Sitemap: https://news.sky.com/sitemap.xml

User-Agent: *
Disallow: /preview/*

# Disallow AI Model Training Crawlers
User-agent: AI2Bot
User-agent: AmazonBot
User-agent: anthropic-ai
User-agent: Applebot-Extended
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: Bytespider
User-agent: CCBot
User-agent: ClaudeBot
User-agent: cohere-ai
User-agent: Diffbot
User-agent: FacebookBot
User-agent: Google-Extended
User-agent: GPTBot
User-agent: magpie-crawler
User-agent: Meta-ExternalAgent
User-agent: omgili
User-agent: omgilibot
User-agent: PanguBot
User-agent: PerplexityBot
User-agent: Scrapy
User-agent: TurnitinBot
User-agent: Webzio-Extended
Disallow: /
Allow: /info/policies-and-standards
Allow: /info/library-sales

# Allow user initiated AI actions / searches
User-agent: ChatGPT-User
User-agent: Claude-Web
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: MistralAI-User
User-agent: OAI-SearchBot
User-agent: Perplexity-User
Disallow: /preview/*

# Disallow news aggregators except on RSS.
User-agent: NewsNow
User-agent: news-please
Disallow: /
Allow: /info/policies-and-standards
Allow: /info/library-sales
Allow: /info/rss

User-agent: DataForSeoBot
Disallow: /preview/*