github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

[videolecturesnet] Improve playlist extraction

Browse source
This commit is contained in:
Sergey M․ 2015-10-01 22:44:51 +06:00
parent 0c996b9f48
commit fb97809e64
1 changed files with 20 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
youtube_dl/extractor/videolecturesnet.py
View file

@ -3,8 +3,14 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urlparse from ..compat import (
from ..utils import parse_duration compat_HTTPError,
compat_urlparse,
)
from ..utils import (
ExtractorError,
parse_duration,
)
class VideoLecturesNetIE(InfoExtractor): class VideoLecturesNetIE(InfoExtractor):
@ -28,17 +34,19 @@ class VideoLecturesNetIE(InfoExtractor):
video_id = self._match_id(url) video_id = self._match_id(url)
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_smil(smil_url, video_id, fatal=False)
# Probably a playlist try:
if smil is False: smil = self._download_smil(smil_url, video_id)
webpage = self._download_webpage(url, video_id) except ExtractorError as e:
entries = [ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet') # Probably a playlist
for _, video_url in re.findall(r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', webpage)] webpage = self._download_webpage(url, video_id)
playlist_title = self._html_search_meta('title', webpage, 'title', fatal=True) entries = [
playlist_description = self._html_search_meta('description', webpage, 'description') self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet')
return self.playlist_result(entries, video_id, playlist_title, playlist_description) 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)
info = self._parse_smil(smil, smil_url, video_id) info = self._parse_smil(smil, smil_url, video_id)