Get Your War On Scrape to RSS

#!/usr/bin/perl
 
use HTML::Entities;
use LWP::Simple;
 
# print a feed header
print "<?xml version=\"1.0\" encoding=\"ISO-8859-1\"?>\n".
	"<rdf:RDF\n".
	"xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\"\n".
	"xmlns:content=\"http://purl.org/rss/1.0/modules/content/\"\n".
	"xmlns=\"http://my.netscape.com/rdf/simple/0.9/\">\n".
	"<channel>\n".
	"  <title>Get Your War On</title>\n".
	"  <link>http://www.mnftiu.cc/mnftiu.cc/war.html</link>\n".
	"  <description>A webcomic about our 9/11 epilogue.</description>\n".
	"</channel>\n\n";
 
$html_string = get ("http://www.mnftiu.cc/mnftiu.cc/war.html");
 
$i = 2;
 
while ($html_string =~ m/<a href="war(\d|\d\d).html">(\d|\d\d)<\/a>/g)
{
	$i++
}
 
$url = "http://www.mnftiu.cc/mnftiu.cc/war" . $i . ".html";
 
$html_string = get ($url);
 
while ($html_string =~ m/<img src="images\/gywo.(.*?).gif" border=0>/g)
{
	print	"<item>\n".
		"<title>" . $1 . "</title>\n".
	 	"<link>" . $url . "</link>\n".
		"<description>&lt;img src=\"http://www.mnftiu.cc/mnftiu.cc/images/gywo." . $1 . ".gif\"&gt;</description>\n";
 
	print "</item>\n\n";
}
 
print "</rdf:RDF>\n";