From acfb717a18cfa9c0f377372068e16862bba345b4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 1 Oct 2015 22:19:39 +0600 Subject: [PATCH] [videolecturesnet] Use generic SMIL extraction --- youtube_dl/extractor/videolecturesnet.py | 62 +++--------------------- 1 file changed, 8 insertions(+), 54 deletions(-) diff --git a/youtube_dl/extractor/videolecturesnet.py b/youtube_dl/extractor/videolecturesnet.py index ef2da5632..160dbb590 100644 --- a/youtube_dl/extractor/videolecturesnet.py +++ b/youtube_dl/extractor/videolecturesnet.py @@ -1,13 +1,8 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( - find_xpath_attr, - int_or_none, parse_duration, - unified_strdate, ) @@ -29,58 +24,17 @@ class VideoLecturesNetIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) 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'] - description_el = find_xpath_attr(smil, './/meta', 'name', 'abstract') - description = ( - None if description_el is None - else description_el.attrib['content']) - upload_date = unified_strdate( - find_xpath_attr(smil, './/meta', 'name', 'date').attrib['content']) + info = self._parse_smil(smil, smil_url, video_id) + + info['id'] = video_id switch = smil.find('.//switch') - duration = parse_duration(switch.attrib.get('dur')) - thumbnail_el = find_xpath_attr(switch, './image', 'type', 'thumbnail') - thumbnail = ( - None if thumbnail_el is None else thumbnail_el.attrib.get('src')) + if switch is not None: + info['duration'] = parse_duration(switch.attrib.get('dur')) - formats = [] - 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, - } + return info