1 from __future__ import unicode_literals
5 from .common import InfoExtractor
16 class VideoLecturesNetIE(InfoExtractor):
17 _VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/#?]+)/*(?:[#?].*)?$'
18 IE_NAME = 'videolectures.net'
21 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
23 'id': 'promogram_igor_mekjavic_eng',
25 'title': 'Automatics, robotics and biocybernetics',
26 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
27 'upload_date': '20130627',
29 'thumbnail': 're:http://.*\.jpg',
32 'url': 'http://videolectures.net/deeplearning2015_montreal/',
34 'id': 'deeplearning2015_montreal',
35 'title': 'Deep Learning Summer School, Montreal 2015',
36 'description': 'md5:90121a40cc6926df1bf04dcd8563ed3b',
41 def _real_extract(self, url):
42 video_id = self._match_id(url)
44 smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id
47 smil = self._download_smil(smil_url, video_id)
48 except ExtractorError as e:
49 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
51 webpage = self._download_webpage(url, video_id)
53 self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet')
54 for _, video_url in re.findall(r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', webpage)]
55 playlist_title = self._html_search_meta('title', webpage, 'title', fatal=True)
56 playlist_description = self._html_search_meta('description', webpage, 'description')
57 return self.playlist_result(entries, video_id, playlist_title, playlist_description)
59 info = self._parse_smil(smil, smil_url, video_id)
63 switch = smil.find('.//switch')
64 if switch is not None:
65 info['duration'] = parse_duration(switch.attrib.get('dur'))