Fixes for status code and screenshot info

Added `prodotto esaurito` - Italian for out of stock

.github/dependabot.yml

@@ -0,0 +1,10 @@
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: "weekly"
+    groups:
+      all:
+        patterns:
+        - "*"

.github/workflows/codeql-analysis.yml

@@ -34,7 +34,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v2
+      uses: github/codeql-action/init@v3
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -45,7 +45,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v2
+      uses: github/codeql-action/autobuild@v3
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -59,4 +59,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v2
+      uses: github/codeql-action/analyze@v3

.github/workflows/containers.yml

@@ -41,7 +41,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Set up Python 3.11
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: 3.11
 

.github/workflows/pypi-release.yml

@@ -9,7 +9,7 @@ jobs:
     steps:
     - uses: actions/checkout@v4
     - name: Set up Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: "3.x"
     - name: Install pypa/build
@@ -21,7 +21,7 @@ jobs:
     - name: Build a binary wheel and a source tarball
       run: python3 -m build
     - name: Store the distribution packages
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       with:
         name: python-package-distributions
         path: dist/
@@ -34,18 +34,18 @@ jobs:
     - build
     steps:
     - name: Download all the dists
-      uses: actions/download-artifact@v3
+      uses: actions/download-artifact@v4
       with:
         name: python-package-distributions
         path: dist/
     - name: Test that the basic pip built package runs without error
       run: |
-        set -e
+        set -ex
         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
 
 
@@ -64,7 +64,7 @@ jobs:
 
     steps:
     - name: Download all the dists
-      uses: actions/download-artifact@v3
+      uses: actions/download-artifact@v4
       with:
         name: python-package-distributions
         path: dist/

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

@@ -26,7 +26,7 @@ jobs:
     steps:
         - uses: actions/checkout@v4
         - name: Set up Python 3.11
-          uses: actions/setup-python@v4
+          uses: actions/setup-python@v5
           with:
             python-version: 3.11
 

.github/workflows/test-only.yml

@@ -11,7 +11,7 @@ jobs:
 
       # Mainly just for link/flake8
       - name: Set up Python 3.11
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: '3.11'
 
@@ -27,13 +27,13 @@ jobs:
         run: |
           
           docker network create changedet-network
-
+          
-          # Selenium+browserless
+          # Selenium and sockpuppetbrowser
           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
+          docker run --network changedet-network -d --cap-add=SYS_ADMIN --name sockpuppetbrowser --hostname sockpuppetbrowser --rm -p 3000:3000 dgtlmoon/sockpuppetbrowser:latest
           
           # For accessing custom browser tests
-          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 --cap-add=SYS_ADMIN --name sockpuppetbrowser-custom-url --hostname sockpuppetbrowser-custom-url --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"
@@ -61,33 +67,35 @@ jobs:
           # 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'
 
-      - name: Test built container selenium+browserless/playwright
+      - 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 Playwright and SocketPuppetBrowser
-          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: |
-          
+          # Playwright via Sockpuppetbrowser fetch
-          # Settings headers playwright tests - Call back in from Browserless, check headers
+          docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser: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'
-          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'
+
+      - name: Specific tests in built container for headers and requests checks with Playwright
+        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: Specific tests in built container for headers and requests checks with Selenium
+        run: |
           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'          
+
-          
+      - name: Test built container restock detection via Playwright
-          # restock detection via playwright - added name=changedet here so that playwright/browserless can connect to it
+        run: |                            
-          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'
+          # 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'
 
       - 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
-        run: |
-          docker run --rm -e "PUPPETEER_DISK_CACHE=/tmp/data/" -e "USE_EXPERIMENTAL_PUPPETEER_FETCH=yes" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
-          # Browserless would have had -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" added above
-
       - name: Test proxy interaction
         run: |
           cd changedetectionio
@@ -106,10 +114,10 @@ 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

