# robots.txt for abqjournal.com

# Allow major search engines
User-agent: Googlebot
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: Facebot
Allow: /

User-agent: Twitterbot
Allow: /

# --- Block AI/LLM scrapers ---

# OpenAI
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

# Anthropic
User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

# Google AI
User-agent: Google-Extended
Disallow: /

# Meta AI
User-agent: FacebookBot
Disallow: /

# Common Crawl (used to train many LLMs)
User-agent: CCBot
Disallow: /

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

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

# Amazon
User-agent: Amazonbot
Disallow: /

# Bytedance / TikTok
User-agent: Bytespider
Disallow: /

# Diffbot
User-agent: Diffbot
Disallow: /

# ImagesiftBot
User-agent: ImagesiftBot
Disallow: /

# PerplexityBot
User-agent: PerplexityBot
Disallow: /

# YouBot
User-agent: YouBot
Disallow: /

# Omgili
User-agent: omgili
Disallow: /

# Catch-all for everything else not explicitly allowed
User-agent: *
Disallow: /

# Sitemaps
Sitemap: https://www.abqjournal.com/sitemapindex.xml
Sitemap: https://www.abqjournal.com/news?lab_viewport=newssitemap