Day 20. 只是增加看版文章列表測試就變的超難寫 - 分段進行 - iT 邦幫忙::一起幫忙解決難題，拯救 IT 人的一天

2023 iThome 鐵人賽

DAY 20

Software Development

開心撰寫 PHPUnit系列第 20 篇

Day 20. 只是增加看版文章列表測試就變的超難寫 - 分段進行

15th鐵人賽 phpunit

recca0120

2023-10-05 23:27:52

624 瀏覽

分享至

在上一篇最終定義出最終結果希望為

<?php

namespace Recca0120\Ithome30\Tests;

use Mockery;
use GuzzleHttp\Client;
use GuzzleHttp\Psr7\Request;
use PHPUnit\Framework\TestCase;
use Recca0120\Ithome30\PttCrawler;
use Psr\Http\Client\ClientInterface;

class PttCrawlerTest extends TestCase
{
    public function test_fetch_board_page()
    {
        \VCR\VCR::turnOn();
        \VCR\VCR::insertCassette('ptt_home.yaml');

        /** @var Mockery\Mock|ClientInterface $httpClient */
        $httpClient = Mockery::spy(new Client());

        $crawler = new PttCrawler($httpClient);
        $records = $crawler->all();

        self::assertEquals([
            'board_name' => 'Gossiping',
            'board_class' => '綜合',
            'nrec' => '4',
            'type' => '協尋',
            'title' => '9/30 10:15員林回春中醫診所前車禍行車',
            'author' => 'tyujm',
            'date' => '10/3',
            'url' => 'https://www.ptt.cc/bbs/Gossiping/M.1696296400.A.A9B.html',
        ], $records[0]);

        $httpClient->shouldHaveReceived('sendRequest')->once()->with(Mockery::on(function (Request $request) {
            return (((string)$request->getUri()) === 'https://www.ptt.cc/bbs/hotboards.html');
        }));

        \VCR\VCR::eject();
        \VCR\VCR::turnOff();
    }
}

所以我們的主程式可能就會這樣寫 ...

<?php
// src/PttCrawler.php

namespace Recca0120\Ithome30;

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

class PttCrawler
{
    public function __construct(private ClientInterface $httpClient)
    {
    }

    public function all()
    {
        $crawler = new Home($this->httpClient);
        $boardCrawler = new Board($this->httpClient);

        $results = [];
        foreach ($crawler->all() as $board) {
            foreach ($boardCrawler->fetch($board) as $articles) {
                $results[] = $articles;
            }
        }

        return $results;
    }
}

如果持續這樣寫下去，我們的測試就會變成大雜燴，當其中一個環節出錯時，我們會變的很難除錯，那要怎麼解決這個困境呢？我們直接再另外寫一個抓取看版列表的測試，讓我們可以只專注抓取看版列表的開發上，所以我們就可以先寫出這樣的測試案例

<?php

<?php

namespace Recca0120\Ithome30\Tests\Cralwers;

use Mockery;
use GuzzleHttp\Client;
use PHPUnit\Framework\TestCase;
use Recca0120\Ithome30\Crawlers\Board;

class BoardTest extends TestCase
{
    public function test_fetch_board_articles_list()
    {
        \VCR\VCR::turnOn();
        \VCR\VCR::insertCassette('ptt_board_gossiping.yaml');

        /** @var Mockery\Mock|ClientInterface $httpClient */
        $httpClient = Mockery::spy(new Client());

        $board = new Board($httpClient);

        $records = $board->fetch([
            'name' => 'Gossiping',
            "nuser" => '8803',
            'class' => '綜合',
            'title' => '[八卦] 亞運李智凱、許皓鋐奪金！',
            'url' => 'https://www.ptt.cc/bbs/Gossiping/index.html'
        ]);

        self::assertEquals([
            'board_name' => 'Gossiping',
            'board_class' => '綜合',
            'nrec' => '4',
            'type' => '問卦',
            'title' => '保全可以睡覺滑手機那擺個稻草人就好了',
            'author' => 'Ommmmmm5566',
            'date' => '10/05',
            'url' => 'https://www.ptt.cc/bbs/Gossiping/M.1696519188.A.5C8.html',
        ], $records[0]);

        \VCR\VCR::eject();
        \VCR\VCR::turnOff();
    }
}

測試案例出來後，我們就可以進行 Board 的實作

<?php

namespace Recca0120\Ithome30\Crawlers;

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

class Board
{
    public function __construct(private ClientInterface $httpClient)
    {
    }

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

        preg_match_all('/class="r-ent">.+<div class="mark">(.+)<\/div>/sU', $html, $matches);

        $results = [];
        foreach ($matches[0] as $row) {
            preg_match_all('/<div class="(?<name>(nrec|title|author|date))"[^>]*>(?<value>.*?)<\/div>/s', $row, $matches2);
            $temp = [];
            foreach (array_keys($matches2[0]) as $index) {
                $temp[$matches2['name'][$index]] = trim($matches2['value'][$index]);
            }
            preg_match('/href="(.*)"/', $temp['title'], $matched);
            $temp['url'] = 'https://www.ptt.cc' . $matched[1];

            preg_match('/\[(.+)\](.+)/', strip_tags($temp['title']), $matched);
            $temp['type'] = trim($matched[1]);
            $temp['title'] = trim($matched[2]);
            $temp['nrec'] = strip_tags($temp['nrec']);
            $temp['board_name'] = $board['name'];
            $temp['board_class'] = $board['class'];

            $results[] = $temp;
        }

        return $results;
    }
}

測試得到綠燈後，我們再進行重構

<?php

namespace Recca0120\Ithome30\Crawlers;

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

class Board
{
    public function __construct(private ClientInterface $httpClient)
    {
    }

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

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

    private function parseCols($row, $board)
    {
        preg_match_all('/<div class="(?<name>(nrec|title|author|date))"[^>]*>(?<value>.*?)<\/div>/s', $row, $matches);

        $cols = [
            'board_name' => $board['name'],
            'board_class' => $board['class'],
        ];

        foreach (array_keys($matches[0]) as $index) {
            $cols[$matches['name'][$index]] = trim($matches['value'][$index]);
        }
        $cols['nrec'] = strip_tags($cols['nrec']);

        preg_match('/href="(.*)"/', $cols['title'], $matched);
        $cols['url'] = 'https://www.ptt.cc' . $matched[1];

        preg_match('/\[(.+)\](.+)/', strip_tags($cols['title']), $matched);
        $cols['type'] = trim($matched[1]);
        $cols['title'] = trim($matched[2]);

        return $cols;
    }

    private function parseRows($html)
    {
        preg_match_all('/class="r-ent">.+<div class="mark">(.+)<\/div>/sU', $html, $matches);

        return $matches[0];
    }
}

這樣就完成 Board 的程式了