# ⚠️ FICHIER GÉNÉRÉ — NE PAS MODIFIER À LA MAIN.
# Source : packages/seo/robots.ts + packages/seo/bots-ia.ts · Régénérer : pnpm sync:calendriers
#
# 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.

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Robots d'IA : un bloc nommé chacun, autorisés (recherche, agents utilisateurs ET entraînement).
# Un robot qui a son bloc ignore le groupe « * » : chaque bloc reprend donc les interdits.

# OpenAI — entraînement
User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# OpenAI — recherche
User-agent: OAI-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# OpenAI — agent utilisateur
User-agent: ChatGPT-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Anthropic — entraînement
User-agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Anthropic — recherche
User-agent: Claude-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Anthropic — agent utilisateur
User-agent: Claude-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Anthropic — entraînement
User-agent: anthropic-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Perplexity — recherche
User-agent: PerplexityBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Perplexity — agent utilisateur
User-agent: Perplexity-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Google — entraînement (jeton robots.txt, pas un robot)
User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Google — entraînement
User-agent: GoogleOther
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# DuckDuckGo — agent utilisateur
User-agent: DuckAssistBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Mistral AI — agent utilisateur
User-agent: MistralAI-User
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Mistral AI — recherche
User-agent: MistralAI-Index
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Mistral AI — entraînement
User-agent: MistralAI-Training
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Meta — entraînement
User-agent: meta-externalagent
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Meta — agent utilisateur
User-agent: meta-externalfetcher
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Amazon — recherche
User-agent: Amazonbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Apple — entraînement (jeton robots.txt, pas un robot)
User-agent: Applebot-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# You.com — recherche
User-agent: YouBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Cohere — entraînement
User-agent: cohere-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Common Crawl — entraînement
User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# ByteDance — entraînement
User-agent: Bytespider
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Exa — recherche
User-agent: ExaSearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Exa — agent utilisateur
User-agent: ExaUser
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# DeepSeek — recherche
User-agent: DeepSeekBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# ElevenLabs — agent utilisateur
User-agent: ElevenlabsBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /rapport/
Disallow: /api/
Disallow: /diagnostic/?

# Outils SEO et aspirateurs : exclus de tout le site (KST-2666). robots.txt ne lie que les
# robots polis ; le refus effectif est au middleware (remup) et au WAF (docs/seo/anti-aspiration-waf.md).
User-agent: AhrefsBot
User-agent: AhrefsSiteAudit
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: DataForSeoBot
User-agent: BLEXBot
User-agent: PetalBot
Disallow: /

Sitemap: https://valorup.fr/sitemap.xml