#!/usr/bin/perl

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

use strict;
use warnings;

use vars qw($filename $parser $in_body);

die "usage: $0 <filename>" unless $filename = shift @ARGV;

$parser = HTML::TokeParser::Simple->new( $filename );
$in_body = 0;

while ( my $token = $parser->get_token ) {
  if ($in_body) {
    # we are inside BODY
    if ($token->is_text) {
      # it's text, convert it
      print HTML::Entities::encode_entities($token->as_is);
    } else {
      if ($token->is_end_tag( 'body' )) {
        # we've found the end of the BODY
        $in_body = 0;
      }
      print $token->as_is;
    }
  } else {
    if ($token->is_start_tag( 'body' )) {
      # we've found the beginning of the BODY
      $in_body = 1;
    }
    print $token->as_is;
  }
}