# advertising-related bots:
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
User-agent: DOC
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
User-agent: Zealbot
User-agent: MSIECrawler
User-agent: SiteSnagger
User-agent: WebStripper
User-agent: WebCopier
User-agent: Fetch
User-agent: Offline Explorer
User-agent: Teleport
User-agent: TeleportPro
User-agent: WebZIP
User-agent: linko
User-agent: HTTrack
User-agent: Microsoft.URL.Control
User-agent: Xenu
User-agent: larbin
User-agent: libwww
User-agent: ZyBORG
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
User-agent: NPBot
Disallow: /

# A capture bot, downloads gazillions of pages with no public benefit
User-agent: WebReaper
Disallow: /

# Friendly, low-speed bots are welcome viewing pages, but not everything
User-agent: *
Disallow: /admin

# Some RES2 stuff, maybe some crawlers obey these rules.
Crawl-delay: 3            # wait at least 3 seconds for crawling
Request-rate: 1/3         # maximum rate is one page every 3 seconds
Visit-time: 0100-0630     # only visit between 1:00 AM and 6:30 AM UT (GMT)