# ============================================================ # robots.txt — NoidaLuxury.com # LLM guidance: https://noidaluxury.com/llms.txt # ============================================================ # ------------------------------------------------------------ # Blocked scrapers / low-value crawlers # ------------------------------------------------------------ User-agent: Wotbox Disallow: / User-agent: oBot Disallow: / User-agent: YoudaoBot Disallow: / User-agent: SEOkicks-Robot Disallow: / User-agent: IstellaBot Disallow: / User-agent: yacybot Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: BLEXBot Disallow: / # ------------------------------------------------------------ # Search engines — each named bot needs its own full ruleset, # because a bot with its own block ignores User-agent: * # ------------------------------------------------------------ User-agent: Googlebot Disallow: /admin/ Disallow: /cgi-bin/ Disallow: /tmp/ Disallow: /?s= Disallow: /search Allow: / User-agent: Googlebot-Image Allow: / User-agent: Bingbot Disallow: /admin/ Disallow: /cgi-bin/ Disallow: /tmp/ Disallow: /?s= Disallow: /search Allow: / User-agent: BingPreview Disallow: /admin/ Disallow: /cgi-bin/ Disallow: /tmp/ Allow: / # ------------------------------------------------------------ # AI crawlers — allowed for brand visibility in AI answers # ------------------------------------------------------------ User-agent: GPTBot Disallow: /admin/ Disallow: /cgi-bin/ Allow: / User-agent: OAI-SearchBot Disallow: /admin/ Disallow: /cgi-bin/ Allow: / User-agent: ChatGPT-User Disallow: /admin/ Disallow: /cgi-bin/ Allow: / User-agent: Google-Extended Disallow: /admin/ Disallow: /cgi-bin/ Allow: / User-agent: ClaudeBot Disallow: /admin/ Disallow: /cgi-bin/ Allow: / User-agent: Claude-Web Disallow: /admin/ Disallow: /cgi-bin/ Allow: / User-agent: PerplexityBot Disallow: /admin/ Disallow: /cgi-bin/ Allow: / User-agent: CCBot Disallow: /admin/ Disallow: /cgi-bin/ Allow: / # ------------------------------------------------------------ # All other crawlers # ------------------------------------------------------------ User-agent: * Disallow: /admin/ Disallow: /cgi-bin/ Disallow: /tmp/ Disallow: /?s= Disallow: /search Allow: / # ------------------------------------------------------------ Sitemap: https://noidaluxury.com/sitemap.xml