use strict;
my $str = 'https://test.example.com:3000/path/to/page?q=1234&a=b&d=e
https://lots.of.subs.test.example.com:3000/path/to/page?q=1234&a=b&d=e
http://192.168.100.0:8080/path/to/page?q=123
http://localhost:3000/path/to/page?q=123
';
my $regex = qr/^(?<fulldomain>(?<protocol>[a-z]{2,6}):\/\/(?:((?<subdomain>[a-z0-9\-\.]*\.){0,99})(?<domain>[a-z\-0-9]{1,100})\.(?<extension>[a-z]{1,10})|(?<ipaddress>(?:25[0-5]|2[0-4]\d|[0-1]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d{1,2})){3})|(?<localhost>localhost))(?<port>\:[0-9]{1,6}){0,1})\/?(?<filepath>(?<path>[a-z0-9\-_%]{1,20}\/{1}){0,}(?<filename>[a-z0-9\-_]{1,20}\.[a-z0-9]{2,6}){0,1}){0,1}(?<route>(\/[a-z_0-9\-_]{1,20}){1,}){0,10}(?<query>\?[a-z0-9%\+_\-&=\.@\!,\:]{0,200}){0,1}$/mp;
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