                     // no need to keep digging
                     // @todo or, O to go out/up, I to go in
                     // or double click to go up/out the selector?
-                    current_selected_i = i;
+                    current_selected_i = i - 1;
                     found += 1;
                     break;
                 }

changedetectionio/static/js/watch-settings.js

@@ -1,7 +1,7 @@
-$(document).ready(function () {
+$(document).ready(function() {
     function toggle() {
         if ($('input[name="fetch_backend"]:checked').val() == 'html_webdriver') {
-            if (playwright_enabled) {
+            if(playwright_enabled) {
                 // playwright supports headers, so hide everything else
                 // See #664
                 $('#requests-override-options #request-method').hide();
@@ -14,14 +14,9 @@ $(document).ready(function () {
                 $('#requests-override-options').hide();
             }
 
+
             $('#webdriver-override-options').show();
 
-        } else if ($('input[name="fetch_backend"]:checked').val() == 'system') {
-            $('#requests-override-options #request-method').hide();
-            $('#requests-override-options #request-body').hide();
-            $('#ignore-status-codes-option').hide();
-            $('#requests-override-options').hide();
-            $('#webdriver-override-options').hide();
         } else {
 
             $('#requests-override-options').show();

changedetectionio/static/styles/.dockerignore

@@ -1,3 +0,0 @@
-node_modules
-package-lock.json
-

changedetectionio/static/styles/diff.css

@@ -121,19 +121,15 @@ html[data-darkmode="true"] {
   --color-icon-github-hover: var(--color-grey-700);
   --color-watch-table-error: var(--color-light-red);
   --color-watch-table-row-text: var(--color-grey-800); }
+  html[data-darkmode="true"] .watch-controls img {
+    opacity: 0.4; }
+  html[data-darkmode="true"] .watch-table .unviewed {
+    color: #fff; }
   html[data-darkmode="true"] .icon-spread {
     filter: hue-rotate(-10deg) brightness(1.5); }
   html[data-darkmode="true"] .watch-table .title-col a[target="_blank"]::after,
   html[data-darkmode="true"] .watch-table .current-diff-url::after {
     filter: invert(0.5) hue-rotate(10deg) brightness(2); }
-  html[data-darkmode="true"] .watch-table .watch-controls .state-off img {
-    opacity: 0.3; }
-  html[data-darkmode="true"] .watch-table .watch-controls .state-on img {
-    opacity: 1.0; }
-  html[data-darkmode="true"] .watch-table .unviewed {
-    color: #fff; }
-    html[data-darkmode="true"] .watch-table .unviewed.error {
-      color: var(--color-watch-table-error); }
 
 #diff-ui {
   background: var(--color-background);

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

@@ -1,17 +0,0 @@
-ul#requests-extra_proxies {
-  list-style: none;
-  /* tidy up the table to look more "inline" */
-  li {
-    > label {
-      display: none;
-    }
-
-  }
-  /* each proxy entry is a `table` */
-  table {
-    tr {
-      display: inline;
-    }
-  }
-}
-

changedetectionio/static/styles/scss/parts/_variables.scss

@@ -140,7 +140,15 @@ html[data-darkmode="true"] {
   --color-watch-table-error: var(--color-light-red);
   --color-watch-table-row-text: var(--color-grey-800);
 
-
+  // Anything that can't be manipulated through variables follows.
+  .watch-controls {
+    img {
+      opacity: 0.4;
+    }
+  }
+  .watch-table .unviewed {
+    color: #fff;
+  }
   .icon-spread {
     filter: hue-rotate(-10deg) brightness(1.5);
   }
@@ -151,25 +159,5 @@ html[data-darkmode="true"] {
     .current-diff-url::after {
       filter: invert(.5) hue-rotate(10deg) brightness(2);
     }
-
-    .watch-controls {
-      .state-off {
-        img {
-          opacity: 0.3;
-        }
-      }
-      .state-on {
-        img {
-          opacity: 1.0;
-        }
-      }
-    }
-
-    .unviewed {
-      color: #fff;
-      &.error {
-        color: var(--color-watch-table-error);
-      }
-    }
   }
 }

changedetectionio/static/styles/scss/styles.scss

@@ -2,11 +2,10 @@
  * -- BASE STYLES --
  */
 
-@import "parts/_arrows";
-@import "parts/_browser-steps";
-@import "parts/_extra_proxies";
-@import "parts/_spinners";
 @import "parts/_variables";
+@import "parts/_spinners";
+@import "parts/_browser-steps";
+@import "parts/_arrows";
 
 body {
   color: var(--color-text);
@@ -23,13 +22,6 @@ body {
   width: 1px;
 }
 
-// Row icons like chrome, pdf, share, etc
-.status-icon {
-  display: inline-block;
-  height: 1rem;
-  vertical-align: middle;
-}
-
 .pure-table-even {
   background: var(--color-background);
 }
@@ -133,21 +125,22 @@ code {
     &.unviewed {
       font-weight: bold;
     }
-    &.error {
-      color: var(--color-watch-table-error);
-    }
     color: var(--color-watch-table-row-text);
   }
 
 
-  td {
-    white-space: nowrap;
-    &.title-col {
-      word-break: break-all;
-      white-space: normal;
-    }
+  .error {
+    color: var(--color-watch-table-error);
   }
 
+  td {
+    white-space: nowrap;
+  }
+
+  td.title-col {
+    word-break: break-all;
+    white-space: normal;
+  }
 
   th {
     white-space: nowrap;
@@ -241,10 +234,6 @@ body:before {
   font-size: 85%;
 }
 
-.button-xsmall {
-  font-size: 70%;
-}
-
 .fetch-error {
   padding-top: 1em;
   font-size: 80%;
@@ -889,24 +878,6 @@ body.full-width {
   .pure-form-message-inline {
     padding-left: 0;
     color: var(--color-text-input-description);
-    code {
-      font-size: .875em;
-    }
-  }
-  .text-filtering {
-    h3 {
-      margin-top: 0;
-    }
-    border: 1px solid #ccc;
-    padding: 1rem;
-    border-radius: 5px;
-    margin-bottom: 1rem;
-    fieldset:last-of-type {
-      padding-bottom: 0;
-      .pure-control-group {
-        padding-bottom: 0;
-      }
-    }
   }
 }
 
@@ -1036,57 +1007,3 @@ ul {
   border-radius: 5px;
   color: var(--color-warning);
 }
-
-/* automatic price following helpers */
-.tracking-ldjson-price-data {
-  background-color: var(--color-background-button-green);
-  color: #000;
-  padding: 3px;
-  border-radius: 3px;
-  white-space: nowrap;
-}
-
-.ldjson-price-track-offer {
-  a.pure-button {
-    border-radius: 3px;
-    padding: 3px;
-    background-color: var(--color-background-button-green);
-  }
-
-  font-weight: bold;
-  font-style: italic;
-}
-
-.price-follow-tag-icon {
-  display: inline-block;
-  height: 0.8rem;
-  vertical-align: middle;
-}
-
-
-#quick-watch-processor-type {
-  color: #fff;
-  ul {
-    padding: 0.3rem;
-
-    li {
-      list-style: none;
-      font-size: 0.8rem;
-    }
-  }
-
-}
-
-.restock-label {
-  &.in-stock {
-    background-color: var(--color-background-button-green);
-    color: #fff;
-  }
-  &.not-in-stock {
-    background-color: var(--color-background-button-cancel);
-    color: #777;
-  }
-  padding: 3px;
-  border-radius: 3px;
-  white-space: nowrap;
-}

changedetectionio/static/styles/styles.css

@@ -1,139 +1,6 @@
 /*
  * -- BASE STYLES --
  */
-.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); }
-
-#browser_steps {
-  /* convert rows to horizontal cells */ }
-  #browser_steps th {
-    display: none; }
-  #browser_steps li {
-    list-style: decimal;
-    padding: 5px; }
-    #browser_steps li:not(:first-child):hover {
-      opacity: 1.0; }
-    #browser_steps li .control {
-      padding-left: 5px;
-      padding-right: 5px; }
-      #browser_steps li .control a {
-        font-size: 70%; }
-    #browser_steps li.empty {
-      padding: 0px;
-      opacity: 0.35; }
-      #browser_steps li.empty .control {
-        display: none; }
-    #browser_steps li:hover {
-      background: #eee; }
-    #browser_steps li > label {
-      display: none; }
-
-#browser-steps-fieldlist {
-  height: 100%;
-  overflow-y: scroll; }
-
-#browser-steps .flex-wrapper {
-  display: flex;
-  flex-flow: row;
-  height: 600px;
-  /*@todo make this dynamic */ }
-
-/*  this is duplicate :( */
-#browsersteps-selector-wrapper {
-  height: 100%;
-  width: 100%;
-  overflow-y: scroll;
-  position: relative;
-  /* nice tall skinny one */ }
-  #browsersteps-selector-wrapper > img {
-    position: absolute;
-    max-width: 100%; }
-  #browsersteps-selector-wrapper > canvas {
-    position: relative;
-    max-width: 100%; }
-    #browsersteps-selector-wrapper > canvas:hover {
-      cursor: pointer; }
-  #browsersteps-selector-wrapper .loader {
-    position: absolute;
-    left: 50%;
-    top: 50%;
-    transform: translate(-50%, -50%);
-    margin-left: -40px;
-    z-index: 100;
-    max-width: 350px;
-    text-align: center; }
-  #browsersteps-selector-wrapper .spinner, #browsersteps-selector-wrapper .spinner:after {
-    width: 80px;
-    height: 80px;
-    font-size: 3px; }
-  #browsersteps-selector-wrapper #browsersteps-click-start {
-    color: var(--color-grey-400); }
-    #browsersteps-selector-wrapper #browsersteps-click-start:hover {
-      cursor: pointer; }
-
-ul#requests-extra_proxies {
-  list-style: none;
-  /* tidy up the table to look more "inline" */
-  /* each proxy entry is a `table` */ }
-  ul#requests-extra_proxies li > label {
-    display: none; }
-  ul#requests-extra_proxies table tr {
-    display: inline; }
-
-/* spinner */
-.spinner,
-.spinner:after {
-  border-radius: 50%;
-  width: 10px;
-  height: 10px; }
-
-.spinner {
-  margin: 0px auto;
-  font-size: 3px;
-  vertical-align: middle;
-  display: inline-block;
-  text-indent: -9999em;
-  border-top: 1.1em solid rgba(38, 104, 237, 0.2);
-  border-right: 1.1em solid rgba(38, 104, 237, 0.2);
-  border-bottom: 1.1em solid rgba(38, 104, 237, 0.2);
-  border-left: 1.1em solid #2668ed;
-  -webkit-transform: translateZ(0);
-  -ms-transform: translateZ(0);
-  transform: translateZ(0);
-  -webkit-animation: load8 1.1s infinite linear;
-  animation: load8 1.1s infinite linear; }
-
-@-webkit-keyframes load8 {
-  0% {
-    -webkit-transform: rotate(0deg);
-    transform: rotate(0deg); }
-  100% {
-    -webkit-transform: rotate(360deg);
-    transform: rotate(360deg); } }
-
-@keyframes load8 {
-  0% {
-    -webkit-transform: rotate(0deg);
-    transform: rotate(0deg); }
-  100% {
-    -webkit-transform: rotate(360deg);
-    transform: rotate(360deg); } }
-
 /**
  * CSS custom properties (aka variables).
  */
@@ -257,19 +124,139 @@ html[data-darkmode="true"] {
   --color-icon-github-hover: var(--color-grey-700);
   --color-watch-table-error: var(--color-light-red);
   --color-watch-table-row-text: var(--color-grey-800); }
+  html[data-darkmode="true"] .watch-controls img {
+    opacity: 0.4; }
+  html[data-darkmode="true"] .watch-table .unviewed {
+    color: #fff; }
   html[data-darkmode="true"] .icon-spread {
     filter: hue-rotate(-10deg) brightness(1.5); }
   html[data-darkmode="true"] .watch-table .title-col a[target="_blank"]::after,
   html[data-darkmode="true"] .watch-table .current-diff-url::after {
     filter: invert(0.5) hue-rotate(10deg) brightness(2); }
-  html[data-darkmode="true"] .watch-table .watch-controls .state-off img {
-    opacity: 0.3; }
-  html[data-darkmode="true"] .watch-table .watch-controls .state-on img {
-    opacity: 1.0; }
-  html[data-darkmode="true"] .watch-table .unviewed {
-    color: #fff; }
-    html[data-darkmode="true"] .watch-table .unviewed.error {
-      color: var(--color-watch-table-error); }
+
+/* spinner */
+.spinner,
+.spinner:after {
+  border-radius: 50%;
+  width: 10px;
+  height: 10px; }
+
+.spinner {
+  margin: 0px auto;
+  font-size: 3px;
+  vertical-align: middle;
+  display: inline-block;
+  text-indent: -9999em;
+  border-top: 1.1em solid rgba(38, 104, 237, 0.2);
+  border-right: 1.1em solid rgba(38, 104, 237, 0.2);
+  border-bottom: 1.1em solid rgba(38, 104, 237, 0.2);
+  border-left: 1.1em solid #2668ed;
+  -webkit-transform: translateZ(0);
+  -ms-transform: translateZ(0);
+  transform: translateZ(0);
+  -webkit-animation: load8 1.1s infinite linear;
+  animation: load8 1.1s infinite linear; }
+
+@-webkit-keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg); }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg); } }
+
+@keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg); }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg); } }
+
+#browser_steps {
+  /* convert rows to horizontal cells */ }
+  #browser_steps th {
+    display: none; }
+  #browser_steps li {
+    list-style: decimal;
+    padding: 5px; }
+    #browser_steps li:not(:first-child):hover {
+      opacity: 1.0; }
+    #browser_steps li .control {
+      padding-left: 5px;
+      padding-right: 5px; }
+      #browser_steps li .control a {
+        font-size: 70%; }
+    #browser_steps li.empty {
+      padding: 0px;
+      opacity: 0.35; }
+      #browser_steps li.empty .control {
+        display: none; }
+    #browser_steps li:hover {
+      background: #eee; }
+    #browser_steps li > label {
+      display: none; }
+
+#browser-steps-fieldlist {
+  height: 100%;
+  overflow-y: scroll; }
+
+#browser-steps .flex-wrapper {
+  display: flex;
+  flex-flow: row;
+  height: 600px;
+  /*@todo make this dynamic */ }
+
+/*  this is duplicate :( */
+#browsersteps-selector-wrapper {
+  height: 100%;
+  width: 100%;
+  overflow-y: scroll;
+  position: relative;
+  /* nice tall skinny one */ }
+  #browsersteps-selector-wrapper > img {
+    position: absolute;
+    max-width: 100%; }
+  #browsersteps-selector-wrapper > canvas {
+    position: relative;
+    max-width: 100%; }
+    #browsersteps-selector-wrapper > canvas:hover {
+      cursor: pointer; }
+  #browsersteps-selector-wrapper .loader {
+    position: absolute;
+    left: 50%;
+    top: 50%;
+    transform: translate(-50%, -50%);
+    margin-left: -40px;
+    z-index: 100;
+    max-width: 350px;
+    text-align: center; }
+  #browsersteps-selector-wrapper .spinner, #browsersteps-selector-wrapper .spinner:after {
+    width: 80px;
+    height: 80px;
+    font-size: 3px; }
+  #browsersteps-selector-wrapper #browsersteps-click-start {
+    color: var(--color-grey-400); }
+    #browsersteps-selector-wrapper #browsersteps-click-start:hover {
+      cursor: pointer; }
+
+.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: var(--color-text);
@@ -284,11 +271,6 @@ body {
   white-space: nowrap;
   width: 1px; }
 
