Simple scraper tool

scraper.js

var http = require('http'),
    Url = require('url'),
    htmlparser = require('node-htmlparser'),
    dom = require('jsdom/level1/core').dom.level1.core,
    index = require('jsdom/browser/index'),
    sizzleInit = require('sizzle').sizzleInit;

// Simple wrapper around node's http client, htmlparser, jsdom, and sizzle
function fetch(url, callback) {
  var uri = Url.parse(url);
  var server = http.createClient(uri.port || 80, uri.host);
  var request = server.request('GET', uri.pathname, {
    Host: uri.host
  });
  request.end();
  request.on('response', function (response) {
    response.setEncoding('utf8');
    var body = "";
    response.on('data', function (chunk) {
      body += chunk
    });
    response.on('end', function () {
      var browser = index.windowAugmentation(dom, {parser: htmlparser});
      browser.document.body.innerHTML = body;
      var Sizzle = sizzleInit(browser, browser.document);
      callback(null, Sizzle);
    });
    response.on('error', callback);
  });
  request.on('error', callback);
}

// Grabs the main sections from the index page
function getBooks(callback) {
  fetch("http://scriptures.lds.org/", function (err, Sizzle) {
    if (err) return callback(err);
    var results = {};
    Sizzle("a").forEach(function (a) {
      var href = a.href;
      if (!(/\/contents$/).test(href)) return;
      Sizzle(".smallcaps", a).forEach(function (div) {
        results[href] = div.innerHTML.trim();
      })
    });
    callback(null, results);
  });
}


getBooks(function (err, books) {
  if (err) throw err;
  console.dir(books);
});