attempt update for dnspython too

Added `prodotto esaurito` - Italian for out of stock

.github/test/Dockerfile-alpine

@@ -12,8 +12,10 @@ RUN \
     cargo \
     g++ \
     gcc \
+    jpeg-dev \
     libc-dev \
     libffi-dev \
+    libjpeg \
     libxslt-dev \
     make \
     openssl-dev \

.github/workflows/pypi-release.yml

@@ -11,7 +11,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
-        python-version: "3.x"
+        python-version: "3.11"
     - name: Install pypa/build
       run: >-
         python3 -m
@@ -38,14 +38,19 @@ jobs:
       with:
         name: python-package-distributions
         path: dist/
+    - name: Set up Python 3.11
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.11'
     - name: Test that the basic pip built package runs without error
       run: |
-        set -e
+        set -ex
+        sudo pip3 install --upgrade pip 
         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
+        curl --retry-connrefused --retry 6 http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
-        curl http://127.0.0.1:10000/ >/dev/null
+        curl --retry-connrefused --retry 6 http://127.0.0.1:10000/ >/dev/null
         killall changedetection.io
 
 

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

@@ -11,12 +11,14 @@ on:
       - requirements.txt
       - Dockerfile
       - .github/workflows/*
+      - .github/test/Dockerfile*
 
   pull_request:
     paths:
       - requirements.txt
       - Dockerfile
       - .github/workflows/*
+      - .github/test/Dockerfile*
 
   # Changes to requirements.txt packages and Dockerfile may or may not always be compatible with arm etc, so worth testing
   # @todo: some kind of path filter for requirements.txt and Dockerfile

.github/workflows/test-only.yml

@@ -28,12 +28,12 @@ jobs:
           
           docker network create changedet-network
           
-          # Selenium+browserless
+          # Selenium
           docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome:4
-          docker run --network changedet-network -d --name browserless --hostname browserless -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.60-chrome-stable
           
-          # For accessing custom browser tests
+          # SocketPuppetBrowser + Extra for custom browser test
-          docker run --network changedet-network -d --name browserless-custom-url --hostname browserless-custom-url -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm --shm-size="2g"  browserless/chrome:1.60-chrome-stable
+          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser --hostname sockpuppetbrowser --rm -p 3000:3000 dgtlmoon/sockpuppetbrowser:latest                    
+          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser-custom-url --hostname sockpuppetbrowser-custom-url  -p 3001:3000 --rm dgtlmoon/sockpuppetbrowser:latest
 
       - name: Build changedetection.io container for testing
         run: |         
@@ -47,7 +47,13 @@ jobs:
           # Debug SMTP server/echo message back server
           docker run --network changedet-network -d -p 11025:11025 -p 11080:11080  --hostname mailserver test-changedetectionio  bash -c 'python changedetectionio/tests/smtp/smtp-test-server.py' 
 
-      - name: Test built container with pytest
+      - name: Show docker container state and other debug info
+        run: |
+          set -x
+          echo "Running processes in docker..."
+          docker ps
+
+      - name: Test built container with Pytest (generally as requests/plaintext fetching)
         run: |
           # Unit tests
           echo "run test with unittest"
@@ -59,40 +65,76 @@ jobs:
           # The default pytest logger_level is TRACE
           # To change logger_level for pytest(test/conftest.py),
           # append the docker option. e.g. '-e LOGGER_LEVEL=DEBUG'
-          docker run --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio && ./run_basic_tests.sh'
+          docker run --name test-cdio-basic-tests --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio && ./run_basic_tests.sh'
 
-      - name: Test built container selenium+browserless/playwright
+# PLAYWRIGHT/NODE-> CDP
+      - name: Playwright and SocketPuppetBrowser - Specific tests in built container
         run: |
+          # Playwright via Sockpuppetbrowser fetch
+          # tests/visualselector/test_fetch_data.py will do browser steps  
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
 
+
+      - name: Playwright and SocketPuppetBrowser - Headers and requests
+        run: |       
+          # Settings headers playwright tests - Call back in from Sockpuppetbrowser, check headers
+          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
+
+      - name: Playwright and SocketPuppetBrowser - Restock detection
+        run: |                            
+          # restock detection via playwright - added name=changedet here so that playwright and sockpuppetbrowser can connect to it
+          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser: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'
+
+# STRAIGHT TO CDP
+      - name: Pyppeteer and SocketPuppetBrowser - Specific tests in built container
+        run: |
+          # Playwright via Sockpuppetbrowser fetch 
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
+
+      - name: Pyppeteer and SocketPuppetBrowser - Headers and requests checks
+        run: |       
+          # Settings headers playwright tests - Call back in from Sockpuppetbrowser, check headers
+          docker run --name "changedet" --hostname changedet --rm  -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
+
+      - name: Pyppeteer and SocketPuppetBrowser - Restock detection
+        run: |                            
+          # restock detection via playwright - added name=changedet here so that playwright and sockpuppetbrowser can connect to it
+          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet"  -e "FAST_PUPPETEER_CHROME_FETCHER=True"  -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser: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'
+
+# SELENIUM
+      - name: Specific tests in built container for Selenium
+        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
+      - name: Specific tests in built container for headers and requests checks with Selenium
-          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'
+        run: |
-          
-          # Settings headers playwright tests - Call back in from Browserless, check headers
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
           docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "USE_EXPERIMENTAL_PUPPETEER_FETCH=yes" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'          
-          
-          # restock detection via playwright - added name=changedet here so that playwright/browserless can connect to it
-          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
 
+# OTHER STUFF
       - name: Test SMTP notification mime types
         run: |
           # SMTP content types - needs the 'Debug SMTP server/echo message back server' container from above
           docker run --rm  --network changedet-network test-changedetectionio bash -c 'cd changedetectionio;pytest tests/smtp/test_notification_smtp.py'
 
-      - name: Test with puppeteer fetcher and disk cache
+      # @todo Add a test via playwright/puppeteer
-        run: |
+      # squid with auth is tested in run_proxy_tests.sh -> tests/proxy_list/test_select_custom_proxy.py
-          docker run --rm -e "PUPPETEER_DISK_CACHE=/tmp/data/" -e "USE_EXPERIMENTAL_PUPPETEER_FETCH=yes" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
+      - name: Test proxy squid style interaction
-          # Browserless would have had -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" added above
-
-      - name: Test proxy interaction
         run: |
           cd changedetectionio
           ./run_proxy_tests.sh
-          # And again with PLAYWRIGHT_DRIVER_URL=..
+          cd ..
+
+      - name: Test proxy SOCKS5 style interaction
+        run: |
+          cd changedetectionio
+          ./run_socks_proxy_tests.sh
           cd ..
 
       - name: Test custom browser URL
@@ -106,10 +148,10 @@ jobs:
           docker run --name test-changedetectionio -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
+          curl --retry-connrefused --retry 6  -s http://localhost:5556 |grep -q checkbox-uuid
           
           # and IPv6
-          curl -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
+          curl --retry-connrefused --retry 6  -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
 
           # Check whether TRACE log is enabled.
           # Also, check whether TRACE is came from STDERR
@@ -166,6 +208,16 @@ jobs:
           # @todo - scan the container log to see the right "graceful shutdown" text exists           
           docker rm sig-test
 
-#export WEBDRIVER_URL=http://localhost:4444/wd/hub
+      - name: Dump container log
-#pytest tests/fetchers/test_content.py
+        if: always()
-#pytest tests/test_errorhandling.py
+        run: |
+          mkdir output-logs
+          docker logs test-cdio-basic-tests > output-logs/test-cdio-basic-tests-stdout.txt
+          docker logs test-cdio-basic-tests 2> output-logs/test-cdio-basic-tests-stderr.txt
+
+      - name: Store container log
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-cdio-basic-tests-output
+          path: output-logs

CONTRIBUTING.md

@@ -2,7 +2,7 @@ Contributing is always welcome!
 
 I am no professional flask developer, if you know a better way that something can be done, please let me know!
 
-Otherwise, it's always best to PR into the `dev` branch.
+Otherwise, it's always best to PR into the `master` branch.
 
 Please be sure that all new functionality has a matching test!
 

Dockerfile

@@ -1,5 +1,8 @@
 # pip dependencies install stage
-FROM python:3.11-slim-bookworm as builder
+
+# @NOTE! I would love to move to 3.11 but it breaks the async handler in changedetectionio/content_fetchers/puppeteer.py
+#        If you know how to fix it, please do! and test it for both 3.10 and 3.11
+FROM python:3.10-slim-bookworm as builder
 
 # See `cryptography` pin comment in requirements.txt
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
@@ -25,11 +28,11 @@ RUN pip install --target=/dependencies -r /requirements.txt
 # Playwright is an alternative to Selenium
 # Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
 # https://github.com/dgtlmoon/changedetection.io/pull/1067 also musl/alpine (not supported)
-RUN pip install --target=/dependencies playwright~=1.40 \
+RUN pip install --target=/dependencies playwright~=1.41.2 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
-FROM python:3.11-slim-bookworm
+FROM python:3.10-slim-bookworm
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libxslt1.1 \

MANIFEST.in

@@ -1,8 +1,8 @@
 recursive-include changedetectionio/api *
 recursive-include changedetectionio/blueprint *
+recursive-include changedetectionio/content_fetchers *
 recursive-include changedetectionio/model *
 recursive-include changedetectionio/processors *
-recursive-include changedetectionio/res *
 recursive-include changedetectionio/static *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/tests *

README.md

@@ -91,6 +91,14 @@ We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) glob
 
 Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
 
+### We have a Chrome extension!
+
+Easily add the current web page to your changedetection.io tool, simply install the extension and click "Sync" to connect it to your existing changedetection.io install.
+
+[<img src="./docs/chrome-extension-screenshot.png" style="max-width:80%;" alt="Chrome Extension to easily add the current web-page to detect a change."  title="Chrome Extension to easily add the current web-page to detect a change."  />](https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop)
+
+[Goto the Chrome Webstore to download the extension.](https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop)
+
 ## Installation
 
 ### Docker

changedetectionio/__init__.py

@@ -2,15 +2,15 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.45.13'
+__version__ = '0.45.17'
 
 from distutils.util import strtobool
 from json.decoder import JSONDecodeError
-
+import os
+#os.environ['EVENTLET_NO_GREENDNS'] = 'yes'
 import eventlet
 import eventlet.wsgi
 import getopt
-import os
 import signal
 import socket
 import sys

changedetectionio/blueprint/browser_steps/TODO.txt

@@ -0,0 +1,7 @@
+- This needs an abstraction to directly handle the puppeteer connection methods
+- Then remove the playwright stuff
+- Remove hack redirect at line 65 changedetectionio/processors/__init__.py
+
+The screenshots are base64 encoded/decoded which is very CPU intensive for large screenshots (in playwright) but not
+in the direct puppeteer connection (they are binary end to end)
+

changedetectionio/blueprint/browser_steps/__init__.py

@@ -4,22 +4,13 @@
 # Why?
 # `browsersteps_playwright_browser_interface.chromium.connect_over_cdp()` will only run once without async()
 # - this flask app is not async()
-# - browserless has a single timeout/keepalive which applies to the session made at .connect_over_cdp()
+# - A single timeout/keepalive which applies to the session made at .connect_over_cdp()
 #
 # So it means that we must unfortunately for now just keep a single timer since .connect_over_cdp() was run
 # and know when that reaches timeout/keepalive :( when that time is up, restart the connection and tell the user
 # that their time is up, insert another coin. (reload)
 #
-# Bigger picture
-# - It's horrible that we have this click+wait deal, some nice socket.io solution using something similar
-# to what the browserless debug UI already gives us would be smarter..
 #
-# OR
-# - Some API call that should be hacked into browserless or playwright that we can "/api/bump-keepalive/{session_id}/60"
-# So we can tell it that we need more time (run this on each action)
-#
-# OR
-# - use multiprocessing to bump this over to its own process and add some transport layer (queue/pipes)
 
 from distutils.util import strtobool
 from flask import Blueprint, request, make_response

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -6,6 +6,8 @@ import re
 from random import randint
 from loguru import logger
 
+from changedetectionio.content_fetchers.base import manage_user_agent
+
 # Two flags, tell the JS which of the "Selector" or "Value" field should be enabled in the front end
 # 0- off, 1- on
 browser_step_ui_config = {'Choose one': '0 0',
@@ -169,7 +171,7 @@ class steppable_browser_interface():
         self.page.locator(selector, timeout=1000).uncheck(timeout=1000)
 
 
-# Responsible for maintaining a live 'context' with browserless
+# Responsible for maintaining a live 'context' with the chrome CDP
 # @todo - how long do contexts live for anyway?
 class browsersteps_live_ui(steppable_browser_interface):
     context = None
@@ -178,6 +180,7 @@ class browsersteps_live_ui(steppable_browser_interface):
     stale = False
     # bump and kill this if idle after X sec
     age_start = 0
+    headers = {}
 
     # use a special driver, maybe locally etc
     command_executor = os.getenv(
@@ -192,7 +195,8 @@ class browsersteps_live_ui(steppable_browser_interface):
 
     browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
 
-    def __init__(self, playwright_browser, proxy=None):
+    def __init__(self, playwright_browser, proxy=None, headers=None):
+        self.headers = headers or {}
         self.age_start = time.time()
         self.playwright_browser = playwright_browser
         if self.context is None:
@@ -206,16 +210,17 @@ class browsersteps_live_ui(steppable_browser_interface):
 
         # @todo handle multiple contexts, bind a unique id from the browser on each req?
         self.context = self.playwright_browser.new_context(
-            # @todo
+            accept_downloads=False,  # Should never be needed
-            #                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
+            bypass_csp=True,  # This is needed to enable JavaScript execution on GitHub and others
-            #               proxy=self.proxy,
+            extra_http_headers=self.headers,
-            # This is needed to enable JavaScript execution on GitHub and others
+            ignore_https_errors=True,
-            bypass_csp=True,
+            proxy=proxy,
-            # Should never be needed
+            service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
-            accept_downloads=False,
+            # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
-            proxy=proxy
+            user_agent=manage_user_agent(headers=self.headers),
         )
 
+
         self.page = self.context.new_page()
 
         # self.page.set_default_navigation_timeout(keep_open)
@@ -243,7 +248,7 @@ 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__, "../../content_fetchers/res/xpath_element_scraper.js").decode('utf-8')
         now = time.time()
         self.page.wait_for_timeout(1 * 1000)
 
@@ -278,10 +283,10 @@ 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')
+        xpath_element_js = resource_string(__name__, "../../content_fetchers/res/xpath_element_scraper.js").decode('utf-8')
-        from changedetectionio.content_fetcher import visualselector_xpath_selectors
+        from changedetectionio.content_fetchers import visualselector_xpath_selectors
         xpath_element_js = xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
         xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")
-        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
 
         return (screenshot, xpath_data)

changedetectionio/blueprint/browser_steps/nonContext.py

@@ -1,5 +1,4 @@
 from playwright.sync_api import PlaywrightContextManager
-import asyncio
 
 # So playwright wants to run as a context manager, but we do something horrible and hacky
 # we are holding the session open for as long as possible, then shutting it down, and opening a new one

changedetectionio/blueprint/check_proxies/__init__.py

@@ -1,14 +1,11 @@
 from concurrent.futures import ThreadPoolExecutor
+from changedetectionio.store import ChangeDetectionStore
 
 from functools import wraps
 
 from flask import Blueprint
 from flask_login import login_required
 
-from changedetectionio.processors import text_json_diff
-from changedetectionio.store import ChangeDetectionStore
-
-
 STATUS_CHECKING = 0
 STATUS_FAILED = 1
 STATUS_OK = 2
@@ -32,7 +29,8 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @threadpool
     def long_task(uuid, preferred_proxy):
         import time
-        from changedetectionio import content_fetcher
+        from changedetectionio.content_fetchers import exceptions as content_fetcher_exceptions
+        from changedetectionio.processors import text_json_diff
 
         status = {'status': '', 'length': 0, 'text': ''}
         from jinja2 import Environment, BaseLoader
@@ -43,7 +41,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             update_handler = text_json_diff.perform_site_check(datastore=datastore, watch_uuid=uuid)
             update_handler.call_browser()
         # title, size is len contents not len xfer
-        except content_fetcher.Non200ErrorCodeReceived as e:
+        except content_fetcher_exceptions.Non200ErrorCodeReceived as e:
             if e.status_code == 404:
                 status.update({'status': 'OK', 'length': len(contents), 'text': f"OK but 404 (page not found)"})
             elif e.status_code == 403 or e.status_code == 401:
@@ -52,12 +50,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 status.update({'status': 'ERROR', 'length': len(contents), 'text': f"Status code: {e.status_code}"})
         except text_json_diff.FilterNotFoundInResponse:
             status.update({'status': 'OK', 'length': len(contents), 'text': f"OK but CSS/xPath filter not found (page changed layout?)"})
-        except content_fetcher.EmptyReply as e:
+        except content_fetcher_exceptions.EmptyReply as e:
             if e.status_code == 403 or e.status_code == 401:
                 status.update({'status': 'ERROR OTHER', 'length': len(contents), 'text': f"Got empty reply with code {e.status_code} - Access denied"})
             else:
                 status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': f"Empty reply with code {e.status_code}, needs chrome?"})
-        except content_fetcher.ReplyWithContentButNoText as e:
+        except content_fetcher_exceptions.ReplyWithContentButNoText as e:
             txt = f"Got reply but with no content - Status code {e.status_code} - It's possible that the filters were found, but contained no usable text (or contained only an image)."
             status.update({'status': 'ERROR', 'text': txt})
         except Exception as e:

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -18,8 +18,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
     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))
+        return redirect(url_for("index"))
-
 
