_ Git - youtube-dl/blob - youtube_dl/extractor/videolecturesnet.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_HTTPError,
   8     compat_urlparse,
   9 )
  10 from ..utils import (
  11     ExtractorError,
  12     parse_duration,
  13 )
  14
  15
  16 class VideoLecturesNetIE(InfoExtractor):
  17     _VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/#?]+)/*(?:[#?].*)?$'
  18     IE_NAME = 'videolectures.net'
  19
  20     _TESTS = [{
  21         'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
  22         'info_dict': {
  23             'id': 'promogram_igor_mekjavic_eng',
  24             'ext': 'mp4',
  25             'title': 'Automatics, robotics and biocybernetics',
  26             'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  27             'upload_date': '20130627',
  28             'duration': 565,
  29             'thumbnail': 're:http://.*\.jpg',
  30         },
  31     }, {
  32         # video with invalid direct format links (HTTP 403)
  33         'url': 'http://videolectures.net/russir2010_filippova_nlp/',
  34         'info_dict': {
  35             'id': 'russir2010_filippova_nlp',
  36             'ext': 'flv',
  37             'title': 'NLP at Google',
  38             'description': 'md5:fc7a6d9bf0302d7cc0e53f7ca23747b3',
  39             'duration': 5352,
  40             'thumbnail': 're:http://.*\.jpg',
  41         },
  42         'params': {
  43             # rtmp download
  44             'skip_download': True,
  45         },
  46     }, {
  47         'url': 'http://videolectures.net/deeplearning2015_montreal/',
  48         'info_dict': {
  49             'id': 'deeplearning2015_montreal',
  50             'title': 'Deep Learning Summer School, Montreal 2015',
  51             'description': 'md5:90121a40cc6926df1bf04dcd8563ed3b',
  52         },
  53         'playlist_count': 30,
  54     }]
  55
  56     def _real_extract(self, url):
  57         video_id = self._match_id(url)
  58
  59         smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id
  60
  61         try:
  62             smil = self._download_smil(smil_url, video_id)
  63         except ExtractorError as e:
  64             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
  65                 # Probably a playlist
  66                 webpage = self._download_webpage(url, video_id)
  67                 entries = [
  68                     self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet')
  69                     for _, video_url in re.findall(r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', webpage)]
  70                 playlist_title = self._html_search_meta('title', webpage, 'title', fatal=True)
  71                 playlist_description = self._html_search_meta('description', webpage, 'description')
  72                 return self.playlist_result(entries, video_id, playlist_title, playlist_description)
  73
  74         info = self._parse_smil(smil, smil_url, video_id)
  75
  76         info['id'] = video_id
  77
  78         switch = smil.find('.//switch')
  79         if switch is not None:
  80             info['duration'] = parse_duration(switch.attrib.get('dur'))
  81
  82         return info