User-agent: * Disallow: /news/yellow/ Disallow: /files/ Disallow: /news/summerscoop/ Disallow: /computing/ Disallow: /giving/honorroll/ Disallow: /news/weekly/ Disallow: /archive/ # Disallow: /news/calendar/ical.cfm Disallow: /gts/w/ Disallow: /biology/systematics/w/ Disallow: /general_catalog/18_19/ Disallow: /general_catalog/17_18/ Disallow: /general_catalog/16_17/ Disallow: /general_catalog/15_16/ Disallow: /general_catalog/14_15/ Disallow: /general_catalog/13_14/ Disallow: /general_catalog/12_13/ Disallow: /general_catalog/11_12/ Disallow: /general_catalog/10_11/ Disallow: /general_catalog/09_10/ Disallow: /general_catalog/08_09/ Disallow: /general_catalog/07_08/ Disallow: /general_catalog/06_07/ Disallow: /general_catalog/05_06/ Disallow: /general_catalog/04_05/ Disallow: /general_catalog/03_04/ Disallow: /general_catalog/02_03/ Disallow: /general_catalog/01_02/ Disallow: /general_catalog/00_01/ Disallow: /plugins/ Disallow: /flag-page/ Disallow: /search/ Disallow: /concert/ Disallow: /social/ Disallow: /campus/ Disallow: /welcome/ Disallow: /academics/overlays/ Disallow: /academics/profiles/ Disallow: /giving/donorprofiles/ Disallow: /finearts/ensembles/ Disallow: /feedback/ Disallow: /account/aToZ Disallow: /calendar/exportItem Disallow: /oncampus/ #Disallow: */secure/ Disallow: /about/webcam Disallow: /covid/ Disallow: /library/library_home.php # advertising-related bots: User-agent: Mediapartners-Google* Disallow: / # Wikipedia work bots: User-agent: IsraBot Disallow: User-agent: Orthogaffe Disallow: # 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: /