# 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.
#

## added for AI bots
User-agent: Amazonbot
User-agent: GPTBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: cohere-ai
User-agent: Diffbot
User-agent: FacebookBot
User-agent: GoogleOther
User-agent: Google-Extended
User-agent: ImagesiftBot
User-agent: PerplexityBot
User-agent: OmigiliBot
User-agent: Omigili
User-agent: meta-externalagent
Disallow: /

# 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: /

# Per their statement, semrushbot respects crawl-delay directives
# We want them to overall stay within reasonable request rates to
# the backend (20 rps); keeping in mind that the crawl-delay will
# be applied by site and not globally by the bot, 5 seconds seem
# like a reasonable approximation
User-agent: SemrushBot
Crawl-delay: 5

#
# 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 and other uncached content.
#
# Another exception is for REST API documentation, located at
# /api/rest_v1/?doc.
#
User-agent: *
Allow: /api.php?action=mobileview&
Allow: /load.php?
Allow: /api/rest_v1/?doc
Allow: /rest.php/site/v1/sitemap
Disallow: /api/
Disallow: /trap/
Disallow: /Special:
Disallow: /Spezial:
Disallow: /Spesial:
Disallow: /Special%3A
Disallow: /Spezial%3A
Disallow: /Spesial%3A
#
# ar:
Disallow: /%D8%AE%D8%A7%D8%B5:Search
Disallow: /%D8%AE%D8%A7%D8%B5%3ASearch
# T16075
Disallow: /MediaWiki:Spam-blacklist
Disallow: /MediaWiki%3ASpam-blacklist
Disallow: /MediaWiki_talk:Spam-blacklist
Disallow: /MediaWiki_talk%3ASpam-blacklist
#
# hewiki:
Disallow: /%D7%9E%D7%99%D7%95%D7%97%D7%93:Search
Disallow: /%D7%9E%D7%99%D7%95%D7%97%D7%93%3ASearch
#T11517
Disallow: /ויקיפדיה:רשימת_מועמדים_למחיקה/
Disallow: /ויקיפדיה%3Aרשימת_מועמדים_למחיקה/
Disallow: /%D7%95%D7%99%D7%A7%D7%99%D7%A4%D7%93%D7%99%D7%94:%D7%A8%D7%A9%D7%99%D7%9E%D7%AA_%D7%9E%D7%95%D7%A2%D7%9E%D7%93%D7%99%D7%9D_%D7%9C%D7%9E%D7%97%D7%99%D7%A7%D7%94/
Disallow: /%D7%95%D7%99%D7%A7%D7%99%D7%A4%D7%93%D7%99%D7%94%3A%D7%A8%D7%A9%D7%99%D7%9E%D7%AA_%D7%9E%D7%95%D7%A2%D7%9E%D7%93%D7%99%D7%9D_%D7%9C%D7%9E%D7%97%D7%99%D7%A7%D7%94/
Disallow: /ויקיפדיה:ערכים_לא_קיימים_ומוגנים
Disallow: /ויקיפדיה%3Aערכים_לא_קיימים_ומוגנים
Disallow: /%D7%95%D7%99%D7%A7%D7%99%D7%A4%D7%93%D7%99%D7%94:%D7%A2%D7%A8%D7%9B%D7%99%D7%9D_%D7%9C%D7%90_%D7%A7%D7%99%D7%99%D7%9E%D7%99%D7%9D_%D7%95%D7%9E%D7%95%D7%92%D7%A0%D7%99%D7%9D
Disallow: /%D7%95%D7%99%D7%A7%D7%99%D7%A4%D7%93%D7%99%D7%94%3A%D7%A2%D7%A8%D7%9B%D7%99%D7%9D_%D7%9C%D7%90_%D7%A7%D7%99%D7%99%D7%9E%D7%99%D7%9D_%D7%95%D7%9E%D7%95%D7%92%D7%A0%D7%99%D7%9D
Disallow: /ויקיפדיה:דפים_לא_קיימים_ומוגנים
Disallow: /ויקיפדיה%3Aדפים_לא_קיימים_ומוגנים
Disallow: /%D7%95%D7%99%D7%A7%D7%99%D7%A4%D7%93%D7%99%D7%94:%D7%93%D7%A4%D7%99%D7%9D_%D7%9C%D7%90_%D7%A7%D7%99%D7%99%D7%9E%D7%99%D7%9D_%D7%95%D7%9E%D7%95%D7%92%D7%A0%D7%99%D7%9D
Disallow: /%D7%95%D7%99%D7%A7%D7%99%D7%A4%D7%93%D7%99%D7%94%3A%D7%93%D7%A4%D7%99%D7%9D_%D7%9C%D7%90_%D7%A7%D7%99%D7%99%D7%9E%D7%99%D7%9D_%D7%95%D7%9E%D7%95%D7%92%D7%A0%D7%99%D7%9D
#
# huwiki:
Disallow: /Speci%C3%A1lis:Search
Disallow: /Speci%C3%A1lis%3ASearch
#


Sitemap: https://en.wikipedia.org/w/rest.php/site/v1/sitemap/0

#
Disallow: /wiki/Category:Noindexed_pages