]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/redbulltv.py
Prepare to release.
[youtubedl] / 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)/(?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 }, {
46 'url': 'https://www.redbull.tv/film/AP-1MSKKF5T92111/in-motion',
47 'only_matching': True,
48 }]
49
50 def _real_extract(self, url):
51 video_id = self._match_id(url)
52
53 session = self._download_json(
54 'https://api-v2.redbull.tv/session', video_id,
55 note='Downloading access token', query={
56 'build': '4.370.0',
57 'category': 'personal_computer',
58 'os_version': '1.0',
59 'os_family': 'http',
60 })
61 if session.get('code') == 'error':
62 raise ExtractorError('%s said: %s' % (
63 self.IE_NAME, session['message']))
64 auth = '%s %s' % (session.get('token_type', 'Bearer'), session['access_token'])
65
66 try:
67 info = self._download_json(
68 'https://api-v2.redbull.tv/content/%s' % video_id,
69 video_id, note='Downloading video information',
70 headers={'Authorization': auth}
71 )
72 except ExtractorError as e:
73 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
74 error_message = self._parse_json(
75 e.cause.read().decode(), video_id)['message']
76 raise ExtractorError('%s said: %s' % (
77 self.IE_NAME, error_message), expected=True)
78 raise
79
80 video = info['video_product']
81
82 title = info['title'].strip()
83
84 formats = self._extract_m3u8_formats(
85 video['url'], video_id, 'mp4', 'm3u8_native')
86 self._sort_formats(formats)
87
88 subtitles = {}
89 for _, captions in (try_get(
90 video, lambda x: x['attachments']['captions'],
91 dict) or {}).items():
92 if not captions or not isinstance(captions, list):
93 continue
94 for caption in captions:
95 caption_url = caption.get('url')
96 if not caption_url:
97 continue
98 ext = caption.get('format')
99 if ext == 'xml':
100 ext = 'ttml'
101 subtitles.setdefault(caption.get('lang') or 'en', []).append({
102 'url': caption_url,
103 'ext': ext,
104 })
105
106 subheading = info.get('subheading')
107 if subheading:
108 title += ' - %s' % subheading
109
110 return {
111 'id': video_id,
112 'title': title,
113 'description': info.get('long_description') or info.get(
114 'short_description'),
115 'duration': float_or_none(video.get('duration'), scale=1000),
116 # 'timestamp': unified_timestamp(info.get('published')),
117 'series': info.get('show_title'),
118 'season_number': int_or_none(info.get('season_number')),
119 'episode_number': int_or_none(info.get('episode_number')),
120 'formats': formats,
121 'subtitles': subtitles,
122 }