# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

User-agent: *
Crawl-delay: 5
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

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*
Disallow: /*?yith_wcan*

 
 
#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$
User-agent: GeedoShopProductFinder
Disallow: /

User-agent: BLEXBot
Disallow: / 
 
# En condiciones normales este es el sitemap
Sitemap: https://milanoiluminacion.es/sitemap_index.xml
 
# Si utilizas Yoast SEO estos son los sitemaps principales
Sitemap: https://milanoiluminacion.es/post-sitemap.xml
Sitemap: https://milanoiluminacion.es/page-sitemap.xml
Sitemap: https://milanoiluminacion.es/product-sitemap.xml
Sitemap: https://milanoiluminacion.es/product-sitemap2.xml
Sitemap: https://milanoiluminacion.es/product-sitemap3.xml
Sitemap: https://milanoiluminacion.es/product-sitemap4.xml
Sitemap: https://milanoiluminacion.es/product-sitemap5.xml
Sitemap: https://milanoiluminacion.es/category-sitemap.xml
Sitemap: https://milanoiluminacion.es/post_tag-sitemap.xml
Sitemap: https://milanoiluminacion.es/product_brand-sitemap.xml
Sitemap: https://milanoiluminacion.es/product_cat-sitemap.xml
Sitemap: https://milanoiluminacion.es/product_tag-sitemap.xml
Sitemap: https://milanoiluminacion.es/product_tag-sitemap2.xml
Sitemap: https://milanoiluminacion.es/product_tag-sitemap3.xml
Sitemap: https://milanoiluminacion.es/product_tag-sitemap4.xml