# ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ # ┃ Compumail.dk - Robots Policy (Retail + AI Optimized) ┃ # ┣━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┫ # ┃ 1. LLM Discovery enabled (via llms.txt) ┃ # ┃ 2. Unified Crawl Policy (Standardized for all agents) ┃ # ┃ 3. Filter traps & retail system paths blocked ┃ # ┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛ # ========================================================= # SCRAPER & AGGRESSIVE BOTS BLOCK # ========================================================= User-agent: AhrefsBot User-agent: Semrush User-agent: CCBot User-agent: Omgilibot User-agent: Omgili User-agent: FacebookBot User-agent: Bytespider User-agent: ImagesiftBot User-agent: Amazonbot Disallow: / # ========================================================= # GENERAL RULES & AI DISCOVERY (All other bots) # ========================================================= User-agent: * # Priority Access for AI Instructions Allow: /llms.txt Allow: /llms-full.txt # Block system & noise Disallow: /admin Disallow: /sis Disallow: /sonata Disallow: /basket Disallow: /checkout Disallow: /profile Disallow: /login Disallow: /pdfspec/ Disallow: /sv Disallow: /*?filters Disallow: /*?tb Disallow: /*&tb # ========================================================= # SITEMAP # ========================================================= Sitemap: https://www.compumail.dk/sitemap/sitemap.xml