Adding global ignore text (#339)

changedetectionio/__init__.py

@@ -552,6 +552,7 @@ def changedetection_app(config=None, datastore_o=None):
         if request.method == 'GET':
             form.minutes_between_check.data = int(datastore.data['settings']['requests']['minutes_between_check'])
             form.notification_urls.data = datastore.data['settings']['application']['notification_urls']
+            form.global_ignore_text.data = datastore.data['settings']['application']['global_ignore_text']
             form.extract_title_as_title.data = datastore.data['settings']['application']['extract_title_as_title']
             form.fetch_backend.data = datastore.data['settings']['application']['fetch_backend']
             form.notification_title.data = datastore.data['settings']['application']['notification_title']
@@ -578,6 +579,7 @@ def changedetection_app(config=None, datastore_o=None):
             datastore.data['settings']['application']['notification_format'] = form.notification_format.data
             datastore.data['settings']['application']['notification_urls'] = form.notification_urls.data
             datastore.data['settings']['application']['base_url'] = form.base_url.data
+            datastore.data['settings']['application']['global_ignore_text'] =  form.global_ignore_text.data
             
             if form.trigger_check.data:
                 if len(form.notification_urls.data):

changedetectionio/fetch_site_status.py

@@ -129,11 +129,11 @@ class perform_site_check():
             update_obj["last_check_status"] = fetcher.get_last_status_code()
             update_obj["last_error"] = False
 
-
             # If there's text to skip
             # @todo we could abstract out the get_text() to handle this cleaner
-            if len(watch['ignore_text']):
+            text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
-                stripped_text_from_html = self.strip_ignore_text(stripped_text_from_html, watch['ignore_text'])
+            if len(text_to_ignore):
+                stripped_text_from_html = self.strip_ignore_text(stripped_text_from_html, text_to_ignore)
             else:
                 stripped_text_from_html = stripped_text_from_html.encode('utf8')
 

changedetectionio/forms.py

@@ -258,3 +258,4 @@ class globalSettingsForm(commonSettingsForm):
                                                [validators.NumberRange(min=1)])
     extract_title_as_title = BooleanField('Extract <title> from document and use as watch title')
     base_url = StringField('Base URL', validators=[validators.Optional()])
+    global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])

changedetectionio/store.py

@@ -45,6 +45,7 @@ class ChangeDetectionStore:
                     'base_url' : None,
                     'extract_title_as_title': False,
                     'fetch_backend': 'html_requests',
+                    'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
                     'notification_urls': [], # Apprise URL list
                     # Custom notification content
                     'notification_title': None,

changedetectionio/templates/settings.html

@@ -13,6 +13,7 @@
             <li class="tab" id="default-tab"><a href="#general">General</a></li>
             <li class="tab"><a href="#notifications">Notifications</a></li>
             <li class="tab"><a href="#fetching">Fetching</a></li>
+            <li class="tab"><a href="#filters">Global Filters</a></li>
         </ul>
     </div>
     <div class="box-wrap inner">
@@ -65,6 +66,20 @@
                     </span>
                 </div>
             </div>
+
+
+            <div class="tab-pane-inner" id="filters">
+                <span class="pure-form-message-inline">Note: This is applied globally in addition to the per-watch rules.</span>
+                            <fieldset class="pure-group">
+                    {{ render_field(form.global_ignore_text, rows=5, placeholder="Some text to ignore in a line
+/some.regex\d{2}/ for case-INsensitive regex
+                    ") }}
+                    <span class="pure-form-message-inline">
+                    Each line processed separately, any line matching will be ignored.<br/>
+                    Regular Expression support, wrap the line in forward slash <b>/regex/</b>.
+                </span>
+           </div>
+
             <div id="actions">
                 <div class="pure-control-group">
                     <button type="submit" class="pure-button pure-button-primary">Save</button>

changedetectionio/tests/test_ignore_text.py

@@ -151,3 +151,88 @@ def test_check_ignore_text_functionality(client, live_server):
 
     res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
+
+def test_check_global_ignore_text_functionality(client, live_server):
+    sleep_time_for_fetch_thread = 3
+
+    ignore_text = "XXXXX\r\nYYYYY\r\nZZZZZ"
+    set_original_ignore_response()
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    # Trigger a check
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # Goto the settings page, add our ignore text
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "minutes_between_check": 180,
+            "global_ignore_text": ignore_text,
+            'fetch_backend': "html_requests"
+        },
+        follow_redirects=True
+    )
+    assert b"Settings updated." in res.data
+
+    # Goto the edit page of the item, add our ignore text
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"ignore_text": "something irrelevent but just to check", "url": test_url, 'fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+
+    # Check it saved
+    res = client.get(
+        url_for("settings_page"),
+    )
+    assert bytes(ignore_text.encode('utf-8')) in res.data
+
+    # Trigger a check
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+    assert b'/test-endpoint' in res.data
+
+    #  Make a change
+    set_modified_ignore_response()
+
+    # Trigger a check
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # It should report nothing found (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+    assert b'/test-endpoint' in res.data
+
+    # Just to be sure.. set a regular modified change..
+    set_modified_original_ignore_response()
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    time.sleep(sleep_time_for_fetch_thread)
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data