## milkycode Magento robots.txt 06/2019
## copyright: milkycode GmbH <www.milkycode.com>
## author: Christian Hinz

## 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: 60

## Magento sitemap: uncomment and replace the URL to your Magento sitemap file
#Sitemap: http://www.yoururl.de/sitemap.xml

## DEVELOPMENT RELATED SETTINGS

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

## GENERAL MAGENTO SETTINGS

## Do not crawl common Magento technical folders
Disallow: /404/
Disallow: /app/
Disallow: /downloader/
Disallow: /errors/
Disallow: /includes/
Disallow: /lib/
Disallow: /pkginfo/
Disallow: /shell/
Disallow: /var/
Disallow: /magento/
Disallow: /report/
Disallow: /stats/
Disallow: /scripts/

## 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
Disallow: /STATUS.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*

# Allowable Index
Allow: /*?p=

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

## Do not crawl links with session IDs
Disallow: /*?SID=

## Paths (no clean URLs)
Disallow: /*.php$
Disallow: /*?p=*&
Disallow: /*?s=*

## Do not crawl user account pages
Disallow: /customer/
Disallow: /customer/account/
Disallow: /customer/account/login/

## Do not crawl seach pages and not-SEO optimized catalog links
Disallow: /catalogsearch/
Disallow: /catalog/product_compare/
Disallow: /catalog/category/view/
Disallow: /catalog/product/view/
Disallow: /catalog/product/gallery/
Disallow: /wishlist/
Disallow: /sendfriend/
Disallow: /control/
Disallow: /customize/
Disallow: /newsletter/
Disallow: /poll/
Disallow: /review/
Disallow: /sales/guest/form/
Disallow: /contact/
Disallow: /contacts/

## 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

## EXTENSION SPECIFIC
Disallow: /productquestion/
Disallow: /calculator/
Disallow: /catalog/product_bcp/
Disallow: /po-connect/
Disallow: /onestepcheckout
Disallow: /druckkosten

## IMAGE CRAWLERS SETTINGS
User-agent: Mediapartners-Google
Allow: /*?s=*

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