slake-school-service/tests/Unit/NewsContentHtmlTest.php

<?php

namespace Tests\Unit;

use App\Services\Crawl\NewsContentHtml;
use PHPUnit\Framework\TestCase;

class NewsContentHtmlTest extends TestCase
{
    public function test_extracts_sjtu_article_content(): void
    {
        $html = <<<'HTML'
<div class="Article_content">
<p>正文段落一</p>
<p><img src="/resource/upload/202604/a.png" alt="图"/></p>
<p>正文段落二，需要足够长的文字才能通过提取阈值校验。</p>
</div>
<div class="Article-source">来源</div>
HTML;

        $body = NewsContentHtml::extractBody($html);
        $this->assertNotNull($body);
        $this->assertStringContainsString('正文段落一', $body);
        $this->assertStringContainsString('/resource/upload/', $body);
    }

    public function test_resolves_relative_image_src(): void
    {
        $normalized = NewsContentHtml::normalize(
            '<img src="/resource/upload/a.png">',
            'https://news.sjtu.edu.cn/jdyw/20260408/221279.html'
        );

        $this->assertStringContainsString('https://news.sjtu.edu.cn/resource/upload/a.png', $normalized);
    }

    public function test_extracts_pedata_article_main(): void
    {
        $html = <<<'HTML'
<div class="article_con">
<div class="article_main">
<p>清科研究中心正文段落一，包含足够长的文字用于通过正文提取阈值校验。</p>
<p>第二段正文内容继续补充长度，确保 strip_tags 后超过三十个字符。</p>
</div>
</div>
<div class="news_all_text">版权声明</div>
HTML;

        $body = NewsContentHtml::extractBody($html);

        $this->assertNotNull($body);
        $this->assertStringContainsString('清科研究中心正文段落一', $body);
    }
}