]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/discoverygo.py
Prepare new release.
[youtubedl] / youtube_dl / extractor / discoverygo.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..compat import compat_str
5 from ..utils import (
6 extract_attributes,
7 int_or_none,
8 parse_age_limit,
9 ExtractorError,
10 )
11
12
13 class DiscoveryGoIE(InfoExtractor):
14 _VALID_URL = r'''(?x)https?://(?:www\.)?(?:
15 discovery|
16 investigationdiscovery|
17 discoverylife|
18 animalplanet|
19 ahctv|
20 destinationamerica|
21 sciencechannel|
22 tlc|
23 velocitychannel
24 )go\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'''
25 _TEST = {
26 'url': 'https://www.discoverygo.com/love-at-first-kiss/kiss-first-ask-questions-later/',
27 'info_dict': {
28 'id': '57a33c536b66d1cd0345eeb1',
29 'ext': 'mp4',
30 'title': 'Kiss First, Ask Questions Later!',
31 'description': 'md5:fe923ba34050eae468bffae10831cb22',
32 'duration': 2579,
33 'series': 'Love at First Kiss',
34 'season_number': 1,
35 'episode_number': 1,
36 'age_limit': 14,
37 },
38 }
39
40 def _real_extract(self, url):
41 display_id = self._match_id(url)
42
43 webpage = self._download_webpage(url, display_id)
44
45 container = extract_attributes(
46 self._search_regex(
47 r'(<div[^>]+class=["\']video-player-container[^>]+>)',
48 webpage, 'video container'))
49
50 video = self._parse_json(
51 container.get('data-video') or container.get('data-json'),
52 display_id)
53
54 title = video['name']
55
56 stream = video.get('stream')
57 if not stream:
58 if video.get('authenticated') is True:
59 raise ExtractorError(
60 'This video is only available via cable service provider subscription that'
61 ' is not currently supported. You may want to use --cookies.', expected=True)
62 else:
63 raise ExtractorError('Unable to find stream')
64 STREAM_URL_SUFFIX = 'streamUrl'
65 formats = []
66 for stream_kind in ('', 'hds'):
67 suffix = STREAM_URL_SUFFIX.capitalize() if stream_kind else STREAM_URL_SUFFIX
68 stream_url = stream.get('%s%s' % (stream_kind, suffix))
69 if not stream_url:
70 continue
71 if stream_kind == '':
72 formats.extend(self._extract_m3u8_formats(
73 stream_url, display_id, 'mp4', entry_protocol='m3u8_native',
74 m3u8_id='hls', fatal=False))
75 elif stream_kind == 'hds':
76 formats.extend(self._extract_f4m_formats(
77 stream_url, display_id, f4m_id=stream_kind, fatal=False))
78 self._sort_formats(formats)
79
80 video_id = video.get('id') or display_id
81 description = video.get('description', {}).get('detailed')
82 duration = int_or_none(video.get('duration'))
83
84 series = video.get('show', {}).get('name')
85 season_number = int_or_none(video.get('season', {}).get('number'))
86 episode_number = int_or_none(video.get('episodeNumber'))
87
88 tags = video.get('tags')
89 age_limit = parse_age_limit(video.get('parental', {}).get('rating'))
90
91 subtitles = {}
92 captions = stream.get('captions')
93 if isinstance(captions, list):
94 for caption in captions:
95 subtitle_url = caption.get('fileUrl')
96 if (not subtitle_url or not isinstance(subtitle_url, compat_str) or
97 not subtitle_url.startswith('http')):
98 continue
99 lang = caption.get('fileLang', 'en')
100 subtitles.setdefault(lang, []).append({'url': subtitle_url})
101
102 return {
103 'id': video_id,
104 'display_id': display_id,
105 'title': title,
106 'description': description,
107 'duration': duration,
108 'series': series,
109 'season_number': season_number,
110 'episode_number': episode_number,
111 'tags': tags,
112 'age_limit': age_limit,
113 'formats': formats,
114 'subtitles': subtitles,
115 }