# 27/04/2020 # robots.txt para la LaRepublica.pe # User-agent: * Disallow: /buscador* Disallow: /terminos-de-uso Disallow: /data Disallow: /data/* Disallow: /contactenos Disallow: /*/pag/ Disallow: /*/pag/* Disallow: /*/*/page/* User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / User-agent: sitecheck.internetseer.com Disallow: / User-agent: Zealbot Disallow: / User-agent: MSIECrawler Disallow: / User-agent: SiteSnagger Disallow: / User-agent: WebStripper Disallow: / User-agent: WebCopier Disallow: / User-agent: Fetch Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: WebZIP Disallow: / User-agent: linko Disallow: / User-agent: HTTrack Disallow: / User-agent: Microsoft.URL.Control Disallow: / User-agent: Xenu Disallow: / User-agent: larbin Disallow: / User-agent: libwww Disallow: / User-agent: ZyBORG Disallow: / User-agent: Download Ninja Disallow: / User-agent: wget Disallow: / User-agent: grub-client Disallow: / User-agent: k2spider Disallow: / User-agent: NPBot Disallow: / User-agent: WebReaper Disallow: / User-agent: grapeshot Disallow: User-agent: BLP_bbot/0.1 Disallow: / User-agent: BLP_bbot Disallow: / User-agent: TweetmemeBot Disallow: / User-agent: MegaIndex Disallow: / User-agent: MegaIndex.ru/2.0 Disallow: / User-agent: RavenCrawler Disallow: / Sitemap: https://larepublica.pe/sitemaps/noticias.xml?outputType=xml