Fix for YouTube internationalization changes

This commit is contained in:
Ricardo Garcia 2009-01-31 10:12:22 +01:00
parent 240b737ebd
commit 72ac78b8b0

View File

@ -431,14 +431,19 @@ class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com.""" """Information extractor for youtube.com."""
_VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
_LOGIN_URL = 'http://uk.youtube.com/login?next=/' _LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_AGE_URL = 'http://uk.youtube.com/verify_age?next_url=/' _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NETRC_MACHINE = 'youtube' _NETRC_MACHINE = 'youtube'
@staticmethod @staticmethod
def suitable(url): def suitable(url):
return (re.match(YoutubeIE._VALID_URL, url) is not None) return (re.match(YoutubeIE._VALID_URL, url) is not None)
def report_lang(self):
"""Report attempt to set language."""
self.to_stdout(u'[youtube] Setting language')
def report_login(self): def report_login(self):
"""Report attempt to log in.""" """Report attempt to log in."""
self.to_stdout(u'[youtube] Logging in') self.to_stdout(u'[youtube] Logging in')
@ -487,6 +492,15 @@ class YoutubeIE(InfoExtractor):
if username is None: if username is None:
return return
# Set language
request = urllib2.Request(self._LOGIN_URL, None, std_headers)
try:
self.report_lang()
urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.to_stderr(u'WARNING: unable to set language: %s' % str(err))
return
# Log in # Log in
login_form = { login_form = {
'current_form': 'loginForm', 'current_form': 'loginForm',
@ -537,7 +551,7 @@ class YoutubeIE(InfoExtractor):
video_extension = {'18': 'mp4', '17': '3gp'}.get(format_param, 'flv') video_extension = {'18': 'mp4', '17': '3gp'}.get(format_param, 'flv')
# Normalize URL, including format # Normalize URL, including format
normalized_url = 'http://uk.youtube.com/watch?v=%s' % video_id normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
if format_param is not None: if format_param is not None:
normalized_url = '%s&fmt=%s' % (normalized_url, format_param) normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
request = urllib2.Request(normalized_url, None, std_headers) request = urllib2.Request(normalized_url, None, std_headers)
@ -554,7 +568,7 @@ class YoutubeIE(InfoExtractor):
if mobj is None: if mobj is None:
self.to_stderr(u'ERROR: unable to extract "t" parameter') self.to_stderr(u'ERROR: unable to extract "t" parameter')
return [None] return [None]
video_real_url = 'http://uk.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1)) video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1))
if format_param is not None: if format_param is not None:
video_real_url = '%s&fmt=%s' % (video_real_url, format_param) video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
self.report_video_url(video_id, video_real_url) self.report_video_url(video_id, video_real_url)
@ -655,7 +669,7 @@ class MetacafeIE(InfoExtractor):
# Check if video comes from YouTube # Check if video comes from YouTube
mobj2 = re.match(r'^yt-(.*)$', video_id) mobj2 = re.match(r'^yt-(.*)$', video_id)
if mobj2 is not None: if mobj2 is not None:
return self._youtube_ie.extract('http://uk.youtube.com/watch?v=%s' % mobj2.group(1)) return self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
simple_title = mobj.group(2).decode('utf-8') simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv' video_extension = 'flv'
@ -711,7 +725,7 @@ class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists.""" """Information Extractor for YouTube playlists."""
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)' _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
_TEMPLATE_URL = 'http://uk.youtube.com/view_play_list?p=%s&page=%s' _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&' _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s' _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
_youtube_ie = None _youtube_ie = None
@ -765,7 +779,7 @@ class YoutubePlaylistIE(InfoExtractor):
information = [] information = []
for id in video_ids: for id in video_ids:
information.extend(self._youtube_ie.extract('http://uk.youtube.com/watch?v=%s' % id)) information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
return information return information
class PostProcessor(object): class PostProcessor(object):