[videolecturesnet] Improve playlist extraction

pull/8/head
Sergey M․ 9 years ago
parent 0c996b9f48
commit fb97809e64

@ -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)
try:
# Probably a playlist smil = self._download_smil(smil_url, video_id)
if smil is False: except ExtractorError as e:
webpage = self._download_webpage(url, video_id) if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
entries = [ # Probably a playlist
self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet') webpage = self._download_webpage(url, video_id)
for _, video_url in re.findall(r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', webpage)] entries = [
playlist_title = self._html_search_meta('title', webpage, 'title', fatal=True) self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet')
playlist_description = self._html_search_meta('description', webpage, 'description') for _, video_url in re.findall(r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', webpage)]
return self.playlist_result(entries, video_id, playlist_title, playlist_description) 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)

Loading…
Cancel
Save