November 26, 2024

Robots.txt for scientificamerican.com

        User-agent: 008
Disallow: /

User-agent: *
Sitemap: https://www.scientificamerican.com/sciam/sitemap.xml
Sitemap: https://blogs.scientificamerican.com/blogs/sitemap.xml

Crawl-Delay: 5
Disallow: /admin/
Disallow: /tasks/
Disallow: /requirements/
Disallow: /config/

Disallow: /default/

Disallow: /page/slbu
Disallow: /page/scientific-american-mind-digital-subscription-user-guide/
Disallow: /page/scientific-american-digital-subscription-user-guide/
Disallow: /my-account
Disallow: /products/world-war-i/?category=*
Disallow: /sciam/remote/*
Disallow: /sciam/esi-my-account.cfm*
Disallow: /checkout/cart
Disallow: /checkout
Disallow: /upgrade-offer/

Disallow: /arabic/
Disallow: /espanol/
Disallow: /blog/
Disallow: /tag/
Disallow: /search/?*

Disallow: /store/
Disallow: /magazine/
Disallow: /search/

User-agent: CCBot
Disallow: /
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-Agent: RepoLookupBot
Disallow: /
User-Agent: AwarioSmartBot
Disallow: /
User-Agent: PerplexityAI
Disallow: /