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.
45 lines
825 B
PHP
45 lines
825 B
PHP
<?php
|
|
|
|
namespace App\Models;
|
|
|
|
use Illuminate\Database\Eloquent\Model;
|
|
use Illuminate\Database\Eloquent\Relations\BelongsTo;
|
|
|
|
class SitePage extends Model
|
|
{
|
|
protected $fillable = [
|
|
'site_id',
|
|
'urlkey',
|
|
'url',
|
|
'timestamp',
|
|
'mime',
|
|
'mime_detected',
|
|
'status',
|
|
'digest',
|
|
'length',
|
|
'offset',
|
|
'filename',
|
|
'languages',
|
|
'charset',
|
|
'redirect',
|
|
'title',
|
|
'description',
|
|
'keywords',
|
|
'content',
|
|
'raw',
|
|
'record_hash',
|
|
];
|
|
|
|
protected $casts = [
|
|
'raw' => 'array',
|
|
'status' => 'integer',
|
|
'length' => 'integer',
|
|
'offset' => 'integer',
|
|
];
|
|
|
|
public function site(): BelongsTo
|
|
{
|
|
return $this->belongsTo(Site::class);
|
|
}
|
|
}
|