#!/usr/bin/perl -w

use strict;
use LWP::Simple qw(get);
use Data::Dumper qw(Dumper);

#Define the columns to parse out
my @columns = qw(
  headline 
  year month day hour minute second 
  url 
  description
);

#Generate a regex to fetch the column data
my $regex = join '\n', (
  '([^\n]+)',
  '(\d{4})-(\d{2})-(\d{2})\s(\d{2}):(\d{2}):(\d{2})',
  '([^\n]+)',
  '(.*?)\s+', #match everything, except the last bit of whitespace
);

#get the web page
my $text = get('http://www.beoscentral.com/headlines.php');

my @rows;

foreach my $record (split "%%\n", $text) {
  my %row;
  @row{@columns} = ($record =~ /^$regex$/so) or next;
  push @rows, \%row;
}

print Dumper(\@rows);

__END__