X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube-dl;h=e3c324f1f20ce8efed6e9b9817ab6030898e15e9;hb=240b737ebd2356f9d117ccd0c14349d4ec88e90e;hp=7690898b2e623cb115554524dc52ba1318e4169a;hpb=65cd34c5d735f968b03c6e618db4e177ed80f1ac;p=youtube-dl.git diff --git a/youtube-dl b/youtube-dl index 7690898b2..e3c324f1f 100755 --- a/youtube-dl +++ b/youtube-dl @@ -4,6 +4,7 @@ # License: Public domain code import htmlentitydefs import httplib +import locale import math import netrc import os @@ -430,8 +431,8 @@ class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' - _LOGIN_URL = 'http://www.youtube.com/login?next=/' - _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/' + _LOGIN_URL = 'http://uk.youtube.com/login?next=/' + _AGE_URL = 'http://uk.youtube.com/verify_age?next_url=/' _NETRC_MACHINE = 'youtube' @staticmethod @@ -536,7 +537,7 @@ class YoutubeIE(InfoExtractor): video_extension = {'18': 'mp4', '17': '3gp'}.get(format_param, 'flv') # Normalize URL, including format - normalized_url = 'http://www.youtube.com/watch?v=%s' % video_id + normalized_url = 'http://uk.youtube.com/watch?v=%s' % video_id if format_param is not None: normalized_url = '%s&fmt=%s' % (normalized_url, format_param) request = urllib2.Request(normalized_url, None, std_headers) @@ -553,7 +554,7 @@ class YoutubeIE(InfoExtractor): if mobj is None: self.to_stderr(u'ERROR: unable to extract "t" parameter') return [None] - video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1)) + video_real_url = 'http://uk.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1)) if format_param is not None: video_real_url = '%s&fmt=%s' % (video_real_url, format_param) self.report_video_url(video_id, video_real_url) @@ -592,7 +593,7 @@ class MetacafeIE(InfoExtractor): """Information Extractor for metacafe.com.""" _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' - _DISCLAIMER = 'http://www.metacafe.com/disclaimer' + _DISCLAIMER = 'http://www.metacafe.com/family_filter/' _youtube_ie = None def __init__(self, youtube_ie, downloader=None): @@ -631,10 +632,10 @@ class MetacafeIE(InfoExtractor): # Confirm age disclaimer_form = { - 'allowAdultContent': '1', + 'filters': '0', 'submit': "Continue - I'm over 18", } - request = urllib2.Request('http://www.metacafe.com/watch/', urllib.urlencode(disclaimer_form), std_headers) + request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers) try: self.report_age_confirmation() disclaimer = urllib2.urlopen(request).read() @@ -654,7 +655,7 @@ class MetacafeIE(InfoExtractor): # Check if video comes from YouTube mobj2 = re.match(r'^yt-(.*)$', video_id) if mobj2 is not None: - return self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1)) + return self._youtube_ie.extract('http://uk.youtube.com/watch?v=%s' % mobj2.group(1)) simple_title = mobj.group(2).decode('utf-8') video_extension = 'flv' @@ -684,7 +685,7 @@ class MetacafeIE(InfoExtractor): video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) - mobj = re.search(r'(?im)(.*) - Video', webpage) if mobj is None: self.to_stderr(u'ERROR: unable to extract title') return [None] @@ -710,7 +711,7 @@ class YoutubePlaylistIE(InfoExtractor): """Information Extractor for YouTube playlists.""" _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)' - _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s' + _TEMPLATE_URL = 'http://uk.youtube.com/view_play_list?p=%s&page=%s' _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s' _youtube_ie = None @@ -752,10 +753,11 @@ class YoutubePlaylistIE(InfoExtractor): return [None] # Extract video identifiers - ids_in_page = set() + ids_in_page = [] for mobj in re.finditer(self._VIDEO_INDICATOR, page): - ids_in_page.add(mobj.group(1)) - video_ids.extend(list(ids_in_page)) + if mobj.group(1) not in ids_in_page: + ids_in_page.append(mobj.group(1)) + video_ids.extend(ids_in_page) if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page: break @@ -763,7 +765,7 @@ class YoutubePlaylistIE(InfoExtractor): information = [] for id in video_ids: - information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)) + information.extend(self._youtube_ie.extract('http://uk.youtube.com/watch?v=%s' % id)) return information class PostProcessor(object): @@ -836,7 +838,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2008.07.26', + version='2008.11.01', conflict_handler='resolve', ) parser.add_option('-h', '--help', @@ -900,6 +902,9 @@ if __name__ == '__main__': youtube_pl_ie = YoutubePlaylistIE(youtube_ie) # File downloader + charset = locale.getdefaultlocale()[1] + if charset is None: + charset = 'ascii' fd = FileDownloader({ 'usenetrc': opts.usenetrc, 'username': opts.username, @@ -909,7 +914,7 @@ if __name__ == '__main__': 'forcetitle': opts.gettitle, 'simulate': (opts.simulate or opts.geturl or opts.gettitle), 'format': opts.format, - 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode()) + 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(charset)) or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s') or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s') or u'%(id)s.%(ext)s'),