我想拿一根绳子

var a = "http://example.com/aa/bb/"

然后把它加工成一个物体

a.hostname == "example.com"

and

a.pathname == "/aa/bb"

当前回答

你也可以使用来自Locutus项目(前php.js)的parse_url()函数。

代码:

parse_url('http://username:password@hostname/path?arg=value#anchor');

结果:

{
  scheme: 'http',
  host: 'hostname',
  user: 'username',
  pass: 'password',
  path: '/path',
  query: 'arg=value',
  fragment: 'anchor'
}

其他回答

跨浏览器的URL解析,围绕IE 6、7、8和9的相对路径问题工作:

function ParsedUrl(url) {
    var parser = document.createElement("a");
    parser.href = url;

    // IE 8 and 9 dont load the attributes "protocol" and "host" in case the source URL
    // is just a pathname, that is, "/example" and not "http://domain.com/example".
    parser.href = parser.href;

    // IE 7 and 6 wont load "protocol" and "host" even with the above workaround,
    // so we take the protocol/host from window.location and place them manually
    if (parser.host === "") {
        var newProtocolAndHost = window.location.protocol + "//" + window.location.host;
        if (url.charAt(1) === "/") {
            parser.href = newProtocolAndHost + url;
        } else {
            // the regex gets everything up to the last "/"
            // /path/takesEverythingUpToAndIncludingTheLastForwardSlash/thisIsIgnored
            // "/" is inserted before because IE takes it of from pathname
            var currentFolder = ("/"+parser.pathname).match(/.*\//)[0];
            parser.href = newProtocolAndHost + currentFolder + url;
        }
    }

    // copies all the properties to this object
    var properties = ['host', 'hostname', 'hash', 'href', 'port', 'protocol', 'search'];
    for (var i = 0, n = properties.length; i < n; i++) {
      this[properties[i]] = parser[properties[i]];
    }

    // pathname is special because IE takes the "/" of the starting of pathname
    this.pathname = (parser.pathname.charAt(0) !== "/" ? "/" : "") + parser.pathname;
}

使用方法(演示JSFiddle在这里):

var myUrl = new ParsedUrl("http://www.example.com:8080/path?query=123#fragment");

结果:

{
    hash: "#fragment"
    host: "www.example.com:8080"
    hostname: "www.example.com"
    href: "http://www.example.com:8080/path?query=123#fragment"
    pathname: "/path"
    port: "8080"
    protocol: "http:"
    search: "?query=123"
}

对于那些正在寻找在IE, Firefox和Chrome中工作的现代解决方案的人:

这些使用超链接元素的解决方案都不会在chrome中起同样的作用。如果你传递一个无效(或空白)的url给chrome,它总是会返回脚本被调用的主机。所以在IE中你会得到空白,而在Chrome中你会得到localhost(或其他什么)。

如果你试图看着推荐人,这是骗人的。你需要确保你返回的主机在原始url中,以处理这个问题:

    function getHostNameFromUrl(url) {
        // <summary>Parses the domain/host from a given url.</summary>
        var a = document.createElement("a");
        a.href = url;

        // Handle chrome which will default to domain where script is called from if invalid
        return url.indexOf(a.hostname) != -1 ? a.hostname : '';
    }

freddiefujiwara的答案很好,但我也需要在ie中支持相对url。我想出了以下解决方案:

function getLocation(href) {
    var location = document.createElement("a");
    location.href = href;
    // IE doesn't populate all link properties when setting .href with a relative URL,
    // however .href will return an absolute URL which then can be used on itself
    // to populate these additional fields.
    if (location.host == "") {
      location.href = location.href;
    }
    return location;
};

现在使用它来获得所需的属性:

var a = getLocation('http://example.com/aa/bb/');
document.write(a.hostname);
document.write(a.pathname);

例子:

function getLocation(href) { var location = document.createElement("a"); location.href = href; // IE doesn't populate all link properties when setting .href with a relative URL, // however .href will return an absolute URL which then can be used on itself // to populate these additional fields. if (location.host == "") { location.href = location.href; } return location; }; var urlToParse = 'http://example.com/aa/bb/', a = getLocation(urlToParse); document.write('Absolute URL: ' + urlToParse); document.write('<br />'); document.write('Hostname: ' + a.hostname); document.write('<br />'); document.write('Pathname: ' + a.pathname);

下面是一个使用regexp的简单函数,它模仿了a标记行为。

Pros

可预测的行为(无跨浏览器问题) 不需要DOM 它真的很短。

Cons

regexp有点难读

-

function getLocation(href) {
    var match = href.match(/^(https?\:)\/\/(([^:\/?#]*)(?:\:([0-9]+))?)([\/]{0,1}[^?#]*)(\?[^#]*|)(#.*|)$/);
    return match && {
        href: href,
        protocol: match[1],
        host: match[2],
        hostname: match[3],
        port: match[4],
        pathname: match[5],
        search: match[6],
        hash: match[7]
    }
}

-

getLocation("http://example.com/");
/*
{
    "protocol": "http:",
    "host": "example.com",
    "hostname": "example.com",
    "port": undefined,
    "pathname": "/"
    "search": "",
    "hash": "",
}
*/

getLocation("http://example.com:3000/pathname/?search=test#hash");
/*
{
    "protocol": "http:",
    "host": "example.com:3000",
    "hostname": "example.com",
    "port": "3000",
    "pathname": "/pathname/",
    "search": "?search=test",
    "hash": "#hash"
}
*/

编辑:

下面是正则表达式的分解

var reURLInformation = new RegExp([
    '^(https?:)//', // protocol
    '(([^:/?#]*)(?::([0-9]+))?)', // host (hostname and port)
    '(/{0,1}[^?#]*)', // pathname
    '(\\?[^#]*|)', // search
    '(#.*|)$' // hash
].join(''));
var match = href.match(reURLInformation);

只需使用url.js库(用于web和node.js)。

https://github.com/websanova/js-url

url: http://example.com?param=test#param=again

url('?param'); // test
url('#param'); // again
url('protocol'); // http
url('port'); // 80
url('domain'); // example.com
url('tld'); // com

etc...