码迷,mamicode.com
首页 > Web开发 > 详细

最近采集写的一个超简单实用的HTML解析类

时间:2014-08-30 17:41:09      阅读:311      评论:0      收藏:0      [点我收藏+]

标签:des   android   style   http   color   os   io   ar   for   

1. [文件] HtmlDom.php 
<?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, $index = null)
    {http://www.enterdesk.com/special/shouhui?
        if($this->_nodePath == ‘‘)
            $this->_nodePath = ‘//‘;
        else手绘图片
            $this->_nodePath .= ‘/‘;
  
        $nodes = $this->_xpath->query($this->_nodePath.$query);
        if ($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);
    }
 
}

最近采集写的一个超简单实用的HTML解析类

标签:des   android   style   http   color   os   io   ar   for   

原文地址:http://www.cnblogs.com/xkzy/p/3946588.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!