README.md

@@ -273,3 +273,9 @@ I offer commercial support, this software is depended on by network security, ae
 ## Third-party licenses
 
 changedetectionio.html_tools.elementpath_tostring: Copyright (c), 2018-2021, SISSA (Scuola Internazionale Superiore di Studi Avanzati), Licensed under [MIT license](https://github.com/sissaschool/elementpath/blob/master/LICENSE)
+
+## Contributors
+
+Recognition of fantastic contributors to the project
+
+- Constantin Hong https://github.com/Constantin1489

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.45.12'
+__version__ = '0.45.14'
 
 from distutils.util import strtobool
 from json.decoder import JSONDecodeError
@@ -60,7 +60,7 @@ def main():
     try:
         opts, args = getopt.getopt(sys.argv[1:], "6Ccsd:h:p:l:", "port")
     except getopt.GetoptError:
-        print('backend.py -s SSL enable -h [host] -p [port] -d [datastore path] -l [debug level]')
+        print('backend.py -s SSL enable -h [host] -p [port] -d [datastore path] -l [debug level - TRACE, DEBUG(default), INFO, SUCCESS, WARNING, ERROR, CRITICAL]')
         sys.exit(2)
 
     create_datastore_dir = False

changedetectionio/api/api_v1.py

@@ -133,6 +133,7 @@ class WatchHistory(Resource):
 
     # Get a list of available history for a watch by UUID
     # curl http://localhost:5000/api/v1/watch/<string:uuid>/history
+    @auth.check_token
     def get(self, uuid):
         """
         @api {get} /api/v1/watch/<string:uuid>/history Get a list of all historical snapshots available for a watch

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

@@ -169,7 +169,7 @@ 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

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/content_fetcher.py

@@ -51,8 +51,9 @@ class BrowserStepsStepException(Exception):
         return
 
 
+# @todo - make base Exception class that announces via logger()
 class PageUnloadable(Exception):
-    def __init__(self, status_code, url, message, screenshot=False):
+    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
@@ -60,6 +61,10 @@ class PageUnloadable(Exception):
         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):
@@ -306,117 +311,6 @@ class base_html_playwright(Fetcher):
         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,
@@ -428,21 +322,6 @@ class base_html_playwright(Fetcher):
             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
 
@@ -511,8 +390,15 @@ class base_html_playwright(Fetcher):
             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
+                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:
 
@@ -552,16 +438,17 @@ class base_html_playwright(Fetcher):
             # 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
+                # The actual screenshot - this always base64 and needs decoding! horrible! huge CPU usage
-                self.screenshot = self.page.screenshot(type='jpeg', full_page=True,
+                self.screenshot = self.page.screenshot(type='jpeg',
-                                                       quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+                                                       full_page=True,
+                                                       quality=int(os.getenv("PLAYWRIGHT_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()
-                raise ScreenshotUnavailable(url=url, status_code=response.status_code)
-
-            context.close()
-            browser.close()
 
 
 class base_html_webdriver(Fetcher):
@@ -698,6 +585,9 @@ class html_requests(Fetcher):
             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",
@@ -737,6 +627,8 @@ class html_requests(Fetcher):
                 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)
 
@@ -753,7 +645,7 @@ class html_requests(Fetcher):
         else:
             self.content = r.text
 
-        self.headers = r.headers
+
         self.raw_content = r.content
 
 

changedetectionio/flask_app.py

@@ -13,7 +13,6 @@ from threading import Event
 import datetime
 import flask_login
 from loguru import logger
-import sys
 import os
 import pytz
 import queue
@@ -317,6 +316,9 @@ 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 +382,12 @@ 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 +396,7 @@ 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'])
@@ -1603,7 +1610,7 @@ def notification_runner():
                     n_object['notification_title'] = datastore.data['settings']['application'].get('notification_title')
 
                 if not n_object.get('notification_format') and datastore.data['settings']['application'].get('notification_format'):
-                    n_object['notification_title'] = datastore.data['settings']['application'].get('notification_format')
+                    n_object['notification_format'] = datastore.data['settings']['application'].get('notification_format')
 
                 sent_obj = notification.process_notification(n_object, datastore)
 

changedetectionio/forms.py

@@ -465,6 +465,7 @@ 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)

