Random perl hack for getting new xckd images....

get_xckd.pl

#!/usr/bin/env perl
use strict;
use LWP::Simple;
use Data::Dumper;

my $dump_folder = '/home/damian/Pictures/xckd';
my $base_perm_url = 'http://xkcd.com';
my $base_image_url = 'http://imgs.xkcd.com/comics';

sub get_cid {
	my $content = get "$base_perm_url/";

	if( !$content ) {
		print "Failed to get cid\n";
		return;
	}

	my $url = $base_perm_url;
	$url =~ s/\//\\\//g;
	$url =~ s/\./\\./g;
	my $pattern = "<h3>Permanent link to this comic: ($url\/([0-9]+)\/)<\/h3>";

	my $id = $content;
	$id =~ s/\n+//g;
	$id =~ s/.*$pattern.*/$2/;

	if( $id =~ /^[0-9]+$/ ) {
		return $id;
	}

	return;
}

sub get_lcid {
	if( -f "$dump_folder/.lcid" ) {
		open(my $FH, "<", "$dump_folder/.lcid");
		return <$FH>;
		close($FH);
	}
	return 1;
}

sub update_lcid {
	my $id = shift;

	open(my $FH, ">", "$dump_folder/.lcid");
	print $FH $id;
	close($FH);
}

sub get_image {
	my $id = shift;
	my $name = shift;

	my $content = get "$base_image_url/$name";
	if( !$content ) {
		print "Failed to get $name ($id)\n";
		return;
	}

	my $ext = ($name =~ m/([^.]+)$/)[0];
	open(my $FH, ">", "$dump_folder/$id.$ext");
	print $FH $content;
	close($FH);
	return 1;
}

sub get_image_from_id {
	my $id = shift;
	my $content = get "$base_perm_url/$id";

	if( !$content ) {
		print "Failed to get image for $id\n";
		return;
	}

	my $url = $base_image_url;
	$url =~ s/\//\\\//g;
	$url =~ s/\./\\./g;
	my $pattern = "<h3>Image URL \\(for hotlinking\/embedding\\): ($url\/(.*))<\/h3>";

	my $image = $content;
	$image =~ s/\n+//g;
	$image =~ s/.*$pattern.*/$2/;
	return $image;
}

sub main {
	if( !-d "$dump_folder" ) {
		mkdir($dump_folder);
	}
	
	my $lcid = get_lcid;
	my $cid = get_cid;
	if( !$cid ) {
		print "Could not get cid\n";
		exit;
	}

	if( $lcid < $cid ) {
		my $i;
		for( $i=$lcid+1; $i < $cid; $i++ ) {
			my $image = get_image_from_id($i);
			if( !$image ) {
				print "Failed to get image for $i....\n";
			} else {
				if(get_image($i, $image)) {
					print "Downloaded $i ($image)\n";
					update_lcid($i);
				}
			}
		}
	}
}

main;