#**************************************************************************** # robots.txt # : Robots, spiders, and search engines use this file to detmine which # content they should *not* crawl while indexing your website. # : This system is called "The Robots Exclusion Standard." # : It is strongly encouraged to use a robots.txt validator to check # for valid syntax before any robots read it! # # Examples: # # Instruct all robots to stay out of the admin area. # : User-agent: * # : Disallow: /admin/ # # Restrict Google and MSN from indexing your images. # : User-agent: Googlebot # : Disallow: /images/ # : User-agent: MSNBot # : Disallow: /images/ # # slurp er yahoo # #**************************************************************************** User-agent: * Disallow: /wp-admin/ # disallow search retsult pages Disallow: /?s=* Sitemap: https://loppetjansen.dk/sitemap_index.xml crawl-delay: 30 User-agent: Nuclei User-agent: WikiDo User-agent: Riddler User-agent: PetalBot User-agent: Zoominfobot User-agent: Go-http-client User-agent: Node/simplecrawler User-agent: CazoodleBot User-agent: dotbot/1.0 User-agent: Gigabot User-agent: Barkrowler User-agent: BLEXBot User-agent: magpie-crawler User-agent: yandex User-agent: baiduspider Disallow: /