# 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: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content


# Robots policy to reduce crawl pressure while allowing good bots reasonable access
Sitemap: https://www.olympiandatabase.com/sitemap/sitemap_index.xml

# Default rules for all crawlers
User-agent: *
# Noisy or resource-intensive paths
Disallow: /admin/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /api/
Disallow: /ajax/
Disallow: /search
Disallow: /search/
Disallow: /track/
# Common heavy query patterns
Disallow: /*?*debug=
Disallow: /*?*utm_
Disallow: /*?*session=
Disallow: /*?*sort=
Disallow: /*?*page=
Disallow: /*?*offset=
# Gentle crawl pace for bots that honor Crawl-delay (Google ignores this)
Crawl-delay: 8

# Googlebot: keep access broad; Google ignores Crawl-delay but we include for clarity
User-agent: Googlebot
Disallow: /admin/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /api/
Disallow: /ajax/
Disallow: /search
Disallow: /search/
Disallow: /track/
Crawl-delay: 2

# Bingbot: allow but limit pace modestly
User-agent: Bingbot
Disallow: /admin/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /api/
Disallow: /ajax/
Disallow: /search
Disallow: /search/
Disallow: /track/
Crawl-delay: 5

# DuckDuckBot: allow but limit pace modestly
User-agent: DuckDuckBot
Disallow: /admin/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /api/
Disallow: /ajax/
Disallow: /search
Disallow: /search/
Disallow: /track/
Crawl-delay: 5

# Qwantbot: slow down significantly
User-agent: Qwantbot
Disallow: /admin/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /api/
Disallow: /ajax/
Disallow: /search
Disallow: /search/
Disallow: /track/
Crawl-delay: 15

# PetalBot: slow down significantly
User-agent: PetalBot
Disallow: /admin/
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /api/
Disallow: /ajax/
Disallow: /search
Disallow: /search/
Disallow: /track/
Crawl-delay: 20

# Bytespider: block entirely (reduce pressure). Remove or relax if you prefer to allow it.
User-agent: Bytespider
Disallow: /

# ClaudeBot: slow down and avoid query-string crawling (reduces id-scanning)
User-agent: ClaudeBot
Disallow: /*?*
Crawl-delay: 20

# AhrefsBot: high load with low value; block
User-agent: AhrefsBot
Disallow: /

# DotBot (Moz): slow and avoid query-string crawling
User-agent: DotBot
Disallow: /*?*
Crawl-delay: 15

# DataForSeoBot: high-frequency SEO crawler; block
User-agent: DataForSeoBot
Disallow: /

# ChatGPT-User: allow but be very slow; avoid query-string crawling
User-agent: ChatGPT-User
Disallow: /*?*
Crawl-delay: 30

# Facebook crawler (used for link previews): allow
User-agent: facebookexternalhit
Allow: /

# Meta external agent alias observed in logs: allow
User-agent: meta-externalagent
Allow: /