# Bloqueo basico para todos los bots y crawlers

# puede dar problemas por bloqueo de recursos en GWT

User-agent: *

Allow: /wp-content/uploads/*

Allow: /wp-content/*.js

Allow: /wp-content/*.css

Allow: /wp-includes/*.js

Allow: /wp-includes/*.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*

 

# Bloqueo de las URL dinamicas

Disallow: /*?

 

 

#Bloqueo de busquedas

User-agent: *

Disallow: /?s= 

Disallow: /search

 

 

# Bloqueo de trackbacks

User-agent: *

Disallow: /trackback

Disallow: /*trackback

Disallow: /*trackback*

Disallow: /*/trackback

 

 

# Bloqueo de feeds para crawlers

User-agent: *

Allow: /feed/$ 

Disallow: /feed/ 

Disallow: /comments/feed/

Disallow: /*/feed/$ 

Disallow: /*/feed/rss/$ 

Disallow: /*/trackback/$ 

Disallow: /*/*/feed/$ 

Disallow: /*/*/feed/rss/$ 

Disallow: /*/*/trackback/$ 

Disallow: /*/*/*/feed/$ 

Disallow: /*/*/*/feed/rss/$ 

Disallow: /*/*/*/trackback/$

 

 

# Ralentizamos algunos bots que se suelen volver locos

User-agent: noxtrumbot

Crawl-delay: 20

User-agent: msnbot

Crawl-delay: 20

User-agent: Slurp

Crawl-delay: 20

 

 

# Bloqueo de bots y crawlers poco utiles

User-agent: MSIECrawler

Disallow: / 

User-agent: WebCopier 

Disallow: / 

User-agent: HTTrack 

Disallow: / 

User-agent: Microsoft.URL.Control 

Disallow: / 

User-agent: libwww 

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: /

 

 

# Previene problemas de recursos bloqueados en Google Webmaster Tools

User-Agent: Googlebot

Allow: /*.css$

Allow: /*.js$

 

 

# En condiciones normales este es el sitemap

Sitemap: https://webinstant.es/sitemap_index.xml