gitlab-com-dstftw/youtube-dl
1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
Code Issues Releases Wiki Activity

TED: get thumbnails

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-02-23 17:27:49 +01:00
parent 4be0aa3539
commit c85538dba1
1 changed files with 10 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
youtube_dl/InfoExtractors.py
View file

@ -4011,31 +4011,30 @@ class TEDIE(InfoExtractor):
([.\s]*?)data-playlist_item_id="(\d+)" ([.\s]*?)data-playlist_item_id="(\d+)"
([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)" ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)"
''' '''
video_name_RE=r'<p\ class="talk-title"><a href="/talks/(.+).html">(?P<fullname>.+?)</a></p>' video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>'
webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage') webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage')
m_videos=re.finditer(video_RE,webpage,re.VERBOSE) m_videos=re.finditer(video_RE,webpage,re.VERBOSE)
m_names=re.finditer(video_name_RE,webpage) m_names=re.finditer(video_name_RE,webpage)
info=[] info=[]
for m_video, m_name in zip(m_videos,m_names): for m_video, m_name in zip(m_videos,m_names):
video_dic={ video_id=m_video.group('video_id')
'id': m_video.group('video_id'), talk_url='http://www.ted.com%s' % m_name.group('talk_url')
'url': self._talk_video_link(m_video.group('mediaSlug')), info.append(self._talk_info(talk_url,video_id))
'ext': 'mp4',
'title': m_name.group('fullname')
}
info.append(video_dic)
return info return info
def _talk_info(self, url, video_id=0): def _talk_info(self, url, video_id=0):
"""Return the video for the talk in the url""" """Return the video for the talk in the url"""
m=re.match(self._VALID_URL, url,re.VERBOSE) m=re.match(self._VALID_URL, url,re.VERBOSE)
videoName=m.group('name') videoName=m.group('name')
webpage=self._download_webpage(url, video_id, 'Downloading \"%s\" page' % videoName) webpage=self._download_webpage(url, video_id, 'Downloading \"%s\" page' % videoName)
# If the url includes the language we get the title translated # If the url includes the language we get the title translated
title_RE=r'<h1><span id="altHeadline" >(?P<title>[\s\w:/\.\?=\+-\\\']*)</span></h1>' title_RE=r'<h1><span id="altHeadline" >(?P<title>.*)</span></h1>'
title=re.search(title_RE, webpage).group('title') title=re.search(title_RE, webpage).group('title')
info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?) info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?)
"id":(?P<videoID>[\d]+).*? "id":(?P<videoID>[\d]+).*?
"mediaSlug":"(?P<mediaSlug>[\w\d]+?)"''' "mediaSlug":"(?P<mediaSlug>[\w\d]+?)"'''
thumb_RE=r'</span>[\s.]*</div>[\s.]*<img src="(?P<thumbnail>.*?)"'
thumb_match=re.search(thumb_RE,webpage)
info_match=re.search(info_RE,webpage,re.VERBOSE) info_match=re.search(info_RE,webpage,re.VERBOSE)
video_id=info_match.group('videoID') video_id=info_match.group('videoID')
mediaSlug=info_match.group('mediaSlug') mediaSlug=info_match.group('mediaSlug')
@ -4044,7 +4043,8 @@ class TEDIE(InfoExtractor):
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'ext': 'mp4', 'ext': 'mp4',
'title': title 'title': title,
'thumbnail': thumb_match.group('thumbnail')
} }
return info return info