download images of one piece manga chapter from kissmanga

.gitignore

chapters

.versions.conf

ruby=ruby-2.1.0
ruby-gemset=one_piece
#ruby-gem-install=bundler rake
#ruby-bundle-install=true

Gemfile

# A sample Gemfile
source "https://rubygems.org"

gem 'pry'
gem 'nokogiri'
gem 'em-synchrony'
gem 'em-http-request'

Gemfile.lock

GEM
  remote: https://rubygems.org/
  specs:
    addressable (2.3.5)
    coderay (1.1.0)
    cookiejar (0.3.0)
    em-http-request (1.1.2)
      addressable (>= 2.3.4)
      cookiejar
      em-socksify (>= 0.3)
      eventmachine (>= 1.0.3)
      http_parser.rb (>= 0.6.0)
    em-socksify (0.3.0)
      eventmachine (>= 1.0.0.beta.4)
    em-synchrony (1.0.3)
      eventmachine (>= 1.0.0.beta.1)
    eventmachine (1.0.3)
    http_parser.rb (0.6.0)
    method_source (0.8.2)
    mini_portile (0.5.2)
    nokogiri (1.6.1)
      mini_portile (~> 0.5.0)
    pry (0.9.12.4)
      coderay (~> 1.0)
      method_source (~> 0.8)
      slop (~> 3.4)
    slop (3.4.7)

PLATFORMS
  ruby

DEPENDENCIES
  em-http-request
  em-synchrony
  nokogiri
  pry

loader.rb

#!/usr/bin/env ruby
require 'bundler/setup'

require 'open-uri'
require 'rss'
require 'fileutils'
require 'nokogiri'
require "em-synchrony"
require "em-synchrony/em-http"

RSS_URL = "http://kissmanga.com/RSS/Manga/One-Piece".freeze
DOWNLOAD_BASE = "./chapters"

def extract_chapter_image_urls chapter
  chapter = Nokogiri::HTML(chapter)
  chapter.search('div#divImage img').map{|e| e['src']}
end

def get_images_concurrent(urls, concurrency=5)
  image_data = nil
  EM.synchrony do
    # iterator will execute async blocks until completion, .each, .inject also work!
    results = EM::Synchrony::Iterator.new(urls, concurrency).map do |url, iter|
      # fire async requests, on completion advance the iterator
      http = EventMachine::HttpRequest.new(url).aget
      http.callback { iter.return(http) }
      http.errback { iter.return(http) }
    end

    image_data = results # all completed requests
    EventMachine.stop
  end
  image_data.map{|image|
    [ image.response,
      image.req.path.split('/').last
    ]
  }
end

case ARGV.size
when 1
  first2load = ARGV.first.to_i
when 2
  first2load = ARGV[0].to_i
  last2load = ARGV[1].to_i
else
  p "wtf"
  exit 1
end

open(RSS_URL) do |rss|
  feed = RSS::Parser.parse(rss)
  feed.items.each do |item|
    number = item.title.match(/\d{3}/)[0].to_i
    next if (last2load && number >= last2load)
    exit if number < first2load
    title = item.title.gsub(/^One Piece /,'')
    chapter_path = "#{DOWNLOAD_BASE}/#{title}"
    next if File.exists?(chapter_path)
    FileUtils.mkdir_p(chapter_path)
    #open(URI.encode(item.link)) do |chapter|
    #  IO.write("#{chapter_path}/images.urls", extract_chapter_image_urls(chapter).join("\n"))
    #end
    open(URI.encode(item.link)) do |chapter|
      images = get_images_concurrent(extract_chapter_image_urls(chapter))
      images.each do |data,filename|
        IO.write("#{chapter_path}/#{filename}", data)
      end
    end
    p "Chapter #{title} downloaded!"
  end
end