# 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

# Search engines standards (Google, Bing, DuckDuckGo, Yandex…)
User-agent: *
Allow: /
Disallow: /admin
Disallow: /admin/
Disallow: /api/
Disallow: /letter/      # noindex,follow : navigation interne, pas pour search
Disallow: /*?q=         # résultats recherche, noindex
Disallow: /*?p=         # paramètres pagination obsolètes (on utilise /page-N/)
Disallow: /*?city=
Disallow: /*?cat=
Disallow: /*?price_max=
Disallow: /*?promo=
Disallow: /*?top=

# === Bots IA / LLM training : BLOCK ===
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: DuckAssistBot
Disallow: /

User-agent: AwarioRssBot
Disallow: /

User-agent: AwarioSmartBot
Disallow: /

User-agent: Quora-Bot
Disallow: /

User-agent: Magpie-Crawler
Disallow: /

User-agent: Webzio-Extended
Disallow: /

# === Scrapers SEO commerciaux : BLOCK ===
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: SerendeputyBot
Disallow: /

User-agent: MegaIndex.ru
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: ZumBot
Disallow: /

User-agent: linkfluence
Disallow: /

User-agent: TurnitinBot
Disallow: /

# === Sitemaps ===
Sitemap: https://fapfapfap.net/sitemap-profils.xml
Sitemap: https://fapfapfap.net/sitemap-categories.xml
Sitemap: https://fapfapfap.net/sitemap-guides.xml