## robots.txt for Magento Community and Enterprise

## GENERAL SETTINGS

## Enable robots.txt rules for all crawlers
User-agent: *

## Crawl-delay parameter: number of seconds to wait between successive requests to the same server.
## Set a custom crawl rate if you're experiencing traffic problems with your server.
Crawl-delay: 30
Request-rate: 1/30
Visit-time: 0400-0845


User-agent: SemrushBot
Disallow: /

# Block MJ12bot as it is just noise
User-agent: MJ12bot
Disallow: /

# Block Ahrefs
User-agent: AhrefsBot
Disallow: /

# Block Sogou
User-agent: sogou spider
Disallow: /

# Block SEOkicks
User-agent: SEOkicks-Robot
Disallow: /

# Block BlexBot
User-agent: BLEXBot
Disallow: /

# Block SISTRIX
User-agent: SISTRIX Crawler
Disallow: /

# Block Uptime robot
User-agent: UptimeRobot/2.0
Disallow: /

User-agent: 008
Disallow: /

# Block Ezooms Robot
User-agent: Ezooms Robot
Disallow: /

# Block Perl LWP
User-agent: Perl LWP
Disallow: /

# Block BlexBot
User-agent: BLEXBot
Disallow: /

# Block netEstate NE Crawler (+http://www.website-datenbank.de/)
User-agent: netEstate NE Crawler (+http://www.website-datenbank.de/)
Disallow: /

# Block WiseGuys Robot
User-agent: WiseGuys Robot
Disallow: /

# Block Turnitin Robot
User-agent: Turnitin Robot
Disallow: /

# Block Heritrix
User-agent: Heritrix
Disallow: /

# Block pricepi 
User-agent: pimonster
Disallow: /
User-agent: Pimonster
Disallow: /
User-agent: Pi-Monster
Disallow: /

# Block Searchmetrics Bot
User-agent: SearchmetricsBot
Disallow: /

# Block Eniro
User-agent: ECCP/1.0 (search@eniro.com)
Disallow: /

# Block YandexBot
User-agent: Yandex
Disallow: /

# Block Baidu
User-agent: Baiduspider
User-agent: Baiduspider-video
User-agent: Baiduspider-image
Disallow: /

# Block SoGou
User-agent: Sogou Spider
Disallow: /

# Block Youdao
User-agent: YoudaoBot
Disallow: /


# Website Sitemap
# Sitemap: 

## DEVELOPMENT RELATED SETTINGS

## Do not crawl development files and folders: CVS, svn directories and dump files
Disallow: CVS
Disallow: .svn
Disallow: .idea
Disallow: .sql
Disallow: .tgz

## GENERAL MAGENTO SETTINGS

## Do not crawl Magento admin page
Disallow: /admin/

## Do not crawl common Magento technical folders
Disallow: /app/
Disallow: /downloader/
Disallow: /errors/
Disallow: /includes/
Disallow: /lib/
Disallow: /pkginfo/
Disallow: /shell/
Disallow: /var/
Disallow: /magento/
Disallow: /report/
Disallow: /scripts/
Disallow: /skin/
Disallow: /stats/
Disallow: /admin/


## Do not crawl common Magento files
Disallow: /api.php
Disallow: /cron.php
Disallow: /cron.sh
Disallow: /error_log
Disallow: /get.php
Disallow: /install.php
Disallow: /LICENSE.html
Disallow: /LICENSE.txt
Disallow: /LICENSE_AFL.txt
Disallow: /README.txt
Disallow: /RELEASE_NOTES.txt

## MAGENTO SEO IMPROVEMENTS

## Do not crawl sub category pages that are sorted or filtered.
Disallow: /*?dir*
Disallow: /*?dir=desc
Disallow: /*?dir=asc
Disallow: /*?limit=all
Disallow: /*?mode*

## Do not crawl 2-nd home page copy (example.com/index.php/). Uncomment it only if you activated 

## Magento SEO URLs.
## Disallow: /index.php/

# Paths (no clean URLs)
##    Disallow: /*.js$
##    Disallow: /*.css$
    Disallow: /*.php$
    Disallow: /*?SID=

## Do not crawl checkout and user account pages
Disallow: /checkout/
Disallow: /onestepcheckout/
Disallow: /onepage/
Disallow: /firecheckout/
Disallow: /suggest/
Disallow: /customer/
Disallow: /customer/account/
Disallow: /customer/account/login/
Disallow: /paypal/
Disallow: /wishlist/

# Paths (clean URLs)
    Disallow: /*?cat=
    Disallow: /*&cat=
    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: /review/
    Disallow: /newsletter/
    Disallow: /poll/
    Disallow: /sendfriend/
    Disallow: /tag/
    Disallow: /wishlist/
    Disallow: /catalog/product/gallery/

## SERVER SETTINGS

## Do not crawl common server technical folders and files
Disallow: /cgi-bin/
Disallow: /cleanup.php
Disallow: /apc.php
Disallow: /memcache.php
Disallow: /phpinfo.php
Disallow: /turpentine/

## IMAGE CRAWLERS SETTINGS

## Extra: Uncomment if you do not wish Google and Bing to index your images
# User-agent: Googlebot-Image
# Disallow: /
# User-agent: msnbot-media
# Disallow: /