Improve docker-compose browserless docker container, add env var for STEALTH and BLOCK_ADS

.github/ISSUE_TEMPLATE/bug_report.md

@@ -21,7 +21,7 @@ Steps to reproduce the behavior:
 3. Scroll down to '....'
 4. See error
 
-! ALWAYS INCLUDE AN EXAMPLE URL WHERE IT IS POSSIBLE TO RE-CREATE THE ISSUE !
+! ALWAYS INCLUDE AN EXAMPLE URL WHERE IT IS POSSIBLE TO RE-CREATE THE ISSUE - USE THE 'SHARE WATCH' FEATURE AND PASTE IN THE SHARE-LINK!
 
 **Expected behavior**
 A clear and concise description of what you expected to happen.

.github/workflows/containers.yml

@@ -85,8 +85,8 @@ jobs:
           version: latest
           driver-opts: image=moby/buildkit:master
 
-      # master always builds :latest
-      - name: Build and push :latest
+      # master branch -> :dev container tag
+      - name: Build and push :dev
         id: docker_build
         if: ${{ github.ref }} == "refs/heads/master"
         uses: docker/build-push-action@v2
@@ -95,12 +95,12 @@ jobs:
           file: ./Dockerfile
           push: true
           tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest,ghcr.io/${{ github.repository }}:latest
+            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
 
-      # A new tagged release is required, which builds :tag
+      # A new tagged release is required, which builds :tag and :latest
       - name: Build and push :tag
         id: docker_build_tag_release
         if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
@@ -110,7 +110,10 @@ jobs:
           file: ./Dockerfile
           push: true
           tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:${{ github.event.release.tag_name }},ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
+            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:${{ github.event.release.tag_name }}
+            ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
+            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest
+            ghcr.io/dgtlmoon/changedetection.io:latest
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
@@ -125,5 +128,3 @@ jobs:
           key: ${{ runner.os }}-buildx-${{ github.sha }}
           restore-keys: |
             ${{ runner.os }}-buildx-
-
-

README.md

@@ -56,9 +56,9 @@ Easily see what changed, examine by word, line, or individual character.
 
 Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
 
-### Target elements with the Visual Selector tool.
+### Filter by elements using the Visual Selector tool.
 
-Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (available also as part of our subscription service)
+Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
 
 <img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />
 
@@ -67,14 +67,18 @@ Available when connected to a <a href="https://github.com/dgtlmoon/changedetecti
 ### Docker
 
 With Docker composer, just clone this repository and..
+
 ```bash
 $ docker-compose up -d
 ```
+
 Docker standalone
 ```bash
 $ docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/datastore --name changedetection.io dgtlmoon/changedetection.io
 ```
 
+`:latest` tag is our latest stable release, `:dev` tag is our bleeding edge `master` branch.
+
 ### Windows
 
 See the install instructions at the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Microsoft-Windows

changedetectionio/__init__.py

@@ -44,7 +44,7 @@ from flask_wtf import CSRFProtect
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.39.14'
+__version__ = '0.39.15'
 
 datastore = None
 
@@ -108,7 +108,7 @@ def _jinja2_filter_datetime(watch_obj, format="%Y-%m-%d %H:%M:%S"):
     # Worker thread tells us which UUID it is currently processing.
     for t in running_update_threads:
         if t.current_uuid == watch_obj['uuid']:
-            return "Checking now.."
+            return '<span class="loader"></span><span> Checking now</span>'
 
     if watch_obj['last_checked'] == 0:
         return 'Not yet'
@@ -855,6 +855,12 @@ def changedetection_app(config=None, datastore_o=None):
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
 
+        # Normally you would never reach this, because the 'preview' button is not available when there's no history
+        # However they may try to scrub and reload the page
+        if datastore.data['watching'][uuid].history_n == 0:
+            flash("Preview unavailable - No fetch/check completed or triggers not reached", "error")
+            return redirect(url_for('index'))
+
         extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
 
         try:
@@ -924,7 +930,7 @@ def changedetection_app(config=None, datastore_o=None):
     def notification_logs():
         global notification_debug_log
         output = render_template("notification-log.html",
-                                 logs=notification_debug_log if len(notification_debug_log) else ["No errors or warnings detected"])
+                                 logs=notification_debug_log if len(notification_debug_log) else ["Notification logs are empty - no notifications sent yet."])
 
