test these files

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/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 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: |         
@@ -47,6 +47,12 @@ 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: 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
@@ -63,43 +69,33 @@ jobs:
 
       - 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'
 
-      - name: Specific tests in built container for Playwright
-        run: |         
-          # Playwright/Browserless fetch
-          docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
+      - name: Specific tests in built container for Playwright and SocketPuppetBrowser
+        run: |
+          # Playwright via Sockpuppetbrowser fetch
+          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'
 
       - name: Specific tests in built container for headers and requests checks with Playwright
-        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'
+        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: |                  
+        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'
 
-      - name: Specific tests in built container with Playwright as Puppeteer experimental fetcher
-        run: |                  
-          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
         run: |                            
-          # 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'
+          # 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

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.45.13'
+__version__ = '0.45.14'
 
 from distutils.util import strtobool
 from json.decoder import JSONDecodeError

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

@@ -53,7 +53,7 @@ class BrowserStepsStepException(Exception):
 
 # @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
@@ -61,6 +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):
@@ -307,125 +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
-            try:
-                x = response.json()
-            except Exception as e:
-                raise PageUnloadable(url=url, message="Error reading JSON response from browserless")
-
-            try:
-                self.status_code = response.status_code
-            except Exception as e:
-                raise PageUnloadable(url=url, message="Error reading status_code code response from browserless")
-
-            self.headers = x.get('headers')
-
-            if self.status_code != 200 and not ignore_status_codes:
-                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, page_html=x.get('content',''))
-
-            if self.status_code == 200:
-                import base64
-
-                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)
-
-                self.content = x.get('content')
-                self.instock_data = x.get('instock_data')
-                self.screenshot = base64.b64decode(x.get('screenshot'))
-                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,
@@ -437,21 +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
 
@@ -524,8 +394,10 @@ class base_html_playwright(Fetcher):
                 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(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:
@@ -566,16 +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
-                self.screenshot = self.page.screenshot(type='jpeg', full_page=True,
-                                                       quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+                # 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("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):
@@ -712,6 +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",

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,
@@ -57,6 +58,7 @@ base_config = {
     '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/text_json_diff.py

@@ -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')
 

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

@@ -36,6 +36,7 @@ function isItemInStock() {
         'nicht zur verfügung',
         'niet beschikbaar',
         'niet leverbaar',
+        'niet op voorraad',
         'no disponible temporalmente',
         'no longer in stock',
         'no tickets available',
@@ -47,6 +48,7 @@ function isItemInStock() {
         'não estamos a aceitar encomendas',
         'out of stock',
         'out-of-stock',
+        'prodotto esaurito',
         'produkt niedostępny',
         'sold out',
         'sold-out',

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 logs browserless-custom-url &>log.txt
+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 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 logs browserless-custom-url &>log.txt
+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 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/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) {
-            document.getElementById('browserless-seconds-remaining').innerText = browserless_seconds_remaining + " seconds remaining in session";
-            browserless_seconds_remaining -= 1;
+        if (browser_interface_seconds_remaining >= 1) {
+            document.getElementById('browser-seconds-remaining').innerText = browser_interface_seconds_remaining + " seconds remaining in session";
+            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/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>
@@ -483,6 +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/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
-              # 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_connection_url': 'ws://sockpuppetbrowser-custom-url:3000',
               '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_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

@@ -14,7 +14,7 @@ def test_headers_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', 'changedet')
 
     # Add the test URL twice, we will check
@@ -89,7 +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(
@@ -181,7 +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
@@ -258,7 +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_unique_lines_functionality(client, live_server):
+def test_setup(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/update_worker.py

@@ -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
@@ -407,7 +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
@@ -430,6 +434,12 @@ 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
                         logger.error(f"Exception (UnableToExtractRestockData) reached processing watch UUID: {uuid}")

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
   #
@@ -71,32 +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
-#            - 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
-#
+#            - MAX_CONCURRENT_CHROME_PROCESSES=10
 
      # 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)
      #       Does not report status codes (200, 404, 403) and other issues
-     # More information about the advantages of playwright/browserless https://www.browserless.io/blog/2023/12/13/migrating-selenium-to-playwright/
 #    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
-elementpath
+# XPath 2.0-3.1 support - 4.2.0 broke something?
+elementpath==4.1.5
 
 selenium~=4.14.0