从html数据中删除脚本…使用javascript

Question

So I have this function to strip out scripts from the page, but some scripts that are many lines long are still showing up. Is there a way to remove all scripts from the page that loads.

 function filterData(data){

// filter all the nasties out
// no body tags
data = data.replace(/<?\/body[^>]*>/g,'');
// no linebreaks
data = data.replace(/[\r|\n]+/g,'');
// no comments
data = data.replace(/<--[\S\s]*?-->/g,'');
// no noscript blocks
data = data.replace(/<noscript[^>]*>[\S\s]*?<\/noscript>/g,'');
// no script blocks
data = data.replace(/<script[^>]*>[\S\s]*?<\/script>/g,'');
// no self closing scripts
data = data.replace(/<script.*\/>/,'');

// [... add as needed ...]
return data;
  }

Here is an example of the script that comes through in the html

<script type="text/javascript">
var ccKeywords="keyword=";
if (typeof(ccauds) != 'undefined')
{
 for (var cci = 0; cci < ccauds.Profile.Audiences.Audience.length; cci++)
{
  if (cci > 0) ccKeywords += "&keyword="; ccKeywords +=     ccauds.Profile.Audiences.Audience[cci].abbr;
}
}
</script>

Answer 1

If I got you right, you need to remove all <script> tags with inner code from piece of HTML string. In this case you can try the following regular expression:

data.replace(/<script.*?>[\s\S]*?<\/script>/ig, "");

It should successfully work with one-liners and multi-liners, and does not affect other tags.

DEMO: http://jsfiddle.net/9jBSD/

Answer 2

checkout sugar.js - http://sugarjs.com/

it has a removeTags method that should do what you want

http://sugarjs.com/api/String/removeTags

Answer 3

function filterData(data){
    var root = document.createElement("body");
    root.innerHTML = data;

    $(root).find("script,noscript").remove();

    function removeAttrs( node ) {
        $.each( node.attributes, function( index, attr ) {
            if( attr.name.toLowerCase().indexOf("on") === 0 ) {
                node.removeAttribute(attr.name);
            }
        });
    }

    function walk( root ) {
        removeAttrs(root);
        $( root.childNodes ).each( function() {
            if( this.nodeType === 3 ) {
                if( !$.trim( this.nodeValue ).length ) {
                    $(this).remove();
                }
            }
            else if( this.nodeType === 8 ) {
                $(this).remove();
            }
            else if( this.nodeType === 1 ) {
                walk(this);
            }
        });
    }

    walk(root);

    return root.innerHTML; 
}

filterData("<script>alert('hello');</script></noscript></script><div onclick='alert'>hello</div>\n\n<!-- comment -->");
//"<div>hello</div>"