# robots.txt
# State: PRIVATE — indexing is refused via X-Robots-Tag and meta robots, deliberately NOT via Disallow here (see comment in src/pages/robots.txt.ts).
#
# This file stays permissive in both states. A blanket "Disallow: /" would
# stop crawlers from reading our noindex directive, producing unremovable
# URL-only search listings. Indexing is refused at the response layer.
#
# Policy: allow search and user-initiated crawlers, block training crawlers.
# robots.txt groups are never merged, so each token below stands alone.

# ---------- Search crawlers: allowed ----------

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Google-InspectionTool
Allow: /

User-agent: bingbot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Applebot
Allow: /

User-agent: Amzn-SearchBot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

# ---------- Link preview bots: allowed ----------

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: Slackbot-LinkExpanding
Allow: /

# ---------- Training crawlers: blocked ----------
# Costs no search visibility. Google states Google-Extended "does not impact
# a site's inclusion in Google Search"; Apple states an Applebot-Extended
# opt-out keeps content discoverable in Spotlight, Siri and Safari.

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: meta-externalfetcher
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

# ---------- Default ----------

User-agent: *
Allow: /

Sitemap: https://anuarnurkenov.com/sitemap-index.xml