#!/usr/bin/perl -w
use strict;
use XML::RSS;
use DBI;
use HTML::TokeParser;
use LWP::Simple;

my ($DSN) = "DBI:mysql:xparnasse_2:mysql.parnasse.com";
my ($DBUSER) = "xparnasse";
my ($DBPASS) = "damask235";
my (@news);
my ($DB);
my ($qry); 
my ($today);

use POSIX qw(strftime);
    $today = strftime "%a, %e %b %Y %H:%M:%S", gmtime;
    
my $rss = XML::RSS->new( version => '0.91' );
$rss->channel(
	title        => "Classical MP3 Portal Music News",
	link         => "http://parnasse.com/ca/html",
	language		 => "en-us",
	copyright    => "Copyright 2003, Jeffrey Harrington",
	pubDate			 => $today . " GMT",
	lastBuildDate => $today . " GMT",
  managingEditor => "editor\@parnasse.com",
  webMaster     =>	"webmaster\@parnasse.com", 
	category			=> "Classical Music News",
	description  => "News for the classical music community including news about chamber and orchestral music and opera. Classical Music News Provided by The Classical MP3 Portal.");
	

my $url = "http://news.scena.org/WEBNEWS/WEBNEWS.ASP?LAN=2";
my $rawHTML = get($url); # attempt to d/l the page to mem

die "LWP::Simple messed up $!" unless ($rawHTML);

my $tp;
$tp = HTML::TokeParser->new(\$rawHTML) or die "WTF $tp gone bad: $!";

  while (my $token = $tp->get_tag("td")) {
      my $atoken = $tp->get_tag("a");
			my $url = $atoken->[1]{href} || "-";
			$url =~ /lnk=(http.*$)/;
			my $urlString = $1; 
			my $title = $tp->get_trimmed_text("/a");
			#([\w\W\s]*)
			$title =~ /[a-zA-Z0-9\s]*/;
      my $description = $tp->get_trimmed_text("/td");
			$description =~ /^(, )?([\w\W\s]*)/;
			if (defined $title && defined $2 && defined $urlString) {
				if ($title ne "" && $2 ne "" && $urlString ne "") {
					if ("http://" eq substr( $urlString, 0, 7)) {
						print $urlString . "\n";
						$rss->add_item( title => $title, description => $2, link => $urlString);
					}
				}
			}
  }  						 
$rss->save("/big/dom/xparnasse/www/ca/html/classicalmusic.rss");

exit(0);