php中xss过滤的方法
墨初 编程开发 880阅读
XSS也被叫做跨站脚本攻击，指的是将一些特殊或敏感的代码提交给网站，一定代码提交成功就可以利用这些恶意代码爬取网站的漏洞，从而对网站进行信息的盗取与破环。为了保证网站的安全性，在用户向网站提交任何信息时，都需要过滤掉一些敏感或恶意代码。下面73so博客就提供两个php脚本过滤XSS的示例。
php过滤xss的方法
方法1：
/**
* @name 过滤XSS的函数
* @param string $val 需要被过滤的数据
*
* @return string 过滤后的数据
* @host https://www.73so.com
*/
function remove_xss($val)
{
$val = preg_replace('/([\x00-\x08,\x0b-\x0c,\x0e-\x19])/', '', $val);
$search = 'abcdefghijklmnopqrstuvwxyz';
$search .= 'ABCDEFGHIJKLMNOPQRSTUVWXYZ';
$search .= '1234567890!@#$%^&*()';
$search .= '~`";:?+/={}[]-_|\'\\';
for ($i = 0; $i < strlen($search); $i++) {
$val = preg_replace('/(&#[xX]0{0,8}'.dechex(ord($search[$i])).';?)/i', $search[$i], $val);
$val = preg_replace('/(�{0,8}'.ord($search[$i]).';?)/', $search[$i], $val);
}
$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);
$found = true;
while ($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 .= '(&#[xX]0{0,8}([9ab]);)';
$pattern .= '|';
$pattern .= '|(�{0,8}([9|10|13]);)';
$pattern .= ')*';
}
$pattern .= $ra[$i][$j];
}
$pattern .= '/i';
$replacement = substr($ra[$i], 0, 2).'<x>'.substr($ra[$i], 2);
$val = preg_replace($pattern, $replacement, $val);
if ($val_before == $val) {
$found = false;
}
}
}
return $val;
}
// 调用函数
echo remove_xss('73so.com');方法2：
以下代码来自zblogphp博客程序，其github地址：http://phith0n.github.io/XssHtml/
class XssHtml
{
private $m_dom;
private $m_xss;
private $m_ok;
private $m_AllowAttr = array('title', 'src', 'href', 'id', 'class', 'style', 'width', 'height', 'alt', 'target', 'align');
private $m_AllowTag = array('a', 'img', 'br', 'strong', 'b', 'code', 'pre', 'p', 'div', 'em', 'span', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'table', 'ul', 'ol', 'tr', 'th', 'td', 'hr', 'li', 'u');
/**
* 构造函数.
*
* @param string $html 待过滤的文本
* @param string $charset 文本编码，默认utf-8
* @param array $AllowTag 允许的标签，如果不清楚请保持默认，默认已涵盖大部分功能，不要增加危险标签
*/
public function __construct($html, $charset = 'utf-8', $AllowTag = array())
{
$this->m_AllowTag = empty($AllowTag) ? $this->m_AllowTag : $AllowTag;
$this->m_xss = strip_tags($html, '<' . implode('><', $this->m_AllowTag) . '>');
if (empty($this->m_xss)) {
$this->m_ok = false;
return;
}
$this->m_xss = "<meta http-equiv=\"Content-Type\" content=\"text/html;charset={$charset}\"><nouse>" . $this->m_xss . '</nouse>';
$this->m_dom = new DOMDocument('1.0', 'utf-8');
$this->m_dom->strictErrorChecking = false;
$this->m_ok = @$this->m_dom->loadHTML($this->m_xss);
}
/**
* 获得过滤后的内容.
*/
public function getHtml()
{
if (!$this->m_ok) {
return '';
}
$nodeList = $this->m_dom->getElementsByTagName('*');
for ($i = 0; $i < $nodeList->length; $i++) {
$node = $nodeList->item($i);
if (in_array($node->nodeName, $this->m_AllowTag)) {
if (method_exists($this, "__node_{$node->nodeName}")) {
call_user_func(array($this, "__node_{$node->nodeName}"), $node);
} else {
call_user_func(array($this, '__node_default'), $node);
}
}
}
$html = strip_tags($this->m_dom->saveHTML(), '<' . implode('><', $this->m_AllowTag) . '>');
$html = preg_replace('/^\n(.*)\n$/s', '$1', $html);
return $html;
}
private function __true_url($url)
{
if (preg_match('#^https?://.+#is', $url)) {
return $url;
} else {
return 'http://' . $url;
}
}
private function __get_style($node)
{
if ($node->attributes->getNamedItem('style')) {
$style = $node->attributes->getNamedItem('style')->nodeValue;
$style = str_replace('\\', ' ', $style);
$style = str_replace(array('&#', '/*', '*/'), ' ', $style);
$style = preg_replace('#e.*x.*p.*r.*e.*s.*s.*i.*o.*n#Uis', ' ', $style);
return $style;
} else {
return '';
}
}
private function __get_link($node, $att)
{
$link = $node->attributes->getNamedItem($att);
if ($link) {
return $this->__true_url($link->nodeValue);
} else {
return '';
}
}
private function __setAttr($dom, $attr, $val)
{
if (!empty($val)) {
$dom->setAttribute($attr, $val);
}
}
private function __set_default_attr($node, $attr, $default = '')
{
$o = $node->attributes->getNamedItem($attr);
if ($o) {
$this->__setAttr($node, $attr, $o->nodeValue);
} else {
$this->__setAttr($node, $attr, $default);
}
}
private function __common_attr($node)
{
$list = array();
foreach ($node->attributes as $attr) {
if (!in_array(
$attr->nodeName,
$this->m_AllowAttr
)
) {
$list[] = $attr->nodeName;
}
}
foreach ($list as $attr) {
$node->removeAttribute($attr);
}
$style = $this->__get_style($node);
$this->__setAttr($node, 'style', $style);
$this->__set_default_attr($node, 'title');
$this->__set_default_attr($node, 'id');
$this->__set_default_attr($node, 'class');
}
private function __node_img($node)
{
$this->__common_attr($node);
$this->__set_default_attr($node, 'src');
$this->__set_default_attr($node, 'width');
$this->__set_default_attr($node, 'height');
$this->__set_default_attr($node, 'alt');
$this->__set_default_attr($node, 'align');
}
private function __node_a($node)
{
$this->__common_attr($node);
$href = $this->__get_link($node, 'href');
$this->__setAttr($node, 'href', $href);
$this->__set_default_attr($node, 'target', '_blank');
}
private function __node_embed($node)
{
$this->__common_attr($node);
$link = $this->__get_link($node, 'src');
$this->__setAttr($node, 'src', $link);
$this->__setAttr($node, 'allowscriptaccess', 'never');
$this->__set_default_attr($node, 'width');
$this->__set_default_attr($node, 'height');
}
private function __node_default($node)
{
$this->__common_attr($node);
}
}
// 类的调用方法
$html = '73so.com';
$xss = new XssHtml($html);
echo $xss->getHtml();