文本处理去除html标签,删除html标签得到纯文本可处理嵌套的标签

方法基本上来自THinkphp中的源码，但是被我修改了一下

/*

*@Description:删除HTML标签，得到纯文本。可以处理嵌套的标签

*

*/

class deleteHtmlTags{

private $filename;

function __construct($filename='C:/AppServ/www/text.txt'){

$this->filename = $filename;

}

/**

* 删除html标签，得到纯文本。可以处理嵌套的标签,局限性在于连标签内的属性值都会删除掉

* @access public

* @param string $string 要处理的html

* @return string

*/

public function deletehtmltags(){

$content = $this->contentGet();

while(strstr($content, '>')){

$currentBegin = strpos($content, '

$currentEnd = strpos($content, '>');

$cha = $currentEnd - $currentBegin - 1;

$tmpStringBegin = @substr($content, 0, $currentBegin);

// $tmpStringMiddle = @ substr($content, $currentBegin + 1, $cha);

$tmpStringEnd = @substr($content, $currentEnd + 1, strlen($content));

// $content = $tmpStringBegin.$tmpStringMiddle.$tmpStringEnd;

$content = $tmpStringBegin.$tmpStringEnd;

}

return $content;

}

private function contentGet(){

$fd = fopen($this->filename, 'r');

$content = fread($fd, filesize($this->filename));

fclose($fd);

return $content;

}

}

$deleteHtml = new deleteHtmlTags();

$content = $deleteHtml->deletehtmltags();

echo $content;

?>

修改部分也在上面，只是注释掉了。个人觉得这个方法比用正则这类的方法更好。