yt_dlp/extractor/voot.py

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