欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  IT编程

php实现的一个很好用HTML解析器类可用于采集数据

程序员文章站 2022-11-14 19:18:56
复制代码 代码如下:
复制代码 代码如下:

<?php  
 $oldsetting = libxml_use_internal_errors( true );   
libxml_clear_errors();  
/**
 * 
 * -+-----------------------------------
 * |php5 framework - 2011
 * |web site: www.iblue.cc
 * |e-mail: mejinke@gmail.com
 * |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 –nexus');  
        $content = '';  
        if(strpos(strtolower($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);