The Onion's What Do You Think? Scrape to RSS

#!/usr/bin/perl
 
use HTML::Entities;
use LWP::Simple;
 
print	"<?xml version=\"1.0\"?>\n".
	"<rss version=\"2.0\">\n".
 
	"<channel>\n".
	"<title>The Onion - What Do You Think?</title>\n".
	"<link>http://www.theonion.com/content/topics/American+Voices</link>\n".
	"<description>The Onion's place to vent anger at All of Us USA.</description>\n".
	"<ttl>180</ttl>\n".
	"<skipDays>\n".
		"\t<day>Saturday</day>\n".
		"\t<day>Sunday</day>\n".
	"</skipDays>\n".
	"<category>Humor</category>\n".
	"<language>en-us</language>\n".
	"\n";
 
$html_string = get("http://www.theonion.com/content/topics/American+Voices");
 
while ($html_string =~ m/<a href="(.*?)" class="plain">(.*?)<\/a>/g)
{
	$url = "http://www.theonion.com" . $1;
 
	$article = get($url);
 
	if ($article =~ m/<h2 class="title">(.*?)<\/h2>(.*?)<div id="thumbs">/s) {
		$title = $1;
		$intro = $2;
	}
 
	else {
		die("<item><title>whatdoyouthink.pl - Error grabbing article title and heading!</title></item></channel></rss>\n");
	}
 
	if ($article =~ m/<div id="thumbs">(.*?)<div id="amvo_below">/s) {
		$content = $1;
	}
	else {
		die("<item><title>whatdoyouthink.pl - Error grabbing article text!</title></item></channel></rss>\n");
	}
 
	print	"<item>\n".
		"<title>" . $title . "</title>\n".
		"<link>" . $url . "</link>\n".
		"<category>Humor</category>\n".
		"<description>\n".
		"<![CDATA[" . $intro . $content . "]]>\n".
		"</description>\n".
		"</item>\n\n";
}
 
print	"</channel>\n".
	"</rss>";