Add link

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.45.23'
+__version__ = '0.45.22'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError

changedetectionio/content_fetchers/base.py

@@ -28,7 +28,7 @@ def manage_user_agent(headers, current_ua=''):
     :return:
     """
     # Ask it what the user agent is, if its obviously ChromeHeadless, switch it to the default
-    ua_in_custom_headers = headers.get('User-Agent')
+    ua_in_custom_headers = next((v for k, v in headers.items() if k.lower() == "user-agent"), None)
     if ua_in_custom_headers:
         return ua_in_custom_headers
 

changedetectionio/content_fetchers/puppeteer.py

@@ -92,38 +92,15 @@ class fetcher(Fetcher):
                                                        ignoreHTTPSErrors=True
                                                        )
         except websockets.exceptions.InvalidStatusCode as e:
-            raise BrowserConnectError(msg=f"Error while trying to connect the browser, Code {e.status_code} (check your access, whitelist IP, password etc)")
+            raise BrowserConnectError(msg=f"Error while trying to connect the browser, Code {e.status_code} (check your access)")
         except websockets.exceptions.InvalidURI:
             raise BrowserConnectError(msg=f"Error connecting to the browser, check your browser connection address (should be ws:// or wss://")
         except Exception as e:
             raise BrowserConnectError(msg=f"Error connecting to the browser {str(e)}")
-
-        # Better is to launch chrome with the URL as arg
-        # non-headless - newPage() will launch an extra tab/window, .browser should already contain 1 page/tab
-        # headless - ask a new page
-        self.page = (pages := await browser.pages) and len(pages) or await browser.newPage()
-
-        try:
-            from pyppeteerstealth import inject_evasions_into_page
-        except ImportError:
-            logger.debug("pyppeteerstealth module not available, skipping")
-            pass
         else:
-            # I tried hooking events via self.page.on(Events.Page.DOMContentLoaded, inject_evasions_requiring_obj_to_page)
-            # But I could never get it to fire reliably, so we just inject it straight after
-            await inject_evasions_into_page(self.page)
+            self.page = await browser.newPage()
 
-        # This user agent is similar to what was used when tweaking the evasions in inject_evasions_into_page(..)
-        user_agent = None
-        if request_headers and request_headers.get('User-Agent'):
-            # Request_headers should now be CaaseInsensitiveDict
-            # Remove it so it's not sent again with headers after
-            user_agent = request_headers.pop('User-Agent').strip()
-            await self.page.setUserAgent(user_agent)
-
-        if not user_agent:
-            # Attempt to strip 'HeadlessChrome' etc
-            await self.page.setUserAgent(manage_user_agent(headers=request_headers, current_ua=await self.page.evaluate('navigator.userAgent')))
+        await self.page.setUserAgent(manage_user_agent(headers=request_headers, current_ua=await self.page.evaluate('navigator.userAgent')))
 
         await self.page.setBypassCSP(True)
         if request_headers:

changedetectionio/flask_app.py

@@ -124,10 +124,10 @@ def _jinja2_filter_datetime(watch_obj, format="%Y-%m-%d %H:%M:%S"):
 
 @app.template_filter('format_timestamp_timeago')
 def _jinja2_filter_datetimestamp(timestamp, format="%Y-%m-%d %H:%M:%S"):
-    if not timestamp:
+    if timestamp == False:
         return 'Not yet'
 
-    return timeago.format(int(timestamp), time.time())
+    return timeago.format(timestamp, time.time())
 
 
 @app.template_filter('pagination_slice')
@@ -771,7 +771,7 @@ def changedetection_app(config=None, datastore_o=None):
                                      jq_support=jq_support,
                                      playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False),
                                      settings_application=datastore.data['settings']['application'],
-                                     using_global_webdriver_wait=not default['webdriver_delay'],
+                                     using_global_webdriver_wait=default['webdriver_delay'] is None,
                                      uuid=uuid,
                                      visualselector_enabled=visualselector_enabled,
                                      watch=watch

changedetectionio/model/Watch.py

@@ -333,9 +333,7 @@ class model(dict):
         # 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 self.__newest_history_key and int(timestamp) == int(self.__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)
-            time.sleep(1)
+            time.sleep(timestamp - self.__newest_history_key)
 
         threshold = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
         skip_brotli = strtobool(os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False'))

changedetectionio/processors/__init__.py

@@ -1,10 +1,10 @@
 from abc import abstractmethod
-from changedetectionio.strtobool import strtobool
-from copy import deepcopy
-from loguru import logger
-import hashlib
 import os
+import hashlib
 import re
+from copy import deepcopy
+from changedetectionio.strtobool import strtobool
+from loguru import logger
 
 class difference_detection_processor():
 
