# $Id: robots.txt,v 1.7.2.3 2014/11/18 20:24:38 drumm Exp $ # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/wc/robots.html # # For syntax checking, see: # https://www.google.com/webmasters/tools/robots-testing-tool User-agent: * Crawl-delay: 20 # Directories / Paths # Note: x dir is to prevent spidering/following affs Disallow: /admin/ Disallow: /calibre/ Disallow: /chat/ Disallow: /comment/edit/ Disallow: /comment/reply/ Disallow: /contact/ Disallow: /dbbackup/ Disallow: /devtools/ Disallow: /doe/ Disallow: /files/ Disallow: /forums/everything-else/phrozen-crew/private-phrozen-crew/ Disallow: /forums/private-contributing-editors/ Disallow: /forums/private-moderation/ Disallow: /forums/private-pandoras-box/ Disallow: /forums/private-premium-member-area/ Disallow: /forums/private-the-core/ Disallow: /ignore_user/add/ Disallow: /IM/ Disallow: /imce/ Disallow: /includes/ Disallow: /logout/ Disallow: /misc/ Disallow: /modules/ Disallow: /myspace/ Disallow: /node/add/ Disallow: /og/subscribe/ Disallow: /privatemsg/ Disallow: /profiles/ Disallow: /reference/ Disallow: /scripts/ # Disallow: /search/ Disallow: /sites/ Disallow: /sxm-gen/ Disallow: /test/ Disallow: /themes/ Disallow: /user/login/ Disallow: /user/password/ Disallow: /user/register/ Disallow: /userpoints/ Disallow: /x/ # Enable Following 2 lines to have User Profiles crawled # Disallow: /user/ # Disallow: /users/ # Paths (no clean URLs) Disallow: /?q=admin/ Disallow: /?q=comment/reply/ Disallow: /?q=contact/ Disallow: /?q=logout/ Disallow: /?q=node/add/ Disallow: /?q=search/ Disallow: /?q=user/password/ Disallow: /?q=user/register/ Disallow: /?q=user/login/ # Files Disallow: /2de0f5212b76.html Disallow: /?q=warning.html Disallow: /CHANGELOG.txt Disallow: /cron.php Disallow: /image2.gif Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /install.php Disallow: /INSTALL.txt Disallow: /LICENSE.txt Disallow: /LiveSearchSiteAuth.xml Disallow: /MAINTAINERS.txt Disallow: /moderators-long.inc Disallow: /php.ini Disallow: /pinterest-1ed04.html Disallow: /premie-list.htm Disallow: /sites/default/settings.php Disallow: /temp-blacklist.html Disallow: /update.php Disallow: /UPGRADE.txt Disallow: /warning.html Disallow: /xmlrpc.php # Bots and Scrapers User-agent: Aboundexbot Disallow: / User-agent: AhrefsBot Disallow: / User-agent: AlphaSeoBot Disallow: / User-agent: AlphaSeoBot-SA Disallow: / User-agent: BLEXBot Disallow: / User-agent: BOT/0.1 (BOT for JCE) Disallow: / User-agent: coccoc Disallow: / User-agent: DAUM Disallow: / User-agent: discoverybot Disallow: / User-agent: dotbot Disallow: / User-agent: Ezooms Disallow: / User-agent: MegaIndex.ru Disallow: / User-agent: MegaIndex.ru/2.0 Disallow: / User-agent: MJ12bot Disallow: / User-agent: Riddler Disallow: / User-agent: SemrushBot Disallow: / User-agent: SEOkicks-Robot Disallow: / User-agent: SeznamBot Disallow: / User-agent: SMTBot Disallow: / User-agent: Sogou spider Disallow: / User-agent: Sogou Pic Spider Disallow: / User-agent: Sogou Pic Spider/3.0 Disallow: / User-agent: Sogou Web spider Disallow: / User-agent: Spinn3r Disallow: / User-agent: TurnitinBot Disallow: / User-agent: Yandex Disallow: / User-agent: Y!J-ASR/0.1 crawler Disallow: / User-agent: magpie-crawler Disallow: / User-agent: netEstate NE Crawler (+http://www.website-datenbank.de/) Disallow: / User-agent: netEstate NE Crawler Disallow: /