Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

add domain parsing with custom psl list and removing false positives #84452

Merged
merged 14 commits into from
Sep 26, 2024
Merged
Show file tree
Hide file tree
Changes from 10 commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion package.json
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,8 @@
},
"dependencies": {
"@metamask/phishing-controller": "^12.0.2",
"fastest-levenshtein": "^1.0.16"
"fastest-levenshtein": "^1.0.16",
"tldts": "^6.1.43"
},
"devDependencies": {
"@types/punycode": "^2.1.4",
Expand Down
16 changes: 0 additions & 16 deletions src/config.json
Original file line number Diff line number Diff line change
Expand Up @@ -11941,7 +11941,6 @@
"web-zksync.network",
"airdroper.app",
"airdrop.fueleproject.network",
"auroria.explorer-api.zksync.stratisplatform.com",
"zksync.guru",
"metamask.zenliner.com",
"metamaskint.com",
Expand Down Expand Up @@ -12386,7 +12385,6 @@
"metsesklogin.gitbook.io",
"support--metamaklogin.gitbook.io",
"wallaet-metammaskorg.gitbook.io",
"auroria.explorer.zksync.stratisplatform.com",
"tensorbuiltmaxifi.pages.dev",
"xn--zrcuit-3va.com",
"lineasurge.com",
Expand Down Expand Up @@ -18191,7 +18189,6 @@
"dh-uniswap-fork.web.app",
"pudgymetaverse.com",
"coinbase-rejectlogin.com",
"uniswap.tokenpocket.pro",
"coin-prestbase.com",
"zeta-chain.pages.dev",
"xrpinvest.net",
Expand Down Expand Up @@ -39879,7 +39876,6 @@
"claim-earndrop.io",
"claim-nfp.com",
"claim-services.codes",
"claim.seedify.fund",
"maskofficial.link",
"claimairdrop.top",
"claiming-app.com",
Expand Down Expand Up @@ -42141,7 +42137,6 @@
"metamask.io-1s2r17.sewakamerabandung.id",
"metamask.io-defi-web3-dapps-and-nfts.sewakamerabandung.id",
"metamask.joys.digital",
"metamask.mainnet.rsk.co",
"metamask.playmonstergalaxy.com",
"metamask.setakins.ir",
"metamasklogin.pages.dev",
Expand Down Expand Up @@ -42471,7 +42466,6 @@
"lido-finance-wallet.com",
"lido-finance.exchange",
"login.trezor.com.usmaninterlining.com",
"metamask.consensys.net",
"metamask.shpdkj.com",
"pannacakev2.online",
"pepecoinstake.com",
Expand Down Expand Up @@ -44604,7 +44598,6 @@
"uniswap.credit",
"uniswap.cryptolisting.com",
"uniswap.imbc.app",
"uniswap.zeon.network",
"upgrade-ethereum.com",
"zethereum.com",
"dev-webconnect.pantheonsite.io",
Expand Down Expand Up @@ -57523,7 +57516,6 @@
"launchpaad.xyz",
"joingrapes.world",
"blast.bar",
"news-canary.ops.bitcoin.com",
"0x88329958832775392885353.com",
"pyth-community.com",
"debank.42web.io",
Expand Down Expand Up @@ -59130,7 +59122,6 @@
"lamatex.wtf",
"pork-colns.com",
"lamatex.biz",
"e.expressoil.com",
"celsius-claimassets.com",
"klepdao.xyz",
"logchainserver-claim.pages.dev",
Expand Down Expand Up @@ -59513,7 +59504,6 @@
"illuvium-claim.io",
"impotsgouv-crypto.com",
"join-metis.org",
"locker.bella.fi",
"newcontractbridge.io",
"open-listing.io",
"portal.dymension.ink",
Expand Down Expand Up @@ -80523,7 +80513,6 @@
"mysterymint-s7.vercel.app",
"changelly.tech",
"mysteryclaimh4.vercel.app",
"pepepresale.z13.web.core.windows.net",
"lauxxx.top",
"nodes-ai.web.app",
"analosmeme.netlify.app",
Expand Down Expand Up @@ -99886,7 +99875,6 @@
"net-157-254-169.net",
"lyanan-bntuan-cs-ovo.id-officiall.com",
"gas-fee.cc",
"arf.berkeley.edu",
"mocaverses.org",
"pakmooon.net",
"reward-wtoken.com",
Expand Down Expand Up @@ -126290,7 +126278,6 @@
"tokens-roost.wtf",
"marketplace-renzo.io",
"join-everyworld.com",
"blockpg-aloe.safezone.mcafee.com",
"metisl2voin.info",
"app-airdrop.net",
"runepunksnft.xyz",
Expand Down Expand Up @@ -196284,7 +196271,6 @@
"fourmeme.info",
"app-matrixport.com",
"claim-unitokens.nis.edu.au",
"arbitrum-0.meowrpc.com",
"horld.world",
"web-compound-finance.org",
"swap.cowdao.pro",
Expand Down Expand Up @@ -196797,7 +196783,6 @@
"metamask.io.desktop.nestbtq.com",
"metaismasxkxlogiin.gitbook.io",
"v1-matrixport.com",
"nor01.safelinks.protection.outlook.com",
"mentimasklogion.gitbook.io",
"meitexmeskc-ibb.gitbook.io",
"meta-mask-wallit.gitbook.io",
Expand Down Expand Up @@ -204632,7 +204617,6 @@
"park-lineabuild.pages.dev",
"zksync.cat",
"zksync.bonus-services-web3.network",
"arbitrum.nodes.guru",
"arbitrum-foundation.rd1.xyz",
"arbitrum-one.node.opsvc.io",
"starknelt.pro",
Expand Down
236 changes: 236 additions & 0 deletions test/custom-tlds.ts
Original file line number Diff line number Diff line change
@@ -0,0 +1,236 @@
/*
Extend public suffix list by adding to this list.
