我想匹配的只是一个URL的根,而不是一个文本字符串的整个URL。考虑到:

http://www.youtube.com/watch?v=ClkQA2Lb_iE
http://youtu.be/ClkQA2Lb_iE
http://www.example.com/12xy45
http://example.com/random

我想让最后2个实例解析到www.example.com或example.com域。

我听说正则表达式很慢,这将是我在页面上的第二个正则表达式,所以如果有办法做到没有正则表达式,请告诉我。

我正在寻找这个解决方案的JS/jQuery版本。


当前回答

// use this if you know you have a subdomain
// www.domain.com -> domain.com
function getDomain() {
  return window.location.hostname.replace(/([a-zA-Z0-9]+.)/,"");
}

其他回答

好吧,我知道这是一个老问题,但我做了一个超级高效的url解析器,所以我想我要分享它。

如你所见,这个函数的结构很奇怪,但这是为了提高效率。不使用原型函数,字符串迭代次数不超过一次,处理字符的次数也不超过必要的次数。

function getDomain(url) {
    var dom = "", v, step = 0;
    for(var i=0,l=url.length; i<l; i++) {
        v = url[i]; if(step == 0) {
            //First, skip 0 to 5 characters ending in ':' (ex: 'https://')
            if(i > 5) { i=-1; step=1; } else if(v == ':') { i+=2; step=1; }
        } else if(step == 1) {
            //Skip 0 or 4 characters 'www.'
            //(Note: Doesn't work with www.com, but that domain isn't claimed anyway.)
            if(v == 'w' && url[i+1] == 'w' && url[i+2] == 'w' && url[i+3] == '.') i+=4;
            dom+=url[i]; step=2;
        } else if(step == 2) {
            //Stop at subpages, queries, and hashes.
            if(v == '/' || v == '?' || v == '#') break; dom += v;
        }
    }
    return dom;
}

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.

尝试下面的代码为精确的域名使用正则表达式,

字符串line = "http://www.youtube.com/watch?v=ClkQA2Lb_iE";

  String pattern3="([\\w\\W]\\.)+(.*)?(\\.[\\w]+)";

  Pattern r = Pattern.compile(pattern3);


  Matcher m = r.matcher(line);
  if (m.find( )) {

    System.out.println("Found value: " + m.group(2) );
  } else {
     System.out.println("NO MATCH");
  }
String.prototype.trim = function(){return his.replace(/^\s+|\s+$/g,"");}
function getHost(url){
    if("undefined"==typeof(url)||null==url) return "";
    url = url.trim(); if(""==url) return "";
    var _host,_arr;
    if(-1<url.indexOf("://")){
        _arr = url.split('://');
        if(-1<_arr[0].indexOf("/")||-1<_arr[0].indexOf(".")||-1<_arr[0].indexOf("\?")||-1<_arr[0].indexOf("\&")){
            _arr[0] = _arr[0].trim();
            if(0==_arr[0].indexOf("//")) _host = _arr[0].split("//")[1].split("/")[0].trim().split("\?")[0].split("\&")[0];
            else return "";
        }
        else{
            _arr[1] = _arr[1].trim();
            _host = _arr[1].split("/")[0].trim().split("\?")[0].split("\&")[0];
        }
    }
    else{
        if(0==url.indexOf("//")) _host = url.split("//")[1].split("/")[0].trim().split("\?")[0].split("\&")[0];
        else return "";
    }
    return _host;
}
function getHostname(url){
    if("undefined"==typeof(url)||null==url) return "";
    url = url.trim(); if(""==url) return "";
    return getHost(url).split(':')[0];
}
function getDomain(url){
    if("undefined"==typeof(url)||null==url) return "";
    url = url.trim(); if(""==url) return "";
    return getHostname(url).replace(/([a-zA-Z0-9]+.)/,"");
}

所有url属性,没有依赖,没有JQuery,容易理解

这个解决方案给了你的答案和额外的性质。不需要JQuery或其他依赖,粘贴和走。

使用

getUrlParts("https://news.google.com/news/headlines/technology.html?ned=us&hl=en")

输出

{
  "origin": "https://news.google.com",
  "domain": "news.google.com",
  "subdomain": "news",
  "domainroot": "google.com",
  "domainpath": "news.google.com/news/headlines",
  "tld": ".com",
  "path": "news/headlines/technology.html",
  "query": "ned=us&hl=en",
  "protocol": "https",
  "port": 443,
  "parts": [
    "news",
    "google",
    "com"
  ],
  "segments": [
    "news",
    "headlines",
    "technology.html"
  ],
  "params": [
    {
      "key": "ned",
      "val": "us"
    },
    {
      "key": "hl",
      "val": "en"
    }
  ]
}

代码 代码设计得很容易理解,而不是超级快。每秒可以轻松调用100次,因此它非常适合前端或少量服务器使用,但不适用于高容量吞吐量。

function getUrlParts(fullyQualifiedUrl) {
    var url = {},
        tempProtocol
    var a = document.createElement('a')
    // if doesn't start with something like https:// it's not a url, but try to work around that
    if (fullyQualifiedUrl.indexOf('://') == -1) {
        tempProtocol = 'https://'
        a.href = tempProtocol + fullyQualifiedUrl
    } else
        a.href = fullyQualifiedUrl
    var parts = a.hostname.split('.')
    url.origin = tempProtocol ? "" : a.origin
    url.domain = a.hostname
    url.subdomain = parts[0]
    url.domainroot = ''
    url.domainpath = ''
    url.tld = '.' + parts[parts.length - 1]
    url.path = a.pathname.substring(1)
    url.query = a.search.substr(1)
    url.protocol = tempProtocol ? "" : a.protocol.substr(0, a.protocol.length - 1)
    url.port = tempProtocol ? "" : a.port ? a.port : a.protocol === 'http:' ? 80 : a.protocol === 'https:' ? 443 : a.port
    url.parts = parts
    url.segments = a.pathname === '/' ? [] : a.pathname.split('/').slice(1)
    url.params = url.query === '' ? [] : url.query.split('&')
    for (var j = 0; j < url.params.length; j++) {
        var param = url.params[j];
        var keyval = param.split('=')
        url.params[j] = {
            'key': keyval[0],
            'val': keyval[1]
        }
    }
    // domainroot
    if (parts.length > 2) {
        url.domainroot = parts[parts.length - 2] + '.' + parts[parts.length - 1];
        // check for country code top level domain
        if (parts[parts.length - 1].length == 2 && parts[parts.length - 1].length == 2)
            url.domainroot = parts[parts.length - 3] + '.' + url.domainroot;
    }
    // domainpath (domain+path without filenames) 
    if (url.segments.length > 0) {
        var lastSegment = url.segments[url.segments.length - 1]
        var endsWithFile = lastSegment.indexOf('.') != -1
        if (endsWithFile) {
            var fileSegment = url.path.indexOf(lastSegment)
            var pathNoFile = url.path.substr(0, fileSegment - 1)
            url.domainpath = url.domain
            if (pathNoFile)
                url.domainpath = url.domainpath + '/' + pathNoFile
        } else
            url.domainpath = url.domain + '/' + url.path
    } else
        url.domainpath = url.domain
    return url
}