# robots.txt from https://fr.wikipedia.org/robots.txt # # Please note: There are a lot of pages on this site, and there are # some misbehaved spiders out there that go _way_ too fast. If you're # irresponsible, your access to the site may be blocked. # # advertising-related bots: User-agent: Mediapartners-Google* Disallow: / # Wikipedia work bots: User-agent: IsraBot Disallow: User-agent: Orthogaffe Disallow: # Crawlers that are kind enough to obey, but which we'd rather not have # unless they're feeding search engines. User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / # Some bots are known to be trouble, particularly those designed to copy # entire sites. Please obey robots.txt. User-agent: sitecheck.internetseer.com Disallow: / User-agent: Zealbot Disallow: / User-agent: MSIECrawler Disallow: / User-agent: SiteSnagger Disallow: / User-agent: WebStripper Disallow: / User-agent: WebCopier Disallow: / User-agent: Fetch Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: WebZIP Disallow: / User-agent: linko Disallow: / User-agent: HTTrack Disallow: / User-agent: Microsoft.URL.Control Disallow: / User-agent: Xenu Disallow: / User-agent: larbin Disallow: / User-agent: libwww Disallow: / User-agent: ZyBORG Disallow: / User-agent: Download Ninja Disallow: / # Misbehaving: requests much too fast: User-agent: fast Disallow: / # # Sorry, wget in its recursive mode is a frequent problem. # Please read the man page and use it properly; there is a # --wait option you can use to set the delay between hits, # for instance. # User-agent: wget Disallow: / # # The 'grub' distributed client has been *very* poorly behaved. # User-agent: grub-client Disallow: / # # Doesn't follow robots.txt anyway, but... # User-agent: k2spider Disallow: / # # Hits many times per second, not acceptable # http://www.nameprotect.com/botinfo.html User-agent: NPBot Disallow: / # A capture bot, downloads gazillions of pages with no public benefit # http://www.webreaper.net/ User-agent: WebReaper Disallow: / # Wayback Machine: defaults and whether to index user-pages # FIXME: Complete the removal of this block, per T7582. # User-agent: archive.org_bot # Allow: / # # Friendly, low-speed bots are welcome viewing article pages, but not # dynamically-generated pages please. # # Inktomi's "Slurp" can read a minimum delay between hits; if your # bot supports such a thing using the 'Crawl-delay' or another # instruction, please let us know. # # There is a special exception for API mobileview to allow dynamic # mobile web & app views to load section content. # These views aren't HTTP-cached but use parser cache aggressively # and don't expose special: pages etc. # # Another exception is for REST API documentation, located at # /api/rest_v1/?doc. # User-agent: * Allow: /w/api.php?action=mobileview& Allow: /w/load.php? Allow: /api/rest_v1/?doc Disallow: /w/index.php? Disallow: /w/skins/ Disallow: /api/ Disallow: /trap/ # #
# # partie robots.txt pour http://fr.wikipedia.org/ seulement # # Une partie générale pour tous les sites est ajoutée au-dessus de # celle-ci dans http://fr.wikipedia.org/robots.txt # # Merci de vérifier chaque modification avec un vérificateur de syntaxe # comme http://tool.motoricerca.info/robots-checker.phtml # Entrez http://fr.wikipedia.org/robots.txt comme URL à vérifier. # # ------------------------------------------------------------------------ # # Nom localisé des pages spéciales # Disallow: /wiki/Special:RandomPage Disallow: /wiki/Special:Search #Sitemap: https://de.wikidebates.org/w/sitemaps/de/sitemap-index-dewikidebates.xml Sitemap: https://en.wikidebates.org/w/sitemaps/en/sitemap-index-enwikidebates.xml Sitemap: https://es.wikidebates.org/w/sitemaps/es/sitemap-index-eswikidebates.xml Sitemap: https://fr.wikidebates.org/w/sitemaps/fr/sitemap-index-frwikidebates.xml Sitemap: https://it.wikidebates.org/w/sitemaps/it/sitemap-index-itwikidebates.xml Sitemap: https://pt.wikidebates.org/w/sitemaps/pt/sitemap-index-ptwikidebates.xml