# robots.txt — ArtifactSearch.com
# Generated by the application as the single authoritative source for this file.
# Search engines and AI-SEARCH crawlers may crawl and index the public catalog;
# AI-TRAINING crawlers are disallowed (Content-Signal: ai-train=no plus the
# per-bot groups below). Private and duplicate-URL paths are disallowed for all.

# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no
Allow: /
Allow: /api/search
Allow: /api/img
Allow: /account/login
Allow: /account/register
Disallow: /admin/
Disallow: /api/
Disallow: /account/
Disallow: /cdn-cgi/
Disallow: /go/
Disallow: /partner/agreement
Disallow: /prototype
Disallow: /prototype-round-2
Disallow: /prototype-round-3
# Faceted views of the taxonomy hubs: already noindex, and every item in
# them is reachable from the unfiltered page above. Don't spend crawl
# budget re-walking them. Plain ?page=N is deliberately still allowed.
Disallow: /categories/*?*only=
Disallow: /categories/*?*affiliation=
Disallow: /categories/*?*sort=
Disallow: /categories/*?*perPage=
Disallow: /civil-war/*?*affiliation=
Disallow: /civil-war/*?*sort=
Disallow: /civil-war/*?*perPage=

# AI-training crawlers — fully disallowed. Search and AI-SEARCH crawlers are
# intentionally NOT listed here (they stay under the `*` group above):
# Googlebot, Bingbot, DuckDuckBot, Applebot, OAI-SearchBot, PerplexityBot,
# Claude-SearchBot/Claude-User.
User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: GrokBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

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