     @login_required
     @price_data_follower_blueprint.route("/<string:uuid>/reject", methods=['GET'])

changedetectionio/blueprint/tags/__init__.py

@@ -11,9 +11,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def tags_overview_page():
         from .form import SingleTag
         add_form = SingleTag(request.form)
+        sorted_tags = sorted(datastore.data['settings']['application'].get('tags').items(), key=lambda x: x[1]['title'])
         output = render_template("groups-overview.html",
                                  form=add_form,
-                                 available_tags=datastore.data['settings']['application'].get('tags', {}),
+                                 available_tags=sorted_tags,
                                  )
 
         return output

changedetectionio/blueprint/tags/templates/groups-overview.html

@@ -40,7 +40,7 @@
                 <td colspan="3">No website organisational tags/groups configured</td>
             </tr>
             {% endif %}
-            {% for uuid, tag in available_tags.items()  %}
+            {% for uuid, tag in available_tags  %}
             <tr id="{{ uuid }}" class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }}">
                 <td class="watch-controls">
                     <a class="link-mute state-{{'on' if tag.notification_muted else 'off'}}" href="{{url_for('tags.mute', uuid=tag.uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute" ></a>

changedetectionio/content_fetcher.py

@@ -1,771 +0,0 @@
-from abc import abstractmethod
-from distutils.util import strtobool
-from urllib.parse import urlparse
-import chardet
-import hashlib
-import json
-import os
-import requests
-import sys
-import time
-import urllib.parse
-from loguru import logger
-
-visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4, header, footer, section, article, aside, details, main, nav, section, summary'
-
-
-class Non200ErrorCodeReceived(Exception):
-    def __init__(self, status_code, url, screenshot=None, xpath_data=None, page_html=None):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        self.xpath_data = xpath_data
-        self.page_text = None
-
-        if page_html:
-            from changedetectionio import html_tools
-            self.page_text = html_tools.html_to_text(page_html)
-        return
-
-
-class checksumFromPreviousCheckWasTheSame(Exception):
-    def __init__(self):
-        return
-
-
-class JSActionExceptions(Exception):
-    def __init__(self, status_code, url, screenshot, message=''):
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        self.message = message
-        return
-
-
-class BrowserStepsStepException(Exception):
-    def __init__(self, step_n, original_e):
-        self.step_n = step_n
-        self.original_e = original_e
-        logger.debug(f"Browser Steps exception at step {self.step_n} {str(original_e)}")
-        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, has_filters=False, html_content=''):
-        # 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.has_filters = has_filters
-        self.html_content = html_content
-        return
-
-
-class Fetcher():
-    browser_connection_is_custom = None
-    browser_connection_url = None
-    browser_steps = None
-    browser_steps_screenshot_path = None
-    content = None
-    error = None
-    fetcher_description = "No description"
-    headers = {}
-    instock_data = None
-    instock_data_js = ""
-    status_code = None
-    webdriver_js_execute_code = None
-    xpath_data = None
-    xpath_element_js = ""
-
-    # Will be needed in the future by the VisualSelector, always get this where possible.
-    screenshot = False
-    system_http_proxy = os.getenv('HTTP_PROXY')
-    system_https_proxy = os.getenv('HTTPS_PROXY')
-
-    # Time ONTOP of the system defined env minimum time
-    render_extract_delay = 0
-
-    def __init__(self):
-        from pkg_resources import resource_string
-        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
-        self.xpath_element_js = resource_string(__name__, "res/xpath_element_scraper.js").decode('utf-8')
-        self.instock_data_js = resource_string(__name__, "res/stock-not-in-stock.js").decode('utf-8')
-
-    @abstractmethod
-    def get_error(self):
-        return self.error
-
-    @abstractmethod
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-        # Should set self.error, self.status_code and self.content
-        pass
-
-    @abstractmethod
-    def quit(self):
-        return
-
-    @abstractmethod
-    def get_last_status_code(self):
-        return self.status_code
-
-    @abstractmethod
-    def screenshot_step(self, step_n):
-        return None
-
-    @abstractmethod
-    # Return true/false if this checker is ready to run, in the case it needs todo some special config check etc
-    def is_ready(self):
-        return True
-
-    def get_all_headers(self):
-        """
-        Get all headers but ensure all keys are lowercase
-        :return:
-        """
-        return {k.lower(): v for k, v in self.headers.items()}
-
-    def browser_steps_get_valid_steps(self):
-        if self.browser_steps is not None and len(self.browser_steps):
-            valid_steps = filter(
-                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
-                self.browser_steps)
-
-            return valid_steps
-
-        return None
-
-    def iterate_browser_steps(self):
-        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
-        from playwright._impl._errors import TimeoutError, Error
-        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 = self.browser_steps_get_valid_steps()
-
-            for step in valid_steps:
-                step_n += 1
-                logger.debug(f">> Iterating check - browser Step n {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 (Error, TimeoutError) as e:
-                    logger.debug(str(e))
-                    # Stop processing here
-                    raise BrowserStepsStepException(step_n=step_n, original_e=e)
-
-    # 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:
-                if os.path.isfile(f):
-                    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, custom_browser_connection_url=None):
-        super().__init__()
-
-        self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
-
-        if custom_browser_connection_url:
-            self.browser_connection_is_custom = True
-            self.browser_connection_url = custom_browser_connection_url
-        else:
-            # Fallback to fetching from system
-            # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
-            self.browser_connection_url = 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
-            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))
-            logger.debug(f"Saving step screenshot to {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))
-        logger.debug(f"Saving step HTML to {destination}")
-        with open(destination, 'w') as f:
-            f.write(content)
-
-    def run_fetch_browserless_puppeteer(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-
-        from pkg_resources import resource_string
-
-        extra_wait_ms = (int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay) * 1000
-
-        self.xpath_element_js = self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
-        code = resource_string(__name__, "res/puppeteer_fetch.js").decode('utf-8')
-        # In the future inject this is a proper JS package
-        code = code.replace('%xpath_scrape_code%', self.xpath_element_js)
-        code = code.replace('%instock_scrape_code%', self.instock_data_js)
-
-        from requests.exceptions import ConnectTimeout, ReadTimeout
-        wait_browserless_seconds = 240
-
-        browserless_function_url = os.getenv('BROWSERLESS_FUNCTION_URL')
-        from urllib.parse import urlparse
-        if not browserless_function_url:
-            # Convert/try to guess from PLAYWRIGHT_DRIVER_URL
-            o = urlparse(os.getenv('PLAYWRIGHT_DRIVER_URL'))
-            browserless_function_url = o._replace(scheme="http")._replace(path="function").geturl()
-
-
-        # Append proxy connect string
-        if self.proxy:
-            # Remove username/password if it exists in the URL or you will receive "ERR_NO_SUPPORTED_PROXIES" error
-            # Actual authentication handled by Puppeteer/node
-            o = urlparse(self.proxy.get('server'))
-            proxy_url = urllib.parse.quote(o._replace(netloc="{}:{}".format(o.hostname, o.port)).geturl())
-            browserless_function_url = f"{browserless_function_url}&--proxy-server={proxy_url}"
-
-        try:
-            amp = '&' if '?' in browserless_function_url else '?'
-            response = requests.request(
-                method="POST",
-                json={
-                    "code": code,
-                    "context": {
-                        # Very primitive disk cache - USE WITH EXTREME CAUTION
-                        # Run browserless container  with -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]"
-                        'disk_cache_dir': os.getenv("PUPPETEER_DISK_CACHE", False), # or path to disk cache ending in /, ie /tmp/cache/
-                        'execute_js': self.webdriver_js_execute_code,
-                        'extra_wait_ms': extra_wait_ms,
-                        'include_filters': current_include_filters,
-                        'req_headers': request_headers,
-                        'screenshot_quality': int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)),
-                        'url': url,
-                        'user_agent': {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None),
-                        'proxy_username': self.proxy.get('username', '') if self.proxy else False,
-                        'proxy_password': self.proxy.get('password', '') if self.proxy and self.proxy.get('username') else False,
-                        'no_cache_list': [
-                            'twitter',
-                            '.pdf'
-                        ],
-                        # Could use https://github.com/easylist/easylist here, or install a plugin
-                        'block_url_list': [
-                            'adnxs.com',
-                            'analytics.twitter.com',
-                            'doubleclick.net',
-                            'google-analytics.com',
-                            'googletagmanager',
-                            'trustpilot.com'
-                        ]
-                    }
-                },
-                # @todo /function needs adding ws:// to http:// rebuild this
-                url=browserless_function_url+f"{amp}--disable-features=AudioServiceOutOfProcess&dumpio=true&--disable-remote-fonts",
-                timeout=wait_browserless_seconds)
-
-        except ReadTimeout:
-            raise PageUnloadable(url=url, status_code=None, message=f"No response from browserless in {wait_browserless_seconds}s")
-        except ConnectTimeout:
-            raise PageUnloadable(url=url, status_code=None, message=f"Timed out connecting to browserless, retrying..")
-        else:
-            # 200 Here means that the communication to browserless worked only, not the page state
-            if response.status_code == 200:
-                import base64
-
-                x = response.json()
-                if not x.get('screenshot'):
-                    # https://github.com/puppeteer/puppeteer/blob/v1.0.0/docs/troubleshooting.md#tips
-                    # https://github.com/puppeteer/puppeteer/issues/1834
-                    # https://github.com/puppeteer/puppeteer/issues/1834#issuecomment-381047051
-                    # Check your memory is shared and big enough
-                    raise ScreenshotUnavailable(url=url, status_code=None)
-
-                if not x.get('content', '').strip():
-                    raise EmptyReply(url=url, status_code=None)
-
-                if x.get('status_code', 200) != 200 and not ignore_status_codes:
-                    raise Non200ErrorCodeReceived(url=url, status_code=x.get('status_code', 200), page_html=x['content'])
-
-                self.content = x.get('content')
-                self.headers = x.get('headers')
-                self.instock_data = x.get('instock_data')
-                self.screenshot = base64.b64decode(x.get('screenshot'))
-                self.status_code = x.get('status_code')
-                self.xpath_data = x.get('xpath_data')
-
-            else:
-                # Some other error from browserless
-                raise PageUnloadable(url=url, status_code=None, message=response.content.decode('utf-8'))
-
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-
-
-        # For now, USE_EXPERIMENTAL_PUPPETEER_FETCH is not supported by watches with BrowserSteps (for now!)
-        # browser_connection_is_custom doesnt work with puppeteer style fetch (use playwright native too in this case)
-        if not self.browser_connection_is_custom and not self.browser_steps and os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
-            if strtobool(os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH')):
-                # Temporary backup solution until we rewrite the playwright code
-                return self.run_fetch_browserless_puppeteer(
-                    url,
-                    timeout,
-                    request_headers,
-                    request_body,
-                    request_method,
-                    ignore_status_codes,
-                    current_include_filters,
-                    is_binary)
-
-        from playwright.sync_api import sync_playwright
-        import playwright._impl._errors
-
-        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.browser_connection_url, timeout=60000)
-
-            # SOCKS5 with authentication is not supported (yet)
-            # https://github.com/microsoft/playwright/issues/10567
-
-            # Set user agent to prevent Cloudflare from blocking the browser
-            # Use the default one configured in the App.py model that's passed from fetch_site_status.py
-            context = browser.new_context(
-                user_agent={k.lower(): v for k, v in request_headers.items()}.get('user-agent', None),
-                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)
-
-            # Listen for all console events and handle errors
-            self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
-
-            # Re-use as much code from browser steps as possible so its the same
-            from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
-            browsersteps_interface = steppable_browser_interface()
-            browsersteps_interface.page = self.page
-
-            response = browsersteps_interface.action_goto_url(value=url)
-            self.headers = response.all_headers()
-
-            if response is None:
-                context.close()
-                browser.close()
-                logger.debug("Content Fetcher > Response object was none")
-                raise EmptyReply(url=url, status_code=None)
-
-            try:
-                if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
-                    browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
-            except playwright._impl._errors.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:
-                logger.debug(f"Content Fetcher > Other exception when executing custom JS code {str(e)}")
-                context.close()
-                browser.close()
-                raise PageUnloadable(url=url, status_code=None, message=str(e))
-
-            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-            self.page.wait_for_timeout(extra_wait * 1000)
-
-            try:
-                self.status_code = response.status
-            except Exception as e:
-                # https://github.com/dgtlmoon/changedetection.io/discussions/2122#discussioncomment-8241962
-                logger.critical(f"Response from browserless/playwright did not have a status_code! Response follows.")
-                logger.critical(response)
-                raise PageUnloadable(url=url, status_code=None, message=str(e))
-
-            if self.status_code != 200 and not ignore_status_codes:
-
-                screenshot=self.page.screenshot(type='jpeg', full_page=True,
-                                     quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
-
-                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
-
-            if len(self.page.content().strip()) == 0:
-                context.close()
-                browser.close()
-                logger.debug("Content Fetcher > Content was empty")
-                raise EmptyReply(url=url, status_code=response.status)
-
-            # Run Browser Steps here
-            if self.browser_steps_get_valid_steps():
-                self.iterate_browser_steps()
-                
-            self.page.wait_for_timeout(extra_wait * 1000)
-
-            # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
-            if current_include_filters is not None:
-                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 + "}")
-
-            self.content = self.page.content()
-            # Bug 3 in Playwright screenshot handling
-            # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
-            # JPEG is better here because the screenshots can be very very large
-
-            # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
-            # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
-            # acceptable screenshot quality here
-            try:
-                # The actual screenshot
-                self.screenshot = self.page.screenshot(type='jpeg', full_page=True,
-                                                       quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
-            except Exception as e:
-                context.close()
-                browser.close()
-                raise ScreenshotUnavailable(url=url, status_code=response.status_code)
-
-            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"
-
-    # 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, custom_browser_connection_url=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 not custom_browser_connection_url:
-            self.browser_connection_url = os.getenv("WEBDRIVER_URL", 'http://browser-chrome:4444/wd/hub').strip('"')
-        else:
-            self.browser_connection_is_custom = True
-            self.browser_connection_url = custom_browser_connection_url
-
-        # 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.chrome.options import Options as ChromeOptions
-        from selenium.common.exceptions import WebDriverException
-        # request_body, request_method unused for now, until some magic in the future happens.
-
-        options = ChromeOptions()
-        if self.proxy:
-            options.proxy = self.proxy
-
-        self.driver = webdriver.Remote(
-            command_executor=self.browser_connection_url,
-            options=options)
-
-        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.chrome.options import Options as ChromeOptions
-
-        self.driver = webdriver.Remote(
-            command_executor=self.command_executor,
-            options=ChromeOptions())
-
-        # 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:
-                logger.debug(f"Content Fetcher > Exception in chrome shutdown/quit {str(e)}")
-
-
-# "html_requests" is listed as the default fetcher in store.py!
-class html_requests(Fetcher):
-    fetcher_description = "Basic fast Plaintext/HTTP Client"
-
-    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
-        super().__init__()
-        self.proxy_override = proxy_override
-        # browser_connection_url is none because its always 'launched locally'
-
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
-
-        # Make requests use a more modern looking user-agent
-        if not {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None):
-            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
-
-        # https://requests.readthedocs.io/en/latest/user/advanced/#socks
-        # Should also work with `socks5://user:pass@host:port` type syntax.
-
-        if self.proxy_override:
-            proxies = {'http': self.proxy_override, 'https': self.proxy_override, 'ftp': self.proxy_override}
-        else:
-            if self.system_http_proxy:
-                proxies['http'] = self.system_http_proxy
-            if self.system_https_proxy:
-                proxies['https'] = self.system_https_proxy
-
-        r = requests.request(method=request_method,
-                             data=request_body,
-                             url=url,
-                             headers=request_headers,
-                             timeout=timeout,
-                             proxies=proxies,
-                             verify=False)
-
-        # If the response did not tell us what encoding format to expect, Then use chardet to override what `requests` thinks.
-        # For example - some sites don't tell us it's utf-8, but return utf-8 content
-        # This seems to not occur when using webdriver/selenium, it seems to detect the text encoding more reliably.
-        # https://github.com/psf/requests/issues/1604 good info about requests encoding detection
-        if not is_binary:
-            # Don't run this for PDF (and requests identified as binary) takes a _long_ time
-            if not r.headers.get('content-type') or not 'charset=' in r.headers.get('content-type'):
-                encoding = chardet.detect(r.content)['encoding']
-                if encoding:
-                    r.encoding = encoding
-
-        if not r.content or not len(r.content):
-            raise EmptyReply(url=url, status_code=r.status_code)
-
-        # @todo test this
-        # @todo maybe you really want to test zero-byte return pages?
-        if r.status_code != 200 and not ignore_status_codes:
-            # maybe check with content works?
-            raise Non200ErrorCodeReceived(url=url, status_code=r.status_code, page_html=r.text)
-
-        self.status_code = r.status_code
-        if is_binary:
-            # Binary files just return their checksum until we add something smarter
-            self.content = hashlib.md5(r.content).hexdigest()
-        else:
-            self.content = r.text
-
-        self.headers = r.headers
-        self.raw_content = r.content
-
-
-# Decide which is the 'real' HTML webdriver, this is more a system wide config
-# rather than site-specific.
-use_playwright_as_chrome_fetcher = os.getenv('PLAYWRIGHT_DRIVER_URL', False)
-if use_playwright_as_chrome_fetcher:
-    html_webdriver = base_html_playwright
-else:
-    html_webdriver = base_html_webdriver

changedetectionio/content_fetchers/__init__.py

@@ -0,0 +1,43 @@
+import sys
+from distutils.util import strtobool
+from loguru import logger
+from changedetectionio.content_fetchers.exceptions import BrowserStepsStepException
+import os
+
+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'
+
+# available_fetchers() will scan this implementation looking for anything starting with html_
+# this information is used in the form selections
+from changedetectionio.content_fetchers.requests import fetcher as html_requests
+
+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
+
+
+# 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:
+    # @note - For now, browser steps always uses playwright
+    if not strtobool(os.getenv('FAST_PUPPETEER_CHROME_FETCHER', 'False')):
+        logger.debug('Using Playwright library as fetcher')
+        from .playwright import fetcher as html_webdriver
+    else:
+        logger.debug('Using direct Python Puppeteer library as fetcher')
+        from .puppeteer import fetcher as html_webdriver
+
+else:
+    logger.debug("Falling back to selenium as fetcher")
+    from .webdriver_selenium import fetcher as html_webdriver
+

