const regex = /(?i)\s((?:https?:\/\/|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}\/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’]))/gm;
// Alternative syntax using RegExp constructor
// const regex = new RegExp('(?i)\\s((?:https?:\\\/\\\/|www\\d{0,3}[.]|[a-z0-9.\\-]+[.][a-z]{2,4}\\\/)(?:[^\\s()<>]+|\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\))+(?:\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\)|[^\\s`!()\\[\\]{};:\'\\".,<>?«»“”‘’]))', 'gm')
const str = `<a href="https://example.com/page.php?goto=200">https://example.com/page.php?goto=200</a>The problem occurs when I have almost identical links. For example: https://example.com/page.php?goto=200 and https://example.com/page.php
<a href="https://example.com/page.php?goto=200">https://example.com/page.php?goto=200</a>`;
// Reset `lastIndex` if this regex is defined globally
// regex.lastIndex = 0;
let m;
while ((m = regex.exec(str)) !== null) {
// This is necessary to avoid infinite loops with zero-width matches
if (m.index === regex.lastIndex) {
regex.lastIndex++;
}
// The result can be accessed through the `m`-variable.
m.forEach((match, groupIndex) => {
console.log(`Found match, group ${groupIndex}: ${match}`);
});
}
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for JavaScript, please visit: https://developer.mozilla.org/en/docs/Web/JavaScript/Guide/Regular_Expressions