#!/usr/bin/perl use strict; use warnings; use LWP::RobotUA; use HTML::LinkExtor; use HTML::TokeParser; use URI::URL; use Data::Dumper; # for show and troubleshooting my $ua = LWP::RobotUA->new(); foreach my $forum_id (17, 3) { my $url = "http://www.nukeforums.com/forums/viewforum.php?f=$forum_id"; my $links = get_threads($url); foreach my $page (@$links) { ... } } sub get_thread { ... } sub get_threads { my $page = shift; my @links; my $lp = HTML::LinkExtor->new(sub { my($tag, %attr) = @_; return unless exists $attr{'href'}; return if $attr{'href'} !~ /^viewtopic\.php\?t=/; push @links, values %attr; }); my $request = HTTP::Request->new(GET => $url); my $response = $ua->request($request, sub {$lp->parse($_[0])}); # Expand URLs to absolute ones my $base = $response->base; return [ map { url($_, $base)->abs } @links ]; }