changedetectionio/content_fetchers/base.py

@@ -0,0 +1,171 @@
+import os
+from abc import abstractmethod
+from loguru import logger
+
+from changedetectionio.content_fetchers import BrowserStepsStepException
+
+
+def manage_user_agent(headers, current_ua=''):
+    """
+    Basic setting of user-agent
+
+    NOTE!!!!!! The service that does the actual Chrome fetching should handle any anti-robot techniques
+    THERE ARE MANY WAYS THAT IT CAN BE DETECTED AS A ROBOT!!
+    This does not take care of
+    - Scraping of 'navigator' (platform, productSub, vendor, oscpu etc etc) browser object (navigator.appVersion) etc
+    - TCP/IP fingerprint JA3 etc
+    - Graphic rendering fingerprinting
+    - Your IP being obviously in a pool of bad actors
+    - Too many requests
+    - Scraping of SCH-UA browser replies (thanks google!!)
+    - Scraping of ServiceWorker, new window calls etc
+
+    See https://filipvitas.medium.com/how-to-set-user-agent-header-with-puppeteer-js-and-not-fail-28c7a02165da
+    Puppeteer requests https://github.com/dgtlmoon/pyppeteerstealth
+
+    :param page:
+    :param headers:
+    :return:
+    """
+    # Ask it what the user agent is, if its obviously ChromeHeadless, switch it to the default
+    ua_in_custom_headers = next((v for k, v in headers.items() if k.lower() == "user-agent"), None)
+    if ua_in_custom_headers:
+        return ua_in_custom_headers
+
+    if not ua_in_custom_headers and current_ua:
+        current_ua = current_ua.replace('HeadlessChrome', 'Chrome')
+        return current_ua
+
+    return None
+
+
+class Fetcher():
+    browser_connection_is_custom = None
+    browser_connection_url = None
+    browser_steps = None
+    browser_steps_screenshot_path = None
+    content = None
+    error = None
+    fetcher_description = "No description"
+    headers = {}
+    instock_data = None
+    instock_data_js = ""
+    status_code = None
+    webdriver_js_execute_code = None
+    xpath_data = None
+    xpath_element_js = ""
+
+    # Will be needed in the future by the VisualSelector, always get this where possible.
+    screenshot = False
+    system_http_proxy = os.getenv('HTTP_PROXY')
+    system_https_proxy = os.getenv('HTTPS_PROXY')
+
+    # Time ONTOP of the system defined env minimum time
+    render_extract_delay = 0
+
+    def __init__(self):
+        from pkg_resources import resource_string
+        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
+        self.xpath_element_js = resource_string(__name__, "res/xpath_element_scraper.js").decode('utf-8')
+        self.instock_data_js = resource_string(__name__, "res/stock-not-in-stock.js").decode('utf-8')
+
+    @abstractmethod
+    def get_error(self):
+        return self.error
+
+    @abstractmethod
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None,
+            is_binary=False):
+        # Should set self.error, self.status_code and self.content
+        pass
+
+    @abstractmethod
+    def quit(self):
+        return
+
+    @abstractmethod
+    def get_last_status_code(self):
+        return self.status_code
+
+    @abstractmethod
+    def screenshot_step(self, step_n):
+        return None
+
+    @abstractmethod
+    # Return true/false if this checker is ready to run, in the case it needs todo some special config check etc
+    def is_ready(self):
+        return True
+
+    def get_all_headers(self):
+        """
+        Get all headers but ensure all keys are lowercase
+        :return:
+        """
+        return {k.lower(): v for k, v in self.headers.items()}
+
+    def browser_steps_get_valid_steps(self):
+        if self.browser_steps is not None and len(self.browser_steps):
+            valid_steps = filter(
+                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+                self.browser_steps)
+
+            return valid_steps
+
+        return None
+
+    def iterate_browser_steps(self):
+        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+        from playwright._impl._errors import TimeoutError, Error
+        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 = self.browser_steps_get_valid_steps()
+
+            for step in valid_steps:
+                step_n += 1
+                logger.debug(f">> Iterating check - browser Step n {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 (Error, TimeoutError) as e:
+                    logger.debug(str(e))
+                    # Stop processing here
+                    raise BrowserStepsStepException(step_n=step_n, original_e=e)
+
+    # 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:
+                if os.path.isfile(f):
+                    os.unlink(f)
+
+    def save_step_html(self, param):
+        pass

changedetectionio/content_fetchers/exceptions/__init__.py

@@ -0,0 +1,97 @@
+from loguru import logger
+
+
+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 BrowserConnectError(Exception):
+    msg = ''
+    def __init__(self, msg):
+        self.msg = msg
+        logger.error(f"Browser connection error {msg}")
+        return
+
+class BrowserFetchTimedOut(Exception):
+    msg = ''
+    def __init__(self, msg):
+        self.msg = msg
+        logger.error(f"Browser processing took too long - {msg}")
+        return
+
+class BrowserStepsStepException(Exception):
+    def __init__(self, step_n, original_e):
+        self.step_n = step_n
+        self.original_e = original_e
+        logger.debug(f"Browser Steps exception at step {self.step_n} {str(original_e)}")
+        return
+
+
+# @todo - make base Exception class that announces via logger()
+class PageUnloadable(Exception):
+    def __init__(self, status_code=None, 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 BrowserStepsInUnsupportedFetcher(Exception):
+    def __init__(self, url):
+        self.url = url
+        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, has_filters=False, html_content=''):
+        # 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.has_filters = has_filters
+        self.html_content = html_content
+        return

changedetectionio/content_fetchers/playwright.py

@@ -0,0 +1,208 @@
+import json
+import os
+from urllib.parse import urlparse
+
+from loguru import logger
+
+from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
+from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, ScreenshotUnavailable
+
+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, custom_browser_connection_url=None):
+        super().__init__()
+
+        self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
+
+        if custom_browser_connection_url:
+            self.browser_connection_is_custom = True
+            self.browser_connection_url = custom_browser_connection_url
+        else:
+            # Fallback to fetching from system
+            # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+            self.browser_connection_url = 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
+            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=int(os.getenv("SCREENSHOT_QUALITY", 72)))
+
+        if self.browser_steps_screenshot_path is not None:
+            destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.jpeg'.format(step_n))
+            logger.debug(f"Saving step screenshot to {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))
+        logger.debug(f"Saving step HTML to {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._errors
+        from changedetectionio.content_fetchers import visualselector_xpath_selectors
+        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.browser_connection_url, timeout=60000)
+
+            # SOCKS5 with authentication is not supported (yet)
+            # https://github.com/microsoft/playwright/issues/10567
+
+            # Set user agent to prevent Cloudflare from blocking the browser
+            # Use the default one configured in the App.py model that's passed from fetch_site_status.py
+            context = browser.new_context(
+                accept_downloads=False,  # Should never be needed
+                bypass_csp=True,  # This is needed to enable JavaScript execution on GitHub and others
+                extra_http_headers=request_headers,
+                ignore_https_errors=True,
+                proxy=self.proxy,
+                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'), # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
+                user_agent=manage_user_agent(headers=request_headers),
+            )
+
+            self.page = context.new_page()
+
+            # Listen for all console events and handle errors
+            self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
+
+            # Re-use as much code from browser steps as possible so its the same
+            from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+            browsersteps_interface = steppable_browser_interface()
+            browsersteps_interface.page = self.page
+
+            response = browsersteps_interface.action_goto_url(value=url)
+            self.headers = response.all_headers()
+
+            if response is None:
+                context.close()
+                browser.close()
+                logger.debug("Content Fetcher > Response object was none")
+                raise EmptyReply(url=url, status_code=None)
+
+            try:
+                if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
+                    browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
+            except playwright._impl._errors.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:
+                logger.debug(f"Content Fetcher > Other exception when executing custom JS code {str(e)}")
+                context.close()
+                browser.close()
+                raise PageUnloadable(url=url, status_code=None, message=str(e))
+
+            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+            self.page.wait_for_timeout(extra_wait * 1000)
+
+            try:
+                self.status_code = response.status
+            except Exception as e:
+                # https://github.com/dgtlmoon/changedetection.io/discussions/2122#discussioncomment-8241962
+                logger.critical(f"Response from the browser/Playwright did not have a status_code! Response follows.")
+                logger.critical(response)
+                context.close()
+                browser.close()
+                raise PageUnloadable(url=url, status_code=None, message=str(e))
+
+            if self.status_code != 200 and not ignore_status_codes:
+                screenshot = self.page.screenshot(type='jpeg', full_page=True,
+                                                  quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
+
+                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
+
+            if len(self.page.content().strip()) == 0:
+                context.close()
+                browser.close()
+                logger.debug("Content Fetcher > Content was empty")
+                raise EmptyReply(url=url, status_code=response.status)
+
+            # Run Browser Steps here
+            if self.browser_steps_get_valid_steps():
+                self.iterate_browser_steps()
+
+            self.page.wait_for_timeout(extra_wait * 1000)
+
+            # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
+            if current_include_filters is not None:
+                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 + "}")
+
+            self.content = self.page.content()
+            # Bug 3 in Playwright screenshot handling
+            # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
+            # JPEG is better here because the screenshots can be very very large
+
+            # 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 - this always base64 and needs decoding! horrible! huge CPU usage
+                self.screenshot = self.page.screenshot(type='jpeg',
+                                                       full_page=True,
+                                                       quality=int(os.getenv("SCREENSHOT_QUALITY", 72)),
+                                                       )
+            except Exception as e:
+                # It's likely the screenshot was too long/big and something crashed
+                raise ScreenshotUnavailable(url=url, status_code=self.status_code)
+            finally:
+                context.close()
+                browser.close()

changedetectionio/content_fetchers/puppeteer.py

@@ -0,0 +1,247 @@
+import asyncio
+import json
+import os
+import websockets.exceptions
+from urllib.parse import urlparse
+
+from loguru import logger
+
+from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
+from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, BrowserFetchTimedOut, BrowserConnectError
+
+
+class fetcher(Fetcher):
+    fetcher_description = "Puppeteer/direct {}/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 = ''
+
+    proxy = None
+
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
+        super().__init__()
+
+        if custom_browser_connection_url:
+            self.browser_connection_is_custom = True
+            self.browser_connection_url = custom_browser_connection_url
+        else:
+            # Fallback to fetching from system
+            # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+            self.browser_connection_url = os.getenv("PLAYWRIGHT_DRIVER_URL", 'ws://playwright-chrome:3000').strip('"')
+
+        # allow per-watch proxy selection override
+        # @todo check global too?
+        if proxy_override:
+            # Playwright needs separate username and password values
+            parsed = urlparse(proxy_override)
+            if parsed:
+                self.proxy = {'username': parsed.username, 'password': parsed.password}
+                # Add the proxy server chrome start option, the username and password never gets added here
+                # (It always goes in via await self.page.authenticate(self.proxy))
+
+                # @todo filter some injection attack?
+                # check scheme when no scheme
+                proxy_url = parsed.scheme + "://" if parsed.scheme else 'http://'
+                r = "?" if not '?' in self.browser_connection_url else '&'
+                port = ":"+str(parsed.port) if parsed.port else ''
+                q = "?"+parsed.query if parsed.query else ''
+                proxy_url += f"{parsed.hostname}{port}{parsed.path}{q}"
+                self.browser_connection_url += f"{r}--proxy-server={proxy_url}"
+
+    # 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))
+    #         logger.debug(f"Saving step screenshot to {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))
+    #     logger.debug(f"Saving step HTML to {destination}")
+    #     with open(destination, 'w') as f:
+    #         f.write(content)
+
+    async def fetch_page(self,
+                         url,
+                         timeout,
+                         request_headers,
+                         request_body,
+                         request_method,
+                         ignore_status_codes,
+                         current_include_filters,
+                         is_binary
+                         ):
+
+        from changedetectionio.content_fetchers import visualselector_xpath_selectors
+        self.delete_browser_steps_screenshots()
+        extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+
+        from pyppeteer import Pyppeteer
+        pyppeteer_instance = Pyppeteer()
+
+        # Connect directly using the specified browser_ws_endpoint
+        # @todo timeout
+        try:
+            browser = await pyppeteer_instance.connect(browserWSEndpoint=self.browser_connection_url,
+                                                       ignoreHTTPSErrors=True
+                                                       )
+        except websockets.exceptions.InvalidStatusCode as e:
+            raise BrowserConnectError(msg=f"Error while trying to connect the browser, Code {e.status_code} (check your access)")
+        except websockets.exceptions.InvalidURI:
+            raise BrowserConnectError(msg=f"Error connecting to the browser, check your browser connection address (should be ws:// or wss://")
+        except Exception as e:
+            raise BrowserConnectError(msg=f"Error connecting to the browser {str(e)}")
+        else:
+            self.page = await browser.newPage()
+
+        await self.page.setUserAgent(manage_user_agent(headers=request_headers, current_ua=await self.page.evaluate('navigator.userAgent')))
+
+        await self.page.setBypassCSP(True)
+        if request_headers:
+            await self.page.setExtraHTTPHeaders(request_headers)
+
+        # SOCKS5 with authentication is not supported (yet)
+        # https://github.com/microsoft/playwright/issues/10567
+        self.page.setDefaultNavigationTimeout(0)
+        await self.page.setCacheEnabled(True)
+        if self.proxy and self.proxy.get('username'):
+            # Setting Proxy-Authentication header is deprecated, and doing so can trigger header change errors from Puppeteer
+            # https://github.com/puppeteer/puppeteer/issues/676 ?
+            # https://help.brightdata.com/hc/en-us/articles/12632549957649-Proxy-Manager-How-to-Guides#h_01HAKWR4Q0AFS8RZTNYWRDFJC2
+            # https://cri.dev/posts/2020-03-30-How-to-solve-Puppeteer-Chrome-Error-ERR_INVALID_ARGUMENT/
+            await self.page.authenticate(self.proxy)
+
+        # Re-use as much code from browser steps as possible so its the same
+        # from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+
+        # not yet used here, we fallback to playwright when browsersteps is required
+        #            browsersteps_interface = steppable_browser_interface()
+        #            browsersteps_interface.page = self.page
+
+        response = await self.page.goto(url, waitUntil="load")
+
+
+        if response is None:
+            await self.page.close()
+            await browser.close()
+            logger.warning("Content Fetcher > Response object was none")
+            raise EmptyReply(url=url, status_code=None)
+
+        self.headers = response.headers
+
+        try:
+            if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
+                await self.page.evaluate(self.webdriver_js_execute_code)
+        except Exception as e:
+            logger.warning("Got exception when running evaluate on custom JS code")
+            logger.error(str(e))
+            await self.page.close()
+            await browser.close()
+            # This can be ok, we will try to grab what we could retrieve
+            raise PageUnloadable(url=url, status_code=None, message=str(e))
+
+        try:
+            self.status_code = response.status
+        except Exception as e:
+            # https://github.com/dgtlmoon/changedetection.io/discussions/2122#discussioncomment-8241962
+            logger.critical(f"Response from the browser/Playwright did not have a status_code! Response follows.")
+            logger.critical(response)
+            await self.page.close()
+            await browser.close()
+            raise PageUnloadable(url=url, status_code=None, message=str(e))
+
+        if self.status_code != 200 and not ignore_status_codes:
+            screenshot = await self.page.screenshot(type_='jpeg',
+                                                    fullPage=True,
+                                                    quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
+
+            raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
+        content = await self.page.content
+        if len(content.strip()) == 0:
+            await self.page.close()
+            await browser.close()
+            logger.error("Content Fetcher > Content was empty")
+            raise EmptyReply(url=url, status_code=response.status)
+
+        # Run Browser Steps here
+        # @todo not yet supported, we switch to playwright in this case
+        #            if self.browser_steps_get_valid_steps():
+        #                self.iterate_browser_steps()
+
+        await asyncio.sleep(1 + extra_wait)
+
+        # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
+        # Setup the xPath/VisualSelector scraper
+        if current_include_filters is not None:
+            js = json.dumps(current_include_filters)
+            await self.page.evaluate(f"var include_filters={js}")
+        else:
+            await self.page.evaluate(f"var include_filters=''")
+
+        self.xpath_data = await self.page.evaluate(
+            "async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
+        self.instock_data = await self.page.evaluate("async () => {" + self.instock_data_js + "}")
+
+        self.content = await self.page.content
+        # Bug 3 in Playwright screenshot handling
+        # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
+        # JPEG is better here because the screenshots can be very very large
+
+        # 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:
+            self.screenshot = await self.page.screenshot(type_='jpeg',
+                                                         fullPage=True,
+                                                         quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
+        except Exception as e:
+            logger.error("Error fetching screenshot")
+            # // May fail on very large pages with 'WARNING: tile memory limits exceeded, some content may not draw'
+            # // @ todo after text extract, we can place some overlay text with red background to say 'croppped'
+            logger.error('ERROR: content-fetcher page was maybe too large for a screenshot, reverting to viewport only screenshot')
+            try:
+                self.screenshot = await self.page.screenshot(type_='jpeg',
+                                                             fullPage=False,
+                                                             quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
+            except Exception as e:
+                logger.error('ERROR: Failed to get viewport-only reduced screenshot :(')
+                pass
+        finally:
+            # It's good to log here in the case that the browser crashes on shutting down but we still get the data we need
+            logger.success(f"Fetching '{url}' complete, closing page")
+            await self.page.close()
+            logger.success(f"Fetching '{url}' complete, closing browser")
+            await browser.close()
+        logger.success(f"Fetching '{url}' complete, exiting puppeteer fetch.")
+
+    async def main(self, **kwargs):
+        await self.fetch_page(**kwargs)
+
+    def run(self, url, timeout, request_headers, request_body, request_method, ignore_status_codes=False,
+            current_include_filters=None, is_binary=False):
+
+        #@todo make update_worker async which could run any of these content_fetchers within memory and time constraints
+        max_time = os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180)
+
+        # This will work in 3.10 but not >= 3.11 because 3.11 wants tasks only
+        try:
+            asyncio.run(asyncio.wait_for(self.main(
+                url=url,
+                timeout=timeout,
+                request_headers=request_headers,
+                request_body=request_body,
+                request_method=request_method,
+                ignore_status_codes=ignore_status_codes,
+                current_include_filters=current_include_filters,
+                is_binary=is_binary
+            ), timeout=max_time))
+        except asyncio.TimeoutError:
+            raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))
+

changedetectionio/content_fetchers/requests.py

@@ -0,0 +1,91 @@
+import hashlib
+import os
+
+import chardet
+import requests
+
+from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
+from changedetectionio.content_fetchers.base import Fetcher
+
+
+# "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, custom_browser_connection_url=None):
+        super().__init__()
+        self.proxy_override = proxy_override
+        # browser_connection_url is none because its always 'launched locally'
+
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None,
+            is_binary=False):
+
+        if self.browser_steps_get_valid_steps():
+            raise BrowserStepsInUnsupportedFetcher(url=url)
+
+        # Make requests use a more modern looking user-agent
+        if not {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None):
+            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
+
+        # https://requests.readthedocs.io/en/latest/user/advanced/#socks
+        # Should also work with `socks5://user:pass@host:port` type syntax.
+
+        if self.proxy_override:
+            proxies = {'http': self.proxy_override, 'https': self.proxy_override, 'ftp': self.proxy_override}
+        else:
+            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
+
+        self.headers = r.headers
+
+        if not r.content or not len(r.content):
+            raise EmptyReply(url=url, status_code=r.status_code)
+
+        # @todo test this
+        # @todo maybe you really want to test zero-byte return pages?
+        if r.status_code != 200 and not ignore_status_codes:
+            # maybe check with content works?
+            raise Non200ErrorCodeReceived(url=url, status_code=r.status_code, page_html=r.text)
+
+        self.status_code = r.status_code
+        if is_binary:
+            # Binary files just return their checksum until we add something smarter
+            self.content = hashlib.md5(r.content).hexdigest()
+        else:
+            self.content = r.text
+
+
+        self.raw_content = r.content

changedetectionio/content_fetchers/res/puppeteer_fetch.js

@@ -146,7 +146,7 @@ module.exports = async ({page, context}) => {
     var xpath_data;
     var instock_data;
     try {
-        // Not sure the best way here, in the future this should be a new package added to npm then run in browserless
+        // Not sure the best way here, in the future this should be a new package added to npm then run in evaluatedCode
         // (Once the old playwright is removed)
         xpath_data = await page.evaluate((include_filters) => {%xpath_scrape_code%}, include_filters);
         instock_data = await page.evaluate(() => {%instock_scrape_code%});

