gildia_comics_crawler 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 72ddcf2cb680b72acf076be6e2e0281feaf82063
+  data.tar.gz: bddad7c5e780f9c404f4df509e4a1bf7b7beb323
+SHA512:
+  metadata.gz: ba5098722ed46e65111ce5f770f593411739f15a291853b90755247c6020a050ed8337a203c31250dec41ee23ee02754b6f337a1d19c7b578429f1ec990b5ad3
+  data.tar.gz: 82dd51629e8751f51dffa2515da4cebbabcffaffd7d548582d809d1c562f474b1006e09c9a3fe020ed091f77e71c4d17b74960d5671be67f78f9ecbc4f0d2434

data/.gitignore

@@ -0,0 +1,18 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+.idea/

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Jan Jędrychowski
+
+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 +1,25 @@
+# GildiaComicsCrawler
+
+komiks.gildia.pl crawler. It can crawl comic database (http://www.komiks.gildia.pl/komiksy)
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'gildia_comics_crawler'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install gildia_comics_crawler
+
+## Usage
+
+    require 'gildia_comics_crawler'
+
+    GildiaComicsCrawler::Crawler.new.crawl do |series|
+        ...
+    end

data/Rakefile

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

data/gildia_comics_crawler.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'gildia_comics_crawler/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "gildia_comics_crawler"
+  spec.version       = GildiaComicsCrawler::VERSION
+  spec.authors       = ["Jan Jędrychowski"]
+  spec.email         = ["jan@jedrychowski.org"]
+  spec.description   = "Crawler for downloading comics from komiks.gildia.pl"
+  spec.summary       = spec.description
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  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_runtime_dependency "nokogiri"
+end

data/lib/gildia_comics_crawler/comic_crawler.rb

@@ -0,0 +1,87 @@
+module GildiaComicsCrawler
+  class ComicCrawler
+    include Downloader
+
+    def initialize link
+      @link = link
+    end
+
+    def crawl
+      @noko = download(@link)
+      @data = {gildia_link: @downloader_uri}
+      @data[:gildia_sklep_link] = @noko.css('#product a.p').first[:href] rescue nil
+      @data[:cover] = @noko.css('.main-article-image').first[:src] rescue nil
+      elements = @noko.css('.widetext').children
+      @data[:title] = elements.css('h1').children.first.text
+
+      @data.merge! first_block_elements(elements)
+      @data.merge! second_block_elements(elements)
+
+      @data
+    end
+
+    private
+
+    FIRST_BLOCK_SECTIONS = {
+        "Scenariusz:" => :scenario,
+        "Rysunek:" => :drawing,
+        "Tłumaczenie:" => :translation
+    }
+
+    def first_block_elements elements
+      found_elements = []
+      elements.each do |el|
+        break if el.name == 'div' && !el[:class]
+        found_elements << el if el.name == 'text' || el.name == 'a'
+      end
+      extracted_data = found_elements.map(&:text).map(&:strip).reject { |t| t.empty? || t == ',' }
+      data = {}
+      current_section = nil
+      extracted_data.each do |text|
+        if (new_section=FIRST_BLOCK_SECTIONS[text])
+          current_section = new_section
+        else
+          data[current_section] ||= []
+          data[current_section] << text
+        end
+      end
+
+      data
+    end
+
+    SECOND_BLOCK_SECTIONS = {
+      "Tytuł oryginalny" => :origin_title,
+      "Wydawca oryginalny" => :origin_publisher,
+      "Rok wydania oryginału:" => :origin_publish_year,
+      "Liczba stron" => :pages_count,
+      "Oprawa" => :binding,
+      "Papier" => :paper,
+      "Druk" => :color,
+      "ISBN-13" => :isbn,
+      "Wydanie" => :edition,
+      "Cena z okładki" => :original_price
+    }
+
+    def second_block_elements elements
+      data = {}
+      extracted_data = elements.filter('div:not([class])')[1].children.map(&:text).map(&:strip).reject(&:empty?)
+      if extracted_data[0] == 'Wydawnictwo:'
+        data[:publisher] = extracted_data[1]
+        extracted_data.shift(2)
+      end
+      if extracted_data[0] =~ /^\d+\/\d+$/
+        month, year = extracted_data.shift.split('/')
+        data[:publish_date_month] = month
+        data[:publish_date_year] = year
+      end
+
+      extracted_data.each do |line|
+        attr, val = line.split(':', 2)
+        if(attr_sym=SECOND_BLOCK_SECTIONS[attr])
+          data[attr_sym] = val.strip
+        end
+      end
+      data
+    end
+  end
+end

