Laravel 下使用 Guzzle 编写多线程爬虫实战

php artisan make:console MultithreadingRequest --command=test:multithreading-request

Commands\MultithreadingRequest::class,

$this->info('hello');

$ php artisan test:multithreading-requesthello

composer require guzzlehttp/guzzle "6.2"

<?php namespace App\Console\Commands;use GuzzleHttp\Client;use GuzzleHttp\Pool;use GuzzleHttp\Psr7\Request;use GuzzleHttp\Exception\ClientException;use Illuminate\Console\Command;class MultithreadingRequest extends Command{    private $totalPageCount;    private $counter        = 1;    private $concurrency    = 7;  // 同时并发抓取    private $users = ['CycloneAxe', 'appleboy', 'Aufree', 'lifesign',                        'overtrue', 'zhengjinghua', 'NauxLiu'];    protected $signature = 'test:multithreading-request';    protected $description = 'Command description';    public function __construct()    {        parent::__construct();    }    public function handle()    {        $this->totalPageCount = count($this->users);        $client = new Client();        $requests = function ($total) use ($client) {            foreach ($this->users as $key => $user) {                $uri = 'https://api.github.com/users/' . $user;                yield function() use ($client, $uri) {                    return $client->getAsync($uri);                };            }        };        $pool = new Pool($client, $requests($this->totalPageCount), [            'concurrency' => $this->concurrency,            'fulfilled'   => function ($response, $index){                $res = json_decode($response->getBody()->getContents());                $this->info("请求第 $index 个请求，用户 " . $this->users[$index] . " 的 Github ID 为：" .$res->id);                $this->countedAndCheckEnded();            },            'rejected' => function ($reason, $index){                $this->error("rejected" );                $this->error("rejected reason: " . $reason );                $this->countedAndCheckEnded();            },        ]);        // 开始发送请求        $promise = $pool->promise();        $promise->wait();    }    public function countedAndCheckEnded()    {        if ($this->counter < $this->totalPageCount){            $this->counter++;            return;        }        $this->info("请求结束！");    }}

$ php artisan test:multithreading-request请求第 5 个请求，用户 zhengjinghua 的 Github ID 为：3413430请求第 6 个请求，用户 NauxLiu 的 Github ID 为：9570112请求第 0 个请求，用户 CycloneAxe 的 Github ID 为：6268176请求第 1 个请求，用户 appleboy 的 Github ID 为：21979请求第 2 个请求，用户 Aufree 的 Github ID 为：5310542请求第 3 个请求，用户 lifesign 的 Github ID 为：2189610请求第 4 个请求，用户 overtrue 的 Github ID 为：1472352请求结束！