# pietergort.github.io crawl policy
# Map: https://pietergort.github.io/llms.txt
# Brief: https://pietergort.github.io/machine.md
#
# Search / user-fetch bots → full site (find + quote).
# Training / data-collection bots → machine discovery paths only.

User-agent: *
Allow: /

Sitemap: https://pietergort.github.io/sitemap.xml

# --- Search / live citation / user-initiated fetch ---
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

# --- Training / foundation-model data collection (machine paths only) ---
# Longest-match Allow wins over Disallow: / on major crawlers.
User-agent: GPTBot
Allow: /machine
Allow: /llms
Allow: /.well-known/
Disallow: /

User-agent: ClaudeBot
Allow: /machine
Allow: /llms
Allow: /.well-known/
Disallow: /

User-agent: Google-Extended
Allow: /machine
Allow: /llms
Allow: /.well-known/
Disallow: /

User-agent: Applebot-Extended
Allow: /machine
Allow: /llms
Allow: /.well-known/
Disallow: /

User-agent: CCBot
Allow: /machine
Allow: /llms
Allow: /.well-known/
Disallow: /

User-agent: meta-externalagent
Allow: /machine
Allow: /llms
Allow: /.well-known/
Disallow: /

User-agent: Bytespider
Allow: /machine
Allow: /llms
Allow: /.well-known/
Disallow: /