Filter - unique lines fix for empty set

.github/test/Dockerfile-alpine

@@ -2,32 +2,33 @@
 # Test that we can still build on Alpine (musl modified libc https://musl.libc.org/)
 # Some packages wont install via pypi because they dont have a wheel available under this architecture.
 
-FROM ghcr.io/linuxserver/baseimage-alpine:3.18
+FROM ghcr.io/linuxserver/baseimage-alpine:3.21
 ENV PYTHONUNBUFFERED=1
 
 COPY requirements.txt /requirements.txt
 
 RUN \
-  apk add --update --no-cache --virtual=build-dependencies \
+ apk add --update --no-cache --virtual=build-dependencies \
+    build-base \
     cargo \
-    g++ \
-    gcc \
+    git \
     jpeg-dev \
     libc-dev \
     libffi-dev \
-    libjpeg \
     libxslt-dev \
-    make \
     openssl-dev \
-    py3-wheel \
     python3-dev \
+    zip \
     zlib-dev && \
   apk add --update --no-cache \
+    libjpeg \
     libxslt \
-    python3 \
-    py3-pip && \
+    nodejs \
+    poppler-utils \
+    python3 && \
   echo "**** pip3 install test of changedetection.io ****" && \
-  pip3 install -U pip wheel setuptools && \
-  pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.18/ -r /requirements.txt && \
+  python3 -m venv /lsiopy  && \
+  pip install -U pip wheel setuptools && \
+  pip install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.21/ -r /requirements.txt && \
   apk del --purge \
     build-dependencies

.github/workflows/containers.yml

@@ -103,6 +103,19 @@ jobs:
 #          provenance: false
 
       # A new tagged release is required, which builds :tag and :latest
+      - name: Docker meta :tag
+        if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
+        uses: docker/metadata-action@v5
+        id: meta
+        with:
+            images: |
+                ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io
+                ghcr.io/dgtlmoon/changedetection.io
+            tags: |
+                type=semver,pattern={{version}}
+                type=semver,pattern={{major}}.{{minor}}
+                type=semver,pattern={{major}}
+
       - name: Build and push :tag
         id: docker_build_tag_release
         if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
@@ -111,11 +124,7 @@ jobs:
           context: ./
           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:latest
-            ghcr.io/dgtlmoon/changedetection.io:latest
+          tags: ${{ steps.meta.outputs.tags }}
           platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/v8
           cache-from: type=gha
           cache-to: type=gha,mode=max

.github/workflows/pypi-release.yml

@@ -45,7 +45,6 @@ jobs:
     - name: Test that the basic pip built package runs without error
       run: |
         set -ex
-        sudo pip3 install --upgrade pip 
         pip3 install dist/changedetection.io*.whl
         changedetection.io -d /tmp -p 10000 &
         sleep 3

.github/workflows/test-stack-reusable-workflow.yml

@@ -64,14 +64,16 @@ jobs:
           echo "Running processes in docker..."
           docker ps
 
-      - name: Test built container with Pytest (generally as requests/plaintext fetching)
+      - name: Run Unit Tests
         run: |
           # Unit tests
-          echo "run test with unittest"
           docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
           docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_watch_model'
           docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_jinja2_security'
-          
+          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_semver'
+
+      - name: Test built container with Pytest (generally as requests/plaintext fetching)
+        run: |
           # All tests
           echo "run test with pytest"
           # The default pytest logger_level is TRACE

README.md

@@ -120,7 +120,7 @@ Easily add the current web page to your changedetection.io tool, simply install
 
 [<img src="./docs/chrome-extension-screenshot.png" style="max-width:80%;" alt="Chrome Extension to easily add the current web-page to detect a change."  title="Chrome Extension to easily add the current web-page to detect a change."  />](https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop)
 
-[Goto the Chrome Webstore to download the extension.](https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop)
+[Goto the Chrome Webstore to download the extension.](https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop) ( Or check out the [GitHub repo](https://github.com/dgtlmoon/changedetection.io-browser-extension) ) 
 
 ## Installation
 

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.48.01'
+__version__ = '0.49.1'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError
@@ -24,6 +24,9 @@ from loguru import logger
 app = None
 datastore = None
 
+def get_version():
+    return __version__
+
 # Parent wrapper or OS sends us a SIGTERM/SIGINT, do everything required for a clean shutdown
 def sigshutdown_handler(_signo, _stack_frame):
     global app

changedetectionio/api/api_schema.py

@@ -112,6 +112,35 @@ def build_watch_json_schema(d):
 
     schema['properties']['time_between_check'] = build_time_between_check_json_schema()
 
+    schema['properties']['browser_steps'] = {
+        "anyOf": [
+            {
+                "type": "array",
+                "items": {
+                    "type": "object",
+                    "properties": {
+                        "operation": {
+                            "type": ["string", "null"],
+                            "maxLength": 5000  # Allows null and any string up to 5000 chars (including "")
+                        },
+                        "selector": {
+                            "type": ["string", "null"],
+                            "maxLength": 5000
+                        },
+                        "optional_value": {
+                            "type": ["string", "null"],
+                            "maxLength": 5000
+                        }
+                    },
+                    "required": ["operation", "selector", "optional_value"],
+                    "additionalProperties": False  # No extra keys allowed
+                }
+            },
+            {"type": "null"},  # Allows null for `browser_steps`
+            {"type": "array", "maxItems": 0}  # Allows empty array []
+        ]
+    }
+
     # headers ?
     return schema
 

changedetectionio/api/api_v1.py

@@ -76,6 +76,7 @@ class Watch(Resource):
         # Return without history, get that via another API call
         # Properties are not returned as a JSON, so add the required props manually
         watch['history_n'] = watch.history_n
+        # attr .last_changed will check for the last written text snapshot on change
         watch['last_changed'] = watch.last_changed
         watch['viewed'] = watch.viewed
         return watch

changedetectionio/apprise_asset.py

@@ -1,3 +1,4 @@
+from changedetectionio import apprise_plugin
 import apprise
 
 # Create our AppriseAsset and populate it with some of our new values:

changedetectionio/apprise_plugin/__init__.py

@@ -1,6 +1,8 @@
 # include the decorator
 from apprise.decorators import notify
 from loguru import logger
+from requests.structures import CaseInsensitiveDict
+
 
 @notify(on="delete")
 @notify(on="deletes")
@@ -13,70 +15,84 @@ from loguru import logger
 def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
     import requests
     import json
+    import re
+
     from urllib.parse import unquote_plus
-    from apprise.utils import parse_url as apprise_parse_url
-    from apprise import URLBase
+    from apprise.utils.parse import parse_url as apprise_parse_url
 
     url = kwargs['meta'].get('url')
+    schema = kwargs['meta'].get('schema').lower().strip()
 
-    if url.startswith('post'):
-        r = requests.post
-    elif url.startswith('get'):
-        r = requests.get
-    elif url.startswith('put'):
-        r = requests.put
-    elif url.startswith('delete'):
-        r = requests.delete
+    # Choose POST, GET etc from requests
+    method =  re.sub(rf's$', '', schema)
+    requests_method = getattr(requests, method)
 
-    url = url.replace('post://', 'http://')
-    url = url.replace('posts://', 'https://')
-    url = url.replace('put://', 'http://')
-    url = url.replace('puts://', 'https://')
-    url = url.replace('get://', 'http://')
-    url = url.replace('gets://', 'https://')
-    url = url.replace('put://', 'http://')
-    url = url.replace('puts://', 'https://')
-    url = url.replace('delete://', 'http://')
-    url = url.replace('deletes://', 'https://')
-
-    headers = {}
-    params = {}
+    params = CaseInsensitiveDict({}) # Added to requests
     auth = None
+    has_error = False
 
     # Convert /foobar?+some-header=hello to proper header dictionary
     results = apprise_parse_url(url)
-    if results:
-        # Add our headers that the user can potentially over-ride if they wish
-        # to to our returned result set and tidy entries by unquoting them
-        headers = {unquote_plus(x): unquote_plus(y)
-                   for x, y in results['qsd+'].items()}
 
-        # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
-        # In Apprise, it relies on prefixing each request arg with "-", because it uses say &method=update as a flag for apprise
-        # but here we are making straight requests, so we need todo convert this against apprise's logic
-        for k, v in results['qsd'].items():
-            if not k.strip('+-') in results['qsd+'].keys():
-                params[unquote_plus(k)] = unquote_plus(v)
+    # Add our headers that the user can potentially over-ride if they wish
+    # to to our returned result set and tidy entries by unquoting them
+    headers = CaseInsensitiveDict({unquote_plus(x): unquote_plus(y)
+               for x, y in results['qsd+'].items()})
 
-        # Determine Authentication
-        auth = ''
-        if results.get('user') and results.get('password'):
-            auth = (unquote_plus(results.get('user')), unquote_plus(results.get('user')))
-        elif results.get('user'):
-            auth = (unquote_plus(results.get('user')))
+    # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
+    # In Apprise, it relies on prefixing each request arg with "-", because it uses say &method=update as a flag for apprise
+    # but here we are making straight requests, so we need todo convert this against apprise's logic
+    for k, v in results['qsd'].items():
+        if not k.strip('+-') in results['qsd+'].keys():
+            params[unquote_plus(k)] = unquote_plus(v)
 
-    # Try to auto-guess if it's JSON
-    h = 'application/json; charset=utf-8'
+    # Determine Authentication
+    auth = ''
+    if results.get('user') and results.get('password'):
+        auth = (unquote_plus(results.get('user')), unquote_plus(results.get('user')))
+    elif results.get('user'):
+        auth = (unquote_plus(results.get('user')))
+
+    # If it smells like it could be JSON and no content-type was already set, offer a default content type.
+    if body and '{' in body[:100] and not headers.get('Content-Type'):
+        json_header = 'application/json; charset=utf-8'
+        try:
+            # Try if it's JSON
+            json.loads(body)
+            headers['Content-Type'] = json_header
+        except ValueError as e:
+            logger.warning(f"Could not automatically add '{json_header}' header to the notification because the document failed to parse as JSON: {e}")
+            pass
+
+    # POSTS -> HTTPS etc
+    if schema.lower().endswith('s'):
+        url = re.sub(rf'^{schema}', 'https', results.get('url'))
+    else:
+        url = re.sub(rf'^{schema}', 'http', results.get('url'))
+
+    status_str = ''
     try:
-        json.loads(body)
-        headers['Content-Type'] = h
-    except ValueError as e:
-        logger.warning(f"Could not automatically add '{h}' header to the {kwargs['meta'].get('schema')}:// notification because the document failed to parse as JSON: {e}")
-        pass
+        r = requests_method(url,
+          auth=auth,
+          data=body.encode('utf-8') if type(body) is str else body,
+          headers=headers,
+          params=params
+        )
 
-    r(results.get('url'),
-      auth=auth,
-      data=body.encode('utf-8') if type(body) is str else body,
-      headers=headers,
-      params=params
-      )
+        if not (200 <= r.status_code < 300):
+            status_str = f"Error sending '{method.upper()}' request to {url} - Status: {r.status_code}: '{r.reason}'"
+            logger.error(status_str)
+            has_error = True
+        else:
+            logger.info(f"Sent '{method.upper()}' request to {url}")
+            has_error = False
+
+    except requests.RequestException as e:
+        status_str = f"Error sending '{method.upper()}' request to {url} - {str(e)}"
+        logger.error(status_str)
+        has_error = True
+
+    if has_error:
+        raise TypeError(status_str)
+
+    return True

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -52,6 +52,8 @@ class steppable_browser_interface():
     page = None
     start_url = None
 
+    action_timeout = 10 * 1000
+
     def __init__(self, start_url):
         self.start_url = start_url
 
@@ -102,7 +104,7 @@ class steppable_browser_interface():
             return
         elem = self.page.get_by_text(value)
         if elem.count():
-            elem.first.click(delay=randint(200, 500), timeout=3000)
+            elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
 
     def action_click_element_containing_text_if_exists(self, selector=None, value=''):
         logger.debug("Clicking element containing text if exists")
@@ -111,7 +113,7 @@ class steppable_browser_interface():
         elem = self.page.get_by_text(value)
         logger.debug(f"Clicking element containing text - {elem.count()} elements found")
         if elem.count():
-            elem.first.click(delay=randint(200, 500), timeout=3000)
+            elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
         else:
             return
 
@@ -119,7 +121,7 @@ class steppable_browser_interface():
         if not len(selector.strip()):
             return
 
-        self.page.fill(selector, value, timeout=10 * 1000)
+        self.page.fill(selector, value, timeout=self.action_timeout)
 
     def action_execute_js(self, selector, value):
         response = self.page.evaluate(value)
@@ -130,7 +132,7 @@ class steppable_browser_interface():
         if not len(selector.strip()):
             return
 
-        self.page.click(selector=selector, timeout=30 * 1000, delay=randint(200, 500))
+        self.page.click(selector=selector, timeout=self.action_timeout + 20 * 1000, delay=randint(200, 500))
 
     def action_click_element_if_exists(self, selector, value):
         import playwright._impl._errors as _api_types
@@ -138,7 +140,7 @@ class steppable_browser_interface():
         if not len(selector.strip()):
             return
         try:
-            self.page.click(selector, timeout=10 * 1000, delay=randint(200, 500))
+            self.page.click(selector, timeout=self.action_timeout, delay=randint(200, 500))
         except _api_types.TimeoutError as e:
             return
         except _api_types.Error as e:
@@ -185,10 +187,10 @@ class steppable_browser_interface():
         self.page.keyboard.press("PageDown", delay=randint(200, 500))
 
     def action_check_checkbox(self, selector, value):
-        self.page.locator(selector).check(timeout=1000)
+        self.page.locator(selector).check(timeout=self.action_timeout)
 
     def action_uncheck_checkbox(self, selector, value):
-        self.page.locator(selector, timeout=1000).uncheck(timeout=1000)
+        self.page.locator(selector).uncheck(timeout=self.action_timeout)
 
 
 # Responsible for maintaining a live 'context' with the chrome CDP

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

@@ -52,6 +52,7 @@ function isItemInStock() {
         'niet leverbaar',
         'niet op voorraad',
         'no disponible',
+        'non disponibile',
         'no longer in stock',
         'no tickets available',
         'not available',

changedetectionio/diff.py

@@ -1,6 +1,9 @@
 import difflib
 from typing import List, Iterator, Union
 
+REMOVED_STYLE = "background-color: #fadad7; color: #b30000;"
+ADDED_STYLE = "background-color: #eaf2c2; color: #406619;"
+
 def same_slicer(lst: List[str], start: int, end: int) -> List[str]:
     """Return a slice of the list, or a single element if start == end."""
     return lst[start:end] if start != end else [lst[start]]
@@ -12,11 +15,12 @@ def customSequenceMatcher(
     include_removed: bool = True,
     include_added: bool = True,
     include_replaced: bool = True,
-    include_change_type_prefix: bool = True
+    include_change_type_prefix: bool = True,
+    html_colour: bool = False
 ) -> Iterator[List[str]]:
     """
     Compare two sequences and yield differences based on specified parameters.
-    
+
     Args:
         before (List[str]): Original sequence
         after (List[str]): Modified sequence
@@ -25,26 +29,35 @@ def customSequenceMatcher(
         include_added (bool): Include added parts
         include_replaced (bool): Include replaced parts
         include_change_type_prefix (bool): Add prefixes to indicate change types
-    
+        html_colour (bool): Use HTML background colors for differences
+
     Yields:
         List[str]: Differences between sequences
     """
     cruncher = difflib.SequenceMatcher(isjunk=lambda x: x in " \t", a=before, b=after)
-    
+
+
+
     for tag, alo, ahi, blo, bhi in cruncher.get_opcodes():
         if include_equal and tag == 'equal':
             yield before[alo:ahi]
         elif include_removed and tag == 'delete':
-            prefix = "(removed) " if include_change_type_prefix else ''
-            yield [f"{prefix}{line}" for line in same_slicer(before, alo, ahi)]
+            if html_colour:
+                yield [f'<span style="{REMOVED_STYLE}">{line}</span>' for line in same_slicer(before, alo, ahi)]
+            else:
+                yield [f"(removed) {line}" for line in same_slicer(before, alo, ahi)] if include_change_type_prefix else same_slicer(before, alo, ahi)
         elif include_replaced and tag == 'replace':
-            prefix_changed = "(changed) " if include_change_type_prefix else ''
-            prefix_into = "(into) " if include_change_type_prefix else ''
-            yield [f"{prefix_changed}{line}" for line in same_slicer(before, alo, ahi)] + \
-                  [f"{prefix_into}{line}" for line in same_slicer(after, blo, bhi)]
+            if html_colour:
+                yield [f'<span style="{REMOVED_STYLE}">{line}</span>' for line in same_slicer(before, alo, ahi)] + \
+                      [f'<span style="{ADDED_STYLE}">{line}</span>' for line in same_slicer(after, blo, bhi)]
+            else:
+                yield [f"(changed) {line}" for line in same_slicer(before, alo, ahi)] + \
+                      [f"(into) {line}" for line in same_slicer(after, blo, bhi)] if include_change_type_prefix else same_slicer(before, alo, ahi) + same_slicer(after, blo, bhi)
         elif include_added and tag == 'insert':
-            prefix = "(added) " if include_change_type_prefix else ''
-            yield [f"{prefix}{line}" for line in same_slicer(after, blo, bhi)]
+            if html_colour:
+                yield [f'<span style="{ADDED_STYLE}">{line}</span>' for line in same_slicer(after, blo, bhi)]
+            else:
+                yield [f"(added) {line}" for line in same_slicer(after, blo, bhi)] if include_change_type_prefix else same_slicer(after, blo, bhi)
 
 def render_diff(
     previous_version_file_contents: str,
@@ -55,11 +68,12 @@ def render_diff(
     include_replaced: bool = True,
     line_feed_sep: str = "\n",
     include_change_type_prefix: bool = True,
-    patch_format: bool = False
+    patch_format: bool = False,
+    html_colour: bool = False
 ) -> str:
     """
     Render the difference between two file contents.
-    
+
     Args:
         previous_version_file_contents (str): Original file contents
         newest_version_file_contents (str): Modified file contents
@@ -70,7 +84,8 @@ def render_diff(
         line_feed_sep (str): Separator for lines in output
         include_change_type_prefix (bool): Add prefixes to indicate change types
         patch_format (bool): Use patch format for output
-    
+        html_colour (bool): Use HTML background colors for differences
+
     Returns:
         str: Rendered difference
     """
@@ -88,10 +103,11 @@ def render_diff(
         include_removed=include_removed,
         include_added=include_added,
         include_replaced=include_replaced,
-        include_change_type_prefix=include_change_type_prefix
+        include_change_type_prefix=include_change_type_prefix,
+        html_colour=html_colour
     )
 
     def flatten(lst: List[Union[str, List[str]]]) -> str:
         return line_feed_sep.join(flatten(x) if isinstance(x, list) else x for x in lst)
 
-    return flatten(rendered_diff)
+    return flatten(rendered_diff)

changedetectionio/flask_app.py

@@ -598,17 +598,31 @@ def changedetection_app(config=None, datastore_o=None):
 
             if 'notification_title' in request.form and request.form['notification_title'].strip():
                 n_object['notification_title'] = request.form.get('notification_title', '').strip()
+            elif datastore.data['settings']['application'].get('notification_title'):
+                n_object['notification_title'] = datastore.data['settings']['application'].get('notification_title')
+            else:
+                n_object['notification_title'] = "Test title"
 
             if 'notification_body' in request.form and request.form['notification_body'].strip():
                 n_object['notification_body'] = request.form.get('notification_body', '').strip()
+            elif datastore.data['settings']['application'].get('notification_body'):
+                n_object['notification_body'] = datastore.data['settings']['application'].get('notification_body')
+            else:
+                n_object['notification_body'] = "Test body"
 
