# ========================================== # Newswise Robots Policy – Updated 2025-11-03 # ========================================== Sitemap: https://www.newswise.com/sitemap.xml Sitemap: https://www.newswise.com/news-sitemap.xml # ========================================== # Tier 1 Google Search bots # ========================================== User-agent: Googlebot Allow: / Disallow: /tracker/c/ User-agent: Googlebot-News Allow: / User-agent: Googlebot-Image Allow: / User-agent: Googlebot-Mobile Allow: / User-agent: facebookexternalhit Allow: / # ========================================== # Tier 1 Other major search bots # ========================================== User-agent: Applebot Allow: / Crawl-delay: 10 User-agent: Bingbot Allow: / Crawl-delay: 10 # ========================================== # Tier 2 SEO crawlers (restricted) # ========================================== User-agent: AhrefsBot Crawl-delay: 10 User-agent: SemrushBot Crawl-delay: 10 User-agent: Baiduspider Crawl-delay: 20 # ========================================== # Tier 3 Block Bad / Low-Value Crawlers # ========================================== User-agent: SputnikBot Disallow: / User-agent: DotBot Disallow: / User-agent: Majestic Disallow: / User-agent: PetalBot Disallow: / User-agent: Baiduspider-video Disallow: / User-agent: Baiduspider-image Disallow: / # ========================================== # Tier 4 Block AI Model Training Crawlers # ========================================== User-agent: GPTBot Disallow: / User-agent: ClaudeBot Disallow: / User-agent: Google-Extended Disallow: / User-agent: Amazonbot Disallow: / User-agent: Bytespider Disallow: / User-agent: CCBot Disallow: / User-agent: Meta-ExternalAgent Disallow: / User-agent: Bytespider Disallow: / # ========================================== # Tier 5 Global Rules (apply to ALL bots) # ========================================== User-agent: * # Allowed resources (JS, CSS, Experts pages) Allow: /javascripts/ Allow: /stylesheets/ Allow: /users/expert/ Allow: /users/expert-list/ Allow: /sitemaps/ # Disallowed internal or duplicate sections Disallow: /search/ Disallow: /cdn-cgi/l/email-protection Disallow: /nz/feed_widget/ Disallow: /nz/search_google Disallow: /reports/ Disallow: /legacy/ Disallow: /images/uploads/ Disallow: /archive/get_wire Disallow: /nz/clips_view/ Disallow: /archive/list_wires Disallow: /multimedia/ Disallow: /special-channel/tabarticles/ Disallow: /Users/rotate-image Disallow: /users/register/ Disallow: /users/login/ Disallow: /users/register Disallow: /users/login Disallow: /cdn-cgi/ Crawl-delay: 15