github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[tumblr] Use unicode_literals

Browse source
This commit is contained in:
Philipp Hagemeister 2014-01-27 07:36:18 +01:00
parent 7e8caf30c0
commit c060b77446
1 changed files with 10 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
youtube_dl/extractor/tumblr.py
View file

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -9,11 +11,11 @@
class TumblrIE(InfoExtractor): 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>\d*)/(.*?)'
_TEST = { _TEST = {
u'url': u'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', 'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
u'file': u'54196191430.mp4', 'file': '54196191430.mp4',
u'md5': u'479bb068e5b16462f5176a6828829767', 'md5': '479bb068e5b16462f5176a6828829767',
u'info_dict': { 'info_dict': {
u"title": u"tatiana maslany news" "title": "tatiana maslany news"
} }
} }
@ -28,18 +30,18 @@ def _real_extract(self, url):
re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id) re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
video = re.search(re_video, webpage) video = re.search(re_video, webpage)
if video is None: if video is None:
raise ExtractorError(u'Unable to extract video') raise ExtractorError('Unable to extract video')
video_url = video.group('video_url') video_url = video.group('video_url')
ext = video.group('ext') ext = video.group('ext')
video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22', video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22',
webpage, u'thumbnail', fatal=False) # We pick the first poster webpage, 'thumbnail', fatal=False) # We pick the first poster
if video_thumbnail: video_thumbnail = video_thumbnail.replace('\\', '') if video_thumbnail: video_thumbnail = video_thumbnail.replace('\\', '')
# The only place where you can get a title, it's not complete, # The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos # but searching in other places doesn't work for all videos
video_title = self._html_search_regex(r'<title>(?P<title>.*?)(?: \| Tumblr)?</title>', video_title = self._html_search_regex(r'<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
webpage, u'title', flags=re.DOTALL) webpage, 'title', flags=re.DOTALL)
return [{'id': video_id, return [{'id': video_id,
'url': video_url, 'url': video_url,