# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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.

# ---------------------------------------------------------------------------
# AirNav Radar crawler policy
#
# Informational pages -- /about, /faq, /blog, the ADS-B and MLAT explainers, the
# product, hardware and API pages -- are open to every crawler, AI crawlers
# included. We would rather models know what AirNav Radar is than not.
#
# /data/ is not. It is millions of generated flight, aircraft, airport and
# airline pages: the bulk of the crawl cost and the asset we sell. AI crawlers
# are disallowed there. Search engines and user-directed AI fetches are not.
#
# ai-train is deliberately absent from every Content-Signal below. Per clause
# (c) above that neither grants nor restricts training rights, so nothing here
# waives the Article 4 reservation. Access, not signalling, carries the policy:
# content signals cannot be scoped to a path, ordinary robots.txt rules can.
#
# Machine-readable site summary for LLMs: https://www.airnavradar.com/llms.txt
# ---------------------------------------------------------------------------

# Everything not named below. Note that a named group REPLACES this one for that
# agent rather than adding to it, so the two replay endpoints have to be repeated
# in every group that is allowed to crawl the site. Disallow lines are listed
# before "Allow: /" on purpose: RFC 9309 requires longest-match, but parsers
# that match in file order need the narrower rule first to reach it.
User-agent: *
Content-Signal: search=yes,ai-input=yes,use=reference
Disallow: /data/getReplay
Disallow: /data/get-replay
Allow: /

# AI crawlers that collect for training. Free of the site except /data/.
# Google-Extended and Applebot-Extended are control tokens, not crawlers:
# Googlebot and Applebot still crawl /data/ for Search under the group above.
# Caveat on Google-Extended -- Google uses the one token for both Gemini
# training and Gemini grounding, so this also keeps /data/ out of grounded
# Gemini answers. Move it to its own group with "Allow: /" if being cited on
# flight pages is worth more than keeping them out of training.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: Bytespider
Content-Signal: search=yes,ai-input=yes,use=reference
Disallow: /data/
Allow: /

# Answer-time agents: search indexes for AI assistants, and fetches a user has
# explicitly asked for. These are the ones that cite us and send traffic, and
# they get /data/ too. Named explicitly so a future tightening of the wildcard
# group above cannot catch them by accident.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Content-Signal: search=yes,ai-input=yes,use=reference
Disallow: /data/getReplay
Disallow: /data/get-replay
Allow: /

# Cloudflare's Browser Rendering crawler, which third parties can point at any
# site through Cloudflare's API. Blocked outright, as it was under Cloudflare's
# managed robots.txt.
User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

Sitemap: https://www.airnavradar.com/sitemap.xml