TMCIT Exam archives downaloder

sangi.rb

#!/usr/bin/env ruby
# -*- coding: utf-8 -*-
# ++ TMCIT Exam Archives Downloader ++
# ++ I don't like regular expression. ++
# !! At your own risk !!

# License
# Copyright (c) 2012 atpons
#
# 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.

require "mechanize"
require "uri"

module Atpons
  class Downloader
    def initialize(*args)
      @agent = Mechanize.new
      @site = args[0]
      @index_uri = args[1] || args[0]
      @index = @agent.get(@index_uri)
      @dlfiles = []
    end

    def get_links; nil; end

    def download!(*args)
      save_to = args[0]
      #proc = Proc.new
      @dlfiles.each do |f|
        p uri = URI.join(@site, f)
        aget = if save_to
                 @agent.get uri, save_to
               else
                 @agent.get uri
               end
        aget.save
      end
    end
  end

  class TMCITDownloader < Downloader
    SITE_URI = "http://www.metro-cit.ac.jp/examination/"
    SITE_INDEX = "http://www.metro-cit.ac.jp/examination/honka_haihu.html"
    YEAR_RANGE = 2008..2012
    PDF_TYPE = %w(shoronbun mondai kaito)

    # 酢よ、これが性器表現だ
    year = YEAR_RANGE.to_a.join('|')
    subject = "[a-z]+"
    type = PDF_TYPE.join("|")
    RE_PARSE_FILENAME = /^(#{year})(?:_(#{subject}))?_(#{type})\.pdf$/

    ParsedFilename = Struct.new("ParsedFilename", :year, :subject, :type)
    
    def initialize
      @files = []
      super SITE_URI, SITE_INDEX
    end

    def get_links
      @agent.page.links_with(:href => /pdf\Z/).each do |link|
        target_uri = URI.join(SITE_URI, link.uri.to_s)
        #aget = @agent.get(target_uri)

        b = link.uri.to_s
        fetch = target_uri
        bb = b.gsub("pdf/","")
        @dlfiles << b
        #aget.save
      end
    end

    def download
      unless @dlfiles.size != 0
        nil
      end
    end

    def download!
      mkdir_p
      get_links
      super
      @dlfiles
    end

    def TMCITDownloader.download
      @instance = new
      @instance.download!
    end

    #正規表現要らない
    def mkdir_p
      puts "[*]Making directory..."
      YEAR_RANGE.each do |year|
        PDF_TYPE.each do |type|
          FileUtils.mkdir_p "#{year}/#{type}"
        end
      end
    end

    def parse_filename(str)
      str =~ RE_PARSE_FILENAME
      year = $1
      subject = $2
      type = $3
      
      ParsedFilename.new(year, subject, type)
    end
  end
end


if __FILE__ == $0
  include Atpons
  TMCITDownloader.download
end