+            n_object['as_async'] = False
             n_object.update(watch.extra_notification_token_values())
+            from .notification import process_notification
+            sent_obj = process_notification(n_object, datastore)
 
-            from . import update_worker
-            new_worker = update_worker.update_worker(update_q, notification_q, app, datastore)
-            new_worker.queue_notification_for_watch(notification_q=notification_q, n_object=n_object, watch=watch)
         except Exception as e:
-            return make_response(f"Error: str(e)", 400)
+            e_str = str(e)
+            # Remove this text which is not important and floods the container
+            e_str = e_str.replace(
+                "DEBUG - <class 'apprise.decorators.base.CustomNotifyPlugin.instantiate_plugin.<locals>.CustomNotifyPluginWrapper'>",
+                '')
+
+            return make_response(e_str, 400)
 
         return 'OK - Sent test notifications'
 
@@ -841,7 +855,7 @@ def changedetection_app(config=None, datastore_o=None):
             if request.args.get("next") and request.args.get("next") == 'diff':
                 return redirect(url_for('diff_history_page', uuid=uuid))
 
-            return redirect(url_for('index'))
+            return redirect(url_for('index', tag=request.args.get("tag",'')))
 
         else:
             if request.method == 'POST' and not form.validate():
@@ -1395,13 +1409,13 @@ def changedetection_app(config=None, datastore_o=None):
         if new_uuid:
             if add_paused:
                 flash('Watch added in Paused state, saving will unpause.')
-                return redirect(url_for('edit_page', uuid=new_uuid, unpause_on_save=1))
+                return redirect(url_for('edit_page', uuid=new_uuid, unpause_on_save=1, tag=request.args.get('tag')))
             else:
                 # Straight into the queue.
                 update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
                 flash("Watch added.")
 
-        return redirect(url_for('index'))
+        return redirect(url_for('index', tag=request.args.get('tag','')))
 
 
 

changedetectionio/forms.py

@@ -308,8 +308,12 @@ class ValidateAppRiseServers(object):
         # so that the custom endpoints are registered
         from changedetectionio.apprise_plugin import apprise_custom_api_call_wrapper
         for server_url in field.data:
-            if not apobj.add(server_url):
-                message = field.gettext('\'%s\' is not a valid AppRise URL.' % (server_url))
+            url = server_url.strip()
+            if url.startswith("#"):
+                continue
+
+            if not apobj.add(url):
+                message = field.gettext('\'%s\' is not a valid AppRise URL.' % (url))
                 raise ValidationError(message)
 
 class ValidateJinja2Template(object):

changedetectionio/html_tools.py

@@ -1,5 +1,6 @@
-from typing import List
+from loguru import logger
 from lxml import etree
+from typing import List
 import json
 import re
 
@@ -298,8 +299,10 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
 # https://github.com/dgtlmoon/changedetection.io/pull/2041#issuecomment-1848397161w
     # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded within HTML tags
     try:
-        stripped_text_from_html = _parse_json(json.loads(content), json_filter)
-    except json.JSONDecodeError:
+        # .lstrip("\ufeff") strings ByteOrderMark from UTF8 and still lets the UTF work
+        stripped_text_from_html = _parse_json(json.loads(content.lstrip("\ufeff") ), json_filter)
+    except json.JSONDecodeError as e:
+        logger.warning(str(e))
 
         # Foreach <script json></script> blob.. just return the first that matches json_filter
         # As a last resort, try to parse the whole <body>

changedetectionio/model/App.py

@@ -69,7 +69,7 @@ def parse_headers_from_text_file(filepath):
         for l in f.readlines():
             l = l.strip()
             if not l.startswith('#') and ':' in l:
-                (k, v) = l.split(':')
+                (k, v) = l.split(':', 1)  # Split only on the first colon
                 headers[k.strip()] = v.strip()
 
     return headers

changedetectionio/model/Watch.py

@@ -247,37 +247,32 @@ class model(watch_base):
         bump = self.history
         return self.__newest_history_key
 
-    # Given an arbitrary timestamp, find the closest next key
-    # For example, last_viewed = 1000 so it should return the next 1001 timestamp
-    #
-    # used for the [diff] button so it can preset a smarter from_version
+    # Given an arbitrary timestamp, find the best history key for the [diff] button so it can preset a smarter from_version
     @property
-    def get_next_snapshot_key_to_last_viewed(self):
+    def get_from_version_based_on_last_viewed(self):
 
         """Unfortunately for now timestamp is stored as string key"""
         keys = list(self.history.keys())
         if not keys:
             return None
+        if len(keys) == 1:
+            return keys[0]
 
         last_viewed = int(self.get('last_viewed'))
-        prev_k = keys[0]
         sorted_keys = sorted(keys, key=lambda x: int(x))
         sorted_keys.reverse()
 
-        # When the 'last viewed' timestamp is greater than the newest snapshot, return second last
-        if last_viewed > int(sorted_keys[0]):
+        # When the 'last viewed' timestamp is greater than or equal the newest snapshot, return second newest
+        if last_viewed >= int(sorted_keys[0]):
             return sorted_keys[1]
+        
+        # When the 'last viewed' timestamp is between snapshots, return the older snapshot
+        for newer, older in list(zip(sorted_keys[0:], sorted_keys[1:])):
+            if last_viewed < int(newer) and last_viewed >= int(older):
+                return older
 
-        for k in sorted_keys:
-            if int(k) < last_viewed:
-                if prev_k == sorted_keys[0]:
-                    # Return the second last one so we dont recommend the same version compares itself
-                    return sorted_keys[1]
-
-                return prev_k
-            prev_k = k
-
-        return keys[0]
+        # When the 'last viewed' timestamp is less than the oldest snapshot, return oldest
+        return sorted_keys[-1]
 
     def get_history_snapshot(self, timestamp):
         import brotli
@@ -357,7 +352,7 @@ class model(watch_base):
     # Iterate over all history texts and see if something new exists
     # Always applying .strip() to start/end but optionally replace any other whitespace
     def lines_contain_something_unique_compared_to_history(self, lines: list, ignore_whitespace=False):
-        local_lines = []
+        local_lines = set([])
         if lines:
             if ignore_whitespace:
                 if isinstance(lines[0], str): # Can be either str or bytes depending on what was on the disk

changedetectionio/notification.py

@@ -23,7 +23,7 @@ valid_tokens = {
 }
 
 default_notification_format_for_watch = 'System default'
-default_notification_format = 'Text'
+default_notification_format = 'HTML Color'
 default_notification_body = '{{watch_url}} had a change.\n---\n{{diff}}\n---\n'
 default_notification_title = 'ChangeDetection.io Notification - {{watch_url}}'
 
@@ -31,6 +31,7 @@ valid_notification_formats = {
     'Text': NotifyFormat.TEXT,
     'Markdown': NotifyFormat.MARKDOWN,
     'HTML': NotifyFormat.HTML,
+    'HTML Color': 'htmlcolor',
     # Used only for editing a watch (not for global)
     default_notification_format_for_watch: default_notification_format_for_watch
 }
@@ -66,6 +67,10 @@ def process_notification(n_object, datastore):
 
     sent_objs = []
     from .apprise_asset import asset
+
+    if 'as_async' in n_object:
+        asset.async_mode = n_object.get('as_async')
+
     apobj = apprise.Apprise(debug=True, asset=asset)
 
     if not n_object.get('notification_urls'):
@@ -76,9 +81,16 @@ def process_notification(n_object, datastore):
 
             # Get the notification body from datastore
             n_body = jinja_render(template_str=n_object.get('notification_body', ''), **notification_parameters)
+            if n_object.get('notification_format', '').startswith('HTML'):
+                n_body = n_body.replace("\n", '<br>')
+
             n_title = jinja_render(template_str=n_object.get('notification_title', ''), **notification_parameters)
 
             url = url.strip()
+            if url.startswith('#'):
+                logger.trace(f"Skipping commented out notification URL - {url}")
+                continue
+
             if not url:
                 logger.warning(f"Process Notification: skipping empty notification URL.")
                 continue
@@ -149,8 +161,6 @@ def process_notification(n_object, datastore):
             attach=n_object.get('screenshot', None)
         )
 
-        # Give apprise time to register an error
-        time.sleep(3)
 
         # Returns empty string if nothing found, multi-line string otherwise
         log_value = logs.getvalue()

changedetectionio/processors/__init__.py

@@ -33,8 +33,8 @@ class difference_detection_processor():
 
         url = self.watch.link
 
-        # Protect against file://, file:/ access, check the real "link" without any meta "source:" etc prepended.
-        if re.search(r'^file:/', url.strip(), re.IGNORECASE):
+        # Protect against file:, file:/, file:// access, check the real "link" without any meta "source:" etc prepended.
+        if re.search(r'^file:', url.strip(), re.IGNORECASE):
             if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
                 raise Exception(
                     "file:// type access is denied for security reasons."

changedetectionio/static/js/notifications.js

@@ -1,42 +1,52 @@
-$(document).ready(function() {
+$(document).ready(function () {
 
