use strict;
use warnings;

use HTML::TableExtract;
use Data::Dumper;

my $html = <<'EOHTML';
<table cellspacing="0" cellpadding="2" border="0" width="100%">
    <tr>
      <td width="20%" align="right" valign="top" bgcolor="#CCCCCC">
      <font face="arial, helvetica" size="2"><b>02:44 AM
      EDT</b></font><br>
      <font face="arial, helvetica" size="1">0:42
      (est.)</font><br></td>

      <td valign="top"><font face="arial, helvetica" size=
      "1">Speech</font><br>
      <font face="arial, helvetica" size="2"><a href=
      "/cspan/cspan.csp?command=dprogram&amp;record=142524675">U.S.-Japan
      Relations</a><br>
      Asia Society, Washington Center<br></font> <font face=
      "arial, helvetica" size="2" color="#CC0000">Ryozo Kato</font>
      <font face="arial, helvetica" size="1">, Japan</font></td>
    </tr>
  </table>
EOHTML

my $te = HTML::TableExtract->new();
$te->parse( $html );

my @datatypes = qw( time length type title org );

foreach my $ts ( $te->table_states )
{
    foreach my $row ( $ts->rows )
    {
        my @extracted = map { split( /\n\n/, $_ ) } @$row;
        my %data = map { $datatypes[$_] => clean_whitespace( $extracted[$_] ) } ( 0 .. $#datatypes );
        print Dumper( \%data );
    }
}

sub clean_whitespace
{
	my ( $text ) = @_;
	$text =~ s/^\s+//;
	$text =~ s/\s+$//;
	$text =~ s/\s+/ /g;
	return $text;
}

__OUTPUT__

$VAR1 = {
          'org' => 'Asia Society, Washington Center Ryozo Kato , Japan',
          'title' => 'U.S.-Japan Relations',
          'length' => '0:42 (est.)',
          'type' => 'Speech',
          'time' => '02:44 AM EDT'
        };