# 01/06/2019 Robots.txt for TomaChollos.com # # Allow # Evita bloqueos de CSS y JS. User-Agent: * Allow: /*.js$ Allow: /*.css$ Allow: */modules/*.css Allow: /*.css Allow: /*.js Allow: /wp-admin/*.js Allow: /wp-admin/*.css Allow: /wp-admin/admin-ajax.php Allow: /wp-includes/js/jquery/jquery.js Allow: /wp-includes/js/jquery/jquery.min.js Allow: /wp-includes/js/* Allow: /wp-content/themes/kadence/assets/css/*.css Allow: /wp-content/themes/kadence/assets/css/* # Seguimos por contenido adjunto User-Agent: * Allow: /wp-content/uploads/ Allow: /wp-content/litespeed/cssjs/*.css Allow: /wp-content/litespeed/cssjs/*.js Allow: /wp-content/webp-express/webp-images/doc-root/wp-content/ Allow: /wp-content/webp-express/webp-images/doc-root/wp-content/* Disallow: /wp-content/plugins/ Disallow: /wp-includes/ # Seguimos por contenido admin y redirects User-Agent: * Disallow: /wp-admin/ Disallow: /redirect-to # Otra info y búsquedas User-Agent: * Disallow: /wp- Disallow: /?s= Disallow: */?s= Disallow: /*?s= Disallow: /search Disallow: /wp-content/ Disallow: /archives/ Disallow: /cgi-bin Disallow: /suscripciones-a-comentarios/* Disallow: /xmlrpc.php Disallow: /?attachment_id* Disallow: /go/ # Paginación #User-Agent: * #Disallow: /*/page/ #Disallow: /tag/*/page/ #Disallow: /page/ # No indexamos copias de seguridad User-Agent: * Disallow: /*.sql$ Disallow: /*.tgz$ Disallow: /*.gz$ Disallow: /*.tar$ Disallow: /*.svn$ # Autorizamos el feed general para Google Blogsearch # Pero impedimos que permalink/feed/ sea indexado ya que el # feed con los comentarios suele posicionarse en lugar de # la entrada y desorienta a los usuarios. # # Lo mismo con URLs terminadas en /trackback/ que sólo # sirven como Trackback URI (y son contenido duplicado). # User-Agent: * Allow: /feed/$ Disallow: /feed/ Disallow: /comments/feed Disallow: /*/feed/ Disallow: /*/feed/$ Disallow: /*/feed/rss/$ Disallow: /*/trackback/$ Disallow: /*/*/feed/$ Disallow: /*/*/feed/rss/$ Disallow: /*/*/trackback/$ Disallow: /*/*/*/feed/$ Disallow: /*/*/*/feed/rss/$ Disallow: /*/*/*/trackback/$ Disallow: /trackback/ Disallow: /tag/*/feed/ Disallow: */out Disallow: /*/*/*/feed.xml # Ahora el sitemap User-Agent: * Sitemap: https://www.tomachollos.com/sitemap_index.xml # Lista de bots permitidos User-agent: Googlebot-Image Allow: /wp-content/uploads/ User-agent: Adsbot-Google Allow: / User-agent: Googlebot-Mobile Allow: / # Lista de bots que suelen respetar el robots.txt pero rara # vez hacen un buen uso del sitio y abusan bastante… # User-agent: MSIECrawler Disallow: / Crawl-delay: 10 User-agent: WebCopier Disallow: / Crawl-delay: 10 User-agent: HTTrack Disallow: / Crawl-delay: 10 User-agent: Microsoft.URL.Control Disallow: / Crawl-delay: 10 User-agent: libwww Disallow: / Crawl-delay: 10 # Slurp (Yahoo!), Noxtrum y el bot de MSN a veces tienen # idas de pinza, toca decirles que reduzcan la marcha. # User-agent: noxtrumbot Crawl-delay: 20 User-agent: msnbot Crawl-delay: 20 User-agent: Slurp Crawl-delay: 20 # CuteStat no es muy respetuoso con los privacy y otros son poco útiles. # User-agent: CuteStat Disallow: / User-agent: Orthogaffe Disallow: / User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / User-agent: sitecheck.internetseer.com Disallow: / User-agent: Zealbot Disallow: / User-agent: MSIECrawler Disallow: / User-agent: SiteSnagger Disallow: / User-agent: WebStripper Disallow: / User-agent: WebCopier Disallow: / User-agent: Fetch Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: WebZIP Disallow: / User-agent: linko Disallow: / User-agent: HTTrack Disallow: / User-agent: Microsoft.URL.Control Disallow: / User-agent: Xenu Disallow: / User-agent: larbin Disallow: / User-agent: libwww Disallow: / User-agent: ZyBORG Disallow: / User-agent: Download Ninja Disallow: / User-agent: wget Disallow: / User-agent: grub-client Disallow: / User-agent: k2spider Disallow: / User-agent: NPBot Disallow: / User-agent: WebReaper Disallow: /