depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-13 21:05:39 +00:00
Code Issues Releases Wiki Activity

[videolecturesnet] Use generic SMIL extraction

Browse source
This commit is contained in:
Sergey M․ 2015-10-01 22:19:39 +06:00
parent 647eab4541
commit acfb717a18
1 changed files with 8 additions and 54 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

62
youtube_dl/extractor/videolecturesnet.py
View file

@ -1,13 +1,8 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
find_xpath_attr,
int_or_none,
parse_duration, parse_duration,
unified_strdate,
) )
@ -29,58 +24,17 @@ class VideoLecturesNetIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id
smil = self._download_xml(smil_url, video_id) smil = self._download_smil(smil_url, video_id)
title = find_xpath_attr(smil, './/meta', 'name', 'title').attrib['content'] info = self._parse_smil(smil, smil_url, video_id)
description_el = find_xpath_attr(smil, './/meta', 'name', 'abstract')
description = ( info['id'] = video_id
None if description_el is None
else description_el.attrib['content'])
upload_date = unified_strdate(
find_xpath_attr(smil, './/meta', 'name', 'date').attrib['content'])
switch = smil.find('.//switch') switch = smil.find('.//switch')
duration = parse_duration(switch.attrib.get('dur')) if switch is not None:
thumbnail_el = find_xpath_attr(switch, './image', 'type', 'thumbnail') info['duration'] = parse_duration(switch.attrib.get('dur'))
thumbnail = (
None if thumbnail_el is None else thumbnail_el.attrib.get('src'))
formats = [] return info
for v in switch.findall('./video'):
proto = v.attrib.get('proto')
if proto not in ['http', 'rtmp']:
continue
f = {
'width': int_or_none(v.attrib.get('width')),
'height': int_or_none(v.attrib.get('height')),
'filesize': int_or_none(v.attrib.get('size')),
'tbr': int_or_none(v.attrib.get('systemBitrate')) / 1000.0,
'ext': v.attrib.get('ext'),
}
src = v.attrib['src']
if proto == 'http':
if self._is_valid_url(src, video_id):
f['url'] = src
formats.append(f)
elif proto == 'rtmp':
f.update({
'url': v.attrib['streamer'],
'play_path': src,
'rtmp_real_time': True,
})
formats.append(f)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'upload_date': upload_date,
'duration': duration,
'thumbnail': thumbnail,
'formats': formats,
}