manga-downloadr 1.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 1b1a496ff7a0146d994b4e53490c869344a032da
+  data.tar.gz: c333cb615114dbde3956a162ea56d332829550c8
+SHA512:
+  metadata.gz: 7eac6dc32977973b667c30935e31645946ac083b2de60fe5d1397539b8605158e0d43a745f742ffe7ce99c17d7793b983115b1a77b07ee3d380519a0c0bf5826
+  data.tar.gz: b3f7538dd773bdea1f308bf26b6274cf89255cbd56e9e9644f64ca3327ba677ff51be17a06e23aafa4abcfcbc7fc86ef9328cca99333e1a465b3e55252daa5f7

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2014 Fabio Akita
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,32 @@
+# Manga Downloadr
+
+I just bought a new Kindle Paperwhite and so happens it's the perfect form factor
+to read good old, black and white, mangas.
+
+So I decided to automate the process of fetching manga images from MangaReader.net,
+optimize and compile them into PDF files that fit the Kindle resolution.
+
+## Installation
+
+Just install with:
+
+```
+gem install manga-downloadr
+```
+
+## Usage
+
+And then execute:
+
+    $ manga-downloader -n berserk -u http://www.mangareader.net/96/berserk.html -d /MyDocuments/MyMangas
+
+If there's any interruption (bad network) you can run the same command line again and it will resume from
+where it was interrupted before.
+
+## Contributing
+
+1. Fork it ( https://github.com/akitaonrails/manga-downloadr/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+

data/bin/manga-downloadr

@@ -0,0 +1,59 @@
+#!/usr/bin/env ruby
+$LOAD_PATH.unshift File.join(File.dirname(__FILE__), '..', 'lib')
+require 'optparse'
+
+options = {}
+option_parser = OptionParser.new do |opts|
+  opts.banner = "Usage: manga-downloadr [options]"
+
+  opts.on("-u URL", "--url URL",
+    "Full MangaReader.net manga homepage URL - required") do |v|
+    options[:url] = v
+  end
+
+  opts.on("-n NAME", "--name NAME",
+    "slug to be used for the sub-folder to store all manga files - required") do |n|
+    options[:name] = n
+  end
+
+  opts.on("-d DIRECTORY", "--directory DIRECTORY",
+    "main folder where all mangas will be stored - required") do |d|
+    options[:directory] = d
+  end
+
+  opts.on("-h", "--help", "Show this message") do
+    puts opts
+    exit
+  end
+end
+
+begin
+  ARGV << "-h" if ARGV.empty?
+  option_parser.parse!(ARGV)
+rescue OptionParser::ParseError
+  $stderr.print "Error: " + $! + "\n"
+  exit
+end
+
+require 'manga-downloadr'
+generator = MangaDownloadr::Workflow.create(options[:url], options[:name], manga_root: options[:directory])
+unless generator.state?(:chapter_urls)
+  puts "Massive parallel scanning of all chapters "
+  generator.fetch_chapter_urls!
+end
+unless generator.state?(:page_urls)
+  puts "\nMassive parallel scanning of all pages "
+  generator.fetch_page_urls!
+end
+unless generator.state?(:image_urls)
+  puts "\nMassive parallel scanning of all images "
+  generator.fetch_image_urls!
+  puts "\nTotal page links found: #{generator.chapter_pages_count}"
+end
+unless generator.state?(:images)
+  puts "\nMassive parallel download of all page images "
+  generator.fetch_images!
+end
+puts "\nCompiling all images into PDF volumes "
+generator.compile_ebooks!
+puts "\nProcess finished."