-.status-icon {
-  display: inline-block;
-  height: 1rem;
-  vertical-align: middle; }
-
 .pure-table-even {
   background: var(--color-background); }
 
@@ -361,13 +343,13 @@ code {
     color: var(--color-watch-table-row-text); }
     .watch-table tr.unviewed {
       font-weight: bold; }
-    .watch-table tr.error {
-      color: var(--color-watch-table-error); }
+  .watch-table .error {
+    color: var(--color-watch-table-error); }
   .watch-table td {
     white-space: nowrap; }
-    .watch-table td.title-col {
-      word-break: break-all;
-      white-space: normal; }
+  .watch-table td.title-col {
+    word-break: break-all;
+    white-space: normal; }
   .watch-table th {
     white-space: nowrap; }
     .watch-table th a {
@@ -432,9 +414,6 @@ body:before {
 .button-small {
   font-size: 85%; }
 
-.button-xsmall {
-  font-size: 70%; }
-
 .fetch-error {
   padding-top: 1em;
   font-size: 80%;
@@ -870,19 +849,6 @@ body.full-width .edit-form {
   .edit-form .pure-form-message-inline {
     padding-left: 0;
     color: var(--color-text-input-description); }
-    .edit-form .pure-form-message-inline code {
-      font-size: .875em; }
-  .edit-form .text-filtering {
-    border: 1px solid #ccc;
-    padding: 1rem;
-    border-radius: 5px;
-    margin-bottom: 1rem; }
-    .edit-form .text-filtering h3 {
-      margin-top: 0; }
-    .edit-form .text-filtering fieldset:last-of-type {
-      padding-bottom: 0; }
-      .edit-form .text-filtering fieldset:last-of-type .pure-control-group {
-        padding-bottom: 0; }
 
 ul {
   padding-left: 1em;
@@ -973,43 +939,3 @@ ul {
     display: inline;
     height: 26px;
     vertical-align: middle; }
-
-/* automatic price following helpers */
-.tracking-ldjson-price-data {
-  background-color: var(--color-background-button-green);
-  color: #000;
-  padding: 3px;
-  border-radius: 3px;
-  white-space: nowrap; }
-
-.ldjson-price-track-offer {
-  font-weight: bold;
-  font-style: italic; }
-  .ldjson-price-track-offer a.pure-button {
-    border-radius: 3px;
-    padding: 3px;
-    background-color: var(--color-background-button-green); }
-
-.price-follow-tag-icon {
-  display: inline-block;
-  height: 0.8rem;
-  vertical-align: middle; }
-
-#quick-watch-processor-type {
-  color: #fff; }
-  #quick-watch-processor-type ul {
-    padding: 0.3rem; }
-    #quick-watch-processor-type ul li {
-      list-style: none;
-      font-size: 0.8rem; }
-
-.restock-label {
-  padding: 3px;
-  border-radius: 3px;
-  white-space: nowrap; }
-  .restock-label.in-stock {
-    background-color: var(--color-background-button-green);
-    color: #fff; }
-  .restock-label.not-in-stock {
-    background-color: var(--color-background-button-cancel);
-    color: #777; }

changedetectionio/store.py

@@ -1,20 +1,20 @@
 from flask import (
     flash
 )
-
-from . model import App, Watch
-from copy import deepcopy
-from os import path, unlink
-from threading import Lock
 import json
 import logging
 import os
-import re
-import requests
-import secrets
 import threading
 import time
 import uuid as uuid_builder
+from copy import deepcopy
+from os import path, unlink
+from threading import Lock
+import re
+import requests
+import secrets
+
+from . model import App, Watch
 
 # Is there an existing library to ensure some data store (JSON etc) is in sync with CRUD methods?
 # Open a github issue if you know something :)
@@ -36,6 +36,7 @@ class ChangeDetectionStore:
         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
         # Base definition for all watchers
@@ -77,10 +78,10 @@ class ChangeDetectionStore:
                     self.__data['watching'][uuid] = Watch.model(datastore_path=self.datastore_path, default=watch)
                     print("Watching:", uuid, self.__data['watching'][uuid]['url'])
 
-        # First time ran, Create the datastore.
-        except (FileNotFoundError):
+        # First time ran, doesnt exist.
+        except (FileNotFoundError, json.decoder.JSONDecodeError):
             if include_default_watches:
-                print("No JSON DB found at {}, creating JSON store at {}".format(self.json_store_path, self.datastore_path))
+                print("Creating JSON store at", self.datastore_path)
                 self.add_watch(url='https://news.ycombinator.com/',
                                tag='Tech news',
                                extras={'fetch_backend': 'html_requests'})
@@ -88,10 +89,8 @@ class ChangeDetectionStore:
                 self.add_watch(url='https://changedetection.io/CHANGELOG.txt',
                                tag='changedetection.io',
                                extras={'fetch_backend': 'html_requests'})
-        self.__data['version_tag'] = version_tag
 
-        # Just to test that proxies.json if it exists, doesnt throw a parsing error on startup
-        test_list = self.proxy_list
+        self.__data['version_tag'] = version_tag
 
         # Helper to remove password protection
         password_reset_lockfile = "{}/removepassword.lock".format(self.datastore_path)
@@ -117,6 +116,11 @@ class ChangeDetectionStore:
             secret = secrets.token_hex(16)
             self.__data['settings']['application']['api_access_token'] = secret
 
+        # Proxy list support - available as a selection in settings when text file is imported
+        proxy_list_file = "{}/proxies.json".format(self.datastore_path)
+        if path.isfile(proxy_list_file):
+            self.import_proxy_list(proxy_list_file)
+
         # Bump the update version by running updates
         self.run_updates()
 
@@ -171,6 +175,14 @@ class ChangeDetectionStore:
 
     @property
     def data(self):
+        has_unviewed = False
+        for uuid, watch in self.__data['watching'].items():
+            # #106 - Be sure this is None on empty string, False, None, etc
+            # Default var for fetch_backend
+            # @todo this may not be needed anymore, or could be easily removed
+            if not self.__data['watching'][uuid]['fetch_backend']:
+                self.__data['watching'][uuid]['fetch_backend'] = self.__data['settings']['application']['fetch_backend']
+
         # Re #152, Return env base_url if not overriden, @todo also prefer the proxy pass url
         env_base_url = os.getenv('BASE_URL','')
         if not self.__data['settings']['application']['base_url']:
@@ -192,24 +204,27 @@ class ChangeDetectionStore:
         tags.sort()
         return tags
 
+    def unlink_history_file(self, path):
+        try:
+            unlink(path)
+        except (FileNotFoundError, IOError):
+            pass
+
     # Delete a single watch by UUID
     def delete(self, uuid):
-        import pathlib
-        import shutil
-
         with self.lock:
             if uuid == 'all':
                 self.__data['watching'] = {}
 
                 # GitHub #30 also delete history records
                 for uuid in self.data['watching']:
-                    path = pathlib.Path(os.path.join(self.datastore_path, uuid))
-                    shutil.rmtree(path)
-                    self.needs_write_urgent = True
+                    for path in self.data['watching'][uuid].history.values():
+                        self.unlink_history_file(path)
 
             else:
-                path = pathlib.Path(os.path.join(self.datastore_path, uuid))
-                shutil.rmtree(path)
+                for path in self.data['watching'][uuid].history.values():
+                    self.unlink_history_file(path)
+
                 del self.data['watching'][uuid]
 
             self.needs_write_urgent = True
@@ -235,15 +250,12 @@ class ChangeDetectionStore:
     def clear_watch_history(self, uuid):
         import pathlib
 
-        self.__data['watching'][uuid].update({
-                'last_checked': 0,
-                'has_ldjson_price_data': None,
-                'last_error': False,
-                'last_notification_error': False,
-                'last_viewed': 0,
-                'previous_md5': False,
-                'track_ldjson_price_data': None,
-            })
+        self.__data['watching'][uuid].update(
+            {'last_checked': 0,
+             'last_viewed': 0,
+             'previous_md5': False,
+             'last_notification_error': False,
+             'last_error': False})
 
         # JSON Data, Screenshots, Textfiles (history index and snapshots), HTML in the future etc
         for item in pathlib.Path(os.path.join(self.datastore_path, uuid)).rglob("*.*"):
@@ -287,7 +299,6 @@ class ChangeDetectionStore:
                     'method',
                     'paused',
                     'previous_md5',
-                    'processor',
                     'subtractive_selectors',
                     'tag',
                     'text_should_not_be_present',
@@ -307,12 +318,9 @@ class ChangeDetectionStore:
                 logging.error("Error fetching metadata for shared watch link", url, str(e))
                 flash("Error fetching metadata for {}".format(url), 'error')
                 return False
-        from .model.Watch import is_safe_url
-        if not is_safe_url(url):
-            flash('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX', 'error')
-            return None
 
         with self.lock:
+
             # #Re 569
             new_watch = Watch.model(datastore_path=self.datastore_path, default={
                 'url': url,
@@ -361,6 +369,11 @@ class ChangeDetectionStore:
             f.write(screenshot)
             f.close()
 
+        # Make a JPEG that's used in notifications (due to being a smaller size) available
+        from PIL import Image
+        im1 = Image.open(target_path)
+        im1.convert('RGB').save(target_path.replace('.png','.jpg'), quality=int(os.getenv("NOTIFICATION_SCREENSHOT_JPG_QUALITY", 75)))
+
 
     def save_error_text(self, watch_uuid, contents):
         if not self.data['watching'].get(watch_uuid):
@@ -447,30 +460,10 @@ class ChangeDetectionStore:
                     print ("Removing",item)
                     unlink(item)
 
-    @property
-    def proxy_list(self):
-        proxy_list = {}
-        proxy_list_file = os.path.join(self.datastore_path, 'proxies.json')
-
-        # Load from external config file
-        if path.isfile(proxy_list_file):
-            with open("{}/proxies.json".format(self.datastore_path)) as f:
-                proxy_list = json.load(f)
-
-        # Mapping from UI config if available
-        extras = self.data['settings']['requests'].get('extra_proxies')
-        if extras:
-            i=0
-            for proxy in extras:
-                i += 0
-                if proxy.get('proxy_name') and proxy.get('proxy_url'):
-                    k = "ui-" + str(i) + proxy.get('proxy_name')
-                    proxy_list[k] = {'label': proxy.get('proxy_name'), 'url': proxy.get('proxy_url')}
-
-
-        return proxy_list if len(proxy_list) else None
-
-
+    def import_proxy_list(self, filename):
+        with open(filename) as f:
+            self.proxy_list = json.load(f)
+            print ("Registered proxy list", list(self.proxy_list.keys()))
 
 
     def get_preferred_proxy_for_watch(self, uuid):
@@ -480,10 +473,11 @@ class ChangeDetectionStore:
         :return: proxy "key" id
         """
 
+        proxy_id = None
         if self.proxy_list is None:
             return None
 
-        # If it's a valid one
+        # 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()):
@@ -496,9 +490,8 @@ class ChangeDetectionStore:
             if self.proxy_list.get(system_proxy_id):
                 return system_proxy_id
 
-
-        # Fallback - Did not resolve anything, or doesnt exist, use the first available
-        if system_proxy_id is None or not self.proxy_list.get(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
 
@@ -628,54 +621,4 @@ class ChangeDetectionStore:
                     watch['include_filters'] = [existing_filter]
             except:
                 continue
-        return
-
-    # Convert old static notification tokens to jinja2 tokens
-    def update_9(self):
-        # Each watch
-        import re
-        # only { } not {{ or }}
-        r = r'(?<!{){(?!{)(\w+)(?<!})}(?!})'
-        for uuid, watch in self.data['watching'].items():
-            try:
-                n_body = watch.get('notification_body', '')
-                if n_body:
-                    watch['notification_body'] = re.sub(r, r'{{\1}}', n_body)
-
-                n_title = watch.get('notification_title')
-                if n_title:
-                    watch['notification_title'] = re.sub(r, r'{{\1}}', n_title)
-
-                n_urls = watch.get('notification_urls')
-                if n_urls:
-                    for i, url in enumerate(n_urls):
-                        watch['notification_urls'][i] = re.sub(r, r'{{\1}}', url)
-
-            except:
-                continue
-
-        # System wide
-        n_body = self.data['settings']['application'].get('notification_body')
-        if n_body:
-            self.data['settings']['application']['notification_body'] = re.sub(r, r'{{\1}}', n_body)
-
-        n_title = self.data['settings']['application'].get('notification_title')
-        if n_body:
-            self.data['settings']['application']['notification_title'] = re.sub(r, r'{{\1}}', n_title)
-
-        n_urls =  self.data['settings']['application'].get('notification_urls')
-        if n_urls:
-            for i, url in enumerate(n_urls):
-                self.data['settings']['application']['notification_urls'][i] = re.sub(r, r'{{\1}}', url)
-
-        return
-
-    # Some setups may have missed the correct default, so it shows the wrong config in the UI, although it will default to system-wide
-    def update_10(self):
-        for uuid, watch in self.data['watching'].items():
-            try:
-                if not watch.get('fetch_backend', ''):
-                    watch['fetch_backend'] = 'system'
-            except:
-                continue
-        return
+        return

changedetectionio/templates/_common_fields.jinja

@@ -16,16 +16,14 @@
                                 <li><code>discord://</code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
                                 <li><code>tgram://</code> bots cant send messages to other bots, so you should specify chat ID of non-bot user.</li>
                                 <li><code>tgram://</code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
-                                <li><code>gets://</code>, <code>posts://</code>, <code>puts://</code>, <code>deletes://</code> for direct API calls (or omit the "<code>s</code>" for non-SSL ie <code>get://</code>)</li>
-                                  <li>Accepts the <code>{{ '{{token}}' }}</code> placeholders listed below</li>
                               </ul>
                             </div>
                             <div class="notifications-wrapper">
-                              <a id="send-test-notification" class="pure-button button-secondary button-xsmall" >Send test notification</a>
+                              <a id="send-test-notification" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Send test notification</a>
                             {% if emailprefix %}
-                              <a id="add-email-helper" class="pure-button button-secondary button-xsmall" >Add email</a>
+                              <a id="add-email-helper" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Add email</a>
                             {% endif %}
-                              <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" >Notification debug logs</a>
+                              <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Notification debug logs</a>
                             </div>
                         </div>
                         <div id="notification-customisation" class="pure-control-group">
@@ -43,9 +41,8 @@
                                 <span class="pure-form-message-inline">Format for all notifications</span>
                             </div>
                             <div class="pure-controls">
-                            <p class="pure-form-message-inline">
-                                You can use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> templating in the notification title, body and URL.
-                            </p>
+                            <span class="pure-form-message-inline">
+                                These tokens can be used in the notification body and title to customise the notification text.
 
