# https://www.blockchain0x.com robots.txt
# Last updated: 2026-05-15

# ============================================================
# Default: Allow all search engine bots
# ============================================================
User-agent: *
Allow: /
Disallow: /node_modules/
Disallow: /api/
Disallow: /_internal/
Disallow: /dist/
Disallow: /server/

# ============================================================
# Major Search Engine Crawlers — explicitly allowed
# ============================================================

# Google Search
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Storebot-Google
Allow: /

# Google Ads / Rich Results
User-agent: AdsBot-Google
Allow: /

User-agent: Mediapartners-Google
Allow: /

# Bing / Microsoft Search
User-agent: Bingbot
Allow: /

User-agent: MicrosoftPreview
Allow: /

# Yahoo
User-agent: Slurp
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# Baidu (China)
User-agent: Baiduspider
Allow: /

# Yandex (Russia)
User-agent: YandexBot
Allow: /

# Apple (Siri, Spotlight, Safari suggestions)
User-agent: Applebot
Allow: /

# Amazon (Alexa, Amazon search)
User-agent: Amazonbot
Allow: /

# Facebook / Meta (link previews, sharing)
User-agent: facebookexternalhit
Allow: /

# Twitter/X (link previews, cards)
User-agent: Twitterbot
Allow: /

# LinkedIn (link previews)
User-agent: LinkedInBot
Allow: /

# Pinterest
User-agent: Pinterestbot
Allow: /

# TikTok / ByteDance (search & previews)
User-agent: Bytespider
Allow: /

# Naver (Korea)
User-agent: Yeti
Allow: /

# Sogou (China)
User-agent: Sogou
Allow: /

# Seznambot (Czech Republic)
User-agent: SeznamBot
Allow: /

# Archive.org (web archive / citation)
User-agent: ia_archiver
Allow: /

# Qwant (EU search engine)
User-agent: Qwantify
Allow: /

# Brave Search
User-agent: BraveBot
Allow: /

# Mojeek (independent search)
User-agent: MojeekBot
Allow: /

# ============================================================
# AI Training Crawlers — allowed
# ============================================================

# OpenAI (GPT training)
User-agent: GPTBot
Allow: /

# Google AI training
User-agent: Google-Extended
Allow: /

# Anthropic (Claude training)
User-agent: ClaudeBot
Allow: /

# Common Crawl
User-agent: CCBot
Allow: /

# Meta AI training
User-agent: meta-externalagent
Allow: /

# Cohere AI
User-agent: cohere-ai
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Omgili / Webz.io
User-agent: omgili
Allow: /

# OpenAI SearchBot (ChatGPT search index crawler, separate from GPTBot)
User-agent: OAI-SearchBot
Allow: /

# Apple Intelligence (Applebot extended for AI training/answering)
User-agent: Applebot-Extended
Allow: /

# Standard Apple Search
User-agent: Applebot
Allow: /

# ============================================================
# Sitemaps
# ============================================================
Sitemap: https://www.blockchain0x.com/sitemap_index.xml