# =============================================================
# robots.txt — Agência Seoloc Brasil
# https://www.seolocbrasil.com.br
# Atualizado: 8 de outubro de 2026
# Estratégia: máxima visibilidade em mecanismos de busca e
# IAs generativas (GEO/AEO) — entidade aberta, scraping
# agressivo bloqueado
# =============================================================

# --- Regra global ---
# Content-Signal (contentsignals.org): busca sim, respostas de IA sim, treinamento não. Vale para todos os robôs.
User-agent: *
Allow: /
Disallow: /cdn-cgi/
Disallow: /api/
Disallow: /busca/
Disallow: /en/search/
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_
Content-Signal: search=yes, ai-input=yes, ai-train=no

# =============================================================
# MECANISMOS DE BUSCA TRADICIONAIS
# =============================================================

# Google
User-agent: Googlebot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Microsoft Bing (cobre também DuckDuckGo e Ecosia via índice)
User-agent: bingbot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Yahoo (crawler legado próprio)
User-agent: Slurp
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Yandex (dominante na Rússia)
User-agent: YandexBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Baidu (dominante na China)
User-agent: Baiduspider
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Naver (dominante na Coreia do Sul)
User-agent: NaverBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Sogou (segundo maior buscador chinês)
User-agent: Sogou
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Qihoo 360 (terceiro maior buscador chinês)
User-agent: 360Spider
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# You.com (busca com IA nativa)
User-agent: YouBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Apple (Spotlight, Safari Suggestions — base)
User-agent: Applebot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Huawei Petal Search (mercados Huawei/China)
User-agent: PetalBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# =============================================================
# INTELIGÊNCIA ARTIFICIAL GENERATIVA — TREINAMENTO E BUSCA
# =============================================================

# OpenAI — treinamento GPT
User-agent: GPTBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# OpenAI — busca do ChatGPT
User-agent: OAI-SearchBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# OpenAI — requisições de usuário em tempo real
User-agent: ChatGPT-User
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# OpenAI — agentes autônomos (novo em 2026)
User-agent: ChatGPT-Agent
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Anthropic — treinamento Claude
User-agent: ClaudeBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Anthropic — requisições de usuário em tempo real
User-agent: Claude-User
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Anthropic — busca do Claude
User-agent: Claude-SearchBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Google — treinamento Gemini e AI Overviews
User-agent: Google-Extended
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Perplexity — indexação
User-agent: PerplexityBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Perplexity — requisições de usuário em tempo real
User-agent: Perplexity-User
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Common Crawl (alimenta DeepSeek, LLaMA e modelos open source)
User-agent: CCBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# xAI — Grok
User-agent: GrokBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# DeepSeek
User-agent: DeepSeekBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Apple — treinamento de modelos de IA
User-agent: Applebot-Extended
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Amazon — Alexa e modelos AWS
User-agent: Amazonbot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Meta — modelos LLaMA
User-agent: meta-externalagent
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

User-agent: Meta-ExternalFetcher
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Mistral AI
User-agent: MistralAI-User
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Cohere (Command R+)
User-agent: cohere-ai
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Alibaba / Qwen
User-agent: QwenBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# iask.ai
User-agent: iaskspider
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# DuckDuckGo AI (DuckAssist)
User-agent: DuckAssistBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Diffbot (estrutura dados para LLMs)
User-agent: Diffbot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# FriendlyCrawler (pipelines open source)
User-agent: FriendlyCrawler
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Google — pesquisa aprofundada com Gemini (2026)
User-agent: Gemini-Research
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Apple Intelligence (2026)
User-agent: AppleIntelligenceBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# OpenAI — SearchGPT (2026)
User-agent: SearchGPT
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Meta — crawler de conteúdo/IA (distinto do facebookexternalhit de preview de link)
User-agent: FacebookBot
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# Meta/Facebook — limitação de taxa de rastreamento
User-agent: facebookexternalhit
Crawl-delay: 600

User-agent: meta-externalads
Crawl-delay: 600

# =============================================================
# BLOQUEADOS — não conformidade documentada
# =============================================================

# ByteDance/TikTok — treinamento de IA. Liberado em 28/09/2026 para
# maximizar citabilidade; histórico de ignorar robots.txt é conhecido,
# então este Allow é sobre política, não garantia técnica de comportamento.
User-agent: Bytespider
Allow: /
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=
Disallow: /*?ref=
Disallow: /*&utm_

# DataForSeo — revenda de dados com comportamento agressivo
User-agent: DataForSeoBot
Disallow: /

# MegaIndex — sobrecarga documentada de servidores
User-agent: MegaIndex
Disallow: /

# Scrapy genérico — framework sem identificação adequada
User-agent: Scrapy
Disallow: /

# =============================================================
# llms.txt: https://www.seolocbrasil.com.br/llms.txt
# llms-full.txt: https://www.seolocbrasil.com.br/llms-full.txt
Sitemap: https://www.seolocbrasil.com.br/sitemap.xml