Github search scraping

gistfile1.js

/*
Usage: io github <query> [language]
    io github django
    io github coffeescript

To limit search results to a certain language:
    io github django python

To see debug info:
    io --debug github django
*/

var nodeio = require('node.io'), search_url, added_additional = false;

exports.job = new nodeio.Job({max: 50, retries: 3, auto_retry: true}, {
    init: function () {
        var query = '', language = '';

        //Parse command line args
        switch (this.options.args.length) {
            case 0:
                console.log('node.io github <query> [language]');
                process.exit();
            case 2: language = this.options.args[1];
            case 1: query = this.options.args[0];
        }

        //Build the base search URL
        search_url = 'https://github.com/search?type=Repositories&language='
                   + language + '&q=' + query
                   + '&repo=&langOverride=&x=0&y=0&start_value=';

        //The initial input is page 1 of search results
        this.input = [search_url + 1];
    },

    run: function (search_page) {
        this.getHtml(search_page, function(err, $) {

            //Add additional pages of search results to the input queue (only once)
            if (!added_additional) {
                var page, total_pages = $('.pager_link').last().text;
                for (page = 2; page < total_pages; page++) {
                    this.add(search_url + page);
                }
                added_additional = true;
            }

            //Scrape projects on the page and emit
            var projects = [];
            $('.result').each(function (listing) {
                var project = {}, title, language;
                title = $('h2 a', listing).fulltext;
                language = $('.language', listing).fulltext;
                project.author = title.substring(0, title.indexOf(" / "));
                project.title = title.substring(title.indexOf(" / ") + 3);
                project.link = "https://github.com" + $('h2 a', listing).attribs.href;
                project.language = language.substring(1, language.length - 1);
                project.description = $('.description', listing).fulltext;
                projects.push(project);
            });
            this.emit(projects);
        });
    }
});