use HTML::TokeParser::Simple;
my $parser = HTML::TokeParser::Simple->new(\$html);

my $new_html = '';
while (my $token = $parser->get_token) {
    my $text = $token->as_is;
    $new_html .= $token->is_text ? munge_text($text) : $text;
}
print $new_html;

sub munge_text {
    # put your text munging stuff here
}