diff --git a/yt_dlp/extractor/vk.py b/yt_dlp/extractor/vk.py index 4b36e41ff..faf3e60b0 100644 --- a/yt_dlp/extractor/vk.py +++ b/yt_dlp/extractor/vk.py @@ -116,6 +116,7 @@ class VKIE(VKBaseIE): 'id': '-77521_162222515', 'ext': 'mp4', 'title': 'ProtivoGunz - Хуёвая песня', + 'description': 'Видео из официальной группы Noize MC\nhttp://vk.com/noizemc', 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*', 'uploader_id': '39545378', 'duration': 195, @@ -165,6 +166,7 @@ class VKIE(VKBaseIE): 'id': '-93049196_456239755', 'ext': 'mp4', 'title': '8 серия (озвучка)', + 'description': 'Видео из официальной группы Noize MC\nhttp://vk.com/noizemc', 'duration': 8383, 'comment_count': int, 'uploader': 'Dizi2021', @@ -240,6 +242,7 @@ class VKIE(VKBaseIE): 'upload_date': '20221005', 'uploader': 'Шальная Императрица', 'uploader_id': '-74006511', + 'description': 'md5:f9315f7786fa0e84e75e4f824a48b056', }, }, { @@ -278,6 +281,25 @@ class VKIE(VKBaseIE): }, 'skip': 'No formats found', }, + { + 'note': 'video has chapters', + 'url': 'https://vkvideo.ru/video-18403220_456239696', + 'info_dict': { + 'id': '-18403220_456239696', + 'ext': 'mp4', + 'title': 'Трамп отменяет гранты // DeepSeek - Революция в ИИ // Илон Маск читер', + 'description': 'md5:b112ea9de53683b6d03d29076f62eec2', + 'uploader': 'Руслан Усачев', + 'uploader_id': '-18403220', + 'comment_count': int, + 'like_count': int, + 'duration': 1983, + 'thumbnail': r're:https?://.+\.jpg', + 'chapters': 'count:21', + 'timestamp': 1738252883, + 'upload_date': '20250130', + }, + }, { # live stream, hls and rtmp links, most likely already finished live # stream by the time you are reading this comment @@ -449,7 +471,6 @@ class VKIE(VKBaseIE): return self.url_result(opts_url) data = player['params'][0] - title = unescapeHTML(data['md_title']) # 2 = live # 3 = post live (finished live) @@ -507,17 +528,29 @@ class VKIE(VKBaseIE): return { 'id': video_id, 'formats': formats, - 'title': title, - 'thumbnail': data.get('jpg'), - 'uploader': data.get('md_author'), - 'uploader_id': str_or_none(data.get('author_id') or mv_data.get('authorId')), - 'duration': int_or_none(data.get('duration') or mv_data.get('duration')), + 'subtitles': subtitles, + **traverse_obj(mv_data, { + 'title': ('title', {unescapeHTML}), + 'description': ('desc', {clean_html}, filter), + 'duration': ('duration', {int_or_none}), + 'like_count': ('likes', {int_or_none}), + 'comment_count': ('commcount', {int_or_none}), + }), + **traverse_obj(data, { + 'title': ('md_title', {unescapeHTML}), + 'description': ('description', {clean_html}, filter), + 'thumbnail': ('jpg', {url_or_none}), + 'uploader': ('md_author', {str}), + 'uploader_id': (('author_id', 'authorId'), {str_or_none}, any), + 'duration': ('duration', {int_or_none}), + 'chapters': ('time_codes', lambda _, v: isinstance(v['time'], int), { + 'title': ('text', {str}), + 'start_time': 'time', + }), + }), 'timestamp': timestamp, 'view_count': view_count, - 'like_count': int_or_none(mv_data.get('likes')), - 'comment_count': int_or_none(mv_data.get('commcount')), 'is_live': is_live, - 'subtitles': subtitles, '_format_sort_fields': ('res', 'source'), }