# ============================================================
# robots.txt — Mozg-info.pl
# Last updated: 2026-05-02
# Polityka egzekwowana również w Cloudflare Worker
# (cloudflare-worker-seo.js: 403 + X-Robots-Tag dla AI training)
# ============================================================

# ---------- Default (wszystkie inne boty) ----------
User-agent: *
Allow: /
Disallow: /__health
Disallow: /__crawler-stats
Disallow: /api/
Disallow: /*?*utm_
Disallow: /*?*fbclid
Disallow: /*?*gclid
Crawl-delay: 1

# ---------- Tradycyjne wyszukiwarki (priorytet) ----------
User-agent: Googlebot
Allow: /
Disallow: /__health
Disallow: /__crawler-stats

User-agent: Googlebot-Image
Allow: /og/
Allow: /

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /
Crawl-delay: 2

User-agent: Applebot
Allow: /

User-agent: Seznambot
Allow: /

# ---------- AI Search (DOZWOLONE — kierują ruch do źródła) ----------
User-agent: Google-Extended
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Applebot-Extended
Allow: /

# ---------- Social media (DOZWOLONE — podgląd linków) ----------
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

User-agent: Discordbot
Allow: /

User-agent: Slackbot
Allow: /

User-agent: Pinterestbot
Allow: /

# ---------- AI Training (BLOKOWANE — bez wynagrodzenia dla wydawców) ----------
User-agent: GPTBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Cohere-AI
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SemrushBot-OCOB
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: Scrapy
Disallow: /

# ---------- Sygnały dodatkowe ----------
Sitemap: https://mozg-info.pl/sitemap-index.xml
Sitemap: https://mozg-info.pl/sitemap.xml
Sitemap: https://mozg-info.pl/sitemap-images.xml

# Host preferred (informacyjnie dla Yandex i niektórych botów)
Host: https://mozg-info.pl