now downloads soundcloud songs, need to polish title grabbing and file naming

pull/213/head
Kevin Ngo 2011-11-12 16:48:43 -08:00
parent b20d4f8626
commit 871be928a8
1 changed files with 11 additions and 10 deletions

View File

@ -3533,10 +3533,10 @@ class SoundcloudIE(InfoExtractor):
self.report_extraction('%s/%s' % (uploader, slug_title)) self.report_extraction('%s/%s' % (uploader, slug_title))
# extract uid and access token # extract uid and access token
mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', page) mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage)
if mobj: if mobj:
video_id = match.group(1) video_id = mobj.group(1)
stream_token = match.group(2) stream_token = mobj.group(2)
# construct media url (with uid/token) to request song # construct media url (with uid/token) to request song
mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s" mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s"
@ -3544,17 +3544,18 @@ class SoundcloudIE(InfoExtractor):
# description # description
description = u'No description available' description = u'No description available'
mobj = re.search('track-description-value"><p>(.*?)</p>', page) mobj = re.search('track-description-value"><p>(.*?)</p>', webpage)
if mobj: if mobj:
description = mobj.group(1) description = mobj.group(1)
# upload date # upload date
mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", page) upload_date = None
mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage)
if mobj: if mobj:
try: try:
upload_date = datetime.datetime.strptime(match.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d') upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
except: except Exception as e:
pass print str(e)
# for soundcloud, a request must be made to a cross domain to establish # for soundcloud, a request must be made to a cross domain to establish
# needed cookies # needed cookies
@ -3563,10 +3564,10 @@ class SoundcloudIE(InfoExtractor):
try: try:
self._downloader.process_info({ self._downloader.process_info({
'id': video_id, 'id': video_id,
'url': video_url, 'url': mediaURL,
'uploader': uploader, 'uploader': uploader,
'upload_date': upload_date, 'upload_date': upload_date,
'title': video_title, 'title': simple_title,
'stitle': simple_title, 'stitle': simple_title,
'ext': u'mp3', 'ext': u'mp3',
'format': u'NA', 'format': u'NA',