# robots.txt, Recharge Vodafone
# https://rechargevodafone.co.uk
#
# Política: permitimos explícitamente todos los crawlers de motores
# generativos (LLM-powered search). El objetivo es maximizar la
# visibilidad en ChatGPT search, Claude search, Perplexity y Google
# AI Overviews.

# ── OpenAI ──
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# ── Anthropic (3 bots distintos: training, web, search) ──
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: claude-web
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# ── Perplexity ──
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# ── Google (search + AI Overviews) ──
User-agent: Googlebot
Allow: /

User-agent: Google-Extended
Allow: /

# ── Microsoft / Bing ──
User-agent: Bingbot
Allow: /

User-agent: msnbot
Allow: /

# ── Common Crawl (entrena la mayoría de LLMs open-source) ──
User-agent: CCBot
Allow: /

# ── SEO competitor scrapers, bloqueados (consumen banda sin beneficio) ──
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: SemrushBot-SA
Disallow: /

User-agent: rogerbot
Disallow: /

User-agent: dotbot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: SerendeputyBot
Disallow: /

User-agent: SiteAuditBot
Disallow: /

# ── Admin + Lab (no indexar) + resto de crawlers ──
# Un unico grupo `User-agent: *` para evitar ambiguedad de parseo:
# tener dos grupos `*` puede hacer que un crawler ignore los Disallow.
User-agent: *
Disallow: /admin/
Disallow: /lab/
Allow: /

# Sitemap
Sitemap: https://rechargevodafone.co.uk/sitemap-index.xml