#
# 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: *
Crawl-delay: 10
# 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: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/
Disallow: /core/
Disallow: /profiles/

# 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
Disallow: /README.txt
Disallow: /web.config

# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/
Disallow: /comment/reply/
Disallow: /filter/tips/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
Disallow: /people/register/
Disallow: /people/password/
Disallow: /people/login/
Disallow: /people/logout/
Disallow: /admin/content/benefit/
Disallow: /admin/content/benefit
Disallow: /cgi-bin/
Disallow: /home/indigohe/public_html/snip-right-sidebar.php

# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=filter/tips/
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: /?q=people/password/
Disallow: /?q=people/register/
Disallow: /?q=people/login/
Disallow: /?q=people/logout/
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/people/password
Disallow: /index.php/people/register
Disallow: /index.php/people/login
Disallow: /index.php/people/logout

# Google Image Crawler Setup
User-agent: Googlebot-Image
Disallow:

# Google Crawler Setup
User-agent: Googlebot
Allow: /*.css$
Allow: /*.css?
Allow: /*.js$
Allow: /*.js?
Allow: /*.gif
Allow: /*.jpg
Allow: /*.jpeg
Allow: /*.png
Allow: /*.svg

User-agent: AwarioBot
User-agent: SeekportBot
User-agent: YandexBot
User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: Baiduspider
User-agent: 360Spider
User-agent: Yisouspider
User-agent: PetalBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Sogou web spider
Disallow: /

User-agent: Sogou inst spider
Disallow: /

User-agent: GPTBot
Disallow: /

# Start: Block ChatGPT crawler
User-agent: ChatGPT-User
Disallow: /
# End

sitemap: https://www.indigo-herbs.co.uk/sitemap.xml