如何获取没有子域名的域名?
例如,如果URL是“http://one.two.roothost.co.uk/page.html”,如何获取“roothost.co.uk”?
如何获取没有子域名的域名?
例如,如果URL是“http://one.two.roothost.co.uk/page.html”,如何获取“roothost.co.uk”?
以下是提取没有子域名的域名的解决方案。此解决方案不对URL格式做出任何假设,因此适用于任何URL。由于某些域名只有一个后缀(.com
),而有些域名有两个或更多后缀(.co.uk
),为了在所有情况下获得准确结果,我们需要使用Public Suffix List解析主机名,该列表包含所有公共域名后缀。
首先,在HTML中的
const firstTLDs = "ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|be|bf|bg|bh|bi|bj|bm|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|cl|cm|cn|co|cr|cu|cv|cw|cx|cz|de|dj|dk|dm|do|dz|ec|ee|eg|es|et|eu|fi|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jo|jp|kg|ki|km|kn|kp|kr|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|na|nc|ne|nf|ng|nl|no|nr|nu|nz|om|pa|pe|pf|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|yt".split('|');
const secondTLDs = "com|edu|gov|net|mil|org|nom|sch|caa|res|off|gob|int|tur|ip6|uri|urn|asn|act|nsw|qld|tas|vic|pro|biz|adm|adv|agr|arq|art|ato|bio|bmd|cim|cng|cnt|ecn|eco|emp|eng|esp|etc|eti|far|fnd|fot|fst|g12|ggf|imb|ind|inf|jor|jus|leg|lel|mat|med|mus|not|ntr|odo|ppg|psc|psi|qsl|rec|slg|srv|teo|tmp|trd|vet|zlg|web|ltd|sld|pol|fin|k12|lib|pri|aip|fie|eun|sci|prd|cci|pvt|mod|idv|rel|sex|gen|nic|abr|bas|cal|cam|emr|fvg|laz|lig|lom|mar|mol|pmn|pug|sar|sic|taa|tos|umb|vao|vda|ven|mie|北海道|和歌山|神奈川|鹿児島|ass|rep|tra|per|ngo|soc|grp|plc|its|air|and|bus|can|ddr|jfk|mad|nrw|nyc|ski|spy|tcm|ulm|usa|war|fhs|vgs|dep|eid|fet|fla|flå|gol|hof|hol|sel|vik|cri|iwi|ing|abo|fam|gok|gon|gop|gos|aid|atm|gsm|sos|elk|waw|est|aca|bar|cpa|jur|law|sec|plo|www|bir|cbg|jar|khv|msk|nov|nsk|ptz|rnd|spb|stv|tom|tsk|udm|vrn|cmw|kms|nkz|snz|pub|fhv|red|ens|nat|rns|rnu|bbs|tel|bel|kep|nhs|dni|fed|isa|nsn|gub|e12|tec|орг|обр|упр|alt|nis|jpn|mex|ath|iki|nid|gda|inc".split('|');
const knownSubdomains = "www|studio|mail|remote|blog|webmail|server|ns1|ns2|smtp|secure|vpn|m|shop|ftp|mail2|test|portal|ns|ww1|host|support|dev|web|bbs|ww42|squatter|mx|email|1|mail1|2|forum|owa|www2|gw|admin|store|mx1|cdn|api|exchange|app|gov|2tty|vps|govyty|hgfgdf|news|1rer|lkjkui";
function removeSubdomain(s) {
const knownSubdomainsRegExp = new RegExp(`^(${knownSubdomains})\.`, 'i');
s = s.replace(knownSubdomainsRegExp, '');
const parts = s.split('.');
while (parts.length > 3) {
parts.shift();
}
if (parts.length === 3 && ((parts[1].length > 2 && parts[2].length > 2) || (secondTLDs.indexOf(parts[1]) === -1) && firstTLDs.indexOf(parts[2]) === -1)) {
parts.shift();
}
return parts.join('.');
};
var tests = {
'www.sidanmor.com': 'sidanmor.com',
'exemple.com': 'exemple.com',
'argos.co.uk': 'argos.co.uk',
'www.civilwar.museum': 'civilwar.museum',
'www.sub.civilwar.museum': 'civilwar.museum',
'www.xxx.sub.civilwar.museum': 'civilwar.museum',
'www.exemple.com': 'exemple.com',
'main.testsite.com': 'testsite.com',
'www.ex-emple.com.ar': 'ex-emple.com.ar',
