Allow extractors to specify section_start/end for clips

[yt-dlp.git] / yt_dlp / extractor / youtube.py

diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py
index a6fcebf826132aa12efaad623788001a98b02b9c..da249f7a9d49039b2dfdbf8dd3d3008d16ef6361 100644 (file)
--- a/yt_dlp/extractor/youtube.py
+++ b/yt_dlp/extractor/youtube.py
@@ -3555,7 +3555,7 @@ def feed_entry(name):
             'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
             'uploader_url': owner_profile_url,
             'channel_id': channel_id,
-            'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
+            'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
             'duration': duration,
             'view_count': int_or_none(
                 get_first((video_details, microformats), (..., 'viewCount'))
@@ -3625,7 +3625,7 @@ def process_language(container, base_url, lang_code, sub_name, query):
                         if 'translated_subs' in self._configuration_arg('skip'):
                             continue
                         trans_code += f'-{lang_code}'
-                        trans_name += format_field(lang_name, template=' from %s')
+                        trans_name += format_field(lang_name, None, ' from %s')
                     # Add an "-orig" label to the original language so that it can be distinguished.
                     # The subs are returned without "-orig" as well for compatibility
                     if lang_code == f'a-{orig_trans_code}':
@@ -3684,13 +3684,22 @@ def process_language(container, base_url, lang_code, sub_name, query):
                 headers=self.generate_api_headers(ytcfg=master_ytcfg),
                 note='Downloading initial data API JSON')
 
+        info['comment_count'] = traverse_obj(initial_data, (
+            'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
+            'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
+        ), (
+            'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
+            'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
+        ), expected_type=int_or_none, get_all=False)
+
         try:  # This will error if there is no livechat
             initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
         except (KeyError, IndexError, TypeError):
             pass
         else:
             info.setdefault('subtitles', {})['live_chat'] = [{
-                'url': f'https://www.youtube.com/watch?v={video_id}',  # url is needed to set cookies
+                # url is needed to set cookies
+                'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
                 'video_id': video_id,
                 'ext': 'json',
                 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',