@@ -21,7 +21,7 @@ class difference_detection_processor():
         self.watch = deepcopy(self.datastore.data['watching'].get(watch_uuid))
 
     def call_browser(self):
-        from requests.structures import CaseInsensitiveDict
+
         # Protect against file:// access
         if re.search(r'^file://', self.watch.get('url', '').strip(), re.IGNORECASE):
             if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
@@ -93,16 +93,14 @@ class difference_detection_processor():
             self.fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, self.watch.get('uuid'))
 
         # Tweak the base config with the per-watch ones
-        request_headers = CaseInsensitiveDict()
+        request_headers = self.watch.get('headers', [])
+        request_headers.update(self.datastore.get_all_base_headers())
+        request_headers.update(self.datastore.get_all_headers_in_textfile_for_watch(uuid=self.watch.get('uuid')))
 
         ua = self.datastore.data['settings']['requests'].get('default_ua')
         if ua and ua.get(prefer_fetch_backend):
             request_headers.update({'User-Agent': ua.get(prefer_fetch_backend)})
 
-        request_headers.update(self.watch.get('headers', {}))
-        request_headers.update(self.datastore.get_all_base_headers())
-        request_headers.update(self.datastore.get_all_headers_in_textfile_for_watch(uuid=self.watch.get('uuid')))
-
         # https://github.com/psf/requests/issues/4525
         # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
         # do this by accident.

changedetectionio/static/js/preview.js

@@ -40,13 +40,9 @@ if (selectElement) {
     if (selectedOption) {
         if (selectedOption.previousElementSibling) {
             document.getElementById('btn-previous').href = "?version=" + selectedOption.previousElementSibling.value;
-        } else {
-            document.getElementById('btn-previous').remove()
         }
         if (selectedOption.nextElementSibling) {
             document.getElementById('btn-next').href = "?version=" + selectedOption.nextElementSibling.value;
-        } else {
-            document.getElementById('btn-next').remove()
         }
 
     }

changedetectionio/store.py

@@ -178,7 +178,7 @@ class ChangeDetectionStore:
     @property
     def has_unviewed(self):
         for uuid, watch in self.__data['watching'].items():
-            if watch.history_n >= 2 and watch.viewed == False:
+            if watch.viewed == False:
                 return True
         return False
 

changedetectionio/templates/base.html

@@ -6,9 +6,7 @@
     <meta name="viewport" content="width=device-width, initial-scale=1.0" >
     <meta name="description" content="Self hosted website change detection." >
     <title>Change Detection{{extra_title}}</title>
-    {% if app_rss_token %}
-      <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag_uuid %}- {{active_tag.title}}{% endif %}" href="{{ url_for('rss', tag=active_tag_uuid , token=app_rss_token)}}" >
-    {% endif %}
+    <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}" >
     <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}" >
     <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}?v={{ get_css_version() }}" >
     {% if extra_stylesheets %}
@@ -85,8 +83,8 @@
           <li class="pure-menu-item pure-form" id="search-menu-item">
             <!-- We use GET here so it offers people a chance to set bookmarks etc -->
             <form name="searchForm" action="" method="GET">
-              <input id="search-q" class="" name="q" placeholder="URL or Title {% if active_tag_uuid %}in '{{ active_tag.title }}'{% endif %}" required="" type="text" value="">
-              <input name="tags" type="hidden" value="{% if active_tag_uuid %}{{active_tag_uuid}}{% endif %}">
+              <input id="search-q" class="" name="q" placeholder="URL or Title {% if active_tag %}in '{{ active_tag }}'{% endif %}" required="" type="text" value="">
+              <input name="tags" type="hidden" value="{% if active_tag %}{{active_tag}}{% endif %}">
               <button class="toggle-button " id="toggle-search" type="button" title="Search, or Use Alt+S Key" >
                 {% include "svgs/search-icon.svg" %}
               </button>

changedetectionio/templates/edit.html

@@ -433,8 +433,7 @@ Unavailable") }}
                     <div class="pure-control-group">
                         {% if visualselector_enabled %}
                             <span class="pure-form-message-inline">
-                                The Visual Selector tool lets you select the <i>text</i> elements that will be used for the change detection &dash; after the <i>Browser Steps</i> has completed.<br>
-                                This tool is a helper to manage filters in the  "CSS/JSONPath/JQ/XPath Filters" box of the <a href="#filters-and-triggers">Filters & Triggers</a> tab.
+                                The Visual Selector tool lets you select the <i>text</i> elements that will be used for the change detection &dash; after the <i>Browser Steps</i> has completed, this tool is a helper to manage filters in the  "CSS/JSONPath/JQ/XPath Filters" box of the <a href="#filters-and-triggers">Filters & Triggers</a> tab.
                             </span>
 
