Google AngularJS SEO talk from July, 2013

nodejs_phantomjs_render.js

/* render website with JS and return its rendered output
   Syntax: node nodejs_phantomjs_render.js [url] [output {default=stdout}] */

var system = require('system'),
        fs = require('fs'),
      page = new WebPage(),
       url = system.args[1],
    output = system.args[2],
    result;


page.open(url, function (status) {
    if (status !== 'success') {
        console.log('FAILED to load the url');
        phantom.exit();
    } else {
        result = page.evaluate(function () {
            var html, doc;

            html = document.querySelector('html');

            return html.outerHTML;
        });

        if (output) {
            var rendered = fs.open(output, 'w');
            rendered.write(result);
            rendered.flush();
            rendered.close();
        } else {
            console.log(result);
        }
    }
    phantom.exit();
});

phantomjs_render.js

/* pure phantomjs version
   Syntax: phantomjs phantomjs_render.js
   Easy to use with CLI args and/or node also, just copy syntax from nodejs_phantomjs_render.js */

var page = require('webpage').create();
page.open('http://localhost:8000/app/index.html', function (status) {
    if (status !== 'success') {
        console.log('Unable to access network');
    } else {
        var p = page.evaluate(function () {
            return document.getElementsByTagName('html')[0].innerHTML
        });
        console.log(p); // Can output to file instead, just copy syntax from nodejs_phantomjs_render.js 
    }
    phantom.exit();
});

sitemap_gen.js

/* Renders sitemap.xml in syntax of http://www.sitemaps.org/protocol.html
   See final line for syntax use.
   Easy to use with CLI args also, just copy syntax from nodejs_phantomjs_render.js */

var fs    = require('fs'),
    jsdom = require('jsdom');

var dir_name = require('path').dirname(require.main.filename);
console.log('Working dir: ' + dir_name);

var static_index = fs.readFileSync('static_index.html', 'utf-8');
var document = jsdom.jsdom(static_index);

// Building sitemap from the `<a href=""></a>` links.
// Trivial to extend recursively through subpages.
var all_href = [], l = document.links;
for (var i = 0; i < l.length; i++) {
    all_href.push(l[i].href);
}

function generate_xml_sitemap(root, url_array) {
    var urls = url_array;
    // the root of your website - the protocol and the domain name with a trailing slash
    var root_path = root;
    // XML sitemap generation starts here
    var priority = 0.5;
    var freq = 'monthly';
    var xml = '<?xml version="1.0" encoding="UTF-8"?>';
    xml += '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">';
    for (var i in urls) {
        xml += '<url>';
        xml += '<loc>' + root_path + urls[i] + '</loc>';
        xml += '<changefreq>' + freq + '</changefreq>';
        xml += '<priority>' + priority + '</priority>';
        xml += '</url>';
        i++;
    }
    xml += '</urlset>';
    return xml;
}

console.log(generate_xml_sitemap('http://localhost:8000/', all_href));