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>
checkout sugar.js – http://sugarjs.com/
it has a removeTags method that should do what you want
http://sugarjs.com/api/String/removeTags