[generic] Add support for <meta redirect>

Fixes #413
This commit is contained in:
Philipp Hagemeister 2014-02-27 07:21:59 +01:00
parent a83a3139d1
commit 89ef304bed

View file

@ -83,10 +83,10 @@ class GenericIE(InfoExtractor):
# Direct link to a video # Direct link to a video
{ {
'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
'file': 'trailer.mp4',
'md5': '67d406c2bcb6af27fa886f31aa934bbe', 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
'info_dict': { 'info_dict': {
'id': 'trailer', 'id': 'trailer',
'ext': 'mp4',
'title': 'trailer', 'title': 'trailer',
'upload_date': '20100513', 'upload_date': '20100513',
} }
@ -94,7 +94,6 @@ class GenericIE(InfoExtractor):
# ooyala video # ooyala video
{ {
'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219', 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
'file': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ.mp4',
'md5': '5644c6ca5d5782c1d0d350dad9bd840c', 'md5': '5644c6ca5d5782c1d0d350dad9bd840c',
'info_dict': { 'info_dict': {
'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ', 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
@ -102,6 +101,22 @@ class GenericIE(InfoExtractor):
'title': '2cc213299525360.mov', # that's what we get 'title': '2cc213299525360.mov', # that's what we get
}, },
}, },
# google redirect
{
'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
'info_dict': {
'id': 'cmQHVoWB5FY',
'ext': 'mp4',
'upload_date': '20130224',
'uploader_id': 'TheVerge',
'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.',
'uploader': 'The Verge',
'title': 'First Firefox OS phones side-by-side',
},
'params': {
'skip_download': False,
}
}
] ]
def report_download_webpage(self, video_id): def report_download_webpage(self, video_id):
@ -411,6 +426,18 @@ class GenericIE(InfoExtractor):
if mobj is None: if mobj is None:
# HTML5 video # HTML5 video
mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL) mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
if mobj is None:
mobj = re.search(
r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'([^\']+)\'"',
webpage)
if mobj:
new_url = mobj.group(1)
self.report_following_redirect(new_url)
return {
'_type': 'url',
'url': new_url,
}
if mobj is None: if mobj is None:
raise ExtractorError('Unsupported URL: %s' % url) raise ExtractorError('Unsupported URL: %s' % url)