Question

I’m processing some text in JavaScript (using Node, so please no jQuery). I want to extract all URL’s that are in <a> tags on the page. How can I do this in JavaScript?

Answer 1

var myArray = preg_match_all("<a.*?href=[\'|\"](.*?)[\'|\"]", "How can I get the URL of an <a href=\"http://www.mysite.com\"> in JavaScript? How can I get the URL of an <a href=\"http://www.mysite.org\"> in JavaScript?")

if ( myArray != null) {
  for ( i = 0; i < myArray.length; i++ ) { 
    alert(myArray[i]);
  }
}

function preg_match_all(regex, haystack) {
   var globalRegex = new RegExp(regex, 'g');
   var globalMatch = haystack.match(globalRegex);
   matchArray = new Array();
   for (var i in globalMatch) {
      nonGlobalRegex = new RegExp(regex);
      nonGlobalMatch = globalMatch[i].match(nonGlobalRegex);
      matchArray.push(nonGlobalMatch[1]);
   }
   return matchArray;
}

preg_match_all function taken from http://coding.pressbin.com/16/Javascript-equivalent-of-PHPs-pregmatchall

I would recommend using an online tester such as this one: http://www.pagecolumn.com/tool/regtest.htm