# ################################################################################ # _____ # | . . | # |_____| # ____ ___|_|___ ____ # ()___) __ ()___) # // /| ____ |\ \\ # // / | ____ | \ \\ # (___) |___________| (___) # (___) (_______) (___) # (___) (___) (___) # (___) |_| (___) # (___) ___/___\___ | | # | | | . . . | |.| # |.| |___________| /___\ # /___\ ||| ||| // \\ # // \\ ||| ||| \\ // # \\ // ||| ||| \\ // # \\ // ()__) (__() # /// \\\ # /// \\\ # _///___ ___\\\_ # |_______| |_______| robots.txt # ################################################################################ # Bad bots ------> BLOCK ################################################################################ # proximic Documentation https://www.comscore.com/proximic-spider User-agent: proximic User-agent: BizInformation User-agent: BLEXBot User-agent: Riddler User-agent: ltx71 User-agent: magpie-crawler User-agent: grapeshot User-agent: GrapeshotCrawler User-agent: GigablastOpenSource User-agent: BUbiNG User-agent: linkdexbot User-agent: linkdexbot/2.2 User-agent: SEOkicks User-agent: SEOkicks-Robot User-Agent: panscient.com User-agent: WebDataStats User-agent: ZoominfoBot Disallow: / # BLEXBot (very bad bot) Documentation http://webmeup-crawler.com/ User-agent: BLEXBot Disallow: / # Common Crawl ----> Block Documentation http://commoncrawl.org/faq/ User-agent: CCBot Disallow: / # SEO bots ------> BLOCK ################################################################################ # MOZ.com (DotBot) Documentation https://moz.com/researchtools/ose/dotbot # MAJESTIC.com Documentation http://www.majestic12.co.uk/projects/dsearch/mj12bot.php # Ahrefs.com Documentation https://ahrefs.com/robot # SEOkick.de Documentation http://www.seokicks.de/robot.html # MegaIndex.com Documentation https://megaindex.com/crawler # Semrush.com Documentation https://fr.semrush.com/bot/ # OpenLinkProfiler Documentation http://openlinkprofiler.org/bot User-agent: dotbot User-agent: DotBot User-agent: DotBot/1.1 User-agent: MJ12bot User-agent: AhrefsBot User-agent: SEOkicks-Robot Disallow: / # MOZ.com (DotBot) Documentation https://moz.com/researchtools/ose/dotbot User-agent: dotbot Disallow: / User-agent: DotBot Disallow: / User-agent: DotBot/1.1 Disallow: / # Semrush.com Documentation https://fr.semrush.com/bot/ User-agent: SemrushBot Disallow: / User-agent: SemrushBot-SA Disallow: / # MegaIndex.ru (very bad bot) ---> Respects only the following directive "User-agent: *" User-agent: MegaIndex.ru User-agent: MegaIndex.ru/2.0 Disallow: / # OpenLinkProfiler Documentation http://openlinkprofiler.org/bot User-agent: spbot Disallow: / # Crawl-delay: 10 # Crawler ################################################################################ # Linguee ----> Block https://www.linguee.com/bot User-agent: Linguee Disallow: / # DeuSu ----> Block Documentation https://deusu.de/robot.html User-agent: DeuSu Disallow: / # TurnitinBot ----> Block Documentation https://turnitin.com/robot/crawlerinfo.html User-agent: TurnitinBot Disallow: / # Social Network ################################################################################ # Pinterest ----> Temporary off Documentation https://help.pinterest.com/fr/articles/about-pinterest-crawler#Web user-agent: Pinterest Disallow: / # Crawl-delay: 20 # Search engines ################################################################################ # Yandex ----> Block Documentation https://yandex.com/support/webmaster/controlling-robot/robots-txt.xml # Coccobot ----> Block Documentation http://help.coccoc.com/en/search-engine/robots-txt # Yeti ----> Block Documentation http://naver.me/bot # Baidu ----> Block Documentation http://robots-txt.com/ressources/robots-txt-baidu/ # 360Spider ----> Block Documentation http://www.botreports.com/user-agent/360spider.shtml # Sogou ----> Block # Seekbot ----> Block Seekport Crawler http://seekport.com/ - no documentation User-agent: Yandex User-agent: YandexBot User-agent: YandexMobileBot User-agent: YandexImageResizer User-agent: coccocbot User-agent: coccocbot-web User-agent: coccocbot-image # User-agent: 360Spider User-agent: Yeti # User-agent: Baiduspider # User-agent: Sogou web spider # User-agent: Sogou User-Agent: seekbot User-Agent: Seekport User-Agent: Seekport Crawler Disallow: / # Picsearch ----> Temporary off Documentation http://www.picsearch.com/bot.html image search service User-agent: psbot Disallow: / # Tiscali IstellaBot # User-agent: IstellaBot # Disallow: / # Cliqzbot Documentation https://cliqz.com/en/cliqzbot # User-agent: Cliqzbot # Disallow: / # MojeekBot Documentation https://www.mojeek.com/bot.html # User-agent: MojeekBot # Disallow: / # Applebot Documentation http://robots-txt.com/ressources/robots-txt-apple/ # User-agent: Applebot # Disallow: / # Qwant Documentation http://robots-txt.com/ressources/robots-txt-qwant/ # User-agent: Qwantify # Disallow: / # Exalead Documentation https://www.exalead.com/search/webmasterguide # User-agent: Exabot # Crawl-delay: 60 # Yahoo Documentation http://robots-txt.com/ressources/robots-txt-yahoo/ https://help.yahoo.com/kb/SLN22600.html # User-agent: Slurp # Crawl-delay: 60 # Orange Documentation http://blog.lemoteur.fr/orangebot/ # User-agent: OrangeBot # User-agent: OrangeBot-Collector # Crawl-delay: 60 # Bing Documentation http://robots-txt.com/ressources/robots-txt-bing/ # User-agent: bingbot # User-agent: msnbot # Crawl-delay: 20 # Disallow: / # Google Documentation https://support.google.com/webmasters/answer/1061943?hl=fr # User-agent: Googlebot # User-agent: Googlebot-Image # User-agent: Googlebot-Video # Disallow: / # Wayback Machine (archive.org) ---> ALLOW ################################################################################ # Documentation http://robots-txt.com/ressources/robots-txt-alexa/ # https://archive.org/details/archive.org_bot # User-agent: ia_archiver # User-agent: ia_archiver-web.archive.org # User-agent: archive.org_bot # Disallow: / # https://www.skimble.com/robots.txt # https://github.com/jfqd/robots.txt/blob/master/robots.txt # https://www.transindus.co.uk/robots.txt # http://www.columbec.com/robots.txt # http://www.mecatrouve.com/robots.txt ################################################################################ # See http://www.robotstxt.org/wc/norobots.html for documentation on how to use the robots.txt file # # To ban all spiders from the entire site uncomment the next two lines: # User-Agent: * # Disallow: / # SITEMAP: http://www.skimble.com/sitemap_index.xml.gz # Slow down bots User-agent: * Crawl-delay: 1 User-Agent: * Disallow: /wp-admin/ User-Agent: * Disallow: /upload/ User-Agent: * Disallow: /media/ User-agent: MauiBot Disallow: / User-agent: PetalBot Disallow: / User-agent: grapeshot Disallow: / # User-Agent: Baiduspider # Disallow: / User-Agent: MegaIndex Disallow: / User-Agent: Treato-Bot Disallow: / User-agent: SemrushBot Disallow: / User-agent: Linguee Bot Disallow: / User-Agent: The Knowledge AI Disallow: / # Disallow: Sistrix User-agent: sistrix Disallow: / # Disallow: Sistrix User-agent: SISTRIX Crawler Disallow: / # Disallow: Sistrix User-agent: SISTRIX Disallow: / # Disallow: SEOkicks-Robot User-agent: SEOkicks-Robot Disallow: / # Disallow: jobs.de-Robot User-agent: jobs.de-Robot Disallow: / # Backlink Analysis user-agent: AhrefsBot disallow: / # Bot der Leipziger Unister Holding GmbH user-agent: UnisterBot disallow: / # http://www.opensiteexplorer.org/dotbot User-agent: DotBot Disallow: / User-agent: dotbot Disallow: / # http://www.searchmetrics.com User-agent: SearchmetricsBot Disallow: / # http://www.majestic12.co.uk/projects/dsearch/mj12bot.php User-agent: MJ12bot Disallow: / # http://www.domaintools.com/webmasters/surveybot.php User-agent: SurveyBot Disallow: / # http://www.seodiver.com/bot user-agent: SEOdiver disallow: / # http://openlinkprofiler.org/bot User-agent: spbot Disallow: / # http://www.wotbox.com/bot/ User-agent: wotbox Disallow: / # http://www.meanpath.com/meanpathbot.html User-agent: meanpathbot Disallow: / # http://www.backlinktest.com/crawler.html User-agent: BacklinkCrawler Disallow: / # http://www.brandwatch.com/magpie-crawler/ User-agent: magpie-crawler Disallow: / # http://filterdb.iss.net/crawler/ User-agent: oBot Disallow: / User-agent: fr-crawler Disallow: / # http://webmeup-crawler.com User-agent: BLEXBot Disallow: / # https://megaindex.com/crawler