const regex = /<p>(\s*)(<a(.*)>)?(\s*)(https?:\/\/)?(w{3}\.)?(instagram\.com)\/(p\/)?(?<photoID>[A-Za-z0-9-_]{11})(\S*)(\s*)(<\/a>)?(\s*)?<\/p>/g;
// Alternative syntax using RegExp constructor
// const regex = new RegExp('<p>(\\s*)(<a(.*)>)?(\\s*)(https?:\\\/\\\/)?(w{3}\\.)?(instagram\\.com)\\\/(p\\\/)?(?<photoID>[A-Za-z0-9-_]{11})(\\S*)(\\s*)(<\\\/a>)?(\\s*)?<\\\/p>', 'g')
const str = `Best case
<p>https://www.instagram.com/p/B9XK4J3jVui/</p>
Whitespace
<p>
https://www.instagram.com/p/B9XK4J3jVui/
</p>
Protocol variations
<p>http://www.instagram.com/p/B9XK4J3jVui/</p>
<p>www.instagram.com/p/B9XK4J3jVui/</p>
<p>instagram.com/p/B9XK4J3jVui/</p>
Trailing slash or not
<p>http://www.instagram.com/p/B9XK4J3jVui/</p>
<p>http://www.instagram.com/p/B9XK4J3jVui</p>
Linked
<p><a href="http://www.instagram.com/p/B9XK4J3jVui/">http://www.instagram.com/p/B9XK4J3jVui/</a></p>
<p>
<a href="http://www.instagram.com/p/B9XK4J3jVui/">
http://www.instagram.com/p/B9XK4J3jVui/
</a>
</p>
Extraneous URL params
<p>https://www.instagram.com/p/B9XK4J3jVui?foo=bar</p>
<p>https://www.instagram.com/p/B9XK4J3jVui?foo=bar&baz=buzz</p>`;
// 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