#
# 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: *

# 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
Allow: /sites/*/files/

# Directories
Disallow: /core/
Disallow: /profiles/
Disallow: /modules/
Disallow: /libraries/
Disallow: /themes/
Disallow: /sites/

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

# Paths (clean URLs)
Disallow: /admin/
Disallow: /en/admin/
Disallow: /fr/admin/
Disallow: /comment/
Disallow: /en/comment/
Disallow: /fr/comment/
Disallow: /filter/tips
Disallow: /en/filter/tips
Disallow: /fr/filter/tips
Disallow: /node/
Disallow: /en/node/
Disallow: /fr/node/
Disallow: /search?
Disallow: /en/search?
Disallow: /fr/search?
Disallow: /search/*?
Disallow: /en/search/*?
Disallow: /fr/search/*?
Disallow: /external-comment/
Disallow: /en/external-comment/
Disallow: /fr/external-comment/
Disallow: /external-vote/
Disallow: /en/external-vote/
Disallow: /fr/external-vote/
Disallow: /vote-result/
Disallow: /en/vote-result/
Disallow: /fr/vote-result/
Disallow: /vote?
Disallow: /en/vote?
Disallow: /fr/vote?

# Datasets
Disallow: /data/revision/
Disallow: /data/dataset/*/history
Disallow: /data/api/
Disallow: /data/en/api/
Disallow: /data/fr/api/
Disallow: /data/dataset?keywords=*
Disallow: /data/en/dataset?keywords=*
Disallow: /data/fr/dataset?keywords=*
Disallow: /data/dataset?subject=*
Disallow: /data/en/dataset?subject=*
Disallow: /data/fr/dataset?subject=*
Disallow: /data/dataset?topic_category=*
Disallow: /data/en/dataset?topic_category=*
Disallow: /data/fr/dataset?topic_category=*

# Paths (no clean URLs)
Disallow: /index.php/admin/
Disallow: /index.php/comment/
Disallow: /index.php/filter/tips
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/external-comment/
Disallow: /index.php/external-vote/
Disallow: /index.php/vote-result/
Disallow: /index.php/user/

# Sitemap
Sitemap: https://open.canada.ca/sitemap.xml

# Crawl-delay
Crawl-delay: 5