                                 <table class="pure-table" id="token-table">
                                     <thead>
@@ -56,67 +53,52 @@
                                     </thead>
                                     <tbody>
                                     <tr>
-                                        <td><code>{{ '{{base_url}}' }}</code></td>
+                                        <td><code>{base_url}</code></td>
                                         <td>The URL of the changedetection.io instance you are running.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{watch_url}}' }}</code></td>
+                                        <td><code>{watch_url}</code></td>
                                         <td>The URL being watched.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{watch_uuid}}' }}</code></td>
+                                        <td><code>{watch_uuid}</code></td>
                                         <td>The UUID of the watch.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{watch_title}}' }}</code></td>
+                                        <td><code>{watch_title}</code></td>
                                         <td>The title of the watch.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{watch_tag}}' }}</code></td>
-                                        <td>The watch label / tag</td>
+                                        <td><code>{watch_tag}</code></td>
+                                        <td>The tag of the watch.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{preview_url}}' }}</code></td>
+                                        <td><code>{preview_url}</code></td>
                                         <td>The URL of the preview page generated by changedetection.io.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{diff_url}}' }}</code></td>
-                                        <td>The URL of the diff output for the watch.</td>
-                                    </tr>
-									<tr>
-                                        <td><code>{{ '{{diff}}' }}</code></td>
-                                        <td>The diff output - only changes, additions, and removals</td>
-                                    </tr>
-									<tr>
-                                        <td><code>{{ '{{diff_added}}' }}</code></td>
-                                        <td>The diff output - only changes and additions</td>
-                                    </tr>
-									<tr>
-                                        <td><code>{{ '{{diff_removed}}' }}</code></td>
-                                        <td>The diff output - only changes and removals</td>
+                                        <td><code>{diff}</code></td>
+                                        <td>The diff output - differences only</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{diff_full}}' }}</code></td>
+                                        <td><code>{diff_full}</code></td>
                                         <td>The diff output - full difference output</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{current_snapshot}}' }}</code></td>
+                                        <td><code>{diff_url}</code></td>
+                                        <td>The URL of the diff page generated by changedetection.io.</td>
+                                    </tr>
+                                    <tr>
+                                        <td><code>{current_snapshot}</code></td>
                                         <td>The current snapshot value, useful when combined with JSON or CSS filters
                                         </td>
                                     </tr>
-                                    <tr>
-                                        <td><code>{{ '{{triggered_text}}' }}</code></td>
-                                        <td>Text that tripped the trigger from filters</td>
-                                    </tr>
                                     </tbody>
                                 </table>
-                                <div class="pure-form-message-inline">
-                                    <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 "{{settings_application['current_base_url']}}"
-									<br>
-									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removal%7D%7D-notification-tokens">More Here</a> </br>
-                                </div>
+                                <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 "{{settings_application['current_base_url']}}"
+                            </span>
                             </div>
                         </div>
 {% endmacro %}

changedetectionio/templates/base.html

@@ -1,5 +1,5 @@
 <!DOCTYPE html>
-<html lang="en" data-darkmode="{{ get_darkmode_state() }}">
+<html lang="en" data-darkmode="{{ dark_mode|lower }}">
 
   <head>
     <meta charset="utf-8"/>

changedetectionio/templates/diff.html

@@ -76,12 +76,8 @@
     </div>
 
      <div class="tab-pane-inner" id="text">
-         <div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.</div>
-
-         {% if password_enabled_and_share_is_off %}
-           <div class="tip">Pro-tip: You can enable <strong>"share access when password is enabled"</strong> from settings</div>
-         {% endif %}
-
+         <div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.
+         </div>
          <div class="snapshot-age">{{watch_a.snapshot_text_ctime|format_timestamp_timeago}}</div>
 
          <table>
@@ -124,12 +120,12 @@
             <div class="pure-control-group">
                 {{ render_field(extract_form.extract_regex) }}
                 <span class="pure-form-message-inline">
-                    A <strong>RegEx</strong> is a pattern that identifies exactly which part inside of the text that you want to extract.<br>
+                    A <strong>RegEx</strong> is a pattern that identifies exactly which part inside of the text that you want to extract.<br/>
 
                     <p>
-                        For example, to extract only the numbers from text &dash;<br>
-                        <strong>Raw text</strong>: <code>Temperature <span style="color: red">5.5</span>°C in Sydney</code><br>
-                        <strong>RegEx to extract:</strong> <code>Temperature <span style="color: red">([0-9\.]+)</span></code><br>
+                        For example, to extract only the numbers from text &dash;</br>
+                        <strong>Raw text</strong>: <code>Temperature <span style="color: red">5.5</span>°C in Sydney</code></br>
+                        <strong>RegEx to extract:</strong> <code>Temperature ([0-9\.]+)</code><br/>
                     </p>
                     <p>
                         <a href="https://RegExr.com/">Be sure to test your RegEx here.</a>
@@ -154,4 +150,4 @@
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
 
 
-{% endblock %}
+{% endblock %}

changedetectionio/templates/edit.html

@@ -34,15 +34,8 @@
             {% if playwright_enabled %}
             <li class="tab"><a id="browsersteps-tab" href="#browser-steps">Browser Steps</a></li>
             {% endif %}
-
-            {% if watch['processor'] == 'text_json_diff' %}
             <li class="tab"><a id="visualselector-tab" href="#visualselector">Visual Filter Selector</a></li>
             <li class="tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
-            {% endif %}
-
-            {% if watch['processor'] == 'restock_diff' %}
-            <li class="tab"><a href="#restock">Restock Detection</a></li>
-            {% endif %}
             <li class="tab"><a href="#notifications">Notifications</a></li>
         </ul>
     </div>
@@ -56,18 +49,8 @@
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.url, placeholder="https://...", required=true, class="m-d") }}
-                        <span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span><br>
-                        <span class="pure-form-message-inline">You can use variables in the URL, perfect for inserting the current date and other logic, <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a></span><br>
-                        <span class="pure-form-message-inline">
-                        {% if watch['processor'] == 'text_json_diff' %}
-                            Current mode: <strong>Webpage Text/HTML, JSON and PDF changes.</strong><br>
-                          <a href="{{url_for('edit_page', uuid=uuid)}}?switch_processor=restock_diff" class="pure-button button-xsmall">Switch to re-stock detection mode.</a>
-                        {% else %}
-                        Current mode: <strong>Re-stock detection.</strong><br>
-                          <a href="{{url_for('edit_page', uuid=uuid)}}?switch_processor=text_json_diff" class="pure-button button-xsmall">Switch to Webpage Text/HTML, JSON and PDF changes mode.</a>
-                        {% endif %}
-                        </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") }}
@@ -123,10 +106,10 @@
                         {{ render_field(form.webdriver_delay) }}
                         <div class="pure-form-message-inline">
                             <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
-                            <br>
+                            <br/>
                             This will wait <i>n</i> seconds before extracting the text.
                             {% if using_global_webdriver_wait %}
-                            <br><strong>Using the current global default settings</strong>
+                            <br/><strong>Using the current global default settings</strong>
                             {% endif %}
                         </div>
                     </div>
@@ -231,10 +214,9 @@ User-Agent: wonderbra 1.0") }}
                 </fieldset>
             </div>
 
-            {% if watch['processor'] == 'text_json_diff' %}
             <div class="tab-pane-inner" id="filters-and-triggers">
                     <div class="pure-control-group">
-                            <strong>Pro-tips:</strong><br>
+                            <strong>Pro-tips:</strong><br/>
                             <ul>
                                 <li>
                                     Use the preview page to see your filters and triggers highlighted.
@@ -244,6 +226,12 @@ User-Agent: wonderbra 1.0") }}
                                 </li>
                             </ul>
                     </div>
+                    <fieldset>
+                        <div class="pure-control-group">
+                            {{ render_checkbox_field(form.check_unique_lines) }}
+                            <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
+                        </div>
+                    </fieldset>
                     <div class="pure-control-group">
                         {% set field = render_field(form.include_filters,
                             rows=5,
@@ -253,9 +241,9 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                         %}
                         {{ 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>
+                          <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br/>
                         {% endif %}
-                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br>
+                        <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>
@@ -278,42 +266,40 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                             </li>
                     </ul>
                     Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
-                                href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
+                                href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br/>
                 </span>
                     </div>
-                <fieldset class="pure-control-group">
-                    {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
+                    <div class="pure-control-group">
+                      {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
 footer
 nav
 .stockticker") }}
-                    <span class="pure-form-message-inline">
+                      <span class="pure-form-message-inline">
                         <ul>
                           <li> Remove HTML element(s) by CSS selector before text conversion. </li>
                           <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
-                </fieldset>
-                <div class="text-filtering">
-                <fieldset class="pure-group" id="text-filtering-type-options">
-                    <h3>Text filtering</h3>
-                        Limit trigger/ignore/block/extract to;<br>
-                        {{ render_checkbox_field(form.filter_text_added) }}
-                        {{ render_checkbox_field(form.filter_text_replaced) }}
-                        {{ render_checkbox_field(form.filter_text_removed) }}
-                    <span class="pure-form-message-inline">Note: Depending on the length and similarity of the text on each line, the algorithm may consider an <strong>addition</strong> instead of <strong>replacement</strong> for example.</span>
-                    <span class="pure-form-message-inline">So it's always better to select <strong>Added</strong>+<strong>Replaced</strong> when you're interested in new content.</span><br>
-                    <span class="pure-form-message-inline">When content is merely moved in a list, it will also trigger an <strong>addition</strong>, consider enabling <code><strong>Only trigger when unique lines appear</strong></code></span>
-                </fieldset>
+                    </div>
+                <fieldset class="pure-group">
+                    {{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
+/some.regex\d{2}/ for case-INsensitive regex
+                    ") }}
+                    <span class="pure-form-message-inline">
+                        <ul>
+                            <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
+                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
+                            <li>Changing this will affect the comparison checksum which may trigger an alert</li>
+                            <li>Use the preview/show current tab to see ignores</li>
+                        </ul>
+                </span>
 
-                <fieldset class="pure-control-group">
-                    {{ render_checkbox_field(form.check_unique_lines) }}
-                    <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
-                </fieldset>
+            </fieldset>
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.trigger_text, rows=5, placeholder="Some text to wait for in a line
 /some.regex\d{2}/ for case-INsensitive regex
-") }}
+                    ") }}
                         <span class="pure-form-message-inline">
                     <ul>
                         <li>Text to wait for before triggering a change/notification, all text and regex are tested <i>case-insensitive</i>.</li>
@@ -324,21 +310,6 @@ nav
                         </span>
                     </div>
                 </fieldset>
-                <fieldset class="pure-group">
-                    {{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
-/some.regex\d{2}/ for case-INsensitive regex
-") }}
-                    <span class="pure-form-message-inline">
-                        <ul>
-                            <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
-                            <li>Changing this will affect the comparison checksum which may trigger an alert</li>
-                            <li>Use the preview/show current tab to see ignores</li>
-                        </ul>
-                </span>
-
-                </fieldset>
-
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.text_should_not_be_present, rows=5, placeholder="For example: Out of stock
@@ -363,7 +334,7 @@ Unavailable") }}
                         <li>Extracts text in the final output (line by line) after other filters using regular expressions;
                             <ul>
                                 <li>Regular expression &dash; example <code>/reports.+?2022/i</code></li>
-                                <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br></li>
+                                <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br/></li>
                                 <li>Keyword example &dash; example <code>Out of stock</code></li>
                                 <li>Use groups to extract just that text &dash; example <code>/reports.+?(\d+)/i</code> returns a list of years only</li>
                             </ul>
@@ -373,22 +344,8 @@ Unavailable") }}
                         </span>
                     </div>
                 </fieldset>
-                </div>
             </div>
-            {% endif %}
 
-            {% if watch['processor'] == 'restock_diff' %}
-            <div class="tab-pane-inner" id="restock">
-                    <fieldset>
-                        <div class="pure-control-group">
-                            {{ render_checkbox_field(form.in_stock_only) }}
-                            <span class="pure-form-message-inline">Only trigger notifications when page changes from <strong>out of stock</strong> to <strong>back in stock</strong></span>
-                        </div>
-                    </fieldset>
-            </div>
-            {% endif %}
-
-            {% if watch['processor'] == 'text_json_diff' %}
             <div class="tab-pane-inner visual-selector-ui" id="visualselector">
                 <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
 