data/lib/gildia_comics_crawler/comics_crawler.rb

@@ -0,0 +1,21 @@
+module GildiaComicsCrawler
+  class ComicsCrawler
+    include Downloader
+    def initialize base_url
+      @base_url = base_url
+    end
+
+    def all_comics
+      comics_list.map do |link|
+        ComicCrawler.new(link).crawl
+      end
+    end
+
+    def comics_list
+      download(@base_url).css('.CDgallery a').map do |link|
+        link[:href]
+      end
+    end
+  end
+
+end

data/lib/gildia_comics_crawler/crawler.rb

@@ -0,0 +1,10 @@
+module GildiaComicsCrawler
+  class Crawler
+    def crawl
+      SeriesCrawler.new.all_series.each do |series|
+        comics = ComicsCrawler.new(series[:link]).all_comics
+        yield series.merge(comics: comics)
+      end
+    end
+  end
+end

data/lib/gildia_comics_crawler/downloader.rb

@@ -0,0 +1,27 @@
+require 'nokogiri'
+require 'open-uri'
+
+module GildiaComicsCrawler
+  module Downloader
+    BASE_URI = 'http://www.komiks.gildia.pl/'
+
+    class Base
+      def initialize uri
+        uri = URI::join(BASE_URI, uri) unless uri.start_with?('http://')
+        @uri = uri
+      end
+
+      attr_accessor :uri
+
+      def download
+        Nokogiri::HTML(open(@uri))
+      end
+    end
+
+    def download uri
+      downloader = Base.new(uri)
+      @downloader_uri = downloader.uri.to_s
+      downloader.download
+    end
+  end
+end

data/lib/gildia_comics_crawler/series_crawler.rb

@@ -0,0 +1,30 @@
+module GildiaComicsCrawler
+  class SeriesCrawler
+    include Downloader
+    SERIES_BASE_URL = 'komiksy'
+
+    def all_series
+      find_pages.flat_map do |page|
+        series_from_page(page)
+      end
+    end
+
+    def series_from_page page
+      download(page).css('.long-list a').map do |serie_link|
+        {
+            name: serie_link.text,
+            link: serie_link[:href]
+        }
+      end
+    end
+
+    def find_pages
+      @pages ||= begin
+        download(SERIES_BASE_URL).css('.header-letters a').map do |letter|
+          letter[:href]
+        end
+      end
+    end
+
+  end
+end

data/lib/gildia_comics_crawler/version.rb

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

data/lib/gildia_comics_crawler.rb

@@ -0,0 +1,9 @@
+require "gildia_comics_crawler/version"
+require "gildia_comics_crawler/downloader"
+require "gildia_comics_crawler/series_crawler"
+require "gildia_comics_crawler/comic_crawler"
+require "gildia_comics_crawler/comics_crawler"
+require "gildia_comics_crawler/crawler"
+
+module GildiaComicsCrawler
+end

metadata

@@ -0,0 +1,99 @@
+--- !ruby/object:Gem::Specification
+name: gildia_comics_crawler
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Jan Jędrychowski
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-12-21 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Crawler for downloading comics from komiks.gildia.pl
+email:
+- jan@jedrychowski.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- gildia_comics_crawler.gemspec
+- lib/gildia_comics_crawler.rb
+- lib/gildia_comics_crawler/comic_crawler.rb
+- lib/gildia_comics_crawler/comics_crawler.rb
+- lib/gildia_comics_crawler/crawler.rb
+- lib/gildia_comics_crawler/downloader.rb
+- lib/gildia_comics_crawler/series_crawler.rb
+- lib/gildia_comics_crawler/version.rb
+homepage: ''
+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: 2.0.14
+signing_key: 
+specification_version: 4
+summary: Crawler for downloading comics from komiks.gildia.pl
+test_files: []