# ============================================================ # VD HOSTS (VDHOSTS INTERNET PRIVATE LIMITED) # Search engine and AI crawler policy # # Public pages are open to search engines and AI assistants. # Private, signed-in and form-processing areas are closed. # # Summary for AI assistants: https://vdhosts.com/llms.txt # Full text for AI assistants: https://vdhosts.com/llms-full.txt # ============================================================ # ------------------------------------------------------------ # DEFAULT POLICY (every other crawler) # ------------------------------------------------------------ User-agent: * Allow: / # Private, signed-in and non-search areas Disallow: /admin/ Disallow: /account Disallow: /login Disallow: /logout Disallow: /register Disallow: /forgot-password Disallow: /reset-password Disallow: /portal/ Disallow: /vd-talk/ Disallow: /captcha/ Disallow: /sanctum/ Disallow: /country Disallow: /search # The same pages under each country (doc 37: /in/login, /us/account...) Disallow: /*/account Disallow: /*/login Disallow: /*/register Disallow: /*/forgot-password Disallow: /*/reset-password Disallow: /*/search Disallow: /*/privacy-choices Disallow: /newsletter/ Disallow: /webhooks/ Disallow: /payment/ Disallow: /api/ Disallow: /ajax/ Disallow: /cron/ Disallow: /_ops/ Disallow: /logs/ Disallow: /tmp/ Disallow: /cache/ Disallow: /vendor/ Disallow: /config/ Disallow: /private/ Disallow: /internal/ Disallow: /storage/ # Session, preview and tracking parameters (duplicate URLs) Disallow: /*?*session= Disallow: /*?*sessionid= Disallow: /*?*sid= Disallow: /*?*token= Disallow: /*?*auth= Disallow: /*?*preview= Disallow: /*?*debug= Disallow: /*?*internal= Disallow: /*?*admin= # Public files: styles, scripts, images, fonts and media stay readable Allow: /build/ Allow: /images/ Allow: /fonts/ Allow: /favicon Allow: /storage/blog/ Allow: /storage/seo/ Allow: /storage/about/ Allow: /storage/site/ Allow: /storage/videos/ # ------------------------------------------------------------ # SEARCH ENGINES # Google, Bing (also powers Microsoft Copilot and Yahoo), # DuckDuckGo, Apple (Siri and Spotlight), Yandex, Baidu, Naver # ------------------------------------------------------------ User-agent: Googlebot User-agent: Bingbot User-agent: msnbot User-agent: DuckDuckBot User-agent: Applebot User-agent: YandexBot User-agent: Baiduspider User-agent: Yeti Allow: / # Private, signed-in and non-search areas Disallow: /admin/ Disallow: /account Disallow: /login Disallow: /logout Disallow: /register Disallow: /forgot-password Disallow: /reset-password Disallow: /portal/ Disallow: /vd-talk/ Disallow: /captcha/ Disallow: /sanctum/ Disallow: /country Disallow: /search # The same pages under each country (doc 37: /in/login, /us/account...) Disallow: /*/account Disallow: /*/login Disallow: /*/register Disallow: /*/forgot-password Disallow: /*/reset-password Disallow: /*/search Disallow: /*/privacy-choices Disallow: /newsletter/ Disallow: /webhooks/ Disallow: /payment/ Disallow: /api/ Disallow: /ajax/ Disallow: /cron/ Disallow: /_ops/ Disallow: /logs/ Disallow: /tmp/ Disallow: /cache/ Disallow: /vendor/ Disallow: /config/ Disallow: /private/ Disallow: /internal/ Disallow: /storage/ # Session, preview and tracking parameters (duplicate URLs) Disallow: /*?*session= Disallow: /*?*sessionid= Disallow: /*?*sid= Disallow: /*?*token= Disallow: /*?*auth= Disallow: /*?*preview= Disallow: /*?*debug= Disallow: /*?*internal= Disallow: /*?*admin= # Public files: styles, scripts, images, fonts and media stay readable Allow: /build/ Allow: /images/ Allow: /fonts/ Allow: /favicon Allow: /storage/blog/ Allow: /storage/seo/ Allow: /storage/about/ Allow: /storage/site/ Allow: /storage/videos/ # ------------------------------------------------------------ # IMAGE, VIDEO AND LINK-PREVIEW CRAWLERS # ------------------------------------------------------------ User-agent: Googlebot-Image User-agent: Googlebot-Video User-agent: Storebot-Google User-agent: BingPreview User-agent: msnbot-media User-agent: LinkedInBot User-agent: Twitterbot User-agent: facebookexternalhit User-agent: WhatsApp User-agent: Slackbot Allow: / # Private, signed-in and non-search areas Disallow: /admin/ Disallow: /account Disallow: /login Disallow: /logout Disallow: /register Disallow: /forgot-password Disallow: /reset-password Disallow: /portal/ Disallow: /vd-talk/ Disallow: /captcha/ Disallow: /sanctum/ Disallow: /country Disallow: /search # The same pages under each country (doc 37: /in/login, /us/account...) Disallow: /*/account Disallow: /*/login Disallow: /*/register Disallow: /*/forgot-password Disallow: /*/reset-password Disallow: /*/search Disallow: /*/privacy-choices Disallow: /newsletter/ Disallow: /webhooks/ Disallow: /payment/ Disallow: /api/ Disallow: /ajax/ Disallow: /cron/ Disallow: /_ops/ Disallow: /logs/ Disallow: /tmp/ Disallow: /cache/ Disallow: /vendor/ Disallow: /config/ Disallow: /private/ Disallow: /internal/ Disallow: /storage/ # Session, preview and tracking parameters (duplicate URLs) Disallow: /*?