# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

User-agent: *
Allow: /

# Block admin and private routes (also enforced by middleware auth, but
# explicit Disallow keeps Google from wasting crawl budget on them).
Disallow: /admin/
Disallow: /org/
Disallow: /api/
Disallow: /reset-password
Disallow: /invite/

# Locale-aware versions of the same private routes — middleware redirects
# to /uk/admin etc., and Google would otherwise crawl them via that path.
Disallow: /uk/admin/
Disallow: /uk/org/
Disallow: /uk/profile
Disallow: /uk/reset-password
Disallow: /uk/invite/
Disallow: /en/admin/
Disallow: /en/org/
Disallow: /en/profile
Disallow: /en/reset-password
Disallow: /en/invite/
Disallow: /pl/admin/
Disallow: /pl/org/
Disallow: /pl/profile
Disallow: /pl/reset-password
Disallow: /pl/invite/
Disallow: /ro/admin/
Disallow: /ro/org/
Disallow: /ro/profile
Disallow: /ro/reset-password
Disallow: /ro/invite/

# ── AI / LLM crawlers — explicitly allowed ────────────────────────────────────
# All public calendar, event and destination pages are open for indexing.
# Explicit Allow overrides any ambiguity from the private-route Disallows above.

# OpenAI (ChatGPT, GPT plugins)
User-agent: GPTBot
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /
User-agent: anthropic-ai
Allow: /

# Google (Gemini, AI Overviews, Vertex AI)
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Meta (LLaMA, Ray-Ban AI, Meta AI)
User-agent: Meta-ExternalAgent
Allow: /
User-agent: FacebookBot
Allow: /

# Microsoft / Bing (Copilot)
User-agent: bingbot
Allow: /

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

# Common Crawl (used by many open-source LLMs for training data)
User-agent: CCBot
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Apple (Siri, Spotlight, Mail link previews)
User-agent: Applebot
Allow: /
User-agent: Applebot-Extended
Allow: /

Sitemap: https://startlek.com/sitemap.xml