# 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
#
# For syntax checking, see:
# http://www.frobee.com/robots-txt-check

User-agent: DotBot 
Disallow: /

User-agent: TurnItInBot 
Disallow: /

User-agent: GarlikCrawler 
Disallow: /

User-agent: Riddler 
Disallow: /

User-agent: CCBot 
Disallow: /

User-agent: NTENTbot 
Disallow: /

User-agent: NTENTbot-fetch 
Disallow: /

User-agent: NTENTbot-news 
Disallow: /

User-agent: ERACrawler 
Disallow: /

User-agent: ConveraCrawler 
Disallow: /

User-agent: mixnode.com 
Disallow: /

# Block SEO crawlers from bringing down site.
User-agent: SemrushBot 
Crawl-delay: 30

User-agent: SemrushBot-SA 
Crawl-delay: 30

User-agent: Yahoo! Slurp 
Crawl-delay: 30

User-agent: Slurp 
Crawl-delay: 30

User-agent: bingbot 
Crawl-delay: 30

User-agent: spbot 
Crawl-delay: 30

User-agent: Applebot 
Crawl-delay: 30

User-agent: Cliqzbot 
Crawl-delay: 30

# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/
Disallow: /product/add/
# 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: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips/
Disallow: /node/add/
Disallow: /search/
Disallow: /user/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
# 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/
Disallow: /*EDITION*
Disallow: archive.ethnologue.com/
Disallow: /node/*
Disallow: /language/*-19*
Disallow: /language/*-18*
Disallow: /language/*-17*