# MyHairMail robots.txt - optimized for SEO + LLM discovery (Shopify)

# ===== GLOBAL RULES (safe crawl, no sensitive pages) =====
User-agent: *
Disallow: /admin
Disallow: /cart
Disallow: /carts
Disallow: /checkouts/
Disallow: /checkout
Disallow: /orders
Disallow: /account
Disallow: /a/downloads/-/*
Disallow: /75395563833/checkouts
Disallow: /75395563833/orders
Disallow: /apple-app-site-association
Disallow: /.well-known/shopify/monorail
Disallow: /cdn/wpm/*.js
Disallow: /recommendations/products
Disallow: /*/recommendations/products

# Reduce duplicate URLs / faceted filters
# (Keep BOTH root and /*/ forms so English root & language folders are covered)
Disallow: /collections/*sort_by*
Disallow: /*/collections/*sort_by*
Disallow: /collections/*+*
Disallow: /collections/*%2B*
Disallow: /collections/*%2b*
Disallow: /*/collections/*+*
Disallow: /*/collections/*%2B*
Disallow: /*/collections/*%2b*
Disallow: */collections/*filter*&*filter*
Disallow: /blogs/*+*
Disallow: /blogs/*%2B*
Disallow: /blogs/*%2b*
Disallow: /*/blogs/*+*
Disallow: /*/blogs/*%2B*
Disallow: /*/blogs/*%2b*
Disallow: /*?*oseid=*
Disallow: /*?*variant=*
Disallow: /*preview_theme_id*
Disallow: /*preview_script_id*
Disallow: /search
Disallow: /*/search

# Block common tracking params to reduce duplicate crawl
Disallow: /*?*utm_*
Disallow: /*?*fbclid=*
Disallow: /*?*gclid=*
Disallow: /*?*msclkid=*
Disallow: /*?*sca_ref=*

# (Optional) If you want policy pages OUT of the index, uncomment:
# Disallow: /policies/
# Disallow: /*/policies/

# ===== SEARCH + AD CRAWLERS =====
User-agent: Googlebot
Allow: /

User-agent: AdsBot-Google
Allow: /
Disallow: /checkout
Disallow: /checkouts/
Disallow: /orders

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Pinterest
Crawl-delay: 1

# ===== SEO TOOLS =====
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: AhrefsSiteAudit
Crawl-delay: 10

User-agent: MJ12bot
Crawl-delay: 10

User-agent: Nutch
Disallow: /

# ===== BLOCKED AGGRESSIVE SCRAPERS (added 2026-06-10) =====
# Bytespider (ByteDance) drove a multi-million-session crawl flood with zero revenue.
# PetalBot (Huawei) blocked preventively.
User-agent: Bytespider
Disallow: /

User-agent: PetalBot
Disallow: /

# ===== AI / LLM DISCOVERY (opt-in for visibility) =====
# Group AI/LLM bots so Allow applies to all; delay is optional
# OpenAI: GPTBot (training/index), ChatGPT-User (user browsing), OAI-SearchBot (ChatGPT search)
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
# Anthropic: ClaudeBot (crawler), Claude-User (user browsing), Claude-SearchBot; Claude-Web = legacy
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: Claude-Web
# Perplexity: PerplexityBot (index), Perplexity-User (user browsing)
User-agent: PerplexityBot
User-agent: Perplexity-User
# Google AI training opt-in (Gemini browsing rides Googlebot, allowed above)
User-agent: Google-Extended
# Meta AI: crawler + user-fetch agent
User-agent: meta-externalagent
User-agent: Meta-ExternalFetcher
# Mistral user-fetch agent
User-agent: MistralAI-User
# Other AI indexes
User-agent: CCBot
User-agent: Amazonbot
User-agent: YouBot
Allow: /
Crawl-delay: 2


# ===== SITEMAPS (Shopify) =====
Sitemap: https://myhairmail.com/sitemap.xml