如果您想检测带有http:// OR而不带有http://或ftp或其他可能的情况(如删除末尾的标点符号)的链接，请查看这段代码。

https://jsfiddle.net/AndrewKang/xtfjn8g3/

使用它的一个简单方法是使用NPM

npm install --save url-knife

我在谷歌上搜索了这个问题很长一段时间，然后我想到了一个Android方法，Android .text.util。Linkify，它利用一些非常健壮的正则表达式来完成这个。幸运的是，Android是开源的。

他们使用一些不同的模式来匹配不同类型的url。你可以在这里找到它们: http://grepcode.com/file/repository.grepcode.com/java/ext/com.google.android/android/2.0_r1/android/text/util/Regex.java#Regex.0WEB_URL_PATTERN

如果你只关心匹配WEB_URL_PATTERN的url，也就是说，url符合RFC 1738规范，你可以使用这个:

/((?:(http|https|Http|Https|rtsp|Rtsp):\/\/(?:(?:[a-zA-Z0-9\$\-\_\.\+\!\*\'\(\)\,\;\?\&\=]|(?:\%[a-fA-F0-9]{2})){1,64}(?:\:(?:[a-zA-Z0-9\$\-\_\.\+\!\*\'\(\)\,\;\?\&\=]|(?:\%[a-fA-F0-9]{2})){1,25})?\@)?)?((?:(?:[a-zA-Z0-9][a-zA-Z0-9\-]{0,64}\.)+(?:(?:aero|arpa|asia|a[cdefgilmnoqrstuwxz])|(?:biz|b[abdefghijmnorstvwyz])|(?:cat|com|coop|c[acdfghiklmnoruvxyz])|d[ejkmoz]|(?:edu|e[cegrstu])|f[ijkmor]|(?:gov|g[abdefghilmnpqrstuwy])|h[kmnrtu]|(?:info|int|i[delmnoqrst])|(?:jobs|j[emop])|k[eghimnrwyz]|l[abcikrstuvy]|(?:mil|mobi|museum|m[acdghklmnopqrstuvwxyz])|(?:name|net|n[acefgilopruz])|(?:org|om)|(?:pro|p[aefghklmnrstwy])|qa|r[eouw]|s[abcdeghijklmnortuvyz]|(?:tel|travel|t[cdfghjklmnoprtvwz])|u[agkmsyz]|v[aceginu]|w[fs]|y[etu]|z[amw]))|(?:(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[0-9])))(?:\:\d{1,5})?)(\/(?:(?:[a-zA-Z0-9\;\/\?\:\@\&\=\#\~\-\.\+\!\*\'\(\)\,\_])|(?:\%[a-fA-F0-9]{2}))*)?(?:\b|$)/gi;

以下是原文全文:

"((?:(http|https|Http|Https|rtsp|Rtsp):\\/\\/(?:(?:[a-zA-Z0-9\\$\\-\\_\\.\\+\\!\\*\\'\\(\\)"
+ "\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,64}(?:\\:(?:[a-zA-Z0-9\\$\\-\\_"
+ "\\.\\+\\!\\*\\'\\(\\)\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,25})?\\@)?)?"
+ "((?:(?:[a-zA-Z0-9][a-zA-Z0-9\\-]{0,64}\\.)+"   // named host
+ "(?:"   // plus top level domain
+ "(?:aero|arpa|asia|a[cdefgilmnoqrstuwxz])"
+ "|(?:biz|b[abdefghijmnorstvwyz])"
+ "|(?:cat|com|coop|c[acdfghiklmnoruvxyz])"
+ "|d[ejkmoz]"
+ "|(?:edu|e[cegrstu])"
+ "|f[ijkmor]"
+ "|(?:gov|g[abdefghilmnpqrstuwy])"
+ "|h[kmnrtu]"
+ "|(?:info|int|i[delmnoqrst])"
+ "|(?:jobs|j[emop])"
+ "|k[eghimnrwyz]"
+ "|l[abcikrstuvy]"
+ "|(?:mil|mobi|museum|m[acdghklmnopqrstuvwxyz])"
+ "|(?:name|net|n[acefgilopruz])"
+ "|(?:org|om)"
+ "|(?:pro|p[aefghklmnrstwy])"
+ "|qa"
+ "|r[eouw]"
+ "|s[abcdeghijklmnortuvyz]"
+ "|(?:tel|travel|t[cdfghjklmnoprtvwz])"
+ "|u[agkmsyz]"
+ "|v[aceginu]"
+ "|w[fs]"
+ "|y[etu]"
+ "|z[amw]))"
+ "|(?:(?:25[0-5]|2[0-4]" // or ip address
+ "[0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\\.(?:25[0-5]|2[0-4][0-9]"
+ "|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(?:25[0-5]|2[0-4][0-9]|[0-1]"
+ "[0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}"
+ "|[1-9][0-9]|[0-9])))"
+ "(?:\\:\\d{1,5})?)" // plus option port number
+ "(\\/(?:(?:[a-zA-Z0-9\\;\\/\\?\\:\\@\\&\\=\\#\\~"  // plus option query params
+ "\\-\\.\\+\\!\\*\\'\\(\\)\\,\\_])|(?:\\%[a-fA-F0-9]{2}))*)?"
+ "(?:\\b|$)";

如果你想要更花哨，你也可以测试电子邮件地址。电子邮件地址的正则表达式是:

/[a-zA-Z0-9\\+\\.\\_\\%\\-]{1,256}\\@[a-zA-Z0-9][a-zA-Z0-9\\-]{0,64}(\\.[a-zA-Z0-9][a-zA-Z0-9\\-]{0,25})+/gi

