# direct seomoz crawler to focus on store pages, not community User-agent: rogerbot Disallow: /action/viewLook Disallow: /users/ # www.apptus.com's crawler generates many exceptions User-agent: apptus_tce Disallow: / # www.apptus.com's crawler generates many exceptions User-agent: apptus_tce/1.2 Disallow: / # MSRBOT causes some exceptions (its a microsoft research test bot) User-agent: MSRBOT Disallow: / # Twiceler causes exceptions User-agent: twiceler Disallow: / # This thing is generating exceptions User-agent: VSynCrawler/1.0 Disallow: / # This thing is not respecting nofollow User-agent: wwwster/1.4 (Beta, mailto:gue@cis.uni-muenchen.de) Disallow: / # This thing comes with a bogus sc1 cookie User-agent: iCrossing - Apollo - icrossing.com Disallow: / # This is related to the blog pages coming from popsugar User-agent: Googlebot-Image Disallow: /blog/static/ck.php # Another item related to blocking the crawling of popsugar blogs User-agent: dotbot Disallow: /blog/ # Sitemap Sitemap: http://www.shopstyle.com/sitemap_index.xml ### CAREFUL with the whitespace - We can't have blank lines within this one big block for UA=* User-agent: * Allow: /action/viewLook Allow: /action/spreadWidgetImage Disallow: /action/ Disallow: /api/ Disallow: *TopAd728x90.html Disallow: /*crawl=no Disallow: /page/SearchWidget Disallow: /page/TrendWidget Disallow: /page/LookBrowserWidget Disallow: /page/GroupList Disallow: /page/GroupTopic Disallow: /page/BlogWidget Disallow: /page/EditorPicks Disallow: /page/Error404 Disallow: /product Disallow: /item # curtail most image crawling. Since it does get us some referals, leave the std prod and spread images Disallow: *_small.jpg$ Disallow: *_small/*.jpg$ Disallow: *_smallmed.jpg$ Disallow: *_medium.jpg$ Disallow: *_medium/*.jpg$ Disallow: *_58.jpg$ Disallow: *_40.jpg$ Disallow: *_30.jpg$ Disallow: *.gif$ Disallow: *.png$ Disallow: /xim/ Disallow: /lim/ Disallow: /mim/ #Block all popsugar blog pages Disallow: /blog/user/ Disallow: /blog/warn/ Disallow: /blog/buddy/ Disallow: /blog/find/ Disallow: /blog/privatemsg/ Disallow: /blog/forward/ Disallow: /blog/favorite_nodes/ Disallow: /blog/subscriptions/ Disallow: /blog/node/ Disallow: /blog/favorites/ Disallow: /blog/submit2/ Disallow: /blog/forum/ Disallow: /blog/register Disallow: /blog/sharer/ Disallow: /blog/gallery/sharer/ Disallow: /blog/remotelogin Disallow: /blog/outgoing/ Disallow: /blog/mobile/ Disallow: /blog/recipes/ Disallow: /blog//ajax/ Disallow: /blog/entertainment/ Disallow: /blog/files/health/ Disallow: /blog/gallery/ Disallow: /blog/nodebody/ Disallow: /blog/products/dialog Disallow: /blog/products/like/ Disallow: /blog/search Disallow: /blog/shopsense/cookie Disallow: /blog/shopstyle Disallow: /blog/social/ajax/ Disallow: /blog/sugar-ads/ Disallow: /blog/voting/ Disallow: /node/ Disallow: /sharer/ Disallow: /social/ajax/