# robots.txt for The Men's Clinic (Houston, TX)
# Crawl public service + content pages. Disallow admin, API, and any
# noindex pages so they never reach the index in the first place.
#
# AI assistants (ChatGPT, Claude, Gemini, Perplexity, Copilot) are
# EXPLICITLY WELCOME — being cited when Houston men ask about ED treatment,
# TRT, or men's health clinics is a lead source. See also /llms.txt.

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /admin/tracking
Disallow: /api/
Disallow: /data-deletion

# --- OpenAI (ChatGPT answers, ChatGPT search, model training) ---
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# --- Anthropic (Claude answers + training) ---
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

# --- Google (Gemini + AI Overviews grounding) ---
User-agent: Google-Extended
Allow: /

# --- Perplexity ---
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# --- Common Crawl (training corpus used by many models) ---
User-agent: CCBot
Allow: /

# --- Others (Copilot uses Bingbot, allowed via *; Meta AI; Apple Intelligence; Amazon/Alexa) ---
User-agent: meta-externalagent
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Allow: /

# Aggressive scrapers we get no benefit from
User-agent: Bytespider
Disallow: /

Sitemap: https://themensclinic.com/sitemap.xml