# House of McPolin — Aaron McPolin
# Full terms: https://mcpolinhouse.com/terms-and-conditions/
#
# Search engines are welcome. Being findable is the point.
# Ingestion for machine learning training is not licensed. The distinction
# below is deliberate: crawlers that only index are allowed, crawlers whose
# job is to collect training data are not. Where a company runs both, the
# search crawler is allowed and the training crawler is named and blocked.

# ---- search: allowed, and wanted --------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: Applebot
Allow: /

User-agent: DuckAssistBot
Allow: /

# ---- AI search: allowed ------------------------------------------------
# These index pages so the work can be found and cited in AI search answers
# ("fine art nude photographers", "erotic fine art photography"). Each
# company states in its crawler documentation that these agents are not used
# to train its models; the training crawlers are separate, and blocked below.
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: /

# ---- AI training: not licensed ----------------------------------------
# Blocking the training crawler while allowing the search crawler is exactly
# what Google-Extended and Applebot-Extended exist for.
User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: YouBot
Disallow: /

# ---- everyone else -----------------------------------------------------
User-agent: *
Allow: /

# Facts about the artist, editions and representation, from the studio:
# https://mcpolinhouse.com/llms.txt

Sitemap: https://mcpolinhouse.com/sitemap-index.xml
Sitemap: https://mcpolinhouse.com/sitemap.xml
Sitemap: https://mcpolinhouse.com/sitemap-images.xml