Download all the lecture videos from a Coursera class index page. Requires phantomjs and wget.

coursera-slurp

#!/usr/bin/env phantomjs
/**
 * Scrapes a Coursera class index page and downloads the
 * individual lecture mp4s. Requires phantomjs and curl.
 * Usage: ./coursera-slurp [index-url]
 *
 * If something breaks, it's probably the DOM selector in the
 * remote page. Try fiddling with the 'linkSelector' function.
 */
var page = require('webpage').create(),
    spawn = require("child_process").spawn,
    args = require('system').args,
    opts = parseOpts(args),
    userAgent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.71 Safari/537.36",
    max_proc = 5,           //max concurrent child processes, 0 for unlimited
    return_tally = 0,       //keep track of returned "threads"
    linkqueue;              //collection of link objects

if (opts.help) {
  console.log("Usage: coursera-slurp [options] index-url");
  console.log("Options:");
  console.log("  -h, --help            Print help");
  console.log("  -v, --verbose         Print verbose output");
  console.log("  -D, --dry-run         Display remote files found but don't download");
  console.log("  -A, --auth=token      Supply login token, this is the 'CAUTH' cookie");
  console.log("  -C, --cookies=string  Use additional cookies");
  phantom.exit(0);
}

if (opts.cookies) {
  for (var name in opts.cookies) {
    phantom.addCookie({
      'name': name,                //required
      'value': opts.cookies[name], //required
      'domain': '.coursera.org'    //required
    });
  }
}

page.settings.userAgent = userAgent;

if (opts.verbose) {
  console.log("Downloading page: " + opts.url);
}
page.open(opts.url, function (status) {
  if (status !== 'success') {
    console.warn('Failed to load url, aborting.');
    phantom.exit(1);
  }
  linkqueue = page.evaluate(linkSelector).concat();

  if (linkqueue.length === 0) {
    console.error("No files found!");
    phantom.exit(1);
  }
  
  if (opts.verbose || opts.dryrun) {
    console.log("Found files:");
    linkqueue.forEach(function (link) {
      var filename = getLinkFilename(link),
          downloadurl = getLinkURL(link);
      console.log(downloadurl + " => " + filename);
    });
  }
  if (opts.dry_run) {
    phantom.exit(0);
  }
  //off we go ...
  if (max_proc === 0) {
    max_proc = linkqueue.length;
  }
  for (var i = 0; i < max_proc; i++) {
    if (linkqueue.length > 0) {
      var link = linkqueue.shift();
      window.setTimeout(downloadLink, 0, link);
    }
  }
});

page.onError = function (msg, trace) {
  console.error("Error in remote page:\n\t", msg);
};

/* Evaluated in webpage, limited cross-polination with phantomjs.
 * @return {Array} Links in order: [link1, link2, ...]
 * A link object looks like: {id: 'lectureid', title: 'lecture title', pos: idx}
 */
function linkSelector () {
  var link_elems = document.querySelectorAll('.lecture-link'),
      links = [];
  Array.prototype.slice.call(link_elems).forEach(function (elem, i) {
    links.push({
      id: elem.getAttribute('data-lecture-id'), //url-id
      title: elem.innerText.trim(),             //link title
      pos: i                                    //position in page
    });
  });
  return links;
}

/* Downloads the given link.
 * On finish, download another or close application.
 */
function downloadLink (link) {
  var filename = getLinkFilename(link),
      downloadurl = getLinkURL(link),
      curlOpts = ['--location', '--user-agent', userAgent, downloadurl, '--output', filename];
  //add cookies
  if (Array.isArray(phantom.cookies) && phantom.cookies.length > 0) {
    var cookieStr = '';
    phantom.cookies.forEach(function (cookie, i) {
      if (i !== 0) { cookieStr += "; "; }
      cookieStr += (cookie.name + "=" + cookie.value);
    });
    curlOpts.unshift('--cookie', cookieStr);
  }
  if (opts.verbose) {
    curlOpts.unshift('--verbose');
    console.log("curl options: " + curlOpts.join(' '));
  }
  //download
  var proc = spawn('curl', curlOpts);
  console.log("Downloading " + filename);
  //on finish, use this "thread" to download the next link or ring finished bell
  proc.on('exit', function (status) {
    if (opts.verbose) {
      console.log("Download finished for " + filename + ", status: " + status);
    }
    if (linkqueue.length > 0) {
      var nextlink = linkqueue.shift();
      downloadLink(nextlink);
    } else {
      return_tally += 1;
      if (return_tally === max_proc) {
        console.log("All downloads complete!");
        phantom.exit();
      }
    }
  });
  if (opts.verbose) {
    var logOut = function (data) { console.log(data); };
    proc.stdout.on('data', logOut);
    proc.stderr.on('data', logOut);
  }
}

/* Construct download link from Link id.
 * @return {string} URL of file download.
 */
function getLinkURL (link) {
  var linkPostfix = "/download.mp4?lecture_id=",
      url = opts.url,
      base = (url[url.length-1] === '/') ? url.slice(0, -1) : url;
  return (base + linkPostfix + link.id);
}

/* Create a output filename based using Link title.
 * @return {string} Local filename, in form: '001-First-Lecture.mp4'
 */
function getLinkFilename (link) {
  var base = link.title.replace(/\s/g, '-').replace(/[^\w\n-]/g, ''),
      ext = "mp4",
      filename = base + '.' + ext;
  if (typeof link.pos === 'number') {
    var i = link.pos + 1,
        pre = (i < 100) ? ("00" + i).slice(-3) : i; //pad
    filename = (pre + '-' + filename);
  }
  return filename;
}

/* Parse command-line options.
 */
function parseOpts (args) {
  var opts = {
    url: args[args.length-1] //url should be last
  };
  if (args.length < 2) {
    opts.help = true;
  } else {
    for (var i = 1, len = args.length; i < len; i++) {
      switch (args[i]) {
      case '-h': case '--help':
        opts.help = true;
        break;
      case '-D': case '--dry-run':
        opts.dry_run = true;
        break;
      case '-C': case '--cookies':
        if (!opts.cookies) { opts.cookies = {}; }
        //parse cookie string
        args[i+1].split(';').forEach(function (entry) {
          var keyval = entry.trim().split('=');
          opts.cookies[keyval[0]] = keyval[1];
        });
        break;
      case '-A': case '--auth':
        if (!opts.cookies) { opts.cookies = {}; }
        opts.cookies = {'CAUTH': args[i+1]}
        break;
      case '-v': case '--verbose':
        opts.verbose = true;
        break;
      }
    }
  }
  return opts;
}

I tried this script using phantomjs coursera-slurp.js --auth=myCAUTHkey https://class.coursera.org/algs4partII-003/lecture and it returns no files. However executing linkSelector() in browser console returns 12 links. My Phantomjs version is 1.9.7. What am I missing here? Any help would be great.