# This site's content is provided for human readers and disclosed search/AI-answer citation only.
# Commercial scraping, bulk extraction, or use of this content to train AI models is not authorized.
# See /terms for our full Terms of Service.

User-agent: *
Allow: /

# =====================================================
# AI training crawlers — disallowed. We do not permit
# our content to be copied into AI model training sets.
# =====================================================
User-agent: GPTBot
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: img2dataset
Disallow: /
User-agent: HuggingFaceBot
Disallow: /
User-agent: Ai2Bot
Disallow: /
User-agent: MistralAI-Bot
Disallow: /
User-agent: xAI-Bot
Disallow: /
User-agent: Timpibot
Disallow: /

# AI retrieval/citation crawlers — explicitly allowed.
# These answer live user queries and cite back to us.
User-agent: ChatGPT-User
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: Claude-Web
Allow: /

# Traditional search engines — explicitly allowed.
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /

Sitemap: https://newsanarchist.com/sitemap.xml
Sitemap: https://newsanarchist.com/sitemap-news.xml