シンプルな HTMLPaser / scriptを削る正規表現はjAutoPagerizeから

HTMLStringToDOM.js

function HTMLStringToDOM(str){
	var html = String(str).replace(/<script(?:[ \t\r\n][^>]*)?>[\S\s]*?<\/script[ \t\r\n]*>|<\/?(?:i?frame|html|script|object)(?:[ \t\r\n][^<>]*)?>/gi, ' ');
	var htmlDoc = document.implementation.createHTMLDocument ?
		document.implementation.createHTMLDocument('HTMLParser') :
		document.implementation.createDocument(null, 'html', null);
	var range = document.createRange();
	range.selectNodeContents(document.documentElement);
	htmlDoc.documentElement.appendChild(htmlDoc.importNode(range.createContextualFragment(html),true));
	return htmlDoc;
}