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

@@ -10,12 +10,15 @@ function isItemInStock() {
     const outOfStockTexts = [
         ' أخبرني عندما يتوفر',
         '0 in stock',
+        'actuellement indisponible',
         'agotado',
         'article épuisé',
         'artikel zurzeit vergriffen',
         'as soon as stock is available',
         'ausverkauft', // sold out
         'available for back order',
+        'awaiting stock',
+        'back in stock soon',
         'back-order or out of stock',
         'backordered',
         'benachrichtigt mich', // notify me
@@ -24,6 +27,7 @@ function isItemInStock() {
         'coming soon',
         'currently have any tickets for this',
         'currently unavailable',
+        'dieser artikel ist bald wieder verfügbar',
         'dostępne wkrótce',
         'en rupture de stock',
         'ist derzeit nicht auf lager',
@@ -36,6 +40,7 @@ function isItemInStock() {
         'nicht zur verfügung',
         'niet beschikbaar',
         'niet leverbaar',
+        'niet op voorraad',
         'no disponible temporalmente',
         'no longer in stock',
         'no tickets available',
@@ -47,23 +52,32 @@ function isItemInStock() {
         'não estamos a aceitar encomendas',
         'out of stock',
         'out-of-stock',
+        'prodotto esaurito',
         'produkt niedostępny',
         'sold out',
         'sold-out',
         'temporarily out of stock',
         'temporarily unavailable',
+        'there were no search results for',
+        'this item is currently unavailable',
         'tickets unavailable',
         'tijdelijk uitverkocht',
         'unavailable tickets',
+        'vorbestellung ist bald möglich',
+        'we couldn\'t find any products that match',
         'we do not currently have an estimate of when this product will be back in stock.',
         'we don\'t know when or if this item will be back in stock.',
+        'we were not able to find a match',
         'zur zeit nicht an lager',
         '品切れ',
+        '已售',
         '已售完',
         '품절'
     ];
 
+
     const vh = Math.max(document.documentElement.clientHeight || 0, window.innerHeight || 0);
+
     function getElementBaseText(element) {
         // .textContent can include text from children which may give the wrong results
         // scan only immediate TEXT_NODEs, which will be a child of the element
@@ -74,29 +88,69 @@ function isItemInStock() {
         return text.toLowerCase().trim();
     }
 
-    const negateOutOfStockRegex = new RegExp('([0-9] in stock|add to cart)', 'ig');
+    const negateOutOfStockRegex = new RegExp('^([0-9] in stock|add to cart|in stock)', 'ig');
 
     // The out-of-stock or in-stock-text is generally always above-the-fold
     // and often below-the-fold is a list of related products that may or may not contain trigger text
     // so it's good to filter to just the 'above the fold' elements
     // and it should be atleast 100px from the top to ignore items in the toolbar, sometimes menu items like "Coming soon" exist
-    const elementsToScan = Array.from(document.getElementsByTagName('*')).filter(element => element.getBoundingClientRect().top + window.scrollY <= vh && element.getBoundingClientRect().top + window.scrollY >= 100);
+
+
+// @todo - if it's SVG or IMG, go into image diff mode
+// %ELEMENTS% replaced at injection time because different interfaces use it with different settings
+
+    console.log("Scanning %ELEMENTS%");
+
+    function collectVisibleElements(parent, visibleElements) {
+        if (!parent) return; // Base case: if parent is null or undefined, return
+
+        // Add the parent itself to the visible elements array if it's of the specified types
+        visibleElements.push(parent);
+
+        // Iterate over the parent's children
+        const children = parent.children;
+        for (let i = 0; i < children.length; i++) {
+            const child = children[i];
+            if (
+                child.nodeType === Node.ELEMENT_NODE &&
+                window.getComputedStyle(child).display !== 'none' &&
+                window.getComputedStyle(child).visibility !== 'hidden' &&
+                child.offsetWidth >= 0 &&
+                child.offsetHeight >= 0 &&
+                window.getComputedStyle(child).contentVisibility !== 'hidden'
+            ) {
+                // If the child is an element and is visible, recursively collect visible elements
+                collectVisibleElements(child, visibleElements);
+            }
+        }
+    }
+
+    const elementsToScan = [];
+    collectVisibleElements(document.body, elementsToScan);
 
     var elementText = "";
 
     // REGEXS THAT REALLY MEAN IT'S IN STOCK
     for (let i = elementsToScan.length - 1; i >= 0; i--) {
         const element = elementsToScan[i];
+
+        // outside the 'fold' or some weird text in the heading area
+        // .getBoundingClientRect() was causing a crash in chrome 119, can only be run on contentVisibility != hidden
+        if (element.getBoundingClientRect().top + window.scrollY >= vh || element.getBoundingClientRect().top + window.scrollY <= 100) {
+            continue
+        }
+
         elementText = "";
         if (element.tagName.toLowerCase() === "input") {
-            elementText = element.value.toLowerCase();
+            elementText = element.value.toLowerCase().trim();
         } else {
             elementText = getElementBaseText(element);
         }
 
         if (elementText.length) {
             // try which ones could mean its in stock
-            if (negateOutOfStockRegex.test(elementText)) {
+            if (negateOutOfStockRegex.test(elementText) && !elementText.includes('(0 products)')) {
+                console.log(`Negating/overriding 'Out of Stock' back to "Possibly in stock" found "${elementText}"`)
                 return 'Possibly in stock';
             }
         }
@@ -105,28 +159,34 @@ function isItemInStock() {
     // OTHER STUFF THAT COULD BE THAT IT'S OUT OF STOCK
     for (let i = elementsToScan.length - 1; i >= 0; i--) {
         const element = elementsToScan[i];
-        if (element.offsetWidth > 0 || element.offsetHeight > 0 || element.getClientRects().length > 0) {
+        // outside the 'fold' or some weird text in the heading area
-            elementText = "";
+        // .getBoundingClientRect() was causing a crash in chrome 119, can only be run on contentVisibility != hidden
-            if (element.tagName.toLowerCase() === "input") {
+        if (element.getBoundingClientRect().top + window.scrollY >= vh + 150 || element.getBoundingClientRect().top + window.scrollY <= 100) {
-                elementText = element.value.toLowerCase();
+            continue
-            } else {
+        }
-                elementText = getElementBaseText(element);
+        elementText = "";
-            }
+        if (element.tagName.toLowerCase() === "input") {
+            elementText = element.value.toLowerCase().trim();
+        } else {
+            elementText = getElementBaseText(element);
+        }
 
-            if (elementText.length) {
+        if (elementText.length) {
-                // and these mean its out of stock
+            // and these mean its out of stock
-                for (const outOfStockText of outOfStockTexts) {
+            for (const outOfStockText of outOfStockTexts) {
-                    if (elementText.includes(outOfStockText)) {
+                if (elementText.includes(outOfStockText)) {
-                        return outOfStockText; // item is out of stock
+                    console.log(`Selected 'Out of Stock' - found text "${outOfStockText}" - "${elementText}"`)
-                    }
+                    return outOfStockText; // item is out of stock
                 }
             }
         }
     }
 
+    console.log(`Returning 'Possibly in stock' - cant' find any useful matching text`)
     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().trim()
 
+

changedetectionio/content_fetchers/res/xpath_element_scraper.js

@@ -16,24 +16,23 @@ try {
 }
 
 
-
 // Include the getXpath script directly, easier than fetching
 function getxpath(e) {
-        var n = e;
+    var n = e;
-        if (n && n.id) return '//*[@id="' + n.id + '"]';
+    if (n && n.id) return '//*[@id="' + n.id + '"]';
-        for (var o = []; n && Node.ELEMENT_NODE === n.nodeType;) {
+    for (var o = []; n && Node.ELEMENT_NODE === n.nodeType;) {
-            for (var i = 0, r = !1, d = n.previousSibling; d;) d.nodeType !== Node.DOCUMENT_TYPE_NODE && d.nodeName === n.nodeName && i++, d = d.previousSibling;
+        for (var i = 0, r = !1, d = n.previousSibling; d;) d.nodeType !== Node.DOCUMENT_TYPE_NODE && d.nodeName === n.nodeName && i++, d = d.previousSibling;
-            for (d = n.nextSibling; d;) {
+        for (d = n.nextSibling; d;) {
-                if (d.nodeName === n.nodeName) {
+            if (d.nodeName === n.nodeName) {
-                    r = !0;
+                r = !0;
-                    break
+                break
-                }
-                d = d.nextSibling
             }
-            o.push((n.prefix ? n.prefix + ":" : "") + n.localName + (i || r ? "[" + (i + 1) + "]" : "")), n = n.parentNode
+            d = d.nextSibling
         }
-        return o.length ? "/" + o.reverse().join("/") : ""
+        o.push((n.prefix ? n.prefix + ":" : "") + n.localName + (i || r ? "[" + (i + 1) + "]" : "")), n = n.parentNode
     }
+    return o.length ? "/" + o.reverse().join("/") : ""
+}
 
 const findUpTag = (el) => {
     let r = el
@@ -59,14 +58,14 @@ const findUpTag = (el) => {
 
     // Strategy 2: Keep going up until we hit an ID tag, imagine it's like  #list-widget div h4
     while (r.parentNode) {
-        if (depth == 5) {
+        if (depth === 5) {
             break;
         }
         if ('' !== r.id) {
             chained_css.unshift("#" + CSS.escape(r.id));
             final_selector = chained_css.join(' > ');
             // Be sure theres only one, some sites have multiples of the same ID tag :-(
-            if (window.document.querySelectorAll(final_selector).length == 1) {
+            if (window.document.querySelectorAll(final_selector).length === 1) {
                 return final_selector;
             }
             return null;
@@ -82,30 +81,60 @@ const findUpTag = (el) => {
 
 // @todo - if it's SVG or IMG, go into image diff mode
 // %ELEMENTS% replaced at injection time because different interfaces use it with different settings
-var elements = window.document.querySelectorAll("%ELEMENTS%");
+
 var size_pos = [];
 // after page fetch, inject this JS
 // build a map of all elements and their positions (maybe that only include text?)
 var bbox;
-for (var i = 0; i < elements.length; i++) {
+console.log("Scanning %ELEMENTS%");
-    bbox = elements[i].getBoundingClientRect();
 
-    // Exclude items that are not interactable or visible
+function collectVisibleElements(parent, visibleElements) {
-    if(elements[i].style.opacity === "0") {
+    if (!parent) return; // Base case: if parent is null or undefined, return
-        continue
+
+
+    // Add the parent itself to the visible elements array if it's of the specified types
+    const tagName = parent.tagName.toLowerCase();
+    if ("%ELEMENTS%".split(',').includes(tagName)) {
+        visibleElements.push(parent);
     }
-    if(elements[i].style.display === "none" || elements[i].style.pointerEvents === "none" ) {
+
-        continue
+    // Iterate over the parent's children
+    const children = parent.children;
+    for (let i = 0; i < children.length; i++) {
+        const child = children[i];
+        if (
+            child.nodeType === Node.ELEMENT_NODE &&
+            window.getComputedStyle(child).display !== 'none' &&
+            window.getComputedStyle(child).visibility !== 'hidden' &&
+            child.offsetWidth >= 0 &&
+            child.offsetHeight >= 0 &&
+            window.getComputedStyle(child).contentVisibility !== 'hidden'
+        ) {
+            // If the child is an element and is visible, recursively collect visible elements
+            collectVisibleElements(child, visibleElements);
+        }
     }
+}
+
+// Create an array to hold the visible elements
+const visibleElementsArray = [];
+
+// Call collectVisibleElements with the starting parent element
+collectVisibleElements(document.body, visibleElementsArray);
+
+
+visibleElementsArray.forEach(function (element) {
+
+    bbox = element.getBoundingClientRect();
 
     // Skip really small ones, and where width or height ==0
-    if (bbox['width'] * bbox['height'] < 100) {
+    if (bbox['width'] * bbox['height'] < 10) {
-        continue;
+        return
     }
 
     // Don't include elements that are offset from canvas
-    if (bbox['top']+scroll_y < 0 || bbox['left'] < 0) {
+    if (bbox['top'] + scroll_y < 0 || bbox['left'] < 0) {
-        continue;
+        return
     }
 
     // @todo the getXpath kind of sucks, it doesnt know when there is for example just one ID sometimes
@@ -114,46 +143,41 @@ for (var i = 0; i < elements.length; i++) {
 
     // 1st primitive - if it has class, try joining it all and select, if theres only one.. well thats us.
     xpath_result = false;
-
     try {
-        var d = findUpTag(elements[i]);
+        var d = findUpTag(element);
         if (d) {
             xpath_result = d;
         }
     } catch (e) {
         console.log(e);
     }
-
     // You could swap it and default to getXpath and then try the smarter one
     // default back to the less intelligent one
     if (!xpath_result) {
         try {
             // I've seen on FB and eBay that this doesnt work
             // ReferenceError: getXPath is not defined at eval (eval at evaluate (:152:29), <anonymous>:67:20) at UtilityScript.evaluate (<anonymous>:159:18) at UtilityScript.<anonymous> (<anonymous>:1:44)
-            xpath_result = getxpath(elements[i]);
+            xpath_result = getxpath(element);
         } catch (e) {
             console.log(e);
-            continue;
+            return
         }
     }
 
-    if (window.getComputedStyle(elements[i]).visibility === "hidden") {
-        continue;
-    }
 
-    // @todo Possible to ONLY list where it's clickable to save JSON xfer size
     size_pos.push({
         xpath: xpath_result,
         width: Math.round(bbox['width']),
         height: Math.round(bbox['height']),
         left: Math.floor(bbox['left']),
-        top: Math.floor(bbox['top'])+scroll_y,
+        top: Math.floor(bbox['top']) + scroll_y,
-        tagName: (elements[i].tagName) ? elements[i].tagName.toLowerCase() : '',
+        tagName: (element.tagName) ? element.tagName.toLowerCase() : '',
-        tagtype: (elements[i].tagName == 'INPUT' && elements[i].type) ? elements[i].type.toLowerCase() : '',
+        tagtype: (element.tagName.toLowerCase() === 'input' && element.type) ? element.type.toLowerCase() : '',
-        isClickable: (elements[i].onclick) || window.getComputedStyle(elements[i]).cursor == "pointer"
+        isClickable: window.getComputedStyle(element).cursor == "pointer"
     });
 
-}
+});
+
 
 // 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.
@@ -180,7 +204,7 @@ if (include_filters.length) {
             }
         } catch (e) {
             // Maybe catch DOMException and alert?
-            console.log("xpath_element_scraper: Exception selecting element from filter "+f);
+            console.log("xpath_element_scraper: Exception selecting element from filter " + f);
             console.log(e);
         }
 
@@ -211,7 +235,7 @@ if (include_filters.length) {
             }
         }
 
-        if(!q) {
+        if (!q) {
             console.log("xpath_element_scraper: filter element " + f + " was not found");
         }
 
@@ -221,7 +245,7 @@ if (include_filters.length) {
                 width: parseInt(bbox['width']),
                 height: parseInt(bbox['height']),
                 left: parseInt(bbox['left']),
-                top: parseInt(bbox['top'])+scroll_y
+                top: parseInt(bbox['top']) + scroll_y
             });
         }
     }
@@ -229,7 +253,7 @@ 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)
+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/content_fetchers/webdriver_selenium.py

@@ -0,0 +1,119 @@
+import os
+import time
+
+from loguru import logger
+from changedetectionio.content_fetchers.base import Fetcher
+
+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"
+
+    # 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, custom_browser_connection_url=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 not custom_browser_connection_url:
+            self.browser_connection_url = os.getenv("WEBDRIVER_URL", 'http://browser-chrome:4444/wd/hub').strip('"')
+        else:
+            self.browser_connection_is_custom = True
+            self.browser_connection_url = custom_browser_connection_url
+
+        # 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.chrome.options import Options as ChromeOptions
+        from selenium.common.exceptions import WebDriverException
+        # request_body, request_method unused for now, until some magic in the future happens.
+
+        options = ChromeOptions()
+        if self.proxy:
+            options.proxy = self.proxy
+
+        self.driver = webdriver.Remote(
+            command_executor=self.browser_connection_url,
+            options=options)
+
+        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.chrome.options import Options as ChromeOptions
+
+        self.driver = webdriver.Remote(
+            command_executor=self.command_executor,
+            options=ChromeOptions())
+
+        # 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:
+                logger.debug(f"Content Fetcher > Exception in chrome shutdown/quit {str(e)}")

changedetectionio/flask_app.py

@@ -1,26 +1,19 @@
 #!/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
-from loguru import logger
-import sys
 import os
-import pytz
 import queue
 import threading
 import time
-import timeago
+from copy import deepcopy
+from distutils.util import strtobool
+from functools import wraps
+from threading import Event
 
+import flask_login
+import pytz
+import timeago
+from feedgen.feed import FeedGenerator
 from flask import (
     Flask,
     abort,
@@ -33,10 +26,16 @@ from flask import (
     session,
     url_for,
 )
-
+from flask_compress import Compress as FlaskCompress
+from flask_login import current_user
 from flask_paginate import Pagination, get_page_parameter
+from flask_restful import abort, Api
+from flask_cors import CORS
+from flask_wtf import CSRFProtect
+from loguru import logger
 
 from changedetectionio import html_tools, __version__
+from changedetectionio import queuedWatchMetaData
 from changedetectionio.api import api_v1
 
 datastore = None
@@ -55,6 +54,9 @@ app = Flask(__name__,
             static_folder="static",
             template_folder="templates")
 
+# Enable CORS, especially useful for the Chrome extension to operate from anywhere
+CORS(app)
+
 # Super handy for compressing large BrowserSteps responses and others
 FlaskCompress(app)
 
@@ -317,6 +319,9 @@ def changedetection_app(config=None, datastore_o=None):
 