'main.test-site.co.uk': 'test-site.co.uk',
'en.tour.mysite.nl': 'tour.mysite.nl',
'www.one.lv': 'one.lv',
'www.onfdsadfsafde.lv': 'onfdsadfsafde.lv',
'aaa.onfdsadfsafde.aa': 'onfdsadfsafde.aa',
};
const firstTLDs = "ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|be|bf|bg|bh|bi|bj|bm|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|cl|cm|cn|co|cr|cu|cv|cw|cx|cz|de|dj|dk|dm|do|dz|ec|ee|eg|es|et|eu|fi|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jo|jp|kg|ki|km|kn|kp|kr|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|na|nc|ne|nf|ng|nl|no|nr|nu|nz|om|pa|pe|pf|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|yt".split('|');
const secondTLDs = "com|edu|gov|net|mil|org|nom|sch|caa|res|off|gob|int|tur|ip6|uri|urn|asn|act|nsw|qld|tas|vic|pro|biz|adm|adv|agr|arq|art|ato|bio|bmd|cim|cng|cnt|ecn|eco|emp|eng|esp|etc|eti|far|fnd|fot|fst|g12|ggf|imb|ind|inf|jor|jus|leg|lel|mat|med|mus|not|ntr|odo|ppg|psc|psi|qsl|rec|slg|srv|teo|tmp|trd|vet|zlg|web|ltd|sld|pol|fin|k12|lib|pri|aip|fie|eun|sci|prd|cci|pvt|mod|idv|rel|sex|gen|nic|abr|bas|cal|cam|emr|fvg|laz|lig|lom|mar|mol|pmn|pug|sar|sic|taa|tos|umb|vao|vda|ven|mie|北海道|和歌山|神奈川|鹿児島|ass|rep|tra|per|ngo|soc|grp|plc|its|air|and|bus|can|ddr|jfk|mad|nrw|nyc|ski|spy|tcm|ulm|usa|war|fhs|vgs|dep|eid|fet|fla|flå|gol|hof|hol|sel|vik|cri|iwi|ing|abo|fam|gok|gon|gop|gos|aid|atm|gsm|sos|elk|waw|est|aca|bar|cpa|jur|law|sec|plo|www|bir|cbg|jar|khv|msk|nov|nsk|ptz|rnd|spb|stv|tom|tsk|udm|vrn|cmw|kms|nkz|snz|pub|fhv|red|ens|nat|rns|rnu|bbs|tel|bel|kep|nhs|dni|fed|isa|nsn|gub|e12|tec|орг|обр|упр|alt|nis|jpn|mex|ath|iki|nid|gda|inc".split('|');
const knownSubdomains = "www|studio|mail|remote|blog|webmail|server|ns1|ns2|smtp|secure|vpn|m|shop|ftp|mail2|test|portal|ns|ww1|host|support|dev|web|bbs|ww42|squatter|mx|email|1|mail1|2|forum|owa|www2|gw|admin|store|mx1|cdn|api|exchange|app|gov|2tty|vps|govyty|hgfgdf|news|1rer|lkjkui";
function removeSubdomain(s) {
const knownSubdomainsRegExp = new RegExp(`^(${knownSubdomains})\.`, 'i');
s = s.replace(knownSubdomainsRegExp, '');
const parts = s.split('.');
while (parts.length > 3) {
parts.shift();
}
if (parts.length === 3 && ((parts[1].length > 2 && parts[2].length > 2) || (secondTLDs.indexOf(parts[1]) === -1) && firstTLDs.indexOf(parts[2]) === -1)) {
parts.shift();
}
return parts.join('.');
};
for (var test in tests) {
if (tests.hasOwnProperty(test)) {
var t = test;
var e = tests[test];
var r = removeSubdomain(test);
var s = e === r;
if (s) {
console.log('OK: "' + t + '" should be "' + e + '" and it is really "' + r + '"');
} else {
console.log('Fail: "' + t + '" should be "' + e + '" but it is NOT "' + r + '"');
}
}
}
参考:
www.d7143.test.me
测试中未通过。它输出的是d7143.test.me
而不是test.me
。 - John the UserremoveSubdomain("main.test-site.fr")
将返回 main.test-site.fr
。 - Eugen只需使用以下代码片段。
/(?<=\.).+/.exec(location.hostname)[0]
这个怎么样?