         return output
 
@@ -1244,6 +1250,9 @@ def check_for_new_version():
 
 def notification_runner():
     global notification_debug_log
+    from datetime import datetime
+    import json
+
     while not app.config.exit.is_set():
         try:
             # At the moment only one thread runs (single runner)
@@ -1252,10 +1261,14 @@ def notification_runner():
             time.sleep(1)
 
         else:
-            # Process notifications
+
+            now = datetime.now()
+            sent_obj = None
+
             try:
                 from changedetectionio import notification
-                notification.process_notification(n_object, datastore)
+
+                sent_obj = notification.process_notification(n_object, datastore)
 
             except Exception as e:
                 logging.error("Watch URL: {}  Error {}".format(n_object['watch_url'], str(e)))
@@ -1268,9 +1281,10 @@ def notification_runner():
                 log_lines = str(e).splitlines()
                 notification_debug_log += log_lines
 
-                # Trim the log length
-                notification_debug_log = notification_debug_log[-100:]
-
+            # Process notifications
+            notification_debug_log+= ["{} - SENDING - {}".format(now.strftime("%Y/%m/%d %H:%M:%S,000"), json.dumps(sent_obj))]
+            # Trim the log length
+            notification_debug_log = notification_debug_log[-100:]
 
 # Thread runner to check every minute, look for new watches to feed into the Queue.
 def ticker_thread_check_time_launch_checks():

changedetectionio/content_fetcher.py

@@ -281,13 +281,14 @@ class base_html_playwright(Fetcher):
         from playwright.sync_api import sync_playwright
         import playwright._impl._api_types
         from playwright._impl._api_types import Error, TimeoutError
-
+        response = None
         with sync_playwright() as p:
             browser_type = getattr(p, self.browser_type)
 
             # Seemed to cause a connection Exception even tho I can see it connect
             # self.browser = browser_type.connect(self.command_executor, timeout=timeout*1000)
-            browser = browser_type.connect_over_cdp(self.command_executor, timeout=timeout * 1000)
+            # 60,000 connection timeout only
+            browser = browser_type.connect_over_cdp(self.command_executor, timeout=60000)
 
             # Set user agent to prevent Cloudflare from blocking the browser
             # Use the default one configured in the App.py model that's passed from fetch_site_status.py
@@ -302,19 +303,24 @@ class base_html_playwright(Fetcher):
 
             page = context.new_page()
             try:
+                page.set_default_navigation_timeout(90000)
+                page.set_default_timeout(90000)
+
                # Bug - never set viewport size BEFORE page.goto
-                response = page.goto(url, timeout=timeout * 1000, wait_until='commit')
-                # Wait_until = commit
-                # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
-                # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
-                # This seemed to solve nearly all 'TimeoutErrors'
-                extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-                page.wait_for_timeout(extra_wait * 1000)
+
+                # Waits for the next navigation. Using Python context manager
+                # prevents a race condition between clicking and waiting for a navigation.
+                with page.expect_navigation():
+                    response = page.goto(url, wait_until='load')
+
             except playwright._impl._api_types.TimeoutError as e:
                 context.close()
                 browser.close()
-                raise EmptyReply(url=url, status_code=None)
+                # This can be ok, we will try to grab what we could retrieve
+                pass
             except Exception as e:
+                print ("other exception when page.goto")
+                print (str(e))
                 context.close()
                 browser.close()
                 raise PageUnloadable(url=url, status_code=None)
@@ -322,18 +328,22 @@ class base_html_playwright(Fetcher):
             if response is None:
                 context.close()
                 browser.close()
-                raise EmptyReply(url=url, status_code=None)
-
-            if len(page.content().strip()) == 0:
-                context.close()
-                browser.close()
+                print ("response object was none")
                 raise EmptyReply(url=url, status_code=None)
 
