在JavaScript中是否有一种方法来检查字符串是否是URL?

regex被排除在外,因为URL很可能写成stackoverflow;也就是说,它可能没有。com, WWW或http。


当前回答

2020年更新。 为了扩展@iamnewton和@ fernando Chavez Herrera的精彩回答,我已经开始看到@被用于url的路径。

所以更新后的正则表达式是:

RegExp('(https?:\\/\\/)?((([a-z\\d]([a-z\\d-]*[a-z\\d])*)\\.)+[a-z]{2,}|((\\d{1,3}\\.){3}\\d{1,3}))(\\:\\d+)?(\\/[-a-z\\d%_.~+@]*)*(\\?[;&a-z\\d%_.~+=-]*)?(\\#[-a-z\\d_]*)?$', 'i');

如果你想在查询字符串和哈希中允许它,使用:

RegExp('(https?:\\/\\/)?((([a-z\\d]([a-z\\d-]*[a-z\\d])*)\\.)+[a-z]{2,}|((\\d{1,3}\\.){3}\\d{1,3}))(\\:\\d+)?(\\/[-a-z\\d%_.~+@]*)*(\\?[;&a-z\\d%_.~+=-@]*)?(\\#[-a-z\\d_@]*)?$', 'i');

话虽如此,我不确定是否有白皮书规则禁止在查询字符串或哈希中使用@。

其他回答

使用validator.js

ES6

import isURL from 'validator/lib/isURL'

isURL(string)

不ES6

var validator = require('validator');

validator.isURL(string)

您还可以通过将可选options对象作为isURL的第二个参数来微调此函数的行为

下面是默认的选项对象:

let options = {
    protocols: [
        'http',
        'https',
        'ftp'
    ],
    require_tld: true,
    require_protocol: false,
    require_host: true,
    require_valid_protocol: true,
    allow_underscores: false,
    host_whitelist: false,
    host_blacklist: false,
    allow_trailing_dot: false,
    allow_protocol_relative_urls: false,
    disallow_auth: false
}

isURL(string, options)

Host_whitelist和host_blacklist可以是主机的阵列。它们还支持正则表达式。

let options = {
    host_blacklist: ['foo.com', 'bar.com'],
}

isURL('http://foobar.com', options) // => true
isURL('http://foo.bar.com/', options) // => true
isURL('http://qux.com', options) // => true

isURL('http://bar.com/', options) // => false
isURL('http://foo.com/', options) // => false


options = {
    host_blacklist: ['bar.com', 'foo.com', /\.foo\.com$/],
}

isURL('http://foobar.com', options) // => true
isURL('http://foo.bar.com/', options) // => true
isURL('http://qux.com', options) // => true

isURL('http://bar.com/', options) // => false
isURL('http://foo.com/', options) // => false
isURL('http://images.foo.com/', options) // => false
isURL('http://cdn.foo.com/', options) // => false
isURL('http://a.b.c.foo.com/', options) // => false

如果你也需要支持https://localhost:3000,那么使用[Devshed]s regex的修改版本。

    function isURL(url) {
        if(!url) return false;
        var pattern = new RegExp('^(https?:\\/\\/)?'+ // protocol
            '((([a-z\\d]([a-z\\d-]*[a-z\\d])*)\\.)+[a-z]{2,}|'+ // domain name
            '((\\d{1,3}\\.){3}\\d{1,3}))|' + // OR ip (v4) address
            'localhost' + // OR localhost
            '(\\:\\d+)?(\\/[-a-z\\d%_.~+]*)*'+ // port and path
            '(\\?[;&a-z\\d%_.~+=-]*)?'+ // query string
            '(\\#[-a-z\\d_]*)?$', 'i'); // fragment locator
        return pattern.test(url);
    }

这里只是一个非常简单的检查,以确保有一个有效的协议,并且域扩展名必须是两个或更多字符。

is_valid_url = ( $url ) => {

    let $url_object = null;

    try {
        $url_object = new URL( $url );
    } catch ( $error ) {
        return false;
    }

    const $protocol = $url_object.protocol;
    const $protocol_position = $url.lastIndexOf( $protocol );
    const $domain_extension_position = $url.lastIndexOf( '.' );

    return (
        $protocol_position === 0 &&
        [ 'http:', 'https:' ].indexOf( $protocol ) !== - 1 &&
        $domain_extension_position > 2 && $url.length - $domain_extension_position > 2
    );

};

这是@palvo的答案的扩展。

function isValidHttpUrl(string) {
  let url;
  try {
    url = new URL(string);
  } catch (_) {
    return false;  
  }
  return (url.protocol === "http:" || url.protocol === "https:") && (url.href == string || url.origin == string);
}

试试以下方法:-

isValidHttpUrl(“https:母羊/ dsdsd”); isValidHttpUrl(“https://ewe/dsdsd”);

Chrome测试

这显然不是最有效的方法,但它是可读的,并且很容易形成您需要的任何形式。从这里添加regex/complexity更容易。这是一个非常实用的方法

const validFirstBits = ["ftp://", "http://", "https://", "www."];
const invalidPatterns = [" ", "//.", ".."];

export function isUrl(word) {
// less than www.1.dk
if (!word || word.length < 8) return false;

// Let's check and see, if our candidate starts with some of our valid first bits
const firstBitIsValid = validFirstBits.some(bit => word.indexOf(bit) === 0);
if (!firstBitIsValid) return false;

const hasInvalidPatterns = invalidPatterns.some(
    pattern => word.indexOf(pattern) !== -1,
);

if (hasInvalidPatterns) return false;

const dotSplit = word.split(".");
if (dotSplit.length > 1) {
    const lastBit = dotSplit.pop(); // string or undefined
    if (!lastBit) return false;
    const length = lastBit.length;
    const lastBitIsValid =
        length > 1 || (length === 1 && !isNaN(parseInt(lastBit)));
    return !!lastBitIsValid;
}

    return false;
}

测试:

import { isUrl } from "./foo";

describe("Foo", () => {
    test("should validate correct urls correctly", function() {
        const validUrls = [
            "http://example.com",
            "http://example.com/blah",
            "http://127.0.0.1",
            "http://127.0.0.1/wow",
            "https://example.com",
            "https://example.com/blah",
            "https://127.0.0.1:1234",
            "ftp://example.com",
            "ftp://example.com/blah",
            "ftp://127.0.0.1",
            "www.example.com",
            "www.example.com/blah",
        ];

        validUrls.forEach(url => {
            expect(isUrl(url) && url).toEqual(url);
        });
    });

    test("should validate invalid urls correctly", function() {
        const inValidUrls = [
            "http:// foo.com",
            "http:/foo.com",
            "http://.foo.com",
            "http://foo..com",
            "http://.com",
            "http://foo",
            "http://foo.c",
        ];

        inValidUrls.forEach(url => {
            expect(!isUrl(url) && url).toEqual(url);
        });
    });
});