     @app.route("/rss", methods=['GET'])
     def rss():
+        from jinja2 import Environment, BaseLoader
+        jinja2_env = Environment(loader=BaseLoader)
+        now = time.time()
         # Always requires token set
         app_rss_token = datastore.data['settings']['application'].get('rss_access_token')
         rss_url_token = request.args.get('token')
@@ -380,8 +385,12 @@ def changedetection_app(config=None, datastore_o=None):
                                              include_equal=False,
                                              line_feed_sep="<br>")
 
-                fe.content(content="<html><body><h4>{}</h4>{}</body></html>".format(watch_title, html_diff),
+                # @todo Make this configurable and also consider html-colored markup
-                           type='CDATA')
+                # @todo User could decide if <link> goes to the diff page, or to the watch link
+                rss_template = "<html><body>\n<h4><a href=\"{{watch_url}}\">{{watch_title}}</a></h4>\n<p>{{html_diff}}</p>\n</body></html>\n"
+                content = jinja2_env.from_string(rss_template).render(watch_title=watch_title, html_diff=html_diff, watch_url=watch.link)
+
+                fe.content(content=content, type='CDATA')
 
                 fe.guid(guid, permalink=False)
                 dt = datetime.datetime.fromtimestamp(int(watch.newest_history_key))
@@ -390,6 +399,7 @@ def changedetection_app(config=None, datastore_o=None):
 
         response = make_response(fg.rss_str())
         response.headers.set('Content-Type', 'application/rss+xml;charset=utf-8')
+        logger.trace(f"RSS generated in {time.time() - now:.3f}s")
         return response
 
     @app.route("/", methods=['GET'])
@@ -398,17 +408,21 @@ def changedetection_app(config=None, datastore_o=None):
         global datastore
         from changedetectionio import forms
 
-        limit_tag = request.args.get('tag', '').lower().strip()
+        active_tag_req = request.args.get('tag', '').lower().strip()
+        active_tag_uuid = active_tag = None
 
         # Be sure limit_tag is a uuid
-        for uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
+        if active_tag_req:
-            if limit_tag == tag.get('title', '').lower().strip():
+            for uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
-                limit_tag = uuid
+                if active_tag_req == tag.get('title', '').lower().strip() or active_tag_req == uuid:
+                    active_tag = tag
+                    active_tag_uuid = uuid
+                    break
 
 
         # Redirect for the old rss path which used the /?rss=true
         if request.args.get('rss'):
-            return redirect(url_for('rss', tag=limit_tag))
+            return redirect(url_for('rss', tag=active_tag_uuid))
 
         op = request.args.get('op')
         if op:
@@ -419,7 +433,7 @@ def changedetection_app(config=None, datastore_o=None):
                 datastore.data['watching'][uuid].toggle_mute()
 
             datastore.needs_write = True
-            return redirect(url_for('index', tag = limit_tag))
+            return redirect(url_for('index', tag = active_tag_uuid))
 
         # Sort by last_changed and add the uuid which is usually the key..
         sorted_watches = []
@@ -430,7 +444,7 @@ def changedetection_app(config=None, datastore_o=None):
             if with_errors and not watch.get('last_error'):
                 continue
 
-            if limit_tag and not limit_tag in watch['tags']:
+            if active_tag_uuid and not active_tag_uuid in watch['tags']:
                     continue
             if watch.get('last_error'):
                 errored_count += 1
@@ -449,11 +463,12 @@ def changedetection_app(config=None, datastore_o=None):
                                 total=total_count,
                                 per_page=datastore.data['settings']['application'].get('pager_size', 50), css_framework="semantic")
 
-
+        sorted_tags = sorted(datastore.data['settings']['application'].get('tags').items(), key=lambda x: x[1]['title'])
         output = render_template(
             "watch-overview.html",
                                  # Don't link to hosting when we're on the hosting environment
-                                 active_tag=limit_tag,
+                                 active_tag=active_tag,
+                                 active_tag_uuid=active_tag_uuid,
                                  app_rss_token=datastore.data['settings']['application']['rss_access_token'],
                                  datastore=datastore,
                                  errored_count=errored_count,
@@ -468,7 +483,7 @@ def changedetection_app(config=None, datastore_o=None):
                                  sort_attribute=request.args.get('sort') if request.args.get('sort') else request.cookies.get('sort'),
                                  sort_order=request.args.get('order') if request.args.get('order') else request.cookies.get('order'),
                                  system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),
-                                 tags=datastore.data['settings']['application'].get('tags'),
+                                 tags=sorted_tags,
                                  watches=sorted_watches
                                  )
 
@@ -756,7 +771,7 @@ def changedetection_app(config=None, datastore_o=None):
     @app.route("/settings", methods=['GET', "POST"])
     @login_optionally_required
     def settings_page():
-        from changedetectionio import content_fetcher, forms
+        from changedetectionio import forms
 
         default = deepcopy(datastore.data['settings'])
         if datastore.proxy_list is not None:
@@ -1416,6 +1431,13 @@ def changedetection_app(config=None, datastore_o=None):
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
             flash("{} watches queued for rechecking".format(len(uuids)))
 
+        elif (op == 'clear-errors'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid]["last_error"] = False
+            flash(f"{len(uuids)} watches errors cleared")
+
         elif (op == 'clear-history'):
             for uuid in uuids:
                 uuid = uuid.strip()

changedetectionio/forms.py

@@ -27,7 +27,7 @@ from validators.url import url as url_validator
 # 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, html_tools
+from changedetectionio import html_tools, content_fetchers
 
 from changedetectionio.notification import (
     valid_notification_formats,
@@ -167,33 +167,31 @@ class ValidateContentFetcherIsReady(object):
         self.message = message
 
     def __call__(self, form, field):
-        import urllib3.exceptions
-        from changedetectionio import content_fetcher
         return
 
 # AttributeError: module 'changedetectionio.content_fetcher' has no attribute 'extra_browser_unlocked<>ASDF213r123r'
         # Better would be a radiohandler that keeps a reference to each class
-        if field.data is not None and field.data != 'system':
+        # if field.data is not None and field.data != 'system':
-            klass = getattr(content_fetcher, field.data)
+        #     klass = getattr(content_fetcher, field.data)
-            some_object = klass()
+        #     some_object = klass()
-            try:
+        #     try:
-                ready = some_object.is_ready()
+        #         ready = some_object.is_ready()
-
+        #
-            except urllib3.exceptions.MaxRetryError as e:
+        #     except urllib3.exceptions.MaxRetryError as e:
-                driver_url = some_object.command_executor
+        #         driver_url = some_object.command_executor
-                message = field.gettext('Content fetcher \'%s\' did not respond.' % (field.data))
+        #         message = field.gettext('Content fetcher \'%s\' did not respond.' % (field.data))
-                message += '<br>' + field.gettext(
+        #         message += '<br>' + field.gettext(
-                    'Be sure that the selenium/webdriver runner is running and accessible via network from this container/host.')
+        #             '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>' + field.gettext('Did you follow the instructions in the wiki?')
-                message += '<br><br>' + field.gettext('WebDriver Host: %s' % (driver_url))
+        #         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><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)))
+        #         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:
+        #     except Exception as e:
-                message = field.gettext('Content fetcher \'%s\' did not respond properly, unable to use it.\n %s')
+        #         message = field.gettext('Content fetcher \'%s\' did not respond properly, unable to use it.\n %s')
-                raise ValidationError(message % (field.data, e))
+        #         raise ValidationError(message % (field.data, e))
 
 
 class ValidateNotificationBodyAndTitleWhenURLisSet(object):
@@ -421,7 +419,7 @@ class commonSettingsForm(Form):
     notification_title = StringField('Notification Title', default='ChangeDetection.io Notification - {{ watch_url }}', validators=[validators.Optional(), ValidateJinja2Template()])
     notification_body = TextAreaField('Notification Body', default='{{ watch_url }} had a change.', validators=[validators.Optional(), ValidateJinja2Template()])
     notification_format = SelectField('Notification format', choices=valid_notification_formats.keys())
-    fetch_backend = RadioField(u'Fetch Method', choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    fetch_backend = RadioField(u'Fetch Method', choices=content_fetchers.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")])
@@ -465,6 +463,7 @@ class watchForm(commonSettingsForm):
     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)
+    sort_text_alphabetically =  BooleanField('Sort text alphabetically', default=False)
 
     filter_text_added = BooleanField('Added lines', default=True)
     filter_text_replaced = BooleanField('Replaced/changed lines', default=True)
@@ -551,7 +550,7 @@ class globalSettingsApplicationForm(commonSettingsForm):
                            render_kw={"placeholder": os.getenv('BASE_URL', 'Not set')}
                            )
     empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
-    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetchers.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
     global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
     ignore_whitespace = BooleanField('Ignore whitespace')

changedetectionio/importer.py

@@ -57,7 +57,7 @@ class import_url_list(Importer):
 
             # Flask wtform validators wont work with basic auth, use validators package
             # Up to 5000 per batch so we dont flood the server
-            # @todo validators.url failed on local hostnames (such as referring to ourself when using browserless)
+            # @todo validators.url will fail when you add your own IP etc
             if len(url) and 'http' in url.lower() and good < 5000:
                 extras = None
                 if processor:

changedetectionio/model/Watch.py

@@ -45,6 +45,7 @@ base_config = {
     'last_error': False,
     'last_viewed': 0,  # history key value of the last viewed via the [diff] link
     'method': 'GET',
+    'notification_alert_count': 0,
     # Custom notification content
     'notification_body': None,
     'notification_format': default_notification_format_for_watch,
@@ -56,6 +57,8 @@ base_config = {
     'previous_md5': False,
     'previous_md5_before_filters': False,  # Used for skipping changedetection entirely
     'proxy': None,  # Preferred proxy connection
+    'remote_server_reply': None, # From 'server' reply header
+    'sort_text_alphabetically': False,
     'subtractive_selectors': [],
     'tag': '', # Old system of text name for a tag, to be removed
     'tags': [], # list of UUIDs to App.Tags

changedetectionio/processors/__init__.py

@@ -2,7 +2,6 @@ from abc import abstractmethod
 import os
 import hashlib
 import re
-from changedetectionio import content_fetcher
 from copy import deepcopy
 from distutils.util import strtobool
 from loguru import logger
@@ -50,7 +49,7 @@ class difference_detection_processor():
             connection = list(
                 filter(lambda s: (s['browser_name'] == key), self.datastore.data['settings']['requests'].get('extra_browsers', [])))
             if connection:
-                prefer_fetch_backend = 'base_html_playwright'
+                prefer_fetch_backend = 'html_webdriver'
                 custom_browser_connection_url = connection[0].get('browser_connection_url')
 
         # PDF should be html_requests because playwright will serve it up (so far) in a embedded page
@@ -60,17 +59,28 @@ class difference_detection_processor():
            prefer_fetch_backend = "html_requests"
 
         # Grab the right kind of 'fetcher', (playwright, requests, etc)
-        if hasattr(content_fetcher, prefer_fetch_backend):
+        from changedetectionio import content_fetchers
-            fetcher_obj = getattr(content_fetcher, prefer_fetch_backend)
+        if hasattr(content_fetchers, prefer_fetch_backend):
+            # @todo TEMPORARY HACK - SWITCH BACK TO PLAYWRIGHT FOR BROWSERSTEPS
+            if prefer_fetch_backend == 'html_webdriver' and self.watch.has_browser_steps:
+                # This is never supported in selenium anyway
+                logger.warning("Using playwright fetcher override for possible puppeteer request in browsersteps, because puppetteer:browser steps is incomplete.")
+                from changedetectionio.content_fetchers.playwright import fetcher as playwright_fetcher
+                fetcher_obj = playwright_fetcher
+            else:
+                fetcher_obj = getattr(content_fetchers, prefer_fetch_backend)
         else:
-            # If the klass doesnt exist, just use a default
+            # What it referenced doesnt exist, Just use a default
-            fetcher_obj = getattr(content_fetcher, "html_requests")
+            fetcher_obj = getattr(content_fetchers, "html_requests")
-
 
         proxy_url = None
         if preferred_proxy_id:
-            proxy_url = self.datastore.proxy_list.get(preferred_proxy_id).get('url')
+            # Custom browser endpoints should NOT have a proxy added
-            logger.debug(f"Selected proxy key '{preferred_proxy_id}' as proxy URL '{proxy_url}' for {url}")
+            if not prefer_fetch_backend.startswith('extra_browser_'):
+                proxy_url = self.datastore.proxy_list.get(preferred_proxy_id).get('url')
+                logger.debug(f"Selected proxy key '{preferred_proxy_id}' as proxy URL '{proxy_url}' for {url}")
+            else:
+                logger.debug(f"Skipping adding proxy data when custom Browser endpoint is specified. ")
 
         # Now call the fetcher (playwright/requests/etc) with arguments that only a fetcher would need.
         # When browser_connection_url is None, it method should default to working out whats the best defaults (os env vars etc)

changedetectionio/processors/text_json_diff.py

@@ -8,8 +8,9 @@ import urllib3
 
 from . import difference_detection_processor
 from ..html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text
-from changedetectionio import content_fetcher, html_tools
+from changedetectionio import html_tools, content_fetchers
 from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
+import changedetectionio.content_fetchers
 from copy import deepcopy
 from loguru import logger
 
@@ -60,7 +61,7 @@ class perform_site_check(difference_detection_processor):
         update_obj['previous_md5_before_filters'] = hashlib.md5(self.fetcher.content.encode('utf-8')).hexdigest()
         if skip_when_checksum_same:
             if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
-                raise content_fetcher.checksumFromPreviousCheckWasTheSame()
+                raise content_fetchers.exceptions.checksumFromPreviousCheckWasTheSame()
 
         # Fetching complete, now filters
 
@@ -116,7 +117,9 @@ class perform_site_check(difference_detection_processor):
         # and then use getattr https://docs.python.org/3/reference/datamodel.html#object.__getitem__
         # https://realpython.com/inherit-python-dict/ instead of doing it procedurely
         include_filters_from_tags = self.datastore.get_tag_overrides_for_watch(uuid=uuid, attr='include_filters')
-        include_filters_rule = [*watch.get('include_filters', []), *include_filters_from_tags]
+
+        # 1845 - remove duplicated filters in both group and watch include filter
+        include_filters_rule = list(dict.fromkeys(watch.get('include_filters', []) + include_filters_from_tags))
 
         subtractive_selectors = [*self.datastore.get_tag_overrides_for_watch(uuid=uuid, attr='subtractive_selectors'),
                                  *watch.get("subtractive_selectors", []),
@@ -202,6 +205,12 @@ class perform_site_check(difference_detection_processor):
                             is_rss=is_rss # #1874 activate the <title workaround hack
                         )
 
+        if watch.get('sort_text_alphabetically') and stripped_text_from_html:
+            # Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap
+            # we end up with 'Some text\n\n', sorting will add all those extra \n at the start, so we remove them here.
+            stripped_text_from_html = stripped_text_from_html.replace('\n\n', '\n')
+            stripped_text_from_html = '\n'.join( sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower() ))
+
         # Re #340 - return the content before the 'ignore text' was applied
         text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
@@ -235,7 +244,7 @@ class perform_site_check(difference_detection_processor):
         # Treat pages with no renderable text content as a change? No by default
         empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
         if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
-            raise content_fetcher.ReplyWithContentButNoText(url=url,
+            raise content_fetchers.exceptions.ReplyWithContentButNoText(url=url,
                                                             status_code=self.fetcher.get_last_status_code(),
                                                             screenshot=screenshot,
                                                             has_filters=has_filter_rule,

changedetectionio/run_custom_browser_url_tests.sh

@@ -2,20 +2,22 @@
 
 # run some tests and look if the 'custom-browser-search-string=1' connect string appeared in the correct containers
 
+# @todo do it again but with the puppeteer one
+
 # enable debug
 set -x
 
 # A extra browser is configured, but we never chose to use it, so it should NOT show in the logs
-docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/custom_browser_url/test_custom_browser_url.py::test_request_not_via_custom_browser_url'
+docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/custom_browser_url/test_custom_browser_url.py::test_request_not_via_custom_browser_url'
-docker logs browserless-custom-url &>log.txt
+docker logs sockpuppetbrowser-custom-url &>log-custom.txt
-grep 'custom-browser-search-string=1' log.txt
+grep 'custom-browser-search-string=1' log-custom.txt
 if [ $? -ne 1 ]
 then
-  echo "Saw a request in 'browserless-custom-url' container with 'custom-browser-search-string=1' when I should not"
+  echo "Saw a request in 'sockpuppetbrowser-custom-url' container with 'custom-browser-search-string=1' when I should not - log-custom.txt"
   exit 1
 fi
 
-docker logs browserless &>log.txt
+docker logs sockpuppetbrowser &>log.txt
 grep 'custom-browser-search-string=1' log.txt
 if [ $? -ne 1 ]
 then
@@ -24,16 +26,16 @@ then
 fi
 
 # Special connect string should appear in the custom-url container, but not in the 'default' one
-docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/custom_browser_url/test_custom_browser_url.py::test_request_via_custom_browser_url'
+docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/custom_browser_url/test_custom_browser_url.py::test_request_via_custom_browser_url'
-docker logs browserless-custom-url &>log.txt
+docker logs sockpuppetbrowser-custom-url &>log-custom.txt
-grep 'custom-browser-search-string=1' log.txt
+grep 'custom-browser-search-string=1' log-custom.txt
 if [ $? -ne 0 ]
 then
-  echo "Did not see request in 'browserless-custom-url' container with 'custom-browser-search-string=1' when I should"
+  echo "Did not see request in 'sockpuppetbrowser-custom-url' container with 'custom-browser-search-string=1' when I should - log-custom.txt"
   exit 1
 fi
 
-docker logs browserless &>log.txt
+docker logs sockpuppetbrowser &>log.txt
 grep 'custom-browser-search-string=1' log.txt
 if [ $? -ne 1 ]
 then

changedetectionio/run_proxy_tests.sh

@@ -10,41 +10,7 @@ set -x
 docker run --network changedet-network -d --name squid-one --hostname squid-one --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
 docker run --network changedet-network -d --name squid-two --hostname squid-two --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
 
