这篇文章主要介绍了thinkphp5.1怎么实现多线程爬虫,具有一定借鉴价值,感兴趣的朋友可以参考下,希望大家阅读完这篇文章之后大有收获,下面让小编带着大家一起了解一下。
创建一个cli命令
php think make:command Thread thread
测试能否成功执行
php think thread
文档地址:guzzle文档地址(https://guzzle-cn.readthedocs.io/zh_CN/latest/quickstart.html)
<?php
/**
* Created by.
* User: Jim
* Date: 2020/9/29
* Time: 14:31
*/
namespace app\command;
use GuzzleHttp\Client;
use GuzzleHttp\Pool;
use think\console\Command;
use think\console\Input;
use think\console\Output;
/**
* Guzzle
* Class Thread
* @package app\command
* 文档地址 https://guzzle-cn.readthedocs.io/zh_CN/latest/quickstart.html
*/
class Thread extends Command
{
/**
* 请求的总次数
* @var int
*/
protected $totalPageCount = 50;
/**
* 当前请求的次数
* @var int
*/
protected static $counter = 1;
/**
* 线程的数量
* @var int
*/
protected $threads = 20;
protected function configure()
{
// 指令配置
$this->setName('thread');
// 设置参数
}
protected function execute(Input $input, Output $output)
{
$client = new Client();
$requests = function ($total) use ($client) {
foreach (range(1, $total) as $r) {
$uri = 'https://apinew.juejin.im/content_api/v1/short_msg/detail';
yield function () use ($client, $uri) {
return $client->postAsync($uri, [
'verify' => false,
'json' => [
'msg_id' => '6845185452727599118'
]
]);
};
}
};
$pool = new Pool($client, $requests($this->totalPageCount), [
'concurrency' => $this->threads,
// 请求成功
'fulfilled' => function ($response, $index) use ($output) {
$res = $response->getBody()->getContents();
$output->writeln($res);
$output->writeln("正在执行第{$index}个·····");
if ($this->checkThreadIsEnd() == true) {
$output->writeln("------------请求结束---------");
return false;
}
},
// 请求失败
'rejected' => function ($reason, $index) use ($output) {
$output->writeln("执行失败,{$reason}");
},
]);
$promise = $pool->promise();
$promise->wait();
}
/**
* 检测任务是否结束
* @return bool
*/
private function checkThreadIsEnd()
{
if (self::$counter < $this->totalPageCount) {
self::$counter++;
return false;
} else {
return true;
}
}
}
php think thread
感谢你能够认真阅读完这篇文章,希望小编分享的“thinkphp5.1怎么实现多线程爬虫”这篇文章对大家有帮助,同时也希望大家多多支持亿速云,关注亿速云行业资讯频道,更多相关知识等着你来学习!
亿速云「云服务器」,即开即用、新一代英特尔至强铂金CPU、三副本存储NVMe SSD云盘,价格低至29元/月。点击查看>>
免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。