# Raw States. Search engines and AI answer engines that cite their sources
# are welcome; bulk corpus scrapers are not. The data on this site is
# original editorial work; see /terms. A machine-readable overview lives
# at /llms.txt.

# Google's own crawlers. Search and the AdSense reviewer render the
# homepage like a browser, and the homepage is a map drawn from the files
# in /js/data/; fenced off them, Google saw an empty map and judged the
# site "low value content" (AdSense, 26 Oct 2026). So Google alone may load
# them. Mediapartners-Google is the AdSense crawler; AdsBot checks ad pages.
User-agent: Googlebot
User-agent: Mediapartners-Google
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
Allow: /
Disallow: /api/
Disallow: /media-kit/

# Answer engines that attribute. One group, shared rules: welcome on every
# page, fenced off the API and the raw data files like everyone else.
User-agent: Bingbot
User-agent: DuckDuckBot
User-agent: Applebot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Perplexity-User
Allow: /
Disallow: /api/
Disallow: /js/data/
Disallow: /media-kit/

# Bulk training and corpus crawlers. Blocking Google-Extended and
# Applebot-Extended affects model training only, never Search or Siri
# citations.
User-agent: GPTBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Bytespider
User-agent: Amazonbot
User-agent: Diffbot
User-agent: ImagesiftBot
User-agent: Meta-ExternalAgent
User-agent: meta-externalagent
User-agent: PetalBot
User-agent: Ai2Bot
User-agent: cohere-training-data-crawler
User-agent: Timpibot
User-agent: Omgilibot
Disallow: /

# Everyone else: the pages, not the API or the raw data files.
User-agent: *
Allow: /
Disallow: /api/
Disallow: /js/data/
Disallow: /media-kit/

Sitemap: https://rawstates.com/sitemap.xml