[vimple] Fix extraction (Closes #5448)
[youtube-dl] / youtube_dl / extractor / vimple.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import int_or_none
5
6
7 class VimpleIE(InfoExtractor):
8     IE_DESC = 'Vimple - one-click video hosting'
9     _VALID_URL = r'https?://(?:player\.vimple\.ru/iframe|vimple\.ru)/(?P<id>[\da-f-]{32,36})'
10     _TESTS = [
11         {
12             'url': 'http://vimple.ru/c0f6b1687dcd4000a97ebe70068039cf',
13             'md5': '2e750a330ed211d3fd41821c6ad9a279',
14             'info_dict': {
15                 'id': 'c0f6b168-7dcd-4000-a97e-be70068039cf',
16                 'ext': 'mp4',
17                 'title': 'Sunset',
18                 'duration': 20,
19                 'thumbnail': 're:https?://.*?\.jpg',
20             },
21         }, {
22             'url': 'http://player.vimple.ru/iframe/52e1beec-1314-4a83-aeac-c61562eadbf9',
23             'only_matching': True,
24         }
25     ]
26
27     def _real_extract(self, url):
28         video_id = self._match_id(url)
29
30         webpage = self._download_webpage(
31             'http://player.vimple.ru/iframe/%s' % video_id, video_id)
32
33         playlist = self._parse_json(
34             self._search_regex(
35                 r'sprutoData\s*:\s*({.+?}),\r\n', webpage, 'spruto data'),
36             video_id)['playlist'][0]
37
38         title = playlist['title']
39         video_id = playlist.get('videoId') or video_id
40         thumbnail = playlist.get('posterUrl') or playlist.get('thumbnailUrl')
41         duration = int_or_none(playlist.get('duration'))
42
43         formats = [{
44             'url': f['url'],
45         } for f in playlist['video']]
46         self._sort_formats(formats)
47
48         return {
49             'id': video_id,
50             'title': title,
51             'thumbnail': thumbnail,
52             'duration': duration,
53             'formats': formats,
54         }