# 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

# ───────────────────────────────────────────────
# PDFRápido — robots.txt
# Política: bloquea crawlers de entrenamiento IA.
# Permite crawlers de búsqueda en vivo (AEO/LLM SEO).
# ───────────────────────────────────────────────

# === Crawlers de entrenamiento IA (BLOQUEADOS) ===
# Evitamos que nuestro contenido se use para entrenar modelos
# sin compensación ni atribución.
User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: TimpiBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Timpibot
Disallow: /

# === Crawlers de búsqueda/respuesta IA (PERMITIDOS — AEO) ===
# Estos bots indexan para generar respuestas en tiempo real.
User-agent: ChatGPT-User
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

User-agent: PerplexityBot
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

User-agent: Perplexity-User
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

User-agent: ClaudeBot
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

User-agent: Claude-Web
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

User-agent: Google-CloudVertexBot
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

# === Crawlers SEO (PERMITIDOS) ===
User-agent: AhrefsBot
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

User-agent: AhrefsSiteAudit
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

User-agent: SemrushBot
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

User-agent: SemrushBot-SA
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

User-agent: MJ12bot
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

User-agent: DotBot
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

User-agent: DataForSeoBot
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/

# === Buscadores tradicionales y resto de bots ===
User-agent: *
Allow: /
Disallow: /api/
Disallow: /wopi/
Disallow: /tmp/
Disallow: /admin/
Disallow: /*.bak$
Disallow: /*.bak-*
Disallow: /markdown-proxy.php
Crawl-delay: 1

# === Sitemaps ===
Sitemap: https://pdfrapido.eu/sitemap-index.xml

# Archivo para IAs (LLMs)
LLMs: https://pdfrapido.eu/llms.txt