一般处理的方式有二种:1.通过编辑器的JS直接去除。2.提交到后台后,直接用程序去掉无效标签。下面我就分享一个通过PHP的处理方式,成功率可能不是100%。这程序也是在PHP官网上看到的,就顺便粘贴过来了。
[U]复制代码[/U] 代码如下:
function ClearHtml($content,$allowtags='') {
mb_regex_encoding('UTF-8');
//replace MS special characters first
$search = array('/‘/u', '/’/u', '/“/u', '/”/u', '/—/u');
$replace = array('\'', '\'', '"', '"', '-');
$content = preg_replace($search, $replace, $content);
//make sure _all_ html entities are converted to the plain ascii equivalents - it appears
//in some MS headers, some html entities are encoded and some aren't
$content = html_entity_decode($content, ENT_QUOTES, 'UTF-8');
//try to strip out any C style comments first, since these, embedded in html comments, seem to
//prevent strip_tags from removing html comments (MS Word introduced combination)
if(mb_stripos($content, '/*') !== FALSE){
$content = mb_eregi_replace('#/\*.*?\*/#s', '', $content, 'm');
}
//introduce a space into any arithmetic expressions that could be caught by strip_tags so that they won't be
//']*>(.*?)#isu', '#]*>(.*?)#isu', '#]*>(.*?)#isu');
$replace = array('$2', '$2', '$1');
$content = preg_replace($search, $replace, $content);
//on some of the ?newer MS Word exports, where you get conditionals of the form 'if gte mso 9', etc., it appears
//that whatever is in one of the html comments prevents strip_tags from eradicating the html comment that contains
//some MS Style Definitions - this last bit gets rid of any leftover comments */
$num_matches = preg_match_all("/\/isu', '', $content);
}
return $content;
}