yamd 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: af2596743157ae9a1eeb8b4f0d485b662de4dbf9
+  data.tar.gz: 0c678459bf2ae8f667aec151f775d4add6188634
+SHA512:
+  metadata.gz: 1488d9483222638626b7b538f2566f0a38074cb0940477f3e76ad74f9d17ba3ec39a4dba59f5a352e17bbae583b682708c9603b72f1d9360cabe5d162ddcccae
+  data.tar.gz: 77fb539ec5ea0e2d84f0148b3e0b8a1132b4549a9eeae3ea4032d7b958707fee2bebb3d325b509935dff537c8ece42229019e77fcbd9f212df5c1424b2f1f3ae

data/bin/yamd

@@ -0,0 +1,23 @@
+#!/usr/bin/ruby
+
+require 'yamd/mangahere'
+require 'yamd/mangafox'
+
+unless ARGV.size > 0
+  puts 'USAGE: yamd <manga main page url>'
+  puts 'EXAMPLE: yamd http://www.mangahere.com/manga/asagao_to_kase_san/'
+  puts 'Support mangahere and mangafox sites so far.'
+  exit
+end
+
+manga_main_page_url = ARGV[0]
+if /mangafox/.match(manga_main_page_url)
+  manga = MangafoxCrawler.new(manga_main_page_url)
+elsif /mangahere/.match(manga_main_page_url)
+  manga = MangahereCrawler.new(manga_main_page_url)
+else
+  puts "The argument (#{manga_main_page_url}) doesn't seem to be a URL of one of the supported sites."
+end
+
+ImageDownloader.new.download(manga)
+

data/lib/yamd.rb

@@ -0,0 +1,124 @@
+require 'nokogiri'
+require 'open-uri'
+require 'addressable/uri'
+require 'pathname'
+
+class PageCrawler
+  attr_reader :custom_data, :url, :parsed_html, :number, :chapter
+
+  def initialize(custom_data, parsed_html, number, chapter)
+    @custom_data = custom_data
+    @url = custom_data[:url]
+    @parsed_html = parsed_html
+    @number = number
+    @chapter = chapter
+  end
+
+  def image_url
+    fail 'This method is abstract and have to be defined in a subclass.'
+  end
+end
+
+class ChapterCrawler
+  attr_reader :custom_data, :url, :parsed_html, :number, :manga
+
+  def initialize(custom_data, chapter_page, number, manga)
+    @custom_data = custom_data
+    @url = custom_data[:url]
+    @number = number
+    @parsed_html = chapter_page
+    @manga = manga
+  end
+
+  def pages_info
+    fail 'This method is abstract and have to be defined in a subclass.'
+  end
+
+  def name
+    fail 'This method is abstract and have to be defined in a subclass.'
+  end
+
+  def pages
+    Enumerator.new do | yielder |
+      number = 1
+      pages_info.each do | page_info |
+        parsed_html = Nokogiri::HTML(open(page_info[:url]))
+        yielder.yield self.class.page_class.new(page_info, parsed_html, number, self)
+        number += 1
+      end
+    end
+  end
+
+  def self.page_class
+    fail 'This method is abstract and have to be defined in a subclass.'
+  end
+end
+
+class MangaCrawler
+  attr_accessor :url, :parsed_html
+
+  def initialize(manga_main_page_url)
+    @url = manga_main_page_url
+    @parsed_html = Nokogiri::HTML(open(manga_main_page_url))
+  end
+
+  def chapters_info
+    fail 'This method is abstract and have to be defined in a subclass.'
+  end
+
+  def chapters
+    Enumerator.new do | yielder |
+      number = 1
+      chapters_info.each do | chapter_info |
+        page = Nokogiri::HTML(open(chapter_info[:url]))
+        yielder.yield self.class.chapter_class.new(chapter_info, page, number, self)
+        number += 1
+      end
+    end
+  end
+
+  def name
+    fail 'This method is abstract and have to be defined in a subclass.'
+  end
+
+  def self.chapter_class
+    fail 'This method is abstract and have to be defined in a subclass.'
+  end
+end
+
+class ImageDownloader
+  def initialize(base_dir = Dir.pwd)
+    @base_dir = base_dir
+  end
+
+  def download(manga)
+    manga_dir = Pathname.new(@base_dir).join(manga.name + '/')
+    if manga_dir.exist?
+      p 'Manga dir exists. Skipping each existing chapter. If the script was forced to stop the last downloaded chapter can be incomplete. Remove it to be downloaded again.'
+    else
+      Dir.mkdir(manga_dir.to_s)
+    end
+    manga.chapters.each do | chapter |
+      chapter_dir = manga_dir.join(chapter.name + '/')
+      unless chapter_dir.exist?
+        Dir.mkdir(chapter_dir.to_s)
+        chapter.pages.each do | page |
+          page_name = self.class.format_page_name(page, chapter, manga)
+          page_abs_path = chapter_dir.join(page_name).to_s
+          File.open(page_abs_path, 'wb') do | f |
+            open(page.image_url, 'rb') do | image |
+              f.write(image.read)
+            end
+          end
+        end
+      end # end "unless chapter_dir.exist?"
+    end
+  end
+
+  def self.format_page_name(page, chapter, manga)
+    # TODO: usar log10 de chapter.pages.size para determinar padding de zeros
+    page_path = Addressable::URI.parse(page.image_url).path
+    format("%04d", page.number) + File.extname(page_path)
+  end
+end
+