             # Bug 2(?) Set the viewport size AFTER loading the page
-            page.set_viewport_size({"width": 1280, "height": 1024})
-
-            self.status_code = response.status
+            page.set_viewport_size({"width": 1280, "height": 1024})            
+            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
+            time.sleep(extra_wait)
             self.content = page.content()
+            self.status_code = response.status
+
+            if len(self.content.strip()) == 0:
+                context.close()
+                browser.close()
+                print ("Content was empty")
+                raise EmptyReply(url=url, status_code=None)
+            
             self.headers = response.all_headers()
 
             if current_css_filter is not None:
@@ -346,9 +356,15 @@ class base_html_playwright(Fetcher):
             # Bug 3 in Playwright screenshot handling
             # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
             # JPEG is better here because the screenshots can be very very large
+
+            # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
+            # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
+            # acceptable screenshot quality here
             try:
-                page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024})
-                self.screenshot = page.screenshot(type='jpeg', full_page=True, quality=92)
+                # Quality set to 1 because it's not used, just used as a work-around for a bug, no need to change this.
+                page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024}, quality=1)
+                # The actual screenshot
+                self.screenshot = page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
             except Exception as e:
                 context.close()
                 browser.close()

changedetectionio/fetch_site_status.py

@@ -224,34 +224,52 @@ class perform_site_check():
         else:
             fetched_md5 = hashlib.md5(stripped_text_from_html).hexdigest()
 
-        # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
-        if not watch.get('previous_md5'):
-            watch['previous_md5'] = fetched_md5
-            update_obj["previous_md5"] = fetched_md5
-
-        blocked_by_not_found_trigger_text = False
+        ############ Blocking rules, after checksum #################
+        blocked = False
 
         if len(watch['trigger_text']):
-            # Yeah, lets block first until something matches
-            blocked_by_not_found_trigger_text = True
+            # Assume blocked
+            blocked = True
             # Filter and trigger works the same, so reuse it
             # It should return the line numbers that match
             result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
                                                   wordlist=watch['trigger_text'],
                                                   mode="line numbers")
-            # If it returned any lines that matched..
+            # Unblock if the trigger was found
             if result:
-                blocked_by_not_found_trigger_text = False
+                blocked = False
 
-        if not blocked_by_not_found_trigger_text and watch['previous_md5'] != fetched_md5:
+
+        if len(watch['text_should_not_be_present']):
+            # If anything matched, then we should block a change from happening
+            result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
+                                                  wordlist=watch['text_should_not_be_present'],
+                                                  mode="line numbers")
+            if result:
+                blocked = True
+
+        # The main thing that all this at the moment comes down to :)
+        if watch['previous_md5'] != fetched_md5:
             changed_detected = True
-            update_obj["previous_md5"] = fetched_md5
+
+        # Looks like something changed, but did it match all the rules?
+        if blocked:
+            changed_detected = False
+        else:
             update_obj["last_changed"] = timestamp
 
+
         # Extract title as title
         if is_html:
             if self.datastore.data['settings']['application']['extract_title_as_title'] or watch['extract_title_as_title']:
                 if not watch['title'] or not len(watch['title']):
                     update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
 
+        # Always record the new checksum
+        update_obj["previous_md5"] = fetched_md5
+
+        # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
+        if not watch.get('previous_md5'):
+            watch['previous_md5'] = fetched_md5
+
         return changed_detected, update_obj, text_content_before_ignored_filter, fetcher.screenshot, fetcher.xpath_data

changedetectionio/forms.py

@@ -341,6 +341,8 @@ 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)
     trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
+    text_should_not_be_present = StringListField('Block change-detection if text matches', [validators.Optional(), ValidateListRegex()])
+
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
     save_and_preview_button = SubmitField('Save & Preview', render_kw={"class": "pure-button pure-button-primary"})
     proxy = RadioField('Proxy')

