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
我已经修改了所有的评论，注释和备注是这个主题，并做了一个新的正则表达式:
^((javascript:[\w-_]+(\([\w-_\s,.]*\))?)|(mailto:([\w\u00C0-\u1FFF\u2C00-\uD7FF-_]+\.)*[\w\u00C0-\u1FFF\u2C00-\uD7FF-_]+@([\w\u00C0-\u1FFF\u2C00-\uD7FF-_]+\.)*[\w\u00C0-\u1FFF\u2C00-\uD7FF-_]+)|(\w+:\/\/(([\w\u00C0-\u1FFF\u2C00-\uD7FF-]+\.)*([\w\u00C0-\u1FFF\u2C00-\uD7FF-]*\.?))(:\d+)?(((\/[^\s#$%^&*?]+)+|\/)(\?[\w\u00C0-\u1FFF\u2C00-\uD7FF:;&%_,.~+=-]+)?)?(#[\w\u00C0-\u1FFF\u2C00-\uD7FF-_]+)?))$
你可以在这里测试和改进它https://regexr.com/668mt。
我检查了下一个值的表达式:
http://www.google.com/url?sa=i&rct=j&q=&esrc=s&source=images&cd=&docid=nIv5rk2GyP3hXM&tbnid=isiOkMe3nCtexM:&ved=0CAUQjRw&url=http%3A%2F%2Fanimalcrossing.wikia.com%2Fwiki%2FLion&ei=ygZXU_2fGKbMsQTf4YLgAQ&bvm=bv.65177938,d.aWc&psig=AFQjCNEpBfKnal9kU7Zu4n7RnEt2nerN4g&ust=1398298682009707
http://192.168.0.4:55/
https://web.archive.org/web/20170817095211/https://github.com/Microsoft/vscode/issues/32405
http://www.example.com
javascript:void()
http://.
https://example.
https://en.m.wikipedia.org/wiki/C_Sharp_(programming_language)
http://zh.wikipedia.org/wiki/Wikipedia:关于中文维基百科/en?a#a
https://medium.com/@User_name/
https://test-test-test-test-test-test-test-test-test.web.app/
http://www.google.com/url?sa=i&rct=j&q=&esrc=s&source=images&cd=&docid=nIv5rk2GyP3hXM&tbnid=isiOkMe3nCtexM:&ved=0CAUQjRw&url=http%3A%2F%2Fanimalcrossing.wikia.com%2Fwiki%2FLion&ei=ygZXU_2fGKbMsQTf4YLgAQ&bvm=bv.65177938,d.aWc&psig=AFQjCNEpBfKnal9kU7Zu4n7RnEt2nerN4g&ust=1398298682009707
https://sdfasdp.ppppppppppp
mailto:sadf@gmail.com
https://тест.юа
其他回答
一个有答案的相关问题
或者来自Devshed的Regexp:
function validURL(str) {
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
'(\\:\\d+)?(\\/[-a-z\\d%_.~+]*)*'+ // port and path
'(\\?[;&a-z\\d%_.~+=-]*)?'+ // query string
'(\\#[-a-z\\d_]*)?$','i'); // fragment locator
return !!pattern.test(str);
}
我已经修改了所有的评论，注释和备注是这个主题，并做了一个新的正则表达式:
^((javascript:[\w-_]+(\([\w-_\s,.]*\))?)|(mailto:([\w\u00C0-\u1FFF\u2C00-\uD7FF-_]+\.)*[\w\u00C0-\u1FFF\u2C00-\uD7FF-_]+@([\w\u00C0-\u1FFF\u2C00-\uD7FF-_]+\.)*[\w\u00C0-\u1FFF\u2C00-\uD7FF-_]+)|(\w+:\/\/(([\w\u00C0-\u1FFF\u2C00-\uD7FF-]+\.)*([\w\u00C0-\u1FFF\u2C00-\uD7FF-]*\.?))(:\d+)?(((\/[^\s#$%^&*?]+)+|\/)(\?[\w\u00C0-\u1FFF\u2C00-\uD7FF:;&%_,.~+=-]+)?)?(#[\w\u00C0-\u1FFF\u2C00-\uD7FF-_]+)?))$
你可以在这里测试和改进它https://regexr.com/668mt。
我检查了下一个值的表达式:
http://www.google.com/url?sa=i&rct=j&q=&esrc=s&source=images&cd=&docid=nIv5rk2GyP3hXM&tbnid=isiOkMe3nCtexM:&ved=0CAUQjRw&url=http%3A%2F%2Fanimalcrossing.wikia.com%2Fwiki%2FLion&ei=ygZXU_2fGKbMsQTf4YLgAQ&bvm=bv.65177938,d.aWc&psig=AFQjCNEpBfKnal9kU7Zu4n7RnEt2nerN4g&ust=1398298682009707
http://192.168.0.4:55/
https://web.archive.org/web/20170817095211/https://github.com/Microsoft/vscode/issues/32405
http://www.example.com
javascript:void()
http://.
https://example.
