Always extract original URL from next_url (#318)

This commit is contained in:
Filippo Valsorda 2012-03-24 01:17:36 +01:00
parent 69d3b2d824
commit 071940680f

View file

@ -1171,12 +1171,11 @@ class InfoExtractor(object):
class YoutubeIE(InfoExtractor): class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com.""" """Information extractor for youtube.com."""
_PREFIX = r'(?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)' _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
_VALID_URL = r'^('+_PREFIX+r'(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
_VALID_URL_WITH_AGE = r'^('+_PREFIX+')verify_age\?next_url=([^&]+)(?:.+)?$'
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
_NETRC_MACHINE = 'youtube' _NETRC_MACHINE = 'youtube'
# Listed in order of quality # Listed in order of quality
_available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13'] _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
@ -1337,13 +1336,10 @@ class YoutubeIE(InfoExtractor):
return return
def _real_extract(self, url): def _real_extract(self, url):
# Extract original video URL from URL with age verification, using next_url parameter # Extract original video URL from URL with redirection, like age verification, using next_url parameter
mobj = re.match(self._VALID_URL_WITH_AGE, url) mobj = re.search(self._NEXT_URL_RE, url)
if mobj: if mobj:
urldecode = lambda x: re.sub(r'%([0-9a-hA-H][0-9a-hA-H])', lambda m: chr(int(m.group(1), 16)), x) url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/')
# Keep original domain. We can probably change to www.youtube.com, but it should not hurt so keep it.
# We just make sure we do not have double //, in URL, so we strip starting slash in next_url.
url = mobj.group(1) + re.sub(r'^/', '', urldecode(mobj.group(2)))
# Extract video id from URL # Extract video id from URL
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)