a script to download wikipedia image galleries

wikifetch.pl

#!/usr/bin/env perl

use strict;
use warnings;

use WWW::Mechanize;

my $mech = new WWW::Mechanize(
	autocheck => 1
);

$mech->agent_alias('Windows IE 6');

my $user_agent = 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)';

unless($ARGV[0]){
	print STDERR "You must specify a Wikimedia Category page\n";
}

print STDERR "Loading $ARGV[0]...\n";
my $response = $mech->get($ARGV[0]);
my %fetched_urls = ();

if($mech->success()){
	print STDERR "Loaded category page...\n";
	my @links = $mech->find_all_links(url_regex => qr/Image\:/ );
	foreach my $link (@links){
		$mech->get($link->url());
		
		if($mech->success()){
			my $image_url = $mech->find_link(text => 'Full resolution');
			if($image_url){
				my $url = $image_url->url();
				unless(exists $fetched_urls{$url}){
					print STDERR "Downloading $url\n";
					
					system("curl -A \"$user_agent\" -O $url");
					if($? == -1) {
						print STDERR "\nfailed to execute: $!\n";
						exit();
					}
					elsif($? & 127) {
						printf STDERR "\nchild died with signal %d, %s coredump\n",
							($? & 127),  ($? & 128) ? 'with' : 'without';
						exit();
					}
					elsif($?){
						printf STDERR "\nchild exited with value %d\n", $? >> 8;
						exit();
					}
				}
				$fetched_urls{$url} = 1;
			}
		}
	}
}
else{
	print STDERR "Couldn't load category page...\n";
}