youtube_dl/extractor/redbulltv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_HTTPError
   6 from ..utils import (
   7     float_or_none,
   8     int_or_none,
   9     try_get,
  10     # unified_timestamp,
  11     ExtractorError,
  12 )
  13
  14
  15 class RedBullTVIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?redbull\.tv/(?:video|film|live)/(?:AP-\w+/segment/)?(?P<id>AP-\w+)'
  17     _TESTS = [{
  18         # film
  19         'url': 'https://www.redbull.tv/video/AP-1Q756YYX51W11/abc-of-wrc',
  20         'md5': 'fb0445b98aa4394e504b413d98031d1f',
  21         'info_dict': {
  22             'id': 'AP-1Q756YYX51W11',
  23             'ext': 'mp4',
  24             'title': 'ABC of...WRC',
  25             'description': 'md5:5c7ed8f4015c8492ecf64b6ab31e7d31',
  26             'duration': 1582.04,
  27             # 'timestamp': 1488405786,
  28             # 'upload_date': '20170301',
  29         },
  30     }, {
  31         # episode
  32         'url': 'https://www.redbull.tv/video/AP-1PMT5JCWH1W11/grime?playlist=shows:shows-playall:web',
  33         'info_dict': {
  34             'id': 'AP-1PMT5JCWH1W11',
  35             'ext': 'mp4',
  36             'title': 'Grime - Hashtags S2 E4',
  37             'description': 'md5:334b741c8c1ce65be057eab6773c1cf5',
  38             'duration': 904.6,
  39             # 'timestamp': 1487290093,
  40             # 'upload_date': '20170217',
  41             'series': 'Hashtags',
  42             'season_number': 2,
  43             'episode_number': 4,
  44         },
  45         'params': {
  46             'skip_download': True,
  47         },
  48     }, {
  49         # segment
  50         'url': 'https://www.redbull.tv/live/AP-1R5DX49XS1W11/segment/AP-1QSAQJ6V52111/semi-finals',
  51         'info_dict': {
  52             'id': 'AP-1QSAQJ6V52111',
  53             'ext': 'mp4',
  54             'title': 'Semi Finals - Vans Park Series Pro Tour',
  55             'description': 'md5:306a2783cdafa9e65e39aa62f514fd97',
  56             'duration': 11791.991,
  57         },
  58         'params': {
  59             'skip_download': True,
  60         },
  61     }, {
  62         'url': 'https://www.redbull.tv/film/AP-1MSKKF5T92111/in-motion',
  63         'only_matching': True,
  64     }]
  65
  66     def _real_extract(self, url):
  67         video_id = self._match_id(url)
  68
  69         session = self._download_json(
  70             'https://api-v2.redbull.tv/session', video_id,
  71             note='Downloading access token', query={
  72                 'build': '4.370.0',
  73                 'category': 'personal_computer',
  74                 'os_version': '1.0',
  75                 'os_family': 'http',
  76             })
  77         if session.get('code') == 'error':
  78             raise ExtractorError('%s said: %s' % (
  79                 self.IE_NAME, session['message']))
  80         auth = '%s %s' % (session.get('token_type', 'Bearer'), session['access_token'])
  81
  82         try:
  83             info = self._download_json(
  84                 'https://api-v2.redbull.tv/content/%s' % video_id,
  85                 video_id, note='Downloading video information',
  86                 headers={'Authorization': auth}
  87             )
  88         except ExtractorError as e:
  89             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
  90                 error_message = self._parse_json(
  91                     e.cause.read().decode(), video_id)['message']
  92                 raise ExtractorError('%s said: %s' % (
  93                     self.IE_NAME, error_message), expected=True)
  94             raise
  95
  96         video = info['video_product']
  97
  98         title = info['title'].strip()
  99
 100         formats = self._extract_m3u8_formats(
 101             video['url'], video_id, 'mp4', entry_protocol='m3u8_native',
 102             m3u8_id='hls')
 103         self._sort_formats(formats)
 104
 105         subtitles = {}
 106         for _, captions in (try_get(
 107                 video, lambda x: x['attachments']['captions'],
 108                 dict) or {}).items():
 109             if not captions or not isinstance(captions, list):
 110                 continue
 111             for caption in captions:
 112                 caption_url = caption.get('url')
 113                 if not caption_url:
 114                     continue
 115                 ext = caption.get('format')
 116                 if ext == 'xml':
 117                     ext = 'ttml'
 118                 subtitles.setdefault(caption.get('lang') or 'en', []).append({
 119                     'url': caption_url,
 120                     'ext': ext,
 121                 })
 122
 123         subheading = info.get('subheading')
 124         if subheading:
 125             title += ' - %s' % subheading
 126
 127         return {
 128             'id': video_id,
 129             'title': title,
 130             'description': info.get('long_description') or info.get(
 131                 'short_description'),
 132             'duration': float_or_none(video.get('duration'), scale=1000),
 133             # 'timestamp': unified_timestamp(info.get('published')),
 134             'series': info.get('show_title'),
 135             'season_number': int_or_none(info.get('season_number')),
 136             'episode_number': int_or_none(info.get('episode_number')),
 137             'formats': formats,
 138             'subtitles': subtitles,
 139         }