@@ -396,7 +353,7 @@ Unavailable") }}
                     <div class="pure-control-group">
                         {% if visualselector_enabled %}
                             <span class="pure-form-message-inline">
-                                The Visual Selector tool lets you select the <i>text</i> elements that will be used for the change detection &dash; after the <i>Browser Steps</i> has completed.<br><br>
+                                The Visual Selector tool lets you select the <i>text</i> elements that will be used for the change detection &dash; after the <i>Browser Steps</i> has completed.<br/><br/>
                             </span>
 
                             <div id="selector-header">
@@ -421,7 +378,6 @@ Unavailable") }}
                     </div>
                 </fieldset>
             </div>
-            {% endif %}
 
             <div id="actions">
                 <div class="pure-control-group">

changedetectionio/templates/import.html

@@ -1,6 +1,5 @@
 {% extends 'base.html' %}
 {% block content %}
-{% from '_helpers.jinja' import render_field %}
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="edit-form monospaced-textarea">
 
@@ -15,6 +14,7 @@
         <form class="pure-form pure-form-aligned" action="{{url_for('import_page')}}" method="POST">
             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
             <div class="tab-pane-inner" id="url-list">
+                <fieldset class="pure-group">
                     <legend>
                         Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma
                         (,):
@@ -23,7 +23,7 @@
                         <br>
                         URLs which do not pass validation will stay in the textarea.
                     </legend>
-                {{ render_field(form.processor, class="processor") }}
+
 
                     <textarea name="urls" class="pure-input-1-2" placeholder="https://"
                               style="width: 100%;
@@ -31,24 +31,22 @@
                                 white-space: pre;
                                 overflow-wrap: normal;
                                 overflow-x: scroll;" rows="25">{{ import_url_list_remaining }}</textarea>
+                </fieldset>
 
-<div id="quick-watch-processor-type">
-
-                    </div>
 
             </div>
 
             <div class="tab-pane-inner" id="distill-io">
 
 
-
+                <fieldset class="pure-group">
                     <legend>
-                        Copy and Paste your Distill.io watch 'export' file, this should be a JSON file.<br>
+                        Copy and Paste your Distill.io watch 'export' file, this should be a JSON file.</br>
                         This is <i>experimental</i>, supported fields are <code>name</code>, <code>uri</code>, <code>tags</code>, <code>config:selections</code>, the rest (including <code>schedule</code>) are ignored.
-                        <br>
+                        <br/>
                         <p>
-                        How to export? <a href="https://distill.io/docs/web-monitor/how-export-and-import-monitors/">https://distill.io/docs/web-monitor/how-export-and-import-monitors/</a><br>
-                        Be sure to set your default fetcher to Chrome if required.<br>
+                        How to export? <a href="https://distill.io/docs/web-monitor/how-export-and-import-monitors/">https://distill.io/docs/web-monitor/how-export-and-import-monitors/</a><br/>
+                        Be sure to set your default fetcher to Chrome if required.</br>
                         </p>
                     </legend>
 
@@ -77,7 +75,7 @@
     ]
 }
 " rows="25">{{ original_distill_json }}</textarea>
-
+                </fieldset>
             </div>
             <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">Import</button>
         </form>

changedetectionio/templates/preview.html

@@ -54,7 +54,7 @@
          <div class="tip">
              For now, Differences are performed on text, not graphically, only the latest screenshot is available.
          </div>
-         <br>
+         </br>
          {% if is_html_webdriver %}
            {% if screenshot %}
              <div class="snapshot-age">{{watch.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
@@ -67,4 +67,4 @@
          {% endif %}
      </div>
 </div>
-{% endblock %}
+{% endblock %}

changedetectionio/templates/settings.html

@@ -21,7 +21,6 @@
             <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="#proxies">CAPTCHA &amp; Proxies</a></li>
         </ul>
     </div>
     <div class="box-wrap inner">
@@ -40,7 +39,7 @@
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.filter_failure_notification_threshold_attempts, class="filter_failure_notification_threshold_attempts") }}
                         <span class="pure-form-message-inline">After this many consecutive times that the CSS/xPath filter is missing, send a notification
-                            <br>
+                            <br/>
                         Set to <strong>0</strong> to disable
                         </span>
                     </div>
@@ -57,16 +56,11 @@
                         {% endif %}
                     </div>
 
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.application.form.shared_diff_access, class="shared_diff_access") }}
-                        <span class="pure-form-message-inline">Allow access to view watch diff page when password is enabled (Good for sharing the diff page)
-                        </span>
-                    </div>
                     <div class="pure-control-group">
                         {{ 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 <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']}}"),
+                            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>
@@ -105,13 +99,13 @@
                         <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>
+                    <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">
                         <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
-                        <br>
+                        <br/>
                         This will wait <i>n</i> seconds before extracting the text.
                     </div>
                     <div class="pure-control-group">
@@ -124,14 +118,14 @@
 
                     <fieldset class="pure-group">
                     {{ render_checkbox_field(form.application.form.ignore_whitespace) }}
-                    <span class="pure-form-message-inline">Ignore whitespace, tabs and new-lines/line-feeds when considering if a change was detected.<br>
+                    <span class="pure-form-message-inline">Ignore whitespace, tabs and new-lines/line-feeds when considering if a change was detected.<br/>
                     <i>Note:</i> Changing this will change the status of your existing watches, possibly trigger alerts etc.
                     </span>
                     </fieldset>
                 <fieldset class="pure-group">
                     {{ render_checkbox_field(form.application.form.render_anchor_tag_content) }}
                     <span class="pure-form-message-inline">Render anchor tag content, default disabled, when enabled renders links as <code>(link text)[https://somesite.com]</code>
-                        <br>
+                        <br/>
                     <i>Note:</i> Changing this could affect the content of your existing watches, possibly trigger alerts etc.
                     </span>
                     </fieldset>
@@ -151,7 +145,7 @@ nav
                     {{ render_field(form.application.form.global_ignore_text, rows=5, placeholder="Some text to ignore in a line
 /some.regex\d{2}/ for case-INsensitive regex
                     ") }}
-                    <span class="pure-form-message-inline">Note: This is applied globally in addition to the per-watch rules.</span><br>
+                    <span class="pure-form-message-inline">Note: This is applied globally in addition to the per-watch rules.</span><br/>
                     <span class="pure-form-message-inline">
                         <ul>
                             <li>Note: This is applied globally in addition to the per-watch rules.</li>
@@ -170,35 +164,20 @@ nav
 
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.api_access_token_enabled) }}
-                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header</div><br>
-                    <div class="pure-form-message-inline"><br>API Key <span id="api-key">{{api_key}}</span>
+                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header</div><br/>
+                    <div class="pure-form-message-inline"><br/>API Key <span id="api-key">{{api_key}}</span>
                         <span style="display:none;" id="api-key-copy" >copy</span>
                     </div>
                 </div>
             </div>
-            <div class="tab-pane-inner" id="proxies">
 
-                <p><strong>Tip</strong>: You can connect to websites using <a href="https://brightdata.grsm.io/n0r16zf7eivq">BrightData</a> proxies, their service <strong>WebUnlocker</strong> will solve most CAPTCHAs, whilst their <strong>Residential Proxies</strong> may help to avoid CAPTCHA altogether. </p>
-                <p>It may be easier to try <strong>WebUnlocker</strong> first, WebUnlocker also supports country selection.</p>
-                <p>
-                    When you have <a href="https://brightdata.grsm.io/n0r16zf7eivq">registered</a>, enabled the required services, visit the <A href="https://brightdata.com/cp/api_example?">API example page</A>, then select <strong>Python</strong>, set the country you wish to use, then copy+paste the example URL below<br>
-                    The Proxy URL with BrightData should start with <code>http://brd-customer...</code>
-                </p>
-
-                <p>When you sign up using <a href="https://brightdata.grsm.io/n0r16zf7eivq">https://brightdata.grsm.io/n0r16zf7eivq</a> BrightData will match any first deposit up to $150</p>
-
-
-                <div class="pure-control-group">
-                    {{ render_field(form.requests.form.extra_proxies) }}
-                    <span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span>
-                </div>
-            </div>
             <div id="actions">
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}
                     <a href="{{url_for('index')}}" class="pure-button button-small button-cancel">Back</a>
                     <a href="{{url_for('clear_all_history')}}" class="pure-button button-small button-cancel">Clear Snapshot History</a>
                 </div>
+
             </div>
         </form>
     </div>

changedetectionio/templates/watch-overview.html

@@ -14,17 +14,13 @@
             <div id="watch-add-wrapper-zone">
                 <div>
                     {{ render_simple_field(form.url, placeholder="https://...", required=true) }}
-                    {{ render_simple_field(form.tag, value=active_tag if active_tag else '', placeholder="watch label / tag") }}
+                    {{ render_simple_field(form.tag, value=active_tag if active_tag else '', placeholder="watch group") }}
                 </div>
                 <div>
                     {{ render_simple_field(form.watch_submit_button, title="Watch this URL!" ) }}
                     {{ render_simple_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
                 </div>
             </div>
-            <div id="quick-watch-processor-type">
-                {{ render_simple_field(form.processor, title="Edit first then Watch") }}
-            </div>
-
         </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>
@@ -32,12 +28,11 @@
     <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"  name="op" value="pause">Pause</button>
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="unpause">UnPause</button>
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="mute">Mute</button>
-        <button class="pure-button button-secondary button-xsmall"  name="op" value="unmute">UnMute</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="recheck">Recheck</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default">Use default notification</button>
+        <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>
@@ -61,9 +56,9 @@
                 <th></th>
                 {% set link_order = "desc" if sort_order else "asc" %}
                 {% set arrow_span = "" %}
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('index', sort='label', order=link_order, tag=active_tag)}}">Website <span class='arrow {{link_order}}'></span></a></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag)}}">Last Checked <span class='arrow {{link_order}}'></span></a></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
+                <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 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>
@@ -76,7 +71,7 @@
               {% if not ( loop.index >= 3 and loop.index <=4) %}{% continue %}{% endif %} -->
              #}
             <tr id="{{ watch.uuid }}"
-                class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }} processor-{{ watch['processor'] }}
+                class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }}
                 {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
                 {% if watch.last_notification_error is defined and watch.last_notification_error != False %}error{% endif %}
                 {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
@@ -93,50 +88,16 @@
                 </td>
                 <td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
                     <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
-                    <a class="link-spread" href="{{url_for('form_share_put_watch', uuid=watch.uuid)}}"><img class="status-icon"  src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" /></a>
+                    <a class="link-spread" 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')}}" class="icon icon-spread" /></a>
 
-                    {% if watch.get_fetch_backend == "html_webdriver"
-                         or (  watch.get_fetch_backend == "system" and system_default_fetcher == 'html_webdriver'  )
-                    %}
-                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a chrome browser" />
-                    {% endif %}
+                    {%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 %}
 
-                    {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" />{% endif %}
                     {% if watch.last_error is defined and watch.last_error != False %}
-                    <div class="fetch-error">{{ watch.last_error }}
-
-                        {% if '403' in watch.last_error %}
-                            {% if has_proxies %}
-                                <a href="{{ url_for('settings_page', uuid=watch.uuid) }}#proxies">Try other proxies/location</a>&nbsp;
-                            {% endif %}
-                            <a href="{{ url_for('settings_page', uuid=watch.uuid) }}#proxies">Try adding external proxies/locations</a>
-                        
-                        {% endif %}
-                    </div>
+                    <div class="fetch-error">{{ watch.last_error }}</div>
                     {% endif %}
                     {% if watch.last_notification_error is defined and watch.last_notification_error != False %}
                     <div class="fetch-error notification-error"><a href="{{url_for('notification_logs')}}">{{ watch.last_notification_error }}</a></div>
                     {% endif %}
-
-                    {% if watch['processor'] == 'text_json_diff'  %}
-                        {% if watch['has_ldjson_price_data'] and not watch['track_ldjson_price_data']  %}
-                        <div class="ldjson-price-track-offer">Embedded price data detected, follow only price data? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
-                        {% endif %}
-                        {% if watch['track_ldjson_price_data'] == 'accepted' %}
-                        <span class="tracking-ldjson-price-data" title="Automatically following embedded price information"><img src="{{url_for('static_content', group='images', filename='price-tag-icon.svg')}}"  class="status-icon price-follow-tag-icon"/> Price</span>
-                        {% endif %}
-                    {% endif %}
-
-                    {% if watch['processor'] == 'restock_diff'  %}
-                    <span class="restock-label {{'in-stock' if watch['in_stock'] else 'not-in-stock' }}" title="detecting restock conditions">
-                        <!-- maybe some object watch['processor'][restock_diff] or.. -->
-                        {% if watch['last_checked'] %}
-                            {% if watch['in_stock'] %} In stock {% else %} Not in stock {% endif %}
-                        {% else %}
-                            Not yet checked
-                        {% endif %}
-                    {% endif %}
-
                     {% if not active_tag %}
                     <span class="watch-tag-list">{{ watch.tag}}</span>
                     {% endif %}

changedetectionio/tests/proxy_list/proxies.json-example

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

changedetectionio/tests/proxy_list/squid-auth.conf

@@ -1,48 +0,0 @@
-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
-
-auth_param basic program /usr/lib/squid3/basic_ncsa_auth /etc/squid3/passwords
-auth_param basic realm proxy
-acl authenticated proxy_auth REQUIRED
-http_access allow authenticated
-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/squid-passwords.txt

@@ -1 +0,0 @@
-test:$apr1$xvhFolTA$E/kz5/Rw1ewcyaSUdwqZs.

