# robots.txt for https://beany.app/
# Goal: allow every search and AI crawler full access, expose the sitemap.
#
# The wildcard block below already permits all crawlers. The named AI-agent
# blocks are for documentation and to override any restrictive default that a
# CMS or CDN might add later. A named User-agent block fully replaces the
# wildcard for that agent, so each is given explicit full access.
#
# Note: Google-Extended and Applebot-Extended govern whether your content may
# be used to TRAIN Google's and Apple's AI models. Allowing them opts Beany in.
# For AI visibility this is usually desirable. Remove those two blocks if you
# want to be retrievable but not used for training.

User-agent: *
Allow: /
Disallow: /contao/

# --- OpenAI / ChatGPT ---
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# --- Anthropic / Claude ---
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

# --- Perplexity ---
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# --- Google (Gemini / Vertex training token) ---
User-agent: Google-Extended
Allow: /

# --- Apple (Siri, Spotlight, Apple Intelligence) ---
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# --- Common Crawl (feeds many open models) ---
User-agent: CCBot
Allow: /

# --- DuckDuckGo assistant ---
User-agent: DuckAssistBot
Allow: /

Sitemap: https://beany.app/sitemap.xml
Sitemap: https://beany.app/sitemaps/sitemap-users.xml
Sitemap: https://beany.app/sitemaps/sitemap-cities.xml
Sitemap: https://beany.app/sitemaps/sitemap-shops.xml
Sitemap: https://beany.app/sitemaps/sitemap-roasters.xml
Sitemap: https://beany.app/sitemaps/sitemap-lists.xml
Sitemap: https://beany.app/sitemaps/sitemap-events.xml
Sitemap: https://beany.app/sitemaps/sitemap-countries.xml