From b9a2c53833a3cebc32df908aad74f7c5a3537aa1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Wed, 4 Dec 2013 23:43:50 +0100 Subject: [PATCH] [metacafe] Add support for cbs videos (fixes #1838) They use theplatform.com --- youtube_dl/extractor/metacafe.py | 29 +++++++++++++++++++++++++---- youtube_dl/extractor/theplatform.py | 2 +- 2 files changed, 26 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index 91480ba87..e59bdd604 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -69,6 +69,21 @@ class MetacafeIE(InfoExtractor): u'age_limit': 18, }, }, + # cbs video + { + u'url': u'http://www.metacafe.com/watch/cb-0rOxMBabDXN6/samsung_galaxy_note_2_samsungs_next_generation_phablet/', + u'info_dict': { + u'id': u'0rOxMBabDXN6', + u'ext': u'flv', + u'title': u'Samsung Galaxy Note 2: Samsung\'s next-generation phablet', + u'description': u'md5:54d49fac53d26d5a0aaeccd061ada09d', + u'duration': 129, + }, + u'params': { + # rtmp download + u'skip_download': True, + }, + }, ] @@ -106,10 +121,16 @@ class MetacafeIE(InfoExtractor): video_id = mobj.group(1) - # Check if video comes from YouTube - mobj2 = re.match(r'^yt-(.*)$', video_id) - if mobj2 is not None: - return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')] + # the video may come from an external site + m_external = re.match('^(\w{2})-(.*)$', video_id) + if m_external is not None: + prefix, ext_id = m_external.groups() + # Check if video comes from YouTube + if prefix == 'yt': + return self.url_result('http://www.youtube.com/watch?v=%s' % ext_id, 'Youtube') + # CBS videos use theplatform.com + if prefix == 'cb': + return self.url_result('theplatform:%s' % ext_id, 'ThePlatform') # Retrieve video webpage to extract further information req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index d1d6a4c2c..920689511 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -11,7 +11,7 @@ _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language class ThePlatformIE(InfoExtractor): - _VALID_URL = r'https?://link\.theplatform\.com/s/[^/]+/(?P[^/\?]+)' + _VALID_URL = r'(?:https?://link\.theplatform\.com/s/[^/]+/|theplatform:)(?P[^/\?]+)' _TEST = { # from http://www.metacafe.com/watch/cb-e9I_cZgTgIPd/blackberrys_big_bold_z30/