Download manga at http://manhua.178.com/wangxiangxueshenghui/

down_manga.rb

#!/usr/bin/env ruby
# encoding=utf-8

#
# Usage: ruby down_manga.rb folder_to_hold_manga image_index_url
# folder_to_hold_manga is a non-existing folder in current directory to save images.
# image_index_url is the index for manga, like: http://manhua.178.com/wangxiangxueshenghui/
#
# Need ruby 1.9 and hpricot gem.
#

major, subver, minor = RUBY_VERSION.split('.')

if major < '2' && subver < '9'
  puts "You need ruby 1.9 and up to run this command"
  exit 1
end

require 'open-uri'
require 'hpricot'
require 'fileutils'

image_base = "http://manhua.178.com/imgs/"

if ARGV.size != 2 || ARGV[1].index("http://") != 0
  puts "Usage: #{$0} FOLDER_NAME WEB_URL"
  puts "FOLDER_NAME is a non-existing folder in current directory to save images."
  puts "WEB_URL is the index for manga, like: http://manhua.178.com/wangxiangxueshenghui/"
  exit 1
elsif File.exists?(ARGV[0])
  puts "#{ARGV[0]} exists, please use another folder name."
  exit 1
else
  if FileUtils.mkdir(ARGV[0])
    main_uri = ARGV[1]
    main_uri += '/' unless (main_uri.rindex('/') + 1) == main_uri.size
    FileUtils.cd(ARGV[0])
    begin
      doc = Hpricot(open main_uri)
    rescue OpenURI::HTTPError => e
      puts "Failed to open web uri.", e.message
      exit 1
    rescue StandardError => e
      puts "Unknown error.", e.message
      exit 1
    end
    vol_uri = []

    doc.search('//.cartoon_online_border/ul/li/a').each do |link|
      vol_uri << [link.inner_text, main_uri + File.basename(link['href'])]
    end
    
    main_dir = FileUtils.pwd
    
    vol_uri.each do |dir, uri|
      puts
      puts "Downloading #{dir}"
      puts
      
      # Goto sub folder
      FileUtils.mkdir(dir)
      FileUtils.cd(dir)
      page = (open uri).read
      page.scan(/g_max_pic_count\s*=\s*(\d+)/)
      image_count = $1
      page.scan(/var\s+pages\s*=\s*'\[([^\]]+)\]'/)
      raw_str = $1
      raw_str.split(",").each do |str|
        next if str.nil?
        str.strip!
        next if str.size < 1
        part = str.gsub(/\\u(\h{4})/) {
          [$1.to_i(16)].pack('U')
        }.gsub(/(\\|")/, '')
        print "Downloading #{File.basename(part)}.."
        if system("wget", '-q', image_base + part)
          puts "Done!"
        else
          puts "Failed!\nFailed to download #{File.basename(part)} in #{dir}\n"
        end
      end
      # Go back to main folder
      FileUtils.cd(main_dir)
    end
  else
    puts "Error make directory in current diretory. \nDoes this directory writable?"
    exit 1
  end
end