# # robots.txt # # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # # This file will be ignored unless it is at the root of your host: # Used: http://example.com/robots.txt # Ignored: http://example.com/site/robots.txt # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/robotstxt.html User-agent: Googlebot Allow: / User-agent: Bingbot Allow: / User-agent: YandexBot Allow: / User-agent: DuckDuckBot Allow: / User-agent: Google-Extended Allow: / User-agent: Applebot Allow: / User-agent: FacebookExternalHit Allow: / User-agent: Pinterestbot Allow: / User-agent: LinkedInBot Allow: / User-agent: amazon-kendra # Amazon Kendra Web Crawler Allow: /articles* # Allow artcile listing pages. Allow: /news/* # Allow article landing pages. Allow: /vault/* # Allow article landing pages. User-agent: bedrockbot-L1VRSRC4OX Allow: /articles* # Allow artcile listing pages. Allow: /news/* # Allow article landing pages. Allow: /vault/* # Allow article landing pages. User-agent: bedrockbot Allow: /articles* # Allow artcile listing pages. Allow: /news/* # Allow article landing pages. Allow: /vault/* # Allow article landing pages. User-agent: * Disallow: / Sitemap: https://worldviewtube.com/sitemap.xml