data/lib/manga-downloadr.rb

@@ -0,0 +1,177 @@
+require 'rubygems'
+require 'bundler/setup'
+
+require 'nokogiri'
+require 'typhoeus'
+require 'fileutils'
+require 'rmagick'
+require 'prawn'
+require 'fastimage'
+require 'open-uri'
+require 'yaml'
+
+module MangaDownloadr
+  ImageData = Struct.new(:folder, :filename, :url)
+
+  class Workflow
+    attr_accessor :manga_root_url, :manga_root, :manga_root_folder, :manga_name, :hydra_concurrency
+    attr_accessor :chapter_list, :chapter_pages, :chapter_images, :download_links, :chapter_pages_count
+    attr_accessor :manga_title, :pages_per_volume, :page_size
+    attr_accessor :processing_state
+
+    def initialize(root_url, manga_name, options = {})
+      self.manga_root_url    = root_url
+      self.manga_root        = options[:manga_root] || "/vagrant/tmp/mangareader/"
+      self.manga_root_folder = File.join(manga_root, manga_name)
+      self.manga_name        = manga_name
+
+      self.hydra_concurrency = options[:hydra_concurrency] || 100
+
+      self.chapter_pages    = {}
+      self.chapter_images   = {}
+
+      self.pages_per_volume = options[:pages_per_volume] || 250
+      self.page_size        = options[:page_size] || [600, 800]
+
+      self.processing_state = []
+    end
+
+    def fetch_chapter_urls!
+      doc = Nokogiri::HTML(open(manga_root_url))
+
+      self.chapter_list = doc.css("#listing a").map { |l| l['href']}
+      self.manga_title  = doc.css("#mangaproperties h1").first.text
+
+      current_state :chapter_urls
+    end
+
+    def fetch_page_urls!
+      hydra = Typhoeus::Hydra.new(max_concurrency: hydra_concurrency)
+      chapter_list.each do |chapter_link|
+        begin
+          request = Typhoeus::Request.new "http://www.mangareader.net#{chapter_link}"
+          request.on_complete do |response|
+            chapter_doc = Nokogiri::HTML(response.body)
+            pages = chapter_doc.css('#selectpage #pageMenu option')
+            chapter_pages.merge!(chapter_link => pages.map { |p| p['value'] })
+            print '.'
+          end
+          hydra.queue request
+        rescue => e
+          puts e
+        end
+      end
+      hydra.run
+
+      self.chapter_pages_count = chapter_pages.values.inject(0) { |total, list| total += list.size }
+      current_state :page_urls
+    end
+
+    def fetch_image_urls!
+      hydra = Typhoeus::Hydra.new(max_concurrency: hydra_concurrency)
+      chapter_list.each do |chapter_key|
+        chapter_pages[chapter_key].each do |page_link|
+          begin
+            request = Typhoeus::Request.new "http://www.mangareader.net#{page_link}"
+            request.on_complete do |response|
+              chapter_doc = Nokogiri::HTML(response.body)
+              image       = chapter_doc.css('#img').first
+              tokens      = image['alt'].match("^(.*?)\s\-\s(.*?)$")
+              extension   = File.extname(URI.parse(image['src']).path)
+
+              chapter_images.merge!(chapter_key => []) if chapter_images[chapter_key].nil?
+              chapter_images[chapter_key] << ImageData.new( tokens[1], "#{tokens[2]}#{extension}", image['src'] )
+              print '.'
+            end
+            hydra.queue request
+          rescue => e
+            puts e
+          end
+        end
+      end
+      hydra.run
+
+      current_state :image_urls
+    end
+
+    def fetch_images!
+      hydra = Typhoeus::Hydra.new(max_concurrency: hydra_concurrency)
+      chapter_list.each_with_index do |chapter_key, chapter_index|
+        chapter_images[chapter_key].each do |file|
+          begin
+            downloaded_filename = File.join(manga_root_folder, file.folder, file.filename)
+            next if File.exists?(downloaded_filename) # effectively resumes the download list without re-downloading everything
+            request = Typhoeus::Request.new file.url
+            request.on_complete do |response|
+              # download
+              FileUtils.mkdir_p(File.join(manga_root_folder, file.folder))
+              File.open(downloaded_filename, "wb+") { |f| f.write response.body }
+
+              # resize
+              image = Magick::Image.read( downloaded_filename ).first
+              resized = image.resize_to_fit(600, 800)
+              resized.write( downloaded_filename ) { self.quality = 50 }
+
+              print '.'
+              GC.start # to avoid a leak too big (ImageMagick is notorious for that, specially on resizes)
+            end
+            hydra.queue request
+          rescue => e
+            puts e
+          end
+        end
+      end
+      hydra.run
+
+      current_state :images
+    end
+
+    def compile_ebooks!
+      folders = Dir[manga_root_folder + "/*/"].sort_by { |element| ary = element.split(" ").last.to_i }
+      self.download_links = folders.inject([]) do |list, folder|
+        list += Dir[folder + "*.*"].sort_by { |element| ary = element.split(" ").last.to_i }
+      end
+
+      # concatenating PDF files (250 pages per volume)
+      chapter_number = 0
+      while !download_links.empty?
+        chapter_number += 1
+        pdf_file = File.join(manga_root_folder, "#{manga_title} #{chapter_number}.pdf")
+        list = download_links.slice!(0..pages_per_volume)
+        Prawn::Document.generate(pdf_file, page_size: page_size) do |pdf|
+          list.each do |image_file|
+            begin
+              pdf.image image_file, position: :center, vposition: :center
+            rescue => e
+              puts "Error in #{image_file} - #{e}"
+            end
+          end
+        end
+        print '.'
+      end
+
+      current_state :ebooks
+    end
+
+    def state?(state)
+      self.processing_state.include?(state)
+    end
+
+    private def current_state(state)
+      self.processing_state << state
+      MangaDownloadr::Workflow.serialize(self)
+    end
+
+    class << self
+      def serialize(obj)
+        File.open("/tmp/#{obj.manga_name}.yaml", 'w') {|f| f.write(YAML::dump(obj)) }
+      end
+
+      def create(root_url, manga_name, options = {})
+        dump_file_name = "/tmp/#{manga_name}.yaml"
+        return YAML::load(File.read(dump_file_name)) if File.exists?(dump_file_name)
+        MangaDownloadr::Workflow.new(root_url, manga_name, options)
+      end
+    end
+  end
+end

data/lib/manga-downloadr/version.rb

@@ -0,0 +1,3 @@
+module MangaDownloadr
+  VERSION = "1.0.1"
+end

metadata

@@ -0,0 +1,120 @@
+--- !ruby/object:Gem::Specification
+name: manga-downloadr
+version: !ruby/object:Gem::Version
+  version: 1.0.1
+platform: ruby
+authors:
+- AkitaOnRails
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-12-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: typhoeus
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.6'
+- !ruby/object:Gem::Dependency
+  name: rmagick
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.13'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.13'
+- !ruby/object:Gem::Dependency
+  name: prawn
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: fastimage
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+description: downloads any manga from MangaReader.net
+email: boss@akitaonrails.com
+executables:
+- manga-downloadr
+extensions: []
+extra_rdoc_files: []
+files:
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/manga-downloadr
+- lib/manga-downloadr.rb
+- lib/manga-downloadr/version.rb
+homepage: http://github.com/akitaonrails/manga-downloadr
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.3
+signing_key: 
+specification_version: 4
+summary: downloads and compile to a Kindle optimized manga in PDF
+test_files: []