# 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.


# ==================================================
# Content signals – EU Directive 2019/790
# ==================================================

User-agent: *
Content-signal: search=yes,ai-input=yes,ai-train=no
Sitemap: https://www.france-voyage.com/external/sitemaps/sitemap.xml
Allow: /
Disallow: /cgi-bin/
Disallow: /scripts/
Disallow: /audio/
Disallow: /partenaires/
Disallow: /transports/*?*
Disallow: /transport/*?*
Disallow: /frankreich-verkehr/*?*
Disallow: /trasporti/*?*
Disallow: /transportes/*?*
Disallow: /frankrijk-vervoer/*?*
Disallow: /admin*/
Disallow: /tmp/
Disallow: /*.pdf$


# ==================================================
# Major search engines
# ==================================================

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /


# ==================================================
# AI assistants – ALLOWED
# ==================================================

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

# Google Gemini / AI summaries
User-agent: Google-Extended
Allow: /


# ==================================================
# AI assistants – BLOCKED
# ==================================================

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Bytespider
Disallow: /


# ==================================================
# Commercial & SEO crawlers - RATE-LIMITED
# ==================================================

User-agent: AhrefsBot
Crawl-delay: 5

User-agent: SEMrushBot
Crawl-delay: 5

User-agent: MJ12bot
Crawl-delay: 5

User-agent: dotbot
Crawl-delay: 5

User-agent: AspiegelBot
Crawl-delay: 5

User-agent: PetalBot
Crawl-delay: 5

User-agent: MauiBot
Crawl-delay: 5