对网站发动XSS攻击的方式有很多种,仅仅使用php的一些内置过滤函数是对付不了的,即使你将filter_var,mysql_real_escape_string,htmlentities,htmlspecialchars,strip_tags这些函数都使用上了也不一定能保证绝对的安全。
现在有很多php开发框架都提供关于防XSS攻击的过滤方法,下面和大家分享一个预防XSS攻击和ajax跨域攻击的函数,摘自某开发框架,相比于仅仅使用内置函数应该还是够强了的吧。
function xss_clean($data){ // Fix &entity\n; $data=str_replace(array('&','<','>'),array('&amp;','&lt;','&gt;'),$data); $data=preg_replace('/(&#*\w+)[\x00-\x20]+;/u','$1;',$data); $data=preg_replace('/(&#x*[0-9A-F]+);*/iu','$1;',$data); $data=html_entity_decode($data,ENT_COMPAT,'UTF-8'); // Remove any attribute starting with "on" or xmlns $data=preg_replace('#(<[^>]+?[\x00-\x20"\'])(?:on|xmlns)[^>]*+>#iu','$1>',$data); // Remove javascript: and vbscript: protocols $data=preg_replace('#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([`\'"]*)[\x00-\x20]*j[\x00-\x20]*a[\x00-\x20]*v[\x00-\x20]*a[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iu','$1=$2nojavascript...',$data); $data=preg_replace('#([a-z]*)[\x00-\x20]*=([\'"]*)[\x00-\x20]*v[\x00-\x20]*b[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iu','$1=$2novbscript...',$data); $data=preg_replace('#([a-z]*)[\x00-\x20]*=([\'"]*)[\x00-\x20]*-moz-binding[\x00-\x20]*:#u','$1=$2nomozbinding...',$data); // Only works in IE: <span style="width: expression(alert('Ping!'));"></span> $data=preg_replace('#(<[^>]+?)style[\x00-\x20]*=[\x00-\x20]*[`\'"]*.*?expression[\x00-\x20]*\([^>]*+>#i','$1>',$data); $data=preg_replace('#(<[^>]+?)style[\x00-\x20]*=[\x00-\x20]*[`\'"]*.*?behaviour[\x00-\x20]*\([^>]*+>#i','$1>',$data); $data=preg_replace('#(<[^>]+?)style[\x00-\x20]*=[\x00-\x20]*[`\'"]*.*?s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:*[^>]*+>#iu','$1>',$data); // Remove namespaced elements (we do not need them) $data=preg_replace('#</*\w+:\w[^>]*+>#i','',$data); // http://php.hhsy.cc/ do{// Remove really unwanted tags $old_data=$data; $data=preg_replace('#</*(?:applet|b(?:ase|gsound|link)|embed|frame(?:set)?|i(?:frame|layer)|l(?:ayer|ink)|meta|object|s(?:cript|tyle)|title|xml)[^>]*+>#i','',$data); }while($old_data!==$data); // we are done... return $data; }