# robots.txt - University American College Skopje (UACS) # https://www.uacs.edu.mk # ============================================= # Search Engine Crawlers (Allow) # ============================================= User-agent: Googlebot Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ User-agent: Googlebot-Image Allow: /images/ Allow: /files/ User-agent: bingbot Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ User-agent: YandexBot Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ User-agent: DuckDuckBot Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ # ============================================= # AI / LLM Bots (Allow - so LLMs learn UACS content) # ============================================= User-agent: GPTBot Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ Disallow: /users/ User-agent: ChatGPT-User Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ Disallow: /users/ User-agent: ClaudeBot Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ Disallow: /users/ User-agent: anthropic-ai Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ Disallow: /users/ User-agent: PerplexityBot Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ Disallow: /users/ User-agent: cohere-ai Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ Disallow: /users/ User-agent: Google-Extended Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ Disallow: /users/ User-agent: Applebot-Extended Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ Disallow: /users/ User-agent: meta-externalagent Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ Disallow: /users/ # ============================================= # Low-Value / Aggressive AI Scrapers (Block) # ============================================= User-agent: Bytespider Disallow: / User-agent: CCBot Disallow: / User-agent: Amazonbot Disallow: / User-agent: Diffbot Disallow: / User-agent: FacebookBot Disallow: / User-agent: ImagesiftBot Disallow: / User-agent: Omgili Disallow: / User-agent: Omgilibot Disallow: / # ============================================= # SEO Crawlers (Allow - useful for monitoring) # ============================================= User-agent: AhrefsBot Allow: / Crawl-delay: 10 User-agent: SemrushBot Allow: / Crawl-delay: 10 User-agent: MJ12bot Disallow: / # ============================================= # Spam / Aggressive Bots (Block) # ============================================= User-agent: AdsBot-Google Disallow: / User-agent: SeznamBot Disallow: / User-agent: dotbot Disallow: / User-agent: PetalBot Disallow: / User-agent: MegaIndex.ru Disallow: / # ============================================= # Default Rule # ============================================= User-agent: * Allow: / Disallow: /cp/ Disallow: /vendor/ Disallow: /storage/ Disallow: /api/ Disallow: /*.json$ Disallow: /users/ Disallow: /search?* Crawl-delay: 5 # ============================================= # Sitemaps # ============================================= Sitemap: https://www.uacs.edu.mk/sitemap.xml