# ---------- Regras gerais para todos os crawlers ----------
User-agent: *
Allow: *

Disallow: /sistema/
Disallow: /system/
Disallow: /admin/
Disallow: /painel/
Disallow: /perfil/
Disallow: /uploads/
Disallow: /upload/
Disallow: /uploads/attendances/
Disallow: /temp/
Disallow: /api/
Disallow: /graphql/
Disallow: /.env
Disallow: /.git/
Disallow: /.htaccess
Disallow: /.htpasswd
Disallow: /.well-known/
Disallow: /config/
Disallow: /backup/
Disallow: /backups/
Disallow: /phpmyadmin/
Disallow: /vendor/
Disallow: /node_modules/
Disallow: /cgi-bin/

# Bloqueia caminhos onde estão as URLs spam indexadas (a chave do problema)
Disallow: /games/
Disallow: /articles/
Disallow: /books/
Disallow: /apps/
Disallow: /store/

# Bloqueia tentativas de WordPress (não é WP)
Disallow: /wp-login.php
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /xmlrpc.php

# Extensões de arquivo sensíveis (sintaxe estendida do Googlebot)
Disallow: /*.json$
Disallow: /*.sql$
Disallow: /*.log$
Disallow: /*.bak$
Disallow: /*.env$
Disallow: /*.sh$
Disallow: /*.xml$
Disallow: /*.git/

# Evita indexação de URLs com query string (duplicação de conteúdo)
Disallow: /*?*

# Exceção para permitir que o bot leia versionamento
Allow: /*?v=*

# Permite assets necessários para renderização correta
Allow: /site/css/
Allow: /site/js/
Allow: /site/img/
Allow: /site/images/
Allow: /uploads/posts/
Allow: /uploads/pages/
Allow: /uploads/profiles/
Allow: /uploads/ad_banners/
Allow: /sitemap.xml

# ---------- Bots de SEO / marketing (alto consumo, sem benefício) ----------
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Barkrowler
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: Seekport Crawler
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: peer39_crawler
Disallow: /

User-agent: Scrapy
Disallow: /

# ---------- Bots de IA (treinamento de LLMs e assistentes) ----------
User-agent: GPTBot
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: DuckAssistBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Timpibot
Disallow: /



# ---------- Sitemap ----------
Sitemap: https://orloski.com.br/sitemap.xml