User-agent: *
Crawl-Delay: 2

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

# Paths (clean URLs)
Disallow: /index.php/
Disallow: /catalog/product_compare/
Disallow: /catalog/category/view/
Disallow: /catalog/product/view/
Disallow: /catalogsearch/
Disallow: /checkout/
Disallow: /control/
Disallow: /contacts/
Disallow: /customer/
Disallow: /customize/
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
Disallow: /vendor

# Do not index pages that are sorted or filtered.
Disallow: /*?*product_list_mode=
Disallow: /*?*product_list_order=
Disallow: /*?*product_list_limit=
Disallow: /*?*product_list_dir=

# Do not index session ID
Disallow: /*?SID=
Disallow: /*.php$

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

Sitemap: https://www.pclairtechnology.com/blog_sitemap.xml


# 3rd Party Module Paths
Disallow: /mageworx_searchsuiteautocomplete/ajax/index/ 


# Blocking Bots

User-Agent: aiHitBot
Disallow: /

User-Agent: AhrefsBot
Disallow: /

User-Agent: Applebot
Disallow: /

User-Agent: Barkrowler
Disallow: /

User-Agent: BitSightBot
Disallow: /

User-Agent: Bytespider
Disallow: /

User-Agent: ClaudeBot
Disallow: /

User-Agent: Cliqzbot
Disallow: /

User-Agent: coccocbot-image
Disallow: /

User-Agent: coccocbot-web
Disallow: /

User-Agent: DataProvider
Disallow: /

User-Agent: DataForSeoBot
Disallow: /

User-Agent: Dormouse
Disallow: /

User-Agent: DotBot
Disallow: /

User-Agent: DuckDuckBot
Disallow: /

User-Agent: ev-crawler
Disallow: /

User-Agent: FriendlyCrawler
Disallow: /

User-Agent: GeedoProductSearch
Disallow: /

# Used by Google Internal for R&D, separate to GoogleBot
User-Agent: GoogleOther
Disallow: /

User-Agent: GPTBot
Disallow: /

User-Agent: ChatGPT-User
Disallow: /

User-Agent: ImagesiftBot
Disallow: /


User-Agent: meta-externalagent
Disallow: /

User-Agent: MJ12bot
Disallow: /

User-Agent: MojeekBot
Disallow: /

User-Agent: OAI-SearchBot
Disallow: /

User-Agent: oBot
Disallow: /

User-Agent: OpenindexSpider
Disallow: /

User-Agent: Orbbot
Disallow: /

User-Agent: PerplexityBot
Disallow: /

User-Agent: PetalBot
Disallow: /

User-Agent: SeekportBot
Disallow: /

User-Agent: SemrushBot
Disallow: /

User-Agent: SeznamBot
Disallow: /

User-Agent: TwitterBot
Disallow: /

User-Agent: YandexBot
Disallow: /

User-Agent: YandexUserProxy
Disallow: /

User-Agent: ZoominfoBot
Disallow: /

# Crawl Delay
User-Agent: SemrushBot
Crawl-Delay: 100

User-Agent: SemrushBot-BA
Crawl-Delay: 100


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