#
# 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: *
# 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: /node/
#Disallow: /search/
Disallow: /?q=search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
# 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
Disallow: /*?popupvideo=true$

# custom
Disallow: /flag/
Disallow: /sites/default/files/pdf/

# Unijobs
# See https://www.timeshighereducation.com/unijobs/robots.txt
Disallow: /unijobs/session-img/
Disallow: /unijobs/invalid-request/
Disallow: /unijobs/document/
Disallow: /unijobs/analytics/
Disallow: /unijobs/en-us/session-img/
Disallow: /unijobs/en-us/invalid-request/
Disallow: /unijobs/en-us/document/
Disallow: /unijobs/en-us/analytics/
Disallow: /unijobs/en-au/session-img/
Disallow: /unijobs/en-au/invalid-request/
Disallow: /unijobs/en-au/document/
Disallow: /unijobs/en-au/analytics/
Disallow: /unijobs/*/searchjobs/*
Disallow: /unijobs/*/jobsrss/*
Disallow: /unijobs/jobsrss/*
Disallow: /unijobs/*/jbequicksignup/*
Disallow: /unijobs/*/emailjob/*
Disallow: /unijobs/your-jobs/*
Disallow: /unijobs/external-redirect-registration*
Disallow: /unijobs/*/emailjob/*
Disallow: /unijobs/*/previewjob/*
Disallow: /unijobs/searchjobs/*
Disallow: /unijobs/jobsrss/*
Disallow: /unijobs/jbequicksignup/*
Disallow: /unijobs/emailjob/*
Disallow: /unijobs/your-jobs/*
Disallow: /unijobs/external-redirect-registration*
Disallow: /unijobs/emailjob/*
Disallow: /unijobs/previewjob/*
Disallow: /*?*keywords=

# Global Nav
Disallow: /global-nav-esi/*

# MZ
Disallow: /et$

# HybridAuth
Disallow: /hybridauth/endpoint

# Bad urls, particularly from Sogou web spider
Disallow: /contact-us/content/*
Disallow: /contact-us/author/*
Allow: /contact-us/

Sitemap: https://www.timeshighereducation.com/sitemap.xml
Sitemap: https://www.timeshighereducation.com/sitemap-types-node-ranking_dataset.xml
Sitemap: https://www.timeshighereducation.com/unijobs/sitemapindex.xml
Sitemap: https://www.timeshighereducation.com/datapoints/sitemap.xml
Sitemap: https://www.timeshighereducation.com/campus/sitemap.xml