#
# 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: *
Sitemap: https://www.nichd.nih.gov/default/sitemap.xml

# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.txt
Disallow: /web.config
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips/
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
# Paths (no clean URLs)
Disallow: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips/
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/user/password/
Disallow: /index.php/user/register/
Disallow: /index.php/user/login/
Disallow: /index.php/user/logout/

# robots.txt file for www.nichd.nih.gov
User-Agent: *
Disallow: /_layouts/
Disallow: /Documents/Forms/
Disallow: /Pages/Forms/
Disallow: /ReusableContent/
Disallow: /Reports%20List/
Disallow: /Search/
Disallow: /SiteCollectionDocuments/
Disallow: /SiteCollectionImages/
Disallow: /WorkflowTasks/
Disallow: /Search.aspx
Disallow: /search.aspx
Disallow: Search.aspx
Disallow: search.aspx

# adding new 2008 wild card syntax (see http://www.searchtools.com/robots/robots-txt-elements.html#wildcards)
Disallow: */_layouts/
Disallow: */Documents/Forms/
Disallow: */Pages/Forms/
Disallow: */ReusableContent/
Disallow: */Reports%20List/
Disallow: */Search/
Disallow: */SiteCollectionDocuments/
Disallow: */SiteCollectionImages/
Disallow: */WorkflowTasks/
# page-level exclusion
Disallow: *WebFldr.aspx$
Disallow: *Upload.aspx$
Disallow: *EditForm.aspx$
Disallow: *external.aspx$
Disallow: *search.aspx$
Disallow: *Search.aspx
Disallow: *search.aspx