############################################
# Global Restrictions for All Bots
############################################
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# Block all internal WordPress system directories
Disallow: /wp-includes/
Disallow: /wp-content/cache/
Disallow: /wp-content/uploads/wc-logs/
Disallow: /wp-content/mu-plugins/
Disallow: /wp-content/upgrade/
Disallow: /wp-content/backups/
Disallow: /wp-json/

# Allow essential assets for proper rendering (SEO critical)
Allow: /wp-includes/js/
Allow: /*.css$
Allow: /*.js$

# Block private files
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /?s=     # Block internal search results (thin content)
Disallow: /*?replytocom=  # Prevent duplicate URLs
Disallow: /*add-to-cart=  # Prevent unnecessary index bloat

# Block crawlers from duplicated archives
Disallow: /category/
Disallow: /tag/
Disallow: /author/
Disallow: /archives/

############################################
# Block Bad / High-Load Crawlers Explicitly
############################################

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Yandex
Disallow: /

User-agent: MauiBot
Disallow: /

############################################
# Allow Only Trusted Major Search Engines
############################################

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

############################################
# Sitemap (SEO Critical)
############################################

Sitemap: https://hackybara.com/sitemap_index.xml