PHP实现网页内容html标签补全和过滤的方法小结【2种方法】

function closetags($html) {
 preg_match_all('#<(?!meta|img|br|hr|input\b)\b([a-z]+)(?: .*)?(?<![/|/ ])>#iU', $html, $result);
 $openedtags = $result[1];
 preg_match_all('#</([a-z]+)>#iU', $html, $result);
 $closedtags = $result[1];
 $len_opened = count($openedtags);
 if (count($closedtags) == $len_opened) {
    return $html;
 }
 $openedtags = array_reverse($openedtags);
 for ($i=0; $i < $len_opened; $i++) {
    if (!in_array($openedtags[$i], $closedtags)) {
     $html .= '</'.$openedtags[$i].'>';
    }else {
     unset($closedtags[array_search($openedtags[$i], $closedtags)]);
    }
 }
 return $html;
}

function checkhtml($html) {
  $html = stripslashes($html);
    preg_match_all("/\<([^\<]+)\>/is", $html, $ms);
    $searchs[] = '<';
    $replaces[] = '<';
    $searchs[] = '>';
    $replaces[] = '>';
    if($ms[1]) {
      $allowtags = 'img|font|div|table|tbody|tr|td|th|br|p|b|strong|i|u|em|span|ol|ul|li';//允许的标签
      $ms[1] = array_unique($ms[1]);
      foreach ($ms[1] as $value) {
        $searchs[] = "<".$value.">";
        $value = shtmlspecialchars($value);
        $value = str_replace(array('\\','/*'), array('.','/.'), $value);
        $value = preg_replace(array("/(javascript|script|eval|behaviour|expression)/i", "/(\s+|"|')on/i"), array('.', ' .'), $value);
        if(!preg_match("/^[\/|\s]?($allowtags)(\s+|$)/is", $value)) {
          $value = '';
        }
        $replaces[] = empty($value)?'':"<".str_replace('"', '"', $value).">";
      }
    }
    $html = str_replace($searchs, $replaces, $html);
  return $html;
}
//取消HTML代码
function shtmlspecialchars($string) {
  if(is_array($string)) {
    foreach($string as $key => $val) {
      $string[$key] = shtmlspecialchars($val);
    }
  } else {
    $string = preg_replace('/&((#(\d{3,5}|x[a-fA-F0-9]{4})|[a-zA-Z][a-z0-9]{2,5});)/', '&\\1',
      str_replace(array('&', '"', '<', '>'), array('&', '"', '<', '>'), $string));
  }
  return $string;
}