# Sample robots.txt file (make sure the filename is ALL LOWERCASE on Linux/Unix systems)
# This file should go in your web site's ROOT directory
#  The root directory is where your site's main /index.html file would be found
#  It is usually found in /yourhomedir/public_html/ or /yourhomedir/httpdocs
#  Where "yourhomedir" is your user account's name
#
# We invite you to also check out our popular contribution: Simple Template System (STS)
#  It lets you layout or change your OSC look-and-feel by modifying a single HTML file
#  http://www.oscommerce.com/community/contributions,1524 or SimpleTemplateSystem.com
#  Enjoy!   - Brian Gallagher @ DiamondSea.com

# This says to apply these settings to ALL search engine spiders/crawlers
User-agent: * 
Crawl-delay: 2
Allow: /

User-agent: PerplexityBot
Disallow: /
User-agent: OAI-SearchBot
Disallow: /
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: Microsoft-AI
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Anthropic-ai
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: AhrefsBot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: contabot
Disallow: /
User-agent: dataprovider
Disallow: /
User-agent: DigExt
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: EmailCollector
Disallow: /
User-agent: ExtractorPro
Disallow: /
User-agent: MegaIndex
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: WebCollector
Disallow: /
User-agent: WebCopier
Disallow: /
User-agent: AliyunSecBot
Disallow: /
User-agent: AwarioBot
Disallow: /
User-agent: BW/
Disallow: /
User-agent: IonCrawl
Disallow: /
User-agent: ISSCyberRiskCrawler
Disallow: /
User-agent: Bytespider
Disallow: /


# These settings will keep spiders from indexing your unwanted pages 
#   This assumes that your OSC install is in your web site's ROOT directory
Disallow: /admin
Disallow: /account.php
Disallow: /checkout_shipping.php
Disallow: /create_account.php
Disallow: /login.php
Disallow: /login.php?
Disallow: /logout.php
Disallow: /popup_image.php
Disallow: /password_forgotten.php
Disallow: /shopping_cart.php
Disallow: /contact_us.php
Disallow: /advanced_search.php
Disallow: /dynamic_sitemap.php
Disallow: /account_notifications.php

# These settings will keep spiders from indexing your unwanted pages 
#   This assumes that your OSC install is in your web site's ROOT directory
#   ie: http://www.yoursite.com/catalog/index.php <- Use if this brings up your OSC main page
# Disallow: /admin
# Disallow: /account.php
# Disallow: /advanced_search.php
# Disallow: /checkout_shipping.php
# Disallow: /create_account.php
# Disallow: /login.php
# Disallow: /logout.php
# Disallow: /password_forgotten.php
# Disallow: /popup_image.php
# Disallow: /shopping_cart.php
# Disallow: /contact_us.php
# Disallow: /advanced_search.php
# Disallow: /dynamic_sitemap.php

# Feel free to add any other pages on your site that you don't want to be indexed by 
#  the search engines.  
# PLEASE NOTE: Any pages that you list here should be secured by other means if you 
#  don't want people to be able to view them, as some malicious users will look at a
#  robots.txt file to try to find "hidden" or "secret" areas of web sites to find 
#  confidential information.
# Just Uncomment a line or add new ones as you see fit.
# Disallow: /private
# Disallow: /hidden

# IF YOU DO NOT WISH TO HAVE THE GOOGLE IMAGE BOT SCAN YOUR DOMAIN FOR IMAGES
# THEN YOU CAN INCLUDE THE FOLLOWING IN YOUR ROBOTS FILE.
# I FOUND THAT MY BANDWIDTH USAGE DROPPED BY A MASSIVE AMOUNT AFTER I GOT RID
# OF THE GOOGLE IMAGE BOT. ALL I HAD WAS IMAGE HUNTERS STEALING PRODUCT SHOTS
# AND NOT EVEN BROWSING THE SITE.

sitemap: http://cdn.attracta.com/sitemap/326147.xml.gz