function getCanonicalHost(hostname) {
const MAX_TLD_LENGTH = 3;
function isNotTLD(_) { return _.length > MAX_TLD_LENGTH; };
hostname = hostname.split('.');
hostname = hostname.slice(Math.max(0, hostname.findLastIndex(isNotTLD)));
hostname = hostname.join('.');
return hostname;
}
console.log(getCanonicalHost('mail.google.com'));
console.log(getCanonicalHost('some.google.com.ar'));
console.log(getCanonicalHost('some.another.google.com.ar'));
console.log(getCanonicalHost('foo.bar.google.com'));
console.log(getCanonicalHost('foo.bar.google.com.ar'));
console.log(getCanonicalHost('bar.google.ar'));
function getCanonicalHost(hostname) {
return getCanonicalHost.tlds.then(function(tlds) {
function isNotTLD(_) { return tlds.indexOf(_) === -1; };
hostname = hostname.toLowerCase();
hostname = hostname.split('.');
hostname = hostname.slice(Math.max(0, hostname.findLastIndex(isNotTLD)));
hostname = hostname.join('.');
return hostname;
});
}
getCanonicalHost.tlds = new Promise(function(res, rej) {
const TLD_LIST_URL= 'https://data.iana.org/TLD/tlds-alpha-by-domain.txt';
const xhr = new XMLHttpRequest();
xhr.addEventListener('error', rej);
xhr.addEventListener('load', function() {
const MAX_TLD_LENGTH = 63;
var tlds = xhr.responseText.split('\n');
tlds = tlds.map(function(_) { return _.trim().toLowerCase(); });
tlds = tlds.filter(Boolean);
tlds = tlds.filter(function(_) { return _.length < MAX_TLD_LENGTH; });
res(tlds);
});
xhr.open('GET', TLD_LIST_URL);
xhr.send();
})
getCanonicalHost('mail.google.com').then(console.log);
getCanonicalHost('some.google.com.ar').then(console.log);
getCanonicalHost('some.another.google.com.ar').then(console.log);
getCanonicalHost('foo.bar.google.com').then(console.log);
getCanonicalHost('foo.bar.google.com.ar').then(console.log);
getCanonicalHost('bar.google.ar').then(console.log);
您可以使用parse-domain
来为您完成繁重的工作。该软件包考虑了公共后缀列表
,并返回一个易于处理的对象,将域名分解。
以下是他们自述文件中的示例:
npm install parse-domain
import { parseDomain, ParseResultType } from 'parse-domain';
const parseResult = parseDomain(
// should be a string with basic latin characters only. more details in the readme
'www.some.example.co.uk',
);
// check if the domain is listed in the public suffix list
if (parseResult.type === ParseResultType.Listed) {
const { subDomains, domain, topLevelDomains } = parseResult;
console.log(subDomains); // ["www", "some"]
console.log(domain); // "example"
console.log(topLevelDomains); // ["co", "uk"]
} else {
// more about other parseResult types in the readme
}
const extractDomain = (value: unknown) => {
const url = toURL(value);
if (!url) {
return null;
}
const hostnameParts = url.hostname.split('.');
// Determine typical hostnames like "domain.com" or "domain.org"
if (hostnameParts.length <= 2) {
return url.hostname;
}
// Determine two-part TLD if second last part of the hostname matches one of the prefixes
const prefixes = ['com', 'co', 'org', 'net', 'gov', 'edu'];
const potentialTwoPartTLD = `${hostnameParts[hostnameParts.length - 2]}.${hostnameParts[hostnameParts.length - 1]}`;
return prefixes.includes(hostnameParts[hostnameParts.length - 2])
? `${hostnameParts[hostnameParts.length - 3]}.${potentialTwoPartTLD}`
: hostnameParts.slice(-2).join('.'); // Fallback to last two parts of hostname
};
const toURL = (value: unknown) => {
if (value instanceof URL) {
return value;
}
if (typeof value !== 'string' || !value) {
return null;
}
try {
const url = new URL(value);
return url.hostname ? url : null;
} catch (error) {
return null;
}
};
还有测试:
describe('extractDomain', () => {
it('should handle regular domains', () => {
expect(extractDomain('https://example.com')).toBe('example.com');
});
it('should handle single subdomains', () => {
expect(extractDomain('https://sub.example.com')).toBe('example.com');
});
it('should handle multiple subdomains', () => {