-# SOCKS5 related - start simple Socks5 proxy server
+# Used for configuring a custom proxy URL via the UI - with username+password auth
-# SOCKSTEST=xyz should show in the logs of this service to confirm it fetched
-docker run --network changedet-network -d --hostname socks5proxy --name socks5proxy -p 1080:1080 -e PROXY_USER=proxy_user123 -e PROXY_PASSWORD=proxy_pass123 serjs/go-socks5-proxy
-docker run --network changedet-network -d --hostname socks5proxy-noauth -p 1081:1080 --name socks5proxy-noauth  serjs/go-socks5-proxy
-
-echo "---------------------------------- SOCKS5 -------------------"
-# SOCKS5 related - test from proxies.json
-docker run --network changedet-network \
-  -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
-  --rm \
-  -e "SOCKSTEST=proxiesjson" \
-  test-changedetectionio \
-  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
-
-# SOCKS5 related - by manually entering in UI
-docker run --network changedet-network \
-  --rm \
-  -e "SOCKSTEST=manual" \
-  test-changedetectionio \
-  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy.py'
-
-# SOCKS5 related - test from proxies.json via playwright - NOTE- PLAYWRIGHT DOESNT SUPPORT AUTHENTICATING PROXY
-docker run --network changedet-network \
-  -e "SOCKSTEST=manual-playwright" \
-  -v `pwd`/tests/proxy_socks5/proxies.json-example-noauth:/app/changedetectionio/test-datastore/proxies.json \
-  -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" \
-  --rm \
-  test-changedetectionio \
-  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
-
-echo "socks5 server logs"
-docker logs socks5proxy
-echo "----------------------------------"
-
-# Used for configuring a custom proxy URL via the UI
 docker run --network changedet-network -d \
   --name squid-custom \
   --hostname squid-custom \
@@ -60,15 +26,17 @@ docker run --network changedet-network \
   test-changedetectionio \
   bash -c 'cd changedetectionio && pytest tests/proxy_list/test_multiple_proxy.py'
 
-
+set +e
-## Should be a request in the default "first" squid
+echo "- Looking for chosen.changedetection.io request in squid-one - it should NOT be here"
 docker logs squid-one 2>/dev/null|grep chosen.changedetection.io
-if [ $? -ne 0 ]
+if [ $? -ne 1 ]
 then
-  echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy - squid one)"
+  echo "Saw a request to chosen.changedetection.io in the squid logs (while checking preferred proxy - squid one) WHEN I SHOULD NOT"
   exit 1
 fi
 
+set -e
+echo "- Looking for chosen.changedetection.io request in squid-two"
 # 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 ]
@@ -77,7 +45,6 @@ then
   exit 1
 fi
 
-
 # Test the UI configurable proxies
 docker run --network changedet-network \
   test-changedetectionio \
@@ -85,6 +52,7 @@ docker run --network changedet-network \
 
 
 # Should see a request for one.changedetection.io in there
+echo "- Looking for .changedetection.io request in squid-custom"
 docker logs squid-custom 2>/dev/null|grep "TCP_TUNNEL.200.*changedetection.io"
 if [ $? -ne 0 ]
 then
@@ -101,7 +69,7 @@ docker run --network changedet-network \
 set +e
 # Check request was never seen in any container
 for c in $(echo "squid-one squid-two squid-custom"); do
-  echo Checking $c
+  echo ....Checking $c
   docker logs $c &> $c.txt
   grep noproxy $c.txt
   if [ $? -ne 1 ]

changedetectionio/run_socks_proxy_tests.sh

@@ -0,0 +1,43 @@
+#!/bin/bash
+
+# exit when any command fails
+set -e
+# enable debug
+set -x
+
+
+# SOCKS5 related - start simple Socks5 proxy server
+# SOCKSTEST=xyz should show in the logs of this service to confirm it fetched
+docker run --network changedet-network -d --hostname socks5proxy --rm  --name socks5proxy -p 1080:1080 -e PROXY_USER=proxy_user123 -e PROXY_PASSWORD=proxy_pass123 serjs/go-socks5-proxy
+docker run --network changedet-network -d --hostname socks5proxy-noauth --rm  -p 1081:1080 --name socks5proxy-noauth  serjs/go-socks5-proxy
+
+echo "---------------------------------- SOCKS5 -------------------"
+# SOCKS5 related - test from proxies.json
+docker run --network changedet-network \
+  -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
+  --rm \
+  -e "SOCKSTEST=proxiesjson" \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+
+# SOCKS5 related - by manually entering in UI
+docker run --network changedet-network \
+  --rm \
+  -e "SOCKSTEST=manual" \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy.py'
+
+# SOCKS5 related - test from proxies.json via playwright - NOTE- PLAYWRIGHT DOESNT SUPPORT AUTHENTICATING PROXY
+docker run --network changedet-network \
+  -e "SOCKSTEST=manual-playwright" \
+  -v `pwd`/tests/proxy_socks5/proxies.json-example-noauth:/app/changedetectionio/test-datastore/proxies.json \
+  -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" \
+  --rm \
+  test-changedetectionio \
+  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+
+echo "socks5 server logs"
+docker logs socks5proxy
+echo "----------------------------------"
+
+docker kill socks5proxy socks5proxy-noauth

changedetectionio/static/js/browser-steps.js

@@ -10,7 +10,7 @@ $(document).ready(function () {
         }
     })
     var browsersteps_session_id;
-    var browserless_seconds_remaining = 0;
+    var browser_interface_seconds_remaining = 0;
     var apply_buttons_disabled = false;
     var include_text_elements = $("#include_text_elements");
     var xpath_data = false;
@@ -49,7 +49,7 @@ $(document).ready(function () {
         $('#browsersteps-img').removeAttr('src');
         $("#browsersteps-click-start").show();
         $("#browsersteps-selector-wrapper .spinner").hide();
-        browserless_seconds_remaining = 0;
+        browser_interface_seconds_remaining = 0;
         browsersteps_session_id = false;
         apply_buttons_disabled = false;
         ctx.clearRect(0, 0, c.width, c.height);
@@ -61,12 +61,12 @@ $(document).ready(function () {
         $('#browser_steps >li:first-child').css('opacity', '0.5');
     }
 
-    // Show seconds remaining until playwright/browserless needs to restart the session
+    // Show seconds remaining until the browser interface needs to restart the session
     // (See comment at the top of changedetectionio/blueprint/browser_steps/__init__.py )
     setInterval(() => {
-        if (browserless_seconds_remaining >= 1) {
+        if (browser_interface_seconds_remaining >= 1) {
-            document.getElementById('browserless-seconds-remaining').innerText = browserless_seconds_remaining + " seconds remaining in session";
+            document.getElementById('browser-seconds-remaining').innerText = browser_interface_seconds_remaining + " seconds remaining in session";
-            browserless_seconds_remaining -= 1;
+            browser_interface_seconds_remaining -= 1;
         }
     }, "1000")
 
@@ -160,6 +160,12 @@ $(document).ready(function () {
                     e.offsetX > item.left * y_scale && e.offsetX < item.left * y_scale + item.width * y_scale
 
                 ) {
+                    // Ignore really large ones, because we are scraping 'div' also from xpath_element_scraper but
+                    // that div or whatever could be some wrapper and would generally make you select the whole page
+                    if (item.width > 800 && item.height > 400) {
+                        return
+                    }
+
                     // There could be many elements here, record them all and then we'll find out which is the most 'useful'
                     // (input, textarea, button, A etc)
                     if (item.width < xpath_data['browser_width']) {
@@ -261,7 +267,7 @@ $(document).ready(function () {
             // This should trigger 'Goto site'
             console.log("Got startup response, requesting Goto-Site (first) step fake click");
             $('#browser_steps >li:first-child .apply').click();
-            browserless_seconds_remaining = 500;
+            browser_interface_seconds_remaining = 500;
             set_first_gotosite_disabled();
         }).fail(function (data) {
             console.log(data);

changedetectionio/static/js/diff-overview.js

@@ -90,5 +90,10 @@ $(document).ready(function () {
         }
     }
 
-
+    $('#diff-form').on('submit', function (e) {
+        if ($('select[name=from_version]').val() === $('select[name=to_version]').val()) {
+            e.preventDefault();
+            alert('Error - You are trying to compare the same version.');
+        }
+    });
 });

changedetectionio/static/styles/scss/styles.scss

@@ -1096,3 +1096,16 @@ ul {
   white-space: nowrap;
 }
 
+#chrome-extension-link {
+  img {
+    height: 21px;
+    padding: 2px;
+    vertical-align: middle;
+  }
+
+  padding: 9px;
+  border: 1px solid var(--color-grey-800);
+  border-radius: 10px;
+  vertical-align: middle;
+}
+

changedetectionio/static/styles/styles.css

@@ -1180,3 +1180,13 @@ ul {
   .restock-label.not-in-stock {
     background-color: var(--color-background-button-cancel);
     color: #777; }
+
+#chrome-extension-link {
+  padding: 9px;
+  border: 1px solid var(--color-grey-800);
+  border-radius: 10px;
+  vertical-align: middle; }
+  #chrome-extension-link img {
+    height: 21px;
+    padding: 2px;
+    vertical-align: middle; }

changedetectionio/store.py

@@ -255,6 +255,7 @@ class ChangeDetectionStore:
                 'last_viewed': 0,
                 'previous_md5': False,
                 'previous_md5_before_filters': False,
+                'remote_server_reply': None,
                 'track_ldjson_price_data': None,
             })
 

changedetectionio/templates/base.html

@@ -147,7 +147,19 @@
     <section class="content">
         <div id="overlay">
             <div class="content">
-                <strong>changedetection.io needs your support!</strong><br>
+                <h4>Try our Chrome extension</h4>
+                <p>
+                    <a id="chrome-extension-link"
+                       title="Try our new Chrome Extension!"
+                       href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
+                        <img src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}">
+                        Chrome Webstore
+                    </a>
+                </p>
+
+                Easily add the current web-page from your browser directly into your changedetection.io tool, more great features coming soon!
+
+                <h4>Changedetection.io needs your support!</h4>
                 <p>
                     You can help us by supporting changedetection.io on these platforms;
                 </p>

changedetectionio/templates/diff.html

@@ -13,7 +13,7 @@
 <script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
 <div id="settings">
-    <form class="pure-form " action="" method="GET">
+    <form class="pure-form " action="" method="GET" id="diff-form">
         <fieldset>
             {% if versions|length >= 1 %}
                 <strong>Compare</strong>

changedetectionio/templates/edit.html

@@ -228,7 +228,7 @@ User-Agent: wonderbra 1.0") }}
                                 </div>
                             </div>
                             <div id="browser-steps-fieldlist" style="padding-left: 1em;  width: 350px; font-size: 80%;" >
-                                <span id="browserless-seconds-remaining">Loading</span> <span style="font-size: 80%;"> (<a target=_new href="https://github.com/dgtlmoon/changedetection.io/pull/478/files#diff-1a79d924d1840c485238e66772391268a89c95b781d69091384cf1ea1ac146c9R4">?</a>) </span>
+                                <span id="browser-seconds-remaining">Loading</span> <span style="font-size: 80%;"> (<a target=_new href="https://github.com/dgtlmoon/changedetection.io/pull/478/files#diff-1a79d924d1840c485238e66772391268a89c95b781d69091384cf1ea1ac146c9R4">?</a>) </span>
                                 {{ render_field(form.browser_steps) }}
                             </div>
                         </div>
@@ -323,6 +323,7 @@ nav
                     <span class="pure-form-message-inline">
                         <ul>
                           <li> Remove HTML element(s) by CSS selector before text conversion. </li>
+                          <li> Don't paste HTML here, use only CSS selectors </li>
                           <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
@@ -339,6 +340,10 @@ nav
                     <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>
 
+                <fieldset class="pure-control-group">
+                    {{ render_checkbox_field(form.sort_text_alphabetically) }}
+                    <span class="pure-form-message-inline">Helps reduce changes detected caused by sites shuffling lines around, combine with <i>check unique lines</i> below.</span>
+                </fieldset>
                 <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>
@@ -401,6 +406,7 @@ Unavailable") }}
                                 <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>
+                                <li>Example - match lines containing a keyword <code>/.*icecream.*/</code></li>
                             </ul>
                         </li>
                         <li>One line per regular-expression/string match</li>
@@ -431,7 +437,7 @@ 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, this tool is a helper to manage filters in the  "CSS/JSONPath/JQ/XPath Filters" box of the <a href="#filters-and-triggers">Filters & Triggers</a> tab.
                             </span>
 
                             <div id="selector-header">
@@ -482,6 +488,10 @@ Unavailable") }}
                             <td>Last fetch time</td>
                             <td>{{ watch.fetch_time }}s</td>
                         </tr>
+                        <tr>
+                            <td>Notification alert count</td>
+                            <td>{{ watch.notification_alert_count }}</td>
+                        </tr>
                         </tbody>
                     </table>
                 </div>

changedetectionio/templates/import.html

@@ -107,7 +107,7 @@
                                     <option value="" style="color: #aaa"> -- none --</option>
                                     <option value="url">URL</option>
                                     <option value="title">Title</option>
-                                    <option value="include_filter">CSS/xPath filter</option>
+                                    <option value="include_filters">CSS/xPath filter</option>
                                     <option value="tag">Group / Tag name(s)</option>
                                     <option value="interval_minutes">Recheck time (minutes)</option>
                                 </select></td>

changedetectionio/templates/settings.html

@@ -168,12 +168,12 @@ nav
            </div>
 
             <div class="tab-pane-inner" id="api">
-
+                <h4>API Access</h4>
                 <p>Drive your changedetection.io via API, More about <a href="https://github.com/dgtlmoon/changedetection.io/wiki/API-Reference">API access here</a></p>
 
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.api_access_token_enabled) }}
-                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header</div><br>
+                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header - required for the Chrome Extension to work</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>
@@ -181,6 +181,20 @@ nav
                 <div class="pure-control-group">
                     <a href="{{url_for('settings_reset_api_key')}}" class="pure-button button-small button-cancel">Regenerate API key</a>
                 </div>
+                <div class="pure-control-group">
+                    <h4>Chrome Extension</h4>
+                    <p>Easily add any web-page to your changedetection.io installation from within Chrome.</p>
+                    <strong>Step 1</strong> Install the extension, <strong>Step 2</strong> Navigate to this page,
+                    <strong>Step 3</strong> Open the extension from the toolbar and click "<i>Sync API Access</i>"
+                    <p>
+                        <a id="chrome-extension-link"
+                           title="Try our new Chrome Extension!"
+                           href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
+                            <img src="{{ url_for('static_content', group='images', filename='Google-Chrome-icon.png') }}">
+                            Chrome Webstore
+                        </a>
+                    </p>
+                </div>
             </div>
             <div class="tab-pane-inner" id="proxies">
                 <div id="recommended-proxy">

changedetectionio/templates/watch-overview.html

@@ -1,6 +1,6 @@
 {% extends 'base.html' %}
 {% block content %}
-{% from '_helpers.jinja' import render_simple_field, render_field, render_nolabel_field %}
+{% from '_helpers.jinja' import render_simple_field, render_field, render_nolabel_field, sort_by_title %}
 <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
 <script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
 
@@ -13,7 +13,7 @@
             <div id="watch-add-wrapper-zone">
 
                     {{ render_nolabel_field(form.url, placeholder="https://...", required=true) }}
-                    {{ render_nolabel_field(form.tags, value=tags[active_tag].title if active_tag else '', placeholder="watch label / tag") }}
+                    {{ render_nolabel_field(form.tags, value=active_tag.title if active_tag else '', placeholder="watch label / tag") }}
                     {{ render_nolabel_field(form.watch_submit_button, title="Watch this URL!" ) }}
                     {{ render_nolabel_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
             </div>
@@ -37,6 +37,7 @@
         <button class="pure-button button-secondary button-xsmall" name="op" value="assign-tag" id="checkbox-assign-tag">Tag</button>
         <button class="pure-button button-secondary button-xsmall" name="op" value="mark-viewed">Mark viewed</button>
         <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default">Use default notification</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="clear-errors">Clear errors</button>
         <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="clear-history">Clear/reset history</button>
         <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="delete">Delete</button>
     </div>
@@ -46,11 +47,13 @@
     {% if search_q %}<div id="search-result-info">Searching "<strong><i>{{search_q}}</i></strong>"</div>{% endif %}
     <div>
         <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag }}">All</a>
-        {% for uuid, tag in tags.items() %}
+
-            {% if tag != "" %}
+    <!-- tag list -->
-                <a href="{{url_for('index', tag=uuid) }}" class="pure-button button-tag {{'active' if active_tag == uuid }}">{{ tag.title }}</a>
+    {% for uuid, tag in tags %}
-            {% endif %}
+        {% if tag != "" %}
-        {% endfor %}
+            <a href="{{url_for('index', tag=uuid) }}" class="pure-button button-tag {{'active' if active_tag_uuid == uuid }}">{{ tag.title }}</a>
+        {% endif %}
+    {% endfor %}
     </div>
 
     {% set sort_order = sort_order or 'asc' %}
@@ -197,8 +200,8 @@
             </li>
             {% endif %}
             <li>
-               <a href="{{ url_for('form_watch_checknow', tag=active_tag, with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Recheck
+               <a href="{{ url_for('form_watch_checknow', tag=active_tag_uuid, with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Recheck
-                all {% if active_tag%} in "{{tags[active_tag].title}}"{%endif%}</a>
+                all {% if active_tag_uuid %} in "{{active_tag.title}}"{%endif%}</a>
             </li>
             <li>
                 <a href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='Generic_Feed-icon.svg')}}" height="15"></a>

changedetectionio/tests/custom_browser_url/test_custom_browser_url.py

@@ -7,10 +7,11 @@ from ..util import live_server_setup, wait_for_all_checks
 def do_test(client, live_server, make_test_use_extra_browser=False):
 
     # Grep for this string in the logs?
-    test_url = f"https://changedetection.io/ci-test.html"
+    test_url = f"https://changedetection.io/ci-test.html?non-custom-default=true"
+    # "non-custom-default" should not appear in the custom browser connection
     custom_browser_name = 'custom browser URL'
 
-    # needs to be set and something like 'ws://127.0.0.1:3000?stealth=1&--disable-web-security=true'
+    # needs to be set and something like 'ws://127.0.0.1:3000'
     assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
 
