# Bloqueo básico para todos los bots y crawlers
User-agent: *
Allow: /wp-content/uploads/
Allow: /*.js$
Allow: /*.css$
Disallow: /cgi-bin
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /wp-includes/
Disallow: /*/attachment/
Disallow: /tag/*/page/
Disallow: /tag/*/feed/
Disallow: /page/
Disallow: /comments/
Disallow: /xmlrpc.php
Disallow: /?attachment_id*
Disallow: /*?s= 
Disallow: /search
Disallow: /trackback
Disallow: /*trackback

# Bloqueo de URLs dinámicas para evitar sobrecarga
Disallow: /*?

# Bloqueo de bots y crawlers poco útiles
User-agent: MSIECrawler
User-agent: WebCopier
User-agent: HTTrack
User-agent: Microsoft.URL.Control
User-agent: libwww
User-agent: Orthogaffe
User-agent: UbiCrawler
User-agent: DOC
User-agent: Zao
User-agent: sitecheck.internetseer.com
User-agent: Zealbot
User-agent: SiteSnagger
User-agent: WebStripper
User-agent: Fetch
User-agent: Offline Explorer
User-agent: Teleport
User-agent: TeleportPro
User-agent: WebZIP
User-agent: linko
User-agent: Xenu
User-agent: larbin
User-agent: ZyBORG
User-agent: Download Ninja
User-agent: wget
User-agent: grub-client
User-agent: k2spider
User-agent: NPBot
User-agent: WebReaper
Disallow: /

# Prevención de problemas de recursos bloqueados en Google
User-agent: Googlebot
Allow: /*.css$
Allow: /*.js$
Crawl-delay: 10

# Limitación general de rastreo para todos los bots
User-agent: *
Crawl-delay: 10

# En condiciones normales este es el sitemap principal
Sitemap: https://www.energynews.es/sitemap_index.xml