thinkphp5 + beanbun은 영화 URL과 사진의 간단한 크롤링을 실현합니다.

CREATE TABLE `think_dy2018` ( 
 `id` int(7) unsigned NOT NULL AUTO_INCREMENT COMMENT '主键id',  
 `movieName` varchar(255) NOT NULL COMMENT '电影名',  
 `movieUrl` varchar(520) NOT NULL COMMENT '电影详情页地址',  
 `addTime` int(11) NOT NULL COMMENT '添加时间',  PRIMARY KEY (`id`)
) ENGINE=InnoDB AUTO_INCREMENT=8808 DEFAULT CHARSET=utf8 COMMENT='dywz信息采集'

CREATE TABLE `think_dy2018imgs` ( 
 `id` int(8) unsigned NOT NULL AUTO_INCREMENT COMMENT '图片id',  
 `urlID` int(7) NOT NULL COMMENT '关联的电影ID',  
 `imgUrl` varchar(520) DEFAULT NULL COMMENT '图片地址',  
 `create_time` int(10) NOT NULL COMMENT '图片添加时间',  PRIMARY KEY (`id`),  
 KEY `urlID` (`urlID`)
 ) ENGINE=InnoDB AUTO_INCREMENT=1279 DEFAULT CHARSET=utf8 COMMENT='图片地址'

<?php
/* 
+------------------------------------------------------------------------------------------- 
+ Title        : 爬虫控制器 
+ Version      : V1.0.0.2 
+ Initial-Time : 2018/3/27 + sgw 
+ Last-time    : 2018/3/27 + sgw + Desc         : 爬取网站电影信息 
+-------------------------------------------------------------------------------------------
*/
namespace app\index\controller;
use \Beanbun\Beanbun;
use Beanbun\Lib\Helper;
use \GuzzleHttp\Client;
use \think\Controller;
use \think\Db;

class Robot extends Controller{  
  /**     
  * 抓取 一级页面信息     
  */    
  public function getList(){   
       $beanbun = new Beanbun;        
       $urlList = [&#39;http://www.ygdy8.net/html/gndy/dyzz/index.html&#39;];        
       for($i=2;$i<=173;$i++ ){      
             $urlList[] = &#39;http://www.ygdy8.net/html/gndy/dyzz/list_23_&#39;.$i.&#39;.html&#39;;        
       }     
       
  $beanbun->seed = $urlList;        
  $beanbun->afterDownloadPage = function($beanbun) {           
     if (strlen($beanbun->page) < 100) {       
              $beanbun->error();           
        }       
       
       # 对抓取内容转码            
       $contents = mb_convert_encoding($beanbun->page,&#39;utf8&#39; ,&#39;gb2312&#39;);            
       file_put_contents(&#39;66.html&#39;, $contents);            
       $patter = &#39;/<td height="26">\s*<b>\s*<a href="(.+)".*>(.*)<\/a>\s*<\/b>/sU&#39;;            
       preg_match_all($patter, $contents, $m);            
       
       # 对抓取的数据分析插入数据库            
       if($m[0]){               
           $hrefs  = $m[1];                
           $titles = $m[2];                
           
           foreach ($hrefs as $key => $href){               
               $url =  Helper::formatUrl($href, $beanbun->url);                   
               $data[] = [                   
                    &#39;movieName&#39; => strip_tags($titles[$key]),                        
                    &#39;movieUrl&#39;  => $url,                        
                    &#39;addTime&#39;   => time()                    
               ];               
          }               
             
              Db::name(&#39;dy2018&#39;)->insertAll($data);           
        }        
    };       
             # 抓取页面之后回调        
             $beanbun->start();    
       }    
       
       /**     
          * 抓取 改url下面相信信息的imges      
          * 查询数据表中id，movieUrl。然后根据movieUrl爷们内容爬取图片（注意这里图片可能有多张，所以用循环对应同一个movieUrl的urlID）     
          *    
      */    
      public function getImage(){        
      # 返回bool        
      $result = Db::table(&#39;think_dywz&#39;)->column(&#39;id,movieUrl&#39;);        
      foreach ($result as $key => $value){       
           $result = $this->https_request($value);            
           $pattern = &#39;/<img border="0"\s+src="(.+)".*>/sU&#39;;            
           preg_match_all($pattern,$result,$m);           
           
          if ($m[0]) {             
             $imgs = $m[1];                
             foreach ($imgs as $k=> $v) {                  
               $data = [                      
                 &#39;imgUrl&#39; => $v,                       
                 &#39;urlID&#39;  => $key,                        
                 &#39;create_time&#39; => time(),                  
              ];                   
              
               Db::name(&#39;dywzimgs&#39;)->insert($data);               
            }            
         }        
     }    
  }    
  
      /**     
      * cURL万能函数     
      * @param [string] $url [请求地址]    
       * @param [arra] $data  [post的数据]     
       * @return mixed     
       */    
       private static function https_request($url, $data = null){     
          # 初始化一个cURL会话        
          $curl = curl_init();        
          
          //设置请求选项, 包括具体的url        
          curl_setopt($curl, CURLOPT_URL, $url);        
          curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, FALSE);  //禁用后cURL将终止从服务端进行验证        
          curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, FALSE);        
          
          if (!empty($data)){         
             curl_setopt($curl, CURLOPT_POST, 1);  //设置为post请求类型            
             curl_setopt($curl, CURLOPT_POSTFIELDS, $data);  //设置具体的post数据      
         }        
         curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);        
         $response = curl_exec($curl);  //执行一个cURL会话并且获取相关回复        
         curl_close($curl);  //释放cURL句柄,关闭一个cURL会话        
         return $response;    
       }
   }