应用curl扩展抓取网页

    <?php  
    namespace Think;  
    header("Content-Type: text/html;charset=utf-8");  
    class Mycurl  
    {  
        public $ch = null;  
        public $data = null;  
      
        public function __construct($url)  
        {  
            $this->ch = curl_init($url);  
            curl_setopt($this->ch, CURLOPT_HEADER, false);   //不返回头部信息  
            //将 curl_exec()获取的信息以文件流的形式返回，而不是直接输出。  
            curl_setopt($this->ch, CURLOPT_RETURNTRANSFER, true);   
            $this->data = curl_exec($this->ch);    
        }  
        public function __destruct()  //释放资源   
        {    
            curl_close($this->ch);  
        }  
      
        public function regmatch()   //正则方式抓取  
        {  
            $reg = '/(?<=<title>)(.*)(?=<\/title>)/i';  //抓取标题  
            $reg = '/<div\sid="article_content"\sclass="article_content">([^(?<\/div>)]*)<\/div>/si'; //抓取文章内容  
            preg_match($reg,$this->data,$out);     
            return $out[1];  
        }   
        public function result($pos1,$pos2)   //字符串方式抓取  
        {  
            $len = strlen($pos1);  
            $flag1 = stripos($this->data, $pos1);  
            $flag2 = stripos($this->data, $pos2);  
            $str = substr($this->data,$flag1,$flag2-$flag1);  
            return $str;  
        }  
        public function exec()   //获取抓取数据  
        {  
            $data = Array();  
            $data['title'] = self::result('<title>','-卢松松博客</title>');  
            $data['title'] = substr($data['title'],7);  //参数7偏移是为了过滤上一步字符串抓取结果中的前面<title>  
            $data['content'] = self::result('<dd class="post-info">','<center>');  
            $data['content'] = str_ireplace("/upload/","http://lusongsong.com/upload/",$data['content']);  //这一步解决抓取文章的图片地址错误  
            $data['content'] = str_ireplace("http://lusongsong.comhttp://lusongsong.com","http://lusongsong.com",$data['content']); //解决上一步产生的副作用，   
            $data['content'] = str_ireplace("bloghttp://lusongsong.com","blog",$data['content']);  //继续解决上两步产生的副作用  
            $data['atime'] = time();  
            $data['author'] = 'Internet';  
            $data['sort'] = '精彩博文';  
            // $data['oldlink'] = '';  
            $data['summary'] = substr(strip_tags($data['content']),0,180);  //截取文章摘要  
            return $data;  
        }  
      
    }  
      
    // 测试  
    $url = 'http://lusongsong.com/reed/';  
    $num = 100;   //住区文章数目  
    $start = 350；  //抓取起点  
      
    $Art = M('article');  
      
    for($i=$start; $i < $start+$num ; $i++)  
    {   
      
        $posurl = $url.$i.'.html';  
        $curl = new Mycurl($posurl);  
        $data = $curl->exec();  
        $data['oldlink'] = $posurl;  
        if($pos = strpos($data['title'], "出现404错误页面了"))  
        {  
            continue;  
        }  
        $Art->add($data);  
        $curl = null;  
    }  
    $this->success("执行完成!","index");  
      
      
      
    ?>  

标签：

版权申明：本站文章部分自网络，如有侵权，请联系：west999com@outlook.com
特别注意：本站所有转载文章言论不代表本站观点！
本站所提供的图片等素材，版权归原作者所有，如需使用，请与原作者联系。