Sitemap: https://www.wikem.org/w/sitemap.xml
Sitemap: http://www.wikem.org/w/sitemap.xml
#
# 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.
#
# 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: /
# Misbehaving: requests much too fast:
User-agent: fast
Disallow: /
# Sorry, wget in its recursive mode is a frequent problem.
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 article pages,
# but not dynamically-generated special pages.
# Slow Bing a little
User-agent: bingbot
Crawl-delay: 10
# Global rules
User-agent: *
# Block Special pages (both pretty URLs and query-string form)
Disallow: /wiki/Special:
Disallow: /w/index.php?title=Special:
# Explicitly block RecentChanges (the heaviest)
Disallow: /wiki/Special:RecentChanges
Disallow: /w/index.php?title=Special:RecentChanges
Disallow: /*title=Special%3ARecentChanges*
# Block internal/runtime directories
Disallow: /w/cache/
Disallow: /w/skins/
Disallow: /nw/
# Allow API mobileview (cached)
Allow: /w/api.php?action=mobileview&