# havelalights.com — robots.txt
# Lighting & home decor. All legitimate crawlers welcome.
# Agent instructions: https://havelalights.com/agents.md
# UCP discovery: https://havelalights.com/.well-known/ucp
# UCP/MCP endpoint: https://havelalights.com/api/ucp/mcp

# -------------------------------------------------------
# GENERAL CRAWLERS
# -------------------------------------------------------
User-agent: *
Allow: /
Allow: /products/
Allow: /collections/
Allow: /pages/
Allow: /blogs/

# Private / transactional
Disallow: /admin
Disallow: /cart/
Disallow: /*/cart/
Disallow: /checkout
Disallow: /*/checkout
Disallow: /checkouts/
Disallow: /*/checkouts/
Disallow: /orders
Disallow: /*/orders
Disallow: /account
Disallow: /*/account
Allow: /account/login
Allow: /*/account/login
Disallow: /93050634575
Disallow: /cdn/wpm/*.js
Disallow: /services
Disallow: /sf_*
Disallow: /cart.js
Disallow: /*/cart.js
Disallow: /recommendations/products

# Crawl traps
Disallow: /collections/*sort_by*
Disallow: /*/collections/*sort_by*
Disallow: /collections/*+*
Disallow: /collections/*%2B*
Disallow: /collections/*%2b*
Disallow: /collections/*filter*&*filter*
Disallow: /*?*oseid=*
Disallow: /*?*preview_theme_id=*
Disallow: /*?*preview_script_id=*

# -------------------------------------------------------
# GOOGLE
# -------------------------------------------------------
User-agent: Googlebot
Allow: /products/
Allow: /collections/
Allow: /pages/
Allow: /blogs/

User-agent: adsbot-google
Allow: /products/
Allow: /*/products/
Allow: /collections/
Allow: /*/collections/
Allow: /pages/
Allow: /*/pages/
Allow: /blogs/
Allow: /*/blogs/
Disallow: /checkout
Disallow: /*/checkout
Disallow: /checkouts/
Disallow: /*/checkouts/
Disallow: /orders
Disallow: /*/orders
Disallow: /services
Disallow: /sf_*
Disallow: /93050634575
Disallow: /cdn/wpm/*.js

# -------------------------------------------------------
# AI ASSISTANTS & LLM CRAWLERS — explicitly allowed
# -------------------------------------------------------

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

# OpenAI browsing plugin
User-agent: ChatGPT-User
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Google Gemini / Bard
User-agent: Google-Extended
Allow: /

# Meta AI (Llama)
User-agent: FacebookBot
Allow: /

# Apple
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Microsoft Copilot / Bing AI
User-agent: bingbot
Allow: /

User-agent: msnbot
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Common Crawl (trains most open LLMs)
User-agent: CCBot
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Diffbot
User-agent: Diffbot
Allow: /

# -------------------------------------------------------
# SITEMAP
# -------------------------------------------------------
Sitemap: https://havelalights.com/sitemap.xml