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
@@ -211,7 +214,7 @@ class model(dict):
         # Read the history file as a dict
         fname = os.path.join(self.watch_data_dir, "history.txt")
         if os.path.isfile(fname):
-            logger.debug("Reading watch history index")
+            logger.debug(f"Reading watch history index for {self.get('uuid')}")
             with open(fname, "r") as f:
                 for i in f.readlines():
                     if ',' in i:
@@ -246,10 +249,10 @@ class model(dict):
     @property
     def has_browser_steps(self):
         has_browser_steps = self.get('browser_steps') and list(filter(
-                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+            lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
-                self.get('browser_steps')))
+            self.get('browser_steps')))
 
-        return  has_browser_steps
+        return has_browser_steps
 
     # Returns the newest key, but if theres only 1 record, then it's counted as not being new, so return 0.
     @property

changedetectionio/notification.py

@@ -116,6 +116,9 @@ def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
 
 def process_notification(n_object, datastore):
 
+    now = time.time()
+    if n_object.get('notification_timestamp'):
+        logger.trace(f"Time since queued {now-n_object['notification_timestamp']:.3f}s")
     # Insert variables into the notification content
     notification_parameters = create_notification_parameters(n_object, datastore)
 
@@ -133,6 +136,8 @@ def process_notification(n_object, datastore):
         # Initially text or whatever
         n_format = datastore.data['settings']['application'].get('notification_format', valid_notification_formats[default_notification_format])
 
+    logger.trace(f"Complete notification body including Jinja and placeholders calculated in  {time.time() - now:.3f}s")
+
     # https://github.com/caronc/apprise/wiki/Development_LogCapture
     # Anything higher than or equal to WARNING (which covers things like Connection errors)
     # raise it as an exception
@@ -147,6 +152,10 @@ def process_notification(n_object, datastore):
     with apprise.LogCapture(level=apprise.logging.DEBUG) as logs:
         for url in n_object['notification_urls']:
             url = url.strip()
+            if not url:
+                logger.warning(f"Process Notification: skipping empty notification URL.")
+                continue
+
             logger.info(">> Process Notification: AppRise notifying {}".format(url))
             url = jinja2_env.from_string(url).render(**notification_parameters)
 

changedetectionio/processors/__init__.py

@@ -70,7 +70,7 @@ class difference_detection_processor():
         proxy_url = None
         if preferred_proxy_id:
             proxy_url = self.datastore.proxy_list.get(preferred_proxy_id).get('url')
-            logger.debug(f"Using proxy Key: {preferred_proxy_id} as Proxy URL {proxy_url}")
+            logger.debug(f"Selected proxy key '{preferred_proxy_id}' as proxy URL '{proxy_url}' for {url}")
 
         # 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/restock_diff.py

@@ -1,8 +1,9 @@
 
-import hashlib
-import urllib3
 from . import difference_detection_processor
 from copy import deepcopy
+from loguru import logger
+import hashlib
+import urllib3
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
@@ -43,11 +44,13 @@ class perform_site_check(difference_detection_processor):
             fetched_md5 = hashlib.md5(self.fetcher.instock_data.encode('utf-8')).hexdigest()
             # 'Possibly in stock' comes from stock-not-in-stock.js when no string found above the fold.
             update_obj["in_stock"] = True if self.fetcher.instock_data == 'Possibly in stock' else False
+            logger.debug(f"Watch UUID {uuid} restock check returned '{self.fetcher.instock_data}' from JS scraper.")
         else:
             raise UnableToExtractRestockData(status_code=self.fetcher.status_code)
 
         # The main thing that all this at the moment comes down to :)
         changed_detected = False
+        logger.debug(f"Watch UUID {uuid} restock check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
 
         if watch.get('previous_md5') and watch.get('previous_md5') != fetched_md5:
             # Yes if we only care about it going to instock, AND we are in stock
@@ -60,5 +63,4 @@ class perform_site_check(difference_detection_processor):
 
