# 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

# robots.txt – ReceitaGrátis
# Otimizado para SEO, segurança, desempenho e economia de crawl budget

User-agent: *

# Bloqueios de áreas sensíveis e administrativas
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /wp-json/
Disallow: /xmlrpc.php

# Evita páginas de busca interna e respostas
Disallow: /*?s=
Disallow: /*&s=
Disallow: /*?replytocom=

# Bloqueia URLs com parâmetros maliciosos ou usados por spam
Disallow: /?e=
Disallow: /*&e=
Disallow: /*&channel=
Disallow: /*&name=
Disallow: /*&from=
Disallow: /*&ref=
Disallow: /*&src=

# Evita rastreamento de parâmetros de tracking de campanhas
Disallow: /*?utm_source
Disallow: /*?utm_medium
Disallow: /*?utm_campaign
Disallow: /*?utm_term
Disallow: /*?utm_content
Disallow: /*?gclid
Disallow: /*?fbclid
Disallow: /*?msclkid

# Bloqueia páginas duplicadas, pouco relevantes ou indexações não estratégicas
Disallow: /tag/
Disallow: /author/
Disallow: /*?amp$
Disallow: /*?amp=1$
Disallow: /*//1000

# Evita indexação de feeds e recursos RSS
Disallow: /feed/
Disallow: /comments/feed/

# Permite recursos essenciais ao carregamento do site
Allow: /wp-admin/admin-ajax.php
Allow: /wp-content/uploads/
Allow: /wp-content/themes/
Allow: /wp-content/plugins/
Allow: /*.css$
Allow: /*.js$
Allow: /*.woff$
Allow: /*.woff2$
Allow: /*.ttf$

# Tratamento para Googlebot de anúncios
User-agent: AdsBot-Google
Allow: /

# Sitemap principal
Sitemap: https://receitagratis.com/sitemap.xml