Update changelog.

[youtubedl] / youtube_dl / extractor / tumblr.py

diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py
index b0851b4f9cd360fc8d4ba58c725c7b04d4708c50..54436906875a727ac6f6eeb3de555f0c0cd461bf 100644 (file)
--- a/youtube_dl/extractor/tumblr.py
+++ b/youtube_dl/extractor/tumblr.py
@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor


@@ -7,7 +9,15 @@ from ..utils import (
 
 
 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 = {
+        'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
+        'file': '54196191430.mp4',
+        'md5': '479bb068e5b16462f5176a6828829767',
+        'info_dict': {
+            "title": "tatiana maslany news"
+        }
+    }

 
     def _real_extract(self, url):
         m_url = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         m_url = re.match(self._VALID_URL, url)


@@ -20,18 +30,20 @@ class TumblrIE(InfoExtractor):
         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)
         if video is None:
         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)
         if video is None:

-           raise ExtractorError(u'Unable to extract video')
+            raise ExtractorError('Unable to extract video')

         video_url = video.group('video_url')
         ext = video.group('ext')
 
         video_url = video.group('video_url')
         ext = video.group('ext')
 

-        video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22',
-            webpage, u'thumbnail', fatal=False)  # We pick the first poster
-        if video_thumbnail: video_thumbnail = video_thumbnail.replace('\\', '')
+        video_thumbnail = self._search_regex(
+            r'posters.*?\[\\x22(.*?)\\x22',
+            webpage, 'thumbnail', fatal=False)  # We pick the first poster
+        if video_thumbnail:
+            video_thumbnail = video_thumbnail.replace('\\\\/', '/')

 
         # The only place where you can get a title, it's not complete,
         # but searching in other places doesn't work for all videos
 
         # 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>',
-            webpage, u'title', flags=re.DOTALL)
+        video_title = self._html_search_regex(r'<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
+            webpage, 'title', flags=re.DOTALL)

 
         return [{'id': video_id,
                  'url': video_url,
 
         return [{'id': video_id,
                  'url': video_url,