changedetectionio/tests/proxy_list/test_select_custom_proxy.py

@@ -1,50 +0,0 @@
-#!/usr/bin/python3
-
-import time
-from flask import url_for
-from ..util import live_server_setup, wait_for_all_checks
-
-# just make a request, we will grep in the docker logs to see it actually got called
-def test_select_custom(client, live_server):
-    live_server_setup(live_server)
-
-    # Goto settings, add our custom one
-    res = client.post(
-        url_for("settings_page"),
-        data={
-            "requests-time_between_check-minutes": 180,
-            "application-ignore_whitespace": "y",
-            "application-fetch_backend": "html_requests",
-            "requests-extra_proxies-0-proxy_name": "custom-test-proxy",
-            # test:awesome is set in tests/proxy_list/squid-passwords.txt
-            "requests-extra_proxies-0-proxy_url": "http://test:awesome@squid-custom:3128",
-        },
-        follow_redirects=True
-    )
-
-    assert b"Settings updated." in res.data
-
-    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": "https://changedetection.io/CHANGELOG.txt"},
-        follow_redirects=True
-    )
-
-    assert b"1 Imported" in res.data
-    wait_for_all_checks(client)
-
-    res = client.get(url_for("index"))
-    assert b'Proxy Authentication Required' not in res.data
-
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-    # We should see something via proxy
-    assert b'<div class=""> - 0.' in res.data
-
-    #
-    # Now we should see the request in the container logs for "squid-squid-custom" because it will be the only default
-

changedetectionio/tests/restock/__init__.py

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

changedetectionio/tests/restock/conftest.py

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

changedetectionio/tests/restock/test_restock.py

@@ -1,106 +0,0 @@
-#!/usr/bin/python3
-import os
-import time
-from flask import url_for
-from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
-from changedetectionio.notification import (
-    default_notification_body,
-    default_notification_format,
-    default_notification_title,
-    valid_notification_formats,
-)
-
-
-def set_original_response():
-    test_return_data = """<html>
-       <body>
-     Some initial text<br>
-     <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
-     <div>price: $10.99</div>
-     <div id="sametext">Out of stock</div>
-     </body>
-     </html>
-    """
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-    return None
-
-
-
-def set_back_in_stock_response():
-    test_return_data = """<html>
-       <body>
-     Some initial text<br>
-     <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
-     <div>price: $10.99</div>
-     <div id="sametext">Available!</div>
-     </body>
-     </html>
-    """
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-    return None
-
-# Add a site in paused mode, add an invalid filter, we should still have visual selector data ready
-def test_restock_detection(client, live_server):
-
-    set_original_response()
-    #assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
-
-    time.sleep(1)
-    live_server_setup(live_server)
-    #####################
-    notification_url = url_for('test_notification_endpoint', _external=True).replace('http://localhost', 'http://changedet').replace('http', 'json')
-
-
-    #####################
-    # 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_webdriver"},
-        follow_redirects=True
-    )
-    # 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 = url_for('test_endpoint', _external=True).replace('http://localhost', 'http://changedet')
-
-
-    client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": test_url, "tag": '', 'processor': 'restock_diff'},
-        follow_redirects=True
-    )
-
-    # Is it correctly show as NOT in stock?
-    wait_for_all_checks(client)
-    res = client.get(url_for("index"))
-    assert b'not-in-stock' in res.data
-
-    # Is it correctly shown as in stock
-    set_back_in_stock_response()
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    wait_for_all_checks(client)
-    res = client.get(url_for("index"))
-    assert b'not-in-stock' not in res.data
-
-    # We should have a notification
-    time.sleep(2)
-    assert os.path.isfile("test-datastore/notification.txt")
-    os.unlink("test-datastore/notification.txt")
-
-    # Default behaviour is to only fire notification when it goes OUT OF STOCK -> IN STOCK
-    # So here there should be no file, because we go IN STOCK -> OUT OF STOCK
-    set_original_response()
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    wait_for_all_checks(client)
-    assert not os.path.isfile("test-datastore/notification.txt")

changedetectionio/tests/test_access_control.py

@@ -1,34 +1,18 @@
-from . util import live_server_setup, extract_UUID_from_client
 from flask import url_for
-import time
+from . util import live_server_setup
 
-def test_check_access_control(app, client, live_server):
+def test_check_access_control(app, client):
     # Still doesnt work, but this is closer.
-    live_server_setup(live_server)
 
     with app.test_client(use_cookies=True) as c:
         # Check we don't have any password protection enabled yet.
         res = c.get(url_for("settings_page"))
         assert b"Remove password" not in res.data
 
-        # add something that we can hit via diff page later
-        res = c.post(
-            url_for("import_page"),
-            data={"urls": url_for('test_random_content_endpoint', _external=True)},
-            follow_redirects=True
-        )
-
-        assert b"1 Imported" in res.data
-        time.sleep(2)
-        res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
-        assert b'1 watches queued for rechecking.' in res.data
-        time.sleep(2)
-
-        # Enable password check and diff page access bypass
+        # Enable password check.
         res = c.post(
             url_for("settings_page"),
             data={"application-password": "foobar",
-                  "application-shared_diff_access": "True",
                   "requests-time_between_check-minutes": 180,
                   'application-fetch_backend': "html_requests"},
             follow_redirects=True
@@ -38,15 +22,9 @@ def test_check_access_control(app, client, live_server):
 
         # Check we hit the login
         res = c.get(url_for("index"), follow_redirects=True)
-        # Should be logged out
+
         assert b"Login" in res.data
 
-        # The diff page should return something valid when logged out
-        res = client.get(url_for("diff_history_page", uuid="first"))
-        assert b'Random content' in res.data
-
-
-
         # Menu should not be available yet
         #        assert b"SETTINGS" not in res.data
         #        assert b"BACKUP" not in res.data
@@ -131,25 +109,3 @@ def test_check_access_control(app, client, live_server):
 
         assert b"Password protection enabled" not in res.data
 
-        # Now checking the diff access
-        # Enable password check and diff page access bypass
-        res = c.post(
-            url_for("settings_page"),
-            data={"application-password": "foobar",
-                  # Should be disabled
-#                  "application-shared_diff_access": "True",
-                  "requests-time_between_check-minutes": 180,
-                  'application-fetch_backend': "html_requests"},
-            follow_redirects=True
-        )
-
-        assert b"Password protection enabled." in res.data
-
-        # Check we hit the login
-        res = c.get(url_for("index"), follow_redirects=True)
-        # Should be logged out
-        assert b"Login" in res.data
-
-        # The diff page should return something valid when logged out
-        res = client.get(url_for("diff_history_page", uuid="first"))
-        assert b'Random content' not in res.data

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -1,176 +0,0 @@
-#!/usr/bin/python3
-
-import time
-from flask import url_for
-from .util import live_server_setup
-from changedetectionio import html_tools
-
-
-def set_original(excluding=None, add_line=None):
-    test_return_data = """<html>
-     <body>
-     <p>Some initial text</p>
-     <p>So let's see what happens.</p>
-     <p>and a new line!</p>
-     <p>The golden line</p>
-     <p>A BREAK TO MAKE THE TOP LINE STAY AS "REMOVED" OR IT WILL GET COUNTED AS "CHANGED INTO"</p>
-     <p>Something irrelevant</p>          
-     </body>
-     </html>
-    """
-
-    if add_line:
-        c=test_return_data.splitlines()
-        c.insert(5, add_line)
-        test_return_data = "\n".join(c)
-
-    if excluding:
-        output = ""
-        for i in test_return_data.splitlines():
-            if not excluding in i:
-                output += f"{i}\n"
-
-        test_return_data = output
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-
-def test_setup(client, live_server):
-    live_server_setup(live_server)
-
-def test_check_removed_line_contains_trigger(client, live_server):
-    sleep_time_for_fetch_thread = 3
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-    set_original()
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
-    # Goto the edit page, add our ignore text
-    # Add our URL to the import page
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={"trigger_text": 'The golden line',
-              "url": test_url,
-              'fetch_backend': "html_requests",
-              'filter_text_removed': 'y'},
-        follow_redirects=True
-    )
-    assert b"Updated watch." in res.data
-    time.sleep(sleep_time_for_fetch_thread)
-    set_original(excluding='Something irrelevant')
-
-    # A line thats not the trigger should not trigger anything
-    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    assert b'1 watches queued for rechecking.' in res.data
-    time.sleep(sleep_time_for_fetch_thread)
-    res = client.get(url_for("index"))
-    assert b'unviewed' not in res.data
-
-    # The trigger line is REMOVED,  this should trigger
-    set_original(excluding='The golden line')
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
-    res = client.get(url_for("index"))
-    assert b'unviewed' in res.data
-
-
-    # Now add it back, and we should not get a trigger
-    client.get(url_for("mark_all_viewed"), follow_redirects=True)
-    set_original(excluding=None)
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
-    res = client.get(url_for("index"))
-    assert b'unviewed' not in res.data
-
-    # Remove it again, and we should get a trigger
-    set_original(excluding='The golden line')
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
-    res = client.get(url_for("index"))
-    assert b'unviewed' in res.data
-
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
-
-
-def test_check_add_line_contains_trigger(client, live_server):
-
-    sleep_time_for_fetch_thread = 3
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://') + "?xxx={{ watch_url }}"
-
-    res = client.post(
-        url_for("settings_page"),
-        data={"application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
-              "application-notification_body": 'triggered text was -{{triggered_text}}-',
-              # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
-              "application-notification_urls": test_notification_url,
-              "application-minutes_between_check": 180,
-              "application-fetch_backend": "html_requests"
-              },
-        follow_redirects=True
-    )
-    assert b'Settings updated' in res.data
-
-    set_original()
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
-    # Goto the edit page, add our ignore text
-    # Add our URL to the import page
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={"trigger_text": 'Oh yes please',
-              "url": test_url,
-              'fetch_backend': "html_requests",
-              'filter_text_removed': '',
-              'filter_text_added': 'y'},
-        follow_redirects=True
-    )
-    assert b"Updated watch." in res.data
-    time.sleep(sleep_time_for_fetch_thread)
-    set_original(excluding='Something irrelevant')
-
-    # A line thats not the trigger should not trigger anything
-    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    assert b'1 watches queued for rechecking.' in res.data
-    time.sleep(sleep_time_for_fetch_thread)
-    res = client.get(url_for("index"))
-    assert b'unviewed' not in res.data
-
-    # The trigger line is ADDED,  this should trigger
-    set_original(add_line='<p>Oh yes please</p>')
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
-    res = client.get(url_for("index"))
-    assert b'unviewed' in res.data
-
-    with open("test-datastore/notification.txt", 'r') as f:
-        response= f.read()
-        assert '-Oh yes please-' in response
-
-
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data

changedetectionio/tests/test_api.py

@@ -11,10 +11,10 @@ import uuid
 def set_original_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
      <div id="changetext">Some text that will change</div>
      </body>
@@ -29,10 +29,10 @@ def set_original_response():
 def set_modified_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>which has this one new line</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
      <div id="changetext">Some text that changes</div>
      </body>
@@ -53,15 +53,14 @@ def is_valid_uuid(val):
         return False
 
 
-def test_setup(client, live_server):
-    live_server_setup(live_server)
-
 def test_api_simple(client, live_server):
+    live_server_setup(live_server)
 
     api_key = extract_api_key_from_UI(client)
 
     # Create a watch
     set_original_response()
+    watch_uuid = None
 
     # Validate bad URL
     test_url = url_for('test_endpoint', _external=True,
@@ -81,34 +80,25 @@ def test_api_simple(client, live_server):
         headers={'content-type': 'application/json', 'x-api-key': api_key},
         follow_redirects=True
     )
-
-    assert is_valid_uuid(res.json.get('uuid'))
-    watch_uuid = res.json.get('uuid')
+    s = json.loads(res.data)
+    assert is_valid_uuid(s['uuid'])
+    watch_uuid = s['uuid']
     assert res.status_code == 201
 
     time.sleep(3)
 
     # Verify its in the list and that recheck worked
     res = client.get(
-        url_for("createwatch", tag="OnE"),
+        url_for("createwatch"),
         headers={'x-api-key': api_key}
     )
-    assert watch_uuid in res.json.keys()
-    before_recheck_info = res.json[watch_uuid]
+    assert watch_uuid in json.loads(res.data).keys()
+    before_recheck_info = json.loads(res.data)[watch_uuid]
     assert before_recheck_info['last_checked'] != 0
     #705 `last_changed` should be zero on the first check
     assert before_recheck_info['last_changed'] == 0
     assert before_recheck_info['title'] == 'My test URL'
 
-    # Check the limit by tag doesnt return anything when nothing found
-    res = client.get(
-        url_for("createwatch", tag="Something else entirely"),
-        headers={'x-api-key': api_key}
-    )
-    assert len(res.json) == 0
-
-    time.sleep(2)
-
     set_modified_response()
     # Trigger recheck of all ?recheck_all=1
     client.get(
@@ -122,7 +112,7 @@ def test_api_simple(client, live_server):
         url_for("createwatch"),
         headers={'x-api-key': api_key},
     )
-    after_recheck_info = res.json[watch_uuid]
+    after_recheck_info = json.loads(res.data)[watch_uuid]
     assert after_recheck_info['last_checked'] != before_recheck_info['last_checked']
     assert after_recheck_info['last_changed'] != 0
 
@@ -131,11 +121,12 @@ def test_api_simple(client, live_server):
         url_for("watchhistory", uuid=watch_uuid),
         headers={'x-api-key': api_key},
     )
-    assert len(res.json) == 2, "Should have two history entries (the original and the changed)"
+    history = json.loads(res.data)
+    assert len(history) == 2, "Should have two history entries (the original and the changed)"
 
     # Fetch a snapshot by timestamp, check the right one was found
     res = client.get(
-        url_for("watchsinglehistory", uuid=watch_uuid, timestamp=list(res.json.keys())[-1]),
+        url_for("watchsinglehistory", uuid=watch_uuid, timestamp=list(history.keys())[-1]),
         headers={'x-api-key': api_key},
     )
     assert b'which has this one new line' in res.data
@@ -152,7 +143,7 @@ def test_api_simple(client, live_server):
         url_for("watch", uuid=watch_uuid),
         headers={'x-api-key': api_key}
     )
-    watch = res.json
+    watch = json.loads(res.data)
     # @todo how to handle None/default global values?
     assert watch['history_n'] == 2, "Found replacement history section, which is in its own API"
 
@@ -161,46 +152,10 @@ def test_api_simple(client, live_server):
         url_for("systeminfo"),
         headers={'x-api-key': api_key},
     )
-    assert res.json.get('watch_count') == 1
-    assert res.json.get('uptime') > 0.5
+    info = json.loads(res.data)
+    assert info.get('watch_count') == 1
+    assert info.get('uptime') > 0.5
 