         # Always record the new checksum
         update_obj["previous_md5"] = fetched_md5
-
         return changed_detected, update_obj, self.fetcher.instock_data.encode('utf-8').strip()

changedetectionio/processors/text_json_diff.py

@@ -6,11 +6,11 @@ import os
 import re
 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.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
 from copy import deepcopy
-from . import difference_detection_processor
-from ..html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text
 from loguru import logger
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
@@ -116,7 +116,9 @@ 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({*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 +204,12 @@ 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')
 
@@ -335,6 +343,8 @@ class perform_site_check(difference_detection_processor):
                 if not watch['title'] or not len(watch['title']):
                     update_obj['title'] = html_tools.extract_element(find='title', html_content=self.fetcher.content)
 
+        logger.debug(f"Watch UUID {uuid} content check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
+
         if changed_detected:
             if watch.get('check_unique_lines', False):
                 has_unique_lines = watch.lines_contain_something_unique_compared_to_history(lines=stripped_text_from_html.splitlines())

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

@@ -1,3 +1,10 @@
+// Restock Detector
+// (c) Leigh Morresi dgtlmoon@gmail.com
+//
+// Assumes the product is in stock to begin with, unless the following appears above the fold ;
+// - outOfStockTexts appears above the fold (out of stock)
+// - negateOutOfStockRegex (really is in stock)
+
 function isItemInStock() {
     // @todo Pass these in so the same list can be used in non-JS fetchers
     const outOfStockTexts = [
@@ -29,6 +36,7 @@ function isItemInStock() {
         'nicht zur verfügung',
         'niet beschikbaar',
         'niet leverbaar',
+        'niet op voorraad',
         'no disponible temporalmente',
         'no longer in stock',
         'no tickets available',
@@ -40,6 +48,7 @@ function isItemInStock() {
         'não estamos a aceitar encomendas',
         'out of stock',
         'out-of-stock',
+        'prodotto esaurito',
         'produkt niedostępny',
         'sold out',
         'sold-out',
@@ -56,6 +65,7 @@ function isItemInStock() {
         '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
@@ -66,19 +76,13 @@ function isItemInStock() {
         return text.toLowerCase().trim();
     }
 
-    const negateOutOfStockRegexs = [
+    const negateOutOfStockRegex = new RegExp('([0-9] in stock|add to cart)', 'ig');
-        '[0-9] in stock'
-    ]
-    var negateOutOfStockRegexs_r = [];
-    for (let i = 0; i < negateOutOfStockRegexs.length; i++) {
-        negateOutOfStockRegexs_r.push(new RegExp(negateOutOfStockRegexs[0], 'g'));
-    }
 
     // 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 <= window.innerHeight && element.getBoundingClientRect().top + window.scrollY >= 100);
+    const elementsToScan = Array.from(document.getElementsByTagName('*')).filter(element => element.getBoundingClientRect().top + window.scrollY <= vh && element.getBoundingClientRect().top + window.scrollY >= 100);
 
     var elementText = "";
 
@@ -94,10 +98,8 @@ function isItemInStock() {
 
         if (elementText.length) {
             // try which ones could mean its in stock
-            for (let i = 0; i < negateOutOfStockRegexs.length; i++) {
+            if (negateOutOfStockRegex.test(elementText)) {
-                if (negateOutOfStockRegexs_r[i].test(elementText)) {
+                return 'Possibly in stock';
-                    return 'Possibly in stock';
-                }
             }
         }
     }

changedetectionio/run_custom_browser_url_tests.sh

@@ -6,16 +6,16 @@
 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.txt
 grep 'custom-browser-search-string=1' log.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"
   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 +24,16 @@ 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.txt
 grep 'custom-browser-search-string=1' log.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"
   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

