gumonji's diary downloader

download_gumonji_diaries.rb

#!/bin/ruby

require 'open-uri'

user_id = 1168
pages = (1..16)

url_prefix = "http://www.gumonji.net/cgi-bin/"
url_no_page_num = url_prefix + "diary_list.cgi?order=id&user_id=" + user_id.to_s + "&page="

pages.each {|page|
  url = url_no_page_num + page.to_s
  open(url) {|f|
    f.each_line {|line|
      if /(diary\.cgi\?id=)(\d*)/ =~ line
        dairy_url = url_prefix + $1 + $2
        p dairy_url
        in_file = open(dairy_url)
        out_file = open("diary/diary" + $2 + ".html", "w")
        out_file.write(in_file.read)
        in_file.close
        out_file.close
      end
    }
  }
}