# ===================================================================== # NectarPlus Health – robots.txt # Goal: maximise Google's ability to crawl & index public SEO landing # pages while excluding private user flows, search/filter permutations, # and tracking-parameter variants that create duplicate content. # ===================================================================== User-agent: * Allow: / # --- Essential resources Googlebot needs to render the page --- Allow: /assets/ Allow: /*.css$ Allow: /*.js$ Allow: /*.mjs$ Allow: /*.json$ Allow: /*.svg$ Allow: /*.png$ Allow: /*.jpg$ Allow: /*.jpeg$ Allow: /*.webp$ Allow: /*.gif$ Allow: /*.ico$ Allow: /*.woff$ Allow: /*.woff2$ # --- Private / authenticated areas (no SEO value) --- # NOTE: /doctor/ and /hospital/ are the doctor & hospital portal dashboards. # Public SEO pages live at /:city/doctor/:slug and /:city/hospital/:slug # (city prefix), so they remain crawlable. Disallow: /auth/ Disallow: /register/ Disallow: /profile/ Disallow: /patient/ Disallow: /doctor/ Disallow: /hospital/ Disallow: /patient-login Disallow: /doctor-login Disallow: /hospital-login Disallow: /admin/ Disallow: /dashboard/ # --- Transactional flows that must not be indexed --- Disallow: /appointment-booking Disallow: /cancel-booking Disallow: /confirm-booking Disallow: /reschedule-booking Disallow: /appointment-completed Disallow: /payment/ Disallow: /checkout/ Disallow: /thank-you # Disallow subtopics across all cities AND bare URLs Disallow: /*/treatment/*/*/recovery Disallow: /*/treatment/*/*/procedure Disallow: /*/treatment/*/*/risks Disallow: /*/treatment/*/*/success-rate Disallow: /treatment/*/*/recovery Disallow: /treatment/*/*/procedure Disallow: /treatment/*/*/risks Disallow: /treatment/*/*/success-rate # --- DEPRECATED URL PATTERNS (removed from indexing June 2026) --- # /*/doctors-for-* was the old pattern for service/speciality search # Consolidated to /:city/:service pattern for cleaner URLs and better SEO # All old URLs now 301 redirect to new pattern. Block here to save crawl budget. Disallow: /*/doctors-for- # --- Excluded / Legally restricted medicine products --- Disallow: /medicines/details/103276* Disallow: /medicines/details/*amaryl-2-mg-tablet* # --- Internal search query URLs (low-value, infinite permutations) --- # Note: only block the bare /search entry point and any query-string variants. # /search-results is intentionally left crawlable so the in-page tag is honoured. Disallowing it would prevent Google from ever # seeing the noindex directive. Disallow: /search$ Disallow: /search? Disallow: /*?q= Disallow: /*?query= Disallow: /*?keyword= # --- Faceted filters & pagination (canonical points to base page) --- Disallow: /*?*page= Disallow: /*?*sort= Disallow: /*?*filter= Disallow: /*?*offset= Disallow: /*?*limit= # --- Tracking parameters (cause duplicate content) --- Disallow: /*?*utm_ Disallow: /*?*gclid= Disallow: /*?*fbclid= Disallow: /*?*msclkid= Disallow: /*?*ref= Disallow: /*?*sessionid= # --- API endpoints should never be indexed --- Disallow: /api/ # --- AI / answer-engine crawlers (GEO policy, July 2026) --- # GPTBot, OAI-SearchBot, ChatGPT-User (OpenAI), ClaudeBot (Anthropic), # PerplexityBot / Perplexity-User, Google-Extended (Gemini grounding), # CCBot (Common Crawl), meta-externalagent, Amazonbot, Applebot-Extended # are all INTENTIONALLY allowed. They inherit the `User-agent: *` group # above: public SEO pages crawlable, private/transactional flows blocked. # ⚠️ Do NOT add per-bot groups containing only `Allow: /` — a bot matching # its own group ignores every Disallow under `*`, which would expose # booking/auth flows to AI crawlers. If a bot must ever be blocked or # scoped, replicate the full Disallow list inside its group. # --- Be friendly to Google's image & video bots --- User-agent: Googlebot-Image Allow: /assets/ Allow: /*.png$ Allow: /*.jpg$ Allow: /*.jpeg$ Allow: /*.webp$ Allow: /*.svg$ # Google Ads crawlers ko main domain par block karein User-agent: AdsBot-Google User-agent: AdsBot-Google-Mobile User-agent: AdsBot-Google-Mobile-Apps User-agent: Google-Adwords-Instant Disallow: /medicines* # --- Sitemaps --- # The split sitemap-index is the only authoritative entry point. The legacy # single-file /sitemap.xml is kept routable for backward compatibility but is # no longer advertised here, to focus crawl budget on the chunked index. Sitemap: https://nectarplus.health/sitemap-index.xml