javascript - 获取不带扩展名的根域名 - Javascript

Question

如何在 JavaScript 中从给定 URL 获取不带扩展名的根域名？

示例:

rootDomain("https://www.etsy.com/market/tumblr_clothing") -> etsy

rootDomain("https://petitions.whitehouse.gov/") -> whitehouse

rootDomain("facebook.com") -> facebook

rootDomain("google.ca") -> google

我找到了一个不完整的解决方案:How to get domain name only using javascript?和 Extract hostname name from string

主要问题是我在创建没有扩展名或子域的解决方案时遇到问题。

解决这个问题的最佳方法是什么？

Answer 1

尝试:

function extractHostname(url) {
    var hostname;
    if (url.indexOf("//") > -1) {
        hostname = url.split('/')[2];
    }
    else {
        hostname = url.split('/')[0];
    }
    hostname = hostname.split(':')[0];
    hostname = hostname.split('?')[0];
    return hostname;
}

function extractRootDomainNoExt(url) {
    var domain = extractHostname(url),
        splitArr = domain.split('.'),
        arrLen = splitArr.length;

    if (arrLen == 2) {
      domain = splitArr[0]
    }
    else if (arrLen > 2) {
        domain = splitArr[arrLen - 2];
        //check to see if it's using a Country Code Top Level Domain (ccTLD) (i.e. ".me.uk")
        if (splitArr[arrLen - 2].length == 2 && splitArr[arrLen - 1].length == 2) {
            domain = splitArr[arrLen - 3];
        }
    }
    return domain;
}

//test extractRootDomainNoExt
console.log("== Testing extractRootDomainNoExt: ==");
console.log(extractRootDomainNoExt("https://www.etsy.com/market/tumblr_clothing"));
console.log(extractRootDomainNoExt("https://petitions.whitehouse.gov/"));
console.log(extractRootDomainNoExt("facebook.com"));
console.log(extractRootDomainNoExt("google.ca"));
console.log(extractRootDomainNoExt("http://www.blog.classroom.me.uk/index.php"));
console.log(extractRootDomainNoExt("http://www.youtube.com/watch?v=ClkQA2Lb_iE"));
console.log(extractRootDomainNoExt("https://www.youtube.com/watch?v=ClkQA2Lb_iE"));
console.log(extractRootDomainNoExt("www.youtube.com/watch?v=ClkQA2Lb_iE"));
console.log(extractRootDomainNoExt("ftps://ftp.websitename.com/dir/file.txt"));
console.log(extractRootDomainNoExt("doesnothaveext/dir/file.txt"));
console.log(extractRootDomainNoExt("websitename.com:1234/dir/file.txt"));
console.log(extractRootDomainNoExt("ftps://websitename.com:1234/dir/file.txt"));
console.log(extractRootDomainNoExt("example.com?param=value"));
console.log(extractRootDomainNoExt("https://facebook.github.io/jest/"));
console.log(extractRootDomainNoExt("//youtube.com/watch?v=ClkQA2Lb_iE"));

*点击“运行代码片段”即可在各种用例中查看这项工作。

这也适用于提取子域和国家/地区编码的域名，例如 classroom.co.uk -> classroom。

另请参阅:Extract hostname name from string