-  $('#add-email-helper').click(function (e) {
-    e.preventDefault();
-    email = prompt("Destination email");
-    if(email) {
-      var n = $(".notification-urls");
-      var p=email_notification_prefix;
-      $(n).val( $.trim( $(n).val() )+"\n"+email_notification_prefix+email );
-    }
-  });
-
-  $('#send-test-notification').click(function (e) {
-    e.preventDefault();
-
-    data = {
-      notification_body: $('#notification_body').val(),
-      notification_format: $('#notification_format').val(),
-      notification_title: $('#notification_title').val(),
-      notification_urls: $('.notification-urls').val(),
-      tags: $('#tags').val(),
-      window_url: window.location.href,
-    }
-
-
-    $.ajax({
-      type: "POST",
-      url: notification_base_url,
-      data : data,
-        statusCode: {
-        400: function(data) {
-          // More than likely the CSRF token was lost when the server restarted
-          alert(data.responseText);
+    $('#add-email-helper').click(function (e) {
+        e.preventDefault();
+        email = prompt("Destination email");
+        if (email) {
+            var n = $(".notification-urls");
+            var p = email_notification_prefix;
+            $(n).val($.trim($(n).val()) + "\n" + email_notification_prefix + email);
         }
-      }
-    }).done(function(data){
-      console.log(data);
-      alert(data);
-    })
-  });
+    });
+
+    $('#send-test-notification').click(function (e) {
+        e.preventDefault();
+
+        data = {
+            notification_body: $('#notification_body').val(),
+            notification_format: $('#notification_format').val(),
+            notification_title: $('#notification_title').val(),
+            notification_urls: $('.notification-urls').val(),
+            tags: $('#tags').val(),
+            window_url: window.location.href,
+        }
+
+        $('.notifications-wrapper .spinner').fadeIn();
+        $('#notification-test-log').show();
+        $.ajax({
+            type: "POST",
+            url: notification_base_url,
+            data: data,
+            statusCode: {
+                400: function (data) {
+                    $("#notification-test-log>span").text(data.responseText);
+                },
+            }
+        }).done(function (data) {
+            $("#notification-test-log>span").text(data);
+        }).fail(function (jqXHR, textStatus, errorThrown) {
+            // Handle connection refused or other errors
+            if (textStatus === "error" && errorThrown === "") {
+                console.error("Connection refused or server unreachable");
+                $("#notification-test-log>span").text("Error: Connection refused or server is unreachable.");
+            } else {
+                console.error("Error:", textStatus, errorThrown);
+                $("#notification-test-log>span").text("An error occurred: " + textStatus);
+            }
+        }).always(function () {
+            $('.notifications-wrapper .spinner').hide();
+        })
+    });
 });
 

changedetectionio/static/styles/scss/styles.scss

@@ -380,7 +380,15 @@ a.pure-button-selected {
 }
 
 .notifications-wrapper {
-  padding: 0.5rem 0 1rem 0;
+  padding-top: 0.5rem;
+  #notification-test-log {
+    padding-top: 1rem;
+    white-space: pre-wrap;
+    word-break: break-word;
+    overflow-wrap: break-word;
+    max-width: 100%;
+    box-sizing: border-box;
+  }
 }
 
 label {

changedetectionio/static/styles/styles.css

@@ -780,7 +780,14 @@ a.pure-button-selected {
   cursor: pointer; }
 
 .notifications-wrapper {
-  padding: 0.5rem 0 1rem 0; }
+  padding-top: 0.5rem; }
+  .notifications-wrapper #notification-test-log {
+    padding-top: 1rem;
+    white-space: pre-wrap;
+    word-break: break-word;
+    overflow-wrap: break-word;
+    max-width: 100%;
+    box-sizing: border-box; }
 
 label:hover {
   cursor: pointer; }

changedetectionio/templates/_common_fields.html

@@ -24,11 +24,13 @@
                               </ul>
                             </div>
                             <div class="notifications-wrapper">
-                              <a id="send-test-notification" class="pure-button button-secondary button-xsmall" >Send test notification</a>
+                              <a id="send-test-notification" class="pure-button button-secondary button-xsmall" >Send test notification</a> <div class="spinner"  style="display: none;"></div>
                             {% if emailprefix %}
                               <a id="add-email-helper" class="pure-button button-secondary button-xsmall" >Add email <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='email.svg')}}" alt="Add an email address"> </a>
                             {% endif %}
                               <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" >Notification debug logs</a>
+                              <br>
+                                <div id="notification-test-log" style="display: none;"><span class="pure-form-message-inline">Processing..</span></div>
                             </div>
                         </div>
                         <div id="notification-customisation" class="pure-control-group">

changedetectionio/templates/edit.html

@@ -45,9 +45,8 @@
             {% if extra_tab_content %}
             <li class="tab"><a href="#extras_tab">{{ extra_tab_content }}</a></li>
             {% endif %}
-            {% if playwright_enabled %}
             <li class="tab"><a id="browsersteps-tab" href="#browser-steps">Browser Steps</a></li>
-            {% endif %}
+        <!-- should goto extra forms? -->
             {% if watch['processor'] == 'text_json_diff' %}
             <li class="tab"><a id="visualselector-tab" href="#visualselector">Visual Filter Selector</a></li>
             <li class="tab" id="filters-and-triggers-tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
@@ -59,7 +58,7 @@
 
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked"
-              action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next'), unpause_on_save = request.args.get('unpause_on_save')) }}" method="POST">
+              action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next'), unpause_on_save = request.args.get('unpause_on_save'), tag = request.args.get('tag')) }}" method="POST">
              <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
 
             <div class="tab-pane-inner" id="general">
@@ -199,8 +198,9 @@ Math: {{ 1 + 1 }}") }}
                     </div>
             </fieldset>
             </div>
-            {% if playwright_enabled %}
+
             <div class="tab-pane-inner" id="browser-steps">
+            {% if playwright_enabled %}
                 <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
                 <fieldset>
                     <div class="pure-control-group">
@@ -240,8 +240,16 @@ Math: {{ 1 + 1 }}") }}
                         </div>
                     </div>
                 </fieldset>
+                {% else %}
+                    <span class="pure-form-message-inline">
+                        <p>Sorry, this functionality only works with Playwright/Chrome enabled watches.</p>
+                        <p>Enable the Playwright Chrome fetcher, or alternatively try our <a href="https://lemonade.changedetection.io/start">very affordable subscription based service</a>.</p>
+                        <p>This is because Selenium/WebDriver can not extract full page screenshots reliably.</p>
+                        <p>You may need to <a href="https://github.com/dgtlmoon/changedetection.io/blob/09ebc6ec6338545bdd694dc6eee57f2e9d2b8075/docker-compose.yml#L31">Enable playwright environment variable</a> and uncomment the <strong>sockpuppetbrowser</strong> from the docker-compose.yml file.</p>
+                    </span>
+                {% endif %}
             </div>
-            {% endif %}
+
 
             <div class="tab-pane-inner" id="notifications">
                 <fieldset>
@@ -493,6 +501,7 @@ keyword") }}
                                 <p>Sorry, this functionality only works with Playwright/Chrome enabled watches.</p>
                                 <p>Enable the Playwright Chrome fetcher, or alternatively try our <a href="https://lemonade.changedetection.io/start">very affordable subscription based service</a>.</p>
                                 <p>This is because Selenium/WebDriver can not extract full page screenshots reliably.</p>
+                                <p>You may need to <a href="https://github.com/dgtlmoon/changedetection.io/blob/09ebc6ec6338545bdd694dc6eee57f2e9d2b8075/docker-compose.yml#L31">Enable playwright environment variable</a> and uncomment the <strong>sockpuppetbrowser</strong> from the docker-compose.yml file.</p>
                             </span>
                         {% endif %}
                     </div>

changedetectionio/templates/settings.html

@@ -280,9 +280,7 @@ nav
                         
                     </div>
                 </div>
-                <p>
-                    Your proxy provider may need to whitelist our IP of <code>204.15.192.195</code>
-                </p>
+
                <p><strong>Tip</strong>: "Residential" and "Mobile" proxy type can be more successfull than "Data Center" for blocked websites.
 
                 <div class="pure-control-group" id="extra-proxies-setting">

changedetectionio/templates/watch-overview.html

@@ -6,7 +6,7 @@
 
 <div class="box">
 
-    <form class="pure-form" action="{{ url_for('form_quick_watch_add') }}" method="POST" id="new-watch-form">
+    <form class="pure-form" action="{{ url_for('form_quick_watch_add', tag=active_tag_uuid) }}" method="POST" id="new-watch-form">
         <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
         <fieldset>
             <legend>Add a new change detection watch</legend>
@@ -108,7 +108,8 @@
                     {% else %}
                     <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause" ></a>
                     {% endif %}
-                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute" ></a>
+                    {% set mute_label = 'UnMute notification' if watch.notification_muted else 'Mute notification' %}
+                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="{{ mute_label }}" title="{{ mute_label }}" class="icon icon-mute" ></a>
                 </td>
                 <td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
                     <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
@@ -187,11 +188,11 @@
                 <td>
                     <a {% if watch.uuid in queued_uuids %}disabled="true"{% endif %} href="{{ url_for('form_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}"
                        class="recheck pure-button pure-button-primary">{% if watch.uuid in queued_uuids %}Queued{% else %}Recheck{% endif %}</a>
-                    <a href="{{ url_for('edit_page', uuid=watch.uuid)}}#general" class="pure-button pure-button-primary">Edit</a>
+                    <a href="{{ url_for('edit_page', uuid=watch.uuid, tag=active_tag_uuid)}}#general" class="pure-button pure-button-primary">Edit</a>
                     {% if watch.history_n >= 2 %}
 
                         {%  if is_unviewed %}
-                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid, from_version=watch.get_next_snapshot_key_to_last_viewed) }}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">History</a>
+                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid, from_version=watch.get_from_version_based_on_last_viewed) }}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">History</a>
                         {% else %}
                            <a href="{{ url_for('diff_history_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">History</a>
                         {% endif %}

changedetectionio/tests/fetchers/test_custom_js_before_content.py

@@ -34,7 +34,7 @@ def test_execute_custom_js(client, live_server, measure_memory_usage):
     assert b"unpaused" in res.data
     wait_for_all_checks(client)
 
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n >= 1, "Watch history had atleast 1 (everything fetched OK)"
 
     assert b"This text should be removed" not in res.data

changedetectionio/tests/proxy_list/test_noproxy.py

@@ -48,7 +48,7 @@ def test_noproxy_option(client, live_server, measure_memory_usage):
         follow_redirects=True
     )
     assert b"Watch added in Paused state, saving will unpause" in res.data
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     res = client.get(
         url_for("edit_page", uuid=uuid, unpause_on_save=1))
     assert b'No proxy' in res.data

changedetectionio/tests/proxy_socks5/test_socks5_proxy.py

@@ -81,7 +81,7 @@ def test_socks5(client, live_server, measure_memory_usage):
     assert "Awesome, you made it".encode('utf-8') in res.data
 