This can include any website that allows user-generated content such as medium.com, wordpress.com, gitbook.io, etc.
Do not add real businesses that are using subdomains that are created by the company itself. You will enable false positives.
If you see a website that is not a hosting provider on this list, please remove it.
If too many obscure hosting providers become a problem, we should reduce the tranco threshold from 200,000 to help filter these out.
*/
export const customTlds = [
"gitbook.io",
"mypinata.cloud",
"fleek.co",
"mystrikingly.com",
"weebly.com",
"wordpress.com",
"surge.sh",
"us.to",
"typeform.com",
"mooo.com",
"netlify.com",
"zendesk.com",
"godaddysites.com",
"line.pm",
"000webhostapp.com",
"work.gd",
"finance.blog",
"wuaze.com",
"eth.limo",
"myddns.me",
"on-fleek.app",
"42web.io",
"tistory.com",
"bravesites.com",
"webcindario.com",
"x10.mx",
"ukit.me",
"mypixieset.com",
"w3spaces.com",
"teachable.com",
"mobirisesite.com",
"gitpod.io",
"onepage.website",
"creatorlink.net",
"flazio.com",
"educatorpages.com",
"dynamic-dns.net",
"webhostbox.net",
"xf.cz",
"website3.me",
"page.link",
"hpage.com",
"livejournal.com",
"square.site",
"uk.to",
"run.place",
"tiiny.site",
"jimdosite.com",
"cloudwaysapps.com",
"my03.com",
"stackstaging.com",
"1gb.ru",
"publicvm.com",
"home.blog",
"webz.cz",
"rf.gd",
"over-blog.com",
"tilda.ws",
"odoo.com",
"company.site",
"ic0.app",
"x24hr.com",
"mybluehost.me",
"zyns.com",
"zzux.com",
"gr8.com",
"icp0.io",
"unaux.com",
"medium.com",
"tumblr.com",
"gopeerclick.com",
"preview-domain.com",
"strangled.net",
"wikidot.com",
"nicepage.io",
"edublogs.org",
"ydns.eu",
"kiln.fi",
"great-site.net",
"site123.me",
"drv.tw",
"imweb.me",
"qhigh.com",
"clickfunnels.com",
"tiny.us",
"mefound.com",
"code.blog",
"orderonline.id",
"fartit.com",
"easterndns.com",
"ns01.us",
"neocities.org",
"wz.cz",
"euweb.cz",
"nichost.ru",
"heliohost.org",
"zzz.com.ua",
"hstgr.cloud",
"nxcli.io",
"b-cdn.net",
"codeanyapp.com",
"tw1.ru",
"fanlink.to",
"alt.technology",
"p2pify.com",
"zebra.com",
"railway.app",
"unicornplatform.page",
"arbitrum-internal.io",
"4everproxy.com",
"formstack.com",
"xyro.io",
"ulb.be",
"onerpc.com",
"newzenler.com",
"rssing.com",
"kr.com",
"ghost.io",
"voog.com",
"beehiiv.com",
"b4a.app",
"rpcpool.com",
"improd.pro",
"dubya.net",
"viewdns.net",
"selcdn.ru",
"cleansite.us",
"longmusic.com",
"jkub.com",
"swanndvr.net",
"dsmtp.com",
"exponea.com",
"ck.page",
"1688.com",
"authorizeddns.us",
"multiscreensite.com",
"iaasdns.com",
"myftp.info",
"onelink.me",
"xxuz.com",
"temporary.link",
"yikj.work",
"rsk.co",
"consensys.net",
"talentlms.com",
"techcombank.com.vn",
"weeblysite.com",
"ignorelist.com",
"dns04.com",
"sci-hub.st",
"awstrack.me",
"faviconkit.com",
"codefi.network",
"serveusers.com",
"crabdance.com",
"dns05.com",
"myddns.com",
"fromsmash.com",
"do.am",
"slack.com",
"swtest.ru",
"joomla.com",
"music.blog",
"96.lt",
"hol.es",
"16mb.com",
"com.com",
"coolpage.biz",
"at.ua",
"ucoz.org",
"unas.cz",
"ezyro.com",
"tekcities.com",
"regruhosting.ru",
"h1n.ru",
"patientpop.com",
"sendgrid.net",
"bio.link",
"hostingersite.com",
"squarespace.com",
"hostpapavps.net",
"w3s.link",
"substack.com",
"filesusr.com",
"googleusercontent.com",
"contaboserver.net",
"sendibt3.com",
"systeme.io",
"cdn36.com",
"klclick3.com",
"mrbonus.com",
"gettrials.com",
"conohawing.com",
"ua.pt",
"infinitypowersvip.com",
"hosted-by-vdsina.ru",
"sg-host.com",
"lflink.com",
"ezua.com",
"timeweb.ru",
"site.com",
"myclickfunnels.com",
"urlgeni.us",
"bigmoney.biz",
"ddnss.eu",
"jigsy.com",
"duda.co",
"infura-ipfs.io",
"shivtr.com",
"creator-spring.com",
"app.com",
"splashthat.com",
"000.pe",
"free.nf",
"elementfx.com",
"had.su",
"dorik.io",
"linkpool.io",
"univer.se",
"codeanywhere.com",
"4everland.io",
"serveo.net",
"site44.com",
"cloudclusters.net",
"fleek.cool",
"serv00.net",
"keenetic.pro",
];
Loading