User-agent: * Disallow: /dashboard/ Disallow: /config/ Disallow: /classes/ Disallow: /vendor/ Disallow: /.htaccess Disallow: /*.php Disallow: /error_log Disallow: /*.sql Disallow: /*.env Disallow: /*.lock Disallow: /*.json Disallow: /maintenance/ Disallow: /sql/ Disallow: /backups/ Disallow: /uploads/temp/ # Prevent crawling of legacy AMP company URLs (redirected to /amp/company/ pattern) # Old pattern was causing 118,000+ GSC duplicate canonical issues Disallow: /company/*/amp # Crawl budget hardening: block utility/auth/account/transaction routes. Disallow: /login Disallow: /register Disallow: /forgot-password Disallow: /reset-password Disallow: /verify-email Disallow: /verify-email-pending Disallow: /logout Disallow: /account/ Disallow: /search/analytics Disallow: /user-settings Disallow: /subscribe-checkout Disallow: /subscribe-success Disallow: /subscribe-cancel Disallow: /add-business # Crawl budget hardening: tracking/noise query parameters. Disallow: /*utm_ Disallow: /*gclid= Disallow: /*fbclid= Disallow: /*_ga= Disallow: /*manual_search= # Block suspicious user agents and vulnerability scanners User-agent: MJ12bot Disallow: / User-agent: AhrefsBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: DotBot Disallow: / User-agent: MagicBot Disallow: / User-agent: YandexBot Disallow: / # Explicitly keep /dashboard/ blocked for named crawlers, while allowing public pages. User-agent: GPTBot Disallow: /dashboard/ Allow: / User-agent: ChatGPT-User Disallow: /dashboard/ Allow: / User-agent: Claudebot Disallow: /dashboard/ Allow: / User-agent: anthropic-ai Disallow: /dashboard/ Allow: / User-agent: PerplexityBot Disallow: /dashboard/ Allow: / User-agent: perplexity-ai Disallow: /dashboard/ Allow: / User-agent: CCBot Disallow: /dashboard/ Allow: / User-agent: Copilot Disallow: /dashboard/ Allow: / User-agent: copilotbot Disallow: /dashboard/ Allow: / User-agent: Googlebot Disallow: /dashboard/ Disallow: /account/ Disallow: /search/analytics Disallow: /login Disallow: /register Disallow: /forgot-password Disallow: /reset-password Disallow: /verify-email Disallow: /verify-email-pending Disallow: /logout Disallow: /user-settings Disallow: /subscribe-checkout Disallow: /subscribe-success Disallow: /subscribe-cancel Disallow: /add-business Disallow: /*utm_ Disallow: /*gclid= Disallow: /*fbclid= Disallow: /*_ga= Disallow: /*manual_search= Allow: / User-agent: Bingbot Disallow: /dashboard/ Disallow: /account/ Disallow: /search/analytics Disallow: /login Disallow: /register Disallow: /forgot-password Disallow: /reset-password Disallow: /verify-email Disallow: /verify-email-pending Disallow: /logout Disallow: /user-settings Disallow: /subscribe-checkout Disallow: /subscribe-success Disallow: /subscribe-cancel Disallow: /add-business Disallow: /*utm_ Disallow: /*gclid= Disallow: /*fbclid= Disallow: /*_ga= Disallow: /*manual_search= Allow: / User-agent: facebookexternalhit Disallow: /dashboard/ Allow: / User-agent: ia_archiver Disallow: /dashboard/ Allow: / User-agent: AppleBot Disallow: /dashboard/ Allow: / User-agent: AppleBot-Extended Disallow: /dashboard/ Allow: / User-agent: Bytespider Disallow: /dashboard/ Allow: / User-agent: DataForSeoBot Disallow: /dashboard/ Allow: / User-agent: Omgilibot Disallow: /dashboard/ Allow: / User-agent: Diffbot Disallow: /dashboard/ Allow: / Crawl-delay: 0 Request-rate: 100/1s # Sitemap index is the single authoritative entry; it lists every sub-sitemap # (static, companies, blog, categories, hs-codes, amp when enabled, ai-sitemap). Sitemap: https://www.haiuae.com/sitemap_index.xml