我正在使用下面的函数来匹配给定文本中的url，并将它们替换为HTML链接。正则表达式工作得很好，但目前我只替换了第一个匹配。
我怎么能替换所有的URL?我想我应该使用exec命令，但我真的不知道如何做到这一点。
function replaceURLWithHTMLLinks(text) {
var exp = /(\b(https?|ftp|file):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])/i;
return text.replace(exp,"<a href='$1'>$1</a>");
}
当前回答
以下是我的解决方案:
var content = "Visit https://wwww.google.com or watch this video: https://www.youtube.com/watch?v=0T4DQYgsazo and news at http://www.bbc.com";
content = replaceUrlsWithLinks(content, "http://");
content = replaceUrlsWithLinks(content, "https://");
function replaceUrlsWithLinks(content, protocol) {
var startPos = 0;
var s = 0;
while (s < content.length) {
startPos = content.indexOf(protocol, s);
if (startPos < 0)
return content;
let endPos = content.indexOf(" ", startPos + 1);
if (endPos < 0)
endPos = content.length;
let url = content.substr(startPos, endPos - startPos);
if (url.endsWith(".") || url.endsWith("?") || url.endsWith(",")) {
url = url.substr(0, url.length - 1);
endPos--;
}
if (ROOTNS.utils.stringsHelper.validUrl(url)) {
let link = "<a href='" + url + "'>" + url + "</a>";
content = content.substr(0, startPos) + link + content.substr(endPos);
s = startPos + link.length;
} else {
s = endPos + 1;
}
}
return content;
}
function validUrl(url) {
try {
new URL(url);
return true;
} catch (e) {
return false;
}
}
其他回答
识别URL很棘手，因为它们经常被标点符号包围，而且用户经常不使用URL的完整形式。有很多JavaScript函数可以用超链接替换url，但我在基于python的web框架Django中找不到一个像urlize过滤器一样好用的。因此，我将Django的urlize函数移植到JavaScript:
https://github.com/ljosa/urlize.js
一个例子:
urlize('Go to SO (stackoverflow.com) and ask. <grin>',
{nofollow: true, autoescape: true})
=> "Go to SO (<a href="http://stackoverflow.com" rel="nofollow">stackoverflow.com</a>) and ask. <grin>"
第二个参数如果为真，则会插入rel="nofollow"。如果第三个参数为真，则转义HTML中具有特殊含义的字符。请参阅README文件。
如果你需要显示更短的链接(仅域)，但具有相同的长URL，你可以尝试我对Sam Hasler的代码版本上面发布的修改
function replaceURLWithHTMLLinks(text) {
var exp = /(\b(https?|ftp|file):\/\/([-A-Z0-9+&@#%?=~_|!:,.;]*)([-A-Z0-9+&@#%?\/=~_|!:,.;]*)[-A-Z0-9+&@#\/%=~_|])/ig;
return text.replace(exp, "<a href='$1' target='_blank'>$3</a>");
}
尝试以下解决方案
function replaceLinkClickableLink(url = '') {
let pattern = new RegExp('^(https?:\\/\\/)?'+
'((([a-z\\d]([a-z\\d-]*[a-z\\d])*)\\.?)+[a-z]{2,}|'+
'((\\d{1,3}\\.){3}\\d{1,3}))'+
'(\\:\\d+)?(\\/[-a-z\\d%_.~+]*)*'+
'(\\?[;&a-z\\d%_.~+=-]*)?'+
'(\\#[-a-z\\d_]*)?$','i');
let isUrl = pattern.test(url);
if (isUrl) {
return `<a href="${url}" target="_blank">${url}</a>`;
}
return url;
}
我将Roshambo String.linkify()更改为emailaddressppattern以识别aaa.bbb.@ccc.ddd地址
if(!String.linkify) {
String.prototype.linkify = function() {
// http://, https://, ftp://
var urlPattern = /\b(?:https?|ftp):\/\/[a-z0-9-+&@#\/%?=~_|!:,.;]*[a-z0-9-+&@#\/%=~_|]/gim;
// www. sans http:// or https://
var pseudoUrlPattern = /(^|[^\/])(www\.[\S]+(\b|$))/gim;
// Email addresses *** here I've changed the expression ***
var emailAddressPattern = /(([a-zA-Z0-9_\-\.]+)@[a-zA-Z_]+?(?:\.[a-zA-Z]{2,6}))+/gim;
return this
.replace(urlPattern, '<a target="_blank" href="$&">$&</a>')
.replace(pseudoUrlPattern, '$1<a target="_blank" href="http://$2">$2</a>')
.replace(emailAddressPattern, '<a target="_blank" href="mailto:$1">$1</a>');
};
}
对Travis的Linkify()代码进行了一些优化。我还修复了子域类型格式的电子邮件地址不匹配的错误(即example@domain.co.uk)。
此外，我改变了String类的原型实现，这样项目就可以像这样匹配:
var text = 'address@example.com';
text.linkify();
'http://stackoverflow.com/'.linkify();
不管怎样，这是剧本:
if(!String.linkify) {
String.prototype.linkify = function() {
// http://, https://, ftp://
var urlPattern = /\b(?:https?|ftp):\/\/[a-z0-9-+&@#\/%?=~_|!:,.;]*[a-z0-9-+&@#\/%=~_|]/gim;
// www. sans http:// or https://
var pseudoUrlPattern = /(^|[^\/])(www\.[\S]+(\b|$))/gim;
// Email addresses
var emailAddressPattern = /[\w.]+@[a-zA-Z_-]+?(?:\.[a-zA-Z]{2,6})+/gim;
return this
.replace(urlPattern, '<a href="$&">$&</a>')
.replace(pseudoUrlPattern, '$1<a href="http://$2">$2</a>')
.replace(emailAddressPattern, '<a href="mailto:$&">$&</a>');
};
}
