# ==================================================================== # GLOBAL CRAWLER INSTRUCTIONS # Targets: Googlebot, Bingbot, MSNBOT, DuckDuckBot, Qwant, and others # ==================================================================== User-agent: Googlebot User-agent: bingbot User-agent: MSNBOT User-agent: DuckDuckBot User-agent: * # Global Allow Rules Allow: / Allow: /*?p= # Magento Technical Directories (DO NOT INDEX) Disallow: /404/ Disallow: /app/ Disallow: /cgi-bin/ Disallow: /downloader/ Disallow: /admin/ Disallow: /errors/ Disallow: /includes/ Disallow: /lib/ Disallow: /magento/ Disallow: /pkginfo/ Disallow: /report/ Disallow: /scripts/ Disallow: /shell/ Disallow: /stats/ Disallow: /var/ # Magento Media Subfolders (Prevents indexing of system/private data) 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/ # Paths & Checkout Restraints (Handles multilocale and clean URLs) 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/ # Core System Files Disallow: /cron.php Disallow: /cron.sh Disallow: /error_log Disallow: /install.php Disallow: /LICENSE.html Disallow: /LICENSE.txt Disallow: /LICENSE_AFL.txt Disallow: /STATUS.txt Disallow: /api.php Disallow: /get.php Disallow: /README.txt Disallow: /RELEASE_NOTES.txt # Magento Layered Navigation & URL Filter Blocks Disallow: /*?dir* Disallow: /*?limit* Disallow: /*?mode* Disallow: /*?___from_store=* Disallow: /*?___store=* Disallow: /*?cat=* Disallow: /*?q=* Disallow: /*?price=* Disallow: /*?availability=* Disallow: /*?brand=* Disallow: /cleanup.php Disallow: /apc.php Disallow: /memcache.php Disallow: /phpinfo.php # Avoid Parameter Duplications & Session Tracking Disallow: /*?p=*& Disallow: /*.php$ Disallow: /*?SID= Disallow: /rss* Disallow: /*PHPSESSID # ==================================================================== # SPECIALIZED CRAWLER HANDLING # ==================================================================== # Google Image Search Optimization User-agent: Googlebot-Image Disallow: # Dedicated Rules for Yandex (Prevents heavy server load via Layered Nav) User-agent: YandexBot Crawl-delay: 20 Allow: /*?p= Disallow: /*?p=*& Disallow: /*? # Global XML Sitemap Route Sitemap: https://netcom.lt/sitemap/sitemap.xml