# # robots.txt # User-Agent: * Allow: /wp-content/uploads/ Disallow: /wp-content/plugins/ Disallow: /wp-content/themes/ Disallow: /wp-includes/ Disallow: /wp-admin/ # incluye cosas como wp-rss.php Disallow: /wp- # # Sitemap permitido, búsquedas no. # Sitemap: http://tu-web/sitemap.xml Disallow: /?s= Disallow: /search # # # # Robots.txt Based on Sigt # Allow: /feed/$ Disallow: /feed Disallow: /comments/feed Disallow: /*/feed/$ Disallow: /*/feed/rss/$ Disallow: /*/trackback/$ Disallow: /*/*/feed/$ Disallow: /*/*/feed/rss/$ Disallow: /*/*/trackback/$ Disallow: /*/*/*/feed/$ Disallow: /*/*/*/feed/rss/$ Disallow: /*/*/*/trackback/$ # # Boots que suelen sobrecargar el site # #User-agent: MSIECrawler #Disallow: / #User-agent: WebCopier #Disallow: / #User-agent: HTTrack #Disallow: / #User-agent: Microsoft.URL.Control #Disallow: / #User-agent: libwww #Disallow: / # #Delay de Boots # User-agent: noxtrumbot Crawl-delay: 50 User-agent: msnbot Crawl-delay: 30 User-agent: Slurp Crawl-delay: 10