     #####################
@@ -19,9 +20,7 @@ def do_test(client, live_server, make_test_use_extra_browser=False):
         data={"application-empty_pages_are_a_change": "",
               "requests-time_between_check-minutes": 180,
               'application-fetch_backend': "html_webdriver",
-              # browserless-custom-url is setup in  .github/workflows/test-only.yml
+              'requests-extra_browsers-0-browser_connection_url': 'ws://sockpuppetbrowser-custom-url:3000',
-              # the test script run_custom_browser_url_test.sh will look for 'custom-browser-search-string' in the container logs
-              'requests-extra_browsers-0-browser_connection_url': 'ws://browserless-custom-url:3000?stealth=1&--disable-web-security=true&custom-browser-search-string=1',
               'requests-extra_browsers-0-browser_name': custom_browser_name
               },
         follow_redirects=True
@@ -51,7 +50,8 @@ def do_test(client, live_server, make_test_use_extra_browser=False):
         res = client.post(
             url_for("edit_page", uuid="first"),
             data={
-                  "url": test_url,
+                # 'run_customer_browser_url_tests.sh' will search for this string to know if we hit the right browser container or not
+                  "url": f"https://changedetection.io/ci-test.html?custom-browser-search-string=1",
                   "tags": "",
                   "headers": "",
                   'fetch_backend': f"extra_browser_{custom_browser_name}",

changedetectionio/tests/fetchers/test_custom_js_before_content.py

@@ -0,0 +1,56 @@
+import os
+from flask import url_for
+from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+
+
+def test_execute_custom_js(client, live_server):
+
+    live_server_setup(live_server)
+    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
+
+    test_url = url_for('test_interactive_html_endpoint', _external=True)
+    test_url = test_url.replace('localhost.localdomain', 'cdio')
+    test_url = test_url.replace('localhost', 'cdio')
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+        data={
+            "url": test_url,
+            "tags": "",
+            'fetch_backend': "html_webdriver",
+            'webdriver_js_execute_code': 'document.querySelector("button[name=test-button]").click();',
+            'headers': "testheader: yes\buser-agent: MyCustomAgent",
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+
+    uuid = extract_UUID_from_client(client)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n >= 1, "Watch history had atleast 1 (everything fetched OK)"
+
+    assert b"This text should be removed" not in res.data
+
+    # Check HTML conversion detected and workd
+    res = client.get(
+        url_for("preview_page", uuid=uuid),
+        follow_redirects=True
+    )
+    assert b"This text should be removed" not in res.data
+    assert b"I smell JavaScript because the button was pressed" in res.data
+
+    assert b"testheader: yes" in res.data
+    assert b"user-agent: mycustomagent" in res.data
+
+    client.get(
+        url_for("form_delete", uuid="all"),
+        follow_redirects=True
+    )

changedetectionio/tests/proxy_list/test_multiple_proxy.py

@@ -1,6 +1,6 @@
 #!/usr/bin/python3
 
-import time
+import os
 from flask import url_for
 from ..util import live_server_setup, wait_for_all_checks
 
@@ -9,22 +9,20 @@ def test_preferred_proxy(client, live_server):
     live_server_setup(live_server)
     url = "http://chosen.changedetection.io"
 
+
     res = client.post(
-        url_for("import_page"),
+        url_for("form_quick_watch_add"),
-        # Because a URL wont show in squid/proxy logs due it being SSLed
+        data={"url": url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
-        # Use plain HTTP or a specific domain-name here
-        data={"urls": url},
         follow_redirects=True
     )
-
+    assert b"Watch added in Paused state, saving will unpause" in res.data
-    assert b"1 Imported" in res.data
 
     wait_for_all_checks(client)
     res = client.post(
-        url_for("edit_page", uuid="first"),
+        url_for("edit_page", uuid="first", unpause_on_save=1),
         data={
                 "include_filters": "",
-                "fetch_backend": "html_requests",
+                "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
                 "headers": "",
                 "proxy": "proxy-two",
                 "tags": "",
@@ -32,6 +30,6 @@ def test_preferred_proxy(client, live_server):
               },
         follow_redirects=True
     )
-    assert b"Updated watch." in res.data
+    assert b"unpaused" in res.data
     wait_for_all_checks(client)
     # Now the request should appear in the second-squid logs

changedetectionio/tests/proxy_list/test_select_custom_proxy.py

@@ -3,6 +3,7 @@
 import time
 from flask import url_for
 from ..util import live_server_setup, wait_for_all_checks
+import os
 
 # just make a request, we will grep in the docker logs to see it actually got called
 def test_select_custom(client, live_server):
@@ -14,7 +15,7 @@ def test_select_custom(client, live_server):
         data={
             "requests-time_between_check-minutes": 180,
             "application-ignore_whitespace": "y",
-            "application-fetch_backend": "html_requests",
+            "application-fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else '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",

changedetectionio/tests/restock/test_restock.py

@@ -95,7 +95,7 @@ def test_restock_detection(client, live_server):
 
     # We should have a notification
     time.sleep(2)
-    assert os.path.isfile("test-datastore/notification.txt")
+    assert os.path.isfile("test-datastore/notification.txt"), "Notification received"
     os.unlink("test-datastore/notification.txt")
 
     # Default behaviour is to only fire notification when it goes OUT OF STOCK -> IN STOCK
@@ -103,4 +103,9 @@ def test_restock_detection(client, live_server):
     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")
+    assert not os.path.isfile("test-datastore/notification.txt"), "No notification should have fired when it went OUT OF STOCK by default"
+
+    # BUT we should see that it correctly shows "not in stock"
+    res = client.get(url_for("index"))
+    assert b'not-in-stock' in res.data, "Correctly showing NOT IN STOCK in the list after it changed from IN STOCK"
+

changedetectionio/tests/test_api.py

@@ -163,6 +163,7 @@ def test_api_simple(client, live_server):
     # Loading the most recent snapshot should force viewed to become true
     client.get(url_for("diff_history_page", uuid="first"), follow_redirects=True)
 
+    time.sleep(3)
     # Fetch the whole watch again, viewed should be true
     res = client.get(
         url_for("watch", uuid=watch_uuid),

changedetectionio/tests/test_backend.py

@@ -29,7 +29,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
 
     assert b"1 Imported" in res.data
 
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # Do this a few times.. ensures we dont accidently set the status
     for n in range(3):

changedetectionio/tests/test_errorhandling.py

@@ -3,7 +3,7 @@
 import time
 
 from flask import url_for
-from . util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
 
 from ..html_tools import *
 
@@ -30,7 +30,7 @@ def _runner_test_http_errors(client, live_server, http_code, expected_text):
     assert b"1 Imported" in res.data
 
     # Give the thread time to pick it up
-    time.sleep(2)
+    wait_for_all_checks(client)
 
     res = client.get(url_for("index"))
     # no change
@@ -57,7 +57,7 @@ def _runner_test_http_errors(client, live_server, http_code, expected_text):
 def test_http_error_handler(client, live_server):
     _runner_test_http_errors(client, live_server, 403, 'Access denied')
     _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, 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
@@ -76,7 +76,7 @@ def test_DNS_errors(client, live_server):
     assert b"1 Imported" in res.data
 
     # Give the thread time to pick it up
-    time.sleep(3)
+    wait_for_all_checks(client)
 
     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
@@ -104,7 +104,7 @@ def test_low_level_errors_clear_correctly(client, live_server):
         follow_redirects=True
     )
     assert b"1 Imported" in res.data
-    time.sleep(2)
+    wait_for_all_checks(client)
 
     # We should see the DNS error
     res = client.get(url_for("index"))
@@ -121,7 +121,7 @@ def test_low_level_errors_clear_correctly(client, live_server):
     )
 
     # Now the error should be gone
-    time.sleep(2)
+    wait_for_all_checks(client)
     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

changedetectionio/tests/test_group.py

@@ -321,3 +321,154 @@ def test_clone_tag_on_quickwatchform_add(client, live_server):
 
     res = client.get(url_for("tags.delete_all"), follow_redirects=True)
     assert b'All tags deleted' in res.data
+
+def test_order_of_filters_tag_filter_and_watch_filter(client, live_server):
+
+    # Add a tag with some config, import a tag and it should roughly work
+    res = client.post(
+        url_for("tags.form_tag_add"),
+        data={"name": "test-tag-keep-order"},
+        follow_redirects=True
+    )
+    assert b"Tag added" in res.data
+    assert b"test-tag-keep-order" in res.data
+    tag_filters = [
+            '#only-this', # duplicated filters
+            '#only-this',
+            '#only-this',
+            '#only-this',
+            ]
+
+    res = client.post(
+        url_for("tags.form_tag_edit_submit", uuid="first"),
+        data={"name": "test-tag-keep-order",
+              "include_filters": '\n'.join(tag_filters) },
+        follow_redirects=True
+    )
+    assert b"Updated" in res.data
+    tag_uuid = get_UUID_for_tag_name(client, name="test-tag-keep-order")
+    res = client.get(
+        url_for("tags.form_tag_edit", uuid="first")
+    )
+    assert b"#only-this" in res.data
+
+
+    d = """<html>
+       <body>
+     Some initial text<br>
+     <p id="only-this">And 1 this</p>
+     <br>
+     <p id="not-this">And 2 this</p>
+     <p id="">And 3 this</p><!--/html/body/p[3]/-->
+     <p id="">And 4 this</p><!--/html/body/p[4]/-->
+     <p id="">And 5 this</p><!--/html/body/p[5]/-->
+     <p id="">And 6 this</p><!--/html/body/p[6]/-->
+     <p id="">And 7 this</p><!--/html/body/p[7]/-->
+     <p id="">And 8 this</p><!--/html/body/p[8]/-->
+     <p id="">And 9 this</p><!--/html/body/p[9]/-->
+     <p id="">And 10 this</p><!--/html/body/p[10]/-->
+     <p id="">And 11 this</p><!--/html/body/p[11]/-->
+     <p id="">And 12 this</p><!--/html/body/p[12]/-->
+     <p id="">And 13 this</p><!--/html/body/p[13]/-->
+     <p id="">And 14 this</p><!--/html/body/p[14]/-->
+     <p id="not-this">And 15 this</p><!--/html/body/p[15]/-->
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(d)
+
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+    wait_for_all_checks(client)
+
+    filters = [
+            '/html/body/p[3]',
+            '/html/body/p[4]',
+            '/html/body/p[5]',
+            '/html/body/p[6]',
+            '/html/body/p[7]',
+            '/html/body/p[8]',
+            '/html/body/p[9]',
+            '/html/body/p[10]',
+            '/html/body/p[11]',
+            '/html/body/p[12]',
+            '/html/body/p[13]', # duplicated tags
+            '/html/body/p[13]',
+            '/html/body/p[13]',
+            '/html/body/p[13]',
+            '/html/body/p[13]',
+            '/html/body/p[14]',
+            ]
+
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"include_filters": '\n'.join(filters),
+            "url": test_url,
+            "tags": "test-tag-keep-order",
+            "headers": "",
+            'fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert b"And 1 this" in res.data  # test-tag-keep-order
+
+    a_tag_filter_check = b'And 1 this' #'#only-this' of tag_filters
+    # check there is no duplication of tag_filters
+    assert res.data.count(a_tag_filter_check) == 1, f"duplicated filters didn't removed {res.data.count(a_tag_filter_check)} of {a_tag_filter_check} in {res.data=}"
+
+    a_filter_check = b"And 13 this" # '/html/body/p[13]'
+    # check there is no duplication of filters
+    assert res.data.count(a_filter_check) == 1, f"duplicated filters didn't removed. {res.data.count(a_filter_check)} of {a_filter_check} in {res.data=}"
+
+    a_filter_check_not_include = b"And 2 this" # '/html/body/p[2]'
+    assert a_filter_check_not_include not in res.data
+
+    checklist = [
+            b"And 3 this",
+            b"And 4 this",
+            b"And 5 this",
+            b"And 6 this",
+            b"And 7 this",
+            b"And 8 this",
+            b"And 9 this",
+            b"And 10 this",
+            b"And 11 this",
+            b"And 12 this",
+            b"And 13 this",
+            b"And 14 this",
+            b"And 1 this", # result of filter from tag.
+            ]
+    # check whether everything a user requested is there
+    for test in checklist:
+        assert test in res.data
+
+    # check whether everything a user requested is in order of filters.
+    n = 0
+    for test in checklist:
+        t_index = res.data[n:].find(test)
+        # if the text is not searched, return -1.
+        assert t_index >= 0, f"""failed because {test=} not in {res.data[n:]=}
+#####################
+Looks like some feature changed the order of result of filters.
+#####################
+the {test} appeared before. {test in res.data[:n]=}
+{res.data[:n]=}
+        """
+        n += t_index + len(test)
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_jsonpath_jq_selector.py

@@ -456,7 +456,7 @@ def test_ignore_json_order(client, live_server):
 
 def test_correct_header_detect(client, live_server):
     # Like in https://github.com/dgtlmoon/changedetection.io/pull/1593
-    # Specify extra html that JSON is sometimes wrapped in - when using Browserless/Puppeteer etc
+    # Specify extra html that JSON is sometimes wrapped in - when using SockpuppetBrowser / Puppeteer / Playwrightetc
     with open("test-datastore/endpoint-content.txt", "w") as f:
         f.write('<html><body>{"hello" : 123, "world": 123}')
 

changedetectionio/tests/test_pdf.py

@@ -29,7 +29,8 @@ def test_fetch_pdf(client, live_server):
         follow_redirects=True
     )
 
-    assert b'PDF-1.5' not in res.data
+    # PDF header should not be there (it was converted to text)
+    assert b'PDF' not in res.data[:10]
     assert b'hello world' in res.data
 
     # So we know if the file changes in other ways

changedetectionio/tests/test_request.py

@@ -10,11 +10,11 @@ def test_setup(live_server):
 # Hard to just add more live server URLs when one test is already running (I think)
 # So we add our test here (was in a different file)
 def test_headers_in_request(client, live_server):
-    #live_server_setup(live_server)
+    #ve_server_setup(live_server)
     # Add our URL to the import page
     test_url = url_for('test_headers', _external=True)
     if os.getenv('PLAYWRIGHT_DRIVER_URL'):
-        # Because its no longer calling back to localhost but from browserless, set in test-only.yml
+        # Because its no longer calling back to localhost but from the browser container, set in test-only.yml
         test_url = test_url.replace('localhost', 'changedet')
 
     # Add the test URL twice, we will check
@@ -70,16 +70,17 @@ def test_headers_in_request(client, live_server):
 
     wait_for_all_checks(client)
 
-    # Re #137 -  Examine the JSON index file, it should have only one set of headers entered
+    # Re #137 -  It should have only one set of headers entered
     watches_with_headers = 0
-    with open('test-datastore/url-watches.json') as f:
+    for k, watch in client.application.config.get('DATASTORE').data.get('watching').items():
-        app_struct = json.load(f)
+            if (len(watch['headers'])):
-        for uuid in app_struct['watching']:
-            if (len(app_struct['watching'][uuid]['headers'])):
                 watches_with_headers += 1
+    assert watches_with_headers == 1
+
+    # 'server' http header was automatically recorded
+    for k, watch in client.application.config.get('DATASTORE').data.get('watching').items():
+        assert 'custom' in watch.get('remote_server_reply') # added in util.py
 
-    # Should be only one with headers set
-    assert watches_with_headers==1
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
@@ -88,7 +89,7 @@ def test_body_in_request(client, live_server):
     # Add our URL to the import page
     test_url = url_for('test_body', _external=True)
     if os.getenv('PLAYWRIGHT_DRIVER_URL'):
-        # Because its no longer calling back to localhost but from browserless, set in test-only.yml
+        # Because its no longer calling back to localhost but from the browser container, set in test-only.yml
         test_url = test_url.replace('localhost', 'cdio')
 
     res = client.post(
@@ -180,7 +181,7 @@ def test_method_in_request(client, live_server):
     # Add our URL to the import page
     test_url = url_for('test_method', _external=True)
     if os.getenv('PLAYWRIGHT_DRIVER_URL'):
-        # Because its no longer calling back to localhost but from browserless, set in test-only.yml
+        # Because its no longer calling back to localhost but from the browser container, set in test-only.yml
         test_url = test_url.replace('localhost', 'cdio')
 
     # Add the test URL twice, we will check
@@ -257,7 +258,7 @@ def test_headers_textfile_in_request(client, live_server):
     # Add our URL to the import page
     test_url = url_for('test_headers', _external=True)
     if os.getenv('PLAYWRIGHT_DRIVER_URL'):
-        # Because its no longer calling back to localhost but from browserless, set in test-only.yml
+        # Because its no longer calling back to localhost but from the browser container, set in test-only.yml
         test_url = test_url.replace('localhost', 'cdio')
 
     print ("TEST URL IS ",test_url)

changedetectionio/tests/test_unique_lines.py

@@ -2,7 +2,7 @@
 
 import time
 from flask import url_for
-from .util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
 
 
 def set_original_ignore_response():
@@ -34,6 +34,23 @@ def set_modified_swapped_lines():
     with open("test-datastore/endpoint-content.txt", "w") as f:
         f.write(test_return_data)
 
+def set_modified_swapped_lines_with_extra_text_for_sorting():
+    test_return_data = """<html>
+     <body>
+     <p>&nbsp;Which is across multiple lines</p>     
+     <p>Some initial text</p>
+     <p>   So let's see what happens.</p>
+     <p>Z last</p>
+     <p>0 numerical</p>
+     <p>A uppercase</p>
+     <p>a lowercase</p>     
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
 
 def set_modified_with_trigger_text_response():
     test_return_data = """<html>
@@ -49,15 +66,14 @@ def set_modified_with_trigger_text_response():
     with open("test-datastore/endpoint-content.txt", "w") as f:
         f.write(test_return_data)
 
-
+def test_setup(client, live_server):
-def test_unique_lines_functionality(client, live_server):
     live_server_setup(live_server)
 
-    sleep_time_for_fetch_thread = 3
+def test_unique_lines_functionality(client, live_server):
+    #live_server_setup(live_server)
+
 
     set_original_ignore_response()
-    # Give the endpoint time to spin up
-    time.sleep(1)
 
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
@@ -67,7 +83,7 @@ def test_unique_lines_functionality(client, live_server):
         follow_redirects=True
     )
     assert b"1 Imported" in res.data
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # Add our URL to the import page
     res = client.post(
@@ -83,12 +99,11 @@ def test_unique_lines_functionality(client, live_server):
     #  Make a change
     set_modified_swapped_lines()
 
-    time.sleep(sleep_time_for_fetch_thread)
     # Trigger a check
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
     # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # It should report nothing found (no new 'unviewed' class)
     res = client.get(url_for("index"))
@@ -97,7 +112,57 @@ def test_unique_lines_functionality(client, live_server):
     # Now set the content which contains the new text and re-ordered existing text
     set_modified_with_trigger_text_response()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
     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_sort_lines_functionality(client, live_server):
+    #live_server_setup(live_server)
+
+    set_modified_swapped_lines_with_extra_text_for_sorting()
+
+    # 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
+    wait_for_all_checks(client)
+
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"sort_text_alphabetically": "n",
+              "url": test_url,
+              "fetch_backend": "html_requests"},
+        follow_redirects=True
+    )
+    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
+    wait_for_all_checks(client)
+
+
+    res = client.get(url_for("index"))
+    # Should be a change registered
+    assert b'unviewed' in res.data
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert res.data.find(b'0 numerical') < res.data.find(b'Z last')
+    assert res.data.find(b'A uppercase') < res.data.find(b'Z last')
+    assert res.data.find(b'Some initial text') < res.data.find(b'Which is across multiple lines')
+    
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/util.py

