m105
1c9fc5d423
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.
22 lines
657 B
PHP
22 lines
657 B
PHP
<?php
|
|
|
|
use Illuminate\Foundation\Application;
|
|
use Illuminate\Foundation\Configuration\Exceptions;
|
|
use Illuminate\Foundation\Configuration\Middleware;
|
|
use Illuminate\Http\Request;
|
|
|
|
return Application::configure(basePath: dirname(__DIR__))
|
|
->withRouting(
|
|
web: __DIR__.'/../routes/web.php',
|
|
commands: __DIR__.'/../routes/console.php',
|
|
health: '/up',
|
|
)
|
|
->withMiddleware(function (Middleware $middleware): void {
|
|
//
|
|
})
|
|
->withExceptions(function (Exceptions $exceptions): void {
|
|
$exceptions->shouldRenderJsonWhen(
|
|
fn (Request $request) => $request->is('api/*'),
|
|
);
|
|
})->create();
|