Day 21. 爬蟲文章列表文頁 - 測試案例是可以調整的 - 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 21

Software Development

開心撰寫 PHPUnit系列第 21 篇

Day 21. 爬蟲文章列表文頁 - 測試案例是可以調整的

15th鐵人賽 phpunit

recca0120

2023-10-06 23:22:22

141 瀏覽

分享至

在上一篇我們只處理了文章列表，並沒有處理分頁問題，所以這次我們把分頁的程式碼加上去

首先我們先用這段程式碼來分析出『最舊、上頁、下頁、最新』的連結，並調整程式碼(調整前記得先執行一次測試)

<?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)
    {
        $url = $board['url'];

        $results = [];
        do {
            $html = $this->sendRequest($url);
            $rows = array_map(
                fn (string $row)  => $this->parseCols($row, $board),
                $this->parseRows($html)
            );
            $results = array_merge($results, $rows);
            $pagination = $this->parsePagination($html);
            $url = $pagination['prev'];
        } while ($pagination['prev'] !== null);

        return $results;
    }

    private function sendRequest($url)
    {
        $request = new Request('GET', $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 $html;
    }

    private function parsePagination($html)
    {
        preg_match_all('/<a class="btn wide( disabled)?"( href="(?<href>.+)")?>.*(?<name>(最舊|上頁|下頁|最新))[^<]*?<\/a>/', $html, $matches);
        $lookup = ['最舊' => 'oldest', '上頁' => 'prev', '下頁' => 'next', '最新' => 'latest'];
        $pagination = [];
        foreach (array_keys($matches[0]) as $index) {
            $pagination[$lookup[$matches['name'][$index]]] = $matches['href'][$index]
                ? 'https://www.ptt.cc' . $matches['href'][$index]
                : null;
        }

        return $pagination;
    }

    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];
    }
}

當程式碼調整完再執行測試會等待超久的時間，因為真的會去抓取分頁，所以這時候該怎麼辦？我們可以調整一下 fetch 的程式碼，增加一個 $take 變數，來限制抓取數量

    public function fetch(array $board, ?int $take = null)
    {
        $url = $board['url'];

        $results = [];
        // 加入已抓取分頁
        $page = 0;
        do {
            $page++;
            $html = $this->sendRequest($url);
            $rows = array_map(
                fn (string $row)  => $this->parseCols($row, $board),
                $this->parseRows($html)
            );
            $results = array_merge($results, $rows);

            // 增加跳出條件
            if ($take !== null && $page >= $take) {
                break;
            }

            $pagination = $this->parsePagination($html);
            $url = $pagination['prev'];
        } while ($pagination['prev'] !== null);

        return $results;
    }

這時我們再調整一下測試案例，指定 take 為 2，然後我們再驗證一下抓取的總筆數即可

<?php

namespace Recca0120\Ithome30\Tests\Crawlers;

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_gossiping.yaml');

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

        $crawler = new Board($httpClient);
        $records = $crawler->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'
        ], 2);

        // 兩頁共 43 筆資料
        self::assertCount(43, $records);
        self::assertEquals([
            'board_name' => 'Gossiping',
            'board_class' => '綜合',
            'nrec' => '4',
            'type' => '問卦',
            'title' => '司機夫人真的有去卡地亞血拚$1.1M嗎?',
            'author' => 'uwmtsa',
            'date' => '10/06',
            'url' => 'https://www.ptt.cc/bbs/Gossiping/M.1696537444.A.1A5.html',
        ], $records[0]);

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

這樣我們就完成了抓取分頁的功能了，但這邊我們可以再思考一下，fetch 回傳資料的格式是不是要再做調整？

$records = [
    [
        // page 1
        [
            'board_name' => 'Gossiping',
            'board_class' => '綜合',
            'nrec' => '4',
            'type' => '問卦',
            'title' => '司機夫人真的有去卡地亞血拚$1.1M嗎?',
            'author' => 'uwmtsa',
            'date' => '10/06',
            'url' => 'https://www.ptt.cc/bbs/Gossiping/M.1696537444.A.1A5.html',
        ],
        // ....
    ],
    [
        // page 2
        [
            'board_name' => 'Gossiping',
            'board_class' => '綜合',
            'nrec' => '4',
            'type' => '問卦',
            'title' => '司機夫人真的有去卡地亞血拚$1.1M嗎?',
            'author' => 'uwmtsa',
            'date' => '10/06',
            'url' => 'https://www.ptt.cc/bbs/Gossiping/M.1696537444.A.1A5.html',
        ],
        // ....
    ]
]

改成二維陣列，以一頁一頁的方式回傳會比較清楚呢，所以我們再調整一下程式碼

<?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, ?int $take = null)
    {
        $url = $board['url'];

        $results = [];
        $page = 0;
        do {
            $page++;
            $html = $this->sendRequest($url);
            $rows = array_map(
                fn (string $row)  => $this->parseCols($row, $board),
                $this->parseRows($html)
            );
            $results[] = $rows;

            if ($take !== null && $page >= $take) {
                break;
            }

            $pagination = $this->parsePagination($html);
            $url = $pagination['prev'];
        } while ($pagination['prev'] !== null);

        return $results;
    }

    private function sendRequest($url)
    {
        $request = new Request('GET', $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 $html;
    }

    private function parsePagination($html)
    {
        preg_match_all('/<a class="btn wide( disabled)?"( href="(?<href>.+)")?>.*(?<name>(最舊|上頁|下頁|最新))[^<]*?<\/a>/', $html, $matches);
        $lookup = ['最舊' => 'oldest', '上頁' => 'prev', '下頁' => 'next', '最新' => 'latest'];
        $pagination = [];
        foreach (array_keys($matches[0]) as $index) {
            $pagination[$lookup[$matches['name'][$index]]] = $matches['href'][$index]
                ? 'https://www.ptt.cc' . $matches['href'][$index]
                : null;
        }

        return $pagination;
    }

    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];
    }
}

<?php

namespace Recca0120\Ithome30\Tests\Crawlers;

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_gossiping.yaml');

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

        $crawler = new Board($httpClient);
        $records = $crawler->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'
        ], 2);

        // 驗證共抓取 2 頁
        self::assertCount(2, $records);
        // 驗證第一頁有 23 筆資料
        self::assertCount(23, $records[0]);
        self::assertEquals([
            'board_name' => 'Gossiping',
            'board_class' => '綜合',
            'nrec' => '4',
            'type' => '問卦',
            'title' => '司機夫人真的有去卡地亞血拚$1.1M嗎?',
            'author' => 'uwmtsa',
            'date' => '10/06',
            'url' => 'https://www.ptt.cc/bbs/Gossiping/M.1696537444.A.1A5.html',
        ], $records[0][0]);

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

這樣我們就完成了分頁功能