Adds Site/SitePage models and the crawlindex:fetch command, which pulls CDX index records from Common Crawl and optionally enriches them with page title/description/keywords/body text extracted from the WARC archive. CDX/WARC access and the site/page upsert logic live in CommonCrawlIndexService and WarcRecordFetcher.
17 lines
243 B
PHP
17 lines
243 B
PHP
<?php
|
|
|
|
namespace Tests\Unit;
|
|
|
|
use PHPUnit\Framework\TestCase;
|
|
|
|
class ExampleTest extends TestCase
|
|
{
|
|
/**
|
|
* A basic test example.
|
|
*/
|
|
public function test_that_true_is_true(): void
|
|
{
|
|
$this->assertTrue(true);
|
|
}
|
|
}
|