X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ftumblr.py;h=2882c1809e0bd55c1e6c8b441c19293aeb64d301;hb=199ece7eb83ffe7ba069b50080fe971df1db2d6c;hp=abbbb9661d2c3a3924c1657b6b28a22f47c8bdd0;hpb=c060b774467f499bc946ae024bc9fc4ecfbc6d67;p=youtube-dl

diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py
index abbbb9661..2882c1809 100644
--- a/youtube_dl/extractor/tumblr.py
+++ b/youtube_dl/extractor/tumblr.py
@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
 import re
@@ -9,15 +10,28 @@ from ..utils import (
 
 
 class TumblrIE(InfoExtractor):
-    _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
-    _TEST = {
+    _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)($|/)'
+    _TESTS = [{
         '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"
+            'id': '54196191430',
+            'ext': 'mp4',
+            'title': 'tatiana maslany news, Orphan Black || DVD extra - behind the scenes ↳...',
+            'description': 'md5:dfac39636969fe6bf1caa2d50405f069',
+            'thumbnail': 're:http://.*\.jpg',
         }
-    }
+    }, {
+        'url': 'http://5sostrum.tumblr.com/post/90208453769/yall-forgetting-the-greatest-keek-of-them-all',
+        'md5': 'bf348ef8c0ef84fbf1cbd6fa6e000359',
+        'info_dict': {
+            'id': '90208453769',
+            'ext': 'mp4',
+            'title': '5SOS STRUM ;)',
+            'description': 'md5:dba62ac8639482759c8eb10ce474586a',
+            'thumbnail': 're:http://.*\.jpg',
+        }
+    }]
 
     def _real_extract(self, url):
         m_url = re.match(self._VALID_URL, url)
@@ -34,9 +48,11 @@ class TumblrIE(InfoExtractor):
         video_url = video.group('video_url')
         ext = video.group('ext')
 
-        video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22',
+        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('\\', '')
+        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
@@ -46,6 +62,7 @@ class TumblrIE(InfoExtractor):
         return [{'id': video_id,
                  'url': video_url,
                  'title': video_title,
+                 'description': self._html_search_meta('description', webpage),
                  'thumbnail': video_thumbnail,
                  'ext': ext
                  }]