From: Filippo Valsorda Date: Sat, 29 Sep 2012 15:02:38 +0000 (+0200) Subject: Merge pull request #403 from FiloSottile/re_VERBOSE X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=5c961d89df83006aede903547ec8b270ed42b785;p=youtube-dl Merge pull request #403 from FiloSottile/re_VERBOSE --- 5c961d89df83006aede903547ec8b270ed42b785 diff --cc youtube_dl/InfoExtractors.py index 4fcff77ff,3875e7fd8..bdb2ec311 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@@ -97,7 -95,24 +97,25 @@@ class InfoExtractor(object) class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|tube\.majestyc\.net/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' + _VALID_URL = r"""^ + ( + (?:https?://)? # http(s):// (optional) - (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/) # the various hostnames, with wildcard subdomains ++ (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/| ++ tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains + (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs + (?: # the various things that can precede the ID: + (?:(?:v|embed|e)/) # v/ or embed/ or e/ + |(?: # or the v= param in all its forms + (?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) + (?:\?|\#!?) # the params delimiter ? or # or #! + (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx) + v= + ) + )? # optional -> youtube.com/xxxx is OK + )? # all until now is optional -> you can pass the naked ID + ([0-9A-Za-z_-]+) # here is it! the YouTube video ID + (?(1).+)? # if we found the ID, everything can follow + $""" _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' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'