-    ######################################################
-    # Mute and Pause, check it worked
-    res = client.get(
-        url_for("watch", uuid=watch_uuid, paused='paused'),
-        headers={'x-api-key': api_key}
-    )
-    assert b'OK' in res.data
-    res = client.get(
-        url_for("watch", uuid=watch_uuid,  muted='muted'),
-        headers={'x-api-key': api_key}
-    )
-    assert b'OK' in res.data
-    res = client.get(
-        url_for("watch", uuid=watch_uuid),
-        headers={'x-api-key': api_key}
-    )
-    assert res.json.get('paused') == True
-    assert res.json.get('notification_muted') == True
-
-    # Now unpause, unmute
-    res = client.get(
-        url_for("watch", uuid=watch_uuid,  muted='unmuted'),
-        headers={'x-api-key': api_key}
-    )
-    assert b'OK' in res.data
-    res = client.get(
-        url_for("watch", uuid=watch_uuid, paused='unpaused'),
-        headers={'x-api-key': api_key}
-    )
-    assert b'OK' in res.data
-    res = client.get(
-        url_for("watch", uuid=watch_uuid),
-        headers={'x-api-key': api_key}
-    )
-    assert res.json.get('paused') == 0
-    assert res.json.get('notification_muted') == 0
-    ######################################################
 
     # Finally delete the watch
     res = client.delete(
@@ -214,7 +169,9 @@ def test_api_simple(client, live_server):
         url_for("createwatch"),
         headers={'x-api-key': api_key}
     )
-    assert len(res.json) == 0, "Watch list should be empty"
+    watch_list = json.loads(res.data)
+    assert len(watch_list) == 0, "Watch list should be empty"
+
 
 def test_access_denied(client, live_server):
     # `config_api_token_enabled` Should be On by default
@@ -246,97 +203,3 @@ def test_access_denied(client, live_server):
         url_for("createwatch")
     )
     assert res.status_code == 200
-
-    # Cleanup everything
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
-
-    res = client.post(
-        url_for("settings_page"),
-        data={
-            "requests-time_between_check-minutes": 180,
-            "application-fetch_backend": "html_requests",
-            "application-api_access_token_enabled": "y"
-        },
-        follow_redirects=True
-    )
-    assert b"Settings updated." in res.data
-
-def test_api_watch_PUT_update(client, live_server):
-
-    #live_server_setup(live_server)
-    api_key = extract_api_key_from_UI(client)
-    time.sleep(1)
-    # Create a watch
-    set_original_response()
-    test_url = url_for('test_endpoint', _external=True,
-                       headers={'x-api-key': api_key}, )
-
-    # Create new
-    res = client.post(
-        url_for("createwatch"),
-        data=json.dumps({"url": test_url, 'tag': "One, Two", "title": "My test URL", 'headers': {'cookie': 'yum'} }),
-        headers={'content-type': 'application/json', 'x-api-key': api_key},
-        follow_redirects=True
-    )
-
-    assert res.status_code == 201
-
-    time.sleep(1)
-
-    # Get a listing, it will be the first one
-    res = client.get(
-        url_for("createwatch"),
-        headers={'x-api-key': api_key}
-    )
-
-    watch_uuid = list(res.json.keys())[0]
-
-    # Check in the edit page just to be sure
-    res = client.get(
-        url_for("edit_page", uuid=watch_uuid),
-    )
-    assert b"cookie: yum" in res.data, "'cookie: yum' found in 'headers' section"
-
-    # HTTP PUT ( UPDATE an existing watch )
-    res = client.put(
-        url_for("watch", uuid=watch_uuid),
-        headers={'x-api-key': api_key, 'content-type': 'application/json'},
-        data=json.dumps({"title": "new title", 'time_between_check': {'minutes': 552}, 'headers': {'cookie': 'all eaten'}}),
-    )
-    assert res.status_code == 200, "HTTP PUT update was sent OK"
-
-    # HTTP GET single watch, title should be updated
-    res = client.get(
-        url_for("watch", uuid=watch_uuid),
-        headers={'x-api-key': api_key}
-    )
-    assert res.json.get('title') == 'new title'
-
-    # Check in the edit page just to be sure
-    res = client.get(
-        url_for("edit_page", uuid=watch_uuid),
-    )
-    assert b"new title" in res.data, "new title found in edit page"
-    assert b"552" in res.data, "552 minutes found in edit page"
-    assert b"One, Two" in res.data, "Tag 'One, Two' was found"
-    assert b"cookie: all eaten" in res.data, "'cookie: all eaten' found in 'headers' section"
-
-    ######################################################
-
-    # HTTP PUT try a field that doenst exist
-
-    # HTTP PUT an update
-    res = client.put(
-        url_for("watch", uuid=watch_uuid),
-        headers={'x-api-key': api_key, 'content-type': 'application/json'},
-        data=json.dumps({"title": "new title", "some other field": "uh oh"}),
-    )
-
-    assert res.status_code == 400, "Should get error 400 when we give a field that doesnt exist"
-    # Message will come from `flask_expects_json`
-    assert b'Additional properties are not allowed' in res.data
-
-    # Cleanup everything
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data

changedetectionio/tests/test_automatic_follow_ldjson_price.py

@@ -1,146 +0,0 @@
-#!/usr/bin/python3
-
-import time
-from flask import url_for
-from .util import live_server_setup, extract_UUID_from_client, extract_api_key_from_UI
-
-def set_response_with_ldjson():
-    test_return_data = """<html>
-       <body>
-     Some initial text<br>
-     <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
-     <div class="sametext">Some text thats the same</div>
-     <div class="changetext">Some text that will change</div>
-     <script type="application/ld+json">
-        {
-           "@context":"https://schema.org/",
-           "@type":"Product",
-           "@id":"https://www.some-virtual-phone-shop.com/celular-iphone-14/p",
-           "name":"Celular Iphone 14 Pro Max 256Gb E Sim A16 Bionic",
-           "brand":{
-              "@type":"Brand",
-              "name":"APPLE"
-           },
-           "image":"https://www.some-virtual-phone-shop.com/15509426/image.jpg",
-           "description":"You dont need it",
-           "mpn":"111111",
-           "sku":"22222",
-           "offers":{
-              "@type":"AggregateOffer",
-              "lowPrice":8097000,
-              "highPrice":8099900,
-              "priceCurrency":"COP",
-              "offers":[
-                 {
-                    "@type":"Offer",
-                    "price":8097000,
-                    "priceCurrency":"COP",
-                    "availability":"http://schema.org/InStock",
-                    "sku":"102375961",
-                    "itemCondition":"http://schema.org/NewCondition",
-                    "seller":{
-                       "@type":"Organization",
-                       "name":"ajax"
-                    }
-                 }
-              ],
-              "offerCount":1
-           }
-        }
-       </script>
-     </body>
-     </html>
-"""
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-    return None
-
-def set_response_without_ldjson():
-    test_return_data = """<html>
-       <body>
-     Some initial text<br>
-     <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
-     <div class="sametext">Some text thats the same</div>
-     <div class="changetext">Some text that will change</div>     
-     </body>
-     </html>
-"""
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-    return None
-
-# actually only really used by the distll.io importer, but could be handy too
-def test_check_ldjson_price_autodetect(client, live_server):
-    live_server_setup(live_server)
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
-    set_response_with_ldjson()
-
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-    time.sleep(3)
-
-    # Should get a notice that it's available
-    res = client.get(url_for("index"))
-    assert b'ldjson-price-track-offer' in res.data
-
-    # Accept it
-    uuid = extract_UUID_from_client(client)
-
-    client.get(url_for('price_data_follower.accept', uuid=uuid, follow_redirects=True))
-    time.sleep(2)
-
-    # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(2)
-    # Offer should be gone
-    res = client.get(url_for("index"))
-    assert b'Embedded price data' not in res.data
-    assert b'tracking-ldjson-price-data' in res.data
-
-    # and last snapshop (via API) should be just the price
-    api_key = extract_api_key_from_UI(client)
-    res = client.get(
-        url_for("watchsinglehistory", uuid=uuid, timestamp='latest'),
-        headers={'x-api-key': api_key},
-    )
-
-    # Should see this (dont know where the whitespace came from)
-    assert b'"highPrice": 8099900' in res.data
-    # And not this cause its not the ld-json
-    assert b"So let's see what happens" not in res.data
-
-    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-
-    ##########################################################################################
-    # And we shouldnt see the offer
-    set_response_without_ldjson()
-
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-    time.sleep(3)
-    res = client.get(url_for("index"))
-    assert b'ldjson-price-track-offer' not in res.data
-    
-    ##########################################################################################
-    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

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, wait_for_all_checks, extract_rss_token_from_UI
+from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
 
 sleep_time_for_fetch_thread = 3
 
@@ -11,7 +11,7 @@ sleep_time_for_fetch_thread = 3
 # Basic test to check inscriptus is not adding return line chars, basically works etc
 def test_inscriptus():
     from inscriptis import get_text
-    html_content = "<html><body>test!<br>ok man</body></html>"
+    html_content = "<html><body>test!<br/>ok man</body></html>"
     stripped_text_from_html = get_text(html_content)
     assert stripped_text_from_html == 'test!\nok man'
 
@@ -67,7 +67,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
 
     # Force recheck
     res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    assert b'1 watches queued for rechecking.' in res.data
+    assert b'1 watches are queued for rechecking.' in res.data
 
     wait_for_all_checks(client)
 
@@ -76,13 +76,12 @@ def test_check_basic_change_detection_functionality(client, live_server):
     assert b'unviewed' in res.data
 
     # #75, and it should be in the RSS feed
-    rss_token = extract_rss_token_from_UI(client)
-    res = client.get(url_for("rss", token=rss_token, _external=True))
+    res = client.get(url_for("rss"))
     expected_url = url_for('test_endpoint', _external=True)
     assert b'<rss' in res.data
 
     # re #16 should have the diff in here too
-    assert b'(into) which has this one new line' in res.data
+    assert b'(into   ) which has this one new line' in res.data
     assert b'CDATA' in res.data
 
     assert expected_url.encode('utf-8') in res.data

changedetectionio/tests/test_block_while_text_present.py

@@ -8,10 +8,10 @@ from changedetectionio import html_tools
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -24,10 +24,10 @@ def set_original_ignore_response():
 def set_modified_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some NEW nice initial text<br>
+     Some NEW nice initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <p>new ignore stuff</p>
      <p>out of stock</p>
      <p>blah</p>
@@ -44,11 +44,11 @@ def set_modified_original_ignore_response():
 def set_modified_response_minus_block_text():
     test_return_data = """<html>
        <body>
-     Some NEW nice initial text<br>
+     Some NEW nice initial text</br>
      <p>Which is across multiple lines</p>
      <p>now on sale $2/p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <p>new ignore stuff</p>
      <p>blah</p>
      </body>
@@ -87,10 +87,7 @@ def test_check_block_changedetection_text_NOT_present(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"text_should_not_be_present": ignore_text,
-              "url": test_url,
-              'fetch_backend': "html_requests"
-              },
+        data={"text_should_not_be_present": ignore_text, "url": test_url, 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -132,6 +129,7 @@ def test_check_block_changedetection_text_NOT_present(client, live_server):
     set_modified_response_minus_block_text()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
+
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 

changedetectionio/tests/test_css_selector.py

@@ -12,10 +12,10 @@ def test_setup(live_server):
 def set_original_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
      <div id="changetext">Some text that will change</div>
      </body>
@@ -29,10 +29,10 @@ def set_original_response():
 def set_modified_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>which has this one new line</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
      <div id="changetext">Some text that changes</div>
      </body>

changedetectionio/tests/test_element_removal.py

@@ -25,10 +25,10 @@ def set_original_response():
     </ul>
     </nav>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
     <div id="changetext">Some text that will change</div>
      </body>
     <footer>
@@ -54,10 +54,10 @@ def set_modified_response():
     </ul>
     </nav>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
     <div id="changetext">Some text that changes</div>
      </body>
     <footer>
@@ -71,6 +71,7 @@ def set_modified_response():
 
 
 def test_element_removal_output():
+    from changedetectionio import fetch_site_status
     from inscriptis import get_text
 
     # Check text with sub-parts renders correctly
@@ -84,7 +85,7 @@ def test_element_removal_output():
     </ul>
     </nav>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>across multiple lines</p>
      <div id="changetext">Some text that changes</div>
      </body>
@@ -120,7 +121,7 @@ def test_element_removal_full(client, live_server):
         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 the filter data
     # Not sure why \r needs to be added - absent of the #changetext this is not necessary
     subtractive_selectors_data = "header\r\nfooter\r\nnav\r\n#changetext"

changedetectionio/tests/test_encoding.py

@@ -38,6 +38,9 @@ def test_check_encoding_detection(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(2)
 

changedetectionio/tests/test_errorhandling.py

@@ -59,8 +59,6 @@ def test_http_error_handler(client, live_server):
     _runner_test_http_errors(client, live_server, 404, 'Page not found')
     _runner_test_http_errors(client, live_server, 500, '(Internal server Error) received')
     _runner_test_http_errors(client, live_server, 400, 'Error - Request returned a HTTP error code 400')
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
 
 # Just to be sure error text is properly handled
 def test_DNS_errors(client, live_server):
@@ -79,52 +77,7 @@ def test_DNS_errors(client, live_server):
     time.sleep(3)
 
     res = client.get(url_for("index"))
-    found_name_resolution_error = b"Temporary failure in name resolution" in res.data or b"Name or service not known" in res.data
-    assert found_name_resolution_error
+    assert b'Name or service not known' in res.data
     # Should always record that we tried
     assert bytes("just now".encode('utf-8')) in res.data
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
 
-# Re 1513
-def test_low_level_errors_clear_correctly(client, live_server):
-    #live_server_setup(live_server)
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write("<html><body><div id=here>Hello world</div></body></html>")
-
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
-
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": "https://dfkjasdkfjaidjfsdajfksdajfksdjfDOESNTEXIST.com"},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-    time.sleep(2)
-
-    # We should see the DNS error
-    res = client.get(url_for("index"))
-    found_name_resolution_error = b"Temporary failure in name resolution" in res.data or b"Name or service not known" in res.data
-    assert found_name_resolution_error
-
-    # Update with what should work
-    client.post(
-        url_for("edit_page", uuid="first"),
-        data={
-            "url": test_url,
-            "fetch_backend": "html_requests"},
-        follow_redirects=True
-    )
-
-    # Now the error should be gone
-    time.sleep(2)
-    res = client.get(url_for("index"))
-    found_name_resolution_error = b"Temporary failure in name resolution" in res.data or b"Name or service not known" in res.data
-    assert not found_name_resolution_error
-
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data

changedetectionio/tests/test_extract_regex.py

@@ -10,10 +10,10 @@ from ..html_tools import *
 def set_original_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
      <div class="changetext">Some text that will change</div>     
      </body>
@@ -28,12 +28,12 @@ def set_original_response():
 def set_modified_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>which has this one new line</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
-     <div class="changetext">Some text that did change ( 1000 online <br> 80 guests<br>  2000 online )</div>
+     <div class="changetext">Some text that did change ( 1000 online <br/> 80 guests<br/>  2000 online )</div>
      <div class="changetext">SomeCase insensitive 3456</div>
      </body>
      </html>
@@ -49,8 +49,8 @@ def set_multiline_response():
     test_return_data = """<html>
        <body>
      
