去除word格式的页面

文章录入界面自己写的文字可以录进，从word拷过来的文字录不进去，疑为word自带格式问题，好像要用正则表达式去除，我才初学.net自己没有办法写出来，望大家帮忙

// 清除WORD冗余格式并粘贴
function cleanAndPaste( html ) {
// Remove all SPAN tags
html = html.replace(/<\/?SPAN[^>]*>/gi, "" );
// Remove Class attributes
html = html.replace(/<(\w[^>]*) class=([^ |>]*)([^>]*)/gi, "<$1$3") ;
// Remove Style attributes
html = html.replace(/<(\w[^>]*) style="([^"]*)"([^>]*)/gi, "<$1$3") ;
// Remove Lang attributes
html = html.replace(/<(\w[^>]*) lang=([^ |>]*)([^>]*)/gi, "<$1$3") ;
// Remove XML elements and declarations
html = html.replace(/<\\?\?xml[^>]*>/gi, "") ;
// Remove Tags with XML namespace declarations: <o:p></o:p>
html = html.replace(/<\/?\w+:[^>]*>/gi, "") ;
// Replace the  
html = html.replace(/ /, " " );
// Transform <P> to <DIV>
var re = new RegExp("(<P)([^>]*>.*?)(<\/P>)","gi") ; // Different because of a IE 5.0 error
html = html.replace( re, "<div$2</div>" ) ;

alert( html ) ;
}