# robots.txt — managramasethu.in User-agent: * Disallow: /a/downloads/-/* Disallow: /admin Disallow: /cart Disallow: /carts Disallow: /orders Disallow: /account Disallow: /checkout Disallow: /checkouts/ # Internal search (thin content) Disallow: /search # Sorting & filter duplicate URLs Disallow: /*?*sort_by=* Disallow: /*?*filter=* # Shopify preview URLs Disallow: /*preview_theme_id* Disallow: /*preview_script_id* # Shopify system endpoints Disallow: /sf_private_access_tokens Disallow: /.well-known/shopify/monorail Disallow: /recommendations/products Disallow: /*/recommendations/products Sitemap: https://managramasethu.in/sitemap.xml # Google AdsBot (must be explicitly defined) User-agent: AdsBot-Google Disallow: /checkout Disallow: /checkouts/ Disallow: /cart Disallow: /carts Disallow: /orders Disallow: /account Disallow: /sf_private_access_tokens Disallow: /*preview_theme_id* Disallow: /*preview_script_id* # Block very old / low-value crawler User-agent: Nutch Disallow: / # AI / LLM Crawlers (Allowed for public content understanding) # ============================================================= User-agent: GPTBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: Google-Extended Allow: / User-agent: ClaudeBot Allow: / User-agent: Claude-Web Allow: / User-agent: CCBot Allow: / User-agent: Amazonbot Allow: / User-agent: Applebot-Extended Allow: / # Throttle aggressive SEO tools # ============================== User-agent: AhrefsBot Crawl-delay: 10 User-agent: SemrushBot Crawl-delay: 10 User-agent: MJ12bot Crawl-delay: 10