taaze 0.0.4 → 0.0.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 3d5eb57aef00d5fdf5a258dde8edc152ac8a2aa4
-  data.tar.gz: 8a9d617755a2dc8d808bcef771ac01e19450025a
+  metadata.gz: 503d21509d28f6411ef50ff8b1ffba0811340922
+  data.tar.gz: ecdce9af22a15b483e625ac71f986b3a405619c1
 SHA512:
-  metadata.gz: e6a308cc4787de2f21ba5f5afaffeae17475d6ed820d8a8cb67138cc6bc25e8a840041915dacd8acb6426cfd168b1fc71797c4a307dccb8d5dff9e90cad17d4e
-  data.tar.gz: 29ab262a8f2971f55e6f828f6e6cfec3dfb3efaf2af657d666eae0b4c0b86b8565e9cd54fe90310a97953d1c26ba92575ad595a1c1d178ae4eec148b3a11fd81
+  metadata.gz: 5b197a82f8aed1e829b999339127b49f142d16c60b284d86bed60052333bae8d9879ec237e0a98f94d1772605ecdbab1cf9abb21adae84f845b62925751e3158
+  data.tar.gz: e3845845ca6638c0e512f285a2d4c0d02d5d40e770a0939f05fa52a55e4051acb4fb6a4caae352b4c075e4853cd411036a30694875e05780b2a6e51a777c258d

data/.gitignore

@@ -0,0 +1,80 @@
+# Created by https://www.gitignore.io/api/ruby,osx,vim
+
+### Ruby ###
+*.gem
+*.rbc
+/.config
+/coverage/
+/InstalledFiles
+/pkg/
+/spec/reports/
+/spec/examples.txt
+/test/tmp/
+/test/version_tmp/
+/tmp/
+Gemfile.lock
+
+## Specific to RubyMotion:
+.dat*
+.repl_history
+build/
+
+## VCR
+/spec/fixures/vcr_cassettes
+
+## Documentation cache and generated files:
+/.yardoc/
+/_yardoc/
+/doc/
+/rdoc/
+
+## Environment normalisation:
+/.bundle/
+/vendor/bundle
+/lib/bundler/man/
+
+# for a library or gem, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# Gemfile.lock
+# .ruby-version
+# .ruby-gemset
+
+# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
+.rvmrc
+
+
+### OSX ###
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+
+### Vim ###
+[._]*.s[a-w][a-z]
+[._]s[a-w][a-z]
+*.un~
+Session.vim
+.netrwhist
+*~

data/.travis.yml

@@ -0,0 +1,8 @@
+language: ruby
+rvm:
+    - ruby-head
+    - ruby-2.1.0
+    - jruby-head
+branches:
+    only:
+    - master

data/Gemfile

@@ -0,0 +1,11 @@
+source 'https://rubygems.org'
+
+group :test do
+  gem 'rake'
+end
+
+gem 'nokogiri'
+gem 'minitest'
+gem 'json'
+gem 'vcr'
+gem 'webmock'

data/LICENSE

@@ -0,0 +1,22 @@
+The MIT License (MIT)
+
+Copyright (c) 2015 BUEZE
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+

data/README.md

@@ -0,0 +1,56 @@
+# taaze [![Build Status](https://travis-ci.org/BUEZE/taaze.svg?branch=master)](https://travis-ci.org/BUEZE/taaze)
+
+---
+Taaze is a light package wrote by Ruby. It easy to use for getting comments or collections from online bookstore [Taaze | 讀冊生活](http://www.taaze.tw/index.html).
+
+### How To Get Started
+Install by Ruby gem [Taaze](https://rubygems.org/gems/taaze)
+
+`gem install taaze`
+
+
+### Requirements
+- [Nokogiri](http://nokogiri.org) - for parsing html use
+- [JSON](http://ruby-doc.org/stdlib-2.0.0/libdoc/json/rdoc/JSON.html) - parsing json data
+
+`$ bundle install`
+
+### Usage
+This gem may be used as a command line utility or called from code
+
+#### How to get ID
+##### User's comment
+- You can get user list at [冊格子](http://www.taaze.tw/zekea_index.html)
+- In every user's personal page , you can get his or her ID from URL
+	 - For Example :
+      - http://www.taaze.tw/container_zekeaclt_view.html?ci=13313301
+      - 'ci=' is User ID
+- Like the user id, you can also get any books' ID from the URL
+- And there are 3 argument for use
+	- --comments : get all comments for the user
+	- --collections : get all book collection for the user
+	- --tags : get all tags of the book
+- And add yaml path where you want to store
+	- --output [file_path]
+- Finally the Taaze will return yaml format file 
+
+### CLI
+
+`taaze --comments [user_id] --output [file_path]` OR
+
+`taaze --collections [user_id] --output [file_path]` OR
+
+`taaze --tags [book_id] --output [file_path]`
+
+### For Example
+      
+`taaze --comments 12522728 --output ./comments.yml`
+
+`taaze --collections 12522728 --output ./collections.yml`
+
+`taaze --tags 11100763435 --output ./tags.yml`
+
+
+### Output Sample
+
+![example.jpg](example.jpg)

