Clean UTF8 WordPress HTML string for XML use.

clean-html-for-xml.php

/**
 * Clean utf8 HTML string for XML.
 *
 *
 * @param  string $string HTML string you want to make XML safe.
 */
function clean_html_for_xml( $string ) {
	$string = strip_tags( $string );
	$string = htmlspecialchars( $string );
	$string = strip_shortcodes( $string );

	// http://stackoverflow.com/questions/12229572/php-generated-xml-shows-invalid-char-value-27-message
	return preg_replace ( '/[^\x{0009}\x{000a}\x{000d}\x{0020}-\x{D7FF}\x{E000}-\x{FFFD}]+/u', ' ', $string );
}