scrape ieee fulltext HTML by rendering in phantom

ieee.js

var webPage = require('webpage');
var fs = require('fs');
var page = webPage.create();

var urls = fs.read("fulltext_html_urls.txt").split("\n");
urls = urls.splice(0, urls.length - 1);

var ar_regex = /([0-9]+$)/;

console.log("scraping " + urls.length + " URLs");

var pageindex = 0;
var fileName = '';
var loadInProgress = false;

var interval = setInterval(function() {
  if (!loadInProgress && pageindex < urls.length) {
    fileName = urls[pageindex];
    page.open(urls[pageindex]);
  }
  if (pageindex == urls.length) {
    console.log("Scraping complete!");
    phantom.exit();
  }
}, 250);

page.onLoadStarted = function() {
  loadInProgress = true;
};

page.onLoadFinished = function(status) {
  console.log('status: ' + status);
  loadInProgress = false;
  var arnumber = ar_regex.exec(urls[pageindex])[1];
  var dest = arnumber + ".html";
  console.log('saving: ' + dest);

  fs.write(dest, page.content); //page source

  pageindex++;
}

page.onResourceError = function(resourceError) {
  console.log('Unable to load resource (#' + resourceError.id + 'URL:' + resourceError.url + ')');
  console.log('Error code: ' + resourceError.errorCode + '. Description: ' + resourceError.errorString);
};