data/Rakefile

@@ -0,0 +1,8 @@
+require 'rake/testtask'
+
+task default: [:spec]
+
+desc 'Run specs'
+Rake::TestTask.new(:spec) do |t|
+  t.pattern = 'spec/*_spec.rb'
+end

data/lib/taaze.rb

@@ -0,0 +1,3 @@
+require_relative 'taaze/collections.rb'
+require_relative 'taaze/comments.rb'
+require_relative 'taaze/tags.rb'

data/lib/taaze/collections.rb

@@ -0,0 +1,56 @@
+require 'json'
+require 'open-uri'
+require 'date'
+
+module Taaze
+  # This class get the user personal page as an input
+  # return a hash of user's collections information
+  # For example, with user's url: http://www.taaze.tw/container_zekeaclt_view.html?ci=12522728
+  # here's the user's collections of books: http://www.taaze.tw/container_zekeaclt_view.html?ci=12522728&cp=1
+  # Sampel output (plz remove them after passing the test):
+  # [
+  #   {"title"=>"村上收音機", "book_url"=>"http://www.taaze.tw/sing.html?pid=11100635522"}
+  #   {"title"=>"尋找漩渦貓的方法", "book_url"=>"http://www.taaze.tw/sing.html?pid=11100210251"}
+  #   and so on ...
+  # ]
+  class TaazeCollections
+    USERS_URL = 'http://www.taaze.tw/container_zekeaclt_view.html?ci='
+    API_URL = 'http://www.taaze.tw/beta/zekeacltBooksDataAgent.jsp?custId='
+    BOOK_URL = 'http://www.taaze.tw/sing.html?pid='
+
+    def initialize(user_id)
+      parse_html(user_id)
+    end
+
+    # Return a hash of user's collections
+    def collections
+      @collections ||= extract_books
+    end
+
+    private
+
+    # Parse the html of the url page.
+    def parse_html(user_id)
+      url = API_URL + user_id
+      first_doc = JSON.parse(open(url).read)
+      totalsize = first_doc['totalsize']
+
+      url = API_URL + user_id + '&startNum=0&endNum=' + totalsize.to_s
+      @doc = JSON.parse(open(url).read)['result1']
+    end
+
+    # Return the books in the format specified in spec.
+    def extract_books
+      booklist = []
+      if @doc.count != 0
+        @doc.each do |book_data|
+          book = {}
+          book['title'] = book_data['titleMain']
+          book['book_url'] = BOOK_URL + book_data['prodId']
+          booklist << book
+        end
+      end
+      booklist
+    end
+  end
+end