                             <div id="selector-header">

changedetectionio/templates/preview.html

@@ -66,7 +66,7 @@
         </div>
 
         <div class="tab-pane-inner" id="text">
-            <div class="snapshot-age">{{ current_version|format_timestamp_timeago }}</div>
+            <div class="snapshot-age">{{ watch.snapshot_text_ctime|format_timestamp_timeago }}</div>
             <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span>
             <span class="tip"><strong>Pro-tip</strong>: Highlight text to add to ignore filters</span>
 

changedetectionio/templates/watch-overview.html

@@ -13,7 +13,7 @@
             <div id="watch-add-wrapper-zone">
 
                     {{ render_nolabel_field(form.url, placeholder="https://...", required=true) }}
-                    {{ render_nolabel_field(form.tags, value=active_tag.title if active_tag_uuid else '', placeholder="watch label / tag") }}
+                    {{ render_nolabel_field(form.tags, value=active_tag.title if active_tag else '', placeholder="watch label / tag") }}
                     {{ render_nolabel_field(form.watch_submit_button, title="Watch this URL!" ) }}
                     {{ render_nolabel_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
             </div>
@@ -46,7 +46,7 @@
     {% endif %}
     {% if search_q %}<div id="search-result-info">Searching "<strong><i>{{search_q}}</i></strong>"</div>{% endif %}
     <div>
-        <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag_uuid }}">All</a>
+        <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag }}">All</a>
 
     <!-- tag list -->
     {% for uuid, tag in tags %}
@@ -67,18 +67,18 @@
             <tr>
                 {% set link_order = "desc" if sort_order  == 'asc' else "asc" %}
                 {% set arrow_span = "" %}
-                <th><input style="vertical-align: middle" type="checkbox" id="check-all" > <a class="{{ 'active '+link_order if sort_attribute == 'date_created' else 'inactive' }}"  href="{{url_for('index', sort='date_created', order=link_order, tag=active_tag_uuid)}}"># <span class='arrow {{link_order}}'></span></a></th>
+                <th><input style="vertical-align: middle" type="checkbox" id="check-all" > <a class="{{ 'active '+link_order if sort_attribute == 'date_created' else 'inactive' }}"  href="{{url_for('index', sort='date_created', order=link_order, tag=active_tag)}}"># <span class='arrow {{link_order}}'></span></a></th>
                 <th></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('index', sort='label', order=link_order, tag=active_tag_uuid)}}">Website <span class='arrow {{link_order}}'></span></a></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag_uuid)}}">Last Checked <span class='arrow {{link_order}}'></span></a></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag_uuid)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('index', sort='label', order=link_order, tag=active_tag)}}">Website <span class='arrow {{link_order}}'></span></a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag)}}">Last Checked <span class='arrow {{link_order}}'></span></a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
                 <th></th>
             </tr>
             </thead>
             <tbody>
             {% if not watches|length %}
             <tr>
-                <td colspan="6" style="text-wrap: wrap;">No website watches configured, please add a URL in the box above, or <a href="{{ url_for('import_page')}}" >import a list</a>.</td>
+                <td colspan="6">No website watches configured, please add a URL in the box above, or <a href="{{ url_for('import_page')}}" >import a list</a>.</td>
             </tr>
             {% endif %}
             {% for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))|pagination_slice(skip=pagination.skip) %}
@@ -95,11 +95,11 @@
                 <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span>{{ loop.index+pagination.skip }}</span></td>
                 <td class="inline watch-controls">
                     {% if not watch.paused %}
-                    <a class="state-off" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause" ></a>
+                    <a class="state-off" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause" ></a>
                     {% 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>
+                    <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><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>
+                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" 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>
@@ -204,7 +204,7 @@
                 all {% if active_tag_uuid %} in "{{active_tag.title}}"{%endif%}</a>
             </li>
             <li>
-                <a href="{{ url_for('rss', tag=active_tag_uuid, token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='Generic_Feed-icon.svg')}}" height="15"></a>
+                <a href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='Generic_Feed-icon.svg')}}" height="15"></a>
             </li>
         </ul>
         {{ pagination.links }}

changedetectionio/tests/smtp/test_notification_smtp.py

@@ -71,8 +71,6 @@ def test_check_notification_email_formats_default_HTML(client, live_server):
 
     wait_for_all_checks(client)
     set_longer_modified_response()
-    time.sleep(2)
-
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
 
