Last active
August 29, 2015 14:01
-
-
Save turizoft/52e2218a3fb612986079 to your computer and use it in GitHub Desktop.
Download csv song collection using tinysong
This file contains hidden or 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
| require 'csv' | |
| require 'i18n' | |
| require 'nokogiri' | |
| require 'open-uri' | |
| require 'watir-webdriver' | |
| # This script reads a csv file with song name and | |
| # artist name in order to download them | |
| # This csv can be generated using for example http://groovebackup.com/ | |
| # if your collection is hosted on Grooveshark | |
| # Songs are downloaded from http://www.mp3xd.com/ | |
| # Before running ensure i18n, watir-webdriver and nokogiri gems are installed | |
| csv_path = 'songs.csv' | |
| # Read song list | |
| puts 'reading song list' | |
| csv_text = File.read(csv_path) | |
| csv = CSV.parse(csv_text, headers: true) | |
| # Start a browser | |
| browser = Watir::Browser.new :chrome | |
| csv.each do |row| | |
| puts "-- downloading #{row[0]} --" | |
| # Format query | |
| query = I18n.transliterate("#{row[1]} #{row[0]}").downcase.squeeze(' ') | |
| query = query.gsub(/[^0-9a-z ]/i, '') | |
| # Generate url | |
| param = query.gsub(' ', '-') | |
| url = "http://www.mp3xd.com/descargar-mp3/#{param}-1.html" | |
| # Download source from search page | |
| doc = Nokogiri::HTML(open(url)) | |
| # Scan document to search for links | |
| if doc.at_css('.song') | |
| href = doc.at_css('.song a.button-icon-descargar')['href'] | |
| dl_url = "http://www.mp3xd.com#{href}" | |
| # Url needs to be opened in a headless browser with js support | |
| browser.goto(dl_url) | |
| browser.iframe(id: 'dlframe').wait_until_present | |
| song_url = browser.iframe(id: 'dlframe').p(id: 'url').a().href | |
| #Download song | |
| song_name = I18n.transliterate(row[0]).squeeze(' ') | |
| artist_name = I18n.transliterate(row[1]).squeeze(' ') | |
| path = "#{artist_name} - #{song_name}.mp3" #Note: override this as needed | |
| open(path, 'wb') do |file| | |
| file << open(song_url).read | |
| end | |
| else | |
| puts "#{row[0]} not found" | |
| end | |
| end | |
| browser.close |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment