use strict;

use LWP::Simple;
use HTML::TokeParser;
use HTML::Entities;


my @newspages = qw(
http://osis.nima.mil
http://osis.nima.mil/myhot.html
http://osis.nima.mil/myoffices.html
http://osis.nima.mil/mytraining.html
http://osis.nima.mil/mygeospatial.html
);
for (@newspages) {   
my $html = $_;
my ($junk,$short) = split(/\./,$html); # get domain name
my $body .= "<td valign=top>$short<br>";
my $get = get("$html");
my $p = HTML::TokeParser->new(\$get);
while (my $token = $p->get_tag("a")) {
my $url = $token->[1]{href} || "-";
my $text = $p->get_trimmed_text("/a");
unless ($url =~ /^mailto|^javascript/){  # don't grab javascrpt or mailto's 
$body .= "<a href=\"$url\" target=\"new\">$text</a><br>\n"; }
        
                                    
} $body .= "</td>"
}
my $body .= "</tr></table>";

		
		
		
open(OUT,">news.txt"); # send to an html file
print OUT "$body";