User-agent: * Allow: / # Private / admin areas — not for indexing Disallow: /admin/ Disallow: /do/ Disallow: /cgi-bin/ Disallow: /include/ Disallow: /config/ Disallow: /error_log Disallow: /sample/ Disallow: /Prototype/ Disallow: /Template/ Disallow: /old/ Disallow: /bq-old/ Disallow: /uploads/pdf/ # Legacy e-commerce URLs (now redirected to contact-us.php) Disallow: /cart.php Disallow: /cart_bill.php Disallow: /cart_checkout.php Disallow: /cart_complete.php Disallow: /login.php Disallow: /sign_up.php Disallow: /update_password.php # Pagination (?pageno=N) is intentionally crawlable. We previously blocked # /*?*pageno= here, but Google still indexed those URLs from internal links — # and because robots.txt blocked the fetch, it could not read the rel=canonical # tag pointing to page 1. Result: GSC flagged "Indexed, though blocked by # robots.txt" and "Duplicate without user-selected canonical". Allowing the # crawl lets Google read the canonical (set in traffic-equip.php to ?typeID=N, # no pageno) and consolidate signals onto page 1. (2026-04-30 fix) # Block referral-spam parameter (e.g. ?from=xiaodiaomao.com) that Chinese SEO # spammers append to backlinks; Google was indexing them as separate URLs. # NOTE: We deliberately do NOT block ?utm_* — those are needed for ads + email # campaigns and are deduplicated by canonical tags. Disallow: /*?*from= # Explicit xiaodiaomao block — added 2026-04-28 because /?from=xiaodiaomao.com # was still showing 25 imp in GSC despite the generic *from= rule. Adding both # the explicit URL and a wildcard ensures Googlebot drops it on next crawl. Disallow: /?from=xiaodiaomao.com Disallow: /*xiaodiaomao* # AI crawlers — explicitly allowed (AEO/AIO) User-agent: GPTBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: PerplexityBot Allow: / User-agent: ClaudeBot Allow: / User-agent: Claude-Web Allow: / User-agent: Google-Extended Allow: / User-agent: anthropic-ai Allow: / User-agent: Applebot-Extended Allow: / User-agent: CCBot Allow: / User-agent: cohere-ai Allow: / User-agent: Amazonbot Allow: / User-agent: Bytespider Allow: / User-agent: FacebookBot Allow: / User-agent: Meta-ExternalAgent Allow: / # LLM guidance file (emerging standard, see llmstxt.org) Sitemap: https://www.muhibahholdings.com/sitemap.xml Sitemap: https://www.muhibahholdings.com/geo-sitemap.xml