PHP同步爬虫

主文件

<?php
/**
 * 同步爬虫
 */
require_once 'Crawler.php';

$start = microtime(true);//unix微妙数

$url = 'http://www.swoole.com/';
$ins = new Crawler($url);
$ins->visitOneDegree();

$timeUsed = microtime(true) - $start;
echo "time used: " . $timeUsed;

爬虫类

<?php

/**
 * Class Crawler
 * Path: /Sync/Crawler.php
 */
class Crawler
{
    private $url;
    private $toVisit = [];
    public function __construct($url)
    {
        $this->url = $url;
    }

    public function visitOneDegree()
    {
        $this->loadPageUrls();
        $this->visitAll();
    }

    private function loadPageUrls()
    {
        $content = $this->visit($this->url);
        $pattern = '#((http|ftp)://(\S*?\.\S*?))([\s)\[\]{},;"\':<]|\.\s|$)#i';
        preg_match_all($pattern, $content, $matched);//正则匹配
        foreach ($matched[0] as $url) {
            if (in_array($url, $this->toVisit)) {
                continue;
            }
            echo $url;echo "<br/>";
            $this->toVisit[] = $url;
        }
    }

    private function visitAll()
    {
        foreach ($this->toVisit as $url) {
            $this->visit($url);
        }
    }

    private function visit($url)
    {
        return @file_get_contents($url);//读取地址内容
    }
}

爬取结果

http://wiki.swoole.com/"
http://compiler.swoole.com/"
http://wiki.swoole.com/wiki/page/prid-1-p-project/change_log.html"
http://group.swoole.com"
http://wiki.swoole.com/wiki/page/prid-1-p-author.html"
http://wiki.swoole.com/wiki/page/p-case.html"
http://wiki.swoole.com/wiki/page/p-donate.html"
http://127.0.0.1:
time used: 275.22750902176

参考地址

https://www.jianshu.com/p/8035266e8f42
https://www.w3cschool.cn/swoole/swoole-functions.html
https://wiki.swoole.com/wiki/page/245.html