#
# 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
# Sitemap
Sitemap: https://www.jyu.fi/sitemap.xml
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.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/
# Define access-restrictions for robots/spiders
# http://www.robotstxt.org/wc/norobots.html
# By default we allow robots to access all areas of our site
# already accessible to anonymous users
User-agent: *
Disallow:
User-agent: Discordbot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: MauiBot
Disallow: /
User-agent: Qwantify
Disallow: /
User-agent: ZumBot
Disallow: /
User-agent: Arachni
Disallow: /
User-agent: VelenPublicWebCrawler
Disallow: /
User-agent: +centurybot9.gmail.com
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: YandexBot
Disallow: /
User-agent: Mediatoolkitbot
Disallow: /
# Add Googlebot-specific syntax extension to exclude forms
# that are repeated for each piece of content in the site
# the wildcard is only supported by Googlebot
# http://www.google.com/support/webmasters/bin/answer.py?answer=40367&ctx=sibling
User-Agent: Googlebot
Disallow: /*?
Disallow: /*atct_album_view$
Disallow: /*folder_factories$
Disallow: /*folder_summary_view$
Disallow: /*login_form$
Disallow: /*mail_password_form$
Disallow: /*@@search$
Disallow: /*/search$
Disallow: /*search_rss$
Disallow: /*sendto_form$
Disallow: /*summary_view$
Disallow: /*thumbnail_view$
Disallow: /*/view$