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/video/(?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
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42
  43         session = self._download_json(
  44             'https://api.redbull.tv/v3/session', video_id,
  45             note='Downloading access token', query={
  46                 'category': 'personal_computer',
  47                 'os_family': 'http',
  48             })
  49         if session.get('code') == 'error':
  50             raise ExtractorError('%s said: %s' % (
  51                 self.IE_NAME, session['message']))
  52         token = session['token']
  53
  54         try:
  55             video = self._download_json(
  56                 'https://api.redbull.tv/v3/products/' + video_id,
  57                 video_id, note='Downloading video information',
  58                 headers={'Authorization': token}
  59             )
  60         except ExtractorError as e:
  61             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
  62                 error_message = self._parse_json(
  63                     e.cause.read().decode(), video_id)['error']
  64                 raise ExtractorError('%s said: %s' % (
  65                     self.IE_NAME, error_message), expected=True)
  66             raise
  67
  68         title = video['title'].strip()
  69
  70         formats = self._extract_m3u8_formats(
  71             'https://dms.redbull.tv/v3/%s/%s/playlist.m3u8' % (video_id, token),
  72             video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
  73         self._sort_formats(formats)
  74
  75         subtitles = {}
  76         for resource in video.get('resources', []):
  77             if resource.startswith('closed_caption_'):
  78                 splitted_resource = resource.split('_')
  79                 if splitted_resource[2]:
  80                     subtitles.setdefault('en', []).append({
  81                         'url': 'https://resources.redbull.tv/%s/%s' % (video_id, resource),
  82                         'ext': splitted_resource[2],
  83                     })
  84
  85         subheading = video.get('subheading')
  86         if subheading:
  87             title += ' - %s' % subheading
  88
  89         return {
  90             'id': video_id,
  91             'title': title,
  92             'description': video.get('long_description') or video.get(
  93                 'short_description'),
  94             'duration': float_or_none(video.get('duration'), scale=1000),
  95             'formats': formats,
  96             'subtitles': subtitles,
  97         }