# $Id: robots.txt,v 1.9.2.2 2010/09/06 10:37:16 goba Exp $
#
# 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/wc/robots.html
#
# For syntax checking, see:
# http://www.sxw.org.uk/computing/robots/check.html

# DueDil robots.txt - Complete no-index configuration
# Prevent all search engines from crawling and indexing the entire site
User-agent: *
Disallow: /

User-agent: Seekbot/1.0*
Disallow: /
User-agent: *
Crawl-delay: 10
# 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.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /contact/
Disallow: /logout/
Disallow: /node/add/
Disallow: /user/register/
Disallow: /user/password
Disallow: /signup_link_share
Disallow: /signup/
Disallow: /verify_signup/
Disallow: /user
Disallow: /user/
Disallow: /ajax_fast_offsite/
Disallow: /ajax_slow_offsite/
Disallow: /linkedin/authenticate
Disallow: /login/
Disallow: /*edit$
Disallow: */contact$
Disallow: */lists/introduction/*
Disallow: */map$
Disallow: */company/*/*/*/contact$
Disallow: */company/*/*/*/group$
Disallow: */company/*/*/*/documents$
Disallow: */company/*/*/*/risk$
Disallow: */company/*/*/*/activity$
Disallow: */company/*/*/*/news$
Disallow: */company/*/*/*/financials$
Disallow: */company/*/*/*/ownership$
Disallow: */ownership/parent-companies$
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=contact/
Disallow: /?q=logout/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Disallow: *?status=*
Disallow: *?view=*
Disallow: *?to=*
# NoIndex
Noindex: *?ref=*
Noindex: *?source=*
Noindex: *?t-curated_collections=*
Noindex: *?flagged=*
Noindex: *?replytocom=*
Noindex: *?s=*
Noindex: *?_method=*
Noindex: */company/*/*/*/people$
Noindex: *?utm_source=*
Noindex: *?sort=*
Noindex: *utm_medium=*
# International
Disallow: */company/fr/*
Disallow: */company/de/*
Disallow: */company/be/*
Disallow: */company/nl/*
Disallow: */company/lu/*
Disallow: */company/no/*
Disallow: */company/se/*
Disallow: */company/fi/*
Disallow: */company/it/*
Disallow: */company/pt/*
Disallow: */company/hu/*
Disallow: */company/pl/*
Disallow: */company/lt/*
Disallow: */company/sk/*
Disallow: */company/mt/*
Disallow: */company/is/*
# Directors
Noindex: */director/*/*
# Misc
User-agent: Companybook-Crawler*
Disallow: /

Disallow: /legal/enterprise/april2018terms