Merge pull request #106 from SteveClement/tools

fix: [alexa] The generator wants to decode things ;)
pull/108/head
Alexandre Dulaunoy 2019-04-24 15:38:25 +02:00 committed by GitHub
commit 4d8ce3986f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 153 additions and 154 deletions

View File

@ -1,14 +1,11 @@
{
"matching_attributes": [
"hostname",
"domain",
"domain|ip"
],
"description": "Event contains one or more entries from the top 1000 of the most used website (Alexa).",
"version": 20190424,
"name": "Top 1000 website from Alexa",
"type": "hostname",
"list": [
"104.com.tw",
"11st.co.kr",
"123rf.com",
"126.com",
"1337x.to",
"163.com",
@ -16,38 +13,37 @@
"178.com",
"17ok.com",
"17track.net",
"1fichier.com",
"2345.com",
"2movierulz.gs",
"33sk.tv",
"2movierulz.ms",
"360.cn",
"360doc.com",
"3c.tmall.com",
"3dmgame.com",
"4399.com",
"45eijvhgj2.com",
"4chan.org",
"4pda.ru",
"51cto.com",
"51job.com",
"51sole.com",
"52pojie.cn",
"58.com",
"5ch.net",
"6.cn",
"91jm.com",
"65vk1fba34.com",
"6uwehz1xp4.com",
"9gag.com",
"abc.es",
"abola.pt",
"abs-cbn.com",
"academia.edu",
"accuweather.com",
"addroplet.com",
"addthis.com",
"adexchangegate.com",
"adkplatform.com",
"adobe.com",
"adp.com",
"agoda.com",
"airbnb.com",
"albawabhnews.com",
"aldar.ma",
"ali213.net",
"alibaba.com",
"alicdn.com",
@ -56,8 +52,7 @@
"aliyun.com",
"allegro.pl",
"allocine.fr",
"almashhadalaraby.com",
"alnaharegypt.com",
"allornamenti.com",
"alodokter.com",
"alwafd.news",
"amazon.ca",
@ -75,33 +70,30 @@
"ameblo.jp",
"americanas.com.br",
"americanexpress.com",
"analdin.com",
"ancestry.com",
"android.com",
"andhrajyothy.com",
"animeflv.net",
"animevost.org",
"aol.com",
"aparat.com",
"apkpure.com",
"apple.com",
"appledaily.com",
"archive.org",
"archiveofourown.org",
"areavip.com.br",
"artstation.com",
"arxiv.org",
"as.com",
"asahi.com",
"asana.com",
"ask.com",
"asos.com",
"asus.com",
"atlassian.net",
"atsofunpar.info",
"att.com",
"auction.co.kr",
"autodesk.com",
"avast.com",
"avgle.com",
"avito.ru",
"azure.com",
"babytree.com",
"baidu.com",
"baike.com",
@ -109,36 +101,35 @@
"bandcamp.com",
"banesconline.com",
"banggood.com",
"bankmellat.ir",
"bankofamerica.com",
"banvenez.com",
"battle.net",
"bbc.co.uk",
"bbc.com",
"beautifultrendstoday.com",
"beeg.com",
"behance.net",
"bestbuy.com",
"bet365.com",
"bet9ja.com",
"beytoote.com",
"bhphotovideo.com",
"biblegateway.com",
"bild.de",
"bilibili.com",
"billdesk.com",
"binance.com",
"bing.com",
"biobiochile.cl",
"bitbucket.org",
"bitly.com",
"blackboard.com",
"bleacherreport.com",
"blibli.com",
"blog.jp",
"blog.me",
"blogfa.com",
"blogger.com",
"blogspot.com",
"bloomberg.com",
"bodelen.com",
"bola.net",
"bol.uol.com.br",
"bolasport.com",
"bongacams.com",
"booking.com",
@ -151,40 +142,39 @@
"browsergames2019.com",
"bukalapak.com",
"businessinsider.com",
