# robots.txt voor nd.nl
# Laatst bijgewerkt: 2 juni 2026
# Blokkering AI scrapers en trainingsdata crawlers

# =========================
# DEFAULT: Global preferences
# Nederlands Dagblad allows search indexing, but no real-time retrieval, no AI training.
# =========================

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

# ====================
# OPENAI
# ====================
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

# ====================
# ANTHROPIC / CLAUDE
# ====================
User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

# ====================
# GOOGLE AI
# ====================
User-agent: Google-Extended
Disallow: /

# ====================
# META / FACEBOOK
# ====================
User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

# ====================
# PERPLEXITY
# ====================
User-agent: PerplexityBot
Disallow: /

# ====================
# CHINESE AI SCRAPERS
# ====================
User-agent: DeepSeekBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Baiduspider
Disallow: /

# ====================
# OVERIGE AI SCRAPERS
# ====================
User-agent: CCBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: TrendictionBot
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: MyCentralAIScraperBot
Disallow: /