# Content-Signal: search=yes, ai-input=yes, ai-train=yes
# We allow search indexing and answer-engine grounding (AI input).
# Training on this content is permitted by default; bots that should
# not train (e.g. CCBot) are blocked below.

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /api/

# --- Major search-engine AI surfaces ---
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# Controls whether Google may use the content for Gemini / AI Overviews.
User-agent: Google-Extended
Allow: /

# --- Answer-engine and assistant crawlers ---
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Applebot-Extended
Allow: /

# --- Bulk dataset crawlers we do not consent to ---
User-agent: CCBot
Disallow: /

# --- Sitemaps for every locale/domain ---
Sitemap: https://www.horkovcesku.cz/sitemap-index-cs.xml
Sitemap: https://www.horucava.sk/sitemap-index-sk.xml
Sitemap: https://www.hitze-in-deutschland.de/sitemap-index-de.xml
Sitemap: https://www.hitze-in-oesterreich.at/sitemap-index-at.xml
Sitemap: https://www.upal-w-polsce.pl/sitemap-index-pl.xml