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

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"
}

其他回答

function parseUrl(url) {
    var m = url.match(/^((?:([^:\/?#]+:)(?:\/\/))?((?:([^\/?#:]*):([^\/?#:]*)@)?([^\/?#:]*)(?::([^\/?#:]*))?))?([^?#]*)(\?[^#]*)?(#.*)?$/),
        r = {
            hash: m[10] || "",                   // #asd
            host: m[3] || "",                    // localhost:257
            hostname: m[6] || "",                // localhost
            href: m[0] || "",                    // http://username:password@localhost:257/deploy/?asd=asd#asd
            origin: m[1] || "",                  // http://username:password@localhost:257
            pathname: m[8] || (m[1] ? "/" : ""), // /deploy/
            port: m[7] || "",                    // 257
            protocol: m[2] || "",                // http:
            search: m[9] || "",                  // ?asd=asd
            username: m[4] || "",                // username
            password: m[5] || ""                 // password
        };
    if (r.protocol.length == 2) {
        r.protocol = "file:///" + r.protocol.toUpperCase();
        r.origin = r.protocol + "//" + r.host;
    }
    r.href = r.origin + r.pathname + r.search + r.hash;
    return r;
};
parseUrl("http://username:password@localhost:257/deploy/?asd=asd#asd");

它既适用于绝对url,也适用于相对url

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);

第一个答案的简单破解

var getLocation = function(href=window.location.href) {
    var l = document.createElement("a");
    l.href = href;
    return l;
};

即使没有参数,也可以使用它来计算当前的主机名 getLocation()。Hostname将给出当前主机名

在这里找到:https://gist.github.com/jlong/2428561

var parser = document.createElement('a');
parser.href = "http://example.com:3000/pathname/?search=test#hash";

parser.protocol; // => "http:"
parser.host;     // => "example.com:3000"
parser.hostname; // => "example.com"
parser.port;     // => "3000"
parser.pathname; // => "/pathname/"
parser.hash;     // => "#hash"
parser.search;   // => "?search=test"
parser.origin;   // => "http://example.com:3000"

这不会解析查询和散列,但除此之外它工作得很好。

const getURIParts = (url) => { const matches = url.match(/^(\w+?:\/\/)?([\w-\.]+(?=\/?))?:?(\d*)?([^:]*)/) return { scheme: matches ? matches[1] : undefined, host: matches ? matches[2] : '', port: matches ? matches[3] : undefined, pathname: matches ? matches[4] : '' } } console.log(getURIParts("")) console.log(getURIParts("http://localhost/bla")) console.log(getURIParts("https://api.spotify.com/")) console.log(getURIParts("https://api.spotify.com")) console.log(getURIParts("wss://wss.slack.com/link/?ticket=1234-5678")) console.log(getURIParts("localhost")) console.log(getURIParts("localhost/bla")) console.log(getURIParts("localhost/")) console.log(getURIParts("api.spotify.com/bla/two")) console.log(getURIParts("api.spotify.com:8000/bla/two")) console.log(getURIParts("https://api.spotify.com:8800/")) console.log(getURIParts("/mp3-preview/f504e6b8e037771318656394f532dede4f9bcaea"))