# robots.txt for xingvei.com
User-agent: *
Allow: /

# Canonical host/path hints for crawlers (helps reduce URL-state drift in GSC)
Host: xingvei.com

Disallow: /admin
Disallow: /auth
Disallow: /cart
Disallow: /api/
Disallow: /*.json

# Keep legacy query URLs crawlable so bots can follow server-side redirects
# to canonical clean paths instead of staying in "blocked by robots.txt".
Allow: /*?*lang=
Allow: /*?*category=
Allow: /*?*utm_
Allow: /*?*gclid=
Allow: /*?*fbclid=
Allow: /*?*msclkid=

# Keep query-parameter URLs crawlable so bots can follow edge redirects
# to canonical paths and avoid persistent "blocked by robots.txt" states
# in Search Console for duplicate URLs.
Allow: /categories/
Allow: /categories/*
Disallow: /*?*token=
Disallow: /*?*session=

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

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: meta-externalagent
Disallow: /

Sitemap: https://xingvei.com/sitemap.xml