use strict;
my $str = 'Допустимые адреса
http://www.company.com
https://www.company.com
https://company.com
http://company.com
www.company.com
company.com
http://www.company.com/some
https://www.company.com/some
www.company.com/some
http://www.company.com/some%20address
https://www.company.com/some%20address
www.company.com/some%20address
http://www.company.com/?sidebar=buyerDetail
https://www.company.com/?sidebar=buyerDetail
www.company.com/?sidebar=buyerDetail
http://www.company.com/some/sidebar=buyerDetail
https://www.company.com/some/sidebar=buyerDetail
www.company.com/some/sidebar=buyerDetail
Недопустимые адреса
1http://www.company.com/some/sidebar=buyerDetail
1https://www.company.com/some/sidebar=buyerDetail
.http://www.company.com/some/sidebar=buyerDetail
.https://www.company.com/some/sidebar=buyerDetail
.http://www.company.com/some/sidebar=buyerDetail
.https://www.company.com/some/sidebar=buyerDetail
com/some/sidebar=buyerDetail
+=.company.com/some/sidebar=buyerDetail';
my $regex = qr/^(https?:\/\/(?:www\.|(?!www))[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\.[^\s]{2,}|www\.[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\.[^\s]{2,}|https?:\/\/(?:www\.|(?!www))[a-zA-Z0-9]+\.[^\s]{2,}|www\.[a-zA-Z0-9]+\.[^\s]{2,})$/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