[discovery] add support for discovery related sites
[youtube-dl] / youtube_dl / extractor / discovery.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import (
5     parse_duration,
6     parse_iso8601,
7 )
8 from ..compat import compat_str
9
10
11 class DiscoveryIE(InfoExtractor):
12     _VALID_URL = r'''(?x)http://(?:www\.)?(?:
13             discovery|
14             investigationdiscovery|
15             discoverylife|
16             animalplanet|
17             ahctv|
18             destinationamerica|
19             sciencechannel|
20             tlc|
21             velocity
22         )\.com/([^/]+/)*(?P<id>[^\./\?#]+)'''
23     _TESTS = [{
24         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
25         'info_dict': {
26             'id': '20769',
27             'ext': 'mp4',
28             'title': 'Mission Impossible Outtakes',
29             'description': ('Watch Jamie Hyneman and Adam Savage practice being'
30                             ' each other -- to the point of confusing Jamie\'s dog -- and '
31                             'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
32                             ' back.'),
33             'duration': 156,
34             'timestamp': 1302032462,
35             'upload_date': '20110405',
36         },
37         'params': {
38             'skip_download': True,  # requires ffmpeg
39         }
40     }, {
41         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mythbusters-the-simpsons',
42         'info_dict': {
43             'id': 'mythbusters-the-simpsons',
44             'title': 'MythBusters: The Simpsons',
45         },
46         'playlist_mincount': 10,
47     }, {
48         'url': 'http://www.animalplanet.com/longfin-eels-maneaters/',
49         'info_dict': {
50             'id': '78326',
51             'ext': 'mp4',
52             'title': 'Longfin Eels: Maneaters?',
53             'description': 'Jeremy Wade tests whether or not New Zealand\'s longfin eels are man-eaters by covering himself in fish guts and getting in the water with them.',
54             'upload_date': '20140725',
55             'timestamp': 1406246400,
56             'duration': 116,
57         },
58     }]
59
60     def _real_extract(self, url):
61         display_id = self._match_id(url)
62         info = self._download_json(url + '?flat=1', display_id)
63
64         video_title = info.get('playlist_title') or info.get('video_title')
65
66         entries = [{
67             'id': compat_str(video_info['id']),
68             'formats': self._extract_m3u8_formats(
69                 video_info['src'], display_id, 'mp4', 'm3u8_native', m3u8_id='hls',
70                 note='Download m3u8 information for video %d' % (idx + 1)),
71             'title': video_info['title'],
72             'description': video_info.get('description'),
73             'duration': parse_duration(video_info.get('video_length')),
74             'webpage_url': video_info.get('href') or video_info.get('url'),
75             'thumbnail': video_info.get('thumbnailURL'),
76             'alt_title': video_info.get('secondary_title'),
77             'timestamp': parse_iso8601(video_info.get('publishedDate')),
78         } for idx, video_info in enumerate(info['playlist'])]
79
80         return self.playlist_result(entries, display_id, video_title)