# robots.txt for http://www.rudata.ru/ (running modified MediaWiki 1.8 site engine)
# based on Wikimedia Foundation robots.txt file
# If several directives fit some URL, then the first directive in selected User-agent block is used

# Friendly, low-speed bots are welcome viewing article pages, but not
# dynamically-generated pages please.
User-agent: *
Disallow: /d86b9d906faba42d911a0f1ba21d51e8/
Disallow: /w/index.php
Disallow: /wiki/%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F:Search
Disallow: /wiki/%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F%3ASearch
Disallow: /wiki/%d0%a1%d0%bb%d1%83%d0%b6%d0%b5%d0%b1%d0%bd%d0%b0%d1%8f:Search
Disallow: /wiki/%d0%a1%d0%bb%d1%83%d0%b6%d0%b5%d0%b1%d0%bd%d0%b0%d1%8f%3aSearch
Disallow: /wiki/Special:Search
Disallow: /wiki/Special%3ASearch
Disallow: /wiki/Special%3aSearch
Sitemap: http://www.rudata.ru/sitemap-index-wikidb.xml

User-agent: Yandex
Allow: *format=yandexnews
Disallow: /d86b9d906faba42d911a0f1ba21d51e8/
Disallow: /w/index.php
Disallow: /wiki/%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F:Search
Disallow: /wiki/%D0%A1%D0%BB%D1%83%D0%B6%D0%B5%D0%B1%D0%BD%D0%B0%D1%8F%3ASearch
Disallow: /wiki/%d0%a1%d0%bb%d1%83%d0%b6%d0%b5%d0%b1%d0%bd%d0%b0%d1%8f:Search
Disallow: /wiki/%d0%a1%d0%bb%d1%83%d0%b6%d0%b5%d0%b1%d0%bd%d0%b0%d1%8f%3aSearch
Disallow: /wiki/Special:Search
Disallow: /wiki/Special%3ASearch
Disallow: /wiki/Special%3aSearch
Sitemap: http://www.rudata.ru/sitemap-index-wikidb.xml
# Crawl-delay: 5

# advertising-related bots:
#
User-agent: Mediapartners-Google
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: /

# --------------------------------------------------------------------------------

# Backup:
# Disallow: /contrib/
# Disallow: /eaccelerator/
# Disallow: /forbidden/
# Disallow: /forum/
# Disallow: /kt/
# Disallow: /oz/
# Disallow: /oz-grabber/
# Disallow: /phpwebadmin/
# Disallow: /rc/
# Disallow: /restricted/
# Disallow: /statistics/
# Disallow: /xampp/

# Don't allow the wayback-maschine to index user-pages
# User-agent: ia_archiver
# Disallow: /wiki/User:
# Disallow: /wiki/User%3A
# Disallow: /wiki/%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:
# Disallow: /wiki/%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA%3A

# Request-rate: 1/5         # maximum rate is one page every 5 seconds
# Visit-time: 0600-0845     # only visit between 6:00 AM and 8:45 AM UT (GMT)

# Checklist:
# http://www.rudata.ru/w/images/a
# http://www.rudata.ru/w/index.php?title=a
# http://www.rudata.ru/wiki/a
# http://www.rudata.ru/wiki/Special:Search
# http://www.rudata.ru/contrib/script.php
# http://www.rudata.ru/w/index.php?title=Special:Newsfeed&format=yandexnews