#!/usr/bin/perl -w

use strict;
use HTML::TokeParser;

my $dir = "c:/windows/desktop/book/work/";
my $file = $dir."work_introduction.htm";

my $p = HTML::TokeParser->new($file) || die "Can't open $file: $!";

while (my $token = $p->get_tag(qw(h1 h2 h3 h4))) {
  my $open  = $token->[0];
  my $close = '/'.$open;
  my $text  = $p->get_trimmed_text($close);
  print "<$open>$text<$close>\n";
}