PS:上述正则表达式支持的顶级域是2007年6月的最新版本。要查看最新的列表，您需要查看https://data.iana.org/TLD/tlds-alpha-by-domain.txt。

功能可以进一步改善渲染图像以及:

function renderHTML(text) { 
    var rawText = strip(text)
    var urlRegex =/(\b(https?|ftp|file):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])/ig;   

    return rawText.replace(urlRegex, function(url) {   

    if ( ( url.indexOf(".jpg") > 0 ) || ( url.indexOf(".png") > 0 ) || ( url.indexOf(".gif") > 0 ) ) {
            return '<img src="' + url + '">' + '<br/>'
        } else {
            return '<a href="' + url + '">' + url + '</a>' + '<br/>'
        }
    }) 
} 

或者对于链接到完整大小图像的缩略图:

return '<a href="' + url + '"><img style="width: 100px; border: 0px; -moz-border-radius: 5px; border-radius: 5px;" src="' + url + '">' + '</a>' + '<br/>'

下面是strip()函数，它通过删除任何现有html对文本字符串进行预处理以实现一致性。

function strip(html) 
    {  
        var tmp = document.createElement("DIV"); 
        tmp.innerHTML = html; 
        var urlRegex =/(\b(https?|ftp|file):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])/ig;   
        return tmp.innerText.replace(urlRegex, function(url) {     
        return '\n' + url 
    })
} 

tmp。innerText未定义。您应该使用tmp.innerHTML

function strip(html) 
    {  
        var tmp = document.createElement("DIV"); 
        tmp.innerHTML = html; 
        var urlRegex =/(\b(https?|ftp|file):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])/ig;   
        return tmp.innerHTML .replace(urlRegex, function(url) {     
        return '\n' + url 
    })

有一个现有的npm包:url-regex，只需用yarn添加url-regex或npm安装url-regex，然后像下面这样使用:

const urlRegex = require('url-regex');

const replaced = 'Find me at http://www.example.com and also at http://stackoverflow.com or at google.com'
  .replace(urlRegex({strict: false}), function(url) {
     return '<a href="' + url + '">' + url + '</a>';
  });

试试这个:

function isUrl(s) {
    if (!isUrl.rx_url) {
        // taken from https://gist.github.com/dperini/729294
        isUrl.rx_url=/^(?:(?:https?|ftp):\/\/)?(?:\S+(?::\S*)?@)?(?:(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z\u00a1-\uffff0-9]-*)*[a-z\u00a1-\uffff0-9]+)(?:\.(?:[a-z\u00a1-\uffff0-9]-*)*[a-z\u00a1-\uffff0-9]+)*(?:\.(?:[a-z\u00a1-\uffff]{2,}))\.?)(?::\d{2,5})?(?:[/?#]\S*)?$/i;
        // valid prefixes
        isUrl.prefixes=['http:\/\/', 'https:\/\/', 'ftp:\/\/', 'www.'];
        // taken from https://w3techs.com/technologies/overview/top_level_domain/all
        isUrl.domains=['com','ru','net','org','de','jp','uk','br','pl','in','it','fr','au','info','nl','ir','cn','es','cz','kr','ua','ca','eu','biz','za','gr','co','ro','se','tw','mx','vn','tr','ch','hu','at','be','dk','tv','me','ar','no','us','sk','xyz','fi','id','cl','by','nz','il','ie','pt','kz','io','my','lt','hk','cc','sg','edu','pk','su','bg','th','top','lv','hr','pe','club','rs','ae','az','si','ph','pro','ng','tk','ee','asia','mobi'];
    }

    if (!isUrl.rx_url.test(s)) return false;
    for (let i=0; i<isUrl.prefixes.length; i++) if (s.startsWith(isUrl.prefixes[i])) return true;
    for (let i=0; i<isUrl.domains.length; i++) if (s.endsWith('.'+isUrl.domains[i]) || s.includes('.'+isUrl.domains[i]+'\/') ||s.includes('.'+isUrl.domains[i]+'?')) return true;
    return false;
}

function isEmail(s) {
    if (!isEmail.rx_email) {
        // taken from http://stackoverflow.com/a/16016476/460084
        var sQtext = '[^\\x0d\\x22\\x5c\\x80-\\xff]';
        var sDtext = '[^\\x0d\\x5b-\\x5d\\x80-\\xff]';
        var sAtom = '[^\\x00-\\x20\\x22\\x28\\x29\\x2c\\x2e\\x3a-\\x3c\\x3e\\x40\\x5b-\\x5d\\x7f-\\xff]+';
        var sQuotedPair = '\\x5c[\\x00-\\x7f]';
        var sDomainLiteral = '\\x5b(' + sDtext + '|' + sQuotedPair + ')*\\x5d';
        var sQuotedString = '\\x22(' + sQtext + '|' + sQuotedPair + ')*\\x22';
        var sDomain_ref = sAtom;
        var sSubDomain = '(' + sDomain_ref + '|' + sDomainLiteral + ')';
        var sWord = '(' + sAtom + '|' + sQuotedString + ')';
        var sDomain = sSubDomain + '(\\x2e' + sSubDomain + ')*';
        var sLocalPart = sWord + '(\\x2e' + sWord + ')*';
        var sAddrSpec = sLocalPart + '\\x40' + sDomain; // complete RFC822 email address spec
        var sValidEmail = '^' + sAddrSpec + '$'; // as whole string

        isEmail.rx_email = new RegExp(sValidEmail);
    }

    return isEmail.rx_email.test(s);
}

还将识别url，如google.com, http://www.google.bla, http://google.bla, www.google.bla但不是google.bla