changedetectionio/model/Watch.py

@@ -38,6 +38,7 @@ class model(dict):
             'extract_text': [],  # Extract text by regex after filters
             'subtractive_selectors': [],
             'trigger_text': [],  # List of text or regex to wait for until a change is detected
+            'text_should_not_be_present': [], # Text that should not present
             'fetch_backend': None,
             'extract_title_as_title': False,
             'proxy': None, # Preferred proxy connection
@@ -85,7 +86,7 @@ class model(dict):
         # Read the history file as a dict
         fname = os.path.join(self.__datastore_path, self.get('uuid'), "history.txt")
         if os.path.isfile(fname):
-            logging.debug("Disk IO accessed " + str(time.time()))
+            logging.debug("Reading history index " + str(time.time()))
             with open(fname, "r") as f:
                 tmp_history = dict(i.strip().split(',', 2) for i in f.readlines())
 

changedetectionio/notification.py

@@ -48,6 +48,7 @@ def process_notification(n_object, datastore):
     # Anything higher than or equal to WARNING (which covers things like Connection errors)
     # raise it as an exception
     apobjs=[]
+    sent_objs=[]
     for url in n_object['notification_urls']:
 
         apobj = apprise.Apprise(debug=True)
@@ -67,6 +68,11 @@ def process_notification(n_object, datastore):
                     url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
 
                 if url.startswith('tgram://'):
+                    # Telegram only supports a limit subset of HTML, remove the '<br/>' we place in.
+                    # re https://github.com/dgtlmoon/changedetection.io/issues/555
+                    # @todo re-use an existing library we have already imported to strip all non-allowed tags
+                    n_body = n_body.replace('<br/>', '\n')
+                    n_body = n_body.replace('</br>', '\n')
                     # real limit is 4096, but minus some for extra metadata
                     payload_max_size = 3600
                     body_limit = max(0, payload_max_size - len(n_title))
@@ -96,6 +102,15 @@ def process_notification(n_object, datastore):
                 log_value = logs.getvalue()
                 if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
                     raise Exception(log_value)
+                
+                sent_objs.append({'title': n_title,
+                                  'body': n_body,
+                                  'url' : url,
+                                  'body_format': n_format})
+
+    # Return what was sent for better logging - after the for loop
+    return sent_objs
+
 
 # Notification title + body content parameters get created here.
 def create_notification_parameters(n_object, datastore):

changedetectionio/run_all_tests.sh

@@ -9,8 +9,6 @@
 # exit when any command fails
 set -e
 
-export MINIMUM_SECONDS_RECHECK_TIME=0
-
 find tests/test_*py -type f|while read test_name
 do
   echo "TEST RUNNING $test_name"

changedetectionio/static/js/notifications.js

@@ -40,13 +40,19 @@ $(document).ready(function() {
     $.ajax({
       type: "POST",
       url: notification_base_url,
-      data : data
+      data : data,
+        statusCode: {
+        400: function() {
+            // More than likely the CSRF token was lost when the server restarted
+          alert("There was a problem processing the request, please reload the page.");
+        }
+      }
     }).done(function(data){
       console.log(data);
       alert('Sent');
     }).fail(function(data){
       console.log(data);
-      alert('Error: '+data.responseJSON.error);
+      alert('There was an error communicating with the server.');
     })
   });
 });

changedetectionio/static/styles/styles.css

@@ -353,6 +353,8 @@ and also iPads specifically.
     /* Hide table headers (but not display: none;, for accessibility) */ }
     .watch-table thead, .watch-table tbody, .watch-table th, .watch-table td, .watch-table tr {
       display: block; }
+    .watch-table .last-checked > span {
+      vertical-align: middle; }
     .watch-table .last-checked::before {
       color: #555;
       content: "Last Checked "; }
@@ -370,7 +372,8 @@ and also iPads specifically.
     .watch-table td {
       /* Behave  like a "row" */
       border: none;
-      border-bottom: 1px solid #eee; }
+      border-bottom: 1px solid #eee;
+      vertical-align: middle; }
       .watch-table td:before {
         /* Top/left values mimic padding */
         top: 6px;
@@ -490,3 +493,42 @@ ul {
 
