# ACM Robots file

# 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: /

User-agent: dotbot
Disallow: /

User-agent: DotBot
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: /

#GOOGLE - Mobile
User-agent: Googlebot
Disallow: /m.cacm.acm.org/browse-by-subject/

#GOOGLE
User-agent: Googlebot
Disallow: /browse-by-subject/

#GOOGLE
User-agent: Googlebot
Disallow: /*/comments

#Yahoo Search
User-agent: Slurp
Crawl-delay: 40
Disallow: /browse-by-subject/

#MSN LiveSearch
User-agent: msnbot
Disallow: /browse-by-subject/

#ASK.COM Search
User-agent: Teoma
Disallow: /browse-by-subject/

#ProQuest Crawler Search
User-agent: Magnolia
Disallow: /browse-by-subject/

# ACM GSA 1; usually gsa1-crawler-acm
User-agent: crawleracm1
Disallow: /browse-by-subject/

# ACM GSA 2
User-agent: gsa2-crawler-acm
Disallow: /browse-by-subject/

# Don't allow indexing by any other bots
# NOTE: this should be "Disallow: /", but the GSAs apparently get tripped up by this.
User-agent: *
Disallow: /browse-by-subject/

#User-agent: *
#Crawl-delay: 60

User-agent: Grabber
Disallow: *