     # PROXY CHECKER WIDGET CHECK - this needs more checking
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
 
     res = client.get(
         url_for("check_proxies.start_check", uuid=uuid),

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -1,9 +1,9 @@
 #!/usr/bin/env python3
+
 import os.path
-import time
+
 from flask import url_for
 from .util import live_server_setup, wait_for_all_checks, wait_for_notification_endpoint_output
-from changedetectionio import html_tools
 
 
 def set_original(excluding=None, add_line=None):
@@ -113,7 +113,8 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     res = client.post(
         url_for("settings_page"),
         data={"application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
-              "application-notification_body": 'triggered text was -{{triggered_text}}- 网站监测 内容更新了',
+              # triggered_text will contain multiple lines
+              "application-notification_body": 'triggered text was -{{triggered_text}}- ### 网站监测 内容更新了 ####',
               # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
               "application-notification_urls": test_notification_url,
               "application-minutes_between_check": 180,
@@ -171,7 +172,7 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     assert os.path.isfile("test-datastore/notification.txt"), "Notification fired because I can see the output file"
     with open("test-datastore/notification.txt", 'rb') as f:
         response = f.read()
-        assert b'-Oh yes please-' in response
+        assert b'-Oh yes please' in response
         assert '网站监测 内容更新了'.encode('utf-8') in response
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

changedetectionio/tests/test_api.py

@@ -44,7 +44,6 @@ def set_modified_response():
 
     return None
 
-
 def is_valid_uuid(val):
     try:
         uuid.UUID(str(val))
@@ -56,8 +55,9 @@ def is_valid_uuid(val):
 def test_setup(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
 
+
 def test_api_simple(client, live_server, measure_memory_usage):
-    #live_server_setup(live_server)
+#    live_server_setup(live_server)
 
     api_key = extract_api_key_from_UI(client)
 
@@ -129,6 +129,9 @@ def test_api_simple(client, live_server, measure_memory_usage):
     assert after_recheck_info['last_checked'] != before_recheck_info['last_checked']
     assert after_recheck_info['last_changed'] != 0
 
+    # #2877 When run in a slow fetcher like playwright etc
+    assert after_recheck_info['last_changed'] ==  after_recheck_info['last_checked']
+
     # Check history index list
     res = client.get(
         url_for("watchhistory", uuid=watch_uuid),

changedetectionio/tests/test_automatic_follow_ldjson_price.py

@@ -99,7 +99,7 @@ def test_check_ldjson_price_autodetect(client, live_server, measure_memory_usage
     assert b'ldjson-price-track-offer' in res.data
 
     # Accept it
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     #time.sleep(1)
     client.get(url_for('price_data_follower.accept', uuid=uuid, follow_redirects=True))
     client.get(url_for("form_watch_checknow"), follow_redirects=True)

changedetectionio/tests/test_backend.py

@@ -2,7 +2,6 @@
 
 import time
 from flask import url_for
-from urllib.request import urlopen
 from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI, \
     extract_UUID_from_client
 
@@ -69,7 +68,7 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
 
     wait_for_all_checks(client)
 
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
 
     # Check the 'get latest snapshot works'
     res = client.get(url_for("watch_get_latest_html", uuid=uuid))

changedetectionio/tests/test_encoding.py

@@ -40,7 +40,7 @@ def test_check_encoding_detection(client, live_server, measure_memory_usage):
 
 
     # Content type recording worked
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     assert live_server.app.config['DATASTORE'].data['watching'][uuid]['content-type'] == "text/html"
 
     res = client.get(

changedetectionio/tests/test_filter_failure_notification.py

@@ -51,7 +51,7 @@ def run_filter_test(client, live_server, content_filter):
     assert b"1 Imported" in res.data
     wait_for_all_checks(client)
 
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
 
     assert live_server.app.config['DATASTORE'].data['watching'][uuid]['consecutive_filter_failures'] == 0, "No filter = No filter failure"
 

changedetectionio/tests/test_group.py

@@ -288,7 +288,7 @@ def test_clone_tag_on_import(client, live_server, measure_memory_usage):
     assert b'test-tag' in res.data
     assert b'another-tag' in res.data
 
-    watch_uuid = extract_UUID_from_client(client)
+    watch_uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     res = client.get(url_for("form_clone", uuid=watch_uuid), follow_redirects=True)
 
     assert b'Cloned' in res.data
@@ -315,7 +315,7 @@ def test_clone_tag_on_quickwatchform_add(client, live_server, measure_memory_usa
     assert b'test-tag' in res.data
     assert b'another-tag' in res.data
 
-    watch_uuid = extract_UUID_from_client(client)
+    watch_uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     res = client.get(url_for("form_clone", uuid=watch_uuid), follow_redirects=True)
 
     assert b'Cloned' in res.data

changedetectionio/tests/test_ignore.py

@@ -36,7 +36,7 @@ def test_ignore(client, live_server, measure_memory_usage):
 
     # Give the thread time to pick it up
     wait_for_all_checks(client)
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     # use the highlighter endpoint
     res = client.post(
         url_for("highlight_submit_ignore_url", uuid=uuid),

changedetectionio/tests/test_jsonpath_jq_selector.py

@@ -514,3 +514,15 @@ def test_check_jq_ext_filter(client, live_server, measure_memory_usage):
 def test_check_jqraw_ext_filter(client, live_server, measure_memory_usage):
     if jq_support:
         check_json_ext_filter('jq:.[] | select(.status | contains("Sold"))', client, live_server)
+
+def test_jsonpath_BOM_utf8(client, live_server, measure_memory_usage):
+    from .. import html_tools
+
+    # JSON string with BOM and correct double-quoted keys
+    json_str = '\ufeff{"name": "José", "emoji": "😊", "language": "中文", "greeting": "Привет"}'
+
+    # See that we can find the second <script> one, which is not broken, and matches our filter
+    text = html_tools.extract_json_as_string(json_str, "json:$.name")
+    assert text == '"José"'
+
+    

changedetectionio/tests/test_live_preview.py

@@ -29,7 +29,7 @@ def test_content_filter_live_preview(client, live_server, measure_memory_usage):
         data={"url": test_url, "tags": ''},
         follow_redirects=True
     )
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     res = client.post(
         url_for("edit_page", uuid=uuid),
         data={

changedetectionio/tests/test_nonrenderable_pages.py

@@ -48,7 +48,7 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     #####################
     client.post(
         url_for("settings_page"),
-        data={"application-empty_pages_are_a_change": "",
+        data={"application-empty_pages_are_a_change": "", # default, OFF, they are NOT a change
               "requests-time_between_check-minutes": 180,
               'application-fetch_backend': "html_requests"},
         follow_redirects=True
@@ -66,6 +66,14 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
 
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
+    watch = live_server.app.config['DATASTORE'].data['watching'][uuid]
+
+    assert watch.last_changed == 0
+    assert watch['last_checked'] != 0
+
+
+
 
     # ok now do the opposite
 
@@ -92,6 +100,10 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     # A totally zero byte (#2528) response should also not trigger an error
     set_zero_byte_response()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
+    # 2877
+    assert watch.last_changed == watch['last_checked']
+
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data # A change should have registered because empty_pages_are_a_change is ON

changedetectionio/tests/test_notification.py

@@ -6,7 +6,7 @@ from flask import url_for
 from loguru import logger
 
 from .util import set_original_response, set_modified_response, set_more_modified_response, live_server_setup, wait_for_all_checks, \
-    set_longer_modified_response
+    set_longer_modified_response, get_index
 from . util import  extract_UUID_from_client
 import logging
 import base64
@@ -29,7 +29,7 @@ def test_check_notification(client, live_server, measure_memory_usage):
 
     # Re 360 - new install should have defaults set
     res = client.get(url_for("settings_page"))
-    notification_url = url_for('test_notification_endpoint', _external=True).replace('http', 'json')
+    notification_url = url_for('test_notification_endpoint', _external=True).replace('http', 'json')+"?status_code=204"
 
     assert default_notification_body.encode() in res.data
     assert default_notification_title.encode() in res.data
@@ -76,7 +76,7 @@ def test_check_notification(client, live_server, measure_memory_usage):
     testimage_png = 'iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYII='
 
 
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     datastore = 'test-datastore'
     with open(os.path.join(datastore, str(uuid), 'last-screenshot.png'), 'wb') as f:
         f.write(base64.b64decode(testimage_png))
@@ -135,7 +135,14 @@ def test_check_notification(client, live_server, measure_memory_usage):
 
     # Trigger a check
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
     time.sleep(3)
+
+    # Check no errors were recorded
+    res = client.get(url_for("index"))
+    assert b'notification-error' not in res.data
+
+
     # Verify what was sent as a notification, this file should exist
     with open("test-datastore/notification.txt", "r") as f:
         notification_submission = f.read()
@@ -284,7 +291,7 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
     # CUSTOM JSON BODY CHECK for POST://
     set_original_response()
     # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#header-manipulation
-    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?xxx={{ watch_url }}&+custom-header=123&+second=hello+world%20%22space%22"
+    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?status_code=204&xxx={{ watch_url }}&+custom-header=123&+second=hello+world%20%22space%22"
 
     res = client.post(
         url_for("settings_page"),
@@ -319,6 +326,11 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
 
     time.sleep(2) # plus extra delay for notifications to fire
 
+
+    # Check no errors were recorded, because we asked for 204 which is slightly uncommon but is still OK
+    res = get_index(client)
+    assert b'notification-error' not in res.data
+
     with open("test-datastore/notification.txt", 'r') as f:
         x = f.read()
         j = json.loads(x)
@@ -360,7 +372,10 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
     #live_server_setup(live_server)
     set_original_response()
     if os.path.isfile("test-datastore/notification.txt"):
-        os.unlink("test-datastore/notification.txt")
+        os.unlink("test-datastore/notification.txt") \
+
+    # 1995 UTF-8 content should be encoded
+    test_body = 'change detection is cool 网站监测 内容更新了'
 
