yt_dlp/extractor/aitube.py

   1 from .common import InfoExtractor
   2 from ..utils import int_or_none, merge_dicts
   3
   4
   5 class AitubeKZVideoIE(InfoExtractor):
   6     _VALID_URL = r'https?://aitube\.kz/(?:video|embed/)\?(?:[^\?]+)?id=(?P<id>[\w-]+)'
   7     _TESTS = [{
   8         # id paramater as first parameter
   9         'url': 'https://aitube.kz/video?id=9291d29b-c038-49a1-ad42-3da2051d353c&playlistId=d55b1f5f-ef2a-4f23-b646-2a86275b86b7&season=1',
  10         'info_dict': {
  11             'id': '9291d29b-c038-49a1-ad42-3da2051d353c',
  12             'ext': 'mp4',
  13             'duration': 2174.0,
  14             'channel_id': '94962f73-013b-432c-8853-1bd78ca860fe',
  15             'like_count': int,
  16             'channel': 'ASTANA TV',
  17             'comment_count': int,
  18             'view_count': int,
  19             'description': 'Смотреть любимые сериалы и видео, поделиться видео и сериалами с друзьями и близкими',
  20             'thumbnail': 'https://cdn.static02.aitube.kz/kz.aitudala.aitube.staticaccess/files/ddf2a2ff-bee3-409b-b5f2-2a8202bba75b',
  21             'upload_date': '20221102',
  22             'timestamp': 1667370519,
  23             'title': 'Ангел хранитель 1 серия',
  24             'channel_follower_count': int,
  25         },
  26     }, {
  27         # embed url
  28         'url': 'https://aitube.kz/embed/?id=9291d29b-c038-49a1-ad42-3da2051d353c',
  29         'only_matching': True,
  30     }, {
  31         # id parameter is not as first paramater
  32         'url': 'https://aitube.kz/video?season=1&id=9291d29b-c038-49a1-ad42-3da2051d353c&playlistId=d55b1f5f-ef2a-4f23-b646-2a86275b86b7',
  33         'only_matching': True,
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38         webpage = self._download_webpage(url, video_id)
  39
  40         nextjs_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['videoInfo']
  41         json_ld_data = self._search_json_ld(webpage, video_id)
  42
  43         formats, subtitles = self._extract_m3u8_formats_and_subtitles(
  44             f'https://api-http.aitube.kz/kz.aitudala.aitube.staticaccess/video/{video_id}/video', video_id)
  45
  46         return merge_dicts({
  47             'id': video_id,
  48             'title': nextjs_data.get('title') or self._html_search_meta(['name', 'og:title'], webpage),
  49             'description': nextjs_data.get('description'),
  50             'formats': formats,
  51             'subtitles': subtitles,
  52             'view_count': (nextjs_data.get('viewCount')
  53                            or int_or_none(self._html_search_meta('ya:ovs:views_total', webpage))),
  54             'like_count': nextjs_data.get('likeCount'),
  55             'channel': nextjs_data.get('channelTitle'),
  56             'channel_id': nextjs_data.get('channelId'),
  57             'thumbnail': nextjs_data.get('coverUrl'),
  58             'comment_count': nextjs_data.get('commentCount'),
  59             'channel_follower_count': int_or_none(nextjs_data.get('channelSubscriberCount')),
  60         }, json_ld_data)