#!/usr/bin/perl -w use strict; use LWP::Simple; my $html = get('http://www.bbc.co.uk/'); while ($html =~ m|href\s*=\s*"((?:[^/]+://[^"/]+)?)/?([^"]+)"|gi) { print "$1, $2 \n"; } #### while ($html =~ m|href\s*=\s*"((?:[^/]+://[^"/]+)?)/?([^"]+)"\s*>(.*?)|gi) { print "$1, $2, $3 \n"; }