# ZeusXR News — robots.txt
# https://news.zeusxr.com/robots.txt

# Default — allow everything for general crawlers
User-agent: *
Allow: /
Disallow: /editor/
Disallow: /editor
Disallow: /invite/
Disallow: /invite
Disallow: /*?slug=
Disallow: /*?token=

# ===== Search engines (allow) =====
User-agent: Googlebot
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Applebot
Allow: /

# ===== AI search agents (allow — they cite us with link) =====
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Bingbot-AI
Allow: /

# ===== AI training crawlers (block — we don't allow training without consent) =====
User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /editor/
Disallow: /invite/

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: cohere-ai
Disallow: /

# ===== Sitemaps =====
Sitemap: https://news.zeusxr.com/sitemap.xml
Sitemap: https://news.zeusxr.com/news-sitemap.xml

# Host directive (Yandex)
Host: https://news.zeusxr.com