#
# 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/

# 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/

User-agent: *
Allow: /

Sitemap: https://www.deltafaucet.com/sitemap.xml

# Legacy
Disallow: *.json$
Disallow: /tooltip/
Disallow: /search/
Disallow: compare.html
Disallow: /customersupport/results.html
Disallow: /alfresco/
Disallow: /kitchen/collection/*/colorbox.html
Disallow: /bath/collection/*/colorbox.html
Disallow: /tooltips/
Disallow: /includes/
Disallow: /kitchen/*/thickbox-emailcollection.html
Disallow: /bath/*/thickbox-emailcollection.html
Disallow: /thickbox-collectionvideo.html
Disallow: /customersupport/faq/*/colorbox/
Disallow: /thickbox-changebackground.html
Disallow: /send-to-phone.html
Disallow: /company/ads/videos/
Disallow: /smart-solutions/videos/
Disallow: /login.html
Disallow: /includes/send-to-phone.html
Disallow: /user/forgotpassword.html
Disallow: /product/thickbox-printproduct.html
Disallow: /*/thickbox-emailproduct.html
Disallow: /product/txtmsg.html
Disallow: /txtmsg/sendmobilelink.html
Disallow: /*/*/reorder.html
Disallow: /thickbox-morephotos.html
Disallow: /thickbox-collectionphotos.html
Disallow: /thickbox-collectionvideo.html
Disallow: /thickbox-product360.html
Disallow: /parts/id-my-product/
Disallow: /parts/troubleshoot-your-product/
Disallow: /parts/commonly-used-parts/

Crawl-delay: 10

# Source: http://en.wikipedia.org/robots.txt
# 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: Justdial
Disallow: /

# The BusinessOnLine crawler needs this for permission
User-Agent: MJ12bot
Disallow: /