Sitemap: https://ento.psu.edu/sitemap.xml.gz # 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: /about/facilities/frost/images Disallow: /outreach/extension/ipm/english/agriculture/greenhouse-ipm Disallow: /outreach/extension/ipm/english/schools-childcares/healthy-homes Disallow: /outreach/extension/ipm/english/schools-childcares/school-ipm-laws # 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: /*? Disallow: /*atct_album_view$ Disallow: /*folder_factories$ Disallow: /*folder_summary_view$ Disallow: /*login_form$ Disallow: /*mail_password_form$ Disallow: /@@search Disallow: /*search_rss$ Disallow: /*sendto_form$ Disallow: /*summary_view$ Disallow: /*thumbnail_view$ Disallow: /*view$