Initial commit: Laravel scaffold + Common Crawl site indexing

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.
This commit is contained in:
m105
2026-07-20 00:04:45 +03:00
commit 1c9fc5d423
64 changed files with 11338 additions and 0 deletions
+25
View File
@@ -0,0 +1,25 @@
<?php
namespace Database\Seeders;
use App\Models\User;
use Illuminate\Database\Console\Seeds\WithoutModelEvents;
use Illuminate\Database\Seeder;
class DatabaseSeeder extends Seeder
{
use WithoutModelEvents;
/**
* Seed the application's database.
*/
public function run(): void
{
// User::factory(10)->create();
User::factory()->create([
'name' => 'Test User',
'email' => 'test@example.com',
]);
}
}