use strict;
my $str = 'www.hwholdsworth.com:80/a/b/c?j=k#z';
my $regex = qr/^(https?:\/\/)? # optional scheme
((?:[-a-z0-9._~!$&\'()*+,;=]|%[0-9a-f]{2})+ # optional username@,
(?::(?:[-a-z0-9._~!$&\'()*+,;=]|%[0-9a-f]{2})+)?@)? # or username:password@
(?:((?:(?:\d|[1-9]\d|1\d{2}|2[0-4]\d|25[0-5])\.){3}(?:\d|[1-9]\d|1\d{2}|2[0-4]\d|25[0-5])) # IPv4 address
|((?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\.)+[a-z][a-z0-9-]*[a-z0-9])) # or dot-separated domain labels
(:\d+)? # optional port number
((?:\/(?:[-a-z0-9._~!$&\'()*+,;=:@]|%[0-9a-f]{2})+)*\/?) # path (possibly empty, may end in /, no double-// allowed)
(\?(?:[-a-z0-9._~!$&\'()*+,;=:@\/?]|%[0-9a-f]{2})*)? # optional querystring
(\#(?:[-a-z0-9._~!$&\'()*+,;=:@\/?]|%[0-9a-f]{2})*)?$ # optional fragment/ixp;
if ( $str =~ /$regex/ ) {
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