# Google Image Crawler
User-agent: Googlebot-Image
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

# OpenAI
User-agent: GPTBot
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

User-agent: OAI-SearchBot
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

User-agent: ChatGPT-User
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

User-agent: OAI-AdsBot
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

# Anthropic
User-agent: ClaudeBot
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

# Google AI
User-agent: Google-Extended
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

# Amazon AI
User-agent: Amazonbot
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

# Perplexity
User-agent: PerplexityBot
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

# Common Crawl
User-agent: CCBot
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

# You.com
User-agent: YouBot
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

# ByteDance / TikTok
User-agent: Bytespider
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

User-agent: meta-externalagent
Allow: /
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

# Microsoft Bing
User-agent: Bingbot
Crawl-delay: 10
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*


# SEMrush - added 2026-09-17. Origin nginx bad-bot-blocker was returning 444 to
# every SEMrush UA (including GET /robots.txt), so none of this was ever reachable.
# Crawl-delay: 10 is the documented maximum SemrushBot honours.
# Each bot needs its own block: a UA-specific group fully replaces the 'User-agent: *'
# group for that crawler, so the layered-nav Disallows must be repeated here.

User-agent: SemrushBot
Crawl-delay: 10
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

User-agent: SiteAuditBot
Crawl-delay: 10
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

User-agent: SemrushBot-BA
Crawl-delay: 10
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

User-agent: SemrushBot-SI
Crawl-delay: 10
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

User-agent: SemrushBot-SWA
Crawl-delay: 10
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

User-agent: SemrushBot-FT
Crawl-delay: 10
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

User-agent: SemrushBot-OCOB
Crawl-delay: 10
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

User-agent: SemrushBot-ESI
Crawl-delay: 10
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

User-agent: SplitSignalBot
Crawl-delay: 10
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

#######################################
############### SITEMAP ###############
#######################################

Sitemap: https://www.americancommercialfurniture.com/sitemaps/americancommercialfurniture/sitemap.xml

#######################################
########### GENERAL RULES #############
#######################################

User-agent: *
# Do not crawl layered-navigation filter combinations (added 2026-07-07).
# Filter option values contain "_"; combining filters joins them with "-".
# Verified: no product/category/CMS URL matches these patterns.
Allow: /media/
Allow: /static/
Allow: /collections/
Disallow: /*_*-*
Disallow: /*-*_*

# Directories
Disallow: /app/
Disallow: /bin/
Disallow: /dev/
Disallow: /lib/
Disallow: /magento1/
Disallow: /phpserver/
Disallow: /pkginfo/
Disallow: /report/
Disallow: /reville/
Disallow: /setup/
Disallow: /update/
Disallow: /var/
Disallow: /vendor/

# Paths (clean URLs)
Disallow: /index.php/
Disallow: /catalog/product_compare/
Disallow: /catalog/category/view/
Disallow: /catalogsearch/
Disallow: /checkout/
Disallow: /control/
Disallow: /contacts/
Disallow: /customer/
Disallow: /customize/
Disallow: /firecheckout/
Disallow: /newsletter/
Disallow: /review/
Disallow: /sendfriend/
Disallow: /wishlist/

# Files
Disallow: /composer.json
Disallow: /composer.lock
Disallow: /CONTRIBUTING.md
Disallow: /CONTRIBUTOR_LICENSE_AGREEMENT.html
Disallow: /COPYING.txt
Disallow: /Gruntfile.js
Disallow: /LICENSE.txt
Disallow: /LICENSE_AFL.txt
Disallow: /nginx.conf.sample
Disallow: /package.json
Disallow: /php.ini.sample
Disallow: /RELEASE_NOTES.txt

# Filtered and sorted pages
Disallow: /*?*product_list_mode=
Disallow: /*?*product_list_order=
Disallow: /*?*product_list_limit=
Disallow: /*?*product_list_dir=

# Session IDs
Disallow: /*?SID=

# PHP files
Disallow: /*.php$

# CVS, SVN, IDE and dump files
Disallow: /*.CVS
Disallow: /*.Zip$
Disallow: /*.Svn$
Disallow: /*.Idea$
Disallow: /*.Sql$
Disallow: /*.Tgz$