https://en.m.wikipedia.org/wiki/C_Sharp_(programming_language)
http://zh.wikipedia.org/wiki/Wikipedia:关于中文维基百科/en?a#a
https://medium.com/@User_name/
https://test-test-test-test-test-test-test-test-test.web.app/
http://www.google.com/url?sa=i&rct=j&q=&esrc=s&source=images&cd=&docid=nIv5rk2GyP3hXM&tbnid=isiOkMe3nCtexM:&ved=0CAUQjRw&url=http%3A%2F%2Fanimalcrossing.wikia.com%2Fwiki%2FLion&ei=ygZXU_2fGKbMsQTf4YLgAQ&bvm=bv.65177938,d.aWc&psig=AFQjCNEpBfKnal9kU7Zu4n7RnEt2nerN4g&ust=1398298682009707
https://sdfasdp.ppppppppppp
mailto:sadf@gmail.com
https://тест.юа
使用纯正则表达式很难做到这一点，因为url有很多“不方便”的地方。
For example domain names have complicated restrictions on hyphens: a. It is allowed to have many consecutive hyphens in the middle. b. but the first character and last character of the domain name cannot be a hyphen c. The 3rd and 4th character cannot be both hyphen Similarly port number can only be in the range 1-65535. This is easy to check if you extract the port part and convert to int but quite difficult to check with a regular expression. There is also no easy way to check valid domain extensions. Some countries have second-level domains(such as 'co.uk'), or the extension can be a long word such as '.international'. And new TLDs are added regularly. This type of things can only be checked against a hard-coded list. (see https://en.wikipedia.org/wiki/Top-level_domain) Then there are magnet urls, ftp addresses etc. These all have different requirements.
然而，这里有一个函数可以处理几乎所有的事情，除了:
案例1。c 接受任何1-5位数的端口号 接受任何扩展2-13个字符 不接受ftp，磁铁等…
function isValidURL(input) { pattern = '^(https?:\\/\\/)?' + // protocol '((([a-zA-Z\\d]([a-zA-Z\\d-]{0,61}[a-zA-Z\\d])*\\.)+' + // sub-domain + domain name '[a-zA-Z]{2,13})' + // extension '|((\\d{1,3}\\.){3}\\d{1,3})' + // OR ip (v4) address '|localhost)' + // OR localhost '(\\:\\d{1,5})?' + // port '(\\/[a-zA-Z\\&\\d%_.~+-:@]*)*' + // path '(\\?[a-zA-Z\\&\\d%_.,~+-:@=;&]*)?' + // query string '(\\#[-a-zA-Z&\\d_]*)?$'; // fragment locator regex = new RegExp(pattern); return regex.test(input); } let tests = []; tests.push(['', false]); tests.push(['http://en.wikipedia.org/wiki/Procter_&_Gamble', true]); tests.push(['https://sdfasd', false]); tests.push(['http://www.google.com/url?sa=i&rct=j&q=&esrc=s&source=images&cd=&docid=nIv5rk2GyP3hXM&tbnid=isiOkMe3nCtexM:&ved=0CAUQjRw&url=http%3A%2F%2Fanimalcrossing.wikia.com%2Fwiki%2FLion&ei=ygZXU_2fGKbMsQTf4YLgAQ&bvm=bv.65177938,d.aWc&psig=AFQjCNEpBfKnal9kU7Zu4n7RnEt2nerN4g&ust=1398298682009707', true]); tests.push(['https://stackoverflow.com/', true]); tests.push(['https://w', false]); tests.push(['aaa', false]); tests.push(['aaaa', false]); tests.push(['oh.my', true]); tests.push(['dfdsfdsfdfdsfsdfs', false]); tests.push(['google.co.uk', true]); tests.push(['test-domain.MUSEUM', true]); tests.push(['-hyphen-start.gov.tr', false]); tests.push(['hyphen-end-.com', false]); tests.push(['https://sdfasdp.international', true]); tests.push(['https://sdfasdp.pppppppp', false]); tests.push(['https://sdfasdp.ppppppppppppppppppp', false]); tests.push(['https://sdfasd', false]); tests.push(['https://sub1.1234.sub3.sub4.sub5.co.uk/?', true]); tests.push(['http://www.google-com.123', false]); tests.push(['http://my--testdomain.com', false]); tests.push(['http://my2nd--testdomain.com', true]); tests.push(['http://thingiverse.com/download:1894343', true]); tests.push(['https://medium.com/@techytimo', true]); tests.push(['http://localhost', true]); tests.push(['localhost', true]); tests.push(['localhost:8080', true]); tests.push(['localhost:65536', true]); tests.push(['localhost:80000', false]); tests.push(['magnet:?xt=urn:btih:123', true]); for (let i = 0; i < tests.length; i++) { console.log('Test #' + i + (isValidURL(tests[i][0]) == tests[i][1] ? ' passed' : ' failed') + ' on ["' + tests[i][0] + '", ' + tests[i][1] + ']'); }
您可以使用ajax请求来检查字符串是否有效的url和可访问的
(function() { $("input").change(function() { const check = $.ajax({ url : this.value, dataType: "jsonp" }); check.then(function() { console.log("Site is valid and registered"); }); //expected output check.catch(function(reason) { if(reason.status === 200) { return console.log("Site is valid and registered"); } console.log("Not a valid site"); }) }); })() <script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.3.1/jquery.min.js"></script> <input type="text" placeholder="Please input url to check ? ">
另一种方法是使用Node.JS的DNS模块。
DNS模块提供了一种执行名称解析的方法，使用它可以验证url是否有效。
const dns = require('dns');
const url = require('url');
const lookupUrl = "https://stackoverflow.com";
const parsedLookupUrl = url.parse(lookupUrl);
dns.lookup(parsedLookupUrl.protocol ? parsedLookupUrl.host
: parsedLookupUrl.path, (error,address,family)=>{
console.log(error || !address ? lookupUrl + ' is an invalid url!'
: lookupUrl + ' is a valid url: ' + ' at ' + address);
}
);
这样您就可以检查url是否有效以及是否存在