@@ -175,12 +175,16 @@ def live_server_setup(live_server):
     @live_server.app.route('/test-headers')
     def test_headers():
 
-        output= []
+        output = []
 
         for header in request.headers:
-             output.append("{}:{}".format(str(header[0]),str(header[1])   ))
+            output.append("{}:{}".format(str(header[0]), str(header[1])))
 
-        return "\n".join(output)
+        content = "\n".join(output)
+
+        resp = make_response(content, 200)
+        resp.headers['server'] = 'custom'
+        return resp
 
     # Just return the body in the request
     @live_server.app.route('/test-body', methods=['POST', 'GET'])
@@ -238,5 +242,28 @@ def live_server_setup(live_server):
             resp.headers['Content-Type'] = 'application/pdf'
             return resp
 
+    @live_server.app.route('/test-interactive-html-endpoint')
+    def test_interactive_html_endpoint():
+        header_text=""
+        for k,v in request.headers.items():
+            header_text += f"{k}: {v}<br>"
+
+        resp = make_response(f"""
+        <html>
+          <body>
+          Primitive JS check for <pre>changedetectionio/tests/visualselector/test_fetch_data.py</pre>
+            <p id="remove">This text should be removed</p>
+              <form onsubmit="event.preventDefault();">
+            <!-- obfuscated text so that we dont accidentally get a false positive due to conversion of the source :) --->
+                <button name="test-button" onclick="getElementById('remove').remove();getElementById('some-content').innerHTML = atob('SSBzbWVsbCBKYXZhU2NyaXB0IGJlY2F1c2UgdGhlIGJ1dHRvbiB3YXMgcHJlc3NlZCE=')">Click here</button>
+                <div id=some-content></div>
+                <pre>
+                {header_text.lower()}
+                </pre>
+              </body>
+         </html>""", 200)
+        resp.headers['Content-Type'] = 'text/html'
+        return resp
+
     live_server.start()
 

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -1,6 +1,5 @@
 #!/usr/bin/python3
 
-import time
 import os
 from flask import url_for
 from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
@@ -8,15 +7,19 @@ from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_cli
 def test_setup(client, live_server):
     live_server_setup(live_server)
 
+
 # Add a site in paused mode, add an invalid filter, we should still have visual selector data ready
 def test_visual_selector_content_ready(client, live_server):
+
     import os
     import json
 
     assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
 
     # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
-    test_url = "https://changedetection.io/ci-test/test-runjs.html"
+    test_url = url_for('test_interactive_html_endpoint', _external=True)
+    test_url = test_url.replace('localhost.localdomain', 'cdio')
+    test_url = test_url.replace('localhost', 'cdio')
 
     res = client.post(
         url_for("form_quick_watch_add"),
@@ -24,28 +27,31 @@ def test_visual_selector_content_ready(client, live_server):
         follow_redirects=True
     )
     assert b"Watch added in Paused state, saving will unpause" in res.data
-
+    uuid = extract_UUID_from_client(client)
     res = client.post(
-        url_for("edit_page", uuid="first", unpause_on_save=1),
+        url_for("edit_page", uuid=uuid, unpause_on_save=1),
         data={
-              "url": test_url,
+            "url": test_url,
-              "tags": "",
+            "tags": "",
-              "headers": "",
+            # For now, cookies doesnt work in headers because it must be a full cookiejar object
-              'fetch_backend': "html_webdriver",
+            'headers': "testheader: yes\buser-agent: MyCustomAgent",
-              'webdriver_js_execute_code': 'document.querySelector("button[name=test-button]").click();'
+            'fetch_backend': "html_webdriver",
         },
         follow_redirects=True
     )
     assert b"unpaused" in res.data
     wait_for_all_checks(client)
-    uuid = extract_UUID_from_client(client)
 
-    # Check the JS execute code before extract worked
+
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n >= 1, "Watch history had atleast 1 (everything fetched OK)"
+
     res = client.get(
-        url_for("preview_page", uuid="first"),
+        url_for("preview_page", uuid=uuid),
         follow_redirects=True
     )
-    assert b'I smell JavaScript' in res.data
+    assert b"testheader: yes" in res.data
+    assert b"user-agent: mycustomagent" in res.data
+
 
     assert os.path.isfile(os.path.join('test-datastore', uuid, 'last-screenshot.png')), "last-screenshot.png should exist"
     assert os.path.isfile(os.path.join('test-datastore', uuid, 'elements.json')), "xpath elements.json data should exist"
@@ -75,30 +81,33 @@ def test_visual_selector_content_ready(client, live_server):
 
 def test_basic_browserstep(client, live_server):
 
-    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
     #live_server_setup(live_server)
+    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
 
-    # 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_interactive_html_endpoint', _external=True)
-    test_url = "https://changedetection.io/ci-test/test-runjs.html"
+    test_url = test_url.replace('localhost.localdomain', 'cdio')
+    test_url = test_url.replace('localhost', 'cdio')
 
     res = client.post(
         url_for("form_quick_watch_add"),
         data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
         follow_redirects=True
     )
+
     assert b"Watch added in Paused state, saving will unpause" in res.data
 
     res = client.post(
         url_for("edit_page", uuid="first", unpause_on_save=1),
         data={
-              "url": test_url,
+            "url": test_url,
-              "tags": "",
+            "tags": "",
-              "headers": "",
+            'fetch_backend': "html_webdriver",
-              'fetch_backend': "html_webdriver",
+            'browser_steps-0-operation': 'Goto site',
-              'browser_steps-0-operation': 'Goto site',
+            'browser_steps-1-operation': 'Click element',
-              'browser_steps-1-operation': 'Click element',
+            'browser_steps-1-selector': 'button[name=test-button]',
-              'browser_steps-1-selector': 'button[name=test-button]',
+            'browser_steps-1-optional_value': '',
-              'browser_steps-1-optional_value': ''
+            # For now, cookies doesnt work in headers because it must be a full cookiejar object
+            'headers': "testheader: yes\buser-agent: MyCustomAgent",
         },
         follow_redirects=True
     )
@@ -106,6 +115,9 @@ def test_basic_browserstep(client, live_server):
     wait_for_all_checks(client)
 
     uuid = extract_UUID_from_client(client)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n >= 1, "Watch history had atleast 1 (everything fetched OK)"
+
+    assert b"This text should be removed" not in res.data
 
     # Check HTML conversion detected and workd
     res = client.get(
@@ -115,13 +127,19 @@ def test_basic_browserstep(client, live_server):
     assert b"This text should be removed" not in res.data
     assert b"I smell JavaScript because the button was pressed" in res.data
 
+    assert b"testheader: yes" in res.data
+    assert b"user-agent: mycustomagent" in res.data
+
+    four_o_four_url =  url_for('test_endpoint', status_code=404, _external=True)
+    four_o_four_url = four_o_four_url.replace('localhost.localdomain', 'cdio')
+    four_o_four_url = four_o_four_url.replace('localhost', 'cdio')
+
     # now test for 404 errors
     res = client.post(
         url_for("edit_page", uuid=uuid, unpause_on_save=1),
         data={
-              "url": "https://changedetection.io/404",
+              "url": four_o_four_url,
               "tags": "",
-              "headers": "",
               'fetch_backend': "html_webdriver",
               'browser_steps-0-operation': 'Goto site',
               'browser_steps-1-operation': 'Click element',

changedetectionio/update_worker.py

@@ -2,8 +2,8 @@ import os
 import threading
 import queue
 import time
-
+from . import content_fetchers
-from changedetectionio import content_fetcher, html_tools
+from changedetectionio import html_tools
 from .processors.text_json_diff import FilterNotFoundInResponse
 from .processors.restock_diff import UnableToExtractRestockData
 
@@ -150,6 +150,10 @@ class update_worker(threading.Thread):
         queued = False
         if n_object and n_object.get('notification_urls'):
             queued = True
+
+            count = watch.get('notification_alert_count', 0) + 1
+            self.datastore.update_watch(uuid=watch_uuid, update_obj={'notification_alert_count': count})
+
             self.queue_notification_for_watch(notification_q=self.notification_q, n_object=n_object, watch=watch)
 
         return queued
@@ -286,7 +290,7 @@ class update_worker(threading.Thread):
                         logger.critical(f"File permission error updating file, watch: {uuid}")
                         logger.critical(str(e))
                         process_changedetection_results = False
-                    except content_fetcher.ReplyWithContentButNoText as e:
+                    except content_fetchers.exceptions.ReplyWithContentButNoText as e:
                         # Totally fine, it's by choice - just continue on, nothing more to care about
                         # Page had elements/content but no renderable text
                         # Backend (not filters) gave zero output
@@ -308,13 +312,15 @@ class update_worker(threading.Thread):
                             self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot)
                         process_changedetection_results = False
 
-                    except content_fetcher.Non200ErrorCodeReceived as e:
+                    except content_fetchers.exceptions.Non200ErrorCodeReceived as e:
                         if e.status_code == 403:
                             err_text = "Error - 403 (Access denied) received"
                         elif e.status_code == 404:
                             err_text = "Error - 404 (Page not found) received"
+                        elif e.status_code == 407:
+                            err_text = "Error - 407 (Proxy authentication required) received, did you need a username and password for the proxy?"
                         elif e.status_code == 500:
-                            err_text = "Error - 500 (Internal server Error) received"
+                            err_text = "Error - 500 (Internal server error) received from the web site"
                         else:
                             err_text = "Error - Request returned a HTTP error code {}".format(str(e.status_code))
 
@@ -352,13 +358,24 @@ class update_worker(threading.Thread):
 
                         process_changedetection_results = False
 
-                    except content_fetcher.checksumFromPreviousCheckWasTheSame as e:
+                    except content_fetchers.exceptions.checksumFromPreviousCheckWasTheSame as e:
                         # Yes fine, so nothing todo, don't continue to process.
                         process_changedetection_results = False
                         changed_detected = False
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': False})
-
+                    except content_fetchers.exceptions.BrowserConnectError as e:
-                    except content_fetcher.BrowserStepsStepException as e:
+                        self.datastore.update_watch(uuid=uuid,
+                                                    update_obj={'last_error': e.msg
+                                                                }
+                                                    )
+                        process_changedetection_results = False
+                    except content_fetchers.exceptions.BrowserFetchTimedOut as e:
+                        self.datastore.update_watch(uuid=uuid,
+                                                    update_obj={'last_error': e.msg
+                                                                }
+                                                    )
+                        process_changedetection_results = False
+                    except content_fetchers.exceptions.BrowserStepsStepException as e:
 
                         if not self.datastore.data['watching'].get(uuid):
                             continue
@@ -400,25 +417,25 @@ class update_worker(threading.Thread):
 
                         process_changedetection_results = False
 
-                    except content_fetcher.EmptyReply as e:
+                    except content_fetchers.exceptions.EmptyReply as e:
                         # Some kind of custom to-str handler in the exception handler that does this?
                         err_text = "EmptyReply - try increasing 'Wait seconds before extracting text', Status Code {}".format(e.status_code)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetcher.ScreenshotUnavailable as e:
+                    except content_fetchers.exceptions.ScreenshotUnavailable as e:
-                        err_text = "Screenshot unavailable, page did not render fully in the expected time - try increasing 'Wait seconds before extracting text'"
+                        err_text = "Screenshot unavailable, page did not render fully in the expected time or page was too long - try increasing 'Wait seconds before extracting text'"
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetcher.JSActionExceptions as e:
+                    except content_fetchers.exceptions.JSActionExceptions as e:
                         err_text = "Error running JS Actions - Page request - "+e.message
                         if e.screenshot:
                             self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot, as_error=True)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
-                    except content_fetcher.PageUnloadable as e:
+                    except content_fetchers.exceptions.PageUnloadable as e:
                         err_text = "Page request from server didnt respond correctly"
                         if e.message:
                             err_text = "{} - {}".format(err_text, e.message)
@@ -430,6 +447,12 @@ class update_worker(threading.Thread):
                                                                            'last_check_status': e.status_code,
                                                                            'has_ldjson_price_data': None})
                         process_changedetection_results = False
+                    except content_fetchers.exceptions.BrowserStepsInUnsupportedFetcher as e:
+                        err_text = "This watch has Browser Steps configured and so it cannot run with the 'Basic fast Plaintext/HTTP Client', either remove the Browser Steps or select a Chrome fetcher."
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
+                        process_changedetection_results = False
+                        logger.error(f"Exception (BrowserStepsInUnsupportedFetcher) reached processing watch UUID: {uuid}")
+
                     except UnableToExtractRestockData as e:
                         # Usually when fetcher.instock_data returns empty
                         logger.error(f"Exception (UnableToExtractRestockData) reached processing watch UUID: {uuid}")
@@ -491,6 +514,16 @@ class update_worker(threading.Thread):
                     if self.datastore.data['watching'].get(uuid):
                         # Always record that we atleast tried
                         count = self.datastore.data['watching'][uuid].get('check_count', 0) + 1
+
+                        # Record the 'server' header reply, can be used for actions in the future like cloudflare/akamai workarounds
+                        try:
+                            server_header = update_handler.fetcher.headers.get('server', '').strip().lower()[:255]
+                            self.datastore.update_watch(uuid=uuid,
+                                                        update_obj={'remote_server_reply': server_header}
+                                                        )
+                        except Exception as e:
+                            pass
+
                         self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
                                                                            'last_checked': round(time.time()),
                                                                            'check_count': count

docker-compose.yml

@@ -30,7 +30,7 @@ services:
   #             https://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.common.proxy
   #
   #       Alternative Playwright URL, do not use "'s or 's!
-  #      - PLAYWRIGHT_DRIVER_URL=ws://playwright-chrome:3000/?stealth=1&--disable-web-security=true
+  #      - PLAYWRIGHT_DRIVER_URL=ws://playwright-chrome:3000
   #
   #       Playwright proxy settings playwright_proxy_server, playwright_proxy_bypass, playwright_proxy_username, playwright_proxy_password
   #
@@ -71,31 +71,23 @@ services:
 #            condition: service_started
 
      # Used for fetching pages via Playwright+Chrome where you need Javascript support.
-     # Note: Playwright/browserless not supported on ARM type devices (rPi etc)
      # RECOMMENDED FOR FETCHING PAGES WITH CHROME
 #    playwright-chrome:
 #        hostname: playwright-chrome
-#        image: browserless/chrome:1.60-chrome-stable
+#        image: dgtlmoon/sockpuppetbrowser:latest
+#        cap_add:
+#            - SYS_ADMIN
+## SYS_ADMIN might be too much, but it can be needed on your platform https://github.com/puppeteer/puppeteer/blob/main/docs/troubleshooting.md#running-puppeteer-on-gitlabci
 #        restart: unless-stopped
 #        environment:
 #            - SCREEN_WIDTH=1920
 #            - SCREEN_HEIGHT=1024
 #            - SCREEN_DEPTH=16
-#            - ENABLE_DEBUGGER=false
+#            - MAX_CONCURRENT_CHROME_PROCESSES=10
-#            - PREBOOT_CHROME=true
-#            - CONNECTION_TIMEOUT=300000
-#            - MAX_CONCURRENT_SESSIONS=10
-#            - CHROME_REFRESH_TIME=600000
-#            - DEFAULT_BLOCK_ADS=true
-#            - DEFAULT_STEALTH=true
-#
-#             Ignore HTTPS errors, like for self-signed certs
-#            - DEFAULT_IGNORE_HTTPS_ERRORS=true
-#
 
      # Used for fetching pages via Playwright+Chrome where you need Javascript support.
-     # Note: works well but is deprecated, does not fetch full page screenshots (doesnt work with Visual Selector) and other issues
+     # Note: Works well but is deprecated, does not fetch full page screenshots (doesnt work with Visual Selector)
-     # More information about the advantages of playwright/browserless https://www.browserless.io/blog/2023/12/13/migrating-selenium-to-playwright/
+     #       Does not report status codes (200, 404, 403) and other issues
 #    browser-chrome:
 #        hostname: browser-chrome
 #        image: selenium/standalone-chrome:4

requirements.txt

@@ -1,4 +1,10 @@
-eventlet>=0.33.3 # related to dnspython fixes
+# Used by Pyppeteer
+pyee
+
+# eventlet 0.33.3 was related to dnspython fixes
+# 0.34.1 - fixes python 3.12 "AttributeError: module 'ssl' has no attribute 'wrap_socket'"
+eventlet==0.34.1
+
 feedgen~=0.9
 flask-compress
 # 0.6.3 included compatibility fix for werkzeug 3.x (2.x had deprecation of url handlers)
@@ -6,6 +12,7 @@ flask-login>=0.6.3
 flask-paginate
 flask_expects_json~=1.7
 flask_restful
+flask_cors # For the Chrome extension to operate
 flask_wtf~=1.2
 flask~=2.3
 inscriptis~=2.2
@@ -19,21 +26,25 @@ validators~=0.21
 brotli~=1.0
 requests[socks]
 
-urllib3>1.26
+urllib3==1.26.18
 chardet>2.3.0
 
 wtforms~=3.0
 jsonpath-ng~=1.5.3
 
-dnspython~=2.4 # related to eventlet fixes
+# Pinned: module 'eventlet.green.select' has no attribute 'epoll'
+# https://github.com/eventlet/eventlet/issues/805#issuecomment-1640463482
+dnspython==2.6.1 # related to eventlet fixes
 
 # jq not available on Windows so must be installed manually
 
 # Notification library
-apprise~=1.7.1
+apprise~=1.7.4
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
-paho-mqtt
+# and 2.0.0 https://github.com/dgtlmoon/changedetection.io/issues/2241 not yet compatible
+# use v1.x due to https://github.com/eclipse/paho.mqtt.python/issues/814
+paho-mqtt < 2.0.0
 
 # This mainly affects some ARM builds, which unlike the other builds ignores "ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1"
 # so without this pinning, the newer versions on ARM will forcefully try to build rust, which results in "rust compiler not found"
@@ -46,8 +57,8 @@ beautifulsoup4
 # XPath filtering, lxml is required by bs4 anyway, but put it here to be safe.
 lxml
 
-# XPath 2.0-3.1 support
+# XPath 2.0-3.1 support - 4.2.0 broke something?
-elementpath
+elementpath==4.1.5
 
 selenium~=4.14.0
 
@@ -66,6 +77,9 @@ jq~=1.3; python_version >= "3.8" and sys_platform == "linux"
 pillow
 # playwright is installed at Dockerfile build time because it's not available on all platforms
 
+# experimental release
+pyppeteer-ng==2.0.0rc5
+
 # Include pytest, so if theres a support issue we can ask them to run these tests on their setup
 pytest ~=7.2
 pytest-flask ~=1.2