# # 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 # # For syntax checking, see: # http://www.frobee.com/robots-txt-check User-agent: googlebot-news Sitemap: https://information.tv5monde.com/googlenews.xml 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.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/ Disallow: /asset/ # 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: *&sa=U&ved=* Disallow: *info/partenaire* Disallow: *info/credits* Disallow: *widget* Disallow: *id_dilem* Disallow: /dilem?* Allow: /misc/*.js* Allow: /sites/*.js* Allow: /template/*.js* Allow: /css/ Allow: /sites/*.css* Sitemap: https://information.tv5monde.com/sitemap-image.xml Sitemap: https://information.tv5monde.com/sitemap-video.xml Sitemap: https://information.tv5monde.com/googlenews.xml Sitemap: https://information.tv5monde.com/sitemap.xml # 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: / Sitemap: https://information.tv5monde.com/sitemap.xml