User-agent: Baiduspider
User-agent: AhrefsBot
User-agent: ComprarAquiBot
User-agent: VoilaBot
User-agent: YandexBot
User-agent: MJ12bot
User-agent: 360Spider
User-agent: Ezooms
User-agent: heritrix
User-agent: BLEXBot
User-agent: JobdiggerSpider
User-agent: kulturarw3
User-agent: XoviBot
User-agent: SiteExplorer
User-agent: Vagabondo
User-agent: EccolaBot
User-agent: SEOkicks
User-agent: DotBot
User-agent: ltx71
User-agent: Scrapy
User-agent: worldwebheritage
User-agent: SemrushBot
User-agent: SemrushBot-SA
User-agent: ProoXiBot
User-agent: spbot
User-agent: nekstbot
# IA — entrenamiento puro, sin retorno de visibilidad ni tráfico (consumen banda)
# Ojo: Applebot-Extended solo controla el entrenamiento de Apple Intelligence;
# el rastreo para Siri/Spotlight lo gobierna Applebot, que va permitido más abajo.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: CCBot
User-agent: Bytespider
User-agent: Applebot-Extended
Disallow: /

User-agent: bingbot
Crawl-delay: 30
Disallow: /admin/
Disallow: /application/
Disallow: /css/
Disallow: /data/
Disallow: /feeds/
Disallow: /imgs/
Disallow: /js/
Disallow: /lib/
Disallow: /plugins/
Disallow: /scripts/
Disallow: /templates/
Disallow: /corp/links
Disallow: /rtp.php
Disallow: /cdn-cgi/
Disallow: /*internal_campaign=
Allow: /

# Google ignores this, but in case... #
User-agent: Googlebot
User-agent: Googlebot-News
User-agent: Googlebot-Image
User-agent: Googlebot-Video
User-agent: Googlebot-Mobile
User-agent: Mediapartners
User-agent: Mediapartners-Google
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
User-agent: Storebot-Google
User-agent: Google-InspectionTool
User-agent: Google-Extended
Crawl-delay: 1
Disallow: /admin/
Disallow: /application/
Disallow: /data/
Disallow: /feeds/
Disallow: /lib/
Disallow: /plugins/
Disallow: /scripts/
Disallow: /templates/
Disallow: /corp/links
Disallow: /rtp.php
Disallow: /cdn-cgi/
Disallow: /*internal_campaign=
Allow: /

# Applebot alimenta Siri y Spotlight: interesa que indexe. Grupo propio y no junto a
# bingbot porque necesita /css/, /js/ e /imgs/ para renderizar — mismo motivo por el
# que el bloque de Google tampoco los bloquea. Sí respeta Crawl-delay.
User-agent: Applebot
Crawl-delay: 30
Disallow: /admin/
Disallow: /application/
Disallow: /data/
Disallow: /feeds/
Disallow: /lib/
Disallow: /plugins/
Disallow: /scripts/
Disallow: /templates/
Disallow: /corp/links
Disallow: /rtp.php
Disallow: /cdn-cgi/
Disallow: /*internal_campaign=
Allow: /

# IA — asistentes/buscadores permitidos (visibilidad de marca, tráfico referral)
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Disallow: /admin/
Disallow: /application/
Disallow: /data/
Disallow: /feeds/
Disallow: /lib/
Disallow: /plugins/
Disallow: /scripts/
Disallow: /templates/
Disallow: /corp/links
Disallow: /rtp.php
Disallow: /cdn-cgi/
Allow: /

User-agent: *
Crawl-delay: 30
Disallow: /admin/
Disallow: /application/
Disallow: /css/
Disallow: /data/
Disallow: /feeds/
Disallow: /imgs/
Disallow: /js/
Disallow: /lib/
Disallow: /plugins/
Disallow: /scripts/
Disallow: /templates/
Disallow: /search/
Disallow: /corp/links
Disallow: /rtp.php
Disallow: /cdn-cgi/
Disallow: /*internal_campaign=
Disallow: /*x-referer-id=
Allow: /

Sitemap: https://www.miscota.de/xmls/sitemap.xml