Javascript 如何仅使用javascript获取域名?

声明:本页面是StackOverFlow热门问题的中英对照翻译,遵循CC BY-SA 4.0协议,如果您需要使用它,必须同样遵循CC BY-SA许可,注明原文地址和作者信息,同时你必须将它归于原作者(不是我):StackOverFlow 原文地址: http://stackoverflow.com/questions/8253136/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me): StackOverFlow

提示:将鼠标放在中文语句上可以显示对应的英文。显示中英文
时间:2020-08-24 05:20:16  来源:igfitidea点击:

How to get domain name only using javascript?

javascriptdns

提问by vNext

I want to get domain name only using javascript. Ex

我想只使用 javascript 获取域名。前任

vn.search.yahoo.com -> yahoo
vn.search.yahoo.com.vn -> yahoo
sub1.sub2.sub3.abcdef.co.uk -> abcdef

Thank you!

谢谢!

Edit: "domain" = domain without extension (ex: .com, .net, .co.uk...) and without sub domain (ex: www, email, cdn, support...)

编辑:“域”= 没有扩展名的域(例如:.com、.net、.co.uk...)并且没有子域(例如:www、电子邮件、cdn、支持...)

回答by Ricardo Tomasi

Use location.hostand cut off subdomains and the TLD:

使用location.host和切断子域和 TLD:

 var domain = (location.host.match(/([^.]+)\.\w{2,3}(?:\.\w{2})?$/) || [])[1]

update: as @demix pointed out, this fails for 2 and 3-letter domains. It also won't work for domains like aero, jobsand dozens others.

更新:正如@demix 指出的,这对于 2 个和 3 个字母的域失败了。它也不会像领域的工作aerojobs和几十人。

The only way around is to know valid TLDs in advance, so here is a more appropriate function:

唯一的方法是提前知道有效的 TLD,所以这里有一个更合适的函数:

// http://data.iana.org/TLD/tlds-alpha-by-domain.txt
var TLDs = ["ac", "ad", "ae", "aero", "af", "ag", "ai", "al", "am", "an", "ao", "aq", "ar", "arpa", "as", "asia", "at", "au", "aw", "ax", "az", "ba", "bb", "bd", "be", "bf", "bg", "bh", "bi", "biz", "bj", "bm", "bn", "bo", "br", "bs", "bt", "bv", "bw", "by", "bz", "ca", "cat", "cc", "cd", "cf", "cg", "ch", "ci", "ck", "cl", "cm", "cn", "co", "com", "coop", "cr", "cu", "cv", "cx", "cy", "cz", "de", "dj", "dk", "dm", "do", "dz", "ec", "edu", "ee", "eg", "er", "es", "et", "eu", "fi", "fj", "fk", "fm", "fo", "fr", "ga", "gb", "gd", "ge", "gf", "gg", "gh", "gi", "gl", "gm", "gn", "gov", "gp", "gq", "gr", "gs", "gt", "gu", "gw", "gy", "hk", "hm", "hn", "hr", "ht", "hu", "id", "ie", "il", "im", "in", "info", "int", "io", "iq", "ir", "is", "it", "je", "jm", "jo", "jobs", "jp", "ke", "kg", "kh", "ki", "km", "kn", "kp", "kr", "kw", "ky", "kz", "la", "lb", "lc", "li", "lk", "lr", "ls", "lt", "lu", "lv", "ly", "ma", "mc", "md", "me", "mg", "mh", "mil", "mk", "ml", "mm", "mn", "mo", "mobi", "mp", "mq", "mr", "ms", "mt", "mu", "museum", "mv", "mw", "mx", "my", "mz", "na", "name", "nc", "ne", "net", "nf", "ng", "ni", "nl", "no", "np", "nr", "nu", "nz", "om", "org", "pa", "pe", "pf", "pg", "ph", "pk", "pl", "pm", "pn", "pr", "pro", "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", "sy", "sz", "tc", "td", "tel", "tf", "tg", "th", "tj", "tk", "tl", "tm", "tn", "to", "tp", "tr", "travel", "tt", "tv", "tw", "tz", "ua", "ug", "uk", "us", "uy", "uz", "va", "vc", "ve", "vg", "vi", "vn", "vu", "wf", "ws", "xn--0zwm56d", "xn--11b5bs3a9aj6g", "xn--3e0b707e", "xn--45brj9c", "xn--80akhbyknj4f", "xn--90a3ac", "xn--9t4b11yi5a", "xn--clchc0ea0b2g2a9gcd", "xn--deba0ad", "xn--fiqs8s", "xn--fiqz9s", "xn--fpcrj9c3d", "xn--fzc2c9e2c", "xn--g6w251d", "xn--gecrj9c", "xn--h2brj9c", "xn--hgbk6aj7f53bba", "xn--hlcj6aya9esc7a", "xn--j6w193g", "xn--jxalpdlp", "xn--kgbechtv", "xn--kprw13d", "xn--kpry57d", "xn--lgbbat1ad8j", "xn--mgbaam7a8h", "xn--mgbayh7gpa", "xn--mgbbh1a71e", "xn--mgbc0a9azcg", "xn--mgberp4a5d4ar", "xn--o3cw4h", "xn--ogbpf8fl", "xn--p1ai", "xn--pgbs0dh", "xn--s9brj9c", "xn--wgbh1c", "xn--wgbl6a", "xn--xkc2al3hye2a", "xn--xkc2dl3a5ee0h", "xn--yfro4i67o", "xn--ygbi2ammx", "xn--zckzah", "xxx", "ye", "yt", "za", "zm", "zw"].join()

