# UPPIT.nl robots.txt
# https://www.uppit.nl/robots.txt
# Last updated: 2026-05-01
#
# Sitemap: https://www.uppit.nl/sitemap.xml
# LLMs guide: https://www.uppit.nl/llms.txt
# More info: https://www.uppit.nl/

# ====================================================================
# DEFAULT — alle crawlers mogen alles, behalve POST API endpoints
# ====================================================================
User-agent: *
Allow: /
Disallow: /api/contact
Disallow: /api/ai-scan
Disallow: /api/og/
Disallow: /404

# ====================================================================
# MAJOR SEARCH ENGINES — uitdrukkelijk welkom
# ====================================================================
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /services/
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: Yandex
Allow: /

User-agent: Baiduspider
Allow: /

# ====================================================================
# AI CRAWLERS — expliciet toegestaan zodat UPPIT geciteerd wordt in AI antwoorden
# (cruciaal voor GEO / Generative Engine Optimization)
# ====================================================================

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

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic / Claude
User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

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

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

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

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: FacebookBot
Allow: /

# Andere LLM crawlers
User-agent: cohere-ai
Allow: /

User-agent: YouBot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Diffbot
Allow: /

User-agent: ImagesiftBot
Allow: /

# ====================================================================
# SOCIAL PREVIEW BOTS — voor link previews op LinkedIn, Twitter, WhatsApp etc.
# ====================================================================
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: Slackbot
Allow: /

User-agent: TelegramBot
Allow: /

User-agent: Discordbot
Allow: /

# ====================================================================
# SEO & MARKETING TOOLS — toegestaan
# ====================================================================
User-agent: AhrefsBot
Allow: /

User-agent: SemrushBot
Allow: /

User-agent: MJ12bot
Allow: /

# ====================================================================
# SITEMAP DISCOVERY
# ====================================================================
Sitemap: https://www.uppit.nl/sitemap.xml

# ====================================================================
# HOST DECLARATION (Yandex / sommige crawlers)
# ====================================================================
Host: https://www.uppit.nl