# Robots.txt for Moctale
# This file provides instructions to web crawlers about which areas of the site they can access

# === BLOCK AI CRAWLERS ===
# This section blocks common AI bots from scraping content for training

# Blocks OpenAI (ChatGPT, GPT-4)
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /

# Blocks Google AI (Gemini, Vertex AI)
User-agent: Google-Extended
Disallow: /

# Blocks Anthropic (Claude)
User-agent: anthropic-ai
Disallow: /
User-agent: ClaudeBot
Disallow: /

# Blocks Perplexity AI
User-agent: PerplexityBot
Disallow: /

# Blocks Cohere AI
User-agent: cohere-ai
Disallow: /

# Blocks Apple AI
User-agent: Applebot-Extended
Disallow: /

# Blocks CommonCrawl (a massive open web archive used for training)
User-agent: CCBot
Disallow: /

# Blocks other AI/data scrapers
User-agent: Bytespider
Disallow: /
User-agent: meta-externalagent
Disallow: /
User-agent: diffbot
Disallow: /

# === ALLOW ADSENSE & GOOGLE AD CRAWLERS ===
# Allows Google AdSense and AdsBot to crawl pages for ad verification and serving
User-agent: Mediapartners-Google
Allow: /

User-agent: Google-Display-Ads-Bot
Allow: /

User-agent: AdsBot-Google
Allow: /

User-agent: AdsBot-Google-Mobile
Allow: /

# === ALLOW MAJOR SEARCH ENGINES ===
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

# === GENERAL RULES FOR ALL OTHER SEARCH ENGINES ===
User-agent: *
# Allow public pages and assets
Allow: /
Allow: /content/
Allow: /about-us
Allow: /privacy-policy
Allow: /terms-of-service
Allow: /deletion-request
Allow: /icons/
Allow: /media/
Allow: /*.css
Allow: /*.js
Allow: /*.png
Allow: /*.jpg
Allow: /*.jpeg
Allow: /*.gif
Allow: /*.svg
Allow: /*.webp
Allow: /*.ico

# Disallow API and build internals
Disallow: /api/
Disallow: /_next/
Disallow: /node_modules/

# Disallow user-specific and auth-protected areas
Disallow: /u/
Disallow: /feed/
Disallow: /explore/
Disallow: /accounts/
Disallow: /my-*
Disallow: /saved-*
Disallow: /schedule/
Disallow: /person/

# Disallow authentication and maintenance pages
Disallow: /login
Disallow: /signup
Disallow: /auth/
Disallow: /maintenance

# Crawl delay to protect server resources
Crawl-delay: 1

# Sitemap location
Sitemap: https://www.moctale.in/sitemap.xml