[vimeo/generic] Move detection logic from GenericIE to VimeoIE

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

diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py
index 2a1ae5a717cf7b2af16bf5a1ce3ef7494e28a7a6..63c20310d8e54f98f2c19bd23f9ebca947ae23d3 100644 (file)
--- a/youtube_dl/extractor/tumblr.py
+++ b/youtube_dl/extractor/tumblr.py
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from .pornhub import PornHubIE
 
 
 class TumblrIE(InfoExtractor):
@@ -28,6 +29,17 @@ class TumblrIE(InfoExtractor):
             'description': 'md5:dba62ac8639482759c8eb10ce474586a',
             'thumbnail': 're:http://.*\.jpg',
         }
+    }, {
+        'url': 'http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching',
+        'md5': 'de07e5211d60d4f3a2c3df757ea9f6ab',
+        'info_dict': {
+            'id': 'Wmur',
+            'ext': 'mp4',
+            'title': 'naked smoking & stretching',
+            'upload_date': '20150506',
+            'timestamp': 1430931613,
+        },
+        'add_ie': ['Vidme'],
     }]
 
     def _real_extract(self, url):
@@ -38,6 +50,16 @@ class TumblrIE(InfoExtractor):
         url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
         webpage = self._download_webpage(url, video_id)
 
+        vid_me_embed_url = self._search_regex(
+            r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
+            webpage, 'vid.me embed', default=None)
+        if vid_me_embed_url is not None:
+            return self.url_result(vid_me_embed_url, 'Vidme')
+
+        pornhub_url = PornHubIE._extract_url(webpage)
+        if pornhub_url:
+            return self.url_result(pornhub_url, 'PornHub')
+
         iframe_url = self._search_regex(
             r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'',
             webpage, 'iframe url')
@@ -56,6 +78,6 @@ class TumblrIE(InfoExtractor):
             'url': video_url,
             'ext': 'mp4',
             'title': video_title,
-            'description': self._og_search_description(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage, default=None),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
         }