"buy.tmall.com",
"buzzfeed.com",
"bytedance.net",
"bzw315.com",
"ca.gov",
"caijing.com.cn",
"caixa.gov.br",
"caliente.mx",
"cam4.com",
"cambridge.org",
"canada.ca",
"canva.com",
"capitalone.com",
"cbc.ca",
"ccleaner.com",
"ccm.net",
"cdiscount.com",
"cdninstagram.com",
"championat.com",
"cdstm.cn",
"cfts1tifqr.com",
"chase.com",
"chaturbate.com",
"chatwork.com",
"chegg.com",
"chess.com",
"china.com.cn",
"chinadaily.com.cn",
"chinaz.com",
"chip.de",
"chiphell.com",
"chouftv.ma",
"chron.com",
"cima4u.tv",
"cimaclub.com",
"cinecalidad.to",
"cisco.com",
"citationmachine.net",
"citi.com",
"cjl58f3agc.com",
"cloudflare.com",
"cloudfront.net",
"cnbc.com",
@ -195,42 +185,41 @@
"cnn.com",
"cnnindonesia.com",
"cnzz.com",
"cobalten.com",
"codepen.io",
"coinmarketcap.com",
"com-fast.live",
"concursolutions.com",
"constintptr.com",
"convert2mp3.net",
"corriere.it",
"cornsapp.com",
"cornshub.com",
"costco.com",
"coupang.com",
"coursehero.com",
"coursera.org",
"craigslist.org",
"creditkarma.com",
"creditonebank.com",
"cricbuzz.com",
"crptentry.com",
"crunchbase.com",
"crunchyroll.com",
"csdn.net",
"dafont.com",
"dagospia.com",
"dailycaller.com",
"dailymail.co.uk",
"dailymotion.com",
"dangdang.com",
"daum.net",
"dawn.com",
"dcard.tw",
"dcinside.com",
"dell.com",
"deloplen.com",
"delta.com",
"depositphotos.com",
"detail.tmall.com",
"detik.com",
"deviantart.com",
"dhgate.com",
"dianping.com",
"dictionary.com",
"digialm.com",
"digikala.com",
"discogs.com",
"discordapp.com",
@ -240,7 +229,8 @@
"dkn.tv",
"dmm.co.jp",
"dmm.com",
"dns-shop.ru",
"dnevnik.ru",
"doc88.com",
"docin.com",
"dolohen.com",
"donga.com",
@ -248,7 +238,6 @@
"douban.com",
"doubleclick.net",
"doublepimp.com",
"doublepimpssl.com",
"douyu.com",
"dribbble.com",
"drive2.ru",
@ -257,14 +246,15 @@
"dropbox.com",
"drudgereport.com",
"dspmulti.com",
"duba.com",
"duckduckgo.com",
"duolingo.com",
"dy2018.com",
"dytt8.net",
"e-hentai.org",
"e9geolgzk6.com",
"ea.com",
"eastday.com",
"eastmoney.com",
"easypdfcombine.com",
"ebay-kleinanzeigen.de",
"ebay.co.uk",
"ebay.com",
@ -275,21 +265,21 @@
"ebc.net.tw",
"echo.msk.ru",
"ecosia.org",
"ecpms.net",
"egy.best",
"eksisozluk.com",
"elbalad.news",
"elitetorrent.io",
"elmogaz.com",
"elmundo.es",
"elmwatin.com",
"elpais.com",
"elsevier.com",
"elwatannews.com",
"engadget.com",
"enoughts.info",
"ensonhaber.com",
"envato.com",
"epfindia.gov.in",
"epicgames.com",
"epochtimes.com",
"eporner.com",
"espn.com",
"espncricinfo.com",
@ -298,36 +288,37 @@
"europa.eu",
"eventbrite.com",
"evernote.com",
"exdynsrv.com",
"ew.com",
"exhentai.org",
"exoclick.com",
"exosrv.com",
"expedia.com",
"express.co.uk",
"eyny.com",
"eztv.io",
"facebook.com",
"factaholics.com",
"familydoctor.com.cn",
"fandom.com",
"fanserials.vet",
"farfetch.com",
"farsnews.com",
"fazenda.gov.br",
"fb.ru",
"fbcdn.net",
