phantomjs not waiting for “full” page load

Question

I\'m using PhantomJS v1.4.1 to load some web pages. I don\'t have access to their server-side, I just getting links pointing to them. I\'m using obsolete version of Phantom

Answer 1

I would rather periodically check for document.readyState status (https://developer.mozilla.org/en-US/docs/Web/API/document.readyState). Although this approach is a bit clunky, you can be sure that inside onPageReady function you are using fully loaded document.

var page = require("webpage").create(),
    url = "http://example.com/index.html";

function onPageReady() {
    var htmlContent = page.evaluate(function () {
        return document.documentElement.outerHTML;
    });

    console.log(htmlContent);

    phantom.exit();
}

page.open(url, function (status) {
    function checkReadyState() {
        setTimeout(function () {
            var readyState = page.evaluate(function () {
                return document.readyState;
            });

            if ("complete" === readyState) {
                onPageReady();
            } else {
                checkReadyState();
            }
        });
    }

    checkReadyState();
});

Additional explanation:

Using nested setTimeout instead of setInterval prevents checkReadyState from "overlapping" and race conditions when its execution is prolonged for some random reasons. setTimeout has a default delay of 4ms (https://stackoverflow.com/a/3580085/1011156) so active polling will not drastically affect program performance.

document.readyState === "complete" means that document is completely loaded with all resources (https://html.spec.whatwg.org/multipage/dom.html#current-document-readiness).

Answer 2

I found this solution useful in a NodeJS app. I use it just in desperate cases because it launches a timeout in order to wait for the full page load.

The second argument is the callback function which is going to be called once the response is ready.

phantom = require('phantom');

var fullLoad = function(anUrl, callbackDone) {
    phantom.create(function (ph) {
        ph.createPage(function (page) {
            page.open(anUrl, function (status) {
                if (status !== 'success') {
                    console.error("pahtom: error opening " + anUrl, status);
                    ph.exit();
                } else {
                    // timeOut
                    global.setTimeout(function () {
                        page.evaluate(function () {
                            return document.documentElement.innerHTML;
                        }, function (result) {
                            ph.exit(); // EXTREMLY IMPORTANT
                            callbackDone(result); // callback
                        });
                    }, 5000);
                }
            });
        });
    });
}

var callback = function(htmlBody) {
    // do smth with the htmlBody
}

fullLoad('your/url/', callback);