manga-crawler 0.0.1

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in manga_crawler.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Thiago Rocha
+
+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 +1,29 @@
+# MangaCrawler
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'manga_crawler'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install manga_crawler
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it
+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 new Pull Request

data/Rakefile

@@ -0,0 +1,10 @@
+require "bundler/gem_tasks"
+require 'rake/testtask'
+
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/*_test.rb'
+  test.verbose = true
+end
+
+task :default => :test

data/lib/manga-crawler.rb

@@ -0,0 +1,6 @@
+require "manga-crawler/version"
+require "manga-crawler/crawler"
+
+module MangaCrawler
+  # Your code goes here...
+end

data/lib/manga-crawler/crawler.rb

@@ -0,0 +1,106 @@
+require 'nokogiri'
+require 'open-uri'
+
+module MangaCrawler
+  class Crawler
+
+    # Returns an array of pairs. The first position contains the 
+    # manga name and the second position the manga link
+    # Params:
+    # +index_link+:: string with the url containing the index of all mangas
+    # +css_path+:: string of a css path format of the links you want to collect
+    # +css_pagination+:: string with the css path to the next page link
+    # +html_field+:: simbol of the field that has the link
+    def get_mangas index_link, css_path, css_pagination, html_field
+
+      result = Array.new
+
+      html_index = Nokogiri::HTML(open(index_link))
+
+      #find all content that matches with the css_path
+      links = html_index.css(css_path)
+
+      #find all content from the anchor nodes found in last search
+      links.each do |anchor|
+        result.push([anchor.content, anchor[html_field]])
+      end
+
+      #TODO
+      #if has a css_pagination, use recursion
+      #example: result += get_mangas next_link, css_path, css_pagination
+
+      return result
+    end
+
+    # Returns the chapters information of a manga. It uses the same
+    # logic of get_mangas.
+    # Params:
+    # +manga_link+:: string with the url containing the manga_link
+    # +css_path+:: string of the css path format of the links you want to collect
+    # +css_pagination+:: string with the css path to the next page link
+    # +html_field+:: simbol of the field that has the link 
+    def get_chapters manga_link, css_path, css_pagination, html_field
+      #TODO
+      #uses the same logic of get_mangas
+      return get_mangas manga_link, css_path, css_pagination, html_field
+    end
+
+    # Returns the direct links of all pages from a specific chapter. It uses two
+    # methods: 'get_pages_links_from_chapter' and 'get_image_from_page'.
+    # Params:
+    # +chapter_link+:: string with the chapter
+    # +css_pages_path+:: string with the CSS path to the pages links
+    # +pages_html_field+:: HTML field with the page link value
+    # +css_image_path+:: CSS path to the image
+    # +image_html_field+:: HTML field with the direct's image url
+    # +url_base+:: Site´s base url
+    def get_pages chapter_link, css_pages_path, pages_html_field, css_image_path, image_html_field, url_base
+      
+      result = Array.new
+
+      pages_links = get_pages_links_from_chapter url_base + chapter_link, css_pages_path, pages_html_field
+
+      pages_links.each do |page|
+        result.push( get_image_from_page url_base + page[1], css_image_path, image_html_field )
+      end
+
+      return result
+
+    end
+
+    # Returns all pages HTML links from a chapter
+    # Params:
+    # +chapter_link+:: Link of the chapter
+    # +css_path+:: CSS path to the block with the pages links
+    # +html_field+:: HTML field that contains the url
+    def get_pages_links_from_chapter chapter_link, css_path, html_field
+
+      result = Array.new
+
+      chapter_page = Nokogiri::HTML(open(chapter_link))
+
+      pages_links = chapter_page.css(css_path)
+
+      pages_links.each do |option|
+        result.push([option.content, option[html_field]])
+      end
+
+      return result
+    end
+
+    # Returns the image's direct url of a manga page
+    # Params:
+    # +page_link+:: HTML page who contains the image
+    # +css_path+:: CSS path to the image
+    # +html_field+:: field that contains the url
+    def get_image_from_page page_link, css_path, html_field
+
+      html_image = Nokogiri::HTML(open(page_link))
+
+      image_link = html_image.at_css(css_path)[html_field]
+
+      return image_link
+    end
+  end
+end
+

data/lib/manga-crawler/version.rb

@@ -0,0 +1,3 @@
+module MangaCrawler
+  VERSION = "0.0.1"
+end

data/manga-crawler.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'manga-crawler/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "manga-crawler"
+  spec.version       = MangaCrawler::VERSION
+  spec.authors       = ["Thiago Rocha"]
+  spec.email         = ["kimobr@gmail.com"]
+  spec.description   = %q{ A gem that collects mangas from websites}
+  spec.summary       = %q{ Retrieve basic manga information }
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "nokogiri"
+end