     # otherwise other settings would have already existed from previous tests in this file
     res = client.post(
@@ -368,8 +383,7 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
         data={
             "application-fetch_backend": "html_requests",
             "application-minutes_between_check": 180,
-            #1995 UTF-8 content should be encoded
-            "application-notification_body": 'change detection is cool 网站监测 内容更新了',
+            "application-notification_body": test_body,
             "application-notification_format": default_notification_format,
             "application-notification_urls": "",
             "application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
@@ -399,12 +413,10 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
     assert res.status_code != 400
     assert res.status_code != 500
 
-    # Give apprise time to fire
-    time.sleep(4)
 
     with open("test-datastore/notification.txt", 'r') as f:
         x = f.read()
-        assert 'change detection is cool 网站监测 内容更新了' in x
+        assert test_body in x
 
     os.unlink("test-datastore/notification.txt")
 
@@ -442,4 +454,67 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
     assert b"Error: You must have atleast one watch configured for 'test notification' to work" in res.data
 
 
+def _test_color_notifications(client, notification_body_token):
 
+    from changedetectionio.diff import ADDED_STYLE, REMOVED_STYLE
+
+    set_original_response()
+
+    if os.path.isfile("test-datastore/notification.txt"):
+        os.unlink("test-datastore/notification.txt")
+
+
+    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?xxx={{ watch_url }}&+custom-header=123"
+
+
+    # otherwise other settings would have already existed from previous tests in this file
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "application-fetch_backend": "html_requests",
+            "application-minutes_between_check": 180,
+            "application-notification_body": notification_body_token,
+            "application-notification_format": "HTML Color",
+            "application-notification_urls": test_notification_url,
+            "application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
+        },
+        follow_redirects=True
+    )
+    assert b'Settings updated' in res.data
+
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": 'nice one'},
+        follow_redirects=True
+    )
+
+    assert b"Watch added" in res.data
+
+    wait_for_all_checks(client)
+
+    set_modified_response()
+
+
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
+
+    wait_for_all_checks(client)
+    time.sleep(3)
+
+    with open("test-datastore/notification.txt", 'r') as f:
+        x = f.read()
+        assert f'<span style="{REMOVED_STYLE}">Which is across multiple lines' in x
+
+
+    client.get(
+        url_for("form_delete", uuid="all"),
+        follow_redirects=True
+    )
+
+def test_html_color_notifications(client, live_server, measure_memory_usage):
+
+    #live_server_setup(live_server)
+    _test_color_notifications(client, '{{diff}}')
+    _test_color_notifications(client, '{{diff_full}}')
+    

changedetectionio/tests/test_request.py

@@ -373,13 +373,14 @@ def test_headers_textfile_in_request(client, live_server, measure_memory_usage):
     wait_for_all_checks(client)
 
     with open('test-datastore/headers-testtag.txt', 'w') as f:
-        f.write("tag-header: test")
+        f.write("tag-header: test\r\nurl-header: http://example.com")
 
     with open('test-datastore/headers.txt', 'w') as f:
-        f.write("global-header: nice\r\nnext-global-header: nice")
+        f.write("global-header: nice\r\nnext-global-header: nice\r\nurl-header-global: http://example.com/global")
 
-    with open('test-datastore/' + extract_UUID_from_client(client) + '/headers.txt', 'w') as f:
-        f.write("watch-header: nice")
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
+    with open(f'test-datastore/{uuid}/headers.txt', 'w') as f:
+        f.write("watch-header: nice\r\nurl-header-watch: http://example.com/watch")
 
     wait_for_all_checks(client)
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
@@ -410,6 +411,9 @@ def test_headers_textfile_in_request(client, live_server, measure_memory_usage):
     assert b"Xxx:ooo" in res.data
     assert b"Watch-Header:nice" in res.data
     assert b"Tag-Header:test" in res.data
+    assert b"Url-Header:http://example.com" in res.data
+    assert b"Url-Header-Global:http://example.com/global" in res.data
+    assert b"Url-Header-Watch:http://example.com/watch" in res.data
 
     # Check the custom UA from system settings page made it through
     if os.getenv('PLAYWRIGHT_DRIVER_URL'):

changedetectionio/tests/test_restock_itemprop.py

@@ -189,6 +189,17 @@ def _run_test_minmax_limit(client, extra_watch_edit_form):
 
     client.get(url_for("mark_all_viewed"))
 
+
+    # 2715 - Price detection (once it crosses the "lower" threshold) again with a lower price - should trigger again!
+    set_original_response(props_markup=instock_props[0], price='820.45')
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'820.45' in res.data
+    assert b'unviewed' in res.data
+    client.get(url_for("mark_all_viewed"))
+
     # price changed to something MORE than max (1100.10), SHOULD be a change
     set_original_response(props_markup=instock_props[0], price='1890.45')
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
@@ -203,7 +214,7 @@ def _run_test_minmax_limit(client, extra_watch_edit_form):
 
 
 def test_restock_itemprop_minmax(client, live_server):
-#    live_server_setup(live_server)
+    #live_server_setup(live_server)
     extras = {
         "restock_settings-follow_price_changes": "y",
         "restock_settings-price_change_min": 900.0,
@@ -369,7 +380,7 @@ def test_change_with_notification_values(client, live_server):
 
     ## Now test the "SEND TEST NOTIFICATION" is working
     os.unlink("test-datastore/notification.txt")
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     res = client.post(url_for("ajax_callback_send_notification_test", watch_uuid=uuid), data={}, follow_redirects=True)
     time.sleep(5)
     assert os.path.isfile("test-datastore/notification.txt"), "Notification received"

changedetectionio/tests/test_rss.py

@@ -132,7 +132,7 @@ def test_rss_xpath_filtering(client, live_server, measure_memory_usage):
     )
     assert b"Watch added in Paused state, saving will unpause" in res.data
 
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     res = client.post(
         url_for("edit_page", uuid=uuid, unpause_on_save=1),
         data={

changedetectionio/tests/test_scheduler.py

@@ -39,7 +39,7 @@ def test_check_basic_scheduler_functionality(client, live_server, measure_memory
 
     assert b"1 Imported" in res.data
     wait_for_all_checks(client)
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
 
     # Setup all the days of the weeks using XXX as the placeholder for monday/tuesday/etc
 
@@ -104,7 +104,7 @@ def test_check_basic_global_scheduler_functionality(client, live_server, measure
 
     assert b"1 Imported" in res.data
     wait_for_all_checks(client)
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
 
     # Setup all the days of the weeks using XXX as the placeholder for monday/tuesday/etc
 

changedetectionio/tests/test_security.py

@@ -1,9 +1,7 @@
 import os
 
 from flask import url_for
-from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
-import time
-
+from .util import live_server_setup, wait_for_all_checks
 from .. import strtobool
 
 
@@ -61,54 +59,44 @@ def test_bad_access(client, live_server, measure_memory_usage):
     assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
 
 
-def test_file_slashslash_access(client, live_server, measure_memory_usage):
-    #live_server_setup(live_server)
+def _runner_test_various_file_slash(client, file_uri):
 
-    test_file_path = os.path.abspath(__file__)
-
-    # file:// is permitted by default, but it will be caught by ALLOW_FILE_URI
     client.post(
         url_for("form_quick_watch_add"),
-        data={"url": f"file://{test_file_path}", "tags": ''},
+        data={"url": file_uri, "tags": ''},
         follow_redirects=True
     )
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
 
+    substrings = [b"URLs with hostname components are not permitted", b"No connection adapters were found for"]
+
+
     # If it is enabled at test time
     if strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
-        res = client.get(
-            url_for("preview_page", uuid="first"),
-            follow_redirects=True
-        )
+        if file_uri.startswith('file:///'):
+            # This one should be the full qualified path to the file and should get the contents of this file
+            res = client.get(
+                url_for("preview_page", uuid="first"),
+                follow_redirects=True
+            )
+            assert b'_runner_test_various_file_slash' in res.data
+        else:
+            # This will give some error from requests or if it went to chrome, will give some other error :-)
+            assert any(s in res.data for s in substrings)
 
-        assert b"test_file_slashslash_access" in res.data
-    else:
-        # Default should be here
-        assert b'file:// type access is denied for security reasons.' in res.data
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
 
 def test_file_slash_access(client, live_server, measure_memory_usage):
     #live_server_setup(live_server)
 
+    # file: is NOT permitted by default, so it will be caught by ALLOW_FILE_URI check
+
     test_file_path = os.path.abspath(__file__)
-
-    # file:// is permitted by default, but it will be caught by ALLOW_FILE_URI
-    client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": f"file:/{test_file_path}", "tags": ''},
-        follow_redirects=True
-    )
-    wait_for_all_checks(client)
-    res = client.get(url_for("index"))
-
-    # If it is enabled at test time
-    if strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
-        # So it should permit it, but it should fall back to the 'requests' library giving an error
-        # (but means it gets passed to playwright etc)
-        assert b"URLs with hostname components are not permitted" in res.data
-    else:
-        # Default should be here
-        assert b'file:// type access is denied for security reasons.' in res.data
+    _runner_test_various_file_slash(client, file_uri=f"file://{test_file_path}")
+    _runner_test_various_file_slash(client, file_uri=f"file:/{test_file_path}")
+    _runner_test_various_file_slash(client, file_uri=f"file:{test_file_path}") # CVE-2024-56509
 
 def test_xss(client, live_server, measure_memory_usage):
     #live_server_setup(live_server)

