#
# 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: *
Crawl-delay: 20
Crawl-limit:5
# CSS, JS, Images
Allow: /misc/*.css$
Allow: /misc/*.css?
Allow: /misc/*.js$
Allow: /misc/*.js?
Allow: /misc/*.gif
Allow: /misc/*.jpg
Allow: /misc/*.jpeg
Allow: /misc/*.png
Allow: /modules/*.css$
Allow: /modules/*.css?
Allow: /modules/*.js$
Allow: /modules/*.js?
Allow: /modules/*.gif
Allow: /modules/*.jpg
Allow: /modules/*.jpeg
Allow: /modules/*.png
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: /themes/*.css$
Allow: /themes/*.css?
Allow: /themes/*.js$
Allow: /themes/*.js?
Allow: /themes/*.gif
Allow: /themes/*.jpg
Allow: /themes/*.jpeg
Allow: /themes/*.png
# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/
Disallow: /sites/all/
# Files
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /INSTALL.sqlite.txt
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
Disallow: /xmlrpc.php
# Paths (clean URLs)
Disallow: /*/wv/
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: /fileadmin/
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=filter/tips/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Disallow: /?q=user/logout/



User-agent: MJ12bot
User-agent: AhrefsBot
Disallow: /


User-agent: MauiBot
Disallow: /

User-agent:Googlebot/2.1
Crawl-delay: 60

User-agent: msnbot
Crawl-delay: 10

User-agent: bingbot
Crawl-delay: 10
Crawl-limit:5

User-Agent: rogerbot
Disallow: /sites/default/files/
Crawl-Delay: 10

User-Agent: rogerbot
Crawl-limit:5


User-Agent: SemrushBot
Crawl-limit:5

User-Agent: SemrushBot-BA
Crawl-limit:5


User-agent: dotbot
Crawl-Delay: 30
Disallow: /sites/default/files/

User-agent: BomboraBot
Crawl-Delay: 60

User-agent: Y!J-ASR/1.0
Crawl-Delay: 60

User-agent: Gigabot
Disallow: /

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


User-agent: MegaIndex.ru
Disallow: /

User-agent: AlphaSeoBot
Disallow: /

User-agent: AlphaSeoBot-SA
Disallow: /

User-agent: spbot
Crawl-delay: 40

User-Agent: The Knowledge AI
Disallow: /

User-agent: SemrushBot
Disallow: /

User-Agent: panscient.com
Disallow: /

User-agent: G-i-g-a-b-o-t
Disallow: /

User-agent: Barkrowler
Disallow: /

User-Agent: panscient
Disallow: /

User-Agent: coccocbot-web/1.0
Disallow: /

User-Agent: coccocbot-web
Disallow: /

User-agent: BUbiNG
Disallow: /


User-agent: PiplBot
Disallow: /

User-agent: CCBot
Crawl-Delay: 30