php 过滤html标记属性类(附源码)

php中文网

发布时间：2016-07-25 08:55:20

1121人浏览过

来源于php中文网

原创

/** html attribute filter
* date: 2013-09-22
* author: fdipzone
* ver: 1.0
* edit: bbs.it-home.org
* func:
* public strip 过滤属性
* public setallow 设置允许的属性
* public setexception 设置特例
* public setignore 设置忽略的标记
* private findelements 搜寻需要处理的元素
* private findattributes 搜寻属性
* private removeattributes 移除属性
* private isexception 判断是否特例
* private createattributes 创建属性
* private protect 特殊字符转义
*/
class htmlattributefilter{ // class start
private $_str = ''; // 源字符串
private $_allow = array(); // 允许保留的属性例如:array('id','class','title')
private $_exception = array(); // 特例例如:array('a'=>array('href','class'),'span'=>array('class'))
private $_ignore = array(); // 忽略过滤的标记例如:array('span','img')
/** 处理html,过滤不保留的属性
* @param string $str 源字符串
* @return string
*/
public function strip($str){
$this->_str = $str;
if(is_string($this->_str) && strlen($this->_str)>0){ // 判断字符串
$this->_str = strtolower($this->_str); // 转成小写
$res = $this->findelements();
if(is_string($res)){
return $res;
}
$nodes = $this->findattributes($res);
$this->removeattributes($nodes);
}
return $this->_str;
}
/** 设置允许的属性
* @param array $param
*/
public function setallow($param=array()){
$this->_allow = $param;
}
/** 设置特例
* @param array $param
*/
public function setexception($param=array()){
$this->_exception = $param;
}
/** 设置忽略的标记
* @param array $param
*/
public function setignore($param=array()){
$this->_ignore = $param;
}
/** 搜寻需要处理的元素 */
private function findelements(){
$nodes = array();
preg_match_all("/ ]+)([^>]*)>/i", $this->_str, $elements);
foreach($elements[1] as $el_key => $element){
if($elements[2][$el_key]){
$literal = $elements[0][$el_key];
$element_name = $elements[1][$el_key];
$attributes = $elements[2][$el_key];
if(is_array($this->_ignore) && !in_array($element_name, $this->_ignore)){
$nodes[] = array('literal'=>$literal, 'name'=>$element_name, 'attributes'=>$attributes);
}
}
}
if(!$nodes[0]){
return $this->_str;
}else{
return $nodes;
}
}
/** 搜寻属性
* @param array $nodes 需要处理的元素
*/
private function findattributes($nodes){
foreach($nodes as &$node){
preg_match_all("/([^ =]+)s*=s*["|']{0,1}([^"']*)["|']{0,1}/i", $node['attributes'], $attributes);
if($attributes[1]){
foreach($attributes[1] as $att_key=>$att){
$literal = $attributes[0][$att_key];
$attribute_name = $attributes[1][$att_key];
$value = $attributes[2][$att_key];
$atts[] = array('literal'=>$literal, 'name'=>$attribute_name, 'value'=>$value);
}
}else{
$node['attributes'] = null;
}
$node['attributes'] = $atts;
unset($atts);
}
return $nodes;
}
/** 移除属性
* @param array $nodes 需要处理的元素
*/
private function removeattributes($nodes){
foreach($nodes as $node){
$node_name = $node['name'];
$new_attributes = '';
if(is_array($node['attributes'])){
foreach($node['attributes'] as $attribute){
if((is_array($this->_allow) && in_array($attribute['name'], $this->_allow)) || $this->isexception($node_name, $attribute['name'], $this->_exception)){
$new_attributes = $this->createattributes($new_attributes, $attribute['name'], $attribute['value']);
}
}
}
$replacement = ($new_attributes) ? "" : "";
$this->_str = preg_replace('/'.$this->protect($node['literal']).'/', $replacement, $this->_str);
}
}
/** 判断是否特例
* @param string $element_name 元素名
* @param string $attribute_name 属性名
* @param array $exceptions 允许的特例
* @return boolean
*/
private function isexception($element_name, $attribute_name, $exceptions){
if(array_key_exists($element_name, $this->_exception)){
if(in_array($attribute_name, $this->_exception[$element_name])){
return true;
}
}
return false;
}
/** 创建属性
* @param String $new_attributes
* @param String $name
* @param String $value
* @return String
*/
private function createAttributes($new_attributes, $name, $value){
if($new_attributes){
$new_attributes .= " ";
}
$new_attributes .= "$name="$value"";
return $new_attributes;
}
/** 特殊字符转义
* @param String $str 源字符串
* @return String
*/
private function protect($str){
$conversions = array(
"^" => "^",
"[" => "[",
"." => ".",
"$" => "$",
"{" => "{",
"*" => "*",
"(" => "(",
"\" => "\\",
"/" => "/",
"+" => "+",
")" => ")",
"|" => "|",
"?" => "?",
" "
">" => ">"
);
return strtr($str, $conversions);
}
} // class end
?>

复制代码

2，演示示例

require('HtmlAttributeFilter.class.php');
$str = '
- yuna
  love
  
  Venice
  Venice AI是一个专注于隐私保护的去中心化生成式AI平台，可以生成无审查和无偏见的AI对话和图像
  
  下载
  
  want to knowYES
';
$obj = new HtmlAttributeFilter();
// 允许id属性
$obj->setAllow(array('id'));
$obj->setException(array(
'a' => array('href'), // a 标签允许有 href属性特例
'ul' => array('class') // ul 标签允许有 class属性特例
));
// img 标签忽略,不过滤任何属性
$obj->setIgnore(array('img'));
echo 'source str:
';
echo htmlspecialchars($str).'

';
echo 'filter str:
';
echo htmlspecialchars($obj->strip($str));
?>