expect(extractDomain('https://sub1.sub2.example.com')).toBe('example.com');
expect(extractDomain('https://deep.sub.domain.co.uk')).toBe('domain.co.uk');
expect(extractDomain('https://a.b.c.d.e.f.g.example.net')).toBe('example.net');
});
it('should handle special TLDs like co.uk', () => {
expect(extractDomain('https://domain.co.uk')).toBe('domain.co.uk');
expect(extractDomain('https://sub.domain.co.uk')).toBe('domain.co.uk');
expect(extractDomain('https://another.domain.com.au')).toBe('domain.com.au');
});
it('should handle localhost', () => {
expect(extractDomain('http://localhost:3000')).toBe('localhost');
expect(extractDomain('http://localhost')).toBe('localhost');
});
it('should handle non-HTTP/HTTPS protocols', () => {
expect(extractDomain('ftp://files.example.com')).toBe('example.com');
expect(extractDomain('ws://websocket.example.com')).toBe('example.com');
});
it('should handle non-string values', () => {
expect(extractDomain(12345)).toBeNull();
expect(extractDomain({})).toBeNull();
expect(extractDomain(['https://example.com'])).toBeNull();
expect(extractDomain(true)).toBeNull();
});
it('should handle URL instances', () => {
expect(extractDomain(new URL('https://test.example.com'))).toBe('example.com');
expect(extractDomain(new URL('https://deeply.nested.subdomain.example.org'))).toBe('example.org');
});
it('should handle invalid URLs gracefully', () => {
expect(extractDomain('not-a-url')).toBeNull();
expect(extractDomain('htt:invalid-url')).toBeNull();
expect(extractDomain('example')).toBeNull();
expect(extractDomain('http://')).toBeNull();
});
it('should handle tricky but valid URLs', () => {
expect(extractDomain('https://example.com#hash')).toBe('example.com');
expect(extractDomain('https://example.com/path')).toBe('example.com');
expect(extractDomain('https://example.com/path?query=string')).toBe('example.com');
});
});
我创建了这个函数,使用URL来解析。它作弊了,假设所有的主机名都只有4个或更少的部分。
const getDomainWithoutSubdomain = url => {
const urlParts = new URL(url).hostname.split('.')
return urlParts
.slice(0)
.slice(-(urlParts.length === 4 ? 3 : 2))
.join('.')
}
[
'https://www.google.com',
'https://www.google.co.uk',
'https://mail.google.com',
'https://www.bbc.co.uk/news',
'https://github.com',
].forEach(url => {
console.log(getDomainWithoutSubdomain(url))
})
最简单的解决方案:
var domain='https://'+window.location.hostname.split('.')[window.location.hostname.split('.').length-2]+'.'+window.location.hostname.split('.')[window.location.hostname.split('.').length-1];
alert(domain);
我使用了Ehsan Lotfinia的答案,并添加了额外的错误处理。
const hostname = location.hostname;
let domain = hostname
if (hostname.includes('.')) { # not localhost
// check if ip address
const regex = /^(?:[0-9]{1,3}\.){3}[0-9]{1,3}$/;
if (!regex.test(hostname)) {
domain = /(?<=\.).+/.exec(location.hostname)[0]
}
}
这里有一个可用的JSFiddle。
我的解决方案假设您要查找的根主机名是“abc.xyz.pp”类型的。
extractDomain()
返回带有所有子域的主机名。
getRootHostName()
通过 .
拆分主机名,然后基于上述假设,使用shift()
删除每个子域名。
最后,parts[]
中剩余的任何内容都会通过 .
连接起来形成根主机名。
Javascript
var urlInput = "http://one.two.roothost.co.uk/page.html";
function extractDomain(url) {
var domain;
//find & remove protocol (http, ftp, etc.) and get domain
if (url.indexOf("://") > -1) {
domain = url.split('/')[2];
} else {
domain = url.split('/')[0];
}
//find & remove port number
domain = domain.split(':')[0];
return domain;
}
function getRootHostName(url) {
var parts = extractDomain(url).split('.');
var partsLength = parts.length - 3;
//parts.length-3 assuming root hostname is of type abc.xyz.pp
for (i = 0; i < partsLength; i++) {
parts.shift(); //remove sub-domains one by one
}
var rootDomain = parts.join('.');
return rootDomain;
}
document.getElementById("result").innerHTML = getRootHostName(urlInput);
HTML
<div id="result"></div>
编辑 1:已更新 JSFiddle 链接。它反映了错误的代码。
http://www.google.com/
上失败了。请参见这里:http://jsfiddle.net/5sccn55k/2/。 - Maximillian Laumeister