php实现的一个很好用HTML解析器类可用于采集数据

下面就是这个 HTML解析类及用法，下面的功能是采集www.opendir.cn这个网站的百度收录数据，需要的朋友可以测试下

<?php   
 $oldSetting = libxml_use_internal_errors( true );    
libxml_clear_errors();   
/** 
 *  
 * -+----------------------------------- 
 * |PHP5 Framework - 2011 
 * |Web Site: www.iblue.cc 
 * |E-mail: [email protected] 
 * |Date: 2012-10-12 
 * -+----------------------------------- 
 *  
 * @desc HTML解析器 
 * @author jingke 
 */    
class XF_HtmlDom   
{   
    private $_xpath = null;   
    private $_nodePath = '';   

    public function __construct($xpath = null, $nodePath = '')   
    {   
        $this->_xpath = $xpath;   
        $this->_nodePath = $nodePath;   
    }   

    public function loadHtml($url)   
    {   
        ini_set('user_agent', 'Mozilla/5.0 (Linux; U; Android 2.1; en-us; Nexus One Build/ERD62) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17 CNexus');   
        $content = '';   
        if(strpos(strtolower($url), 'http')===false)   
        {   
            $content = file_get_contents($url);   
        }   
        else  
        {   
            $ch = curl_init();    
            $user_agent = "Baiduspider+(+http://www.baidu.com/search/spider.htm)";   
            $user_agent1='Mozilla/5.0 (Windows NT 5.1; rv:6.0) Gecko/20100101 Firefox/6.0';   
            curl_setopt($ch, CURLOPT_URL, $url);    
            curl_setopt($ch, CURLOPT_HEADER, false);    
            curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);    
            curl_setopt($ch, CURLOPT_REFERER, $url);   
            curl_setopt($ch, CURLOPT_USERAGENT, $user_agent1);   
            curl_setopt($ch, CURLOPT_FOLLOWLOCATION,1);   
            $content =curl_exec($ch);    
            curl_close($ch);   
        }   

        $html = new DOMDocument();    
        $html->loadHtml($content);    
        $this->_xpath = new DOMXPath( $html );    
        //return $this;  

    }   

    public function find($query, $index = null)   
    {   
        if($this->_nodePath == '')   
            $this->_nodePath = '//';  
        else  
            $this->_nodePath .= '/';   

        $nodes = $this->_xpath->query($this->_nodePath.$query);   
        //echo $nodes->item(0)->getNodePath();exit;  

           
        if ($index == null && !is_numeric($index))    
        {    
            $tmp = array();   
            foreach ($nodes as $node)    
            {   
                $tmp[] = new XF_HtmlDom($this->_xpath, $node->getNodePath());   
            }   
            return $tmp;   
        }   
        return new XF_HtmlDom($this->_xpath,$this->_xpath->query($this->_nodePath.$query)->item($index)->getNodePath());   
    }   

    /** 
     * 获取内容 
     */  
    public function text()   
    {   
        if ($this->_nodePath != '' && $this->_xpath != null )    
            return $this->_xpath->query($this->_nodePath)->item(0)->textContent;   
        else  
            return false;   
    }   

    /** 
     * 获取属性值 
     */  
    public function getAttribute($name)   
    {   
        if ($this->_nodePath != '' && $this->_xpath != null )    
            return $this->_xpath->query($this->_nodePath)->item(0)->getAttribute($name);   
        else  
            return false;   
    }   

    public function __get($name)   
    {   
        if($name == 'innertext')   
            return $this->text();   
        else  
            return $this->getAttribute($name);   
    }     
}     
$xp = new xf_HtmlDom();   
$xp->loadHtml('http://www.aizhan.com/siteall/www.opendir.cn/');  
$rows = $xp->find("td[@id='baidu']/a", 0)->innertext;   
print_r($rows);