use strict;
use LWP::UserAgent;
use HTML::LinkExtor;
use URI::URL qw(url);

my $url     = "http://kernel.org/pub/linux/kernel/v1.0/";

my $ua      = LWP::UserAgent->new;
$ua->agent('pps 0.1.43');
my @links   = ();

sub callback {
        my ($tag, %attr) = @_;
        return if $tag eq 'href';
        push(@links, values %attr);
        return (@links);
}

my $p       = HTML::LinkExtor->new(\&callback);
my $res     = $ua->request(
               HTTP::Request->new(GET => $url),
                       sub {$p->parse($_[0])});

my $base    = $res->base;
@links      = map {$_ = url($_, $base)->abs;} @links;
my @krn     = grep(/tar/, @links);

foreach my $krn (@krn) {
        my @remote_files = HTTP::Request->new(HEAD=>$krn);
        my $resp         = $ua->request(@remote_files);
        my $length       = $resp->header('Content-Length');

        my $bprecise     = sprintf "%.0f", $length;
        my $bsize        = insert_commas($bprecise);
        my $kprecise     = sprintf "%.0f", ($length/1024);
        my $ksize        = insert_commas($kprecise);

        my $archtype;    # tarball? or bzip2? or zip?
        my $krnhref      = substr($krn, 48, 70);

        if ($krn =~ /tar.gz/) {
                $archtype = "tarball";
        } elsif ($krn =~ /bz2/) {
                $archtype = "bzip";
        } else {
                $archtype = "zip";
        }
        print "Path: $krn\nFile: $krnhref ";
        print "($archtype) - ${ksize}kb, $bsize bytes\n\n";
}

sub insert_commas {   
        my $text = reverse $_[0];
        $text =~ s/(\d{3})(?=\d)(?!\d*\.)/$1,/g;
        return scalar reverse $text;
}