thinkphp5使用workerman定时器定时爬取某站点新闻资讯等内容

时间:2022-10-17 23:32:27

1、首先通过 composer 安装workerman,在thinkphp5完全开发手册的扩展-》coposer包-》workerman有详细说明:

#在项目根目录执行以下指令
composer require topthink/think-worker

 2.在项目根目录创建服务启动文件 server.php:

<?php

define('APP_PATH', __DIR__ . '/application/');
define("BIND_MODULE", "server/Worker");
// 加载框架引导文件
require __DIR__ . '/thinkphp/start.php';

 3、在application里创建server模块,并在server里创建控制器 Worker.php:

<?php
namespace app\server\controller;
use think\worker\Server;

class Worker extends Server
{

    public function onWorkerStart($work)
    {
        $handle=new Collection();
        $handle->add_timer();
    }


}

 

4.创建Collection.php类

<?php
namespace app\server\controller;
use app\common\model\ArticleModel;
use think\Controller;
use Workerman\Lib\Timer;

class Collection extends Controller{

	public function __construct(){
		  parent::__construct();
	}

	public function add_timer(){
        Timer::add(10, array($this, 'index'), array(), true);//时间间隔过小,运行会崩溃
    }
    /**
     * 采集数据
     */

    public function index(){
        $total=$this->get_jinse();
        return json(['msg'=>"此次采集数据共 $total 条。",'total'=>$total]);
    }

  
    /**
     * 获取金色财经资讯
     */
    public function get_jinse(){
        $url="https://api.jinse.com/v4/live/list?limit=20";
        $data=$this->get_curl($url);
        $data=json_decode($data);
        $data=$data->list[0]->lives;

        $validate=validate('Article');
        $items=[];

        foreach ($data as $k=>$v){

            preg_match('/【(.+?)】(.+)/u',$v->content,$content);

            if(!@$content[2]){
                continue;
            }
            $list=array(
                'source_id'=>$v->id,
                'source'=>'金色财经',
                'title'=>trim(preg_replace('/.*\|/','',$content[1])),
                'content'=>$content[2],
            );
            if($validate->check($list)){
                $items[]=$list;
            }
        }
        if($items){
            krsort($items);
            $model=new ArticleModel();
            $model->saveAll($items);
        }
        return count($items);
    }
    public function get_curl($url){
        $ch=curl_init();
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
        curl_setopt($ch,CURLOPT_URL,$url);
        curl_setopt($ch,CURLOPT_HEADER,0);
        curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
        $output = curl_exec($ch);

        if($output === FALSE ){
            echo "CURL Error:".curl_error($ch);
        }
        curl_close($ch);
        // 4. 释放curl句柄

        return $output;

    }
  
}

 5、启动服务 php server.php start