PHP通用的XSS攻击过滤函数，Discuz系统中 防止XSS漏洞攻击，过滤HT

[php]代码库

<?php
/**
 * Usage: Run *every* variable passed in through it.
 * The goal of this function is to be a generic function that can be used to
 * parse almost any input and render it XSS safe. For more information on
 * actual XSS attacks, check out http://ha.ckers.org/xss.html. Another
 * excellent site is the XSS Database which details each attack and how it
 * works.
 *
 * Used with permission by the author.
 * URL: http://quickwired.com/smallprojects/php_xss_filter_function.php
 *
 * License:
 * This code is public domain, you are free to do whatever you want with it,
 * including adding it to your own project which can be under any license.
 *
 * $Id: RemoveXSS.php 2663 2007-11-05 09:22:23Z ingmars $
 *
 * @author	Travis Puderbaugh <kallahar@quickwired.com>
 * @package RemoveXSS
 */
class RemoveXSS {
	/**
	 * Wrapper for the RemoveXSS function.
	 * Removes potential XSS code from an input string.
	 *
	 * Using an external class by Travis Puderbaugh <kallahar@quickwired.com>
	 *
	 * @param	string		Input string
	 * @return	string		Input string with potential XSS code removed
	 */
	function RemoveXSS($val)	{
		// remove all non-printable characters. CR(0a) and LF(0b) and TAB(9) are allowed
		// this prevents some character re-spacing such as <java\0script>
		// note that you have to handle splits with \n, \r, and \t later since they *are* allowed in some inputs
		$val = preg_replace('/([\x00-\x08][\x0b-\x0c][\x0e-\x20])/', '', $val);
		// straight replacements, the user should never need these since they're normal characters
		// this prevents like <IMG src="http://www.iamle.com/archives/&#X40&#X61&#X76&#X61&#X73&#X63&#X72&#X69&#X70&#X74&#X3A&#X61&#X6C&#X65&#X72&#X74&#X28&#X27&#X58&#X53&#X53&#X27&#X29>
		$search = "'abcdefghijklmnopqrstuvwxyz';
		$search.= 'ABCDEFGHIJKLMNOPQRSTUVWXYZ';
		$search.= '1234567890!@#$%^&*()';
		$search.= '~`";:?+/={}[]-_|\'\\';
		for ($i = 0; $i < strlen($search); $i++) {
			// ;? matches the ;, which is optional
			// 0{0,7} matches any padded zeros, which are optional and go up to 8 chars
			// &#x0040 @ search for the hex values
			$val = preg_replace('/(&#[x|X]0{0,8}'.dechex(ord($search[$i])).';?)/i', $search[$i], $val); // with a ;
			// &#00064 @ 0{0,7} matches '0' zero to seven times
			$val = preg_replace('/(&#0{0,8}'.ord($search[$i]).';?)/', $search[$i], $val); // with a ;
		}
		// now the only remaining whitespace attacks are \t, \n, and \r
		$ra1 = array('javascript', 'vbscript', 'expression', 'applet', 'meta', 'xml', 'blink', 'link', 'style', 'script', 'embed', 'object', 'iframe', 'frame', 'frameset', 'ilayer', 'layer', 'bgsound', 'title', 'base');
		$ra2 = array('onabort', 'onactivate', 'onafterprint', 'onafterupdate', 'onbeforeactivate', 'onbeforecopy', 'onbeforecut', 'onbeforedeactivate', 'onbeforeeditfocus', 'onbeforepaste', 'onbeforeprint', 'onbeforeunload', 'onbeforeupdate', 'onblur', 'onbounce', 'oncellchange', 'onchange', 'onclick', 'oncontextmenu', 'oncontrolselect', 'oncopy', 'oncut', 'ondataavailable', 'ondatasetchanged', 'ondatasetcomplete', 'ondblclick', 'ondeactivate', 'ondrag', 'ondragend', 'ondragenter', 'ondragleave', 'ondragover', 'ondragstart', 'ondrop', 'onerror', 'onerrorupdate', 'onfilterchange', 'onfinish', 'onfocus', 'onfocusin', 'onfocusout', 'onhelp', 'onkeydown', 'onkeypress', 'onkeyup', 'onlayoutcomplete', 'onload', 'onlosecapture', 'onmousedown', 'onmouseenter', 'onmouseleave', 'onmousemove', 'onmouseout', 'onmouseover', 'onmouseup', 'onmousewheel', 'onmove', 'onmoveend', 'onmovestart', 'onpaste', 'onpropertychange', 'onreadystatechange', 'onreset', 'onresize', 'onresizeend', 'onresizestart', 'onrowenter', 'onrowexit', 'onrowsdelete', 'onrowsinserted', 'onscroll', 'onselect', 'onselectionchange', 'onselectstart', 'onstart', 'onstop', 'onsubmit', 'onunload');
		$ra = array_merge($ra1, $ra2);
		$found = true; // keep replacing as long as the previous round replaced something
		while ($found == true) {
			$val_before = $val;
			for ($i = 0; $i < sizeof($ra); $i++) {
				$pattern = '/';
				for ($j = 0; $j < strlen($ra[$i]); $j++) {
					if ($j > 0) {
						$pattern .= '(';
						$pattern .= '(&#[x|X]0{0,8}([9][a][b]);?)?';
						$pattern .= '|(&#0{0,8}([9][10][13]);?)?';
						$pattern .= ')?';
					}
					$pattern .= $ra[$i][$j];
				}
				$pattern .= '/i';
				$replacement = substr($ra[$i], 0, 2).'<x>'.substr($ra[$i], 2); // add in <> to nerf the tag
				$val = preg_replace($pattern, $replacement, $val); // filter out the hex tags
				if ($val_before == $val) {
					// no replacements were made, so exit the loop
					$found = false;
				}
			}
		}
		return $val;
	}
}
?>