use strict;
my $str = 'http://v.youku.com/v_show/id_XMTMwMDYxMjQxMg==_ev_1.html?from=y1.3-idx-uhome-1519-20887.205805-205902.1-1
http://v.youku.com/v_show/id_XMjMxOTQyOTQw.html?from=y1.6-97.3.1.a44aa406e0c711df97c0
http://v.youku.com/v_show/id_XMTI5Mjg5NjE4MA==.html?from=y1.3-idx-uhome-1519-20887.205921-205922-205810-205923.1-1
http://v.youku.com/v_show/id_XMTI5Mjg5NjE4MA==.html
http://player.youku.com/player.php/sid/XMTI5Mjg5NjE4MA==/v.swf
http://player.youku.com/player.php/sid/XMTI5Mjg5NjE4MA==/v.swf
http://player.youku.com/embed/XMTI5Mjg5NjE4MA==
http://player.youku.com/player.php/Type/Folder/Fid/25924643/Ob/1/sid/XMTMwMDgxNTY0NA==/v.swf
http://player.youku.com/embed/XMTI5NTcwMDA3Mg==';
my $regex = qr/(https?:\/\/)?(v|player)\.youku\.com\/(v_show|player\.php|embed)(\/.*sid)?\/(id_)?(\w+=*)|(\w+)/ip;
if ( $str =~ /$regex/g ) {
print "Whole match is ${^MATCH} and its start/end positions can be obtained via \$-[0] and \$+[0]\n";
# print "Capture Group 1 is $1 and its start/end positions can be obtained via \$-[1] and \$+[1]\n";
# print "Capture Group 2 is $2 ... and so on\n";
}
# ${^POSTMATCH} and ${^PREMATCH} are also available with the use of '/p'
# Named capture groups can be called via $+{name}
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Perl, please visit: http://perldoc.perl.org/perlre.html