#
# 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: /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.md
Disallow: /composer/Metapackage/README.txt
Disallow: /composer/Plugin/ProjectMessage/README.md
Disallow: /composer/Plugin/Scaffold/README.md
Disallow: /composer/Plugin/VendorHardening/README.txt
Disallow: /composer/Template/README.txt
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/README.txt
# 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
Disallow: /media/oembed
Disallow: /*/media/oembed
# 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
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed
# Liens du menu vers des facettes Publications
Disallow: /publication/recherche?f[0]=publication_facet_type_publication%3A1151
Disallow: /publication/recherche?f[0]=publication_facet_type_publication%3A1152
Disallow: /publication/recherche?f[0]=publication_facet_type_publication%3A1149
Disallow: /publication/recherche?f[0]=publication_facet_type_publication%3A1147
Disallow: /en/publication/search?f[0]=publication_facet_type_publication%3A1150
Disallow: /en/publication/search?f[0]=publication_facet_type_publication%3A1304
Disallow: /en/publication/search?f[0]=publication_facet_type_publication%3A1151
Disallow: /en/publication/search?f[0]=publication_facet_type_publication%3A1152
Disallow: /en/publication/search?f[0]=publication_facet_type_publication%3A1300

# Robots exclus de toute indexation.
User-agent: Meltawer
Disallow: /
#
User-agent: Digimind
Disallow: /
#
User-agent: Knowings
Disallow: /
#
User-agent: Sindup
Disallow: /
#
User-agent: Cision
Disallow: /
#
User-agent: Talkwater
Disallow: /
#
User-agent: TurnitinBot
Disallow: /
#
User-agent: ConveraCrawler
Disallow: /
#
User-agent: QuepasaCreep
Disallow: /
#
User-agent: Jetbot
Disallow: /
#
User-agent: NewsNow
Disallow: /
#
User-agent: kbcrawl
Disallow: /
#
User-agent: AmiSoftware
Disallow: /
#
User-agent: Newzbin
Disallow: /
#
User-agent: Ask n read
Disallow: /
#
User-agent: Qwam content intelligence
Disallow: /
#
User-agent: flipboard
Disallow: /
#
User-agent: FlipboardProxy
Disallow: /
#
User-agent: Synthesio
Disallow: /
#
User-agent: trendybuzz
Disallow: /
#
User-agent: spotter
Disallow: /
#
User-agent: scoop.it
Disallow: /
#
User-agent: linkfluence
Disallow: /
#
User-agent: 5emeRue
Disallow: /
#
User-agent: Augure
Disallow: /
#
User-agent: Corporama
Disallow: /
#
User-agent: readability.com
Disallow: /
#
User-agent: grub-client
Disallow: /
#
User-agent: ia_archiver
Disallow: /
#
User-agent: ia_archiver-web.archive.org
Disallow: /
#
User-agent: k2spider
Disallow: /
#
User-agent: libwww
Disallow: /
#
User-agent: wget
Disallow: /
#
User-agent: 5erue
Disallow: /
#
User-agent: adequat
Disallow: /
#
User-agent: adequat-systems
Disallow: /
#
User-agent: auramundi
Disallow: /
#
User-agent: coexel
Disallow: /
#
User-agent: ellisphere
Disallow: /
#
User-agent: leadbox
Disallow: /
#
User-agent: mention
Disallow: /
#
User-agent: Moreover
Disallow: /
#
User-agent: mytwip
Disallow: /
#
User-agent: NewsNow
Disallow: /
#
User-agent: Newzbin
Disallow: /
#
User-agent: opinion-tracker
Disallow: /
#
User-agent: proxem
Disallow: /
#
User-agent: score3
Disallow: /
#
User-agent: trendeo
Disallow: /
#
User-agent: vecteurplus
Disallow: /
#
User-agent: verticalsearch
Disallow: /
#
User-agent: vsw
Disallow: /
#
User-agent: winello
Disallow: /
#
User-agent: Fetch
Disallow: /
#
User-agent: infoseek
Disallow: /
#
User-agent: MSIECrawler
Disallow: /
#
User-agent: Offline Explorer
Disallow: /
#
User-agent: sitecheck.internetseer.com
Disallow: /
#
User-agent: SiteSnagger
Disallow: /
#
User-agent: Teleport
Disallow: /
#
User-agent: TeleportPro
Disallow: /
#
User-agent: WebCopier
Disallow: /
#
User-agent: WebStripper
Disallow: /
#
User-agent: Zealbot
Disallow: /
#
User-agent: asknread.com
Disallow: /
#
User-agent: ellisphere
Disallow: /
#
User-agent: spotter
Disallow: /
#
User-agent: TunitinBot
Disallow: /
#
User-agent: ConveraCrawler
Disallow: /
#
User-agent: QuepasaCreep
Disallow: /
#
User-agent: Meltwater
Disallow: /
#
User-agent: NewsNow
Disallow: /
#
User-agent: Digimind
Disallow: /
#
User-agent: Knowings D
Disallow: /
#
User-agent: Zite
Disallow: /
#
User-agent: Youmag
Disallow: /
#
User-agent: ClaudeBot
Disallow: /
#
User-agent: Bytespider
Disallow: /