# # robots.txt inspired from http://www.wikipedia.org/ # # Please note: There are some misbehaved spiders out there that # go _way_ too fast. If you're irresponsible, your access to the # site may be blocked. # Sitemap: http://www.zamtam.fr/static/sitemaps/www.zamtam.fr/sitemap_index.xml User-agent: * Disallow: /category.all/ Disallow: /category.computer/ Disallow: /category.pregnancy/ Disallow: /category.clothing/ Disallow: /category.video.audio/ Disallow: /category.games/ Disallow: /category.cars/ Disallow: /category.real.estate/ Disallow: /category.* Disallow: /make.* Disallow: /fuel.* Disallow: /provider.* Disallow: /s.* Disallow: /dyn/search Disallow: /*? User-agent: Mediapartners-Google Disallow: /category.all/ Disallow: /category.computer/ Disallow: /category.pregnancy/ Disallow: /category.clothing/ Disallow: /category.video.audio/ Disallow: /category.games/ Disallow: /category.cars/ Disallow: /category.real.estate/ Disallow: /category.* Disallow: /make.* Disallow: /fuel.* Disallow: /provider.* Disallow: /s.* Disallow: /dyn/search Disallow: /*?update # Crawlers that are kind enough to obey, but which we'd rather not have # unless they're feeding search engines. User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / # Some bots are known to be trouble, particularly those designed to copy # entire sites. Please obey robots.txt. 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: / # # Sorry, wget in its recursive mode is a frequent problem. # Please read the man page and use it properly; there is a # --wait option you can use to set the delay between hits, # for instance. # User-agent: wget Disallow: / # # The 'grub' distributed client has been *very* poorly behaved. # User-agent: grub-client Disallow: / # # Doesn't follow robots.txt anyway, but... # User-agent: k2spider Disallow: / # # Hits many times per second, not acceptable # http://www.nameprotect.com/botinfo.html User-agent: NPBot Disallow: / # A capture bot, downloads gazillions of pages with no public benefit # http://www.webreaper.net/ User-agent: WebReaper Disallow: / # Some other crawlers User-agent: Custo Disallow: / User-agent: Vagabondo Disallow: / User-agent: larbin Disallow: / User-agent: Walhello appie Disallow: / User-agent: Netcraft Disallow: / User-agent: SurveyBot Disallow: / User-agent: Voila Disallow: / User-agent: TencentTraveler Disallow: / User-agent: psbot Disallow: / User-agent: Python-urllib Disallow: / User-agent: Nutch Disallow: / User-agent: NutchCVS Disallow: / User-agent: Java Disallow: /