# 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.

# 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
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

# === CONFIGURACION INICIAL ===
Sitemap: https://viruseditorial.net/sitemap_index.xml

# === REGLAS ESPECÍFICAS PARA META (FACEBOOK/INSTAGRAM) ===
User-agent: facebookexternalhit
User-agent: Facebot
User-agent: facebookcatalog
User-agent: meta-webindexer
User-agent: meta-externalhit
# Bloqueo drástico de calquera parámetro (onde se crean as sesións)
Disallow: /*?*
Disallow: /*add-to-cart=*
Disallow: /carrito/
Disallow: /checkout/
Disallow: /finalizar-compra/
Disallow: /wp-admin/
Disallow: /admin-ajax.php
# Meta adoita ignorar o Crawl-delay, pero poñémolo por protocolo
Crawl-delay: 10

# === REGLAS PARA AppleBot ===
User-agent: Applebot
# Prohibir cualquier intento de añadir al carrito (causa de las sesiones pesadas)
Disallow: /*add-to-cart=*
Disallow: /carrito/
Disallow: /checkout/
Disallow: /finalizar-compra/
# Prohibir rastreo de cualquier URL con parámetros (filtros, búsquedas, etc.)
Disallow: /*?*
Disallow: /wp-admin/
Disallow: /admin-ajax.php
# Aumentar el delay por si acaso lo respetan
Crawl-delay: 20

# === REGLAS PARA SEMRUSH ===
User-agent: SemrushBot
Crawl-delay: 5

User-agent: SiteAuditBot
Crawl-delay: 5

# === REGLAS PARA BOTS DE IA (LLMs) ===
User-agent: GPTBot
User-agent: CCBot
Crawl-delay: 10

# === REGLAS PARA BOTS AGRESIVOS / ARCHIVO ===
User-agent: ia_archiver
User-agent: duggmirror
Disallow: /

User-agent: noxtrumbot
Crawl-delay: 50

User-agent: msnbot
Crawl-delay: 30

User-agent: Slurp
Crawl-delay: 10

# === BLOQUEO TOTAL PARA BOTS MALICIOSOS / COPIADORES ===
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
User-agent: AhrefsBot
User-agent: Bytespider
Disallow: /

# === REGLAS GENERALES PARA TODOS LOS BOTS (*) ===
User-Agent: *
Crawl-delay: 5

# --- CONTROL DE WOOCOMMERCE ---
Disallow: /*add-to-cart=*
Disallow: /*add_to_wishlist=*
Disallow: /cart/
Disallow: /carrito/
Disallow: /checkout/
Disallow: /finalizar-compra/
Disallow: /my-account/
Disallow: /mi-cuenta/

# --- SEGURIDAD Y DIRECTORIOS SENSIBLES ---
Disallow: /cgi-bin/
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /wp-includes/
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /index.php
Disallow: /search
Disallow: /archives/
Disallow: /*.php$
Disallow: /*.inc$
Disallow: /*.git$
Disallow: /*.sql$
Disallow: /*.tgz$
Disallow: /*.gz$
Disallow: /*.tar$
Disallow: /*.svn$
Disallow: /*.bz2$
Disallow: /*.log$

# --- LIMPIEZA DE CONTENIDO DUPLICADO Y PARÁMETROS ---
Disallow: /tag/*/page/
Disallow: /tag/*/feed/
Disallow: /page/
Disallow: /comments/
Disallow: /?attachment_id*
Disallow: /refer/
Disallow: /?s=
Disallow: /*?

# --- FEEDS Y TRACKBACKS ---
Disallow: /trackback
Disallow: /*trackback
Disallow: /*trackback*
Disallow: /*/trackback
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/$

# --- CONTENIDO PERMITIDO ---
Allow: /wp-content/uploads/