Raphaël G. Git Repositories - youtubedl/blob - 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     ExtractorError,
   9 )
  10
  11
  12 class RedBullTVIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?redbull(?:\.tv|\.com(?:/[^/]+)?(?:/tv)?)(?:/events/[^/]+)?/(?:videos?|live)/(?P<id>AP-\w+)'
  14     _TESTS = [{
  15         # film
  16         'url': 'https://www.redbull.tv/video/AP-1Q6XCDTAN1W11',
  17         'md5': 'fb0445b98aa4394e504b413d98031d1f',
  18         'info_dict': {
  19             'id': 'AP-1Q6XCDTAN1W11',
  20             'ext': 'mp4',
  21             'title': 'ABC of... WRC - ABC of... S1E6',
  22             'description': 'md5:5c7ed8f4015c8492ecf64b6ab31e7d31',
  23             'duration': 1582.04,
  24         },
  25     }, {
  26         # episode
  27         'url': 'https://www.redbull.tv/video/AP-1PMHKJFCW1W11',
  28         'info_dict': {
  29             'id': 'AP-1PMHKJFCW1W11',
  30             'ext': 'mp4',
  31             'title': 'Grime - Hashtags S2E4',
  32             'description': 'md5:b5f522b89b72e1e23216e5018810bb25',
  33             'duration': 904.6,
  34         },
  35         'params': {
  36             'skip_download': True,
  37         },
  38     }, {
  39         'url': 'https://www.redbull.com/int-en/tv/video/AP-1UWHCAR9S1W11/rob-meets-sam-gaze?playlist=playlists::3f81040a-2f31-4832-8e2e-545b1d39d173',
  40         'only_matching': True,
  41     }, {
  42         'url': 'https://www.redbull.com/us-en/videos/AP-1YM9QCYE52111',
  43         'only_matching': True,
  44     }, {
  45         'url': 'https://www.redbull.com/us-en/events/AP-1XV2K61Q51W11/live/AP-1XUJ86FDH1W11',
  46         'only_matching': True,
  47     }]
  48
  49     def _real_extract(self, url):
  50         video_id = self._match_id(url)
  51
  52         session = self._download_json(
  53             'https://api.redbull.tv/v3/session', video_id,
  54             note='Downloading access token', query={
  55                 'category': 'personal_computer',
  56                 'os_family': 'http',
  57             })
  58         if session.get('code') == 'error':
  59             raise ExtractorError('%s said: %s' % (
  60                 self.IE_NAME, session['message']))
  61         token = session['token']
  62
  63         try:
  64             video = self._download_json(
  65                 'https://api.redbull.tv/v3/products/' + video_id,
  66                 video_id, note='Downloading video information',
  67                 headers={'Authorization': token}
  68             )
  69         except ExtractorError as e:
  70             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
  71                 error_message = self._parse_json(
  72                     e.cause.read().decode(), video_id)['error']
  73                 raise ExtractorError('%s said: %s' % (
  74                     self.IE_NAME, error_message), expected=True)
  75             raise
  76
  77         title = video['title'].strip()
  78
  79         formats = self._extract_m3u8_formats(
  80             'https://dms.redbull.tv/v3/%s/%s/playlist.m3u8' % (video_id, token),
  81             video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
  82         self._sort_formats(formats)
  83
  84         subtitles = {}
  85         for resource in video.get('resources', []):
  86             if resource.startswith('closed_caption_'):
  87                 splitted_resource = resource.split('_')
  88                 if splitted_resource[2]:
  89                     subtitles.setdefault('en', []).append({
  90                         'url': 'https://resources.redbull.tv/%s/%s' % (video_id, resource),
  91                         'ext': splitted_resource[2],
  92                     })
  93
  94         subheading = video.get('subheading')
  95         if subheading:
  96             title += ' - %s' % subheading
  97
  98         return {
  99             'id': video_id,
 100             'title': title,
 101             'description': video.get('long_description') or video.get(
 102                 'short_description'),
 103             'duration': float_or_none(video.get('duration'), scale=1000),
 104             'formats': formats,
 105             'subtitles': subtitles,
 106         }
 107
 108
 109 class RedBullTVRrnContentIE(InfoExtractor):
 110     _VALID_URL = r'https?://(?:www\.)?redbull(?:\.tv|\.com(?:/[^/]+)?(?:/tv)?)/(?:video|live)/rrn:content:[^:]+:(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
 111     _TESTS = [{
 112         'url': 'https://www.redbull.com/int-en/tv/video/rrn:content:live-videos:e3e6feb4-e95f-50b7-962a-c70f8fd13c73/mens-dh-finals-fort-william',
 113         'only_matching': True,
 114     }, {
 115         'url': 'https://www.redbull.com/int-en/tv/video/rrn:content:videos:a36a0f36-ff1b-5db8-a69d-ee11a14bf48b/tn-ts-style?playlist=rrn:content:event-profiles:83f05926-5de8-5389-b5e4-9bb312d715e8:extras',
 116         'only_matching': True,
 117     }]
 118
 119     def _real_extract(self, url):
 120         display_id = self._match_id(url)
 121
 122         webpage = self._download_webpage(url, display_id)
 123
 124         video_url = self._og_search_url(webpage)
 125
 126         return self.url_result(
 127             video_url, ie=RedBullTVIE.ie_key(),
 128             video_id=RedBullTVIE._match_id(video_url))