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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     parse_duration,
   6 )
   7
   8
   9 class VideoLecturesNetIE(InfoExtractor):
  10     _VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/#?]+)/*(?:[#?].*)?$'
  11     IE_NAME = 'videolectures.net'
  12
  13     _TEST = {
  14         'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
  15         'info_dict': {
  16             'id': 'promogram_igor_mekjavic_eng',
  17             'ext': 'mp4',
  18             'title': 'Automatics, robotics and biocybernetics',
  19             'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  20             'upload_date': '20130627',
  21             'duration': 565,
  22             'thumbnail': 're:http://.*\.jpg',
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28
  29         smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id
  30         smil = self._download_smil(smil_url, video_id)
  31
  32         info = self._parse_smil(smil, smil_url, video_id)
  33
  34         info['id'] = video_id
  35
  36         switch = smil.find('.//switch')
  37         if switch is not None:
  38             info['duration'] = parse_duration(switch.attrib.get('dur'))
  39
  40         return info