work on soundcloud information extractor...need to talk to youtube-dl guys

[youtube-dl.git] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 831ec56..263ae65 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -15,7 +15,7 @@ __author__  = (
        )
 
 __license__ = 'Public Domain'
-__version__ = '2011.09.30'
+__version__ = '2011.10.19'
 
 UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
 
@@ -2709,11 +2709,12 @@ class DepositFilesIE(InfoExtractor):
 class FacebookIE(InfoExtractor):
        """Information Extractor for Facebook"""
 
-       _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/video/video\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+       _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
        _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
        _NETRC_MACHINE = 'facebook'
-       _available_formats = ['highqual', 'lowqual']
+       _available_formats = ['video', 'highqual', 'lowqual']
        _video_extensions = {
+               'video': 'mp4',
                'highqual': 'mp4',
                'lowqual': 'mp4',
        }
@@ -2741,10 +2742,9 @@ class FacebookIE(InfoExtractor):
        def _parse_page(self, video_webpage):
                """Extract video information from page"""
                # General data
-               data = {'title': r'class="video_title datawrap">(.*?)</',
+               data = {'title': r'\("video_title", "(.*?)"\)',
                        'description': r'<div class="datawrap">(.*?)</div>',
                        'owner': r'\("video_owner_name", "(.*?)"\)',
-                       'upload_date': r'data-date="(.*?)"',
                        'thumbnail':  r'\("thumb_url", "(?P<THUMB>.*?)"\)',
                        }
                video_info = {}
@@ -3481,6 +3481,67 @@ class XVideosIE(InfoExtractor):
                        self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
 
 
+class SoundcloudIE(InformationExtractor):
+       """Information extractor for soundcloud.com"""
+
+       _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.