"fc2.com",
"fedex.com",
"feedly.com",
"feng.com",
"ficbook.net",
"fhluqrhmqs.com",
"fidelity.com",
"filehippo.com",
"files.wordpress.com",
"film2movie.ws",
"fiverr.com",
"flaticon.com",
"flickr.com",
"flipkart.com",
"flirt4free.com",
"flvto.biz",
"fmovies.to",
"focuusing.com",
"food.tmall.com",
"forbes.com",
"force.com",
@ -335,18 +326,16 @@
"free.fr",
"freejobalert.com",
"freepik.com",
"friv.com",
"fromdoctopdf.com",
"gamepedia.com",
"gamer.com.tw",
"gamersky.com",
"gamespot.com",
"gamib.com",
"gazeta.ru",
"gearbest.com",
"geeksforgeeks.org",
"genius.com",
"getawesome1.com",
"getbootstrap.com",
"getpocket.com",
"gfycat.com",
"giphy.com",
@ -355,14 +344,14 @@
"gizmodo.com",
"glassdoor.com",
"globo.com",
"gloyah.net",
"gmanetwork.com",
"gmarket.co.kr",
"gmw.cn",
"gmx.net",
"go.com",
"goal.com",
"godaddy.com",
"gog.com",
"gogoanime.io",
"gome.com.cn",
"goo.ne.jp",
"goodreads.com",
@ -400,44 +389,48 @@
"google.com.tw",
"google.com.ua",
"google.com.vn",
"google.cz",
"google.de",
"google.dz",
"google.es",
"google.fr",
"google.gr",
"google.hu",
"google.it",
"google.nl",
"google.pl",
"google.pt",
"google.ro",
"google.ru",
"google.se",
"google.sk",
"googleusercontent.com",
"googlevideo.com",
"gosuslugi.ru",
"gotporn.com",
"grammarly.com",
"greatdexchange.com",
"grid.id",
"groupon.com",
"gsmarena.com",
"gstatic.com",
"gtarcade.com",
"guancha.cn",
"gyazo.com",
"hajoopteg.com",
"hao123.com",
"harvard.edu",
"hatena.ne.jp",
"hatenablog.com",
"hbo.com",
"hbogo.com",
"hbonow.com",
"hclips.com",
"hdfcbank.com",
"hdrezka.ag",
"hdzog.com",
"healthline.com",
"heavy.com",
"hellomagazine.com",
"hepsiburada.com",
"heroesofrpg.com",
"hespress.com",
"hh.ru",
"hm.com",
"homedepot.com",
"hotels.com",
@ -450,10 +443,8 @@
"huanqiu.com",
"huawei.com",
"hubspot.com",
"huffingtonpost.com",
"huffpost.com",
"hulu.com",
"humblebundle.com",
"humparsi.com",
"hupu.com",
"hurriyet.com.tr",
"huya.com",
@ -472,13 +463,15 @@
"impress.co.jp",
"in.gr",
"indeed.com",
"independent.co.uk",
"indiamart.com",
"indianexpress.com",
"indiatimes.com",
"indoxxi.bz",
"indoxxi.cx",
"infobae.com",
"infourok.ru",
"inquirer.net",
"instagram.com",
"instructables.com",
"instructure.com",
"intel.com",
"interia.pl",
@ -487,78 +480,84 @@
"inven.co.kr",
"investing.com",
"investopedia.com",
"iplt20.com",
"iqiyi.com",
"iqoption.com",
"irctc.co.in",
"irs.gov",
"issuu.com",
"istockphoto.com",
"ithome.com",
"itmedia.co.jp",
"ivi.ru",
"ixl.com",
"jamnews.com",
"japanpost.jp",
"jb51.net",
"jd.com",
"jf71qh5v14.com",
"jiameng.com",
"jianshu.com",
"jooble.org",
"jqw.com",
"jrj.com.cn",
"jstor.org",
"justdial.com",
"justresonter.com",
"jw.org",
"kaixin001.com",
"kakaku.com",
"kakao.com",
"kapanlagi.com",
"kaskus.co.id",
"kayak.com",
"keyrolan.com",
"kerumal.com",
"khanacademy.org",
"kickstarter.com",
"kijiji.ca",
"kinokrad.co",
