Improving regex for parsing YouTube / Vimeo URLs

Question

I've made a function (in JavaScript) that takes an URL from either YouTube or Vimeo. It figures out the provider and ID for that particular video (demo: http://jsfiddle.net/csjwf/).

function parseVideoURL(url) {

    var provider = url.match(/http:\/\/(:?www.)?(\w*)/)[2],
        id;

    if(provider == "youtube") {

        id = url.match(/http:\/\/(?:www.)?(\w*).com\/.*v=(\w*)/)[2];
    } else if (provider == "vimeo") {

        id = url.match(/http:\/\/(?:www.)?(\w*).com\/(\d*)/)[2];
    } else {
        throw new Error("parseVideoURL() takes a YouTube or Vimeo URL");    
    }
    return {
        provider : provider,
        id : id
    }
}

It works, however as a regex Novice, I'm looking for ways to improve it. The input I'm dealing with, typically looks like this:

http://vimeo.com/(id)
http://youtube.com/watch?v=(id)&blahblahblah.....

1) Right now I'm doing three separate matches, would it make sense to try and do everything in one single expression? If so, how?

2) Could the existing matches be more concise? Are they unnecessarily complex? or perhaps insufficient?

3) Are there any YouTube or Vimeo URL's that would fail being parsed? I've tried quite a few and so far it seems to work pretty well.

To summarize: I'm simply looking for ways improve the above function. Any advice is greatly appreciated.

Answer 1

Here's my attempt at the regex, which covers most updated cases:

function parseVideo(url) {
    // - Supported YouTube URL formats:
    //   - http://www.youtube.com/watch?v=My2FRPA3Gf8
    //   - http://youtu.be/My2FRPA3Gf8
    //   - https://youtube.googleapis.com/v/My2FRPA3Gf8
    // - Supported Vimeo URL formats:
    //   - http://vimeo.com/25451551
    //   - http://player.vimeo.com/video/25451551
    // - Also supports relative URLs:
    //   - //player.vimeo.com/video/25451551

    url.match(/(https?\/\/)(player.|www.)?(vimeo\.com|youtu(be\.com|\.be|be\.googleapis\.com))\/(video\/|embed\/|watch\?v=|v\/)?([A-Za-z0-9._%-]*)(\&\S+)?/);
    var type = null;
    if (RegExp.$3.indexOf('youtu') > -1) {
        type = 'youtube';
    } else if (RegExp.$3.indexOf('vimeo') > -1) {
        type = 'vimeo';
    }

    return {
        type: type,
        id: RegExp.$6
    };
}

Answer 2

Regex is wonderfully terse but can quickly get complicated.

http://jsfiddle.net/8nagx2sk/

function parseYouTube(str) {
    // link : //youtube.com/watch?v=Bo_deCOd1HU
    // share : //youtu.be/Bo_deCOd1HU
    // embed : //youtube.com/embed/Bo_deCOd1HU

    var re = /\/\/(?:www\.)?youtu(?:\.be|be\.com)\/(?:watch\?v=|embed\/)?([a-z0-9_\-]+)/i; 
    var matches = re.exec(str);
    return matches && matches[1];
}

function parseVimeo(str) {
    // embed & link: http://vimeo.com/86164897

    var re = /\/\/(?:www\.)?vimeo.com\/([0-9a-z\-_]+)/i;
    var matches = re.exec(str);
    return matches && matches[1];
}

Sometimes simple code is nicer to your fellow developers.

https://jsfiddle.net/vkg02mhp/1/

// protocol and www nuetral
function getVideoId(str, prefixes) {
  const cleaned = str.replace(/^(https?:)?\/\/(www\.)?/, '');
  for(const prefix of prefixes) {
    if (cleaned.startsWith(prefix))
      return cleaned.substr(prefix.length)
  }
  return undefined;
}

function getYouTubeId(url) {
  return getVideoId(url, [
    'youtube.com/watch?v=',
    'youtu.be/',
    'youtube.com/embed/'
  ]);
}

function getVimeoId(url) {
  return getVideoId(url, [
    'vimeo.com/'
  ]);
}

Which do you prefer to update?