# Define access-restrictions for robots/spiders # http://www.robotstxt.org/wc/norobots.html # By default we allow robots to access all areas of our site # already accessible to anonymous users User-agent: * Disallow: /search Disallow: /m/ Disallow: /nonmobile Crawl-delay: 5 # Add Googlebot-specific syntax extension to exclude forms # that are repeated for each piece of content in the site # the wildcard is only supported by Googlebot # http://www.google.com/support/webmasters/bin/answer.py?answer=40367&ctx;=sibling User-Agent: Googlebot Disallow: /*sendto_form$ Disallow: /*folder_factories$ Disallow: /*?searchterm=* Disallow: /*image$ Disallow: /*image_* Disallow: /*image_view_fullscreen$ Disallow: /m/ Disallow: /nonmobile # Apparently Yahoo supports wildcards, too? # http://help.yahoo.com/l/us/yahoo/search/webcrawler/slurp-02.html User-Agent: Slurp Disallow: /*sendto_form$ Disallow: /*folder_factories$ Disallow: /*?searchterm=* Disallow: /*image$ Disallow: /*image_* Disallow: /*image_view_fullscreen$ Disallow: /m/ Disallow: /nonmobile # Penn State's Google Search Appliance User-Agent: PennStateSpider Disallow: /*sendto_form$ Disallow: /*folder_factories$ Disallow: /*?searchterm=* Disallow: /m/ Disallow: /nonmobile