#!/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,") { 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); }