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

my $html = <some file>; #this is shorthand for example..assume the File has been opened in slurp mode

my $parsed = parseHTML($html);

sub parseHTML {
	my $html = shift;
	my $parsed;
	my $p = HTML::TokeParser::Simple->new(\$html);

	while ( my $token = $p->get_token ) {
		# This prints all text in an HTML doc (i.e., it strips the HTML)
		if ($token->is_text) {
			my $text = $token->as_is;
			encode_entities($text, '",' );
			$parsed .= $text;
		} else {
			$parsed .= $token->as_is;
		}
 	}

	return $parsed;
}