解析域——一个非常可靠的轻量级库

NPM安装解析域

const { fromUrl, parseDomain } = require("parse-domain");

示例1

parseDomain(fromUrl("http://www.example.com/12xy45"))

{ type: 'LISTED',
  hostname: 'www.example.com',
  labels: [ 'www', 'example', 'com' ],
  icann:
   { subDomains: [ 'www' ],
     domain: 'example',
     topLevelDomains: [ 'com' ] },
  subDomains: [ 'www' ],
  domain: 'example',
  topLevelDomains: [ 'com' ] }

示例2

parseDomain(fromUrl("http://subsub.sub.test.ExAmPlE.coM/12xy45"))

{ type: 'LISTED',
  hostname: 'subsub.sub.test.example.com',
  labels: [ 'subsub', 'sub', 'test', 'example', 'com' ],
  icann:
   { subDomains: [ 'subsub', 'sub', 'test' ],
     domain: 'example',
     topLevelDomains: [ 'com' ] },
  subDomains: [ 'subsub', 'sub', 'test' ],
  domain: 'example',
  topLevelDomains: [ 'com' ] }

Why?

Depending on the use case and volume I strongly recommend against solving this problem yourself using regex or other string manipulation means. The core of this problem is that you need to know all the gtld and cctld suffixes to properly parse url strings into domain and subdomains, these suffixes are regularly updated. This is a solved problem and not one you want to solve yourself (unless you are google or something). Unless you need the hostname or domain name in a pinch don't try and parse your way out of this one.

function hostname(url) {
    var match = url.match(/:\/\/(www[0-9]?\.)?(.[^/:]+)/i);
    if ( match != null && match.length > 2 && typeof match[2] === 'string' && match[2].length > 0 ) return match[2];
}

上面的代码将成功解析以下示例url的主机名: http://WWW.first.com/folder/page.html first.com http://mail.google.com/folder/page.html mail.google.com https://mail.google.com/folder/page.html mail.google.com http://www2.somewhere.com/folder/page.html?q=1 somewhere.com https://www.another.eu/folder/page.html?q=1 another.eu

原文出处:http://www.primaryobjects.com/CMS/Article145

我尝试使用给定的解决方案，选择的解决方案对我的目的来说是多余的，而“创建一个元素”对我来说是一团糟。

它还没有准备好在URL的端口。我希望有人觉得它有用

function parseURL(url){
    parsed_url = {}

    if ( url == null || url.length == 0 )
        return parsed_url;

    protocol_i = url.indexOf('://');
    parsed_url.protocol = url.substr(0,protocol_i);

    remaining_url = url.substr(protocol_i + 3, url.length);
    domain_i = remaining_url.indexOf('/');
    domain_i = domain_i == -1 ? remaining_url.length - 1 : domain_i;
    parsed_url.domain = remaining_url.substr(0, domain_i);
    parsed_url.path = domain_i == -1 || domain_i + 1 == remaining_url.length ? null : remaining_url.substr(domain_i + 1, remaining_url.length);

    domain_parts = parsed_url.domain.split('.');
    switch ( domain_parts.length ){
        case 2:
          parsed_url.subdomain = null;
          parsed_url.host = domain_parts[0];
          parsed_url.tld = domain_parts[1];
          break;
        case 3:
          parsed_url.subdomain = domain_parts[0];
          parsed_url.host = domain_parts[1];
          parsed_url.tld = domain_parts[2];
          break;
        case 4:
          parsed_url.subdomain = domain_parts[0];
          parsed_url.host = domain_parts[1];
          parsed_url.tld = domain_parts[2] + '.' + domain_parts[3];
          break;
    }

    parsed_url.parent_domain = parsed_url.host + '.' + parsed_url.tld;

    return parsed_url;
}

运行:

parseURL('https://www.facebook.com/100003379429021_356001651189146');

结果:

Object {
    domain : "www.facebook.com",
    host : "facebook",
    path : "100003379429021_356001651189146",
    protocol : "https",
    subdomain : "www",
    tld : "com"
}

我个人对这个解决方案做了很多研究，我能找到的最好的解决方案实际上来自CloudFlare的“浏览器检查”:

function getHostname(){  
            secretDiv = document.createElement('div');
            secretDiv.innerHTML = "<a href='/'>x</a>";
            secretDiv = secretDiv.firstChild.href;
            var HasHTTPS = secretDiv.match(/https?:\/\//)[0];
            secretDiv = secretDiv.substr(HasHTTPS.length);
            secretDiv = secretDiv.substr(0, secretDiv.length - 1);
            return(secretDiv);  
}  

getHostname();

我重写了变量，使它更“人类”可读，但它比预期的工作做得更好。

只需使用URL()构造函数:

new URL(url).host

好吧，使用正则表达式会容易得多:

    mainUrl = "http://www.mywebsite.com/mypath/to/folder";
    urlParts = /^(?:\w+\:\/\/)?([^\/]+)(.*)$/.exec(mainUrl);
    host = Fragment[1]; // www.mywebsite.com