# AgTech Academy - Robots.txt
# Canonical domain: www.agtech.academy
# Localização: Piracicaba-SP, Brasil
# Last updated: 2026-04-16

# Google Search Bot - Priority crawler
User-agent: Googlebot
Allow: /
Crawl-delay: 1

# Google Images Bot
User-agent: Googlebot-Image
Allow: /

# Google Video Bot
User-agent: Googlebot-Video
Allow: /

# Google News Bot
User-agent: Googlebot-News
Allow: /blog/

# Bing Bot
User-agent: Bingbot
Allow: /
Crawl-delay: 2

# Bing Images
User-agent: msnbot-media
Allow: /

# Yahoo Bot
User-agent: Slurp
Allow: /

# DuckDuckGo Bot
User-agent: DuckDuckBot
Allow: /

# Yandex Bot
User-agent: Yandex
Allow: /

# Social Media Bots - Full access for rich previews
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

User-agent: Pinterest
Allow: /

# All other bots
User-agent: *
Allow: /

# Disallow private/authenticated areas
Disallow: /membros/
Disallow: /admin/
Disallow: /my-enrollments
Disallow: /enrollment-success
Disallow: /video-call/
Disallow: /course/
Disallow: /email-confirmation
Disallow: /instalar

# Disallow old/legacy URL patterns that no longer exist
Disallow: /blog/f/
Disallow: /*?blogcategory=
Disallow: /*?blog=
Disallow: /*?trk=
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=

# Block legacy UUID-based course URLs (replaced by slug-based URLs)
# Pattern: /cursos/{uuid} - any 8-4-4-4-12 hex format
Disallow: /cursos/*-*-*-*-*

# Primary sitemap (static pages)
Sitemap: https://www.agtech.academy/sitemap.xml

# Dynamic sitemap (courses and blog from database - served directly by edge function)
Sitemap: https://ujbgkqsuvbmtzsdlddkx.supabase.co/functions/v1/generate-sitemap

# Host canônico
Host: https://www.agtech.academy