robots.txt details

saved: size: 3352 kb md5 checksum: 76a7f84f4e30c68a9331ce9555bd960b

websites using this robots.txt

content


#
# robots.txt
#

# First, this is the
# robots.txt from http://www.wikipedia.org/ for "other" robots
# Thanks Wikipedians!
#
# 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.
#
#User-agent: Mediapartners-Google*
#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: /

User-agent: gsa-crawler
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: /

User-agent: CNCDialer
Disallow: /

User-agent: Maxthon
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: Slurp
Disallow: /

User-agent: Screaming Frog SEO Spider
Disallow: /

User-agent: *
Disallow: /wp-content/
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wpi/
Disallow: /trackback/
Disallow: /*/*/*/feed.xml
Allow: /retro/*
Disallow: /retro
Disallow: /login.php/
Disallow: /frontend.php/
Disallow: /api/1.0/migration
Disallow: /server
Disallow: /queue
Disallow: /mobile.php/
Disallow: /app.php/
Disallow: /main.php/
Disallow: /redirect
Disallow: /approve
Disallow: /duplicate
Disallow: /1018282
Disallow: /api/
Disallow: /c/
Disallow: /morepostcomments
Disallow: /offtopic
Disallow: /p/
Disallow: /pda
Disallow: /tracker
Disallow: /.well-known/amphtml/apikey.pub

Disallow: /preview-main/*
Disallow: /respuestas/*
Disallow: /expertos/respuestas/*
Disallow: /usuario/*
Noindex: /respuestas/*
Noindex: /expertos/respuestas/*
Noindex: /usuario/*

Sitemap: https://www.genbeta.com/sitemap_news.xml
Sitemap: https://www.genbeta.com/sitemap_index.xml