# robots.txt
# https://geo-scanner.ccie13192.com
#
# NOTE: This site is itself a Generative Engine Optimization (GEO) product.
# AI crawlers are explicitly welcome here - being readable by LLMs is the point.

# ---------------------------------------------------------------
# AI / LLM crawlers - explicitly allowed
# Keep this list up to date. It doubles as the crawler list our
# own scanner checks against.
# ---------------------------------------------------------------

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google (AI training / grounding opt-in; Googlebot itself follows *)
User-agent: Google-Extended
Allow: /

# Apple
User-agent: Applebot-Extended
Allow: /

# ByteDance / Doubao
User-agent: Bytespider
Allow: /

# Common Crawl
User-agent: CCBot
Allow: /

# Meta
User-agent: meta-externalagent
Allow: /

# ---------------------------------------------------------------
# Traditional search engines
# ---------------------------------------------------------------

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# ---------------------------------------------------------------
# Everything else
# ---------------------------------------------------------------

User-agent: *
Allow: /

# Scan result pages are user-specific and thin - keep them out of the index.
Disallow: /report/

# API endpoints
Disallow: /api/

Sitemap: https://geo-scanner.ccie13192.com/sitemap.xml