function getDomain(url){

    var parts = url.split('.');
    if (parts[0] === 'www' && parts[1] !== 'com'){
        parts.shift()
    }
    var ln = parts.length
      , i = ln
      , minLength = parts[parts.length-1].length
      , part

    // iterate backwards
    while(part = parts[--i]){
        // stop when we find a non-TLD part
        if (i === 0                    // 'asia.com' (last remaining must be the SLD)
            || i < ln-2                // TLDs only span 2 levels
            || part.length < minLength // 'www.cn.com' (valid TLD as second-level domain)
            || TLDs.indexOf(part) < 0  // officialy not a TLD
        ){
            return part
        }
    }
}

getDomain(location.host)

I hope I didn't miss too manycorner cases. This should be available in the locationobject :(

我希望我没有错过太多角落案例。这应该在location对象中可用:(

Test cases: http://jsfiddle.net/hqBKd/4/

测试用例:http: //jsfiddle.net/hqBKd/4/

A list of TLDs can be found here: http://mxr.mozilla.org/mozilla-central/source/netwerk/dns/effective_tld_names.dat?raw=1

可以在此处找到 TLD 列表:http: //mxr.mozilla.org/mozilla-central/source/netwerk/dns/effective_tld_names.dat?raw=1

回答by AcidPAT

I was looking for something that would work for the majority of cases, without having to maintain the TLD list (and skip it's size!). It seems to me that you can do this pretty accurately by looking instead at the Second-Level Domain for common ones:

我正在寻找适用于大多数情况的东西,而不必维护 TLD 列表(并跳过它的大小!)。在我看来,您可以通过查看常见的二级域来非常准确地做到这一点:

function getDomainName(domain) {
    var parts = domain.split('.').reverse();
    var cnt = parts.length;
    if (cnt >= 3) {
        // see if the second level domain is a common SLD.
        if (parts[1].match(/^(com|edu|gov|net|mil|org|nom|co|name|info|biz)$/i)) {
            return parts[2] + '.' + parts[1] + '.' + parts[0];
        }
    }
    return parts[1]+'.'+parts[0];
}

Fiddle & Tests @ http://jsfiddle.net/mZPaf/2/

小提琴和测试@ http://jsfiddle.net/mZPaf/2/

Critiques/thoughts welcome.

欢迎批评/想法。

回答by icke

var docdomain = document.domain.split('.');
var dom1 = "";
if (typeof (docdomain[docdomain.length - 2]) != 'undefined') dom1 = docdomain[docdomain.length - 2] + '.';
var domain = dom1 + docdomain[docdomain.length - 1];
console.log(domain);

//without subdomains

回答by Ross

Without having a complete list of TLD's (which would get very long). If you just need the domain name from the current page you can use my technique (using cookies to find the root domain)

没有完整的 TLD 列表(这会变得很长)。如果您只需要当前页面的域名,您可以使用我的技术(使用 cookie 查找根域)

Javascript - Get Domain Name Excluding Subdomain

Javascript - 获取不包括子域的域名

To remove the extension you can then use the first element from a str.split('.')[0]

要删除扩展名,您可以使用第一个元素 str.split('.')[0]

回答by demix

The only way I can imagine is list all the TLD. Sample code like below.

我能想象的唯一方法是列出所有 TLD。示例代码如下。

function getDomainName(){
    var domainList = ['com','org','net',...];//all  TLD
    var tokens = document.domain.split('.');
    while(tokens.length){
        var token = tokens.pop();
        if( domainList.indexOf(token) == -1 ){
            return token;
        }
    }
    return null;
}

Array.prototype.indexOf should do some fix in IE.