-     <p>Something <br>
-        across 6 billion multiple<br>
+     <p>Something <br/>
+        across 6 billion multiple<br/>
         lines
      </p>
      

changedetectionio/tests/test_filter_exist_changes.py

@@ -11,10 +11,10 @@ from changedetectionio.model import App
 def set_response_without_filter():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <div id="nope-doesnt-exist">Some text thats the same</div>     
      </body>
      </html>
@@ -28,10 +28,10 @@ def set_response_without_filter():
 def set_response_with_filter():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <div class="ticket-available">Ticket now on sale!</div>     
      </body>
      </html>
@@ -73,17 +73,17 @@ def test_filter_doesnt_exist_then_exists_should_get_notification(client, live_se
 
     # Just a regular notification setting, this will be used by the special 'filter not found' notification
     notification_form_data = {"notification_urls": notification_url,
-                              "notification_title": "New ChangeDetection.io Notification - {{watch_url}}",
-                              "notification_body": "BASE URL: {{base_url}}\n"
-                                                   "Watch URL: {{watch_url}}\n"
-                                                   "Watch UUID: {{watch_uuid}}\n"
-                                                   "Watch title: {{watch_title}}\n"
-                                                   "Watch tag: {{watch_tag}}\n"
-                                                   "Preview: {{preview_url}}\n"
-                                                   "Diff URL: {{diff_url}}\n"
-                                                   "Snapshot: {{current_snapshot}}\n"
-                                                   "Diff: {{diff}}\n"
-                                                   "Diff Full: {{diff_full}}\n"
+                              "notification_title": "New ChangeDetection.io Notification - {watch_url}",
+                              "notification_body": "BASE URL: {base_url}\n"
+                                                   "Watch URL: {watch_url}\n"
+                                                   "Watch UUID: {watch_uuid}\n"
+                                                   "Watch title: {watch_title}\n"
+                                                   "Watch tag: {watch_tag}\n"
+                                                   "Preview: {preview_url}\n"
+                                                   "Diff URL: {diff_url}\n"
+                                                   "Snapshot: {current_snapshot}\n"
+                                                   "Diff: {diff}\n"
+                                                   "Diff Full: {diff_full}\n"
                                                    ":-)",
                               "notification_format": "Text"}
 
@@ -117,3 +117,18 @@ def test_filter_doesnt_exist_then_exists_should_get_notification(client, live_se
 
     assert 'Ticket now on sale' in notification
     os.unlink("test-datastore/notification.txt")
+
+
+    # Test that if it gets removed, then re-added, we get a notification
+    # Remove the target and re-add it, we should get a new notification
+    set_response_without_filter()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    time.sleep(3)
+    assert not os.path.isfile("test-datastore/notification.txt")
+
+    set_response_with_filter()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    time.sleep(3)
+    assert os.path.isfile("test-datastore/notification.txt")
+
+# Also test that the filter was updated after the first one was requested

changedetectionio/tests/test_filter_failure_notification.py

@@ -1,17 +1,18 @@
 import os
 import time
+import re
 from flask import url_for
-from .util import set_original_response, live_server_setup, extract_UUID_from_client
+from .util import set_original_response, live_server_setup
 from changedetectionio.model import App
 
 
 def set_response_with_filter():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <div id="nope-doesnt-exist">Some text thats the same</div>     
      </body>
      </html>
@@ -55,17 +56,17 @@ def run_filter_test(client, content_filter):
 
     # Just a regular notification setting, this will be used by the special 'filter not found' notification
     notification_form_data = {"notification_urls": notification_url,
-                              "notification_title": "New ChangeDetection.io Notification - {{watch_url}}",
-                              "notification_body": "BASE URL: {{base_url}}\n"
-                                                   "Watch URL: {{watch_url}}\n"
-                                                   "Watch UUID: {{watch_uuid}}\n"
-                                                   "Watch title: {{watch_title}}\n"
-                                                   "Watch tag: {{watch_tag}}\n"
-                                                   "Preview: {{preview_url}}\n"
-                                                   "Diff URL: {{diff_url}}\n"
-                                                   "Snapshot: {{current_snapshot}}\n"
-                                                   "Diff: {{diff}}\n"
-                                                   "Diff Full: {{diff_full}}\n"
+                              "notification_title": "New ChangeDetection.io Notification - {watch_url}",
+                              "notification_body": "BASE URL: {base_url}\n"
+                                                   "Watch URL: {watch_url}\n"
+                                                   "Watch UUID: {watch_uuid}\n"
+                                                   "Watch title: {watch_title}\n"
+                                                   "Watch tag: {watch_tag}\n"
+                                                   "Preview: {preview_url}\n"
+                                                   "Diff URL: {diff_url}\n"
+                                                   "Snapshot: {current_snapshot}\n"
+                                                   "Diff: {diff}\n"
+                                                   "Diff Full: {diff_full}\n"
                                                    ":-)",
                               "notification_format": "Text"}
 
@@ -83,7 +84,6 @@ def run_filter_test(client, content_filter):
         data=notification_form_data,
         follow_redirects=True
     )
-
     assert b"Updated watch." in res.data
     time.sleep(3)
 
@@ -120,10 +120,6 @@ def run_filter_test(client, content_filter):
         notification = f.read()
     assert not 'CSS/xPath filter was not present in the page' in notification
 
-    # Re #1247 - All tokens got replaced
-    uuid = extract_UUID_from_client(client)
-    assert uuid in notification
-
     # cleanup for the next
     client.get(
         url_for("form_delete", uuid="all"),
@@ -145,4 +141,4 @@ def test_check_xpath_filter_failure_notification(client, live_server):
     time.sleep(1)
     run_filter_test(client, '//*[@id="nope-doesnt-exist"]')
 
-# Test that notification is never sent
+# Test that notification is never sent

changedetectionio/tests/test_html_to_text.py

@@ -6,11 +6,11 @@ from ..html_tools import html_to_text
 def test_html_to_text_func():
     test_html = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
      <a href="/first_link"> More Text </a>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <a href="second_link.com"> Even More Text </a>
      </body>
      </html>
@@ -21,7 +21,7 @@ def test_html_to_text_func():
 
     no_links_text = \
         "Some initial text\n\nWhich is across multiple " \
-        "lines\n\nMore Text\nSo let's see what happens.\nEven More Text"
+        "lines\n\nMore Text So let's see what happens. Even More Text"
 
     # check that no links are in the extracted text
     assert text_content == no_links_text
@@ -31,7 +31,7 @@ def test_html_to_text_func():
 
     links_text = \
         "Some initial text\n\nWhich is across multiple lines\n\n[ More Text " \
-        "](/first_link)\nSo let's see what happens.\n[ Even More Text ]" \
+        "](/first_link) So let's see what happens. [ Even More Text ]" \
         "(second_link.com)"
 
     # check that links are present in the extracted text

changedetectionio/tests/test_ignore_regex_text.py

@@ -1,5 +1,7 @@
 #!/usr/bin/python3
 
+import time
+from flask import url_for
 from . util import live_server_setup
 from changedetectionio import html_tools
 
@@ -9,7 +11,7 @@ def test_setup(live_server):
 # Unit test of the stripper
 # Always we are dealing in utf-8
 def test_strip_regex_text_func():
-    from ..processors import text_json_diff as fetch_site_status
+    from changedetectionio import fetch_site_status
 
     test_content = """
     but sometimes we want to remove the lines.

changedetectionio/tests/test_ignore_text.py

@@ -11,8 +11,7 @@ def test_setup(live_server):
 # Unit test of the stripper
 # Always we are dealing in utf-8
 def test_strip_text_func():
-    from ..processors import text_json_diff as fetch_site_status
-
+    from changedetectionio import fetch_site_status
 
     test_content = """
     Some content
@@ -34,10 +33,10 @@ def test_strip_text_func():
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -50,10 +49,10 @@ def set_original_ignore_response():
 def set_modified_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some NEW nice initial text<br>
+     Some NEW nice initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      <p>new ignore stuff</p>
      <p>blah</p>
      </body>
@@ -69,11 +68,11 @@ def set_modified_original_ignore_response():
 def set_modified_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
      <P>ZZZZz</P>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -102,6 +101,9 @@ def test_check_ignore_text_functionality(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)
 
@@ -197,6 +199,9 @@ def test_check_global_ignore_text_functionality(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)
 

changedetectionio/tests/test_ignorehyperlinks.py

@@ -12,10 +12,10 @@ def test_setup(live_server):
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <a href="/original_link"> Some More Text </a>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      </body>
      </html>
     """
@@ -29,10 +29,10 @@ def set_original_ignore_response():
 def set_modified_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <a href="/modified_link"> Some More Text </a>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      </body>
      </html>
     """

changedetectionio/tests/test_ignorestatuscode.py

@@ -12,10 +12,10 @@ def test_setup(live_server):
 def set_original_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      </body>
      </html>
     """
@@ -27,10 +27,10 @@ def set_original_response():
 def set_some_changed_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines, and a new thing too.</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      </body>
      </html>
     """
@@ -69,6 +69,8 @@ def test_normal_page_check_works_with_ignore_status_code(client, live_server):
     assert b"1 Imported" in res.data
 
     time.sleep(sleep_time_for_fetch_thread)
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     set_some_changed_response()
     time.sleep(sleep_time_for_fetch_thread)
@@ -102,6 +104,9 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server):
     )
     assert b"1 Imported" in res.data
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 
@@ -114,9 +119,11 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server):
     )
     assert b"Updated watch." in res.data
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
-
     #  Make a change
     set_some_changed_response()
 

changedetectionio/tests/test_ignorewhitespace.py

@@ -12,15 +12,15 @@ def test_setup(live_server):
 def set_original_ignore_response_but_with_whitespace():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>
 
 
      Which is across multiple lines</p>
      <br>
-     <br>
+     </br>
 
-         So let's see what happens.  <br>
+         So let's see what happens.  </br>
 
 
      </body>
@@ -34,10 +34,10 @@ def set_original_ignore_response_but_with_whitespace():
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      </body>
      </html>
 

changedetectionio/tests/test_jsonpath_jq_selector.py

@@ -198,8 +198,8 @@ def test_check_json_without_filter(client, live_server):
     )
 
     # Should still see '"html": "<b>"'
-    assert b'&#34;html&#34;: &#34;&lt;b&gt;&#34;' in res.data
-    assert res.data.count(b'{') >= 2
+    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
@@ -394,48 +394,6 @@ def check_json_ext_filter(json_filter, client, live_server):
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
-def test_ignore_json_order(client, live_server):
-    # A change in order shouldn't trigger a notification
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write('{"hello" : 123, "world": 123}')
-
-
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', content_type="application/json", _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(2)
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write('{"world" : 123, "hello": 123}')
-
-    # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(2)
-
-    res = client.get(url_for("index"))
-    assert b'unviewed' not in res.data
-
-    # Just to be sure it still works
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write('{"world" : 123, "hello": 124}')
-
-    # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(2)
-
-    res = client.get(url_for("index"))
-    assert b'unviewed' in res.data
-
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
-
 def test_check_jsonpath_ext_filter(client, live_server):
     check_json_ext_filter('json:$[?(@.status==Sold)]', client, live_server)
 

changedetectionio/tests/test_notification.py

@@ -73,12 +73,16 @@ def test_check_notification(client, live_server):
     # We write the PNG to disk, but a JPEG should appear in the notification
     # Write the last screenshot png
     testimage_png = 'iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYII='
+    # This one is created when we save the screenshot from the webdriver/playwright session (converted from PNG)
+    testimage_jpg = '/9j/4AAQSkZJRgABAQEASABIAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMDAsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/wAALCAABAAEBAREA/8QAFAABAAAAAAAAAAAAAAAAAAAACf/EABQQAQAAAAAAAAAAAAAAAAAAAAD/2gAIAQEAAD8AKp//2Q=='
 
 
     uuid = extract_UUID_from_client(client)
     datastore = 'test-datastore'
     with open(os.path.join(datastore, str(uuid), 'last-screenshot.png'), 'wb') as f:
         f.write(base64.b64decode(testimage_png))
+    with open(os.path.join(datastore, str(uuid), 'last-screenshot.jpg'), 'wb') as f:
+        f.write(base64.b64decode(testimage_jpg))
 
     # Goto the edit page, add our ignore text
     # Add our URL to the import page
@@ -86,19 +90,17 @@ def test_check_notification(client, live_server):
     print (">>>> Notification URL: "+notification_url)
 
     notification_form_data = {"notification_urls": notification_url,
-                              "notification_title": "New ChangeDetection.io Notification - {{watch_url}}",
-                              "notification_body": "BASE URL: {{base_url}}\n"
-                                                   "Watch URL: {{watch_url}}\n"
-                                                   "Watch UUID: {{watch_uuid}}\n"
-                                                   "Watch title: {{watch_title}}\n"
-                                                   "Watch tag: {{watch_tag}}\n"
-                                                   "Preview: {{preview_url}}\n"
-                                                   "Diff URL: {{diff_url}}\n"
-                                                   "Snapshot: {{current_snapshot}}\n"
-                                                   "Diff: {{diff}}\n"
-                                                   "Diff Added: {{diff_added}}\n"
-                                                   "Diff Removed: {{diff_removed}}\n"
-                                                   "Diff Full: {{diff_full}}\n"
+                              "notification_title": "New ChangeDetection.io Notification - {watch_url}",
+                              "notification_body": "BASE URL: {base_url}\n"
+                                                   "Watch URL: {watch_url}\n"
+                                                   "Watch UUID: {watch_uuid}\n"
+                                                   "Watch title: {watch_title}\n"
+                                                   "Watch tag: {watch_tag}\n"
+                                                   "Preview: {preview_url}\n"
+                                                   "Diff URL: {diff_url}\n"
+                                                   "Snapshot: {current_snapshot}\n"
+                                                   "Diff: {diff}\n"
+                                                   "Diff Full: {diff_full}\n"
                                                    ":-)",
                               "notification_screenshot": True,
                               "notification_format": "Text"}
@@ -145,7 +147,7 @@ def test_check_notification(client, live_server):
     assert ':-)' in notification_submission
     assert "Diff Full: Some initial text" in notification_submission
     assert "Diff: (changed) Which is across multiple lines" in notification_submission
-    assert "(into) which has this one new line" in notification_submission
+    assert "(into   ) which has this one new line" in notification_submission
     # Re #342 - check for accidental python byte encoding of non-utf8/string
     assert "b'" not in notification_submission
     assert re.search('Watch UUID: [0-9a-f]{8}(-[0-9a-f]{4}){3}-[0-9a-f]{12}', notification_submission, re.IGNORECASE)
@@ -158,12 +160,12 @@ def test_check_notification(client, live_server):
 
