use strict;
my $str = 'Yes:
http://google.it
<a href="http://www.it.com">algo</a>
https://something.com
https://www.something.com
<a href="iaaaaaaaat.com">hola</a>
http://something.com
http://www.something.com
<a href=\'www.it.com\'>hola</a>
https://something.gov
<a href=\'https://www.something.gov\'>Hola</a>
http://something.gov
<a href="ftp://longurljapanese.jp">hollaaaa</a>
<a href="it.it">hollaaaa</a>
http://www.something.gov
https://something.org
https://www.something.org
http://something.org
http://www.something.org
https://something.net
https://www.something.net
http://something.net
http://www.something.net
https://something.edu
https://www.something.edu
http://something.edu
http://www.something.edu
https://something.biz
https://www.something.biz
http://something.biz
http://www.something.biz
something.biz
www.something.biz
something.edu
www.something.edu
something.net
www.something.net
something.org
www.something.org
something.gov
www.something.gov
something.com
www.something.com
No:
https://www.something
http://www.something';
my $regex = qr/href=["'](https?:\/\/(?:www\.|(?!www))[^\s\.]+\.[^\s"']{2,}|(?!ftp:\/\/)[^\s]+\.[^\s'"]{2,})/p;
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