]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/firsttv.py
[brightcove:new] extract subtitles and strip video title
[youtube-dl] / youtube_dl / extractor / firsttv.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import int_or_none
6
7
8 class FirstTVIE(InfoExtractor):
9     IE_NAME = '1tv'
10     IE_DESC = 'Первый канал'
11     _VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>.+)'
12
13     _TESTS = [{
14         'url': 'http://www.1tv.ru/videoarchive/73390',
15         'md5': '777f525feeec4806130f4f764bc18a4f',
16         'info_dict': {
17             'id': '73390',
18             'ext': 'mp4',
19             'title': 'Олимпийские канатные дороги',
20             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
21             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
22             'duration': 149,
23             'like_count': int,
24             'dislike_count': int,
25         },
26         'skip': 'Only works from Russia',
27     }, {
28         'url': 'http://www.1tv.ru/prj/inprivate/vypusk/35930',
29         'md5': 'a1b6b60d530ebcf8daacf4565762bbaf',
30         'info_dict': {
31             'id': '35930',
32             'ext': 'mp4',
33             'title': 'Наедине со всеми. Людмила Сенчина',
34             'description': 'md5:89553aed1d641416001fe8d450f06cb9',
35             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
36             'duration': 2694,
37         },
38         'skip': 'Only works from Russia',
39     }]
40
41     def _real_extract(self, url):
42         video_id = self._match_id(url)
43
44         webpage = self._download_webpage(url, video_id, 'Downloading page')
45
46         video_url = self._html_search_regex(
47             r'''(?s)(?:jwplayer\('flashvideoportal_1'\)\.setup\({|var\s+playlistObj\s*=).*?'file'\s*:\s*'([^']+)'.*?}\);''',
48             webpage, 'video URL')
49
50         title = self._html_search_regex(
51             [r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
52              r"'title'\s*:\s*'([^']+)'"], webpage, 'title')
53         description = self._html_search_regex(
54             r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
55             webpage, 'description', default=None) or self._html_search_meta(
56                 'description', webpage, 'description')
57
58         thumbnail = self._og_search_thumbnail(webpage)
59         duration = self._og_search_property(
60             'video:duration', webpage,
61             'video duration', fatal=False)
62
63         like_count = self._html_search_regex(
64             r'title="Понравилось".*?/></label> \[(\d+)\]',
65             webpage, 'like count', default=None)
66         dislike_count = self._html_search_regex(
67             r'title="Не понравилось".*?/></label> \[(\d+)\]',
68             webpage, 'dislike count', default=None)
69
70         return {
71             'id': video_id,
72             'url': video_url,
73             'thumbnail': thumbnail,
74             'title': title,
75             'description': description,
76             'duration': int_or_none(duration),
77             'like_count': int_or_none(like_count),
78             'dislike_count': int_or_none(dislike_count),
79         }