wikibase/robots.txt

176 lines
3.7 KiB
Plaintext

# robots.txt for http://www.wikipedia.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.
#
# Observed spamming large amounts of https://en.wikipedia.org/?curid=NNNNNN
# and ignoring 429 ratelimit responses, claims to respect robots:
# http://mj12bot.com/
User-agent: MJ12bot
Disallow: /
# 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: /
# Misbehaving: requests much too fast:
User-agent: fast
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 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.
#
# There is a special exception for API mobileview to allow dynamic
# mobile web & app views to load section content.
# These views aren't HTTP-cached but use parser cache aggressively
# and don't expose special: pages etc.
#
# Another exception is for REST API documentation, located at
# /api/rest_v1/?doc.
#
User-agent: *
Allow: /w/api.php?action=mobileview&
Allow: /w/load.php?
Allow: /api/rest_v1/?doc
Allow: /w/images/
Allow: /
Disallow: /w/
Disallow: /api/
Disallow: /trap/
Disallow: /wiki/Special:
Disallow: /wiki/Special%3A
# https://phabricator.wikimedia.org/T16075
Disallow: /wiki/MediaWiki:Spam-blacklist
Disallow: /wiki/MediaWiki%3ASpam-blacklist
Disallow: /wiki/MediaWiki_talk:Spam-blacklist
Disallow: /wiki/MediaWiki_talk%3ASpam-blacklist
#
Disallow: /wiki/Template%3AEditnotices
#
Disallow: /wiki/Category:Noindexed_pages
Disallow: /wiki/Category%3ANoindexed_pages
#
# User sandboxes for modules and Template Styles are placed in these subpages for testing
#
Disallow: /wiki/Module:Sandbox
Disallow: /wiki/Module%3ASandbox
Disallow: /wiki/Template:TemplateStyles_sandbox
Disallow: /wiki/Template%3ATemplateStyles_sandbox