#
# robots.txt
#
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/robotstxt.html

User-agent: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.txt
Disallow: /web.config
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
Disallow: /disclaimer/
# Paths (no clean URLs)
Disallow: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/user/password/
Disallow: /index.php/user/register/
Disallow: /index.php/user/login/
Disallow: /index.php/user/logout/
Disallow: /index.php/disclaimer/

# Block MJ12bot as it is just noise
User-agent: MJ12bot
Disallow: /

# Block Ahrefs
User-agent: AhrefsBot
Disallow: /

# Block Sogou
User-agent: sogou spider
Disallow: /

# Block SEOkicks
User-agent: SEOkicks-Robot
Disallow: /

# Block BlexBot
User-agent: BLEXBot
Disallow: /

# Block SISTRIX
User-agent: SISTRIX Crawler
Disallow: /

# Block Uptime robot
User-agent: UptimeRobot/2.0
Disallow: /

User-agent: 008
Disallow: /

# Block Ezooms Robot
User-agent: Ezooms Robot
Disallow: /

# Block Perl LWP
User-agent: Perl LWP
Disallow: /

# Block BlexBot
User-agent: BLEXBot
Disallow: /

# Block netEstate NE Crawler (+http://www.website-datenbank.de/)
User-agent: netEstate NE Crawler (+http://www.website-datenbank.de/)
Disallow: /

# Block WiseGuys Robot
User-agent: WiseGuys Robot
Disallow: /

# Block WiseGuys Robot
User-agent: Vagabondo/4.0
Disallow: /

# Block Turnitin Robot
User-agent: Turnitin Robot
Disallow: /

User-agent: TurnitinBot/3.0 (http://www.turnitin.com/robot/crawlerinfo.html)
Disallow: /

User-agent: TurnitinBot/3.0
Disallow: /

# Block Heritrix
User-agent: Heritrix
Disallow: /

# Block pricepi
User-agent: pimonster
Disallow: /
User-agent: Pimonster
Disallow: /

# Block Searchmetrics Bot
User-agent: SearchmetricsBot
Disallow: /

# Block Eniro
User-agent: ECCP/1.0 (search@eniro.com)
Disallow: /

# Block YandexBot
User-agent: Yandex
Disallow: /

# Block Baidu
User-agent: Baiduspider
User-agent: Baiduspider-video
User-agent: Baiduspider-image
User-agent: Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)
User-agent: Mozilla/5.0 (compatible; Baiduspider/3.0; +http://www.baidu.com/search/spider.html)
User-agent: Mozilla/5.0 (compatible; Baiduspider/4.0; +http://www.baidu.com/search/spider.html)
User-agent: Mozilla/5.0 (compatible; Baiduspider/5.0; +http://www.baidu.com/search/spider.html)
User-agent: Baiduspider/2.0
User-agent: Baiduspider/3.0
User-agent: Baiduspider/4.0
User-agent: Baiduspider/5.0
Disallow: /

# Block SoGou
User-agent: Sogou Spider
Disallow: /

# Block Youdao
User-agent: YoudaoBot
Disallow: /

# Block Nikon JP Crawler
User-agent: gsa-crawler (Enterprise; T4-KNHH62CDKC2W3; gsa_manage@nikon-sys.co.jp)
Disallow: /

# Block  MegaIndex.ru
User-agent: MegaIndex.ru/2.0
Disallow: /

User-agent: MegaIndex.ru
Disallow: /

User-agent: megaIndex.ru
Disallow: /