#!/usr/bin/perl -w
use strict;

use LWP::RobotUA;
use HTML::SimpleLinkExtor;

use vars qw/$http_ua $link_extractor/;
my @queue;
@queue = qw ("http://www.wired.com");
sub crawl {
        my $a = 0;
        my %visited;
        my $links;
    my @links;
    while(my $url = shift @queue) {
        next if $visited{$url};

        my $content = $http_ua->get($url)->content;
        open(FILE,">/var/www/data/$a.txt");
    print FILE "$url\n";
    print FILE "$content";
    close(FILE);
        print qq{Downloaded: "$url"\n};

        push @queue,
        do { $link_extractor->parse($content);
    @links = $link_extractor->a };
    foreach $links(@links) {
    unshift @queue, $links;
    }
        $visited{$url} = 1;
    $a++;
    }
}

$http_ua = new LWP::RobotUA theusefulbot => 'bot@theusefulnet.com';
$http_ua->delay(10/6000);
$link_extractor = new HTML::SimpleLinkExtor;

crawl(@ARGV);
[download]

Thanks again

You unshift links into the queue after pushing them there several lines above. That's weird, but does not matter as it never crawls to the same url for two times. My original code did everything you need about links and queueing, btw. Next, I can't debug mirroring wired.com, sorry :) I pay for traffic. Try to watch the growing queue of pending visits and catch the moment your script finishes. And last. Your arrays won't get too large anytime soon. Really. Your computer will be able to handle an array of million of links, I suppose, without much problems. I'd suggest filtering visited links before adding new ones to the queue and not before crawling as the first possible optimization.

How do I get it to go to other pages though. When I visit wired.com for example, I want it to take all the links off of it and visit them. And for each page that it visits off of wired, take the links off those pages and visit them and so on. This one only takes the links off of wired.com, not any of the pages that are linked to wired.

Thank you