Created
August 10, 2012 13:19
-
-
Save skord/3314153 to your computer and use it in GitHub Desktop.
4chan board sync
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
| Bundler.require(:default) | |
| require 'open-uri' | |
| require 'net/http' | |
| require "em-synchrony" | |
| require "em-synchrony/em-http" | |
| require 'em-synchrony/fiber_iterator' | |
| class KisamaDownloader | |
| attr_reader :url, :live_thread, :images | |
| def initialize(url) | |
| @url = url | |
| @live_thread = thread_alive? | |
| if thread_alive? | |
| @images = get_image_urls | |
| else | |
| @images = [] | |
| end | |
| end | |
| def response | |
| uri = URI.parse(@url) | |
| response = Net::HTTP.get_response(uri) | |
| end | |
| def thread_alive? | |
| if response.code == "200" | |
| true | |
| else | |
| false | |
| end | |
| end | |
| def get_image_urls | |
| Nokogiri::HTML(open(@url)).css('.fileText a').collect {|x| x['href']} | |
| end | |
| def host | |
| URI(@url).host | |
| end | |
| def path | |
| URI(@url).path | |
| end | |
| def local_files | |
| directory_inventory | |
| end | |
| def images_to_sync | |
| to_sync = [] | |
| local_file_basenames = local_files.collect {|x| File.basename(x)} | |
| @images.each do |image| | |
| unless local_file_basenames.include?(File.basename(image)) | |
| to_sync << image | |
| end | |
| end | |
| to_sync | |
| end | |
| def async_download | |
| itscopy = images_to_sync.length | |
| if images_to_sync.length > 0 | |
| EM.synchrony do | |
| concurrency = 4 | |
| urls = images_to_sync | |
| EM::Synchrony::FiberIterator.new(urls, concurrency).each do |url| | |
| resp = EventMachine::HttpRequest.new(url).get | |
| File.open("#{directory}/#{File.basename(url)}",'w') {|f| f.write(resp.response)} | |
| end | |
| EventMachine.stop | |
| end | |
| end | |
| itscopy | |
| end | |
| def post | |
| match_array = @url.scan(/res\/(\d{1,})/) | |
| unless match_array.nil? | |
| return match_array[0][0] | |
| end | |
| end | |
| def board | |
| match_array = @url.scan(/4chan\.org\/(\w{1,})/) | |
| unless match_array.nil? | |
| return match_array[0][0] | |
| end | |
| end | |
| def directory_check | |
| unless Dir.exists?('public') | |
| Dir.mkdir('public') | |
| end | |
| unless Dir.exists?('public/4chan') | |
| Dir.mkdir('public/4chan') | |
| end | |
| unless Dir.exists?("public/4chan/#{board}") | |
| Dir.mkdir("public/4chan/#{board}") | |
| end | |
| unless Dir.exists?("public/4chan/#{board}/#{post}") | |
| Dir.mkdir("public/4chan/#{board}/#{post}") | |
| end | |
| Dir.exists?("public/4chan/#{board}/#{post}") | |
| end | |
| def directory | |
| directory_check | |
| "public/4chan/#{board}/#{post}" | |
| end | |
| def directory_inventory | |
| directory_check | |
| Dir.glob("#{directory}/*") | |
| end | |
| end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment