Last active
September 15, 2015 02:22
-
-
Save ytera/55ae106764d2dec57c11 to your computer and use it in GitHub Desktop.
読書メーターに登録されている本の読者数を取得するスクリプト
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- encoding: utf-8 -*- | |
require 'mechanize' | |
require 'nokogiri' | |
require 'kconv' | |
require 'fileutils' | |
# ハッシュ | |
module HashInitializable | |
def initialize(attributes={}) | |
attributes.each do |name,value| | |
send("#{name}=",value) | |
end | |
end | |
end | |
class HashInitializableStruct | |
def self.new(*arguments) | |
struct = Struct.new(*arguments) | |
struct.send(:include, HashInitializable) | |
struct | |
end | |
end | |
properties = [:id,:name,:reader_num] | |
Book = HashInitializableStruct.new(*properties) | |
books = Hash.new | |
# メイン | |
agent = Mechanize.new | |
agent.user_agent = 'Mac Safari' | |
f_in = open(ARGV[0], "r") | |
for a in f_in | |
book_url = 'http://bookmeter.com/b/' + a | |
page = agent.get(book_url) | |
doc = Nokogiri::HTML(page.content.toutf8) | |
node = doc.xpath("//*[@id=\"side_left\"]/div/div/div/div/div/span").first | |
reader_num = node.text | |
name = doc.title | |
puts name.split("感想")[0]+reader_num | |
book_property = {id: a, name: name.split("感想")[0], reader_num: reader_num.split("登録")[0]} | |
book = Book.new(book_property) | |
books.store(book.id,book) | |
books | |
end | |
# ファイル出力 | |
day = Time.now | |
out_name = day.strftime("%m%d%H%M") + ".csv" | |
f_out = open(out_name, "w") | |
f_out.printf("%s,%s/%s,%s:%s:%s,",day.year,day.month,day.day,day.hour,day.min,day.sec) | |
books.each_value do |book| | |
f_out.printf("%s,",book.reader_num.split("登録")[0]) | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment