# See http://www.robotstxt.org/wc/norobots.html for documentation on how to use the robots.txt file # # A basic robots.txt file which allows specific pages and regex matches of pages but disallows # every other page from scraping, for all user agents. User-Agent: * Allow: /$ Allow: /login Allow: /register Allow: /employer_registrations/new Allow: /career_fairs/*/student_preview Allow: /career_fairs/*/employer_preview Allow: /events/*/share_preview Allow: /jobs/*/share_preview Allow: /employers Allow: /job_role_groups Allow: /questions Allow: /favicon-32x32.png Allow: /favicon-16x16.png Allow: /favicon.png Allow: /favicon.ico Allow: /profiles/* Disallow: /profiles/*/posts Disallow: /