MediaWiki:Robots.txt

維基文庫,自由的圖書館
跳到导航 跳到搜索

#

#
# robots.txt for http://www.wikisource.org/ and friends
#
# Please note: There are a lot of pages on this site, and there are
# some misbehaved spiders out there that go _way_ too fast. If you're
# irresponsible, your access to the site may be blocked.
#
# Edit at http://zh.wikisource.org/w/index.php?title=MediaWiki:Robots.txt&action=edit
#
# Please check any changes using a syntax validator such as http://tool.motoricerca.info/robots-checker.phtml
# Enter http://zh.wikisource.org/robots.txt as the URL to check.
#

# 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: /

# Don't allow the wayback-maschine to index user-pages
#User-agent: ia_archiver
#Disallow: /wiki/User
#Disallow: /wiki/Benutzer

#
# Friendly, low-speed bots are welcome viewing article pages, but not
# dynamically-generated pages please.
#
# Inktomi's "Slurp" can read a minimum delay between hits; if your
# bot supports such a thing using the 'Crawl-delay' or another
# instruction, please let us know.
#
User-agent: *
Disallow: /w/
Disallow: /trap/
Disallow: /wiki/Special:Random
Disallow: /wiki/Special%3ARandom
Disallow: /wiki/Special:Search
Disallow: /wiki/Special%3ASearch
Disallow:http://zh.wikisource.org/wiki/Category:%E6%80%80%E7%96%91%E4%BE%B5%E7%8A%AF%E7%89%88%E6%9D%83%E6%96%87%E7%AB%A0

Sitemap: http://sitemap.wikimedia.org/zhwikisource/latest/zhwikisource-latest-abstract.xml
Sitemap: http://sitemap.wikimedia.org/zhwikisource/latest/zhwikisource-latest-abstract.xml-rss.xml
Sitemap: http://zh.wikisource.org/w/index.php?title=Special:NewPages&feed=rss&namespace=all

#