changedetectionio/tests/unit/test_semver.py

@@ -0,0 +1,64 @@
+#!/usr/bin/env python3
+
+# run from dir above changedetectionio/ dir
+# python3 -m unittest changedetectionio.tests.unit.test_semver
+
+import re
+import unittest
+
+
+# The SEMVER regex
+SEMVER_REGEX = r"^(?P<major>0|[1-9]\d*)\.(?P<minor>0|[1-9]\d*)\.(?P<patch>0|[1-9]\d*)(?:-(?P<prerelease>(?:0|[1-9]\d*|\d*[a-zA-Z-][0-9a-zA-Z-]*)(?:\.(?:0|[1-9]\d*|\d*[a-zA-Z-][0-9a-zA-Z-]*))*))?(?:\+(?P<buildmetadata>[0-9a-zA-Z-]+(?:\.[0-9a-zA-Z-]+)*))?$"
+
+# Compile the regex
+semver_pattern = re.compile(SEMVER_REGEX)
+
+class TestSemver(unittest.TestCase):
+    def test_valid_versions(self):
+        """Test valid semantic version strings"""
+        valid_versions = [
+            "1.0.0",
+            "0.1.0",
+            "0.0.1",
+            "1.0.0-alpha",
+            "1.0.0-alpha.1",
+            "1.0.0-0.3.7",
+            "1.0.0-x.7.z.92",
+            "1.0.0-alpha+001",
+            "1.0.0+20130313144700",
+            "1.0.0-beta+exp.sha.5114f85"
+        ]
+        for version in valid_versions:
+            with self.subTest(version=version):
+                self.assertIsNotNone(semver_pattern.match(version), f"Version {version} should be valid")
+
+    def test_invalid_versions(self):
+        """Test invalid semantic version strings"""
+        invalid_versions = [
+            "0.48.06",
+            "1.0",
+            "1.0.0-",
+# Seems to pass the semver.org regex?
+#            "1.0.0-alpha-",
+            "1.0.0+",
+            "1.0.0-alpha+",
+            "1.0.0-",
+            "01.0.0",
+            "1.01.0",
+            "1.0.01",
+            ".1.0.0",
+            "1..0.0"
+        ]
+        for version in invalid_versions:
+            with self.subTest(version=version):
+                res = semver_pattern.match(version)
+                self.assertIsNone(res, f"Version '{version}' should be invalid")
+
+    def test_our_version(self):
+        from changedetectionio import get_version
+        our_version = get_version()
+        self.assertIsNotNone(semver_pattern.match(our_version), f"Our version '{our_version}' should be a valid SEMVER string")
+
+
+if __name__ == '__main__':
+    unittest.main()

changedetectionio/tests/unit/test_watch_model.py

@@ -16,7 +16,6 @@ class TestDiffBuilder(unittest.TestCase):
         watch = Watch.model(datastore_path='/tmp', default={})
         watch.ensure_data_dir_exists()
 
-        watch['last_viewed'] = 110
 
         # Contents from the browser are always returned from the browser/requests/etc as str, str is basically UTF-16 in python
         watch.save_history_text(contents="hello world", timestamp=100, snapshot_id=str(uuid_builder.uuid4()))
@@ -25,31 +24,42 @@ class TestDiffBuilder(unittest.TestCase):
         watch.save_history_text(contents="hello world", timestamp=112, snapshot_id=str(uuid_builder.uuid4()))
         watch.save_history_text(contents="hello world", timestamp=115, snapshot_id=str(uuid_builder.uuid4()))
         watch.save_history_text(contents="hello world", timestamp=117, snapshot_id=str(uuid_builder.uuid4()))
+    
+        p = watch.get_from_version_based_on_last_viewed
+        assert p == "100", "Correct 'last viewed' timestamp was detected"
 
-        p = watch.get_next_snapshot_key_to_last_viewed
-        assert p == "112", "Correct last-viewed timestamp was detected"
+        watch['last_viewed'] = 110
+        p = watch.get_from_version_based_on_last_viewed
+        assert p == "109", "Correct 'last viewed' timestamp was detected"
 
-        # When there is only one step of difference from the end of the list, it should return second-last change
         watch['last_viewed'] = 116
-        p = watch.get_next_snapshot_key_to_last_viewed
-        assert p == "115", "Correct 'second last' last-viewed timestamp was detected when using the last timestamp"
+        p = watch.get_from_version_based_on_last_viewed
+        assert p == "115", "Correct 'last viewed' timestamp was detected"
 
         watch['last_viewed'] = 99
-        p = watch.get_next_snapshot_key_to_last_viewed
-        assert p == "100"
+        p = watch.get_from_version_based_on_last_viewed
+        assert p == "100", "When the 'last viewed' timestamp is less than the oldest snapshot, return oldest"
 
         watch['last_viewed'] = 200
-        p = watch.get_next_snapshot_key_to_last_viewed
-        assert p == "115", "When the 'last viewed' timestamp is greater than the newest snapshot, return second last "
+        p = watch.get_from_version_based_on_last_viewed
+        assert p == "115", "When the 'last viewed' timestamp is greater than the newest snapshot, return second newest"
 
         watch['last_viewed'] = 109
-        p = watch.get_next_snapshot_key_to_last_viewed
+        p = watch.get_from_version_based_on_last_viewed
         assert p == "109", "Correct when its the same time"
 
         # new empty one
         watch = Watch.model(datastore_path='/tmp', default={})
-        p = watch.get_next_snapshot_key_to_last_viewed
+        p = watch.get_from_version_based_on_last_viewed
         assert p == None, "None when no history available"
 
+        watch.save_history_text(contents="hello world", timestamp=100, snapshot_id=str(uuid_builder.uuid4()))
+        p = watch.get_from_version_based_on_last_viewed
+        assert p == "100", "Correct with only one history snapshot"
+
+        watch['last_viewed'] = 200
+        p = watch.get_from_version_based_on_last_viewed
+        assert p == "100", "Correct with only one history snapshot"
+
 if __name__ == '__main__':
     unittest.main()

changedetectionio/tests/util.py

@@ -76,6 +76,14 @@ def set_more_modified_response():
     return None
 
 
+def set_empty_text_response():
+    test_return_data = """<html><body></body></html>"""
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+    return None
+
 def wait_for_notification_endpoint_output():
     '''Apprise can take a few seconds to fire'''
     #@todo - could check the apprise object directly instead of looking for this file
@@ -215,9 +223,10 @@ def live_server_setup(live_server):
     def test_method():
         return request.method
 
-    # Where we POST to as a notification
-    @live_server.app.route('/test_notification_endpoint', methods=['POST', 'GET'])
+    # Where we POST to as a notification, also use a space here to test URL escaping is OK across all tests that use this. ( #2868 )
+    @live_server.app.route('/test_notification endpoint', methods=['POST', 'GET'])
     def test_notification_endpoint():
+
         with open("test-datastore/notification.txt", "wb") as f:
             # Debug method, dump all POST to file also, used to prove #65
             data = request.stream.read()
@@ -235,8 +244,11 @@ def live_server_setup(live_server):
                 f.write(request.content_type)
 
         print("\n>> Test notification endpoint was hit.\n", data)
-        return "Text was set"
 
+        content = "Text was set"
+        status_code = request.args.get('status_code',200)
+        resp = make_response(content, status_code)
+        return resp
 
     # Just return the verb in the request
     @live_server.app.route('/test-basicauth', methods=['GET'])
@@ -273,15 +285,43 @@ def live_server_setup(live_server):
             <p id="remove">This text should be removed</p>
               <form onsubmit="event.preventDefault();">
             <!-- obfuscated text so that we dont accidentally get a false positive due to conversion of the source :) --->
-                <button name="test-button" onclick="getElementById('remove').remove();getElementById('some-content').innerHTML = atob('SSBzbWVsbCBKYXZhU2NyaXB0IGJlY2F1c2UgdGhlIGJ1dHRvbiB3YXMgcHJlc3NlZCE=')">Click here</button>
-                <div id=some-content></div>
+                <button name="test-button" onclick="
+                getElementById('remove').remove();
+                getElementById('some-content').innerHTML = atob('SSBzbWVsbCBKYXZhU2NyaXB0IGJlY2F1c2UgdGhlIGJ1dHRvbiB3YXMgcHJlc3NlZCE=');
+                getElementById('reflect-text').innerHTML = getElementById('test-input-text').value;
+                ">Click here</button>
+                
+                <div id="some-content"></div>
+                
                 <pre>
                 {header_text.lower()}
                 </pre>
-              </body>
+                
+                <br>
+                <!-- used for testing that the jinja2 compiled here --->
+                <input type="text" value="" id="test-input-text" /><br>
+                <div id="reflect-text">Waiting to reflect text from #test-input-text here</div>
+              </form>
+                
+           </body>
          </html>""", 200)
         resp.headers['Content-Type'] = 'text/html'
         return resp
 
     live_server.start()
 
+def get_index(client):
+    import inspect
+    # Get the caller's frame (parent function)
+    frame = inspect.currentframe()
+    caller_frame = frame.f_back  # Go back to the caller's frame
+    caller_name = caller_frame.f_code.co_name
+    caller_line = caller_frame.f_lineno
+
+    print(f"Called by: {caller_name}, Line: {caller_line}")
+
+    res = client.get(url_for("index"))
+    with open(f"test-datastore/index-{caller_name}-{caller_line}.html", 'wb') as f:
+        f.write(res.data)
+
+    return res

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -2,14 +2,16 @@
 
 import os
 from flask import url_for
-from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+from ..util import live_server_setup, wait_for_all_checks, get_index
 
-def test_setup(client, live_server, measure_memory_usage):
+def test_setup(client, live_server):
     live_server_setup(live_server)
 
 
 # Add a site in paused mode, add an invalid filter, we should still have visual selector data ready
 def test_visual_selector_content_ready(client, live_server, measure_memory_usage):
+    live_server.stop()
+    live_server.start()
 
     import os
     import json
@@ -27,7 +29,7 @@ def test_visual_selector_content_ready(client, live_server, measure_memory_usage
         follow_redirects=True
     )
     assert b"Watch added in Paused state, saving will unpause" in res.data
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     res = client.post(
         url_for("edit_page", uuid=uuid, unpause_on_save=1),
         data={
@@ -87,7 +89,9 @@ def test_visual_selector_content_ready(client, live_server, measure_memory_usage
 
 def test_basic_browserstep(client, live_server, measure_memory_usage):
 