Array.prototype.indexOf 应该在 IE 中做一些修复。

回答by Chad Scira

i needed to do this and whipped up something simple that accounted for my use case

我需要这样做并提出一些简单的东西来解释我的用例

function stripSubDomainAndTLD (domain) {
    return domain.replace(/^(?:[a-z0-9\-\.]+\.)??([a-z0-9\-]+)(?:\.com|\.net|\.org|\.biz|\.ws|\.in|\.me|\.co\.uk|\.co|\.org\.uk|\.ltd\.uk|\.plc\.uk|\.me\.uk|\.edu|\.mil|\.br\.com|\.cn\.com|\.eu\.com|\.hu\.com|\.no\.com|\.qc\.com|\.sa\.com|\.se\.com|\.se\.net|\.us\.com|\.uy\.com|\.ac|\.co\.ac|\.gv\.ac|\.or\.ac|\.ac\.ac|\.af|\.am|\.as|\.at|\.ac\.at|\.co\.at|\.gv\.at|\.or\.at|\.asn\.au|\.com\.au|\.edu\.au|\.org\.au|\.net\.au|\.id\.au|\.be|\.ac\.be|\.adm\.br|\.adv\.br|\.am\.br|\.arq\.br|\.art\.br|\.bio\.br|\.cng\.br|\.cnt\.br|\.com\.br|\.ecn\.br|\.eng\.br|\.esp\.br|\.etc\.br|\.eti\.br|\.fm\.br|\.fot\.br|\.fst\.br|\.g12\.br|\.gov\.br|\.ind\.br|\.inf\.br|\.jor\.br|\.lel\.br|\.med\.br|\.mil\.br|\.net\.br|\.nom\.br|\.ntr\.br|\.odo\.br|\.org\.br|\.ppg\.br|\.pro\.br|\.psc\.br|\.psi\.br|\.rec\.br|\.slg\.br|\.tmp\.br|\.tur\.br|\.tv\.br|\.vet\.br|\.zlg\.br|\.br|\.ab\.ca|\.bc\.ca|\.mb\.ca|\.nb\.ca|\.nf\.ca|\.ns\.ca|\.nt\.ca|\.on\.ca|\.pe\.ca|\.qc\.ca|\.sk\.ca|\.yk\.ca|\.ca|\.cc|\.ac\.cn|\.com\.cn|\.edu\.cn|\.gov\.cn|\.org\.cn|\.bj\.cn|\.sh\.cn|\.tj\.cn|\.cq\.cn|\.he\.cn|\.nm\.cn|\.ln\.cn|\.jl\.cn|\.hl\.cn|\.js\.cn|\.zj\.cn|\.ah\.cn|\.gd\.cn|\.gx\.cn|\.hi\.cn|\.sc\.cn|\.gz\.cn|\.yn\.cn|\.xz\.cn|\.sn\.cn|\.gs\.cn|\.qh\.cn|\.nx\.cn|\.xj\.cn|\.tw\.cn|\.hk\.cn|\.mo\.cn|\.cn|\.cx|\.cz|\.de|\.dk|\.fo|\.com\.ec|\.tm\.fr|\.com\.fr|\.asso\.fr|\.presse\.fr|\.fr|\.gf|\.gs|\.co\.il|\.net\.il|\.ac\.il|\.k12\.il|\.gov\.il|\.muni\.il|\.ac\.in|\.co\.in|\.org\.in|\.ernet\.in|\.gov\.in|\.net\.in|\.res\.in|\.is|\.it|\.ac\.jp|\.co\.jp|\.go\.jp|\.or\.jp|\.ne\.jp|\.ac\.kr|\.co\.kr|\.go\.kr|\.ne\.kr|\.nm\.kr|\.or\.kr|\.li|\.lt|\.lu|\.asso\.mc|\.tm\.mc|\.com\.mm|\.org\.mm|\.net\.mm|\.edu\.mm|\.gov\.mm|\.ms|\.nl|\.no|\.nu|\.pl|\.ro|\.org\.ro|\.store\.ro|\.tm\.ro|\.firm\.ro|\.www\.ro|\.arts\.ro|\.rec\.ro|\.info\.ro|\.nom\.ro|\.nt\.ro|\.se|\.si|\.com\.sg|\.org\.sg|\.net\.sg|\.gov\.sg|\.sk|\.st|\.tf|\.ac\.th|\.co\.th|\.go\.th|\.mi\.th|\.net\.th|\.or\.th|\.tm|\.to|\.com\.tr|\.edu\.tr|\.gov\.tr|\.k12\.tr|\.net\.tr|\.org\.tr|\.com\.tw|\.org\.tw|\.net\.tw|\.ac\.uk|\.uk\.com|\.uk\.net|\.gb\.com|\.gb\.net|\.vg|\.sh|\.kz|\.ch|\.info|\.ua|\.gov|\.name|\.pro|\.ie|\.hk|\.com\.hk|\.org\.hk|\.net\.hk|\.edu\.hk|\.us|\.tk|\.cd|\.by|\.ad|\.lv|\.eu\.lv|\.bz|\.es|\.jp|\.cl|\.ag|\.mobi|\.eu|\.co\.nz|\.org\.nz|\.net\.nz|\.maori\.nz|\.iwi\.nz|\.io|\.la|\.md|\.sc|\.sg|\.vc|\.tw|\.travel|\.my|\.se|\.tv|\.pt|\.com\.pt|\.edu\.pt|\.asia|\.fi|\.com\.ve|\.net\.ve|\.fi|\.org\.ve|\.web\.ve|\.info\.ve|\.co\.ve|\.tel|\.im|\.gr|\.ru|\.net\.ru|\.org\.ru|\.hr|\.com\.hr)$/, '');
}

