# ==============================================================================
# almanara (براعم) - Fekra Labs (https://almanara.fekralabs.com)
# Official Robots Exclusion & Crawl Policy
# Standard: RFC 9309 Compliant
# ==============================================================================

User-agent: *
Allow: /
Allow: /ar/
Allow: /en/
Allow: /_astro/
Allow: /images/
Allow: /favicon.svg
Allow: /site.webmanifest
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /ai.txt

# Disallowed internal directories & endpoints
Disallow: /api/
Disallow: /scratch/
Disallow: /temp/

# Clean Crawl Budget: Block Tracking Parameters
Disallow: /*?*utm_*
Disallow: /*?*fbclid*
Disallow: /*?*gclid*
Disallow: /*?*ref=*
Disallow: /*?*source=*
Disallow: /*?*token=*
Disallow: /*?*session_id=*
Disallow: /*?*preview=*
Disallow: /*?*q=*

User-agent: Googlebot
Allow: /
Allow: /_astro/
Allow: /images/
Disallow: /api/

User-agent: Googlebot-Image
Allow: /images/
Allow: /*.jpg
Allow: /*.jpeg
Allow: /*.png
Allow: /*.webp
Allow: /*.svg

User-agent: Bingbot
Allow: /

User-agent: Applebot
Allow: /

# Retrieval and citation crawlers
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Bulk training crawlers disallowed
User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

Host: https://almanara.fekralabs.com
Sitemap: https://almanara.fekralabs.com/sitemap-index.xml