 #api-key-copy {
   color: #0078e7; }
+
+/* spinner */
+.loader,
+.loader:after {
+  border-radius: 50%;
+  width: 10px;
+  height: 10px; }
+
+.loader {
+  margin: 0px auto;
+  font-size: 3px;
+  vertical-align: middle;
+  display: inline-block;
+  text-indent: -9999em;
+  border-top: 1.1em solid rgba(38, 104, 237, 0.2);
+  border-right: 1.1em solid rgba(38, 104, 237, 0.2);
+  border-bottom: 1.1em solid rgba(38, 104, 237, 0.2);
+  border-left: 1.1em solid #2668ed;
+  -webkit-transform: translateZ(0);
+  -ms-transform: translateZ(0);
+  transform: translateZ(0);
+  -webkit-animation: load8 1.1s infinite linear;
+  animation: load8 1.1s infinite linear; }
+
+@-webkit-keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg); }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg); } }
+
+@keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg); }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg); } }

changedetectionio/static/styles/styles.scss

@@ -487,6 +487,11 @@ and also iPads specifically.
       display: block;
     }
 
+    .last-checked {
+      > span {
+        vertical-align: middle;
+      }
+    }
     .last-checked::before {
       color: #555;
       content: "Last Checked ";
@@ -517,7 +522,7 @@ and also iPads specifically.
       /* Behave  like a "row" */
       border: none;
       border-bottom: 1px solid #eee;
-
+      vertical-align: middle;
       &:before {
         /* Top/left values mimic padding */
         top: 6px;
@@ -701,3 +706,48 @@ ul {
 #api-key-copy {
   color: #0078e7;
 }
+
+/* spinner */
+.loader,
+.loader:after {
+  border-radius: 50%;
+  width: 10px;
+  height: 10px;
+}
+.loader {
+  margin: 0px auto;
+  font-size: 3px;
+  vertical-align: middle;
+  display: inline-block;
+  text-indent: -9999em;
+  border-top: 1.1em solid rgba(38,104,237, 0.2);
+  border-right: 1.1em solid rgba(38,104,237, 0.2);
+  border-bottom: 1.1em solid rgba(38,104,237, 0.2);
+  border-left: 1.1em solid #2668ed;
+  -webkit-transform: translateZ(0);
+  -ms-transform: translateZ(0);
+  transform: translateZ(0);
+  -webkit-animation: load8 1.1s infinite linear;
+  animation: load8 1.1s infinite linear;
+}
+@-webkit-keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg);
+  }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg);
+  }
+}
+@keyframes load8 {
+  0% {
+    -webkit-transform: rotate(0deg);
+    transform: rotate(0deg);
+  }
+  100% {
+    -webkit-transform: rotate(360deg);
+    transform: rotate(360deg);
+  }
+}
+

changedetectionio/store.py

@@ -290,14 +290,15 @@ class ChangeDetectionStore:
                                      headers={'App-Guid': self.__data['app_guid']})
                 res = r.json()
 
-                # List of permisable stuff we accept from the wild internet
+                # List of permissible attributes we accept from the wild internet
                 for k in ['url', 'tag',
-                                   'paused', 'title',
-                                   'previous_md5', 'headers',
-                                   'body', 'method',
-                                   'ignore_text', 'css_filter',
-                                   'subtractive_selectors', 'trigger_text',
-                                   'extract_title_as_title', 'extract_text']:
+                          'paused', 'title',
+                          'previous_md5', 'headers',
+                          'body', 'method',
+                          'ignore_text', 'css_filter',
+                          'subtractive_selectors', 'trigger_text',
+                          'extract_title_as_title', 'extract_text',
+                          'text_should_not_be_present']:
                     if res.get(k):
                         apply_extras[k] = res[k]
 

changedetectionio/templates/_common_fields.jinja

@@ -14,7 +14,7 @@
                                 <li>Use <a target=_new href="https://github.com/caronc/apprise">AppRise URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.</li>
                                 <li><code>discord://</code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
                                 <li><code>tgram://</code> bots cant send messages to other bots, so you should specify chat ID of non-bot user.</li>
-                                <li>Go here for <a href="{{url_for('notification_logs')}}">notification debug logs</a></li>
+                                <li><code>tgram://</code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
                               </ul>
                             </div>
                             <br/>
@@ -22,6 +22,7 @@
 {% if emailprefix %}
                             <a id="add-email-helper" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Add email</a>
 {% endif %}
+                            <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Notification debug logs</a>
                         </div>
                         <div id="notification-customisation" class="pure-control-group">
                             <div class="pure-control-group">

