#!/usr/bin/perl -w

use strict;
use diagnostics;
use LWP::RobotUA;
use URI::URL;
#use HTML::Parser ();
use HTML::SimpleLinkExtor;

my $a=0;
my $i;
my $links;
my $base;
my $u;
for($u=1; $u<1000000000; $u++)  {
open(FILE1,"</var/www/links/file$u.txt");
while(<FILE1>) {
my $ua = LWP::RobotUA->new('theusefulbot', 'bot@theusefulnet.com');
#my $p = HTML::Parser->new();
$ua->delay(10/600);
my $content = $ua->get($_)->content;
#my $text = $p->parse($content)->parse;
open(OUTPUT,">/var/www/data/$a.txt");

print OUTPUT "$content";
close(OUTPUT);
my $extor = HTML::SimpleLinkExtor->new($base);
$extor->parse($content);
my @links = $extor->a;
$u++;
open(FILE2,">/var/www/links/file$u.txt");
foreach $links(@links) {
print FILE2 url("$links")->abs("$_");
print FILE2 "\n";
}

$a++;
$i=$a;
$u--;
}
close(FILE1);
close(FILE2);
}
[download]

UPDATE: NEW WORKING CODE Thanks to Kappa for making it check itself against a visited list.

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

use LWP::RobotUA;
use HTML::SimpleLinkExtor;
use URI::URL;

use vars qw/$http_ua $link_extractor/;

sub crawl {
    my @queue = @_;
    my %visited;
    my $a = 0;
    my $base;
    while ( my $url = shift @queue ) {
        next if $visited{$url};

        my $content = $http_ua->get($url)->content;

        open FILE, '>' . ++$a . '.txt';
        print FILE "$url\n";
    print FILE $content;
        close FILE;

        print qq{Downloaded: "$url"\n};

        push @queue, do {
            my $link_extractor = HTML::SimpleLinkExtor->new($url);
            $link_extractor->parse($content);
            $link_extractor->a;

        };
        $visited{$url} = 1;
    }
}

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

crawl(@ARGV);
[download]

---

---

Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!

Titles consisting of a single word are discouraged, and in most cases are disallowed outright.

Read Where should I post X? if you're not absolutely sure you're posting in the right place.

Please read these before you post! —

• How do I compose an effective node title?
• How do I post a question effectively?
• Markup in the Monastery

Posts may use any of the Perl Monks Approved HTML tags:

a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr

You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)

	For:		Use:
	&		&
	<		&lt;
	>		&gt;
	[		&#91;
	]		&#93;

Link using PerlMonks shortcuts! What shortcuts can I use for linking?

See Writeup Formatting Tips and other pages linked from there for more info.