Merge remote-tracking branch '5moufl/behindkink'

[youtube-dl] / youtube_dl / extractor / tumblr.py

diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py
index 54436906875a727ac6f6eeb3de555f0c0cd461bf..306fe89741cce8b3c281c94349be266f221028b3 100644 (file)
--- 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*)($|/)'
-    _TEST = {
+    _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/(?:post|video)/(?P<id>[0-9]+)(?:$|[/?#])'
+    _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)
@@ -42,12 +56,15 @@ class TumblrIE(InfoExtractor):
 
         # 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)
-
-        return [{'id': video_id,
-                 'url': video_url,
-                 'title': video_title,
-                 'thumbnail': video_thumbnail,
-                 'ext': ext
-                 }]
+        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,
+        }