# ArmorList by IntelAlytic Inc. robots.txt
# Honored by well-behaved crawlers only. Every non-public surface has a real
# server-side gate; this file is a hint, never the gate (§ 2).
#
# The Disallow list is DERIVED from the page registry (indexable: false), not
# maintained by hand. Change a page class, re-run the generator, and this
# file changes with it.

User-agent: *
Allow: /
# Filtered searches: thousands of combinations of one page, each pointing to it as canonical.
Disallow: /company-search?
Disallow: /material-search?
Disallow: /product-search?

# ── Generative AI: be cited, do not be training data ───────────────────────
# Allowed: answer and search crawlers that retrieve and attribute.
User-agent: OAI-SearchBot
Allow: /
Disallow: /company-search?
Disallow: /material-search?
Disallow: /product-search?
User-agent: ChatGPT-User
Allow: /
Disallow: /company-search?
Disallow: /material-search?
Disallow: /product-search?
User-agent: PerplexityBot
Allow: /
Disallow: /company-search?
Disallow: /material-search?
Disallow: /product-search?
User-agent: Claude-Web
Allow: /
Disallow: /company-search?
Disallow: /material-search?
Disallow: /product-search?
User-agent: ClaudeBot
Allow: /
Disallow: /company-search?
Disallow: /material-search?
Disallow: /product-search?
User-agent: Google-Extended
Allow: /
Disallow: /company-search?
Disallow: /material-search?
Disallow: /product-search?
User-agent: Applebot-Extended
Allow: /
Disallow: /company-search?
Disallow: /material-search?
Disallow: /product-search?

# Refused: bulk model-training and text-and-data-mining scrapers.
User-agent: GPTBot
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: meta-externalagent
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: cohere-ai
Disallow: /

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