# =====================================================================
# robots.txt - Rede Global de Comunicacao
# Atualizado em 18/ago/2026
#
# DOUTRINA: bloqueamos quem TREINA modelo com o nosso conteudo.
# Liberamos quem BUSCA e CITA com link, porque isso traz leitor.
# Quem quiser usar o acervo para treino: /licenciamento
#
# Observacao: /orcamento.html e /trabalhe-conosco.html continuam fora do
# indice pelo header X-Robots-Tag (vercel.json). Nao entram aqui de
# proposito: pagina bloqueada no robots.txt nao pode ser lida, e por
# isso o proprio noindex deixa de ser visto pelo buscador.
# =====================================================================


# ---------------------------------------------------------------------
# 1) BUSCADORES E O RESTO DA WEB - liberado
# ---------------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /admin.html
Disallow: /admin-pro.html
Disallow: /pro/
Disallow: /api/


# ---------------------------------------------------------------------
# 2) TREINAMENTO DE IA - BLOQUEADO
# Estes agentes coletam conteudo para treinar modelo. Nenhum deles
# devolve leitor. Bloquear GPTBot NAO tira o site do ChatGPT Search
# (isso e o OAI-SearchBot, liberado abaixo) e bloquear Google-Extended
# NAO afeta o ranking no Google Search - documentacao oficial do Google.
# ---------------------------------------------------------------------
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: meta-externalfetcher
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: TikTokSpider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: AI2Bot-Dolma
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: SemrushBot-OCOB
Disallow: /

User-agent: peer39_crawler
Disallow: /

User-agent: Scrapy
Disallow: /


# ---------------------------------------------------------------------
# 3) BUSCA POR IA - LIBERADO (cita com link e traz leitor)
# Bloquear estes seria sair do resultado, nao proteger o acervo.
# ---------------------------------------------------------------------
User-agent: OAI-SearchBot
Allow: /
Disallow: /admin.html
Disallow: /admin-pro.html
Disallow: /pro/
Disallow: /api/

User-agent: ChatGPT-User
Allow: /
Disallow: /admin.html
Disallow: /admin-pro.html
Disallow: /pro/
Disallow: /api/

User-agent: Claude-SearchBot
Allow: /
Disallow: /admin.html
Disallow: /admin-pro.html
Disallow: /pro/
Disallow: /api/

User-agent: Claude-User
Allow: /
Disallow: /admin.html
Disallow: /admin-pro.html
Disallow: /pro/
Disallow: /api/

User-agent: PerplexityBot
Allow: /
Disallow: /admin.html
Disallow: /admin-pro.html
Disallow: /pro/
Disallow: /api/

User-agent: Perplexity-User
Allow: /
Disallow: /admin.html
Disallow: /admin-pro.html
Disallow: /pro/
Disallow: /api/

User-agent: Applebot
Allow: /
Disallow: /admin.html
Disallow: /admin-pro.html
Disallow: /pro/
Disallow: /api/

User-agent: MistralAI-User
Allow: /
Disallow: /admin.html
Disallow: /admin-pro.html
Disallow: /pro/
Disallow: /api/


# ---------------------------------------------------------------------
# 4) SITEMAPS
# ---------------------------------------------------------------------
Sitemap: https://www.redeglobaldecomunicacao.com.br/sitemap.xml
Sitemap: https://www.redeglobaldecomunicacao.com.br/news-sitemap.xml
Sitemap: https://www.redeglobaldecomunicacao.com.br/sitemap-jornal.xml
Sitemap: https://www.redeglobaldecomunicacao.com.br/sitemap-indice.xml