PhantomJS 2.0.0 doesn't wait for page to load

Question

The script below contains some URLs in links array. The function gatherLinks() is used to gather more URLs from sitemap.xml of the URLs in links array. Once the links array has enough URLs (decided by variable limit), function request() is called for each URL in links array to send a request to the server, fetch the response and save the image using page.render() function.

The problem is that when I run it using PhantomJS 2.0.0, many of the images lack a lot of content, i.e. PhantomJS probably doesn't wait for all content to load. But when I use PhantomJS 1.9.8, all content is loaded just fine. What could be the reason?

var webpage = require('webpage');
var system = require('system');
var fs = require('fs');
var links = [];

links = [
    "http://somesite.com",
    "http://someothersite.com",
       . 
       .
       .
 ];

var index = 0, fail = 0, limit = 20;
finalTime = Date.now();

var gatherLinks = function(link){
  var page = webpage.create();
  link = link + "/sitemap.xml";
  console.log("Fetching links from " + link);

  page.open(link, function(status){
    if(status != "success"){
      console.log("Sitemap Request FAILED, status: " + status);
      fail++;
      return;
    }

    var content = page.content;
    parser = new DOMParser();
    xmlDoc = parser.parseFromString(content, 'text/xml');
    var loc = xmlDoc.getElementsByTagName('loc');

    for(var i = 0; i < loc.length; i++){
      if(links.length < limit){
        links[links.length] = loc[i].textContent;
      } else{
        console.log(links.length + " Links prepared. Starting requests.\n");
        index = 0;
        page.close();
        request();
        return;
      }
    }

    if(index >= links.length){
      index = 0;
      console.log(links.length + " Links prepared\n\n");
      page.close();
      request();
      return;
    }

    page.close();
    gatherLinks(links[++index]);
  });
};

var request = function(){
  t = Date.now();
  var page = webpage.create();
  page.open(links[index], function(status) {
    console.log('Loading link #' + (index + 1) + ': ' + links[index]);
    console.log("Time taken: " + (Date.now() - t) + " msecs");

    if(status != "success"){
      console.log("Request FAILED, status: " + status);
      fail++;
    }

    page.render("img_200_" + index + ".jpeg", {format: 'jpeg', quality: '100'});
    if(index >= links.length-1){
      console.log("\n\nAll links done, final time taken: " + (Date.now() - finalTime) + " msecs");
      console.log("Requests sent: " + links.length + ", Failures: " + fail);
      console.log("Success ratio: " + ((links.length - fail)/links.length)*100 + "%");
      page.close();
      phantom.exit();
    }

    index++;
    page.close();
    request();
  });
}

gatherLinks(links[0]);

Answer 1

PhantomJS doesn't define when in the page load process the page.open callback is called. So, there's nothing actually wrongly claimed.

It could be that you can add a static wait amount with setTimeout() which should help for dynamic sites. There are also approaches where you can see if there are pending requests by counting how many requests where sent with page.onResourceRequested and how many requests finished with page.onResourceReceived/page.onResourceTimeout/page.onResourceError.

If it is actually a PhantomJS bug, then there is not much can to besides try some of the command line switches.