@@ -35,7 +35,7 @@ docker run --network changedet-network \
 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" \
+  -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" \
   --rm \
   test-changedetectionio \
   bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'

changedetectionio/static/images/steps.svg

@@ -0,0 +1,44 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   aria-hidden="true"
+   viewBox="0 0 19.966091 17.999964"
+   class="css-1oqmxjn"
+   version="1.1"
+   id="svg4"
+   sodipodi:docname="steps.svg"
+   width="19.966091"
+   height="17.999964"
+   inkscape:version="1.1.2 (0a00cf5339, 2022-02-04)"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg">
+  <defs
+     id="defs8" />
+  <sodipodi:namedview
+     id="namedview6"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageshadow="2"
+     inkscape:pageopacity="0.0"
+     inkscape:pagecheckerboard="0"
+     showgrid="false"
+     fit-margin-top="0"
+     fit-margin-left="0"
+     fit-margin-right="0"
+     fit-margin-bottom="0"
+     inkscape:zoom="8.6354167"
+     inkscape:cx="-1.3896261"
+     inkscape:cy="6.1375151"
+     inkscape:window-width="1280"
+     inkscape:window-height="667"
+     inkscape:window-x="2419"
+     inkscape:window-y="250"
+     inkscape:window-maximized="0"
+     inkscape:current-layer="svg4" />
+  <path
+     d="m 16.95807,12.000003 c -0.7076,0.0019 -1.3917,0.2538 -1.9316,0.7113 -0.5398,0.4575 -0.9005,1.091 -1.0184,1.7887 H 5.60804 c -0.80847,0.0297 -1.60693,-0.1865 -2.29,-0.62 -0.26632,-0.1847 -0.48375,-0.4315 -0.63356,-0.7189 -0.14982,-0.2874 -0.22753,-0.607 -0.22644,-0.9311 -0.02843,-0.3931 0.03646,-0.7873 0.1894,-1.1505 0.15293,-0.3632 0.38957,-0.6851 0.6906,-0.9395 0.66628,-0.4559004 1.4637,-0.6807004 2.27,-0.6400004 h 8.35003 c 0.8515,-0.0223 1.6727,-0.3206 2.34,-0.85 0.3971,-0.3622 0.7076,-0.8091 0.9084,-1.3077 0.2008,-0.49857 0.2868,-1.03596 0.2516,-1.57229 0.0113,-0.47161 -0.0887,-0.93924 -0.292,-1.36493 -0.2033,-0.4257 -0.5041,-0.79745 -0.878,-1.08507 -0.7801,-0.55815 -1.7212,-0.84609 -2.68,-0.82 H 5.95804 c -0.12537,-0.7417 -0.5248,-1.40924 -1.11913,-1.87032996 -0.59434,-0.46108 -1.3402,-0.68207 -2.08979,-0.61917 -0.74958,0.06291 -1.44818,0.40512 -1.95736,0.95881 C 0.28259,1.5230126 0,2.2477926 0,3.0000126 c 0,0.75222 0.28259,1.47699 0.79176,2.03068 0.50918,0.55369 1.20778,0.8959 1.95736,0.95881 0.74959,0.0629 1.49545,-0.15808 2.08979,-0.61917 0.59433,-0.46109 0.99376,-1.12863 1.11913,-1.87032 h 7.70003 c 0.7353,-0.03061 1.4599,0.18397 2.06,0.61 0.2548,0.19335 0.4595,0.445 0.597,0.73385 0.1375,0.28884 0.2036,0.60644 0.193,0.92615 0.0316,0.38842 -0.0247,0.77898 -0.165,1.14258 -0.1402,0.36361 -0.3607,0.69091 -0.645,0.95741 -0.5713,0.4398 -1.2799,0.663 -2,0.63 H 5.69804 c -1.03259,-0.0462 -2.05065,0.2568 -2.89,0.86 -0.43755,0.3361 -0.78838,0.7720004 -1.02322,1.2712004 -0.23484,0.4993 -0.34688,1.0474 -0.32678,1.5988 -0.00726,0.484 0.10591,0.9622 0.32934,1.3916 0.22344,0.4295 0.55012,0.7966 0.95066,1.0684 0.85039,0.5592 1.85274,0.8421 2.87,0.81 h 8.40003 c 0.0954,0.5643 0.3502,1.0896 0.7343,1.5138 0.3842,0.4242 0.8817,0.7297 1.4338,0.8803 0.5521,0.1507 1.1358,0.1403 1.6822,-0.0299 0.5464,-0.1702 1.0328,-0.4932 1.4016,-0.9308 0.3688,-0.4376 0.6048,-0.9716 0.6801,-1.5389 0.0752,-0.5673 -0.0134,-1.1444 -0.2554,-1.663 -0.242,-0.5186 -0.6273,-0.9572 -1.1104,-1.264 -0.4831,-0.3068 -1.0439,-0.469 -1.6162,-0.4675 z m 0,5 c -0.3956,0 -0.7823,-0.1173 -1.1112,-0.3371 -0.3289,-0.2197 -0.5852,-0.5321 -0.7366,-0.8975 -0.1514,-0.3655 -0.191,-0.7676 -0.1138,-1.1556 0.0772,-0.3879 0.2677,-0.7443 0.5474,-1.024 0.2797,-0.2797 0.636,-0.4702 1.024,-0.5474 0.388,-0.0771 0.7901,-0.0375 1.1555,0.1138 0.3655,0.1514 0.6778,0.4078 0.8976,0.7367 0.2198,0.3289 0.3371,0.7155 0.3371,1.1111 0,0.5304 -0.2107,1.0391 -0.5858,1.4142 -0.3751,0.3751 -0.8838,0.5858 -1.4142,0.5858 z"
+     id="path2"
+     style="fill:#777777;fill-opacity:1" />
+</svg>

