youtube-dl/youtube_dl/extractor/videolecturesnet.py

128 lines
4.4 KiB
Python
Raw Normal View History

2014-03-21 13:38:37 +00:00
from __future__ import unicode_literals
import re
2014-03-21 13:38:37 +00:00
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_urlparse,
)
from ..utils import (
ExtractorError,
parse_duration,
js_to_json,
parse_iso8601,
)
2014-03-21 13:38:37 +00:00
class VideoLecturesNetIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/]+)(?:/video/(?P<part>\d+))?'
2014-03-21 13:38:37 +00:00
IE_NAME = 'videolectures.net'
2015-10-01 16:45:10 +00:00
_TESTS = [{
2014-03-21 13:38:37 +00:00
'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
'info_dict': {
'id': '20171_part1',
2014-03-21 13:38:37 +00:00
'ext': 'mp4',
'title': 'Automatics, robotics and biocybernetics',
'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
'upload_date': '20130627',
'duration': 565,
'thumbnail': 're:http://.*\.jpg',
},
}, {
# video with invalid direct format links (HTTP 403)
'url': 'http://videolectures.net/russir2010_filippova_nlp/',
'info_dict': {
'id': '14891_part1',
'ext': 'flv',
'title': 'NLP at Google',
'description': 'md5:fc7a6d9bf0302d7cc0e53f7ca23747b3',
'duration': 5352,
'thumbnail': 're:http://.*\.jpg',
},
'params': {
# rtmp download
'skip_download': True,
},
2015-10-01 16:45:10 +00:00
}, {
'url': 'http://videolectures.net/deeplearning2015_montreal/',
'info_dict': {
'id': '23181',
2015-10-01 16:45:10 +00:00
'title': 'Deep Learning Summer School, Montreal 2015',
'description': 'md5:0533a85e4bd918df52a01f0e1ebe87b7',
'timestamp': 1438560000,
2015-10-01 16:45:10 +00:00
},
'playlist_count': 30,
}, {
# multi part lecture
'url': 'http://videolectures.net/mlss09uk_bishop_ibi/',
'info_dict': {
'id': '9737',
'title': 'Introduction To Bayesian Inference',
'timestamp': 1251622800,
},
'playlist': [{
'info_dict': {
'id': '9737_part1',
'ext': 'wmv',
'title': 'Introduction To Bayesian Inference',
},
}, {
'info_dict': {
'id': '9737_part2',
'ext': 'wmv',
'title': 'Introduction To Bayesian Inference',
},
}],
'playlist_count': 2,
2015-10-01 16:45:10 +00:00
}]
2014-03-21 13:38:37 +00:00
def _real_extract(self, url):
lecture_slug, part = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, lecture_slug)
2014-03-21 13:38:37 +00:00
cfg = self._parse_json(self._search_regex(r'cfg\s*:\s*({[^}]+})', webpage, 'cfg'), lecture_slug, js_to_json)
lecture_id = str(cfg['obj_id'])
2014-03-21 13:38:37 +00:00
lecture_data = self._download_json('%s/site/api/lecture/%s?format=json' % (self._proto_relative_url(cfg['livepipe'], 'http:'), lecture_id), lecture_id)['lecture'][0]
2014-03-21 13:38:37 +00:00
lecture_info = {
'id': lecture_id,
'display_id': lecture_slug,
'title': lecture_data['title'],
'timestamp': parse_iso8601(lecture_data.get('time')),
'description': lecture_data.get('description_wiki'),
'thumbnail': lecture_data.get('thumb'),
}
2014-03-21 13:38:37 +00:00
entries = []
parts = cfg.get('videos')
if parts:
if len(parts) == 1:
part = str(parts[0])
if part:
smil_url = 'http://videolectures.net/%s/video/%s/smil.xml' % (lecture_slug, part)
smil = self._download_smil(smil_url, lecture_id)
info = self._parse_smil(smil, smil_url, lecture_id)
info['id'] = '%s_part%s' % (lecture_id, part)
switch = smil.find('.//switch')
if switch is not None:
info['duration'] = parse_duration(switch.attrib.get('dur'))
return info
else:
for part in parts:
entries.append(self.url_result('http://videolectures.net/%s/video/%s' % (lecture_slug, part), 'VideoLecturesNet'))
lecture_info['_type'] = 'multi_video'
else:
# Probably a playlist
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)]
lecture_info['_type'] = 'playlist'
2014-03-21 13:38:37 +00:00
lecture_info['entries'] = entries
return lecture_info