# 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.

# BEGIN Cloudflare Managed content


User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# ===== robots.txt — vu-magazine.com =====
# Politique : on autorise tous les bots des moteurs de recherche
# ET les bots IA qui citent leurs sources (ClaudeBot, GPTBot, Perplexity, Google-Extended).
# On bloque les bots SEO concurrentiels et le scraping agressif.
# Dernière mise à jour : 21 mai 2026

# ─── Tous les crawlers généraux ───
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /api/*
Disallow: /*?session=
Disallow: /*?utm_*

# ─── Bots IA — Autorisés (présence dans les LLMs en 2026) ───
# ChatGPT (OpenAI)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Claude (Anthropic)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google AI (Gemini, AI Overviews, SGE)
User-agent: Google-Extended
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# Mistral / Le Chat (français, important !)
User-agent: MistralAI-User
Allow: /

# ─── Bots SEO concurrentiels — Bloqués ───
# (Ils scrapent ton contenu pour la concurrence sans rien apporter)
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

# ─── Scrapers agressifs ───
User-agent: PetalBot
Disallow: /

User-agent: SeekportBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# ─── Sitemap ───
Sitemap: https://vu-magazine.com/sitemap.xml
Sitemap: https://vu-magazine.com/news-sitemap.xml

# ─── GEO : fichier de contexte pour les LLMs ───
# https://vu-magazine.com/llms.txt