# robots.txt — stateofhealth.net
# Policy: search engines and *answer* engines are welcome (they cite and link back).
# Bulk training crawlers that take the text without attribution are not.
# Last reviewed: 2026-08-31

# ---------------------------------------------------------------
# 1. Default: everything is open except the private areas
# ---------------------------------------------------------------
User-agent: *
Disallow: /geopolitics/admin/
Disallow: /geopolitics/api/
Disallow: /geopolitics/lib/
Disallow: /geopolitics/bin/
Disallow: /geopolitics/tests/
Disallow: /geopolitics/db/
Disallow: /geopolitics/docs/
Disallow: /*.backup-*$
Disallow: /*.bak$
Allow: /

# ---------------------------------------------------------------
# 2. Classic search crawlers — explicitly welcome
# ---------------------------------------------------------------
User-agent: Googlebot
Allow: /
Disallow: /geopolitics/admin/
Disallow: /geopolitics/api/

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /
Disallow: /geopolitics/admin/
Disallow: /geopolitics/api/

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: YandexBot
Allow: /

# ---------------------------------------------------------------
# 3. AI ANSWER engines — welcome. These fetch a page because a user
#    asked a question, and they show a source link in the answer.
# ---------------------------------------------------------------
User-agent: OAI-SearchBot
Allow: /
Disallow: /geopolitics/admin/

User-agent: ChatGPT-User
Allow: /
Disallow: /geopolitics/admin/

User-agent: Claude-User
Allow: /
Disallow: /geopolitics/admin/

User-agent: Claude-SearchBot
Allow: /
Disallow: /geopolitics/admin/

User-agent: PerplexityBot
Allow: /
Disallow: /geopolitics/admin/

User-agent: Perplexity-User
Allow: /
Disallow: /geopolitics/admin/

User-agent: MistralAI-User
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: DuckAssistBot
Allow: /

# ---------------------------------------------------------------
# 4. TRAINING crawlers — not permitted.
#    These harvest text into model weights without a citation link.
#    Ask first: contact@stateofhealth.net
# ---------------------------------------------------------------
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: Scrapy
Disallow: /

# ---------------------------------------------------------------
# 5. Machine-readable descriptions of this site
# ---------------------------------------------------------------
Sitemap: https://stateofhealth.net/sitemap.xml