# robots.txt — DAYNEWS ROMANIA (daynews.ro)
# Ultima actualizare: 2026-07-21
#
# Politică:
# - Permitem crawlerelor clasice (Google, Bing etc.) accesul la conținutul public.
# - Blocăm rutele interne (auth, editor, MCP, .well-known) care sunt oricum noindex.
# - Permitem explicit crawlerele AI/LLM să citească site-ul pentru discovery și
#   citare, dar interzicem accesul la aceleași rute interne.
# - Fișierele llms.txt și sitemap-urile sunt referite explicit mai jos.

# =====================================================================
# 1. Crawlere generale (Google, Bing, DuckDuckGo, Yandex, Baidu, etc.)
# =====================================================================
User-agent: *
Allow: /
Disallow: /auth
Disallow: /auth/
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/
Disallow: /*?*utm_
Disallow: /*?*fbclid=
Disallow: /*?*gclid=

# =====================================================================
# 2. Crawlere AI / LLM — permise pentru discovery și citare
# =====================================================================
# Politica DAYNEWS ROMANIA: permitem crawlerelor AI să indexeze conținutul
# public pentru a putea fi citate corect în răspunsuri generate. Rutele
# interne rămân interzise. Dacă doriți retragerea unui articol, contactați
# redacția.

# OpenAI — ChatGPT (search & browsing) și antrenare
User-agent: OAI-SearchBot
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

User-agent: ChatGPT-User
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

User-agent: GPTBot
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# Google — Gemini / Vertex AI (indexare pentru AI Overviews & training)
User-agent: Google-Extended
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

User-agent: GoogleOther
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# Anthropic — Claude
User-agent: ClaudeBot
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

User-agent: Claude-Web
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

User-agent: anthropic-ai
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# Perplexity
User-agent: PerplexityBot
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

User-agent: Perplexity-User
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# Mistral AI
User-agent: MistralAI-User
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# Meta AI (Llama)
User-agent: Meta-ExternalAgent
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

User-agent: Meta-ExternalFetcher
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

User-agent: FacebookBot
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# Amazon
User-agent: Amazonbot
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# Cohere
User-agent: cohere-ai
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

User-agent: cohere-training-data-crawler
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# ByteDance / TikTok
User-agent: Bytespider
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# You.com
User-agent: YouBot
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# Diffbot / Common data crawlers
User-agent: Diffbot
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# Common Crawl (dataset folosit de multe LLM-uri)
User-agent: CCBot
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# xAI — Grok
User-agent: xAI
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# DeepSeek
User-agent: DeepSeekBot
Allow: /
Disallow: /auth
Disallow: /editor
Disallow: /editor/
Disallow: /editorial/nou
Disallow: /mcp
Disallow: /.mcp/
Disallow: /.well-known/

# =====================================================================
# 3. Sitemap-uri și resurse AI
# =====================================================================
Sitemap: https://daynews.ro/sitemap.xml
Sitemap: https://daynews.ro/news-sitemap.xml

# llms.txt — descriere structurată a site-ului pentru LLM-uri
# https://daynews.ro/llms.txt