# robots.txt for Magento 1.9.x / v1.6 2018-08-19 / Peeter Marvet # (original version from 2015, edited in 2017 to add filter query parameter disallow samples + some wildcards, # edited in 2018 to add query params blocking to Yandex as named User-agent does not read *) # 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.stojanyregaly.cz/sitemap.xml Sitemap: https://www.stojanyregaly.sk/sk/sitemap.xml Sitemap: https://www.allvany-allvanyok.hu/hu/sitemap.xml # # Crawlers Setup User-agent: * Crawl-delay: 5 # # Allow paging (unless paging inside a listing with more params, as disallowed below) Allow: /*?p= Allow: /*?utm_*=* # # Directories #Disallow: /media/ #Disallow: /media/catalog/ #Disallow: /media/wysiwyg/ #Disallow: /skin/ Disallow: /404/ Disallow: /app/ Disallow: /cgi-bin/ Disallow: /downloader/ Disallow: /errors/ Disallow: /includes/ Disallow: /magento/ Disallow: /media/captcha/ Disallow: /media/customer/ Disallow: /media/dhl/ Disallow: /media/downloadable/ Disallow: /media/import/ Disallow: /media/pdf/ Disallow: /media/sales/ Disallow: /media/tmp/ Disallow: /media/xmlconnect/ Disallow: /pkginfo/ Disallow: /report/ Disallow: /scripts/ Disallow: /shell/ Disallow: /stats/ Disallow: /var/ # # Paths (if using shop id in URL must prefix with * or copy for each) Disallow: /catalog/category/view/ Disallow: /catalog/product/gallery/ Disallow: /catalog/product/view/ Disallow: /catalog/product_compare/ Disallow: /catalogsearch/ Disallow: /checkout/ Disallow: /contacts/ Disallow: /control/ Disallow: /customer/ Disallow: /customize/ Disallow: /index.php/ Disallow: /newsletter/ Disallow: /onestepcheckout/ Disallow: /poll/ Disallow: /review/ Disallow: /sendfriend/ Disallow: /tag/ Disallow: /wishlist/ # # Files Disallow: /LICENSE.html Disallow: /LICENSE.txt Disallow: /LICENSE_AFL.txt Disallow: /STATUS.txt Disallow: /cron.php Disallow: /cron.sh Disallow: /error_log Disallow: /install.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=