I have been trying to build in your error checking, as well as tie it into a DBM for when it crashes. Heres what I got:
#!/usr/bin/perl -w
use strict;
use warnings;
use LWP::RobotUA;
use HTML::SimpleLinkExtor;
use vars qw/$http_ua $link_extractor/;
sub crawl {
my @queue = @_;
my %visited;
my $a = 42464;
my $base;
dbmopen(%visited, "visited", 0666);
while ( my $url = shift @queue ) {
next if $visited{$url};
my $response = $http_ua->get($url);
if ($response->is_success) {
my $content = $response->content
open FILE, '>' . ++$a . '.txt';
print FILE "$url\n";
print FILE $content;
close FILE;
print qq{Downloaded: "$url"\n};
push @queue, do {
my $link_extractor = HTML::SimpleLinkExtor->new($u
+rl);
$link_extractor->parse($content);
$link_extractor->a;
};
$visited{$url} = 1;
} else {
dbmclose(%visited);
die $response->status_line;
}
}
}
$http_ua = new LWP::RobotUA theusefulbot => 'bot@theusefulnet.com';
$http_ua->delay( 10 / 6000 );
crawl(@ARGV);
This gives me: Can't call method "is_success" without a package or object reference at theusefulbot.pl line 21.
Any Ideas?
Thank you