#
# 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
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.md
Disallow: /composer/Metapackage/README.txt
Disallow: /composer/Plugin/ProjectMessage/README.md
Disallow: /composer/Plugin/Scaffold/README.md
Disallow: /composer/Plugin/VendorHardening/README.txt
Disallow: /composer/Template/README.txt
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/README.txt
# 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
Disallow: /media/oembed
Disallow: /*/media/oembed
# 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
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed

# Faceted resource browsing.
# Each facet combination is a unique URL that can never be served from
# cache and costs 12-19s of PHP to render, e.g.
#   /resources/tools/learning-area/11/learning-area/84/rla/LHA%20Boards
# Canonical content stays crawlable: /resources, /resources/tools, and
# every /resources/reports/* and /resources/spotlight/* page.
Disallow: /*learning-area/
Disallow: /*/rla/
Disallow: /*?*learning-area=
Disallow: /*?*type=All

# Deep calendar entries.
# Crawlers enumerate these sequentially by node ID (/calendar/216201,
# /calendar/216202, ...). They duplicate the canonical /event/* pages,
# which remain crawlable along with /events and the /calendar landing page.
Disallow: /calendar/

# Legacy date-archive query parameters (10s+ renders, no index value).
Disallow: /*?*m=20
Disallow: /*?*cat=
Disallow: /*?*qt-front_page_tabs=

# Front-page pagination (duplicate content, 6-11s renders).
Disallow: /?page=

# Pace well-behaved crawlers. Honored by Bing, Yandex, marginalia, MJ12bot
# and Sogou. Google ignores Crawl-delay -- set the rate in Search Console.
Crawl-delay: 10

# Point crawlers at canonical URLs instead of letting them walk facets.
Sitemap: https://www.melkinginstitute.org/sitemap.xml