]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tumblr.py
ad5840ca2f4b8f2fe82c46cca261af86716f25dc
3 from .common
import InfoExtractor
9 class TumblrIE(InfoExtractor
):
10 _VALID_URL
= r
'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
12 u
'url': u
'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
13 u
'file': u
'54196191430.mp4',
14 u
'md5': u
'479bb068e5b16462f5176a6828829767',
16 u
"title": u
"tatiana maslany news"
20 def _real_extract(self
, url
):
21 m_url
= re
.match(self
._VALID
_URL
, url
)
22 video_id
= m_url
.group('id')
23 blog
= m_url
.group('blog_name')
25 url
= 'http://%s.tumblr.com/post/%s/' % (blog
, video_id
)
26 webpage
= self
._download
_webpage
(url
, video_id
)
28 re_video
= r
'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog
, video_id
)
29 video
= re
.search(re_video
, webpage
)
31 raise ExtractorError(u
'Unable to extract video')
32 video_url
= video
.group('video_url')
33 ext
= video
.group('ext')
35 video_thumbnail
= self
._search
_regex
(r
'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22',
36 webpage
, u
'thumbnail', fatal
=False) # We pick the first poster
37 if video_thumbnail
: video_thumbnail
= video_thumbnail
.replace('\\', '')
39 # The only place where you can get a title, it's not complete,
40 # but searching in other places doesn't work for all videos
41 video_title
= self
._html
_search
_regex
(r
'<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
42 webpage
, u
'title', flags
=re
.DOTALL
)
44 return [{'id': video_id
,
47 'thumbnail': video_thumbnail
,