Merge pull request #1050 from yasoob/master
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Mon, 15 Jul 2013 19:06:51 +0000 (21:06 +0200)
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Mon, 15 Jul 2013 19:06:51 +0000 (21:06 +0200)
Added an IE and test for Freesound.org .

youtube_dl/extractor/__init__.py
youtube_dl/extractor/freesound.py [new file with mode: 0644]

index 1893eb1cb1e321871079c6caa1bc87518719fe2a..7a2a09ab0fafc9049b67dcbd883d4a8ddb5171e4 100644 (file)
@@ -20,6 +20,7 @@ from .eighttracks import EightTracksIE
 from .escapist import EscapistIE
 from .facebook import FacebookIE
 from .flickr import FlickrIE
+from .freesound import FreeSoundIE
 from .funnyordie import FunnyOrDieIE
 from .gamespot import GameSpotIE
 from .gametrailers import GametrailersIE
diff --git a/youtube_dl/extractor/freesound.py b/youtube_dl/extractor/freesound.py
new file mode 100644 (file)
index 0000000..9a2774d
--- /dev/null
@@ -0,0 +1,36 @@
+# -*- coding: utf-8 -*-
+import re
+
+from .common import InfoExtractor
+
+class FreeSoundIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?freesound\.org/people/([^/]+)/sounds/([^/]+)'
+    _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 by miklovan",
+            u"uploader" : u"miklovan"
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        music_id = mobj.group(2)
+        webpage = self._download_webpage(url, music_id)
+        title = self._html_search_regex(r'<meta property="og:title" content="([^"]*)"',
+                                webpage, 'music title')
+        music_url = self._html_search_regex(r'<meta property="og:audio" content="([^"]*)"',
+                                webpage, 'music url')       
+        uploader = self._html_search_regex(r'<meta property="og:audio:artist" content="([^"]*)"',
+                                webpage, 'music uploader')                                                                        
+        ext = music_url.split('.')[-1]
+
+        return [{
+            'id':       music_id,
+            'title':    title,            
+            'url':      music_url,
+            'uploader': uploader,
+            'ext':      ext,
+        }]
\ No newline at end of file