#!/usr/bin/perl -w

use strict;
use LWP::UserAgent;
use XML::RSS;
use HTML::Entities;

my $ie="Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)";

my $ua = LWP::UserAgent->new;
$ua->agent($ie);
my $url = "http://groups.google.com/groups?safe=images&as_uauthors=Terry%20Pratchett&lr=lang_en&hl=en";
my $response = $ua->get ($url);
my $content;

my $rss = new XML::RSS (version => '1.0');

$rss->channel(title       => 'Terry Pratchett on Usenet',
	      link        => $url,
	      description => 'Terry Pratchett\'s Usenet posts, courtesy of Google Groups');

if ($response->is_success) 
{
	my @chunks = (split ("</?div>", $response->content));
	foreach (split "</font></font>", $chunks[1])
	{
		if (/<p><a\shref="?
			(\/groups[^">]*)   # Link
			"?>
			([^<]*)            # Title
			<\/a><font\ssize="?[^>"]*"?>
			(.*)               # Quote
			<b>...<\/b>\s*
			<br><font\scolor="?green"?><a\shref="?
			([^">\s]*)         # Group link
			"?\sclass="?a"?>
			([^<]*)            # Group name
			<\/a>
			([^<]*)            # Date & author
			<a\shref="?
			(\/groups[^">\s]*) # Thread link
			"?\sclass="?a"?>
			(View\sThread\s\([^\s]*\sarticles?\)) # Thread title
			/six)
		{
			$content = $3;
			$content .= "<br><br>";
			$content .= "<a href='http://groups.google.com$4'>";
			$content .= "$5</a>$6";
			$content .= "<a href='http://groups.google.com$7'>";
			$content .= "$8</a>";
#			print $content;
			$rss->add_item(title       => $2,
				       link        => "http://groups.google.com$1",
				       description => encode_entities($content));
		}
	}
	print $rss->as_string;	
}
else 
{
	die $response->status_line;
}