# robots.txt
# Tell "bitlybot" not to come here at all
User-agent: bitlybot
Disallow: /
# From NYT.com - nobody seems to like this bot
User-agent: Mediapartners-Google
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: /
User-agent: 008
Disallow: /
User-agent: heritrix
Disallow: /
User-agent: heritrix/3.3.0-SNAPSHOT-20140926-2021
Disallow: /
User-agent: BLEXBot
Disallow: /
User-agent: NTENTbot
Disallow: /
User-agent: GigablastOpenSource
Disallow: /
User-agent: omgilibot
Disallow: /
User-agent: Mozilla/5.0 (compatible; Genieo/x.x http://www.genieo.com/webfilter.html)
Disallow: /
User-agent: Mozilla/5.0 (TweetmemeBot/4.0; +http://datasift.com/bot.html) Gecko/20100101 Firefox/31.0
Disallow: /
User-agent: crawler4j
Disallow: /
User-agent: MetaURI
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: /
#
# Friendly, low-speed bots are welcome viewing pages.
#
User-agent: *
Disallow: /media/
Disallow: /login/
Disallow: /account/
Disallow: */checkout/*
Crawl-Delay: 5
Host-load: 1
#
# GoogleBot
#
User-agent: googlebot
Disallow: /media/
Disallow: /login/
Disallow: /account/
Disallow: */checkout/*
#
# MSN Bot listens to Crawl-Delay
#
User-Agent: msnbot
Crawl-Delay: 5
Disallow: /media
Disallow: /login
Disallow: /account
Disallow: */checkout/*
User-Agent: msnbot-NewsBlogs/1.1 (+http://search.msn.com/msnbot.htm)
Crawl-Delay: 5
Disallow: /media
Disallow: /login
Disallow: /account
Disallow: */checkout/*
User-Agent: msnbot/2.0b (+http://search.msn.com/msnbot.htm)
Crawl-Delay: 5
Disallow: /media
Disallow: /login
Disallow: /account
Disallow: */checkout/*
#
# Yahoo/Inktomi listens to Crawl-Delay
#
User-Agent: Slurp
Crawl-Delay: 60
User-Agent: Mozilla/5.0 (compatible; Yahoo! Slurp/3.0; http://help.yahoo.com/help/us/ysearch/slurp)
Crawl-Delay: 60
User-Agent: Mozilla/5.0 (compatible; spbot/2.0.2; +http://www.seoprofiler.com/bot/ )
Disallow: /
#Baiduspider
User-agent: Baiduspider
Crawl-Delay: 60
#Yandex
User-agent: Yandex
Crawl-Delay: 60