User-agent: *
Crawl-delay: 5
Disallow: /*?
Disallow: /index.php/
Disallow: /catalog/product_compare/
Disallow: /catalog/category/view/
Disallow: /catalog/product/view/
Disallow: /wishlist/
Disallow: /admin/
Disallow: /catalogsearch/
Disallow: /onestepcheckout/
Disallow: /customer/
Disallow: /review/product/
Disallow: /sendfriend/
Disallow: /enable-cookies/
Disallow: /LICENSE.txt
Disallow: /LICENSE.html
Disallow: /skin/
Disallow: /js/
Disallow: /directory/
#Stop crawling user account and checkout pages by search engine robot:
Disallow: /checkout/
Disallow: /onestepcheckout/
Disallow: /customer/
Disallow: /customer/account/
Disallow: /customer/account/login/
#Blocking native catalog and search pages:
Disallow: /catalogsearch/
Disallow: /catalog/product_compare/
Disallow: /catalog/category/view/
Disallow: /catalog/product/view/
#Sometimes Webmasters block pages with filters..
Disallow: /*?dir*
Disallow: /*?dir=desc
Disallow: /*?dir=asc
Disallow: /*?limit=all
Disallow: /*?mode*
More reasonable to use canonical tag on these pages.
#Blocking CMS directories.
Disallow: /app/
Disallow: /bin/
Disallow: /dev/
Disallow: /lib/
Disallow: /phpserver/
Disallow: /pub/
#Blocking duplicate content:
Disallow: /tag/
Disallow: /review/
User-agent: Googlebot
Disallow:
User-agent: Googlebot-image
Disallow:
#Sitemaps for each store view
Sitemap: https://www.almedina.net/sitemap.xml
User-agent: Rogerbot
User-agent: Exabot
User-agent: MJ12bot
User-agent: Dotbot
User-agent: Gigabot
User-agent: AhrefsBot
User-agent: BlackWidow
User-agent: ChinaClaw
User-agent: Custo
User-agent: DISCo
User-agent: Download\ Demon
User-agent: eCatch
User-agent: EirGrabber
User-agent: EmailSiphon
User-agent: EmailWolf
User-agent: Express\ WebPictures
User-agent: ExtractorPro
User-agent: EyeNetIE
User-agent: FlashGet
User-agent: GetRight
User-agent: GetWeb!
User-agent: Go!Zilla
User-agent: Go-Ahead-Got-It
User-agent: GrabNet
User-agent: Grafula
User-agent: HMView
User-agent: HTTrack
User-agent: Image\ Stripper
User-agent: Image\ Sucker
User-agent: Indy\ Library
User-agent: InterGET
User-agent: Internet\ Ninja
User-agent: JetCar
User-agent: JOC\ Web\ Spider
User-agent: larbin
User-agent: LeechFTP
User-agent: Mass\ Downloader
User-agent: MIDown\ tool
User-agent: Mister\ PiX
User-agent: Navroad
User-agent: NearSite
User-agent: NetAnts
User-agent: NetSpider
User-agent: Net\ Vampire
User-agent: NetZIP
User-agent: Octopus
User-agent: Offline\ Explorer
User-agent: Offline\ Navigator
User-agent: PageGrabber
User-agent: Papa\ Foto
User-agent: pavuk
User-agent: pcBrowser
User-agent: RealDownload
User-agent: ReGet
User-agent: SiteSnagger
User-agent: SmartDownload
User-agent: SuperBot
User-agent: SuperHTTP
User-agent: Surfbot
User-agent: tAkeOut
User-agent: Teleport\ Pro
User-agent: VoidEYE
User-agent: Web\ Image\ Collector
User-agent: Web\ Sucker
User-agent: WebAuto
User-agent: WebCopier
User-agent: WebFetch
User-agent: WebGo\ IS
User-agent: WebLeacher
User-agent: WebReaper
User-agent: WebSauger
User-agent: Website\ eXtractor
User-agent: Website\ Quester
User-agent: WebStripper
User-agent: WebWhacker
User-agent: WebZIP
User-agent: Wget
User-agent: Widow
User-agent: WWWOFFLE
User-agent: Xaldon\ WebSpider
User-agent: Zeus
Disallow: /