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")
 
@@ -261,7 +261,7 @@ $(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/diff.css

@@ -126,6 +126,8 @@ html[data-darkmode="true"] {
   html[data-darkmode="true"] .watch-table .title-col a[target="_blank"]::after,
   html[data-darkmode="true"] .watch-table .current-diff-url::after {
     filter: invert(0.5) hue-rotate(10deg) brightness(2); }
+  html[data-darkmode="true"] .watch-table .status-browsersteps {
+    filter: invert(0.5) hue-rotate(10deg) brightness(1.5); }
   html[data-darkmode="true"] .watch-table .watch-controls .state-off img {
     opacity: 0.3; }
   html[data-darkmode="true"] .watch-table .watch-controls .state-on img {

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

@@ -152,6 +152,10 @@ html[data-darkmode="true"] {
       filter: invert(.5) hue-rotate(10deg) brightness(2);
     }
 
+    .status-browsersteps {
+      filter: invert(.5) hue-rotate(10deg) brightness(1.5);
+    }
+
     .watch-controls {
       .state-off {
         img {

changedetectionio/static/styles/styles.css

@@ -342,6 +342,8 @@ html[data-darkmode="true"] {
   html[data-darkmode="true"] .watch-table .title-col a[target="_blank"]::after,
   html[data-darkmode="true"] .watch-table .current-diff-url::after {
     filter: invert(0.5) hue-rotate(10deg) brightness(2); }
+  html[data-darkmode="true"] .watch-table .status-browsersteps {
+    filter: invert(0.5) hue-rotate(10deg) brightness(1.5); }
   html[data-darkmode="true"] .watch-table .watch-controls .state-off img {
     opacity: 0.3; }
   html[data-darkmode="true"] .watch-table .watch-controls .state-on img {

changedetectionio/store.py

@@ -83,7 +83,7 @@ class ChangeDetectionStore:
                 for uuid, watch in self.__data['watching'].items():
                     watch['uuid']=uuid
                     self.__data['watching'][uuid] = Watch.model(datastore_path=self.datastore_path, default=watch)
-                    logger.debug(f"Watching: {uuid} {self.__data['watching'][uuid]['url']}")
+                    logger.info(f"Watching: {uuid} {self.__data['watching'][uuid]['url']}")
 
         # First time ran, Create the datastore.
         except (FileNotFoundError):
@@ -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,
             })
 
@@ -616,7 +617,7 @@ class ChangeDetectionStore:
 
         for uuid, tag in self.__data['settings']['application'].get('tags', {}).items():
             if n == tag.get('title', '').lower().strip():
-                logger.error(f">>> Tag {name} already exists")
+                logger.warning(f"Tag '{name}' already exists, skipping creation.")
                 return uuid
 