changedetectionio/templates/edit.html

@@ -199,6 +199,22 @@ nav
                         </span>
                     </div>
                 </fieldset>
+                <fieldset>
+                    <div class="pure-control-group">
+                        {{ render_field(form.text_should_not_be_present, rows=5, placeholder="For example: Out of stock
+Sold out
+Not in stock
+Unavailable") }}
+                        <span class="pure-form-message-inline">
+                            <ul>
+                                <li>Block change-detection while this text is on the page, all text and regex are tested <i>case-insensitive</i>, good for waiting for when a product is available again</li>
+                                <li>Block text is processed from the result-text that comes out of any CSS/JSON Filters for this watch</li>
+                                <li>All lines here must not exist (think of each line as "OR")</li>
+                                <li>Note: Wrap in forward slash / to use regex  example: <code>/foo\d/</code></li>
+                            </ul>
+                        </span>
+                    </div>
+                </fieldset>
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.extract_text, rows=5, placeholder="\d+ online") }}

changedetectionio/templates/notification-log.html

@@ -4,7 +4,7 @@
 <div class="edit-form">
      <div class="inner">
 
-         <h4 style="margin-top: 0px;">The following issues were detected when sending notifications</h4>
+         <h4 style="margin-top: 0px;">Notification debug log</h4>
                 <div id="notification-error-log">
                 <ul style="font-size: 80%; margin:0px; padding: 0 0 0 7px">
                 {% for log in logs|reverse %}

changedetectionio/templates/watch-overview.html

@@ -67,7 +67,7 @@
                     <span class="watch-tag-list">{{ watch.tag}}</span>
                     {% endif %}
                 </td>
-                <td class="last-checked">{{watch|format_last_checked_time}}</td>
+                <td class="last-checked">{{watch|format_last_checked_time|safe}}</td>
                 <td class="last-changed">{% if watch.history_n >=2 and watch.last_changed %}
                     {{watch.last_changed|format_timestamp_timeago}}
                     {% else %}

changedetectionio/tests/conftest.py

@@ -32,6 +32,8 @@ def app(request):
     """Create application for the tests."""
     datastore_path = "./test-datastore"
 
+    # So they don't delay in fetching
+    os.environ["MINIMUM_SECONDS_RECHECK_TIME"] = "0"
     try:
         os.mkdir(datastore_path)
     except FileExistsError:

changedetectionio/tests/test_block_while_text_present.py

@@ -0,0 +1,137 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from . util import live_server_setup
+from changedetectionio import html_tools
+
+def set_original_ignore_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+     </body>
+     </html>
+
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def set_modified_original_ignore_response():
+    test_return_data = """<html>
+       <body>
+     Some NEW nice initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+     <p>new ignore stuff</p>
+     <p>out of stock</p>
+     <p>blah</p>
+     </body>
+     </html>
+
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+# Is the same but includes ZZZZZ, 'ZZZZZ' is the last line in ignore_text
+def set_modified_response_minus_block_text():
+    test_return_data = """<html>
+       <body>
+     Some NEW nice initial text</br>
+     <p>Which is across multiple lines</p>
+     <p>now on sale $2/p>
+     </br>
+     So let's see what happens.  </br>
+     <p>new ignore stuff</p>
+     <p>blah</p>
+     </body>
+     </html>
+
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def test_check_block_changedetection_text_NOT_present(client, live_server):
+    sleep_time_for_fetch_thread = 3
+    live_server_setup(live_server)
+    # Use a mix of case in ZzZ to prove it works case-insensitive.
+    ignore_text = "out of stoCk\r\nfoobar"
+
+    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)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # Goto the edit page, add our ignore text
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"text_should_not_be_present": ignore_text, "url": test_url, 'fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+    # Check it saved
+    res = client.get(
+        url_for("edit_page", uuid="first"),
+    )
+    assert bytes(ignore_text.encode('utf-8')) in res.data
+
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+    assert b'/test-endpoint' in res.data
+
+    # The page changed, BUT the text is still there, just the rest of it changes, we should not see a change
+    set_modified_original_ignore_response()
+
+    # 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)
+
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+    assert b'/test-endpoint' in res.data
+
+
+    # Now we set a change where the text is gone, it should now trigger
+    set_modified_response_minus_block_text()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    time.sleep(sleep_time_for_fetch_thread)
+
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_notification.py

