Yupoo 图片备份工具

yupoo_backup.rb

# coding: UTF-8
#
# Yupoo 照片备份工具
# 此工具不需要API，直接就能备份你的照片信息，下载后以图片 + 一个文本文件的方式存放
# 备份包括内容：
# 原图，标题，说明，Tag，当然有 Exif 信息
#
# Jason Lee <[email protected]>
# http://huacnlee.com
# 2011-01-28
#
# 如何使用
# 安装 Ruby 1.9.2
# 安装 Rubygems
# $ sudo apt-get install ruby1.9 rubygems
# 
# 然后
# $ gem install nokogiri
# $ gem install mechanize
#
# 运行
# ruby main.rb
#
require "nokogiri"
require "open-uri"
require "mechanize"

BASE_URL = 'http://www.yupoo.com'
# 你的个性域名 如: http://huacn.yupoo.com/ 就是 huacn
CUSTOM_LOGIN = "huacn"
# 你的 Yupoo 帐号
USERNAME = "[email protected]"
# 你的 Yupoo 密码
PASSWORD = "123123"
# 图片文件保存位置，./photos/ 就是在当前目录的 photos 里面
SAVE_PATH = "./photos/"
# 开始年, 这个采集是根据年份分别采集的
START_YEAR = 2006
# 结束年
END_YEAR = 2011

@agent = WWW::Mechanize.new
@agent.set_proxy('172.28.150.20', '8080')
page = @agent.get("http://www.yupoo.com/account/login/")
form = page.forms[1]
form.username = USERNAME
form.password = PASSWORD
form.checkboxes[0].checked=true
page_home = form.submit

def save_photo(year,id,title,tags,description,file_url)  
  description = description.gsub(/\n/,"").gsub(/\r/,"")
  dir = "#{SAVE_PATH}#{year}/"
  if not File.directory?(dir)
    Dir.mkdir(dir)
  end
  open("#{dir}/#{id}.jpg","w") do |f|
    f.write(open(file_url).read)
  end
  open("#{dir}/#{id}.desc","w") do |f|
    f.puts "id: #{id}"
    f.puts "title: #{title}"
    f.puts "tags: #{tags}"
    f.puts "description: #{description}"
  end
  puts "saved.".rjust(80)
end

def get_photo(url,year)
  puts ""
  puts "-" * 80
  puts "#{url}".rjust(80)
  originUrl = "#{url}zoom/original/"
  
  doc = Nokogiri::HTML(open(url))
  id = url.match(/\d+/).to_s
  puts "#{id.rjust(13)} : #{id}"
  title = doc.css(".title-display").text.strip
  puts "#{'Title'.rjust(13)} : #{title}" 
  tags = doc.css("#thetags ul li a.Tag").collect { |t| t.text }.join(",")  
  puts "#{'Tags'.rjust(13)} : #{tags}"
  description = doc.css(".des-display").text.strip
  puts "#{'Description'.rjust(13)} : #{description}"
  doc_origin = Nokogiri::HTML(@agent.get(originUrl).body)
  file_url = doc_origin.css("img.Photo").attr("src")  
  puts "#{'File Url'.rjust(13)} : #{file_url}"
  save_photo(year,id,title,tags,description,file_url)
end

def get_photos(year)
  puts ""
  puts "=" * 80
  puts "=" * 80
  puts "#{year} - P1".rjust(80)
  url = "http://www.yupoo.com/photos/#{CUSTOM_LOGIN}/archives/date-taken/#{year}/list/"
  doc = Nokogiri::HTML(open(url))
  doc.css("#archiveList ul li a").each do |item|
    photo_url = "#{BASE_URL}#{item.attr("href")}"  
    get_photo(photo_url,year)
  end
  
  max_page = doc.css(".pages a.end").text.to_i
  2.upto(max_page) do |page|
    puts "=" * 80
    puts "=" * 80
    puts "#{year} - P#{page}".rjust(80)
    url = "http://www.yupoo.com/photos/#{CUSTOM_LOGIN}/archives/date-taken/#{year}/list/page#{page}"
    doc = Nokogiri::HTML(open(url))
    doc.css("#archiveList ul li a").each do |item|
      photo_url = "#{BASE_URL}#{item.attr("href")}"  
      get_photo(photo_url,year)
    end
  end
  
end


START_YEAR.upto(END_YEAR).each do |year|
  get_photos(year)
end

windows xp下该怎么用？