爬虫开发

2026-02-18 12:56:36 +08:00
parent a98bc6f13c
commit 260460df03
45 changed files with 4091 additions and 8 deletions
--- a/app/Models/CrawlRule.php
+++ b/app/Models/CrawlRule.php
@@ -0,0 +1,74 @@
+<?php
+
+declare(strict_types=1);
+
+namespace App\Models;
+
+use App\Enums\CrawlTargetModule;
+use Illuminate\Database\Eloquent\Factories\HasFactory;
+use Illuminate\Database\Eloquent\Model;
+use Illuminate\Database\Eloquent\Relations\HasMany;
+
+class CrawlRule extends Model
+{
+    use HasFactory;
+
+    protected $fillable = [
+        'name',
+        'target_module',
+        'enabled',
+        'entry_urls',
+        'cron_expression',
+        'timezone',
+        'max_pages',
+        'render_js',
+        'user_agent',
+        'headers',
+        'cookies',
+        'proxy',
+        'rate_limit_per_minute',
+        'retry_max',
+        'retry_backoff_seconds',
+        'extractor_config',
+        'mapping_config',
+        'dedupe_config',
+        'ai_fallback_enabled',
+        'ai_provider',
+        'ai_model',
+        'publish_policy',
+        'alert_email',
+        'last_run_at',
+        'next_run_at',
+        'created_by',
+        'updated_by',
+    ];
+
+    protected function casts(): array
+    {
+        return [
+            'target_module' => CrawlTargetModule::class,
+            'enabled' => 'boolean',
+            'entry_urls' => 'array',
+            'headers' => 'array',
+            'cookies' => 'array',
+            'extractor_config' => 'array',
+            'mapping_config' => 'array',
+            'dedupe_config' => 'array',
+            'render_js' => 'boolean',
+            'ai_fallback_enabled' => 'boolean',
+            'last_run_at' => 'datetime',
+            'next_run_at' => 'datetime',
+        ];
+    }
+
+    public function runs(): HasMany
+    {
+        return $this->hasMany(CrawlRun::class, 'rule_id');
+    }
+
+    public function alerts(): HasMany
+    {
+        return $this->hasMany(CrawlAlert::class, 'rule_id');
+    }
+}
+