# 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: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Bloquear o permitir acceso a contenido adjunto. (Si la instalación está en /public_html).

User-agent: *
Disallow: /cgi-bin
Disallow: /wp-content/plugins/   
Disallow: /wp-content/themes/   
Disallow: /wp-includes/   
Disallow: /wp-admin/
Disallow: /login
Disallow: /tag/
#Impedir el acceso a los diferentes feed que genere la página

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/$   

# Impedir URLs terminadas en /trackback/ que sirven como Trackback URL.   

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

# Evita bloqueos de CSS y JS.

Allow: /*.js$
Allow: /*.css$

#Bloquear todos los pdfs

Disallow: /*.pdf$

#Bloquear parámetros

Disallow: / *?

# Lista de bots que deberías permitir.

User-agent: AhrefsSiteAudit
Allow: /

User-agent: AhrefsBot
Allow: /

User-agent: Googlebot-Image
Allow: /wp-content/uploads/

User-agent: Adsbot-Google
Allow: /

User-agent: Googlebot-Mobile
Allow: /

User-agent: Bingbot
Allow: /

User-agent: AdIdxBot
Allow: /

User-agent: BingPreview
Allow: /

User-agent: MicrosoftPreview
Allow: /

User-agent: Twitterbot
Allow: /images

# Lista de bots bloqueados

User-agent: MSIECrawler
Disallow: /
User-agent: WebCopier
Disallow: /
User-agent: HTTrack
Disallow: /
User-agent: Microsoft.URL.Control
Disallow: /
User-agent: libwww
Disallow: /
User-agent: Baiduspider
Disallow: /
User-agent: GurujiBot
Disallow: /
User-agent: hl_ftien_spider
Disallow: /
User-agent: sogou spider
Disallow: /
User-agent: Yeti
Disallow: /
User-agent: YodaoBot
Disallow: /

#Desautorizar a páginas innecesarias

Disallow: /gracias-por-suscribirte

# Añadimos una indicación de la localización del sitemap

Sitemap: https://lacavernainformatica.com/post-sitemap.xml