# # robots.txt # # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # # This file will be ignored unless it is at the root of your host: # Used: http://example.com/robots.txt # Ignored: http://example.com/site/robots.txt # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/robotstxt.html User-agent: * Crawl-delay: 10 # CSS, JS, Images # Allow: # Directories Disallow: /soc/ Disallow: /static/ Disallow: /website/ # Files Disallow: /run.sh Disallow: /tornado_main.py Disallow: /instances.py Disallow: /requirements.txt # Paths (clean URLs) Disallow: /admin/ Disallow: /get_code/ Disallow: /get_books/ Disallow: /get_chapters/ Disallow: /get_examples/ Disallow: /get_contributor/ Disallow: /get_bug_form/ Disallow: /get_bug_form_submit/ Disallow: /get_diff/ Disallow: /get_revisions/ Disallow: /submit-revision/ Disallow: /search_book/ Disallow: /search_book/popular/ Disallow: /search_book/recent/ Disallow: /get_subcategories/ Disallow: /get_node/ Disallow: /get_submit_revision_form/ Disallow: /get_submit_revision_form_submit/ Disallow: /review/get_review_revision/ Disallow: /review/get_push_revision/ Disallow: /review/get_remove_revision/ Disallow: /review/