*session= Disallow: /*?*sessionid= Disallow: /*?*sid= Disallow: /*?*token= Disallow: /*?*auth= Disallow: /*?*preview= Disallow: /*?*debug= Disallow: /*?*internal= Disallow: /*?*admin= # Public files: styles, scripts, images, fonts and media stay readable Allow: /build/ Allow: /images/ Allow: /fonts/ Allow: /favicon Allow: /storage/blog/ Allow: /storage/seo/ Allow: /storage/about/ Allow: /storage/site/ Allow: /storage/videos/ # ------------------------------------------------------------ # AI SEARCH AND AI ASSISTANTS # OpenAI (ChatGPT search, ChatGPT, GPTBot), Anthropic (Claude), # Perplexity, Meta AI, Mistral (Le Chat), Amazon, DuckAssist, # Common Crawl (used by many AI models), Cohere, You.com # ------------------------------------------------------------ User-agent: OAI-SearchBot User-agent: ChatGPT-User User-agent: GPTBot User-agent: ClaudeBot User-agent: Claude-SearchBot User-agent: Claude-User User-agent: PerplexityBot User-agent: Perplexity-User User-agent: Meta-ExternalAgent User-agent: Meta-ExternalFetcher User-agent: MistralAI-User User-agent: Amazonbot User-agent: DuckAssistBot User-agent: CCBot User-agent: cohere-ai User-agent: YouBot Allow: / # Private, signed-in and non-search areas Disallow: /admin/ Disallow: /account Disallow: /login Disallow: /logout Disallow: /register Disallow: /forgot-password Disallow: /reset-password Disallow: /portal/ Disallow: /vd-talk/ Disallow: /captcha/ Disallow: /sanctum/ Disallow: /country Disallow: /search # The same pages under each country (doc 37: /in/login, /us/account...) Disallow: /*/account Disallow: /*/login Disallow: /*/register Disallow: /*/forgot-password Disallow: /*/reset-password Disallow: /*/search Disallow: /*/privacy-choices Disallow: /newsletter/ Disallow: /webhooks/ Disallow: /payment/ Disallow: /api/ Disallow: /ajax/ Disallow: /cron/ Disallow: /_ops/ Disallow: /logs/ Disallow: /tmp/ Disallow: /cache/ Disallow: /vendor/ Disallow: /config/ Disallow: /private/ Disallow: /internal/ Disallow: /storage/ # Session, preview and tracking parameters (duplicate URLs) Disallow: /*?*session= Disallow: /*?*sessionid= Disallow: /*?*sid= Disallow: /*?*token= Disallow: /*?*auth= Disallow: /*?*preview= Disallow: /*?*debug= Disallow: /*?*internal= Disallow: /*?*admin= # Public files: styles, scripts, images, fonts and media stay readable Allow: /build/ Allow: /images/ Allow: /fonts/ Allow: /favicon Allow: /storage/blog/ Allow: /storage/seo/ Allow: /storage/about/ Allow: /storage/site/ Allow: /storage/videos/ # ------------------------------------------------------------ # AI USE CONTROLS (not crawlers; they allow AI products to use # public pages crawled by Googlebot and Applebot) # Google-Extended: Gemini and Vertex AI grounding # Applebot-Extended: Apple Intelligence # ------------------------------------------------------------ User-agent: Google-Extended User-agent: Applebot-Extended Allow: / # Private, signed-in and non-search areas Disallow: /admin/ Disallow: /account Disallow: /login Disallow: /logout Disallow: /register Disallow: /forgot-password Disallow: /reset-password Disallow: /portal/ Disallow: /vd-talk/ Disallow: /captcha/ Disallow: /sanctum/ Disallow: /country Disallow: /search # The same pages under each country (doc 37: /in/login, /us/account...) Disallow: /*/account Disallow: /*/login Disallow: /*/register Disallow: /*/forgot-password Disallow: /*/reset-password Disallow: /*/search Disallow: /*/privacy-choices Disallow: /newsletter/ Disallow: /webhooks/ Disallow: /payment/ Disallow: /api/ Disallow: /ajax/ Disallow: /cron/ Disallow: /_ops/ Disallow: /logs/ Disallow: /tmp/ Disallow: /cache/ Disallow: /vendor/ Disallow: /config/ Disallow: /private/ Disallow: /internal/ Disallow: /storage/ # Session, preview and tracking parameters (duplicate URLs) Disallow: /*?*session= Disallow: /*?*sessionid= Disallow: /*?*sid= Disallow: /*?*token= Disallow: /*?*auth= Disallow: /*?*preview= Disallow: /*?*debug= Disallow: /*?*internal= Disallow: /*?*admin= # Public files: styles, scripts, images, fonts and media stay readable Allow: /build/ Allow: /images/ Allow: /fonts/ Allow: /favicon Allow: /storage/blog/ Allow: /storage/seo/ Allow: /storage/about/ Allow: /storage/site/ Allow: /storage/videos/ # ------------------------------------------------------------ # SITEMAPS # ------------------------------------------------------------ Sitemap: https://vdhosts.com/sitemap.xml Sitemap: https://vdhosts.com/news-sitemap.xml