"kinopoisk.ru",
"kissanime.ru",
"kizlarsoruyor.com",
"kknews.cc",
"kompas.com",
"kompasiana.com",
"kooora.com",
"kp.ru",
"kpu.go.id",
"kumparan.com",
"labanquepostale.fr",
"kuronekoyamato.co.jp",
"ladbible.com",
"leagueoflegends.com",
"leboncoin.fr",
"lefigaro.fr",
"legit.ng",
"lemonde.fr",
"lenovo.com",
"lenta.ru",
"lentainform.com",
"libero.it",
"lifewire.com",
"lifo.gr",
"line.me",
"linkedin.com",
"liputan6.com",
"list-manage.com",
"list.tmall.com",
"live.com",
"live.net",
"livedoor.com",
"livedoor.jp",
"livejasmin.com",
"livejournal.com",
"livescore.com",
"lnkfast.com",
"lofter.com",
"login.tmall.com",
"lordfilms.tv",
"lostfilm.tv",
"lowes.com",
"ltn.com.tw",
"lun.com",
"macys.com",
"mafengwo.cn",
"mail.ru",
"mailchimp.com",
"makemytrip.com",
"manoramaonline.com",
"marca.com",
"marial.pro",
"marketwatch.com",
"marriott.com",
"mathrubhumi.com",
"mathworks.com",
@ -567,17 +566,17 @@
"media.tumblr.com",
"mediafire.com",
"medium.com",
"meetup.com",
"mega.nz",
"meijutt.com",
"memurlar.net",
"mercadolibre.com.ar",
"mercadolibre.com.mx",
"mercadolibre.com.ve",
"mercadolivre.com.br",
"mercari.com",
"merdeka.com",
"merriam-webster.com",
"messenger.com",
"metacritic.com",
"metropoles.com",
"mgid.com",
"mi.com",
@ -585,26 +584,23 @@
"microsoftonline.com",
"mileroticos.com",
"milliyet.com.tr",
"minuto30.com",
"mit.edu",
"miui.com",
"mk.ru",
"mlb.com",
"mobile.de",
"mobile01.com",
"mobispirit.com",
"moe.gov.sa",
"momoshop.com.tw",
"moneycontrol.com",
"moneymake.site",
"motorsport.com",
"movie2free.com",
"moviesearchcenter.com",
"mozilla.org",
"mptentry.com",
"msn.com",
"myanimelist.net",
"myanmarload.com",
"mydiba.xyz",
"mydrivers.com",
"myfreecams.com",
"mynavi.jp",
"myornamenti.com",
"myshopify.com",
"myway.com",
"myworkday.com",
@ -623,9 +619,7 @@
"netflix.com",
"newegg.com",
"news-speaker.com",
"newstrend.news",
"nexusmods.com",
"nfkd2ug8d9.com",
"nga.cn",
"nhentai.net",
"nhk.or.jp",
@ -636,67 +630,66 @@
"nike.com",
"nikkei.com",
"ninisite.com",
"nnu.ng",
"norton.com",
"notify-service.com",
"nownews.com",
"npr.org",
"nsportal.ru",
"nur.kz",
"nutaku.net",
"nvidia.com",
"nvzhuang.tmall.com",
"nyaa.si",
"nypost.com",
"nythatspartaund.info",
"nytimes.com",
"oath.com",
"oclasrv.com",
"office.com",
"office365.com",
"ok.ru",
"okdiario.com",
"okezone.com",
"okta.com",
"oload.space",
"oload.services",
"olx.com.br",
"olx.pl",
"olx.ua",
"onclicksuper.com",
"onet.pl",
"onlinesbi.com",
"onlinevideoconverter.com",
"op.gg",
"openload.co",
"opensubtitles.org",
"opera.com",
"opossumsauce.com",
"oracle.com",
"orange.fr",
"os.tc",
"oschina.net",
"otnolabttmup.com",
"otvfoco.com.br",
"ouedkniss.com",
"ouo.io",
"outbrain.com",
"over-blog.com",
"overleaf.com",
"ozon.ru",
"pages.tmall.com",
"panda.tv",
"pandora.com",
"pantip.com",
"pastebin.com",
"patch.com",
"pathofexile.com",
"patreon.com",
"patria.org.ve",
"paypal.com",
"paytm.com",
"pcgamer.com",
"pchome.com.tw",
"pelisplus.co",
"perfecttoolmedia.com",
"pexels.com",
"pikabu.ru",
"pinimg.com",
"pinterest.com",
"pirateproxy.bet",
"pirateproxy.lat",
"pixabay.com",
"pixiv.net",
"pixnet.net",
"playground.ru",
"playstation.com",
"pngtree.com",
"popads.net",
@ -706,24 +699,24 @@
"pornhub.com",
"pornpics.com",
"pornq.com",
"pozdravok.ru",
"prezi.com",
"primevideo.com",
"prnt.sc",
"prothomalo.com",
"ptt.cc",
"pulzo.com",
"python.org",
"qihoo.com",
"qq.com",
"qualtrics.com",
"quintag.com",
"quizlet.com",
"quora.com",
"rajasthan.gov.in",
"rakuten.co.jp",
"rambler.ru",
"rapidgator.net",
"rarbg.to",
"rarbgprx.org",
"rbc.ru",
"readms.net",
"reallifecam.com",
"realtor.com",
@ -734,44 +727,39 @@
"rediff.com",
"rednet.cn",
"redtube.com",
"redwap.me",
"rensovetors.info",
"remtoaku.net",
"renren.com",
"repubblica.it",
"researchgate.net",
"reuters.com",
"reverso.net",
"ria.ru",
"right.com.cn",
"roblox.com",
"rottentomatoes.com",
"ropleftinwaref.info",
"rotumal.com",
"royalbank.com",
"rpgmasterleague.com",
"rrbonlinereg.co.in",
"rrbonlinereg.net",
"rt.com",
"ruliweb.com",
"runoob.com",
"rus.ec",
"rutor.info",
"rutracker.org",
"rutube.ru",
"sahibinden.com",
"salesforce.com",
"samsung.com",
"sarkariresult.com",
"sat.gob.mx",
"savefrom.net",
"sberbank.ru",
"schoology.com",
"sci-hub.tw",
"sciencedirect.com",
"scol.com.cn",
"scribd.com",
"sdamgia.ru",
"seasonvar.ru",
"secureserver.net",
"segmentfault.com",
"service-now.com",
"setare.com",
"setn.com",
"sex.com",
"seznam.cz",
@ -795,17 +783,18 @@
"softonic.com",
"sogou.com",
"sohu.com",
"sonyliv.com",
"soso.com",
"soundcloud.com",
"souq.com",
"sourceforge.net",
"southcn.com",
"southwest.com",
"sozcu.com.tr",
"spankbang.com",
"speakol.com",
"speedtest.net",
"spiegel.de",
"sportbible.com",
"sports.ru",
"spotify.com",
"spotscenered.info",
"springer.com",
@ -818,52 +807,56 @@
"state.gov",
"steamcommunity.com",
"steampowered.com",
"storiespace.com",
"strava.com",
"streamango.com",
"studfiles.net",
"study.com",
"suara.com",
"subhd.com",
"subito.it",
"subject.tmall.com",
"subscene.com",
"suning.com",
"superuser.com",
"surveymonkey.com",
"sxyprn.com",
"t-online.de",
"t.co",
"t.me",
"t66y.com",
"tabelog.com",
"taboola.com",
"taimienphi.vn",
"taleo.net",
"tamasha.com",
"tamilrockerrs.ch",
"tampermonkey.net",
"tamilwin.com",
"tandfonline.com",
"taobao.com",
"tarafdari.com",
"target.com",
"td.com",
"teacherspayteachers.com",
"teamviewer.com",
"techcrunch.com",
"techradar.com",
"telegram.org",
"telegraph.co.uk",
"telewebion.com",
"tempo.co",
"tencent.com",
"termometropolitico.it",
"theepochtimes.com",
"thefreedictionary.com",
"theguardian.com",
"thehill.com",
"themeforest.net",
"thepiratebay.org",
"thesaurus.com",
"thestartmagazine.com",
"theverge.com",
"thewhizmarketing.com",
