[分享]分享一个东东,将复制word中内容中的垃圾代码自动去掉
改做.net,好久没回ASP来看看了,分享一个东东给asp的朋友们
功能:将复制word中内容中的垃圾代码自动去掉
代码如下:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML>
<HEAD>
<TITLE> New Document </TITLE>
<META NAME="Generator" CONTENT="EditPlus">
<META NAME="Author" CONTENT="">
<META NAME="Keywords" CONTENT="">
<META NAME="Description" CONTENT="">
</HEAD>
<BODY>
<script>
function GetClipboardHTML()
{
var oDiv = document.getElementById("divTemp")
oDiv.innerHTML = "" ;
var oTextRange = document.body.createTextRange() ;
oTextRange.moveToElementText(oDiv) ;
oTextRange.execCommand("Paste") ;
var sData = oDiv.innerHTML ;
oDiv.innerHTML = "" ;
return sData ;
}
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>" ) ;
//insertHtml( html ) ;
return html;
}
function Paste()
{
Form1.my.value = cleanAndPaste(GetClipboardHTML());
}
</script>
<Form id="Form1" name="Form1">
<input type="button" value="paste" onclick="Paste()">
<br>
<br>
<textarea name="my" cols="60" rows="10"></textarea>
<DIV id=divTemp
style="VISIBILITY: hidden; OVERFLOW: hidden; WIDTH: 1px; POSITION: absolute; HEIGHT: 1px"></DIV>
</Form>
</BODY>
</HTML>