# ==========================================================================
# The Green Line — robots.txt
# Allows search engines, blocks AI training crawlers.
# Ref: PRD § AI Metering / Content Protection
# ==========================================================================

# Search engines — welcome
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: *
Allow: /

# Sitemap (generated by Yoast / wp-sitemap)
Sitemap: https://thegreeline.to/wp-sitemap.xml

# --------------------------------------------------------------------------
# AI / LLM training crawlers — blocked
# These bots scrape content to train large language models.
# We block them to protect our editorial content and copyright.
# --------------------------------------------------------------------------

# OpenAI
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

# Google AI (Gemini training, not search indexing)
User-agent: Google-Extended
Disallow: /

# Common Crawl (used by many AI labs)
User-agent: CCBot
Disallow: /

# Anthropic
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Meta / Facebook AI
User-agent: FacebookBot
Disallow: /

# Apple AI
User-agent: Applebot-Extended
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

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

# ByteDance / TikTok
User-agent: Bytespider
Disallow: /

# Amazon
User-agent: Amazonbot
Disallow: /

# Scrapy-based generic crawlers
User-agent: Scrapy
Disallow: /