Merge tag 'upstream/2014.10.30'

[youtubedl] / youtube_dl / extractor / freesound.py

diff --git a/youtube_dl/extractor/freesound.py b/youtube_dl/extractor/freesound.py
index de14b12e5da28b61c9c23fc568c4a3d497e7e24a..5ff62af2a33d1743709bdb076dc0c80be0e3156b 100644 (file)
--- a/youtube_dl/extractor/freesound.py
+++ b/youtube_dl/extractor/freesound.py
@@ -1,18 +1,21 @@
+from __future__ import unicode_literals
+

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

-from ..utils import determine_ext
+

 
 class FreesoundIE(InfoExtractor):
 
 class FreesoundIE(InfoExtractor):

-    _VALID_URL = r'(?:https?://)?(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'

     _TEST = {
     _TEST = {

-        u'url': u'http://www.freesound.org/people/miklovan/sounds/194503/',
-        u'file': u'194503.mp3',
-        u'md5': u'12280ceb42c81f19a515c745eae07650',
-        u'info_dict': {
-            u"title": u"gulls in the city.wav",
-            u"uploader" : u"miklovan",
-            u'description': u'the sounds of seagulls in the city',
+        'url': 'http://www.freesound.org/people/miklovan/sounds/194503/',
+        'md5': '12280ceb42c81f19a515c745eae07650',
+        'info_dict': {
+            'id': '194503',
+            'ext': 'mp3',
+            'title': 'gulls in the city.wav',
+            'uploader': 'miklovan',
+            'description': 'the sounds of seagulls in the city',

         }
     }
 
         }
     }
 


@@ -20,17 +23,17 @@ class FreesoundIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         music_id = mobj.group('id')
         webpage = self._download_webpage(url, music_id)
         mobj = re.match(self._VALID_URL, url)
         music_id = mobj.group('id')
         webpage = self._download_webpage(url, music_id)

-        title = self._html_search_regex(r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
-                                webpage, 'music title', flags=re.DOTALL)
-        music_url = self._og_search_property('audio', webpage, 'music url')
-        description = self._html_search_regex(r'<div id="sound_description">(.*?)</div>',
-                                webpage, 'description', fatal=False, flags=re.DOTALL)
+        title = self._html_search_regex(
+            r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
+            webpage, 'music title', flags=re.DOTALL)
+        description = self._html_search_regex(
+            r'<div id="sound_description">(.*?)</div>', webpage, 'description',
+            fatal=False, flags=re.DOTALL)

 
 

-        return [{
-            'id':       music_id,
-            'title':    title,            
-            'url':      music_url,
+        return {
+            'id': music_id,
+            'title': title,
+            'url': self._og_search_property('audio', webpage, 'music url'),

             'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'),
             'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'),

-            'ext':      determine_ext(music_url),

             'description': description,
             'description': description,

-        }]
+        }