fouesnant.opac3d.fr

# $Id: robots.txt 88626 2017-08-22 07:30:09Z rr $
#
# 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

User-agent: *
Crawl-delay: 10
Sitemap: /sitemap.xml

# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /sites/
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
Disallow: /xmlrpc.php
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /contact/
Disallow: /logout/
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
# Paths (no clean URLs)
Disallow: /*lookfor*
Disallow: /*filter*
Disallow: /*rubrique=CG*
Disallow: /*action=Record*
Disallow: /*action=ajax*
Disallow: /*action=Ajax*
Disallow: /*action=Login*
Disallow: /*action=Account*
Disallow: /*action=Advanced*
Disallow: /*action=Basket*
Disallow: /*action=SSOAuth*
Disallow: /*sites/all/modules/bibliosearch/util/*
User-agent: BLEXBot
User-agent: AhrefsBot
User-agent: MJ12bot
User-agent: SemrushBot
Disallow: /