my $p = HTML::Parser->new( api_version => 3,
                         start_h => [\&start, "tagname, attr"],
                         end_h   => [\&end,   "tagname"],
                         text_h   => [\&text,   "dtext"],
                         marked_sections => 1,
                       );


# Parse directly from file
$p->parse_file($inputFile);

##</code><code>##

sub text {
        my($origtext, $is_cdata) = @_;

        if ( $origtext =~ /^\s*$/ ) { return; }
        $origtext = "UNDEF" if !defined $origtext;
        $is_cdata = "UNDEF" if !defined $is_cdata;
        $origtext =~ s/ \& / \&amp; /g;
        $origtext =~ s/½/\&frac12;/g;
        print $origtext;
}