about summary refs log tree commit diff stats
path: root/js/games/nluqo.github.io/robots.txt
diff options
context:
space:
mode:
authorelioat <elioat@tilde.institute>2023-08-23 07:52:19 -0400
committerelioat <elioat@tilde.institute>2023-08-23 07:52:19 -0400
commit562a9a52d599d9a05f871404050968a5fd282640 (patch)
tree7d3305c1252c043bfe246ccc7deff0056aa6b5ab /js/games/nluqo.github.io/robots.txt
parent5d012c6c011a9dedf7d0a098e456206244eb5a0f (diff)
downloadtour-562a9a52d599d9a05f871404050968a5fd282640.tar.gz
*
Diffstat (limited to 'js/games/nluqo.github.io/robots.txt')
-rw-r--r--js/games/nluqo.github.io/robots.txt94
1 files changed, 94 insertions, 0 deletions
diff --git a/js/games/nluqo.github.io/robots.txt b/js/games/nluqo.github.io/robots.txt
new file mode 100644
index 0000000..150b336
--- /dev/null
+++ b/js/games/nluqo.github.io/robots.txt
@@ -0,0 +1,94 @@
+#
+# 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: *
+Crawl-delay: 10
+# CSS, JS, Images
+Allow: /misc/*.css$
+Allow: /misc/*.css?
+Allow: /misc/*.js$
+Allow: /misc/*.js?
+Allow: /misc/*.gif
+Allow: /misc/*.jpg
+Allow: /misc/*.jpeg
+Allow: /misc/*.png
+Allow: /modules/*.css$
+Allow: /modules/*.css?
+Allow: /modules/*.js$
+Allow: /modules/*.js?
+Allow: /modules/*.gif
+Allow: /modules/*.jpg
+Allow: /modules/*.jpeg
+Allow: /modules/*.png
+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: /themes/*.css$
+Allow: /themes/*.css?
+Allow: /themes/*.js$
+Allow: /themes/*.js?
+Allow: /themes/*.gif
+Allow: /themes/*.jpg
+Allow: /themes/*.jpeg
+Allow: /themes/*.png
+# Directories
+Disallow: /includes/
+Disallow: /misc/
+Disallow: /modules/
+Disallow: /profiles/
+Disallow: /scripts/
+Disallow: /themes/
+# Files
+Disallow: /CHANGELOG.txt
+Disallow: /cron.php
+Disallow: /INSTALL.mysql.txt
+Disallow: /INSTALL.pgsql.txt
+Disallow: /INSTALL.sqlite.txt
+Disallow: /install.php
+Disallow: /INSTALL.txt
+Disallow: /LICENSE.txt
+Disallow: /MAINTAINERS.txt
+Disallow: /update.php
+Disallow: /UPGRADE.txt
+Disallow: /xmlrpc.php
+# 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/
+# added by janp per observed search engine results
+#   consensus seems to be that wildcard is helpful, so including
+Disallow: /home/*
+
+# Paths (no clean URLs)
+Disallow: /?q=admin/
+Disallow: /?q=comment/reply/
+Disallow: /?q=filter/tips/
+Disallow: /?q=node/add/
+Disallow: /?q=search/
+Disallow: /?q=user/password/
+Disallow: /?q=user/register/
+Disallow: /?q=user/login/
+Disallow: /?q=user/logout/