#
# robots.txt
#
#
# 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
# Update Feb 26

User-agent: *
# CSS, JS, Images
Allow: /*.css
Allow: /*.css?
Allow: /*.js$
Allow: /*.js?
Allow: /*.gif
Allow: /*.jpg
Allow: /*.jpeg
Allow: /*.png
Allow: /*.svg

#Download files
Allow: /*.pdf$
Allow: /*.doc$
Allow: /*.docx$
Allow: /*.xls$
Allow: /*.xlsx$


# Directories
Disallow: /core/
Disallow: /profiles/
Disallow: /admin/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /search/
Disallow: */node/*
Disallow: */taxonomy/*
Disallow: */quicktabs/*

# Sensitive Files
Disallow: /README.txt
Disallow: /web.config

# 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/

# Parameters
Disallow: /*?

#Block 404
Disallow: /*404*

#Sitemap
Sitemap: https://www.globant.com/sitemap_index.xml