class TumblrIE(InfoExtractor):
_VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
_TEST = {
- u'url': u'http://resigno.tumblr.com/post/53364321212/e-de-extrema-importancia-que-esse-video-seja',
- u'file': u'53364321212.mp4',
- u'md5': u'0716d3dd51baf68a28b40fdf1251494e',
+ u'url': u'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
+ u'file': u'54196191430.mp4',
+ u'md5': u'479bb068e5b16462f5176a6828829767',
u'info_dict': {
- u"title": u"Rafael Lemos | Tumblr"
+ u"title": u"tatiana maslany news"
}
}
# The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos
- video_title = self._html_search_regex(r'<title>(?P<title>.*?)</title>',
+ video_title = self._html_search_regex(r'<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
webpage, u'title', flags=re.DOTALL)
return [{'id': video_id,