     # Check the attachment was added, and that it is a JPEG from the original PNG
     notification_submission_object = json.loads(notification_submission)
-    # We keep PNG screenshots for now
-    assert notification_submission_object['attachments'][0]['filename'] == 'last-screenshot.png'
+    assert notification_submission_object['attachments'][0]['filename'] == 'last-screenshot.jpg'
     assert len(notification_submission_object['attachments'][0]['base64'])
-    assert notification_submission_object['attachments'][0]['mimetype'] == 'image/png'
+    assert notification_submission_object['attachments'][0]['mimetype'] == 'image/jpeg'
     jpeg_in_attachment = base64.b64decode(notification_submission_object['attachments'][0]['base64'])
-
+    assert b'JFIF' in jpeg_in_attachment
+    assert testimage_png not in notification_submission
     # Assert that the JPEG is readable (didn't get chewed up somewhere)
     from PIL import Image
     import io
@@ -177,6 +179,7 @@ def test_check_notification(client, live_server):
         logging.debug(">>> Skipping BASE_URL check")
 
 
+
     # This should insert the {current_snapshot}
     set_more_modified_response()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
@@ -234,10 +237,10 @@ def test_check_notification(client, live_server):
         follow_redirects=True
     )
 
+
 def test_notification_validation(client, live_server):
-
-    time.sleep(1)
-
+    #live_server_setup(live_server)
+    time.sleep(3)
     # re #242 - when you edited an existing new entry, it would not correctly show the notification settings
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
@@ -265,6 +268,21 @@ def test_notification_validation(client, live_server):
 #    )
 #    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(
+        url_for("settings_page"),
+        data={"application-notification_title": "New ChangeDetection.io Notification - {watch_url}",
+              "application-notification_body": "Rubbish: {rubbish}\n",
+              "application-notification_format": "Text",
+              "application-notification_urls": "json://localhost/foobar",
+              "requests-time_between_check-minutes": 180,
+              "fetch_backend": "html_requests"
+              },
+        follow_redirects=True
+    )
+
+    assert bytes("is not a valid token".encode('utf-8')) in res.data
+
     # cleanup for the next
     client.get(
         url_for("form_delete", uuid="all"),
@@ -272,61 +290,3 @@ def test_notification_validation(client, live_server):
     )
 
 
-
-def test_notification_custom_endpoint_and_jinja2(client, live_server):
-    time.sleep(1)
-
-    # test_endpoint - that sends the contents of a file
-    # test_notification_endpoint - that takes a POST and writes it to file (test-datastore/notification.txt)
-
-    # CUSTOM JSON BODY CHECK for POST://
-    set_original_response()
-    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?xxx={{ watch_url }}"
-
-    res = client.post(
-        url_for("settings_page"),
-        data={"application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
-              "application-notification_body": '{ "url" : "{{ watch_url }}", "secret": 444 }',
-              # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
-              "application-notification_urls": test_notification_url,
-              "application-minutes_between_check": 180,
-              "application-fetch_backend": "html_requests"
-              },
-        follow_redirects=True
-    )
-    assert b'Settings updated' in res.data
-    client.get(
-        url_for("form_delete", uuid="all"),
-        follow_redirects=True
-    )
-    # Add a watch and trigger a HTTP POST
-    test_url = url_for('test_endpoint', _external=True)
-    res = client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": test_url, "tag": 'nice one'},
-        follow_redirects=True
-    )
-
-    assert b"Watch added" in res.data
-
-    time.sleep(2)
-    set_modified_response()
-
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(2)
-
-
-    with open("test-datastore/notification.txt", 'r') as f:
-        x=f.read()
-        j = json.loads(x)
-        assert j['url'].startswith('http://localhost')
-        assert j['secret'] == 444
-
-    # URL check, this will always be converted to lowercase
-    assert os.path.isfile("test-datastore/notification-url.txt")
-    with open("test-datastore/notification-url.txt", 'r') as f:
-        notification_url = f.read()
-        assert 'xxx=http' in notification_url
-
-    os.unlink("test-datastore/notification-url.txt")
-

changedetectionio/tests/test_notification_errors.py

@@ -11,23 +11,23 @@ def test_check_notification_error_handling(client, live_server):
     set_original_response()
 
     # Give the endpoint time to spin up
-    time.sleep(2)
+    time.sleep(3)
 
-    # Set a URL and fetch it, then set a notification URL which is going to give errors
+    # use a different URL so that it doesnt interfere with the actual check until we are ready
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(
         url_for("form_quick_watch_add"),
-        data={"url": test_url, "tag": ''},
+        data={"url": "https://changedetection.io/CHANGELOG.txt", "tag": ''},
         follow_redirects=True
     )
     assert b"Watch added" in res.data
 
-    time.sleep(2)
-    set_modified_response()
+    time.sleep(10)
 
+    # Check we capture the failure, we can just use trigger_check = y here
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"notification_urls": "jsons://broken-url-xxxxxxxx123/test",
+        data={"notification_urls": "jsons://broken-url.changedetection.io/test",
               "notification_title": "xxx",
               "notification_body": "xxxxx",
               "notification_format": "Text",
@@ -36,14 +36,15 @@ def test_check_notification_error_handling(client, live_server):
               "title": "",
               "headers": "",
               "time_between_check-minutes": "180",
-              "fetch_backend": "html_requests"},
+              "fetch_backend": "html_requests",
+              "trigger_check": "y"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
 
     found=False
     for i in range(1, 10):
-
+        time.sleep(1)
         logging.debug("Fetching watch overview....")
         res = client.get(
             url_for("index"))
@@ -52,7 +53,6 @@ def test_check_notification_error_handling(client, live_server):
             found=True
             break
 
-        time.sleep(1)
 
     assert found
 
@@ -60,7 +60,7 @@ def test_check_notification_error_handling(client, live_server):
     # The error should show in the notification logs
     res = client.get(
         url_for("notification_logs"))
-    found_name_resolution_error = b"Temporary failure in name resolution" in res.data or b"Name or service not known" in res.data
-    assert found_name_resolution_error
+    assert bytes("Name or service not known".encode('utf-8')) in res.data
 
-    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+
+    # And it should be listed on the watch overview

changedetectionio/tests/test_pdf.py

@@ -1,40 +0,0 @@
-#!/usr/bin/python3
-
-import time
-from flask import url_for
-from .util import set_original_response, set_modified_response, live_server_setup
-
-sleep_time_for_fetch_thread = 3
-
-# `subtractive_selectors` should still work in `source:` type requests
-def test_fetch_pdf(client, live_server):
-    import shutil
-    shutil.copy("tests/test.pdf", "test-datastore/endpoint-test.pdf")
-
-    live_server_setup(live_server)
-    test_url = url_for('test_pdf_endpoint', _external=True)
-    # Add our URL to the import page
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-
-    assert b"1 Imported" in res.data
-
-    time.sleep(sleep_time_for_fetch_thread)
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-
-    assert b'PDF-1.5' not in res.data
-    assert b'hello world' in res.data
-
-    # So we know if the file changes in other ways
-    import hashlib
-    md5 = hashlib.md5(open("test-datastore/endpoint-test.pdf", 'rb').read()).hexdigest().upper()
-    # We should have one
-    assert len(md5) >0
-    # And it's going to be in the document
-    assert b'Document checksum - '+bytes(str(md5).encode('utf-8')) in res.data

changedetectionio/tests/test_request.py

@@ -20,8 +20,6 @@ def test_headers_in_request(client, live_server):
     )
     assert b"1 Imported" in res.data
 
-    time.sleep(1)
-
     res = client.post(
         url_for("import_page"),
         data={"urls": test_url},
@@ -176,7 +174,6 @@ def test_method_in_request(client, live_server):
     )
     assert b"1 Imported" in res.data
 
-    time.sleep(2)
     res = client.post(
         url_for("import_page"),
         data={"urls": test_url},
@@ -184,8 +181,6 @@ def test_method_in_request(client, live_server):
     )
     assert b"1 Imported" in res.data
 
-    time.sleep(2)
-
     # Attempt to add a method which is not valid
     res = client.post(
         url_for("edit_page", uuid="first"),
@@ -211,7 +206,7 @@ def test_method_in_request(client, live_server):
     assert b"Updated watch." in res.data
 
     # Give the thread time to pick up the first version
-    time.sleep(2)
+    time.sleep(5)
 
     # The service should echo back the request verb
     res = client.get(
@@ -222,7 +217,7 @@ def test_method_in_request(client, live_server):
     # The test call service will return the verb as the body
     assert b"PATCH" in res.data
 
-    time.sleep(2)
+    time.sleep(5)
 
     watches_with_method = 0
     with open('test-datastore/url-watches.json') as f:

changedetectionio/tests/test_rss.py

@@ -1,39 +0,0 @@
-#!/usr/bin/python3
-
-import time
-from flask import url_for
-from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI
-
-
-def test_rss_and_token(client, live_server):
-    set_original_response()
-    live_server_setup(live_server)
-
-    # Add our URL to the import page
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": url_for('test_random_content_endpoint', _external=True)},
-        follow_redirects=True
-    )
-
-    assert b"1 Imported" in res.data
-    rss_token = extract_rss_token_from_UI(client)
-
-    time.sleep(2)
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(2)
-
-    # Add our URL to the import page
-    res = client.get(
-        url_for("rss", token="bad token", _external=True),
-        follow_redirects=True
-    )
-
-    assert b"Access denied, bad token" in res.data
-
-    res = client.get(
-        url_for("rss", token=rss_token, _external=True),
-        follow_redirects=True
-    )
-    assert b"Access denied, bad token" not in res.data
-    assert b"Random content" in res.data

changedetectionio/tests/test_security.py

@@ -2,9 +2,11 @@ from flask import url_for
 from . util import set_original_response, set_modified_response, live_server_setup
 import time
 
-
-def test_bad_access(client, live_server):
+def test_setup(live_server):
     live_server_setup(live_server)
+
+def test_file_access(client, live_server):
+
     res = client.post(
         url_for("import_page"),
         data={"urls": 'https://localhost'},
@@ -17,49 +19,18 @@ def test_bad_access(client, live_server):
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={
-              "url": 'javascript:alert(document.domain)',
+              "url": 'file:///etc/passwd',
               "tag": "",
               "method": "GET",
               "fetch_backend": "html_requests",
               "body": ""},
         follow_redirects=True
     )
+    time.sleep(3)
 
-    assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
-
-    res = client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": '            javascript:alert(123)', "tag": ''},
+    res = client.get(
+        url_for("index", uuid="first"),
         follow_redirects=True
     )
 
-    assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
-
-    res = client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": '%20%20%20javascript:alert(123)%20%20', "tag": ''},
-        follow_redirects=True
-    )
-
-    assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
-
-
-    res = client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": ' source:javascript:alert(document.domain)', "tag": ''},
-        follow_redirects=True
-    )
-
-    assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
-
-    # file:// is permitted by default, but it will be caught by ALLOW_FILE_URI
-
-    client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": 'file:///tasty/disk/drive', "tag": ''},
-        follow_redirects=True
-    )
-    time.sleep(1)
-    res = client.get(url_for("index"))
-
-    assert b'file:// type access is denied for security reasons.' in res.data
+    assert b'denied for security reasons' in res.data

changedetectionio/tests/test_source.py

@@ -40,7 +40,7 @@ def test_check_basic_change_detection_functionality_source(client, live_server):
 
     # Force recheck
     res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    assert b'1 watches queued for rechecking.' in res.data
+    assert b'1 watches are queued for rechecking.' in res.data
 
     time.sleep(5)
 
@@ -90,4 +90,4 @@ def test_check_ignore_elements(client, live_server):
     )
     assert b'foobar-detection' not in res.data
     assert b'<br' not in res.data
-    assert b'<p' in res.data
+    assert b'<p' in res.data

changedetectionio/tests/test_trigger.py

@@ -8,10 +8,10 @@ from . util import live_server_setup
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -24,10 +24,10 @@ def set_original_ignore_response():
 def set_modified_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some NEW nice initial text<br>
+     Some NEW nice initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -40,12 +40,12 @@ def set_modified_original_ignore_response():
 def set_modified_with_trigger_text_response():
     test_return_data = """<html>
        <body>
-     Some NEW nice initial text<br>
+     Some NEW nice initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
      Add to cart
-     <br>
-     So let's see what happens.  <br>
+     <br/>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -142,4 +142,4 @@ def test_trigger_functionality(client, live_server):
     res = client.get(url_for("preview_page", uuid="first"))
 
     # We should be able to see what we triggered on
-    assert b'<div class="triggered">Add to cart' in res.data
+    assert b'<div class="triggered">Add to cart' in res.data

changedetectionio/tests/test_trigger_regex.py

@@ -8,10 +8,10 @@ from . util import live_server_setup
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
+     </br>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -72,7 +72,7 @@ def test_trigger_regex_functionality(client, live_server):
     assert b'unviewed' not in res.data
 
     with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write("regex test123<br>\nsomething 123")
+        f.write("regex test123<br/>\nsomething 123")
 
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
@@ -81,4 +81,4 @@ def test_trigger_regex_functionality(client, live_server):
 
     # Cleanup everything
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
+    assert b'Deleted' in res.data