-    #live_server_setup(live_server)
+    live_server.stop()
+    live_server.start()
+
     assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
 
     test_url = url_for('test_interactive_html_endpoint', _external=True)
@@ -108,9 +112,13 @@ def test_basic_browserstep(client, live_server, measure_memory_usage):
             "url": test_url,
             "tags": "",
             'fetch_backend': "html_webdriver",
-            'browser_steps-0-operation': 'Click element',
-            'browser_steps-0-selector': 'button[name=test-button]',
-            'browser_steps-0-optional_value': '',
+            'browser_steps-0-operation': 'Enter text in field',
+            'browser_steps-0-selector': '#test-input-text',
+            # Should get set to the actual text (jinja2 rendered)
+            'browser_steps-0-optional_value': "Hello-Jinja2-{% now  'Europe/Berlin', '%Y-%m-%d' %}",
+            'browser_steps-1-operation': 'Click element',
+            'browser_steps-1-selector': 'button[name=test-button]',
+            'browser_steps-1-optional_value': '',
             # For now, cookies doesnt work in headers because it must be a full cookiejar object
             'headers': "testheader: yes\buser-agent: MyCustomAgent",
         },
@@ -119,7 +127,7 @@ def test_basic_browserstep(client, live_server, measure_memory_usage):
     assert b"unpaused" in res.data
     wait_for_all_checks(client)
 
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n >= 1, "Watch history had atleast 1 (everything fetched OK)"
 
     assert b"This text should be removed" not in res.data
@@ -132,13 +140,32 @@ def test_basic_browserstep(client, live_server, measure_memory_usage):
     assert b"This text should be removed" not in res.data
     assert b"I smell JavaScript because the button was pressed" in res.data
 
+    assert b'Hello-Jinja2-20' in res.data
+
     assert b"testheader: yes" in res.data
     assert b"user-agent: mycustomagent" in res.data
+    live_server.stop()
+
+def test_non_200_errors_report_browsersteps(client, live_server):
+
+    live_server.stop()
+    live_server.start()
 
     four_o_four_url =  url_for('test_endpoint', status_code=404, _external=True)
     four_o_four_url = four_o_four_url.replace('localhost.localdomain', 'cdio')
     four_o_four_url = four_o_four_url.replace('localhost', 'cdio')
 
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": four_o_four_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
+
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
+
     # now test for 404 errors
     res = client.post(
         url_for("edit_page", uuid=uuid, unpause_on_save=1),
@@ -153,12 +180,14 @@ def test_basic_browserstep(client, live_server, measure_memory_usage):
         follow_redirects=True
     )
     assert b"unpaused" in res.data
+
     wait_for_all_checks(client)
 
-    res = client.get(url_for("index"))
+    res = get_index(client)
+
     assert b'Error - 404' in res.data
 
     client.get(
         url_for("form_delete", uuid="all"),
         follow_redirects=True
-    )
+    )

changedetectionio/update_worker.py

@@ -28,6 +28,8 @@ class update_worker(threading.Thread):
 
     def queue_notification_for_watch(self, notification_q, n_object, watch):
         from changedetectionio import diff
+        from changedetectionio.notification import default_notification_format_for_watch
+
         dates = []
         trigger_text = ''
 
@@ -44,11 +46,21 @@ class update_worker(threading.Thread):
         else:
             snapshot_contents = "No snapshot/history available, the watch should fetch atleast once."
 
+        # If we ended up here with "System default"
+        if n_object.get('notification_format') == default_notification_format_for_watch:
+            n_object['notification_format'] = self.datastore.data['settings']['application'].get('notification_format')
+
+        html_colour_enable = False
         # HTML needs linebreak, but MarkDown and Text can use a linefeed
         if n_object.get('notification_format') == 'HTML':
             line_feed_sep = "<br>"
             # Snapshot will be plaintext on the disk, convert to some kind of HTML
             snapshot_contents = snapshot_contents.replace('\n', line_feed_sep)
+        elif n_object.get('notification_format') == 'HTML Color':
+            line_feed_sep = "<br>"
+            # Snapshot will be plaintext on the disk, convert to some kind of HTML
+            snapshot_contents = snapshot_contents.replace('\n', line_feed_sep)
+            html_colour_enable = True
         else:
             line_feed_sep = "\n"
 
@@ -69,9 +81,9 @@ class update_worker(threading.Thread):
 
         n_object.update({
             'current_snapshot': snapshot_contents,
-            'diff': diff.render_diff(prev_snapshot, current_snapshot, line_feed_sep=line_feed_sep),
+            'diff': diff.render_diff(prev_snapshot, current_snapshot, line_feed_sep=line_feed_sep, html_colour=html_colour_enable),
             'diff_added': diff.render_diff(prev_snapshot, current_snapshot, include_removed=False, line_feed_sep=line_feed_sep),
-            'diff_full': diff.render_diff(prev_snapshot, current_snapshot, include_equal=True, line_feed_sep=line_feed_sep),
+            'diff_full': diff.render_diff(prev_snapshot, current_snapshot, include_equal=True, line_feed_sep=line_feed_sep, html_colour=html_colour_enable),
             '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,
@@ -231,7 +243,6 @@ class update_worker(threading.Thread):
                 os.unlink(full_path)
 
     def run(self):
-        now = time.time()
         
         while not self.app.config.exit.is_set():
             update_handler = None
@@ -242,6 +253,7 @@ class update_worker(threading.Thread):
                 pass
 
             else:
+                fetch_start_time = time.time()
                 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'):
@@ -256,7 +268,6 @@ class update_worker(threading.Thread):
                     watch = self.datastore.data['watching'].get(uuid)
 
                     logger.info(f"Processing watch UUID {uuid} Priority {queued_item_data.priority} URL {watch['url']}")
-                    now = time.time()
 
                     try:
                         # Processor is what we are using for detecting the "Change"
@@ -276,6 +287,10 @@ class update_worker(threading.Thread):
 
                         update_handler.call_browser()
 
+                        # In reality, the actual time of when the change was detected could be a few seconds after this
+                        # For example it should include when the page stopped rendering if using a playwright/chrome type fetch
+                        fetch_start_time = time.time()
+
                         changed_detected, update_obj, contents = update_handler.run_changedetection(watch=watch)
 
                         # Re #342
@@ -500,7 +515,7 @@ class update_worker(threading.Thread):
 
                     if not self.datastore.data['watching'].get(uuid):
                         continue
-                    #
+
                     # Different exceptions mean that we may or may not want to bump the snapshot, trigger notifications etc
                     if process_changedetection_results:
 
@@ -513,8 +528,6 @@ class update_worker(threading.Thread):
                                 except Exception as e:
                                     logger.warning(f"UUID: {uuid} Extract <title> as watch title was enabled, but couldn't find a <title>.")
 
-                        # Now update after running everything
-                        timestamp = round(time.time())
                         try:
                             self.datastore.update_watch(uuid=uuid, update_obj=update_obj)
 
@@ -530,24 +543,28 @@ class update_worker(threading.Thread):
 
                                 # Small hack so that we sleep just enough to allow 1 second  between history snapshots
                                 # this is because history.txt indexes/keys snapshots by epoch seconds and we dont want dupe keys
-
-                                if watch.newest_history_key and int(timestamp) == int(watch.newest_history_key):
+                                # @also - the keys are one per second at the most (for now)
+                                if watch.newest_history_key and int(fetch_start_time) == int(watch.newest_history_key):
                                     logger.warning(
-                                        f"Timestamp {timestamp} already exists, waiting 1 seconds so we have a unique key in history.txt")
-                                    timestamp = str(int(timestamp) + 1)
+                                        f"Timestamp {fetch_start_time} already exists, waiting 1 seconds so we have a unique key in history.txt")
+                                    fetch_start_time += 1
                                     time.sleep(1)
 
                                 watch.save_history_text(contents=contents,
-                                                        timestamp=timestamp,
+                                                        timestamp=int(fetch_start_time),
                                                         snapshot_id=update_obj.get('previous_md5', 'none'))
 
-                                if update_handler.fetcher.content:
-                                    watch.save_last_fetched_html(contents=update_handler.fetcher.content, timestamp=timestamp)
+
+                                empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
+                                if update_handler.fetcher.content or (not update_handler.fetcher.content and empty_pages_are_a_change):
+                                    # attribute .last_changed is then based on this data
+                                    watch.save_last_fetched_html(contents=update_handler.fetcher.content, timestamp=int(fetch_start_time))
 
                                 # 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 watch.get('notification_muted'):
+                                        # @todo only run this if notifications exist
                                         self.send_content_changed_notification(watch_uuid=uuid)
 
                         except Exception as e:
@@ -569,15 +586,15 @@ class update_worker(threading.Thread):
                     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()),
+                    self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - fetch_start_time, 3),
+                                                                       'last_checked': int(fetch_start_time),
                                                                        'check_count': count
                                                                        })
 
 
                 self.current_uuid = None  # Done
                 self.q.task_done()
-                logger.debug(f"Watch {uuid} done in {time.time()-now:.2f}s")
+                logger.debug(f"Watch {uuid} done in {time.time()-fetch_start_time:.2f}s")
 
                 # Give the CPU time to interrupt
                 time.sleep(0.1)

docker-compose.yml

@@ -12,9 +12,6 @@ services:
   #    environment:
   #        Default listening port, can also be changed with the -p option
   #      - PORT=5000
-
-  #      - PUID=1000
-  #      - PGID=1000
   #
   #        Log levels are in descending order. (TRACE is the most detailed one)
   #        Log output levels: TRACE, DEBUG(default), INFO, SUCCESS, WARNING, ERROR, CRITICAL

requirements.txt

@@ -35,7 +35,7 @@ dnspython==2.6.1 # related to eventlet fixes
 # jq not available on Windows so must be installed manually
 
 # Notification library
-apprise==1.9.0
+apprise==1.9.2
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 # use any version other than 2.0.x due to https://github.com/eclipse/paho.mqtt.python/issues/814
@@ -95,3 +95,8 @@ babel
 # Needed for > 3.10, https://github.com/microsoft/playwright-python/issues/2096
 greenlet >= 3.0.3
 
+# Pinned or it causes problems with flask_expects_json which seems unmaintained
+referencing==0.35.1
+
+# Scheduler - Windows seemed to miss a lot of default timezone info (even "UTC" !)
+tzdata