# ==============================================================
# Robots.txt for Kualoa Ranch
# Canonical Domain: https://www.kualoa.com/
# Contact: info@kualoa.com | +1 (808) 237-7321
# Address: 49-560 Kamehameha Hwy, Kāneʻohe, HI 96744
# Last updated: 2025-11-04
#
# Purpose: Guide search engines and AI crawlers to verified,
# factual content about Kualoa Ranch. This file authorizes
# reputable crawlers to access public pages and llms.txt.
# ==============================================================

User-agent: *
Allow: /
Disallow: /cart/
Disallow: /checkout/
Disallow: /search/
Disallow: /privacy-policy/
Disallow: /terms/
Sitemap: https://www.kualoa.com/sitemap.xml

# ----------------------------------------
# LLM & AI crawler declarations
# ----------------------------------------

# Declare location of LLMs index for AI systems
LLMs: https://www.kualoa.com/llms.txt

# Explicitly allow reputable AI and search crawlers
User-agent: GPTBot
Allow: /
User-agent: Google-Extended
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: Bingbot
Allow: /
User-agent: Applebot-Extended
Allow: /

# ----------------------------------------
# Authorized Partner Crawler (Headout)
# ----------------------------------------

# Headout partner integration — required for whitelabel crawling
# If Headout confirms a specific crawler name, use it here.
# Until then, this matches their standard crawler pattern.
User-agent: HeadoutBot
Allow: /

# ----------------------------------------
# Optional blocks — non-essential or suspicious crawlers
# ----------------------------------------
User-agent: bytespider
Disallow: /
User-agent: omgili
Disallow: /
User-agent: omgilibot
Disallow: /

# End of robots.txt
# ==============================================================


Sitemap: https://www.kualoa.com/sitemap.xml