Last active
December 7, 2023 19:56
-
-
Save dfl/2697619352935d6f3e9a8c469f02613b to your computer and use it in GitHub Desktop.
ruby script for downloading kajabi course for archival purposes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # This script requires the nokogiri gem, and youtube-dl to be installed. | |
| # It will fetch video, mp3, and text results. | |
| # download cookies.txt using Chrome plugin "Get cookies.txt" | |
| # download page source as course-page.html | |
| quality = "iphone-360p" # to find quality options, use youtube-dl -v -F --cookies cookies.txt https://{KAJABI_COURSE}/categories/#####/posts/##### | |
| cookies = "=cookies.txt" | |
| course_url = "https://www.MYCOURSE.COM" | |
| domain = course_url.split("/")[2] | |
| # Step 1. parse all the media URLs and titles | |
| file = "#{course_url.split("/").last}.html" | |
| `wget -qO- --load-cookies #{cookies} #{course_url} > #{file}` | |
| require 'nokogiri' | |
| f = File.read(file).gsub(/\n\s+/,'') | |
| doc = Nokogiri::HTML.parse(f) do |config| | |
| config.noblanks | |
| end | |
| doc.css("style").remove | |
| course_title = doc.css("h1").text | |
| outline = doc.css(".product-outline") | |
| categories = outline.css(".product-outline-category") | |
| list = {}; | |
| categories.each_with_index do |cat,idx| | |
| posts = [] | |
| title = "#{idx} - #{cat.text}" | |
| if subtitle = cat.css("+ .product-outline-subcategory").first | |
| title = { cat.text => subtitle.text } | |
| end | |
| post = (subtitle || cat).css("+ .product-outline-post").first | |
| posts << [ post.css(".media-body").text.strip.gsub('"',''), post[:href] ] | |
| e = post | |
| loop do | |
| if post = e.css("+ .product-outline-post").first | |
| posts << [ post.css(".media-body").text.strip.gsub('"',''), post[:href] ] | |
| e = post; | |
| elsif subtitle = e.css("+ .product-outline-subcategory").first | |
| list[title] = posts; | |
| posts = []; | |
| title = { cat.text => subtitle.text } | |
| e = subtitle | |
| else | |
| list[title] = posts; | |
| break | |
| end | |
| end | |
| end | |
| # Step 2. fetch the files | |
| require 'fileutils' | |
| list.each_pair do |k,v| | |
| case k | |
| when String | |
| path = k | |
| when Hash | |
| path = k.to_a.join("/") | |
| end | |
| path = [course_title, path].join("/") # prepend course title | |
| FileUtils.mkpath(path) | |
| v.each do |title, url| | |
| p path | |
| `youtube-dl -v -f #{quality}/#{quality}-0/mp3_audio --download-archive downloaded.txt --cookies #{cookies} -o "./#{path}/#{title}.%(ext)s" https://#{domain}#{url}` | |
| p $?.exitstatus | |
| unless $?.success? #not a video, get file | |
| `wget -qO- --load-cookies #{cookies} https://#{domain}#{url} > "./#{path}/#{title}.html"` | |
| end | |
| end | |
| end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
https://chromewebstore.google.com/detail/get-cookiestxt-locally/cclelndahbckbenkjhflpdbgdldlbecc