curl 和正则采集网页

效果展示：

采集分类

代码实现：

      

<?php  
namespace App\Http\Controllers;
use Illuminate\Support\Facades\Input;
use Illuminate\Http\Request;
use DB;
class GatherController extends NewBaseController
{
     /**
      * 采集首页
      * @param  Request $request [description]
      * @return [array]           [分类数据]
      */
     public function index(Request $request){
         //查询分类信息
 		  $typeList = DB::table('type')->get();
 		  // print_r($typeList);exit;
         return view('gather',['typeList'=>$typeList ]); 
     }

     /**
      * 采集操作
      * @param  Request $request [description]
      * @return [array]           [分类|详细数据]
      */
     public function show(Request $request){
     	     set_time_limit(0); 
        if($request->input('type_id')){
             //分类采集成功
             $data=$request->input();
	         $typeId = $data['type_id'];
	         $typeList = DB::table('type')->where('type_id',$typeId)->first();
	         //确定分类链接 
	         $typeLink=$typeList['type_link'];
	         $url=$typeLink;
	         // $typeLink="";
	         //开始采集
	         if (function_exists('curl_init')) {
	    	 $url = $typeLink;
	   		 $ch = curl_init();
	   		 curl_setopt($ch, CURLOPT_URL, $url);
	   		 curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
	    	 curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 10);
	   		 $dxycontent = curl_exec($ch);
	   		 // echo $dxycontent;exit;
	   		 $reg='#<div class="article-list">.*<div class="pager">#isU';
	   		 preg_match($reg,$dxycontent,$p);
	   		 // print_r($p);exit;
	   		 // print_r($reg);
         	 $reg1 = '#<p>(.*)</p>#isU';
         	 $reg2 = '#<img class=".*" src=".*" data-original="(.*)" alt="(.*)">#isU';
         	 preg_match_all($reg2, $p[0], $img);
         	 // print_r($img);exit;
         	 //标题
         	 $titleList = $img[2];
         	 preg_match_all($reg1, $p[0], $content);
         	 //内容
         	 // $contentList=array();
         	 $contentList = $content[1];
         	 // print_r($contentList);exit;
         	 //图片
         	 $img1 = $img[1];
         	 // print_r($img1);exit;
         	 for($i=0;$i<=9;$i++){
         	 	// $imgList[] = $img1[$i];
         	 	$suff = substr($img1[$i],strrpos($img1[$i],'.'));
         	 	$fileName = rand(10000,90000).time().$suff;
         	 	$imgList[] = $fileName;
         	 	// echo $filename;
         	 	$v=file_get_contents($img1[$i]);
         	 	file_put_contents("upload/".$fileName,$v);
         	 }
         	 // exit;
             //入库
             $arr=array();
             foreach($titleList as $k=>$v){
 				$arr[$k]['news_title'] = $v;
 				$arr[$k]['news_content'] = $contentList[$k];
 				$arr[$k]['news_img'] = $imgList[$k];
 				$arr[$k]['type_id'] =  $typeId;
 				$res=DB::table('news')->insertGetId($arr[$k]);
             }
             // exit;
             if($res){
             	$newsList = DB::table('news')->get(); 
             	// print_R($newsList);exit;
             	 	return view('news_list',['newsList'=>$newsList]);
             }
	   	    }
        }else{
         	//采集分类
         	$link=$request->input('link');
         	     //开始采集
		         if (function_exists('curl_init')) {
		    	 $url = $link;
		   		 $ch = curl_init();
		   		 curl_setopt($ch, CURLOPT_URL, $url);
		   		 curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
		    	 curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 10);
		   		 $dxycontent = curl_exec($ch);
		   		 // echo $dxycontent;
		   		 $reg='#<li ><a href="(.*)">(.*)</a></li>#isU';
		   		 preg_match_all($reg, $dxycontent, $list);
		   		 // print_r($list);exit;
		   		 // $typeName
		   		  $arr=array();
		   		  foreach($list[1] as $k=>$v){
                      $arr[$k]['type_link'] = $v;
		   		  }
		   		  foreach($list[2] as $k=>$v){
                      $arr[$k]['type_name'] = $v;
		   		  }
		   		  //分类入库
		   		  foreach($arr as $k=>$v){
		   		   $res = DB::table('type')->insertGetId($v);
		   		  }
		   		   //跳转到首页
		   		   if($res){
		   		   	 return redirect('/gather');
		   		   }else{
		   		   	  echo "添加失败";
		   		   } 
		   		    // print_r($arr);exit;
		  		 } else {
		   		 echo '主人的服务器尚未开启curl扩展';
		        }
		         	print_r($request->input());
		  }
     }
}






?>

恶心人的地方：正则匹配

需要注意的地方：file_put_contents 的使用