# robots.txt for Magento 1.9.x / v1.52 2017-12-02 / Peeter Marvet # (original version from 2015, edited in 2017 to add filter query parameter disallow samples + some wildcards) # based on: # http://inchoo.net/ecommerce/ultimate-magento-robots-txt-file-examples/ # http://www.byte.nl/blog/magento-robots-txt/ # https://astrio.net/blog/optimize-robots-txt-for-magento/ # # comment and clone at https://gist.github.com/petskratt/016c9dbf159a81b9d6aa # Keep in mind that by standard robots.txt should NOT contain empty lines, except between UA blocks! # # Sitemap (uncomment, change and add language/shop specific sitemaps, if running on multiple domains # keep in mind sitemap can only point to own domain so something like sitemapindex.php is needed) # Sitemap: https://www.customcraftaustralia.com.au/sitemap.xml # # Google Image Crawler Setup - having crawler-specific sections makes it ignore generic e.g * User-agent: Googlebot-Image Disallow: # # Yandex tends to be rather aggressive, may be worth keeping them at arms lenght User-agent: YandexBot Crawl-delay: 20 # # Crawlers Setup User-agent: * # # Allow paging (unless paging inside a listing with more params, as disallowed below) Allow: /*?p= # # # Directories Disallow: /404/ Disallow: /afxgroup/ Disallow: /app/ Disallow: /aussiewebpro.com/ Disallow: /backup/ Disallow: /backup_clone/ Disallow: /captcha/ Disallow: /cgi-bin/ Disallow: /dev/ Disallow: /downloader/ Disallow: /errors/ Disallow: /foodsensations.com.au/ Disallow: /includes/ #Disallow: /js/ Disallow: /lib/ #Disallow: /media/ Disallow: /media/captcha/ #Disallow: /media/catalog/ #Disallow: /media/css/ #Disallow: /media/css_secure/ Disallow: /media/custom_options/ Disallow: /media/customer/ Disallow: /media/dhl/ Disallow: /media/downloadable/ Disallow: /media/email/ Disallow: /media/favicon/ #Disallow: /media/js/ Disallow: /media/sales/ Disallow: /media/tmp/ Disallow: /media/wysiwyg/ Disallow: /media/xmlconnect/ Disallow: /RENAMED_downloader/ Disallow: /shell/ #Disallow: /skin/ Disallow: /tmp/ Disallow: /var/ # # # Paths (if using shop id in URL must prefix with * or copy for each) Disallow: */index.php/ Disallow: */catalog/product_compare/ Disallow: */catalog/category/view/ Disallow: */catalog/product/view/ Disallow: */catalog/product/gallery/ Disallow: */catalogsearch/ Disallow: */control/ Disallow: */contacts/ Disallow: */customer/ Disallow: */customize/ Disallow: */newsletter/ Disallow: */poll/ Disallow: */review/ Disallow: */sendfriend/ Disallow: */tag/ Disallow: */wishlist/ Disallow: */checkout/ Disallow: */onestepcheckout/ # # # Files #Disallow: /.htaccess/ Disallow: /.htaccess.backup/ Disallow: /.htaccess.old/ Disallow: /.htaccess.sample/ Disallow: /api.php/ Disallow: /composer.json/ Disallow: /cron.php/ Disallow: /cron.sh/ Disallow: /error_log/ #Disallow: /favicon.ico/ Disallow: /get.php/ #Disallow: /index.php/ Disallow: /index.php.sample/ Disallow: /index_ORIGINAL.php/ Disallow: /install.php/ Disallow: /LICENSE.html/ Disallow: /LICENSE.txt/ Disallow: /LICENSE_AFL.txt/ Disallow: /mage/ Disallow: /media/.htaccess/ Disallow: /MODMAN/ Disallow: /package.xml/ Disallow: /php.ini.sample/ Disallow: /README.md/ Disallow: /get.php/ # # # Do not crawl sub category pages that are sorted or filtered. # This would be very broad, could hurt (incl. SEO). # Disallow: /*?* # # These are more specific, pick what you need - and do not forget to add your custom filters! Disallow: /*?dir* Disallow: /*?limit* Disallow: /*?mode* Disallow: /*?___from_store=* Disallow: /*?___store=* Disallow: /*?cat=* Disallow: /*?q=* Disallow: /*?price=* Disallow: /*?availability=* Disallow: /*?brand=* # # Paths that can be safely ignored (no clean URLs) Disallow: /*?p=*& Disallow: /*.php$ Disallow: /*?SID= # #