strip_tags延伸函数-处理html（采集用的上）

strip_tags延伸函数-处理html（采集用的上）

/** 
 * This function turns HTML into text  * 将html转化为txt   
*/ 
function html2txt($document) {     
$search = array (&#39;@<script[^>]*?>.*?</script>@si&#39;, 
// Strip out javascript                     
&#39;@<style[^>]*?>.*?</style>@siU&#39;, 
// Strip style tags properly                     
&#39;@<[\/\!]*?[^<>]*?>@si&#39;, // Strip out HTML tags                     
&#39;@<![\s\S]*?--[ \t\n\r]*>@&#39; )// Strip multi-line comments including CDATA     ;     
$text = preg_replace ( $search, &#39;&#39;, $document );     
return $text; }  
/**  
* removes the HTML tags along with their contents  
* 移除/过滤html标签并且移除标签内的内容  
* 注:$tags为需要保留的标签  invert为true时结果相反  
*/ 
function strip_tags_content($text, $tags = &#39;&#39;, $invert = FALSE) {    
 preg_match_all ( &#39;/<(.+?)[\s]*\/?[\s]*>/si&#39;, trim ( $tags ), $tags );     
 $tags = array_unique ( $tags [1] );           
 if (is_array ( $tags ) and count ( $tags ) > 0) {         
 if ($invert == FALSE) {             
 return preg_replace ( &#39;@<(?!(?:&#39; . implode ( &#39;|&#39;, $tags ) . &#39;)\b)(\w+)\b.*?>.*?</\1>@si&#39;, &#39;&#39;, $text );       
   } else {             
   return preg_replace ( &#39;@<(&#39; . implode ( &#39;|&#39;, $tags ) . &#39;)\b.*?>.*?</\1>@si&#39;, &#39;&#39;, $text );         }    
    } elseif ($invert == FALSE) {        
     return preg_replace ( &#39;@<(\w+)\b.*?>.*?</\1>@si&#39;, &#39;&#39;, $text );    
      }     
     return $text; 
     }

 以上就是strip_tags延伸函数-处理html（采集用的上）的内容，更多相关内容请关注PHP中文网（www.php.cn）！