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.
25 lines
361 B
PHP
25 lines
361 B
PHP
<?php
|
|
|
|
namespace App\Providers;
|
|
|
|
use Illuminate\Support\ServiceProvider;
|
|
|
|
class AppServiceProvider extends ServiceProvider
|
|
{
|
|
/**
|
|
* Register any application services.
|
|
*/
|
|
public function register(): void
|
|
{
|
|
//
|
|
}
|
|
|
|
/**
|
|
* Bootstrap any application services.
|
|
*/
|
|
public function boot(): void
|
|
{
|
|
//
|
|
}
|
|
}
|