orumin/get.rb

## get.rb
#!/usr/bin/env ruby
# encoding: utf-8

#
# Web Archiveからスクレイピングして小説家になろうのテキストダウンロードと同じ形式でテキストパクってくるヤツ
#

require 'nokogiri'
require 'open-uri'

for i in 1..124 do
  ans = []
  title = nil

  begin
    if 10 <= i and i <= 12 then
      url = "http://web.archive.org/web/20130708184241/http://ncode.syosetu.com/n7145bl/#{i}"
    else
      url = "http://web.archive.org/web/20131127132412/http://ncode.syosetu.com/n7145bl/#{i}"
    end
    x = ""
    open(url).each{ |d|
      x += d.clone
    }
    doc = Nokogiri.HTML(x)
  rescue
    doc = Nokogiri.HTML("<html><body><p>abort</p></body></html>")
    ans[ans.length] = "Nokogiri aborted"
  end

  begin
    title_element = doc.xpath("//title").inner_text
    title = title_element.sub(/^.* - /,"")
  rescue
    title = "Unknown"
  end

  begin
    ans.push("#{title}\n\n")
    doc.xpath("//div[@class='novel_view']").each do |node|
      next if node.children.inner_text == nil
      node.search('rb').each do |rb| rb.replace('|' + rb.inner_text) end
      node.search('rt').each do |rt| rt.replace(rt.inner_text) end
      node.search('rp').each do |rp|
        rp.replace("《") if rp.inner_text == "("
        rp.replace("》") if rp.inner_text == ")"
      end
      node.search('ruby').each do |ruby| ruby.replace(ruby.inner_text) end
      aa = node.inner_text.clone
      ans.push(aa.clone)
    end
    File.open("#{i} #{title}.txt", 'w') { |file|
      file.write ans.join("")
    }
  rescue
    p "something wrong"
  end
end
	#!/usr/bin/env ruby
	# encoding: utf-8

	#
	# Web Archiveからスクレイピングして小説家になろうのテキストダウンロードと同じ形式でテキストパクってくるヤツ
	#

	require 'nokogiri'
	require 'open-uri'

	for i in 1..124 do
	ans = []
	title = nil

	begin
	if 10 <= i and i <= 12 then
	url = "http://web.archive.org/web/20130708184241/http://ncode.syosetu.com/n7145bl/#{i}"
	else
	url = "http://web.archive.org/web/20131127132412/http://ncode.syosetu.com/n7145bl/#{i}"
	end
	x = ""
	open(url).each{ \|d\|
	x += d.clone
	}
	doc = Nokogiri.HTML(x)
	rescue
	doc = Nokogiri.HTML("<html><body><p>abort</p></body></html>")
	ans[ans.length] = "Nokogiri aborted"
	end

	begin
	title_element = doc.xpath("//title").inner_text
	title = title_element.sub(/^.* - /,"")
	rescue
	title = "Unknown"
	end

	begin
	ans.push("#{title}\n\n")
	doc.xpath("//div[@class='novel_view']").each do \|node\|
	next if node.children.inner_text == nil
	node.search('rb').each do \|rb\| rb.replace('\|' + rb.inner_text) end
	node.search('rt').each do \|rt\| rt.replace(rt.inner_text) end
	node.search('rp').each do \|rp\|
	rp.replace("《") if rp.inner_text == "("
	rp.replace("》") if rp.inner_text == ")"
	end
	node.search('ruby').each do \|ruby\| ruby.replace(ruby.inner_text) end
	aa = node.inner_text.clone
	ans.push(aa.clone)
	end
	File.open("#{i} #{title}.txt", 'w') { \|file\|
	file.write ans.join("")
	}
	rescue
	p "something wrong"
	end
	end