[teachertube] Fix extraction

This commit is contained in:
Sergey M․ 2014-06-23 03:07:10 +07:00
parent c5cd249e41
commit 9a2dc4f7ac
1 changed files with 21 additions and 10 deletions

View File

@ -22,8 +22,8 @@ class TeacherTubeIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '339997', 'id': '339997',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Measures of dispersion from a frequency table_x264', 'title': 'Measures of dispersion from a frequency table',
'description': 'md5:a3e9853487185e9fcd7181a07164650b', 'description': 'Measures of dispersion from a frequency table',
'thumbnail': 're:http://.*\.jpg', 'thumbnail': 're:http://.*\.jpg',
}, },
}, { }, {
@ -33,7 +33,7 @@ class TeacherTubeIE(InfoExtractor):
'id': '340064', 'id': '340064',
'ext': 'mp4', 'ext': 'mp4',
'title': 'How to Make Paper Dolls _ Paper Art Projects', 'title': 'How to Make Paper Dolls _ Paper Art Projects',
'description': 'md5:2ca52b20cd727773d1dc418b3d6bd07b', 'description': 'Learn how to make paper dolls in this simple',
'thumbnail': 're:http://.*\.jpg', 'thumbnail': 're:http://.*\.jpg',
}, },
}, { }, {
@ -43,7 +43,7 @@ class TeacherTubeIE(InfoExtractor):
'id': '8805', 'id': '8805',
'ext': 'mp3', 'ext': 'mp3',
'title': 'PER ASPERA AD ASTRA', 'title': 'PER ASPERA AD ASTRA',
'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNIČKE ŠKOLE PER ASPERA AD ASTRA', 'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNI?KE ?KOLE P',
}, },
}] }]
@ -53,9 +53,19 @@ class TeacherTubeIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_meta('title', webpage, 'title')
TITLE_SUFFIX = ' - TeacherTube'
if title.endswith(TITLE_SUFFIX):
title = title[:-len(TITLE_SUFFIX)].strip()
description = self._html_search_meta('description', webpage, 'description')
if description:
description = description.strip()
quality = qualities(['mp3', 'flv', 'mp4']) quality = qualities(['mp3', 'flv', 'mp4'])
_, media_urls = zip(*re.findall(r'([\'"])file\1\s*:\s*"([^"]+)"', webpage)) media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage)
media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage))
formats = [ formats = [
{ {
@ -68,10 +78,10 @@ class TeacherTubeIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'title': self._og_search_title(webpage), 'title': title,
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._html_search_regex(r'var\s+thumbUrl\s*=\s*"([^"]+)"', webpage, 'thumbnail'),
'formats': formats, 'formats': formats,
'description': self._og_search_description(webpage), 'description': description,
} }
@ -85,7 +95,8 @@ class TeacherTubeClassroomIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('user') user_id = mobj.group('user')
rss = self._download_xml('http://www.teachertube.com/rssclassroom.php?mode=user&username=%s' % user_id, rss = self._download_xml(
'http://www.teachertube.com/rssclassroom.php?mode=user&username=%s' % user_id,
user_id, 'Downloading classroom RSS') user_id, 'Downloading classroom RSS')
entries = [] entries = []