work on soundcloud information extractor...need to talk to youtube-dl guys
authorKevin Ngo <ngoke@onid.oregonstate.edu>
Tue, 8 Nov 2011 08:03:35 +0000 (00:03 -0800)
committerKevin Ngo <ngoke@onid.oregonstate.edu>
Tue, 8 Nov 2011 08:03:35 +0000 (00:03 -0800)
youtube-dl

index cb31d13c96a75a08373a850df8928c9c750e45f3..263ae6540e8a788860b5bb52890ee7ab34962bc6 100755 (executable)
@@ -3484,9 +3484,63 @@ class XVideosIE(InfoExtractor):
 class SoundcloudIE(InformationExtractor):
        """Information extractor for soundcloud.com"""
 
-       _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/(\w\d-]+)'
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
        IE_NAME = u'soundcloud'
 
+    def __init__(self, downloader=None):
+        InfoExtractor.__init__(self, downloader)
+
+       def report_webpage(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+    def _real_initialize(self):
+        return
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+
+        # extract uploader 
+        uploader = mobj.group(3).decode('utf-8')
+        # extract simple title (uploader + slug of song title)
+               slug_title =  mobj.group(4).decode('utf-8')
+               simple_title = uploader + '-' + slug_title
+
+               self.report_webpage('%s/%s' % (uploader, slug_title))
+
+               request = urllib2.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title))
+               try:
+                       webpage = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+                       return
+
+               self.report_extraction('%s/%s' % (uploader, slug_title))
+
+        # extract video_id (soundcloud uid of song)
+        mobj = re.search
+
+        try:
+            self._download.process_info({
+                               'id':           video_id,
+                               'url':          video_url,
+                               'uploader':     uploader,
+                               'upload_date':  u'NA',
+                               'title':        video_title,
+                               'stitle':       simple_title,
+                               'ext':          u'mp3',
+                               'format':       u'NA',
+                               'player_url':   None,
+            })
 
 class PostProcessor(object):
        """Post Processor class.