[youtube] Fix extraction.
[youtube-dl] / youtube_dl / extractor / dotsub.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import (
5     float_or_none,
6     int_or_none,
7 )
8
9
10 class DotsubIE(InfoExtractor):
11     _VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
12     _TESTS = [{
13         'url': 'https://dotsub.com/view/9c63db2a-fa95-4838-8e6e-13deafe47f09',
14         'md5': '21c7ff600f545358134fea762a6d42b6',
15         'info_dict': {
16             'id': '9c63db2a-fa95-4838-8e6e-13deafe47f09',
17             'ext': 'flv',
18             'title': 'MOTIVATION - "It\'s Possible" Best Inspirational Video Ever',
19             'description': 'md5:41af1e273edbbdfe4e216a78b9d34ac6',
20             'thumbnail': 're:^https?://dotsub.com/media/9c63db2a-fa95-4838-8e6e-13deafe47f09/p',
21             'duration': 198,
22             'uploader': 'liuxt',
23             'timestamp': 1385778501.104,
24             'upload_date': '20131130',
25             'view_count': int,
26         }
27     }, {
28         'url': 'https://dotsub.com/view/747bcf58-bd59-45b7-8c8c-ac312d084ee6',
29         'md5': '2bb4a83896434d5c26be868c609429a3',
30         'info_dict': {
31             'id': '168006778',
32             'ext': 'mp4',
33             'title': 'Apartments and flats in Raipur the white symphony',
34             'description': 'md5:784d0639e6b7d1bc29530878508e38fe',
35             'thumbnail': 're:^https?://dotsub.com/media/747bcf58-bd59-45b7-8c8c-ac312d084ee6/p',
36             'duration': 290,
37             'timestamp': 1476767794.2809999,
38             'upload_date': '20161018',
39             'uploader': 'parthivi001',
40             'uploader_id': 'user52596202',
41             'view_count': int,
42         },
43         'add_ie': ['Vimeo'],
44     }]
45
46     def _real_extract(self, url):
47         video_id = self._match_id(url)
48
49         info = self._download_json(
50             'https://dotsub.com/api/media/%s/metadata' % video_id, video_id)
51         video_url = info.get('mediaURI')
52
53         if not video_url:
54             webpage = self._download_webpage(url, video_id)
55             video_url = self._search_regex(
56                 [r'<source[^>]+src="([^"]+)"', r'"file"\s*:\s*\'([^\']+)'],
57                 webpage, 'video url', default=None)
58             info_dict = {
59                 'id': video_id,
60                 'url': video_url,
61                 'ext': 'flv',
62             }
63
64         if not video_url:
65             setup_data = self._parse_json(self._html_search_regex(
66                 r'(?s)data-setup=([\'"])(?P<content>(?!\1).+?)\1',
67                 webpage, 'setup data', group='content'), video_id)
68             info_dict = {
69                 '_type': 'url_transparent',
70                 'url': setup_data['src'],
71             }
72
73         info_dict.update({
74             'title': info['title'],
75             'description': info.get('description'),
76             'thumbnail': info.get('screenshotURI'),
77             'duration': int_or_none(info.get('duration'), 1000),
78             'uploader': info.get('user'),
79             'timestamp': float_or_none(info.get('dateCreated'), 1000),
80             'view_count': int_or_none(info.get('numberOfViews')),
81         })
82
83         return info_dict