# tkal.news — robots.txt
# Last updated: 2026-06-01
#
# POLICY: allow mainstream search + AI engines that CITE and send referral
# traffic; block bulk AI-TRAINING scrapers that take content and give nothing
# back. A bot obeys only the most specific group that names it; the
# "User-agent: *" group applies to bots not listed above.

# ---- Mainstream search engines (keep allowed — this is your discovery) ----
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# ---- AI answer engines that cite + drive referral traffic (allowed) ----
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

# ---- AI training / bulk scrapers (blocked — pure extraction, no traffic) ----
User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: PetalBot
Disallow: /

# ---- Everyone else may read the public site ----
User-agent: *
Allow: /

Sitemap: https://tkal.news/sitemap.xml