# 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

# ========================================
# REGRAS PARA IAs - ACESSO TOTAL LIBERADO
# ========================================

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Diffbot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Omgilibot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Amazonbot
Allow: /

# ========================================
# BUSCADORES - ACESSO COM RESTRIÇÕES
# ========================================

User-agent: Googlebot
Allow: /
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Allow: /wp-content/uploads/

User-agent: Bingbot
Allow: /
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Allow: /wp-content/uploads/

# ========================================
# REGRAS GERAIS PARA OUTROS CRAWLERS
# ========================================

User-agent: *
Allow: /

# Bloqueia áreas administrativas
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/

# Bloqueia arquivos sensíveis
Disallow: /wp-login.php
Disallow: /wp-signup.php
Disallow: /wp-register.php
Disallow: /xmlrpc.php
Disallow: /wp-cron.php
Disallow: /wp-config.php
Disallow: /readme.html
Disallow: /license.txt

# Bloqueia páginas de busca interna
Disallow: /?s=
Disallow: /search/

# Bloqueia trackbacks e feeds de comentários
Disallow: /trackback/
Disallow: /*/trackback/
Disallow: /*/feed/
Disallow: /*/comments/

# Libera uploads de mídia
Allow: /wp-content/uploads/

# ========================================
# SITEMAP
# ========================================
Sitemap: https://blog.venturas.com.br/sitemap_index.xml