@@ -137,7 +135,6 @@ def test_check_notification_email_formats_default_Text_override_HTML(client, liv
 
     wait_for_all_checks(client)
     set_longer_modified_response()
-    time.sleep(2)
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
 

changedetectionio/tests/test_automatic_follow_ldjson_price.py

@@ -105,7 +105,6 @@ def test_check_ldjson_price_autodetect(client, live_server):
     wait_for_all_checks(client)
 
     # Trigger a check
-    time.sleep(1)
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     # Offer should be gone

changedetectionio/tests/test_backend.py

@@ -135,9 +135,6 @@ def test_check_basic_change_detection_functionality(client, live_server):
     # It should have picked up the <title>
     assert b'head title' in res.data
 
-    # Be sure the last_viewed is going to be greater than the last snapshot
-    time.sleep(1)
-
     # hit the mark all viewed link
     res = client.get(url_for("mark_all_viewed"), follow_redirects=True)
 

changedetectionio/tests/test_notification_errors.py

@@ -9,6 +9,9 @@ def test_check_notification_error_handling(client, live_server):
     live_server_setup(live_server)
     set_original_response()
 
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
     # Set a URL and fetch it, then set a notification URL which is going to give errors
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(

changedetectionio/tests/test_request.py

@@ -253,62 +253,6 @@ def test_method_in_request(client, live_server):
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
-# Re #2408 - user-agent override test, also should handle case-insensitive header deduplication
-def test_ua_global_override(client, live_server):
-    # live_server_setup(live_server)
-    test_url = url_for('test_headers', _external=True)
-
-    res = client.post(
-        url_for("settings_page"),
-        data={
-            "application-fetch_backend": "html_requests",
-            "application-minutes_between_check": 180,
-            "requests-default_ua-html_requests": "html-requests-user-agent"
-        },
-        follow_redirects=True
-    )
-    assert b'Settings updated' in res.data
-
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-
-    wait_for_all_checks(client)
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-
-    assert b"html-requests-user-agent" in res.data
-    # default user-agent should have shown by now
-    # now add a custom one in the headers
-
-
-    # Add some headers to a request
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={
-            "url": test_url,
-            "tags": "testtag",
-            "fetch_backend": 'html_requests',
-            # Important - also test case-insensitive
-            "headers": "User-AGent: agent-from-watch"},
-        follow_redirects=True
-    )
-    assert b"Updated watch." in res.data
-    wait_for_all_checks(client)
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-    assert b"agent-from-watch" in res.data
-    assert b"html-requests-user-agent" not in res.data
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
-
 def test_headers_textfile_in_request(client, live_server):
     #live_server_setup(live_server)
     # Add our URL to the import page
@@ -389,7 +333,7 @@ def test_headers_textfile_in_request(client, live_server):
     # Not needed anymore
     os.unlink('test-datastore/headers.txt')
     os.unlink('test-datastore/headers-testtag.txt')
-
+    os.unlink('test-datastore/' + extract_UUID_from_client(client) + '/headers.txt')
     # The service should echo back the request verb
     res = client.get(
         url_for("preview_page", uuid="first"),

requirements.txt

@@ -1,7 +1,7 @@
 # Used by Pyppeteer
 pyee
 
-eventlet==0.35.2 # related to dnspython fixes
+eventlet==0.33.3 # related to dnspython fixes
 feedgen~=0.9
 flask-compress
 # 0.6.3 included compatibility fix for werkzeug 3.x (2.x had deprecation of url handlers)
@@ -73,10 +73,12 @@ openpyxl
 jq~=1.3; python_version >= "3.8" and sys_platform == "darwin"
 jq~=1.3; python_version >= "3.8" and sys_platform == "linux"
 
+# Any current modern version, required so far for screenshot PNG->JPEG conversion but will be used more in the future
+pillow
 # playwright is installed at Dockerfile build time because it's not available on all platforms
 
+# experimental release
 pyppeteer-ng==2.0.0rc5
-pyppeteerstealth>=0.0.4
 
 # Include pytest, so if theres a support issue we can ask them to run these tests on their setup
 pytest ~=7.2