yt-dlc/youtube_dl/extractor/videolecturesnet.py

41 lines
1.2 KiB
Python
Raw Normal View History

2014-03-21 14:38:37 +01:00
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
parse_duration,
)
class VideoLecturesNetIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/#?]+)/*(?:[#?].*)?$'
2014-03-21 14:38:37 +01:00
IE_NAME = 'videolectures.net'
_TEST = {
'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
'info_dict': {
'id': 'promogram_igor_mekjavic_eng',
'ext': 'mp4',
'title': 'Automatics, robotics and biocybernetics',
'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
'upload_date': '20130627',
'duration': 565,
'thumbnail': 're:http://.*\.jpg',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
2014-03-21 14:38:37 +01:00
smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id
smil = self._download_smil(smil_url, video_id)
2014-03-21 14:38:37 +01:00
info = self._parse_smil(smil, smil_url, video_id)
2014-03-21 14:38:37 +01:00
info['id'] = video_id
2014-03-21 14:38:37 +01:00
switch = smil.find('.//switch')
if switch is not None:
info['duration'] = parse_duration(switch.attrib.get('dur'))
2014-03-21 14:38:37 +01:00
return info