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.
19 lines
425 B
PHP
Executable File
19 lines
425 B
PHP
Executable File
#!/usr/bin/env php
|
|
<?php
|
|
|
|
use Illuminate\Foundation\Application;
|
|
use Symfony\Component\Console\Input\ArgvInput;
|
|
|
|
define('LARAVEL_START', microtime(true));
|
|
|
|
// Register the Composer autoloader...
|
|
require __DIR__.'/vendor/autoload.php';
|
|
|
|
// Bootstrap Laravel and handle the command...
|
|
/** @var Application $app */
|
|
$app = require_once __DIR__.'/bootstrap/app.php';
|
|
|
|
$status = $app->handleCommand(new ArgvInput);
|
|
|
|
exit($status);
|