# ===================================== # PaprikaBulk Data Knowledge Hub # Robots.txt # ===================================== User-agent: * Allow: / # Sitemap Sitemap: https://data.paprikabulk.com/sitemap.xml # ===================================== # Block unnecessary system resources # ===================================== Disallow: /404.html Disallow: /overrides/ Disallow: /templates/ # ===================================== # AI Search Crawlers # ===================================== User-agent: GPTBot Allow: / User-agent: OAI-SearchBot Allow: / User-agent: Claude-Web Allow: / Crawl-delay: 1 User-agent: PerplexityBot Allow: / Crawl-delay: 1 User-agent: Google-Extended Allow: / User-agent: CCBot Allow: / User-agent: Applebot-Extended Allow: / User-agent: FacebookBot Allow: / User-agent: Bytespider Allow: / Crawl-delay: 1 User-agent: Cohere-ai Allow: / User-agent: Amazonbot Allow: / # Polite crawl-delay for all crawlers Crawl-delay: 1