# Floorballing.com - robots.txt
# Last updated: 2026-06-17
# Maintained by: Pavel Brus / Floorballing s.r.o.
# Contact: pavel@floorballing.com

# Policy: ALLOW AI crawlers everywhere (we want to be cited).
# Block only repeat abusers (Bytespider, ImagesiftBot, PetalBot).
# Enforcement against bad bots is at WAF/Cloudflare layer.

# ─────────────────────────────────────────────────────────────
# AI SEARCH-TIME bots - explicit ALLOW
# These show citations in user-facing answers (high impact)
# ─────────────────────────────────────────────────────────────

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: YouBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: Diffbot
Allow: /

User-agent: DuckAssistBot
Allow: /

# ─────────────────────────────────────────────────────────────
# AI TRAINING crawlers - ALLOW (we want to be in next-gen models)
# ─────────────────────────────────────────────────────────────

User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: claude-web
Allow: /

User-agent: CCBot
Allow: /

User-agent: omgili
Allow: /

User-agent: FacebookBot
Allow: /

# ─────────────────────────────────────────────────────────────
# Conventional search engines - ALLOW
# ─────────────────────────────────────────────────────────────

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: SeznamBot
Allow: /

User-agent: ia_archiver
Allow: /

# ─────────────────────────────────────────────────────────────
# BLOCK aggressive / non-compliant bots
# ─────────────────────────────────────────────────────────────

User-agent: Bytespider
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: PetalBot
Disallow: /

# ─────────────────────────────────────────────────────────────
# DEFAULT
# ─────────────────────────────────────────────────────────────

User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /tmp/
Disallow: /_astro/
Disallow: /draft/

# ─────────────────────────────────────────────────────────────
# Sitemaps & feeds - declared upfront so crawlers find them on first hit
# ─────────────────────────────────────────────────────────────

Sitemap: https://floorballing.com/sitemap-index.xml
Sitemap: https://floorballing.com/sitemap-0.xml
Sitemap: https://floorballing.com/rss.xml
Sitemap: https://floorballing.com/feed.json

# ─────────────────────────────────────────────────────────────
# LLM resources - non-standard but signals to llms.txt-aware tools
# ─────────────────────────────────────────────────────────────

# Short LLM nav: https://floorballing.com/llms.txt
# Expanded knowledge: https://floorballing.com/llms-full.txt

# ─────────────────────────────────────────────────────────────
# Host
# ─────────────────────────────────────────────────────────────

Host: floorballing.com