require WWW::RobotRules; my $robotsrules = new WWW::RobotRules 'MOMspider/1.0'; use LWP::Simple qw(get); $url = "http://some.place/robots.txt"; my $robots_txt = get $url; $robotsrules->parse($url, $robots_txt); $url = "http://some.other.place/robots.txt"; my $robots_txt = get $url; $robotsrules->parse($url, $robots_txt); # Now we are able to check if a URL is valid for those servers that # we have obtained and parsed "robots.txt" files for. if($robotsrules->allowed($url)) { $c = get $url; ... } User-Agent: Googlebot Disallow: http://www.srvc4u.com/newsletter_page_2.htm