         # Eventually almost everything todo with a watch will apply as a Tag

changedetectionio/templates/_common_fields.jinja

@@ -115,6 +115,12 @@
 									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. <br>
                                     For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removed%7D%7D-notification-tokens">More Here</a> <br>
                                     </p>
+                                    <p>
+                                        For JSON payloads, use <strong>|tojson</strong> without quotes for automatic escaping, for example - <code>{ "name": {{ '{{ watch_title|tojson }}' }} }</code>
+                                    </p>
+                                    <p>
+                                        URL encoding, use <strong>|urlencode</strong>, for example - <code>gets://hook-website.com/test.php?title={{ '{{ watch_title|urlencode }}' }}</code>
+                                    </p>
                                 </div>
                             </div>
                             <div class="pure-control-group">

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>
@@ -339,6 +339,10 @@ 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 +405,7 @@ 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>
@@ -482,6 +487,10 @@ 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/watch-overview.html

@@ -110,6 +110,7 @@
                     {% endif %}
 
                     {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" >{% endif %}
+                    {% if watch.has_browser_steps %}<img class="status-icon status-browsersteps" src="{{url_for('static_content', group='images', filename='steps.svg')}}" title="Browser Steps is enabled" >{% endif %}
                     {% if watch.last_error is defined and watch.last_error != False %}
                     <div class="fetch-error">{{ watch.last_error }}
 

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/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_backup.py

@@ -1,8 +1,8 @@
 #!/usr/bin/python3
 
-from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
+from .util import set_original_response, live_server_setup, wait_for_all_checks
 from flask import url_for
-from urllib.request import urlopen
+import io
 from zipfile import ZipFile
 import re
 import time
@@ -37,15 +37,10 @@ def test_backup(client, live_server):
     # Should be PK/ZIP stream
     assert res.data.count(b'PK') >= 2
 
-    # ZipFile from buffer seems non-obvious, just save it instead
+    backup = ZipFile(io.BytesIO(res.data))
-    with open("download.zip", 'wb') as f:
+    l = backup.namelist()
-        f.write(res.data)
-
-    zip = ZipFile('download.zip')
-    l = zip.namelist()
     uuid4hex = re.compile('^[a-f0-9]{8}-?[a-f0-9]{4}-?4[a-f0-9]{3}-?[89ab][a-f0-9]{3}-?[a-f0-9]{12}.*txt', re.I)
     newlist = list(filter(uuid4hex.match, l))  # Read Note below
 
     # Should be two txt files in the archive (history and the snapshot)
     assert len(newlist) == 2
-

changedetectionio/tests/test_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_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'])

changedetectionio/update_worker.py

@@ -31,6 +31,8 @@ class update_worker(threading.Thread):
         dates = []
         trigger_text = ''
 
+        now = time.time()
+
         if watch:
             watch_history = watch.history
             dates = list(watch_history.keys())
@@ -72,13 +74,14 @@ class update_worker(threading.Thread):
             'diff_full': diff.render_diff(prev_snapshot, current_snapshot, include_equal=True, line_feed_sep=line_feed_sep),
             'diff_patch': diff.render_diff(prev_snapshot, current_snapshot, line_feed_sep=line_feed_sep, patch_format=True),
             'diff_removed': diff.render_diff(prev_snapshot, current_snapshot, include_added=False, line_feed_sep=line_feed_sep),
+            'notification_timestamp': now,
             'screenshot': watch.get_screenshot() if watch and watch.get('notification_screenshot') else None,
             'triggered_text': triggered_text,
             'uuid': watch.get('uuid') if watch else None,
             'watch_url': watch.get('url') if watch else None,
         })
-
+        logger.trace(f"Main rendered notification placeholders (diff_added etc) calculated in {time.time()-now:.3f}s")
-        logger.debug(">> SENDING NOTIFICATION")
+        logger.debug("Queued notification for sending")
         notification_q.put(n_object)
 
     # Prefer - Individual watch settings > Tag settings >  Global settings (in that order)
@@ -147,6 +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
@@ -220,7 +227,8 @@ class update_worker(threading.Thread):
     def run(self):
 
         from .processors import text_json_diff, restock_diff
-
+        now = time.time()
+        
         while not self.app.config.exit.is_set():
             update_handler = None
 