data/test/lib/manga-crawler/crawler_test.rb

@@ -0,0 +1,57 @@
+require "test_helper"
+
+describe MangaCrawler::Crawler do
+
+  crawler = MangaCrawler::Crawler.new
+
+  it "must retrieve mangas" do
+    
+    sample_index = File.open("test/samples/index-page.html")
+    css_path = "a"
+    html_field = :href
+    
+    mangas = crawler.get_mangas sample_index, css_path, nil, html_field
+
+    mangas.must_equal [ ["Naruto", "/first-manga"], 
+                        ["Bleach", "/second-manga"], 
+                        ["One Piece", "/third-manga"] ]
+  end
+
+  it "must retrieve chapters" do
+    
+    sample_manga_page = File.open("test/samples/manga-page.html")
+    css_path = "a"
+    html_field = :href
+
+    chapters = crawler.get_chapters sample_manga_page, css_path, nil, html_field
+
+    chapters.must_equal [ ["Chapter 1", "/first-manga/1"], 
+                          ["Chapter 2", "/second-manga/2"], 
+                          ["Chapter 3", "/third-manga/3"] ]
+  end
+
+  it "must retrieve a direct image link from a page" do
+    
+    sample_image_page = File.open("test/samples/image-page.html")
+    css_path = "#img"
+    html_field = :src
+
+    image = crawler.get_image_from_page sample_image_page, css_path, html_field
+
+    image.must_equal "image.jpg"
+  end
+
+  it "must retrieve all pages links from a chapter" do
+
+    sample_image_page = File.open("test/samples/image-page.html")
+    css_path = "#pageMenu option"
+    html_field = :value
+    
+    pages_links = crawler.get_pages_links_from_chapter sample_image_page, css_path, html_field
+
+    pages_links.must_equal [ ["1", "/first-manga/1/1"],
+                             ["2", "/first-manga/1/2"], 
+                             ["3", "/first-manga/1/3"] ]
+
+  end
+end

data/test/lib/manga-crawler/version_test.rb

@@ -0,0 +1,8 @@
+require "test_helper"
+
+describe MangaCrawler do
+  it "must have a version" do
+    version = MangaCrawler::VERSION
+    version.wont_be_nil
+  end
+end

data/test/samples/image-page.html

@@ -0,0 +1,21 @@
+<html>
+  <head>
+    <title>A sample manga website</title>
+  </head>
+  <body>
+
+    <div id="selectpage">
+      <select id="pageMenu" name="pageMenu">
+        <option value="/first-manga/1/1" selected="selected">1</option>
+        <option value="/first-manga/1/2">2</option>
+        <option value="/first-manga/1/3">3</option>
+      </select>
+    </div>
+
+    <div id="imgholder">
+      <a href="/first-manga/1/2">
+        <img id="img" src="image.jpg" alt="An image" name="img"/>
+      </a>
+    </div>
+  </body>
+</html>

data/test/samples/index-page.html

@@ -0,0 +1,14 @@
+<html>
+  <head>
+    <title>A sample manga website</title>
+  </head>
+  <body>
+    <div class="simple_div">
+      <ul class="simple_div">
+        <li><a href="/first-manga">Naruto</a></li>
+        <li><a href="/second-manga">Bleach</a></li>
+        <li><a href="/third-manga">One Piece</a></li>
+      </ul>
+    </div>
+  </body>
+</html>

data/test/samples/manga-page.html

@@ -0,0 +1,38 @@
+<html>
+  <head>
+    <title>A sample manga website</title>
+  </head>
+  <body>
+    <div id="chapterlist">
+      <table id="listing">
+        
+        <tr class="table_head">
+          <th class="leftgap">Chapter Name</th>
+          <th>Date Added</th>
+        </tr>
+      
+        <tr>
+          <td>
+            <div class="chico_manga"></div>
+            <a href="/first-manga/1">Chapter 1</a> : First chapter </td>
+          <td>09/09/2011</td>
+        </tr>
+      
+        <tr>
+          <td>
+            <div class="chico_manga"></div>
+            <a href="/second-manga/2">Chapter 2</a> : Second chapter</td>
+          <td>09/09/2011</td>
+        </tr>
+
+        <tr>
+          <td>
+            <div class="chico_manga"></div>
+            <a href="/third-manga/3">Chapter 3</a> : Third chapter</td>
+          <td>09/09/2011</td>
+        </tr>
+        
+      </table>
+    </div>
+  </body>
+</html>

data/test/test_helper.rb

@@ -0,0 +1,3 @@
+require 'minitest/autorun'
+require 'minitest/pride'
+require File.expand_path('../../lib/manga-crawler.rb', __FILE__)

metadata

@@ -0,0 +1,117 @@
+--- !ruby/object:Gem::Specification
+name: manga-crawler
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Thiago Rocha
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-04-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: ! ' A gem that collects mangas from websites'
+email:
+- kimobr@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/manga-crawler.rb
+- lib/manga-crawler/crawler.rb
+- lib/manga-crawler/version.rb
+- manga-crawler.gemspec
+- test/lib/manga-crawler/crawler_test.rb
+- test/lib/manga-crawler/version_test.rb
+- test/samples/image-page.html
+- test/samples/image.jpg
+- test/samples/index-page.html
+- test/samples/manga-page.html
+- test/test_helper.rb
+homepage: ''
+licenses:
+- MIT
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.24
+signing_key: 
+specification_version: 3
+summary: Retrieve basic manga information
+test_files:
+- test/lib/manga-crawler/crawler_test.rb
+- test/lib/manga-crawler/version_test.rb
+- test/samples/image-page.html
+- test/samples/image.jpg
+- test/samples/index-page.html
+- test/samples/manga-page.html
+- test/test_helper.rb