# Walkie Talkie — robots.txt
#
# Standard search-engine crawlers are welcome — POI / city / venue
# pages benefit from being indexed by Google, Bing, DuckDuckGo, etc.
# That's the SEO moat.
#
# AI training crawlers are NOT welcome. The curated venue content
# (theme parks, zoos, exhibitions, highlights, route prompts) is
# the result of significant human + editorial work and we don't
# consent to it being used to train commercial LLMs without a
# licensing agreement.
#
# This file signals intent. Well-behaved bots respect it; bad
# actors don't. For the bad-actor case server-side rate limiting +
# IP throttling is the second layer (see server/middleware).

# ─── Allow normal search indexing ────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Slurp
Allow: /

# ─── Block AI training crawlers ──────────────────────────────────
# OpenAI
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

# Anthropic
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Google's "extended" crawler — separate opt-out from Googlebot so
# you can keep search indexing while denying Gemini training data.
User-agent: Google-Extended
Disallow: /

# Common Crawl — feeds many other LLMs downstream
User-agent: CCBot
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

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

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

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: meta-externalagent
Disallow: /

# Amazon
User-agent: Amazonbot
Disallow: /

# Apple (general LLM training crawler, distinct from Applebot for
# Siri/Spotlight which IS allowed above)
User-agent: Applebot-Extended
Disallow: /

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

# Other AI scrapers
User-agent: Diffbot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

# ─── Default ──────────────────────────────────────────────────────
# Everything else not explicitly listed above is allowed by default.
# Adjust if you want a stricter posture.

# Sitemap. The prerender step (scripts/prerender.mjs) replaces this
# placeholder line in dist/robots.txt with the real Sitemap: URL,
# stamped from SITE_URL. Keep the leading "# " — it's the regex
# anchor the replacement matches on.
Sitemap: https://walkietalkie.guide/sitemap.xml