"thingiverse.com",
"tianya.cn",
"ticketmaster.com",
"timeanddate.com",
"tistory.com",
"tmall.com",
"tokopedia.com",
"torrent9.uno",
"torrentwal.com",
"torrentz2.eu",
"toutiao.com",
@ -872,26 +865,34 @@
"tribunnews.com",
"tripadvisor.com",
"trustpilot.com",
"tsa-algerie.com",
"tsinghua.edu.cn",
"ttmeiju.me",
"tube8.com",
"tudou.com",
"tumblr.com",
"turbobit.net",
"turnitin.com",
"tutorialspoint.com",
"tweakboxapp.com",
"twimg.com",
"twitch.tv",
"twitter.com",
"txxx.com",
"uclaut.net",
"ubi.com",
"ubisoft.com",
"udemy.com",
"udn.com",
"uidai.gov.in",
"ukr.net",
"ultimate-guitar.com",
"umblr.com",
"unblocked.win",
"unblocktheship.org",
"uniqlo.com",
"uniqlo.tmall.com",
"unsplash.com",
"uod2quk646.com",
"uol.com.br",
"upgers-armine.com",
"uploaded.net",
"upornia.com",
"ups.com",
@ -902,13 +903,11 @@
"urdupoint.com",
"usatoday.com",
"userapi.com",
"usnews.com",
"usps.com",
"utorrent.com",
"uzone.id",
"v2ex.com",
"varzesh3.com",
"vcommission.com",
"verizonwireless.com",
"vesti.ru",
"vice.com",
@ -918,22 +917,22 @@
"viva.co.id",
"vjav.com",
"vk.com",
"vlive.tv",
"vnexpress.net",
"vox.com",
"vseigru.net",
"w3school.com.cn",
"w3schools.com",
"walmart.com",
"wargaming.net",
"washingtonpost.com",
"wattpad.com",
"wease.im",
"weather.com",
"web.de",
"webex.com",
"weblio.jp",
"webmd.com",
"webofknowledge.com",
"weebly.com",
"weibo.cn",
"weibo.com",
"wellsfargo.com",
"westernjournal.com",
@ -953,21 +952,21 @@
"wordpress.com",
"wordpress.org",
"wordreference.com",
"worldoftanks.ru",
"wowhead.com",
"wp.pl",
"wsj.com",
"wunderground.com",
"www.gov.uk",
"xda-developers.com",
"xe.com",
"xfinity.com",
"xhamster.com",
"xhamsterlive.com",
"xiaomi.com",
"xiami.com",
"xilbalar.com",
"xinhuanet.com",
"xnxx.com",
"xsgcobwd.com",
"xvideos.com",
"y2mate.com",
"yadi.sk",
"yahoo.co.jp",
"yahoo.com",
@ -978,36 +977,36 @@
"yandex.ru",
"yao.tmall.com",
"yaplakal.com",
"ycwb.com",
"yelp.com",
"yenisafak.com",
"yespornplease.com",
"yjc.ir",
"youdao.com",
"youjizz.com",
"youku.com",
"youm7.com",
"youporn.com",
"yourporn.sexy",
"youth.cn",
"youtube.com",
"ytimg.com",
"yts.am",
"yy.com",
"zaful.com",
"zaycev.net",
"zendesk.com",
"zhanqi.tv",
"zhaopin.com",
"zhibo8.cc",
"zhihu.com",
"zillow.com",
"zing.vn",
"zippyshare.com",
"zmz2019.com",
"znanija.com",
"zoho.com",
"zol.com.cn",
"zoom.us",
"zougla.gr"
],
"version": 20190309,
"type": "hostname",
"name": "Top 1000 website from Alexa"
"matching_attributes": [
"hostname",
"domain"
]
}

View File

@ -33,7 +33,7 @@ alexa_warninglist['list'] = []
alexa_warninglist['matching_attributes'] = ['hostname', 'domain']
for site in top1000:
v = str(site).split(',')[1]
v = site.decode('UTF-8').split(',')[1]
alexa_warninglist['list'].append(v.rstrip())
alexa_warninglist['list'] = sorted(set(alexa_warninglist['list']))
print(json.dumps(alexa_warninglist))