# robots.txt for daviddacruz.dev
# David Dacruz
# https://daviddacruz.dev

# Standard crawlers
User-agent: *
Allow: /
Disallow: /api/
Disallow: /context/
Disallow: /_nuxt/
Disallow: /.nuxt/

# Google
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /david-dacruz.webp
Allow: /og.png
Allow: /screenshot-ericeira-review.webp
Allow: /screenshot-jurassic-barks.webp
Allow: /screenshot-lets-paws.webp

# Bing
User-agent: Bingbot
Allow: /

# AI crawlers
User-agent: GPTBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

User-agent: OAI-SearchBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

User-agent: ChatGPT-User
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

User-agent: PerplexityBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

User-agent: Perplexity-User
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

User-agent: ClaudeBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

User-agent: Claude-User
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

User-agent: Claude-SearchBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

User-agent: Google-Extended
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

# Bytedance / Doubao
User-agent: Bytespider
Allow: /

# Common Crawl (used by many AI training sets)
User-agent: CCBot
Allow: /

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

# You.com
User-agent: YouBot
Allow: /

# SEO tools
User-agent: Semrushbot
Allow: /

User-agent: AhrefsBot
Allow: /

User-agent: DotBot
Allow: /

User-agent: MJ12bot
Disallow: /

# Sitemaps
Sitemap: https://daviddacruz.dev/sitemap.xml
Sitemap: https://daviddacruz.dev/news-sitemap.xml

# Additional resources
# llms.txt: https://daviddacruz.dev/llms.txt
# llms-full.txt: https://daviddacruz.dev/llms-full.txt
# location.kml: https://daviddacruz.dev/location.kml