Merge commit '98703c7fbfcf06348220aa63f9422cdd792cfe1a'

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

diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py
index ad5840ca2f4b8f2fe82c46cca261af86716f25dc..306fe89741cce8b3c281c94349be266f221028b3 100644 (file)
--- a/youtube_dl/extractor/tumblr.py
+++ b/youtube_dl/extractor/tumblr.py
@@ -1,3 +1,6 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -7,15 +10,28 @@ from ..utils import (
 
 
 class TumblrIE(InfoExtractor):
-    _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
-    _TEST = {
-        u'url': u'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
-        u'file': u'54196191430.mp4',
-        u'md5': u'479bb068e5b16462f5176a6828829767',
-        u'info_dict': {
-            u"title": u"tatiana maslany news"
+    _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',
+        'info_dict': {
+            '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)
@@ -28,22 +44,27 @@ 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:
-           raise ExtractorError(u'Unable to extract video')
+            raise ExtractorError('Unable to extract video')
         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
-        video_title = self._html_search_regex(r'<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
-            webpage, u'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,
+        }