在上一篇我們抽出了一個 Base 的抽象類別，今天我們換一個方式重構

原本 Home 及 Base 的程式如下

<?php

namespace Recca0120\Ithome30\Crawlers;

use GuzzleHttp\Psr7\Request;
use Psr\Http\Client\ClientInterface;

abstract class Base
{
    protected string $baseUrl = 'https://www.ptt.cc';

    private array $headers = [
        'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8',
        'Accept-Encoding' => 'gzip, deflate, br',
        'Accept-Language' => 'zh-TW,zh;q=0.8',
        'Cache-Control' => 'max-age=0',
        'Cookie' => 'over18=1',
        'Referer' => 'https://www.ptt.cc/bbs/Gossiping/index.html',
        'Sec-Ch-Ua' => '"Brave";v="117", "Not;A=Brand";v="8", "Chromium";v="117"',
        'Sec-Ch-Ua-Mobile' => '?0',
        'Sec-Ch-Ua-Platform' => '"macOS"',
        'Sec-Fetch-Dest' => 'document',
        'Sec-Fetch-Mode' => 'navigate',
        'Sec-Fetch-Site' => 'same-origin',
        'Sec-Fetch-User' => '?1',
        'Sec-Gpc' => '1',
        'Upgrade-Insecure-Requests' => '1',
        'User-Agent' => 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36',
    ];

    public function __construct(protected ClientInterface $httpClient)
    {
    }

    protected function sendRequest($url)
    {
        $request = new Request('GET', $url, $this->headers);
        $response = $this->httpClient->sendRequest($request);
        $html = (string)$response->getBody();

        return $html;
    }
}

<?php
// src/Crawlers/Home.php

namespace Recca0120\Ithome30\Crawlers;

class Home extends Base
{
    public function all()
    {
        $html = $this->sendRequest($this->baseUrl . '/bbs/hotboards.html');

        return array_map(
            fn (string $row) => $this->parseCols($row),
            $this->parseRows($html)
        );
    }

    private function parseCols($row)
    {
        preg_match('/href="(?<url>.+)"/', $row, $matched);
        preg_match_all('/"board-(?<name>\w+)">(?<value>.+?)<\/div>/', $row, $matches);
        $cols = ['url' => $this->baseUrl . $matched['url']];
        foreach (array_keys($matches[0]) as $index) {
            $name = $matches['name'][$index];
            $value = $matches['value'][$index];
            $cols[$name] = str_replace('&#9678;', '', strip_tags($value));
        }

        return $cols;
    }

    private function parseRows($html)
    {
        preg_match_all('/<a\sclass="board"[^>]*>.+?<\/a>/s', $html, $matches);

        return $matches[0];
    }
}

我們快速的重構成

<?php

namespace Recca0120\Ithome30;

use GuzzleHttp\Psr7\Request;
use Psr\Http\Client\ClientInterface;

class Client
{
    protected string $baseUrl = 'https://www.ptt.cc';

    private array $headers = [
        'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8',
        'Accept-Encoding' => 'gzip, deflate, br',
        'Accept-Language' => 'zh-TW,zh;q=0.8',
        'Cache-Control' => 'max-age=0',
        'Cookie' => 'over18=1',
        'Referer' => 'https://www.ptt.cc/bbs/Gossiping/index.html',
        'Sec-Ch-Ua' => '"Brave";v="117", "Not;A=Brand";v="8", "Chromium";v="117"',
        'Sec-Ch-Ua-Mobile' => '?0',
        'Sec-Ch-Ua-Platform' => '"macOS"',
        'Sec-Fetch-Dest' => 'document',
        'Sec-Fetch-Mode' => 'navigate',
        'Sec-Fetch-Site' => 'same-origin',
        'Sec-Fetch-User' => '?1',
        'Sec-Gpc' => '1',
        'Upgrade-Insecure-Requests' => '1',
        'User-Agent' => 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36',
    ];

    public function __construct(protected ClientInterface $httpClient)
    {
    }

    public function sendRequest($url)
    {
        $request = new Request('GET', $url, $this->headers);
        $response = $this->httpClient->sendRequest($request);
        $html = (string)$response->getBody();

        return $html;
    }

    public function getBaseUrl()
    {
        return $this->baseUrl;
    }
}

<?php
// src/Crawlers/Home.php

namespace Recca0120\Ithome30\Crawlers;

use Psr\Http\Client\ClientInterface;
use Recca0120\Ithome30\Client;

class Home
{
    private Client $client;
    
    public function __construct(ClientInterface $clientInterface)
    {
        $this->client = new Client($clientInterface);
    }

    public function all()
    {
        $html = $this->client->sendRequest($this->client->getBaseUrl() . '/bbs/hotboards.html');

        return array_map(
            fn (string $row) => $this->parseCols($row),
            $this->parseRows($html)
        );
    }

    private function parseCols($row)
    {
        preg_match('/href="(?<url>.+)"/', $row, $matched);
        preg_match_all('/"board-(?<name>\w+)">(?<value>.+?)<\/div>/', $row, $matches);
        $cols = ['url' => $this->client->getBaseUrl() . $matched['url']];
        foreach (array_keys($matches[0]) as $index) {
            $name = $matches['name'][$index];
            $value = $matches['value'][$index];
            $cols[$name] = str_replace('&#9678;', '', strip_tags($value));
        }

        return $cols;
    }

    private function parseRows($html)
    {
        preg_match_all('/<a\sclass="board"[^>]*>.+?<\/a>/s', $html, $matches);

        return $matches[0];
    }
}

如果單就消除重覆程式碼，上一篇的方式和這一篇的方式都可以達到目的，但程式的表示力就截然不同，當需求再增加時，兩者的程式調整方式也截然不同。但我們真的認真來討論哪個方案比較好？在新需求還沒出現前，我們都沒辦法預知哪個方案比較好，但還好我們都有測試保護了，在新需求出現時我們再來決定方案就好了