]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/xbef.py
[brightcove:new] extract subtitles and strip video title
[youtube-dl] / youtube_dl / extractor / xbef.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..compat import compat_urllib_parse_unquote
5
6
7 class XBefIE(InfoExtractor):
8     _VALID_URL = r'https?://(?:www\.)?xbef\.com/video/(?P<id>[0-9]+)'
9     _TEST = {
10         'url': 'http://xbef.com/video/5119-glamourous-lesbians-smoking-drinking-and-fucking',
11         'md5': 'a478b565baff61634a98f5e5338be995',
12         'info_dict': {
13             'id': '5119',
14             'ext': 'mp4',
15             'title': 'md5:7358a9faef8b7b57acda7c04816f170e',
16             'age_limit': 18,
17             'thumbnail': 're:^http://.*\.jpg',
18         }
19     }
20
21     def _real_extract(self, url):
22         video_id = self._match_id(url)
23         webpage = self._download_webpage(url, video_id)
24
25         title = self._html_search_regex(
26             r'<h1[^>]*>(.*?)</h1>', webpage, 'title')
27
28         config_url_enc = self._download_webpage(
29             'http://xbef.com/Main/GetVideoURLEncoded/%s' % video_id, video_id,
30             note='Retrieving config URL')
31         config_url = compat_urllib_parse_unquote(config_url_enc)
32         config = self._download_xml(
33             config_url, video_id, note='Retrieving config')
34
35         video_url = config.find('./file').text
36         thumbnail = config.find('./image').text
37
38         return {
39             'id': video_id,
40             'url': video_url,
41             'title': title,
42             'thumbnail': thumbnail,
43             'age_limit': 18,
44         }