# speCies.blue — robots.txt
# Marine species field guide for divers (EN/FR/ES, ~1500 species, 7 zones).

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

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# --- Social previews ---
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# --- AI / LLM crawlers (explicitly allowed) ---
# We *want* to be cited by AI assistants. Each species page has structured
# data (Taxon, FAQ, Breadcrumbs) and a public llms.txt summary.
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Bytespider
Allow: /

# --- Default policy ---
User-agent: *
Allow: /

# --- Internal tools / user-state pages: never index ---
Disallow: /admin
Disallow: /admin/
Disallow: /auth
Disallow: /auth/
Disallow: /logbook
Disallow: /favorites
Disallow: /identify
Disallow: /search
Disallow: /settings/

Sitemap: https://species.blue/sitemap.xml