Filter GA requests

ga-get-resource.js

var page = require('webpage').create(),
    system = require('system'),
    fs = require('fs'),
    file = 'data.json',
    address;

// how long should we wait for the page to load before we exit
// in ms
var WAIT_TIME = 1000;

// if the page hasn't loaded after this long, something is probably wrong.
// in ms
var MAX_EXECUTION_TIME = 15000;

// output error messages
var DEBUG = false



var url;


// a list of regular expressions of resources (urls) to log when we load them
var resources_to_log = [
    new RegExp('^http(s)?://(www|ssl)\.google-analytics\.com.*'),
    new RegExp('^http(s)?://stats\.g\.doubleclick\.net.*')
];

// function to check if the requested resource is an image
function isImg(url) {
    var acceptedExts = ['jpg', 'jpeg', 'png'];
    var baseUrl = url.split('?')[0];
    var ext = baseUrl.split('.').pop().toLowerCase();
    if (acceptedExts.indexOf(ext) > -1) {
        return true;
    } else {
        return false;
    }
}

// function to check if an url has a given extension
function isExt(url, ext) {
    var baseUrl = url.split('?')[0];
    var fileExt = baseUrl.split('.').pop().toLowerCase();
    if (ext == fileExt) {
        return true;
    } else {
        return false;
    }
}

// check we have a url, if not exit
if (system.args.length === 1) {
    console.log('Usage: get_ga_resources.js http://www.yoururl.com');
    phantom.exit(1);
} else {
    // address is the url passed
    address = system.args[1];

    // create a function that is called every time a resource is requested
    // http://phantomjs.org/api/webpage/handler/on-resource-requested.html
    page.onResourceRequested = function(request) {

        if (system.args[1] == request.url) {
            return;
        } else if (isImg(request.url) || isExt(request.url, 'js') || isExt(request.url, 'css') || isExt(request.url, 'woff')) {
            networkRequest.abort();
        } else {

            var length = resources_to_log.length;
            while (length--) {
                if (resources_to_log[length].test(request.url)) {
                    url = request.url;
                    phantom.exit();
                }
            }
        }

    };

    if debug is true, log errors, else ignore them
    page.onError = function(msg, trace) {
        if (DEBUG) {
            console.log('ERROR: ' + msg)
            console.log(trace)
        }
    };

    // make a note of any errors so we can print them out
    page.onResourceError = function(resourceError) {
        page.reason = resourceError.errorString;
        page.reason_url = resourceError.url;
    };

    page.onLoadFinished = function(status) {
        // console.log(JSON.stringify(urls));
        var content = JSON.parse(fs.read(file));

        content.urls.push(url);

        fs.write(file, JSON.stringify(content), 'w');
        phantom.exit();
    };

    // now all we have to do is open the page, wait WAIT_TIME ms and exit
    try {
        page.open(address, function(status) {
            if (status !== 'success') {
                console.log("FAILED: to load " + system.args[1]);
                console.log(page.reason_url);
                console.log(page.reason);
                phantom.exit();
            } else {
                if (address != page.url) {
                    console.log('Redirected: ' + page.url)
                }
                setTimeout(function() {
                    phantom.exit();
                }, WAIT_TIME);
            }
        });
    } finally {

    }
}

To run phantomjs ga-get-resource.js <url>