yt_dlp/extractor/voot.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     ExtractorError,
   5     int_or_none,
   6     try_get,
   7     unified_timestamp,
   8 )
   9
  10
  11 class VootIE(InfoExtractor):
  12     _VALID_URL = r'''(?x)
  13                     (?:
  14                         voot:|
  15                         https?://(?:www\.)?voot\.com/?
  16                         (?:
  17                             movies?/[^/]+/|
  18                             (?:shows|kids)/(?:[^/]+/){4}
  19                         )
  20                      )
  21                     (?P<id>\d{3,})
  22                     '''
  23     _GEO_COUNTRIES = ['IN']
  24     _TESTS = [{
  25         'url': 'https://www.voot.com/shows/ishq-ka-rang-safed/1/360558/is-this-the-end-of-kamini-/441353',
  26         'info_dict': {
  27             'id': '0_8ledb18o',
  28             'ext': 'mp4',
  29             'title': 'Ishq Ka Rang Safed - Season 01 - Episode 340',
  30             'description': 'md5:06291fbbbc4dcbe21235c40c262507c1',
  31             'timestamp': 1472162937,
  32             'upload_date': '20160825',
  33             'series': 'Ishq Ka Rang Safed',
  34             'season_number': 1,
  35             'episode': 'Is this the end of Kamini?',
  36             'episode_number': 340,
  37             'view_count': int,
  38             'like_count': int,
  39         },
  40         'params': {
  41             'skip_download': True,
  42         },
  43         'expected_warnings': ['Failed to download m3u8 information'],
  44     }, {
  45         'url': 'https://www.voot.com/kids/characters/mighty-cat-masked-niyander-e-/400478/school-bag-disappears/440925',
  46         'only_matching': True,
  47     }, {
  48         'url': 'https://www.voot.com/movies/pandavas-5/424627',
  49         'only_matching': True,
  50     }, {
  51         'url': 'https://www.voot.com/movie/fight-club/621842',
  52         'only_matching': True,
  53     }]
  54
  55     def _real_extract(self, url):
  56         video_id = self._match_id(url)
  57         media_info = self._download_json(
  58             'https://wapi.voot.com/ws/ott/getMediaInfo.json', video_id,
  59             query={
  60                 'platform': 'Web',
  61                 'pId': 2,
  62                 'mediaId': video_id,
  63             })
  64
  65         status_code = try_get(media_info, lambda x: x['status']['code'], int)
  66         if status_code != 0:
  67             raise ExtractorError(media_info['status']['message'], expected=True)
  68
  69         media = media_info['assets']
  70
  71         entry_id = media['EntryId']
  72         title = media['MediaName']
  73         formats = self._extract_m3u8_formats(
  74             'https://cdnapisec.kaltura.com/p/1982551/playManifest/pt/https/f/applehttp/t/web/e/' + entry_id,
  75             video_id, 'mp4', m3u8_id='hls')
  76
  77         description, series, season_number, episode, episode_number = [None] * 5
  78
  79         for meta in try_get(media, lambda x: x['Metas'], list) or []:
  80             key, value = meta.get('Key'), meta.get('Value')
  81             if not key or not value:
  82                 continue
  83             if key == 'ContentSynopsis':
  84                 description = value
  85             elif key == 'RefSeriesTitle':
  86                 series = value
  87             elif key == 'RefSeriesSeason':
  88                 season_number = int_or_none(value)
  89             elif key == 'EpisodeMainTitle':
  90                 episode = value
  91             elif key == 'EpisodeNo':
  92                 episode_number = int_or_none(value)
  93         return {
  94             'extractor_key': 'Kaltura',
  95             'id': entry_id,
  96             'title': title,
  97             'description': description,
  98             'series': series,
  99             'season_number': season_number,
 100             'episode': episode,
 101             'episode_number': episode_number,
 102             'timestamp': unified_timestamp(media.get('CreationDate')),
 103             'duration': int_or_none(media.get('Duration')),
 104             'view_count': int_or_none(media.get('ViewCounter')),
 105             'like_count': int_or_none(media.get('like_counter')),
 106             'formats': formats,
 107         }
 108
 109
 110 class VootSeriesIE(InfoExtractor):
 111     _VALID_URL = r'https?://(?:www\.)?voot\.com/shows/[^/]+/(?P<id>\d{3,})'
 112     _TESTS = [{
 113         'url': 'https://www.voot.com/shows/chakravartin-ashoka-samrat/100002',
 114         'playlist_mincount': 442,
 115         'info_dict': {
 116             'id': '100002',
 117         },
 118     }, {
 119         'url': 'https://www.voot.com/shows/ishq-ka-rang-safed/100003',
 120         'playlist_mincount': 341,
 121         'info_dict': {
 122             'id': '100003',
 123         },
 124     }]
 125     _SHOW_API = 'https://psapi.voot.com/media/voot/v1/voot-web/content/generic/season-by-show?sort=season%3Aasc&id={}&responseType=common'
 126     _SEASON_API = 'https://psapi.voot.com/media/voot/v1/voot-web/content/generic/series-wise-episode?sort=episode%3Aasc&id={}&responseType=common&page={:d}'
 127
 128     def _entries(self, show_id):
 129         show_json = self._download_json(self._SHOW_API.format(show_id), video_id=show_id)
 130         for season in show_json.get('result', []):
 131             page_num = 1
 132             season_id = try_get(season, lambda x: x['id'], compat_str)
 133             season_json = self._download_json(self._SEASON_API.format(season_id, page_num),
 134                                               video_id=season_id,
 135                                               note='Downloading JSON metadata page %d' % page_num)
 136             episodes_json = season_json.get('result', [])
 137             while episodes_json:
 138                 page_num += 1
 139                 for episode in episodes_json:
 140                     video_id = episode.get('id')
 141                     yield self.url_result(
 142                         'voot:%s' % video_id, ie=VootIE.ie_key(), video_id=video_id)
 143                 episodes_json = self._download_json(self._SEASON_API.format(season_id, page_num),
 144                                                     video_id=season_id,
 145                                                     note='Downloading JSON metadata page %d' % page_num)['result']
 146
 147     def _real_extract(self, url):
 148         show_id = self._match_id(url)
 149         return self.playlist_result(self._entries(show_id), playlist_id=show_id)