# ============================================================ # robots.txt — Seetharkundu Resorts # https://www.seetharkunduresorts.com/robots.txt # # Seetharkundu Herbal Plantations & Health Resorts Pvt. Ltd. # Near Seetharkundu Waterfalls, Kollengode South, # Palakkad, Kerala — 678506 # # Last updated: 2025-05-01 # ============================================================ # ── DEFAULT: all well-behaved crawlers ─────────────────────── User-agent: * # Allow all public indexable pages Allow: / # ── Block partial / fragment include files ─────────────────── # These are PHP server-side includes, not standalone pages. # Crawling them returns incomplete HTML without or nav. Disallow: /footer.php Disallow: /menu.php Disallow: /booking-head.php Disallow: /community-guidelines-section.php Disallow: /grievance-redressal-section.php Disallow: /terms-of-service-section.php # ── Block admin, system, and utility paths ─────────────────── Disallow: /admin/ Disallow: /administrator/ Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /phpmyadmin/ Disallow: /cpanel/ Disallow: /cgi-bin/ Disallow: /tmp/ Disallow: /cache/ Disallow: /logs/ Disallow: /config/ Disallow: /.env Disallow: /.git/ Disallow: /.htaccess Disallow: /vendor/ Disallow: /node_modules/ # ── Block session and tracking query parameters ────────────── # Prevents duplicate content from URL parameter variants Disallow: /*?sessionid= Disallow: /*?PHPSESSID= Disallow: /*?utm_source= Disallow: /*?utm_medium= Disallow: /*?utm_campaign= Disallow: /*?ref= Disallow: /*?tracking= Disallow: /*?affiliate= # ── Block search result and form-action URLs ───────────────── Disallow: /*?search= Disallow: /*?q= Disallow: /*?s= Disallow: /search Disallow: /search/ # ── Block duplicate protocol/www variants ──────────────────── # Canonical is https://www.seetharkunduresorts.com # Non-www and HTTP versions redirect via server config. # Listed here as belt-and-suspenders for crawlers. # Sitemap location Sitemap: https://www.seetharkunduresorts.com/sitemap.xml # ── GOOGLEBOT specific rules ───────────────────────────────── User-agent: Googlebot Allow: / Disallow: /footer.php Disallow: /menu.php Disallow: /booking-head.php Disallow: /community-guidelines-section.php Disallow: /grievance-redressal-section.php Disallow: /terms-of-service-section.php Disallow: /admin/ Disallow: /cgi-bin/ Disallow: /.git/ Disallow: /*?PHPSESSID= Disallow: /*?utm_source= Disallow: /*?utm_medium= Disallow: /*?utm_campaign= # Allow Google to crawl CSS and JS for rendering Allow: /css/ Allow: /js/ Allow: /vendors/ Allow: /images/ Allow: /favicon/ # ── GOOGLEBOT-IMAGE specific rules ─────────────────────────── User-agent: Googlebot-Image Allow: /images/ Allow: /favicon/ # Block temporary/cache image directories Disallow: /tmp/ Disallow: /cache/ # ── GOOGLEBOT-VIDEO ────────────────────────────────────────── User-agent: Googlebot-Video Allow: / # ── BINGBOT (Microsoft) ────────────────────────────────────── User-agent: Bingbot Allow: / Disallow: /footer.php Disallow: /menu.php Disallow: /booking-head.php Disallow: /community-guidelines-section.php Disallow: /grievance-redressal-section.php Disallow: /terms-of-service-section.php Disallow: /admin/ Disallow: /cgi-bin/ Disallow: /.git/ Disallow: /*?PHPSESSID= Disallow: /*?utm_source= Crawl-delay: 5 # ── SLURP (Yahoo / Oath) ───────────────────────────────────── User-agent: Slurp Allow: / Disallow: /admin/ Disallow: /footer.php Disallow: /menu.php Disallow: /booking-head.php Disallow: /*?PHPSESSID= Crawl-delay: 10 # ── DUCKDUCKBOT ────────────────────────────────────────────── User-agent: DuckDuckBot Allow: / Disallow: /admin/ Disallow: /footer.php Disallow: /menu.php Disallow: /booking-head.php Crawl-delay: 10 # ── YANDEX (Russia) ────────────────────────────────────────── User-agent: YandexBot Allow: / Disallow: /admin/ Disallow: /footer.php Disallow: /menu.php Disallow: /booking-head.php Disallow: /*?PHPSESSID= Crawl-delay: 10 # ── BAIDU (China) ──────────────────────────────────────────── User-agent: Baiduspider Allow: / Disallow: /admin/ Disallow: /footer.php Disallow: /menu.php Crawl-delay: 15 # ── FACEBOOK / META crawlers ───────────────────────────────── # Needed for Open Graph previews (WhatsApp, Facebook shares) User-agent: facebookexternalhit Allow: / Disallow: /admin/ User-agent: Facebot Allow: / Disallow: /admin/ # ── TWITTER / X crawlers ───────────────────────────────────── User-agent: Twitterbot Allow: / Disallow: /admin/ # ── LINKEDINBOT ────────────────────────────────────────────── User-agent: LinkedInBot Allow: / Disallow: /admin/ # ── WHATSAPP link preview ──────────────────────────────────── User-agent: WhatsApp Allow: / # ── APPLEBOT (Siri / Spotlight) ────────────────────────────── User-agent: Applebot Allow: / Disallow: /admin/ Crawl-delay: 10 # ── BLOCK aggressive / harmful bots ───────────────────────── # These bots scrape content, harvest emails, or probe for # vulnerabilities. Block them entirely. User-agent: AhrefsBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: BLEXBot Disallow: / User-agent: serpstatbot Disallow: / User-agent: SEOkicks Disallow: / User-agent: ZoominfoBot Disallow: / User-agent: DataForSeoBot Disallow: / User-agent: PetalBot Disallow: / User-agent: Bytespider Disallow: / User-agent: CCBot Disallow: / User-agent: GPTBot Disallow: / User-agent: Claude-Web Disallow: / User-agent: anthropic-ai Disallow: / User-agent: cohere-ai Disallow: / User-agent: PerplexityBot Disallow: / User-agent: ia_archiver Disallow: / User-agent: Scrapy Disallow: / User-agent: wget Disallow: / User-agent: libwww-perl Disallow: / User-agent: python-requests Disallow: / # ============================================================ # Sitemap declaration (repeated for maximum compatibility) # ============================================================ Sitemap: https://www.seetharkunduresorts.com/sitemap.xml