# Main robots rules
User-agent: *
# Block Nuxt assets
Disallow: /_nuxt/
# Block admin and utility pages
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /404
Disallow: /500
Disallow: /nomoretiers
Disallow: /search
Disallow: /events/newsevent
# Block ONLY the literal `/resources/forms/` redirect URL (it 302s to
# `/resources` and has no useful content). The trailing `$` anchors the
# match to the end of the path so deeper gated-form pages like
# `/resources/forms/analyst-papers/` remain crawler-allowed and are
# included in sitemap.xml. Supported by Googlebot, Bingbot, and most
# major crawlers per the robots.txt extended spec.
Disallow: /resources/forms/$
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: /
# Sitemap
Sitemap: https://www.vastdata.com/sitemap.xml