mainly i just wanted to remove all subdomains, unfortunately this isn't 100% for some of the new TLD's but it works pretty well, and you can always add to the regex.

主要是我只想删除所有子域,不幸的是,对于某些新 TLD 来说,这不是 100%,但它运行良好,您可以随时添加到正则表达式。

http://jsfiddle.net/icodeforlove/TzjJE/2/

http://jsfiddle.net/icodeforlove/TzjJE/2/

回答by Muhammad Khalid

With the help of other friend's code examples given above I created a function which will return only domain name and if it is not valid domain for example TLD is missing then it will attach ".com" as per my requirement.

在上面给出的其他朋友的代码示例的帮助下,我创建了一个仅返回域名的函数,如果它不是有效的域,例如缺少 TLD,那么它将根据我的要求附加“.com”。

function getDomain(url){

var TLDs = ["ac", "ad", "ae", "aero", "af", "ag", "ai", "al", "am", "an", "ao", "aq", "ar", "arpa", "as", "asia", "at", "au", "aw", "ax", "az", "ba", "bb", "bd", "be", "bf", "bg", "bh", "bi", "biz", "bj", "bm", "bn", "bo", "br", "bs", "bt", "bv", "bw", "by", "bz", "ca", "cat", "cc", "cd", "cf", "cg", "ch", "ci", "ck", "cl", "cm", "cn", "co", "com", "coop", "cr", "cu", "cv", "cx", "cy", "cz", "de", "dj", "dk", "dm", "do", "dz", "ec", "edu", "ee", "eg", "er", "es", "et", "eu", "fi", "fj", "fk", "fm", "fo", "fr", "ga", "gb", "gd", "ge", "gf", "gg", "gh", "gi", "gl", "gm", "gn", "gov", "gp", "gq", "gr", "gs", "gt", "gu", "gw", "gy", "hk", "hm", "hn", "hr", "ht", "hu", "id", "ie", "il", "im", "in", "info", "int", "io", "iq", "ir", "is", "it", "je", "jm", "jo", "jobs", "jp", "ke", "kg", "kh", "ki", "km", "kn", "kp", "kr", "kw", "ky", "kz", "la", "lb", "lc", "li", "lk", "lr", "ls", "lt", "lu", "lv", "ly", "ma", "mc", "md", "me", "mg", "mh", "mil", "mk", "ml", "mm", "mn", "mo", "mobi", "mp", "mq", "mr", "ms", "mt", "mu", "museum", "mv", "mw", "mx", "my", "mz", "na", "name", "nc", "ne", "net", "nf", "ng", "ni", "nl", "no", "np", "nr", "nu", "nz", "om", "org", "pa", "pe", "pf", "pg", "ph", "pk", "pl", "pm", "pn", "pr", "pro", "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", "sy", "sz", "tc", "td", "tel", "tf", "tg", "th", "tj", "tk", "tl", "tm", "tn", "to", "tp", "tr", "travel", "tt", "tv", "tw", "tz", "ua", "ug", "uk", "us", "uy", "uz", "va", "vc", "ve", "vg", "vi", "vn", "vu", "wf", "ws", "xn--0zwm56d", "xn--11b5bs3a9aj6g", "xn--3e0b707e", "xn--45brj9c", "xn--80akhbyknj4f", "xn--90a3ac", "xn--9t4b11yi5a", "xn--clchc0ea0b2g2a9gcd", "xn--deba0ad", "xn--fiqs8s", "xn--fiqz9s", "xn--fpcrj9c3d", "xn--fzc2c9e2c", "xn--g6w251d", "xn--gecrj9c", "xn--h2brj9c", "xn--hgbk6aj7f53bba", "xn--hlcj6aya9esc7a", "xn--j6w193g", "xn--jxalpdlp", "xn--kgbechtv", "xn--kprw13d", "xn--kpry57d", "xn--lgbbat1ad8j", "xn--mgbaam7a8h", "xn--mgbayh7gpa", "xn--mgbbh1a71e", "xn--mgbc0a9azcg", "xn--mgberp4a5d4ar", "xn--o3cw4h", "xn--ogbpf8fl", "xn--p1ai", "xn--pgbs0dh", "xn--s9brj9c", "xn--wgbh1c", "xn--wgbl6a", "xn--xkc2al3hye2a", "xn--xkc2dl3a5ee0h", "xn--yfro4i67o", "xn--ygbi2ammx", "xn--zckzah", "xxx", "ye", "yt", "za", "zm", "zw"].join()

