# Main robots rules
User-agent: *
# Block Nuxt image assets
Disallow: /_nuxt/img/
# Block admin and utility pages
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /404
Disallow: /500
Disallow: /nomoretiers
Disallow: /search
Disallow: /events/newsevent
Disallow: /resources/forms/
Disallow: /vast-cash

# Block confirmation pages
Disallow: /cosmos-confirmation
Disallow: /deal-confirmation
Disallow: /demo-confirmation
Disallow: /entry-confirmation
Disallow: /event-confirmation
Disallow: /german-event-confirmation
Disallow: /live-demo-confirmation
Disallow: /lunch-confirmation
Disallow: /meeting-confirmation
Disallow: /partner-confirmation
Disallow: /partner-sko-confirmation
Disallow: /thank-you
Disallow: /thank-you/
Disallow: /trade-show-confirmation
Disallow: /vastronaut-confirmation

# Block search results, pagination, sorting, and filtering
Disallow: /*?query=
Disallow: /*?page=
Disallow: /*?sort=
Disallow: /*?filter=

# Block all Japanese pages by default
Disallow: /ja/

# Explicitly allow specific Japanese pages
Allow: /ja/contact
Allow: /ja/demo
Allow: /ja/personalized-demo
Allow: /ja/platform/dataengine
Allow: /ja/platform/database
Allow: /ja/platform/dataspace
Allow: /ja/platform/datastore
Allow: /ja/platform/overview
Allow: /ja/legal/support-services-terms
Allow: /ja/legal/end-user-services-and-license-agreement
Allow: /ja/solutions
Allow: /ja/whitepaper
Allow: /ja$

# Special handling for social media crawlers
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# Block AI crawlers
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: OmigiliBot
Disallow: /

User-agent: Omigili
Disallow: /

# Sitemap
Sitemap: https://www.vastdata.com/sitemap.xml