github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[tumblr] Modernize

Browse source
This commit is contained in:
Philipp Hagemeister 2014-09-14 12:20:14 +02:00
parent 98676c08a1
commit 3da0e1f8cd
1 changed files with 12 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
youtube_dl/extractor/tumblr.py
View file

@ -10,7 +10,7 @@
class TumblrIE(InfoExtractor):
_VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)($|/)'
_VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/(?:post|video)/(?P<id>[0-9]+)(?:$|[/?#])'
_TESTS = [{
'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
'md5': '479bb068e5b16462f5176a6828829767',
@ -56,13 +56,15 @@ def _real_extract(self, url):
# 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>.*?)(?: \| Tumblr)?</title>',
webpage, 'title', flags=re.DOTALL)
video_title = self._html_search_regex(
r'(?s)<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
webpage, 'title')
return [{'id': video_id,
'url': video_url,
'title': video_title,
'description': self._html_search_meta('description', webpage),
'thumbnail': video_thumbnail,
'ext': ext
}]
return {
'id': video_id,
'url': video_url,
'title': video_title,
'description': self._html_search_meta('description', webpage),
'thumbnail': video_thumbnail,
'ext': ext,
}