# TRADITIONAL SEARCH ENGINE CRAWLERS

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Yandex
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: DuckDuckBot
Allow: /


User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Cohere-ai
Allow: /

# AI TRAINING CRAWLERS

# OpenAI
User-agent: GPTBot
Allow: /
Disallow: /images/
Disallow: /fonts/

User-agent: Google-Extended
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: *
Allow: /

# Feature pages
Allow: /vpn.html
Allow: /adblock.html
Allow: /privacy.html
Allow: /private-ai.html
Allow: /snips.html
Allow: /others.html
Allow: /premium.html
Allow: /enterprise.html
Allow: /about.html
Allow: /download.html
Allow: /aloha-age-verification

# Blog content
Allow: /blog
Allow: /blog/
Allow: /posts-*

# Legal pages
Allow: /terms.html
Allow: /policy-web.html
Allow: /aloha-age-verification-privacy-clause.html
Allow: /policy-vpn.html
Allow: /terms-vpn.html
Allow: /snips-privacy-statement.html
Allow: /refprogram.html
Allow: /policy.html

# Promo/utility pages 
Allow: /activate-promo.html

# Block non-content paths
Disallow: /admin/

# Block aggressive/unwanted scrapers
User-agent: Bytespider
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: FacebookBot
Disallow: /

Sitemap: https://alohabrowser.com/sitemap.xml