    url = url.replace(/.*?:\/\//g, "");
    url = url.replace(/www./g, "");
    var parts = url.split('/');
    url = parts[0];
    var parts = url.split('.');
    if (parts[0] === 'www' && parts[1] !== 'com'){
        parts.shift()
    }
    var ln = parts.length
      , i = ln
      , minLength = parts[parts.length-1].length
      , part

    // iterate backwards
    while(part = parts[--i]){
        // stop when we find a non-TLD part
        if (i === 0                    // 'asia.com' (last remaining must be the SLD)
            || i < ln-2                // TLDs only span 2 levels
            || part.length < minLength // 'www.cn.com' (valid TLD as second-level domain)
            || TLDs.indexOf(part) < 0  // officialy not a TLD
        ){
            var actual_domain = part;
            break;
            //return part
        }
    }
    //console.log(actual_domain);
    var tid ;
    if(typeof parts[ln-1] != 'undefined' && TLDs.indexOf(parts[ln-1]) >= 0)
    {
        tid = '.'+parts[ln-1];
    }
    if(typeof parts[ln-2] != 'undefined' && TLDs.indexOf(parts[ln-2]) >= 0)
    {
        tid = '.'+parts[ln-2]+tid;
    }
    if(typeof tid != 'undefined')
        actual_domain = actual_domain+tid;
    else
        actual_domain = actual_domain+'.com';


    return actual_domain;
}

回答by PHC

function getDomainName( hostname ) {
    var TLDs = new RegExp(/\.(com|net|org|biz|ltd|plc|edu|mil|asn|adm|adv|arq|art|bio|cng|cnt|ecn|eng|esp|etc|eti|fot|fst|g12|ind|inf|jor|lel|med|nom|ntr|odo|ppg|pro|psc|psi|rec|slg|tmp|tur|vet|zlg|asso|presse|k12|gov|muni|ernet|res|store|firm|arts|info|mobi|maori|iwi|travel|asia|web|tel)(\.[a-z]{2,3})?$|(\.[^\.]{2,3})(\.[^\.]{2,3})$|(\.[^\.]{2})$/);
    return hostname.replace(TLDs, '').split('.').pop();
}

/* TEST */

var domains = [
    'domain.com',
    'subdomain.domain.com',
    'www.subdomain.domain.com',
    'www.subdomain.domain.info',
    'www.subdomain.domain.info.xx',
    'mail.subdomain.domain.co.uk',
    'mail.subdomain.domain.xxx.yy',
    'mail.subdomain.domain.xx.yyy',
    'mail.subdomain.domain.xx',
    'domain.xx'
];

var result = [];
for (var i = 0; i < domains.length; i++) {
    result.push( getDomainName( domains[i] ) );
}

alert ( result.join(' | ') );
// result: domain | domain | domain | domain | domain | domain | domain | domain | domain | domain

回答by Alvaro

What about this?

那这个呢?

    function getDomain(){
        if(document.domain.length){
            var parts = document.domain.replace(/^(www\.)/,"").split('.');

            //is there a subdomain? 
            while(parts.length > 2){
                //removing it from our array 
                var subdomain = parts.shift();
            }

            //getting the remaining 2 elements
            var domain = parts.join('.');

            return domain.replace(/(^\.*)|(\.*$)/g, "");
        }
        return '';
    }

回答by RobertN

RegEx I use to get domain name only: ([^.]*[.]){0,}([^.]*)(\.[^.]*)The domain can be found in the second part.

RegEx 我只用来获取域名:([^.]*[.]){0,}([^.]*)(\.[^.]*)域名可以在第二部分找到。