# Search engines are welcome. The point of the site is to be found.
User-agent: *
Allow: /

# Google Images specifically. Photographs turning up in an image search is
# discovery, not theft, and every result links back here.
User-agent: Googlebot-Image
Allow: /

Sitemap: https://rosshartigan.com/sitemap-index.xml

# ---------------------------------------------------------------------------
# Machine learning training crawlers
# ---------------------------------------------------------------------------
# Refused. The photographs are copyright Ross Hartigan and are not licensed as
# training data. See https://rosshartigan.com/privacy/
#
# Note what is NOT in this list: Googlebot, Bingbot, Applebot, OAI-SearchBot,
# ChatGPT-User and Perplexity-User are search and retrieval agents that cite
# and link their sources. They stay allowed above. Only the crawlers that
# collect corpora for model training are blocked here, which is why
# Google-Extended appears but Googlebot does not. Blocking Google-Extended
# opts out of Gemini training without touching Search ranking at all.

User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: DataForSeoBot
Disallow: /