Capture screenshots (png) from multiple sites with phantomjs

capture.js

// How to: save as capture.js and run with "phantomjs capture.js"
// Setup by modifying URLS, PAGE_WIDTH AND PAGE_HEIGHT constants!
// Hint: set PAGE_WIDTH or PAGE_HEIGHT to 0 to capture full page!
// modified version of script at http://www.cameronjtinker.com/post/2011/09/26/Take-Screenshot-of-all-HTML-documents-in-a-folder-using-PhantomJS.aspx

var PAGE_WIDTH = 960;
var PAGE_HEIGHT = 640;

var URLS = [
  "http://github.com",
  "http://twitter.com"
];

// phantomjs page object and helper flag
var page = require('webpage').create(),
  loadInProgress = false,
  pageIndex = 0;


// set clip and viewport based on PAGE_WIDTH and PAGE_HEIGHT constants
if (PAGE_WIDTH > 0 && PAGE_HEIGHT > 0) {
  page.viewportSize = {
    width: PAGE_WIDTH,
    height: PAGE_HEIGHT
  };

  page.clipRect = {
    top: 0,
    left: 0,
    width: PAGE_WIDTH,
    height: PAGE_HEIGHT
  };
}

// page handlers
page.onLoadStarted = function() {
  loadInProgress = true;
  console.log('page ' + (pageIndex + 1) + ' load started');
};

page.onLoadFinished = function() {
  loadInProgress = false;
  page.render("images/output" + (pageIndex + 1) + "_" + PAGE_WIDTH + "x" + PAGE_HEIGHT + ".png");
  console.log('page ' + (pageIndex + 1) + ' load finished');
  pageIndex++;
};

// try to load or process a new page every 250ms
setInterval(function() {
  if (!loadInProgress && pageIndex < URLS.length) {
    console.log("image " + (pageIndex + 1));
    page.open(URLS[pageIndex]);
  }
  if (pageIndex == URLS.length) {
    console.log("image render complete!");
    phantom.exit();
  }
}, 250);

console.log('Number of URLS: ' + URLS.length);

Sorry I feel like using the setInterval function isn't the best way to implement this. You should be using callbacks.

Is it possible to give URLS a sitemap.xml with all the pages you want to crawl. Instead of having to generate a list yourself?

Great code. Is there a way to have customized output file names with the domain included in the name? when making screenshots for thousands of websites it is an impossible task to associate the screenshot with the proper website/domain