simple crawler for getting xkcd comics

crawlThem.pl

#!/usr/bin/env perl

# A simple crawler for getting the nice comics from xkcd.com
#(c) Thomas Lang, 2016
#
# Yes, this is damn non-performant, but if it works, it ain't stupid.

use warnings;
use strict;
use LWP::Simple; 
use XML::Twig;

# No error handling!
# 
# minIdx = minimum image number, e.g. 1615
# maxIdx = maximum image number, e.g. 1618
# verbose = indicator if prints should be made
#      if verbose eq "y" (for yes) then print something
#      else                             print nothing
my ($minIdx, $maxIdx, $verbose) = @ARGV;

# Gets a single image, quite ineffective
sub getImg {
    my $idx = shift;
    my $uri = "http://www.xkcd.com/$idx/";
    my $fil = "./$idx";

    getstore($uri, $fil);

    # Leave only line 64 in the file
    open(my $FH1, '<', $fil) or die "FUCK";
    my @lines = <$FH1>;
    my $line = $lines[63];
    close $FH1;

    open(my $FH2, '>', $fil) or die "Error:$!\n";
    print $FH2 $line;
    close $FH2;
    # end

    my $i;

    # get image url
    my $twig = XML::Twig->new(
        twig_roots => {
            '/img' => sub {
                my $val = $_->att('src');
                $val =~ s/\/\///; # Strip leading '//'
                $i = $val;
            },
        },
        )->parsefile($fil);


    my $img = $i;
    $img =~ s/imgs\.xkcd\.com\/comics\///;
    print "Getting image '$img' ... " if ($verbose eq "y");
    getstore("http://$i", $img);
    print "done.\n" if ($verbose eq "y");

    unlink $fil; # Remove temporary gotten file
}

foreach my $ix ($minIdx .. $maxIdx) {
    getImg $ix;
}