@@ -232,13 +240,12 @@ class update_worker(threading.Thread):
             else:
                 uuid = queued_item_data.item.get('uuid')
                 self.current_uuid = uuid
-
                 if uuid in list(self.datastore.data['watching'].keys()) and self.datastore.data['watching'][uuid].get('url'):
                     changed_detected = False
                     contents = b''
                     process_changedetection_results = True
                     update_obj = {}
-                    logger.debug(f"> Processing UUID {uuid} "
+                    logger.info(f"Processing watch UUID {uuid} "
                             f"Priority {queued_item_data.priority} "
                             f"URL {self.datastore.data['watching'][uuid]['url']}")
                     now = time.time()
@@ -280,7 +287,8 @@ class update_worker(threading.Thread):
                         if not isinstance(contents, (bytes, bytearray)):
                             raise Exception("Error - returned data from the fetch handler SHOULD be bytes")
                     except PermissionError as e:
-                        self.app.logger.error("File permission error updating", uuid, str(e))
+                        logger.critical(f"File permission error updating file, watch: {uuid}")
+                        logger.critical(str(e))
                         process_changedetection_results = False
                     except content_fetcher.ReplyWithContentButNoText as e:
                         # Totally fine, it's by choice - just continue on, nothing more to care about
@@ -403,7 +411,7 @@ class update_worker(threading.Thread):
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
                     except content_fetcher.ScreenshotUnavailable as e:
-                        err_text = "Screenshot unavailable, page did not render fully in the expected time - try increasing 'Wait seconds before extracting text'"
+                        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
@@ -426,13 +434,21 @@ class update_worker(threading.Thread):
                                                                            'last_check_status': e.status_code,
                                                                            'has_ldjson_price_data': None})
                         process_changedetection_results = False
+                    except content_fetcher.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
-                        self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
+                        logger.error(f"Exception (UnableToExtractRestockData) reached processing watch UUID: {uuid}")
+                        logger.error(str(e))
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': f"Unable to extract restock data for this page unfortunately. (Got code {e.status_code} from server)"})
                         process_changedetection_results = False
                     except Exception as e:
-                        self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
+                        logger.error(f"Exception reached processing watch UUID: {uuid}")
+                        logger.error(str(e))
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
                         # Other serious error
                         process_changedetection_results = False
@@ -468,24 +484,33 @@ class update_worker(threading.Thread):
 
                             # A change was detected
                             if changed_detected:
-                                logger.debug(f">> Change detected in UUID {uuid} - {watch['url']}")
-
                                 # Notifications should only trigger on the second time (first time, we gather the initial snapshot)
                                 if watch.history_n >= 2:
+                                    logger.info(f"Change detected in UUID {uuid} - {watch['url']}")
                                     if not self.datastore.data['watching'][uuid].get('notification_muted'):
                                         self.send_content_changed_notification(watch_uuid=uuid)
-
+                                else:
+                                    logger.info(f"Change triggered in UUID {uuid} due to first history saving (no notifications sent) - {watch['url']}")
 
                         except Exception as e:
                             # Catch everything possible here, so that if a worker crashes, we don't lose it until restart!
-                            logger.critical("!!!! Exception in update_worker !!!")
+                            logger.critical("!!!! Exception in update_worker while processing process_changedetection_results !!!")
                             logger.critical(str(e))
-                            self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
                             self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
 
                     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
@@ -500,6 +525,7 @@ class update_worker(threading.Thread):
 
                 self.current_uuid = None  # Done
                 self.q.task_done()
+                logger.debug(f"Watch {uuid} done in {time.time()-now:.2f}s")
 
                 # Give the CPU time to interrupt
                 time.sleep(0.1)

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
   #
@@ -71,30 +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)
+     #       Does not report status codes (200, 404, 403) and other issues
 #    browser-chrome:
 #        hostname: browser-chrome
 #        image: selenium/standalone-chrome:4

requirements.txt

@@ -46,8 +46,8 @@ 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