尋找中英文夾雜 string 中的 URL

find-urls.js

var url = /^(?:(?:ht|f)tp(?:s?)\:\/\/|~\/|\/)?(?:\w+:\w+@)?((?:(?:[-\w\d{1-3}]+\.)+(?:com|org|net|gov|mil|biz|info|mobi|name|aero|jobs|edu|co\.uk|ac\.uk|it|fr|tv|museum|asia|local|travel|[a-z]{2}))|((\b25[0-5]\b|\b[2][0-4][0-9]\b|\b[0-1]?[0-9]?[0-9]\b)(\.(\b25[0-5]\b|\b[2][0-4][0-9]\b|\b[0-1]?[0-9]?[0-9]\b)){3}))(?::[\d]{1,5})?(?:(?:(?:\/(?:[-\w~!$+|.,=]|%[a-f\d]{2})+)+|\/)+|\?|#)?(?:(?:\?(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)(?:&(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)*)*(?:#(?:[-\w~!$ |\/.,*:;=]|%[a-f\d]{2})*)?$/i
  , chinese = /[\u4e00-\u9fa5]+/

  , cText   = '中文https://github.com/夾雜網址。'
  , eText   = 'english https://github.com/ url.'
  , mixText = '中 en 文https://github.com/夾雜 google.com網址'

  , gResult;

// utilities
var flatten = function(array) {
  
  var result = []
    , self = arguments.callee;
    
  array.forEach(function(item) {
    Array.prototype.push.apply(
      result,
      Array.isArray(item) ? self(item) : [item]
    );
  });
  
  return result;
};

gResult =
  mixText
    .split(chinese)
    .map(function (word) {
      return word.split(/\s/);
    });

gResult =
  flatten(gResult)
    .filter(function (word) {
      return url.test(word);
    });

console.log(gResult);
// => [ 'https://github.com/', 'google.com' ]