data/lib/yamd/mangafox.rb

@@ -0,0 +1,56 @@
+require 'yamd'
+require 'addressable/uri'
+
+class MangafoxPage < PageCrawler
+  def image_url
+    @parsed_html.at_css('#viewer a img')['src']
+  end
+end
+
+class MangafoxChapter < ChapterCrawler
+  def self.page_class
+    MangafoxPage
+  end
+
+  def pages_info
+    # there's no need of an lazy enumerator here, no IO action is taken
+    page_options = @parsed_html.at_css('.prev_page + div > select').css('option')
+    pages_number = page_options.map { | option | option['value'].to_i }.max
+    
+    chapter_base_url = Addressable::URI.parse(self.url)
+    chapter_base_path, _ = Pathname.new(chapter_base_url.path).split
+    page_urls = (1..pages_number).to_a.map do | i |
+      chapter_base_url.path = chapter_base_path.join("#{i}.html").to_s
+      { url: chapter_base_url.to_s }
+    end
+
+    page_urls
+  end
+
+  def name
+    @custom_data[:name]
+  end
+end
+
+class MangafoxCrawler < MangaCrawler
+  def chapters_info
+    @parsed_html.css('#chapters ul li div').reverse.map do | chapter_link |
+      name = chapter_link.at_css('a.tips').text
+      # the real chapter name not always exist
+      span_with_real_name = chapter_link.at_css('a.tips + span')
+      name = name + ' - ' + span_with_real_name.text if span_with_real_name
+      { name: name,
+        url: chapter_link.at_css('a.tips')['href']
+      }
+    end
+  end
+
+  def self.chapter_class
+    MangafoxChapter
+  end
+
+  def name
+    @parsed_html.at_css('h1').text.match(/(.+) Manga/)[1]
+  end
+end
+

data/lib/yamd/mangahere.rb

@@ -0,0 +1,46 @@
+require 'yamd'
+
+class MangaherePage < PageCrawler
+  def image_url
+    @parsed_html.at_css('#viewer a img')['src']
+  end
+end
+
+class MangahereChapter < ChapterCrawler
+  def self.page_class
+    MangaherePage
+  end
+
+  def pages_info
+    # there's no need of an lazy enumerator here, no IO action is taken
+    page_options = @parsed_html.at_css('.prew_page + select').css('option')
+    page_urls = []
+    page_options.each do | option |
+      page_urls << { url: option['value'] }
+    end
+    page_urls
+  end
+
+  def name
+    @custom_data[:name]
+  end
+end
+
+class MangahereCrawler < MangaCrawler
+  def self.chapter_class
+    MangahereChapter
+  end
+
+  def chapters_info
+    @parsed_html.css('.detail_list ul li a').reverse.map do | chapter_link |
+        { name: chapter_link.text.strip,
+          url: chapter_link['href']
+        }
+    end
+  end
+
+  def name
+    @parsed_html.at_css('h1').text.strip
+  end
+end
+

metadata

@@ -0,0 +1,79 @@
+--- !ruby/object:Gem::Specification
+name: yamd
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Henrique Becker
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-07-25 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.5'
+- !ruby/object:Gem::Dependency
+  name: addressable
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.3'
+description: 'This gem offers: classes to subclass and create a manga site crawler;
+  a dowloader to use with these classes; some site-specific scripts.'
+email: henriquebecker91@gmail.com
+executables:
+- yamd
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/yamd/mangafox.rb
+- lib/yamd/mangahere.rb
+- lib/yamd.rb
+- bin/yamd
+homepage: http://rubygems.org/gems/yamd
+licenses:
+- Public domain
+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: 2.0.3
+signing_key: 
+specification_version: 4
+summary: YAMD (Yet Another Manga Downloader) - A lazy interface for writting manga
+  downloaders
+test_files: []
+has_rdoc: true