2014-03-21 06:38:37 -07:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
2015-10-01 09:39:38 -07:00
|
|
|
import re
|
|
|
|
|
2014-03-21 06:38:37 -07:00
|
|
|
from .common import InfoExtractor
|
2015-10-01 09:44:51 -07:00
|
|
|
from ..compat import (
|
|
|
|
compat_HTTPError,
|
|
|
|
compat_urlparse,
|
|
|
|
)
|
|
|
|
from ..utils import (
|
|
|
|
ExtractorError,
|
|
|
|
parse_duration,
|
|
|
|
)
|
2014-03-21 06:38:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
class VideoLecturesNetIE(InfoExtractor):
|
2015-08-08 19:51:37 -07:00
|
|
|
_VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/#?]+)/*(?:[#?].*)?$'
|
2014-03-21 06:38:37 -07:00
|
|
|
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):
|
2015-10-01 09:19:39 -07:00
|
|
|
video_id = self._match_id(url)
|
2014-03-21 06:38:37 -07:00
|
|
|
|
|
|
|
smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id
|
2015-10-01 09:44:51 -07:00
|
|
|
|
|
|
|
try:
|
|
|
|
smil = self._download_smil(smil_url, video_id)
|
|
|
|
except ExtractorError as e:
|
|
|
|
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
|
|
|
|
# Probably a playlist
|
|
|
|
webpage = self._download_webpage(url, video_id)
|
|
|
|
entries = [
|
|
|
|
self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet')
|
|
|
|
for _, video_url in re.findall(r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', webpage)]
|
|
|
|
playlist_title = self._html_search_meta('title', webpage, 'title', fatal=True)
|
|
|
|
playlist_description = self._html_search_meta('description', webpage, 'description')
|
|
|
|
return self.playlist_result(entries, video_id, playlist_title, playlist_description)
|
2014-03-21 06:38:37 -07:00
|
|
|
|
2015-10-01 09:19:39 -07:00
|
|
|
info = self._parse_smil(smil, smil_url, video_id)
|
2014-03-21 06:38:37 -07:00
|
|
|
|
2015-10-01 09:19:39 -07:00
|
|
|
info['id'] = video_id
|
2014-03-21 06:38:37 -07:00
|
|
|
|
2015-10-01 09:19:39 -07:00
|
|
|
switch = smil.find('.//switch')
|
|
|
|
if switch is not None:
|
|
|
|
info['duration'] = parse_duration(switch.attrib.get('dur'))
|
2014-03-21 06:38:37 -07:00
|
|
|
|
2015-10-01 09:19:39 -07:00
|
|
|
return info
|