User-agent: MegaIndex.ru Disallow: / User-agent: megaindex.com Disallow: / # http://www.cloudservermarket.com User-Agent: CloudServerMarketSpider Disallow: / # http://www.trendiction.de/de/publisher/bot User-Agent: trendictionbot Disallow: / # http://www.exalead.com User-agent: Exabot Disallow: / # http://www.career-x.de/bot.html User-agent: careerbot Disallow: / # https://www.lipperhey.com/en/about/ User-agent: Lipperhey-Kaus-Australis Disallow: / User-agent: seoscanners.net Disallow: / User-agent: MetaJobBot Disallow: / User-agent: Spiderbot Disallow: / User-agent: LinkStats Disallow: / User-agent: JobboerseBot Disallow: / User-agent: ICCrawler Disallow: / User-agent: Plista Disallow: / User-agent: Domain Re-Animator Bot Disallow: / # https://www.lipperhey.com/en/about/ User-agent: Lipperhey-Kaus-Australis Disallow: / # https://turnitin.com/robot/crawlerinfo.html User-agent: turnitinbot Disallow: / # http://help.coccoc.com/ User-agent: coccoc Disallow: / # ubermetrics-technologies.com User-agent: um-IC Disallow: / # datenbutler.de User-agent: mindUpBot Disallow: / # http://searchgears.de/uber-uns/crawling-faq.html User-agent: sg-Orbiter Disallow: / # http://commoncrawl.org/faq/ User-agent: CCBot Disallow: / # https://www.qwant.com/ User-agent: Qwantify Disallow: / # http://linkfluence.net/ User-agent: Kraken Disallow: / # http://www.botje.com/plukkie.htm User-agent: plukkie Disallow: / # https://www.safedns.com/searchbot User-agent: SafeDNSBot Disallow: / # http://www.haosou.com/help/help_3_2.html User-agent: 360Spider Disallow: / # http://www.haosou.com/help/help_3_2.html User-agent: HaosouSpider Disallow: / # http://www.moz.com/dp/rogerbot User-agent: rogerbot Disallow: / # http://www.openhose.org/bot.html User-agent: OpenHoseBot Disallow: / # http://www.screamingfrog.co.uk/seo-spider/ User-agent: Screaming Frog SEO Spider Disallow: / # http://thumbsniper.com User-agent: ThumbSniper Disallow: / # http://www.radian6.com/crawler User-agent: R6_CommentReader Disallow: / User-agent: ImplisenseBot Disallow: / # http://cliqz.com/company/cliqzbot User-agent: Cliqzbot Disallow: / # https://www.aihitdata.com/about User-agent: aiHitBot Disallow: / # http://www.trendiction.com/en/publisher/bot User-Agent: trendictionbot Disallow: / # http://seocompany.store User-Agent: adscanner Disallow: / # https://github.com/yasserg/crawler4j/ User-Agent: crawler4j Disallow: / # http://warebay.com/bot.html User-agent: WBSearchBot Disallow: / User-agent: Python/3.5 aiohttp Disallow: / User-agent: Toweya.com Disallow: / # http://www.website-datenbank.de/ User-agent: netEstate Disallow: / # http://law.di.unimi.it/BUbiNG.html User-agent: BUbiNG Disallow: / # http://www.linguee.com/bot; bot@linguee.com User-agent: Linguee Disallow: / User-agent: SemrushBot-SA Disallow: / # www.sentibot.eu User-agent: sentibot Disallow: / User-agent: SentiBot Disallow: / # http://velen.io User-agent: VelenPublicWebCrawler Disallow: / User-agent: DomainCrawler Disallow: / # https://moz.com/help/guides/moz-procedures/what-is-rogerbot User-agent: rogerbot Disallow: / User-agent: IndeedBot Disallow: / # http://www.garlik.com User-agent: GarlikCrawler Disallow: / # https://www.gosign.de/typo3-extension/typo3-sicherheitsmonitor/ User-agent: Gosign-Security-Crawler Disallow: / # http://www.siteliner.com/bot User-agent: Siteliner Disallow: / # https://sabsim.com User-agent: SabsimBot Disallow: / # http://ltx71.com/ User-agent: ltx71 Disallow: / ################################################################################ # Rule 1 Records must be separated by empty lines User-agent: MJ12bot Disallow: / User-agent: seznambot Disallow: / User-agent: YandexBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: AhrefsBot Disallow: / # Rule 2 Robots.txt sitemap list is very important! 202205 debug a month ! User-agent: * DisAllow: /wp-admin/ Sitemap: https://qa.1r1g.com/sf/sitemap.xml Sitemap: https://qa.1r1g.com/sf/sitemap-question.xml Sitemap: https://qa.1r1g.com/sf/sitemap-questionpage.xml Sitemap: https://qa.1r1g.com/sf/sitemap-questiontags.xml Sitemap: https://qa.1r1g.com/sf/sitemap-answers.xml Sitemap: https://qa.1r1g.com/sf/sitemap-users.xml