http://ssimas.blog.fc2.com/ の スレッドの本文を抽出する

study.rb

# -*- encoding: utf-8 -*-

require 'nokogiri'
require "open-uri"
require './SSparser.rb'
require './db_manager.rb'

# http://ssimas.blog.fc2.com/

#url = 'http://ssimas.blog.fc2.com/blog-entry-3218.html#more'
puts "input url"
url = gets

charset = nil
html = open(url) do |f|
  charset = f.charset
  f.read
end

thread = ''
doc =  Nokogiri::HTML.parse(html, nil, charset)
doc.xpath('//div[@class="ently_text"]')[0].text.split("\n").each do |v|
  break if v.include?("document.write")
  str = ''
  vvv = nil
  id = 0
  v.split("").each do |vv|
    if vv == 'D' and vvv =='I'
      id = 11
    end
    id -= 1
    if id == 0
      str << vv
      str << "__split__"
    else
      str << vv
    end
    vvv = vv
  end

  str.split("__split__").each do |v|
    break if v.include?("転載元：")
    matchA = v.match(/^\d+ ：.*：\d+\/\d+\/\d+\(.\) \d+:\d+:\d+.\d+ ID:........./)
    matchB = v.match(/\d+ ：.*：\d+\/\d+\/\d+\(.\) \d+:\d+:\d+.\d+ ID:.........$/)
    next if matchA
    if matchB
      thread << v[0..v.index(/\d+ ：.*：\d+\/\d+\/\d+\(.\) \d+:\d+:\d+.\d+ ID:.........$/)-1]
    else
      thread << v
    end
  end

end

#thread.split("  ").delete_if{|v|v==""}.each do |v|
#  p v
#  p "nil" if v.nil?
#end

ss = thread.split('  ').map!{|v|v.split("\r")}.flatten.delete_if{|v|v==""}
#puts ss

parser = SSparser.new

puts "puts or insert?"
output = gets.chomp

if output == "puts" or output == "p"
  puts parser.parse(ss).delete_if{|v|v[:name]!='春香'}
elsif output == "insert" or output == "i"
  db = DbManager.new
  db.insert "amami.db", parser.parse(ss).delete_if{|v|v[:name]!='春香'}
end