Download an edX course as Markdown a file (edX - Course - Web browser console scraping)

edX-Course-Web_browser_console_scraping.js

// Download an edX course as Markdown a file
//
// Usage: 
// * Go to edX course webpage
// * Enroll
// * Get in (audit course, for example)
// * Open web browser console (tested on Chromium)
// * Paste code
// * Press intro
function extracttion() {
  extracted = {}
  // Extract URL
  extracted.url = window.location.href

  // Extract title
  extracted.title = jQuery('.page-title').text()

  // Extract content
  extracted.content = []
  jQuery('.block-tree').find('div').each(function () {
    text = jQuery(this).text()
    text = text.replace(/(\r\n|\n|\r)/gm," ")
    text = text.replace(/\s+/g,' ')
    text = text.trim()

    if (jQuery(this).hasClass('section-name')) text = '## ' + text

    if (text) extracted.content.push(text)
  })

  return extracted
}

function presentation(data) {
  return `# ${data.title}
  url: ${data.url}

  ${data.content.join('\n')}`
}

function download(name, contents, mime_type) {
  mime_type = mime_type || "text/plain";

  var blob = new Blob([contents], {type: mime_type});

  var dlink = document.createElement('a');
  dlink.download = name;
  dlink.href = window.URL.createObjectURL(blob);
  dlink.onclick = function(e) {
      // revokeObjectURL needs a delay to work properly
      var that = this;
      setTimeout(function() {
          window.URL.revokeObjectURL(that.href);
      }, 1500);
  };

  dlink.click();
  dlink.remove();
}

function main() {
  data = extracttion()
  md = presentation(data)
  download(data.title + '.md', md)
}

main()