@@ -154,6 +154,10 @@ def test_check_notification(client, live_server):
     time.sleep(1)
     assert os.path.exists("test-datastore/notification.txt") == False
 
+    res = client.get(url_for("notification_logs"))
+    # be sure we see it in the output log
+    assert b'New ChangeDetection.io Notification - ' + test_url.encode('utf-8') in res.data
+
     # cleanup for the next
     client.get(
         url_for("form_delete", uuid="all"),

changedetectionio/update_worker.py

@@ -45,7 +45,6 @@ class update_worker(threading.Thread):
 
                     try:
                         changed_detected, update_obj, contents, screenshot, xpath_data = update_handler.run(uuid)
-
                         # Re #342
                         # In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.
                         # We then convert/.decode('utf-8') for the notification etc
@@ -56,18 +55,18 @@ class update_worker(threading.Thread):
                     except content_fetcher.ReplyWithContentButNoText as e:
                         # Totally fine, it's by choice - just continue on, nothing more to care about
                         # Page had elements/content but no renderable text
-                        if self.datastore.data['watching'][uuid].get('css_filter'):
+                        if self.datastore.data['watching'].get(uuid, False) and self.datastore.data['watching'][uuid].get('css_filter'):
                             self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found (CSS / xPath Filter not found in page?)"})
                         else:
                             self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found."})
                         pass
                     except content_fetcher.EmptyReply as e:
                         # Some kind of custom to-str handler in the exception handler that does this?
-                        err_text = "EmptyReply: Status Code {}".format(e.status_code)
+                        err_text = "EmptyReply - try increasing 'Wait seconds before extracting text', Status Code {}".format(e.status_code)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                     except content_fetcher.ScreenshotUnavailable as e:
-                        err_text = "Screenshot unavailable, page did not render fully in the expected time"
+                        err_text = "Screenshot unavailable, page did not render fully in the expected time - 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})
                     except content_fetcher.PageUnloadable as e:
@@ -99,9 +98,16 @@ class update_worker(threading.Thread):
 
                                 # Notifications should only trigger on the second time (first time, we gather the initial snapshot)
                                 if watch.history_n >= 2:
-
-                                    dates = list(watch.history.keys())
-                                    prev_fname = watch.history[dates[-2]]
+                                    print(">> Change detected in UUID {} - {}".format(uuid, watch['url']))
+                                    watch_history = watch.history
+                                    dates = list(watch_history.keys())
+                                    # Theoretically it's possible that this could be just 1 long,
+                                    # - In the case that the timestamp key was not unique
+                                    if len(dates) == 1:
+                                        raise ValueError(
+                                            "History index had 2 or more, but only 1 date loaded, timestamps were not unique? maybe two of the same timestamps got written, needs more delay?"
+                                        )
+                                    prev_fname = watch_history[dates[-2]]
 
 
                                     # Did it have any notification alerts to hit?

docker-compose.yml

@@ -73,6 +73,20 @@ services:
 #        hostname: playwright-chrome
 #        image: browserless/chrome
 #        restart: unless-stopped
+#        environment:
+#            - SCREEN_WIDTH=1920
+#            - SCREEN_HEIGHT=1024
+#            - SCREEN_DEPTH=16
+#            - ENABLE_DEBUGGER=false
+#            - SCREEN_WIDTH=1280
+#            - SCREEN_HEIGHT=1024
+#            - SCREEN_DEPTH=16
+#            - PREBOOT_CHROME=true
+#            - CONNECTION_TIMEOUT=300000
+#            - MAX_CONCURRENT_SESSIONS=10
+#            - CHROME_REFRESH_TIME=600000
+#            - DEFAULT_BLOCK_ADS=true
+#            - DEFAULT_STEALTH=true
 
 volumes:
   changedetection-data: