# # 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 # Allowed search engines directives User-agent: Mediapartners-Google User-agent: Googlebot User-agent: Googlebot-Image User-agent: Googlebot-Mobile User-agent: Googlebot-News User-agent: Googlebot-Video User-agent: Adsbot-Google User-agent: Googlebot_Nauxeo User-agent: Twitterbot User-agent: Applebot User-agent: Bingbot User-agent: SiteAuditBot User-agent: Publication-Access-for-Facebook User-agent: facebookexternalhit User-agent: Flipboard User-agent: FlipboardProxy User-agent: upday # Crawl-delay: 10 #Sitemaps Sitemap: https://www.sudinfo.be/sitemap-correctif-si-0.xml Sitemap: https://www.sudinfo.be/sitemap-correctif-si-1.xml Sitemap: https://www.sudinfo.be/sites/default/files/sitemaps/sitemapnews-0.xml Sitemap: https://www.sudinfo.be/sites/default/files/sitemaps/sitemapindex.xml # CSS, JS, Images Allow: /misc/*.css$ Allow: /misc/*.css? Allow: /misc/*.js$ Allow: /misc/*.js? Allow: /misc/*.gif Allow: /misc/*.jpg Allow: /misc/*.jpeg Allow: /misc/*.png Allow: /modules/*.css$ Allow: /modules/*.css? Allow: /modules/*.js$ Allow: /modules/*.js? Allow: /modules/*.gif Allow: /modules/*.jpg Allow: /modules/*.jpeg Allow: /modules/*.png 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: /themes/*.css$ Allow: /themes/*.css? Allow: /themes/*.js$ Allow: /themes/*.js? Allow: /themes/*.gif Allow: /themes/*.jpg Allow: /themes/*.jpeg Allow: /themes/*.png # 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/ # 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: /*fb_comment_id= # Disallow General Path Disallow: /rossel.nuggad.net/ Disallow: /a.teads.tv/ Disallow: /javascripts/ Disallow: /cgi-mod/ Disallow: /shares_callback/ Disallow: /trackuity.immo.vlan.be/ Disallow: /81985301/ Disallow: /GPSLINK* Disallow: /check_cookies* Disallow: /phpincludes/ Disallow: /forward/ Disallow: /api/ Disallow: /reactions_callback/ Disallow: /programme-tv/* Disallow: /*/paywall?page=* Disallow: /taxonomy/term/*/acff/clubs/ Disallow: /term/*/paywall Disallow: /node/* # Archives Paths #Disallow: /archive/index* Disallow: /archives/recherche* # App Universal Linking App IOS #Allow: /.well-known/ #Allow: /apple-app-site-association # Disallowed search engines directives User-agent: 5emeRue Disallow: / User-agent: 5erue Disallow: / User-agent: adequat Disallow: / User-agent: adequat-systems Disallow: / User-agent: AmiSoftware Disallow: / User-agent: anthropic-ai Disallow: / User-agent: Argus Disallow: / User-agent: Ask n read Disallow: / User-agent: asknread.com Disallow: / User-agent: Augure Disallow: / User-agent: auramundi Disallow: / User-agent: Bloodhound Disallow: / User-agent: CCBot Disallow: / User-agent: ChatGPT-User Disallow: / User-agent: Cision Disallow: / User-agent: Claude-Web Disallow: / User-agent: coexel Disallow: / User-agent: ConveraCrawler Disallow: / User-agent: Corporama Disallow: / User-agent: cydralspider Disallow: / User-agent: Digimind Disallow: / User-agent: Download Ninja Disallow: / User-agent: downloadexpress Disallow: / User-agent: EDD Disallow: / User-agent: ellisphere Disallow: / User-agent: eureka Disallow: / User-agent: Europresse Disallow: / User-agent: Explore Disallow: / User-agent: Factiva Disallow: / User-agent: Fasterfox Disallow: / User-agent: Fetch Disallow: / User-agent: gammaSpider Disallow: / User-Agent: Google-Extended Disallow: / User-agent: GPTBot Disallow: / User-agent: grub-client Disallow: / User-agent: HTTrack Disallow: / User-agent: ia_archiver Disallow: / User-agent: ia_archiver-web.archive.org Disallow: / User-agent: indexer Disallow: / User-agent: infoseek Disallow: / User-agent: Jetbot Disallow: / User-agent: k2spider Disallow: / User-agent: Kantar Disallow: / User-agent: kbcrawl Disallow: / User-agent: Knowings Disallow: / User-agent: larbin Disallow: / User-agent: leadbox Disallow: / User-agent: libwww Disallow: / User-agent: linkfluence Disallow: / User-agent: linko Disallow: / User-agent: manageo Disallow: / User-agent: mediacompil Disallow: / User-agent: Meltwater Disallow: / User-agent: mention Disallow: / User-agent: Moreover Disallow: / User-agent: MSIECrawler Disallow: / User-agent: mytwip Disallow: / User-agent: newscan-online Disallow: / User-agent: NewsNow Disallow: / User-agent: Newzbin Disallow: / User-agent: NPBot Disallow: / User-agent: ObjectsSearch Disallow: / User-agent: Offline Explorer Disallow: / User-agent: opinion-tracker Disallow: / User-agent: Pimptrain Disallow: / User-agent: proxem Disallow: / User-agent: QuepasaCreep Disallow: / User-agent: Qwam content intelligence Disallow: / User-agent: Raven Disallow: / User-agent: readability.com Disallow: / User-agent: scoop.it Disallow: / User-agent: score3 Disallow: / User-agent: Sindup Disallow: / User-agent: sitecheck.internetseer.com Disallow: / User-agent: SiteSnagger Disallow: / User-agent: spotter Disallow: / User-agent: Synthesio Disallow: / User-agent: Talkwater Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: trendeo Disallow: / User-agent: trendybuzz Disallow: / User-agent: TunitinBot Disallow: / User-agent: TurnitinBot Disallow: / User-agent: up2news Disallow: / User-agent: vecteurplus Disallow: / User-agent: Verif Disallow: / User-agent: verticalsearch Disallow: / User-agent: vsw Disallow: / User-agent: wapspider Disallow: / User-agent: WebCopier Disallow: / User-agent: WebReaper Disallow: / User-agent: WebStripper Disallow: / User-agent: WebZinger Disallow: / User-agent: WebZIP Disallow: / User-agent: Wget Disallow: / User-agent: winello Disallow: / User-agent: Youmag Disallow: / User-agent: Zealbot Disallow: / User-agent: Zite Disallow: / User-agent: ZyBORG Disallow: /