data/lib/taaze/comments.rb

@@ -0,0 +1,120 @@
+require 'nokogiri'
+require 'open-uri'
+require 'date'
+require 'json'
+require 'net/http'
+
+# Module Taaze
+module Taaze
+  # This class get the user personal page as an input
+  # return a hash of user's collections information
+  # For example, with user's url: http://www.taaze.tw/container_zekeaclt_view.html?ci=12522728
+  # here's the user's comments of books: http://www.taaze.tw/container_zekeaclt_view.html?ci=12522728&cp=2
+  # Sampel output (plz remove them after passing the test):
+  class TaazeComments
+    USERS_URL = 'http://www.taaze.tw/container_zekeaclt_view.html?ci='
+    MAIN_URL = 'http://www.taaze.tw/container_zekeaclt_view.html?'
+    API_URL = 'http://www.taaze.tw/beta/zekeaCommentDataAgent.jsp?custId='
+    BOOK_URL = 'http://www.taaze.tw/sing.html?pid='
+
+    def initialize(user_id)
+      user_id = numeric?(user_id) ? user_id.to_s : user_id
+      parse_html(user_id)
+    end
+
+    # Return a hash of user's comments
+    def comments
+      @comments_found
+    end
+
+    private
+
+    # Check if it is a integer
+    def numeric?(obj)
+      obj.to_s.match(/\A[+-]?\d+?(\.\d+)?\Z/) == nil? ? false : true
+    end
+
+    # Parse the html of the url page.
+    def split_url(url)
+      str = split_get_last(split_get_last(url, '/'), '?')
+      str = split_get_last(str, '&', -1)
+      str
+    end
+
+    # split string and get last
+    # index for
+    # -1 -> return all array
+    #  0 -> return last obj in array
+    #  >=1 -> return obj on array[index]
+    def split_get_last(str_to_split, character, index = 0)
+      arrtmp = str_to_split.split(character)
+      if index == -1
+        arrtmp
+      else
+        index = index == 0 ? arrtmp.length - 1 : index
+        strtmp = arrtmp[index]
+        strtmp
+      end
+    end
+
+    # Parse the html of the url page.
+    def parse_html(user_id)
+      url = API_URL + user_id.to_s + '&startNum=0&endNum=0'
+      # first test and get comments num for the user
+      first_doc = JSON.parse(url_get_html(url))
+      total_num = first_doc['totalsize']
+
+      url = API_URL + user_id.to_s + '&startNum=0&endNum=' + total_num
+      # mainDoc is the all json date for the user's all comment
+      main_doc = JSON.parse(url_get_html(url))
+      extract_comments(main_doc['result1'], user_id)
+    end
+
+    # Send url to get response
+    def url_get_html(url_str)
+      url = URI.parse(URI.encode(url_str)) # first get total size
+      req = Net::HTTP::Get.new(url.to_s)
+      res = Net::HTTP.start(url.host, url.port) { |http| http.request(req) }
+      res.body
+    end
+
+    # Return the comments in the format specified in spec.
+    def extract_comments(content, user_id)
+      # Json format~
+      # "content":"勇氣就是熱誠，來自於我們對自己工作的自信心；.....",
+      # "title":"",
+      # "status":"C",
+      # "stars":"5",
+      # "prodId":"11100597685",
+      # "titleMain":"行銷之神原一平全集(精裝版)",
+      # "orgProdId":"11100597685",
+      # "pkNo":"1000243977",
+      # "mdf_time":"2015/10/15",
+      # "crt_time":"2015/10/15"
+      #
+      # orgProdId -> bookID -> 11100597685
+      # title -> book title
+      # content -> comment
+      # comment_url
+      # pkNo -> comment ID ->13313301
+      #
+      # http://www.taaze.tw/container_zekeaclt_view.html?co=1000238964&ci=12522728&cp=3
+      # co->comment ci->user
+      data_arr = []
+      if content
+        content.each do |cmtItem|
+          data_hash_sub = Hash.new {}
+          data_hash_sub['title'] = cmtItem['titleMain']
+          data_hash_sub['comment'] = cmtItem['content']
+          data_hash_sub['book_url'] = BOOK_URL + cmtItem['orgProdId']
+          url = MAIN_URL + 'co=' + cmtItem['pkNo'] + '&ci=' + user_id + '&cp=3'
+          data_hash_sub['comment_url'] = url
+          data_arr.push(data_hash_sub)
+        end
+      else
+        data_arr = []
+      end
+      @comments_found ||= data_arr
+    end
+  end
+end

data/lib/taaze/tags.rb

@@ -0,0 +1,38 @@
+require 'open-uri'
+require 'nokogiri'
+
+module Taaze
+  # This class get the product id as an input
+  # return a list of tags
+  # Sample input with  product id : 11100763252
+  # Sample output ['轉型正義', '白色恐怖', '社會科學', '臺灣民主運動']
+
+  class TaazeBooktags
+    BOOKS_URL = 'http://www.taaze.tw/sing.html?pid='
+
+    def initialize(book_id)
+      parse_html(book_id)
+    end
+
+    # Return a list of book's tags
+    def tags
+      @tags ||= extract_tags
+    end
+
+    private
+
+    # parse the html
+    def parse_html(book_id)
+      url = BOOKS_URL + book_id
+      @document = Nokogiri::HTML(open(url))
+    end
+
+    def extract_tags
+      tags = []
+      @document.xpath('//a[@class="tag"]').each do |t|
+        tags << t.text
+      end
+      tags
+    end
+  end
+end

data/lib/taaze/version.rb

@@ -0,0 +1,5 @@
+# Versioning
+module Taaze
+  VERSION = '0.0.5'
+  DATE = '2015-10-25'
+end

data/spec/collections_spec.rb

@@ -0,0 +1,32 @@
+require 'yaml'
+require 'minitest/autorun'
+require 'vcr'
+require 'webmock/minitest'
+require_relative '../lib/taaze.rb'
+
+USER_ID = %w(12522728 13193872)
+collections_from_file = YAML.load(File.read('./spec/fixures/collections.yml'))
+
+VCR.configure do |config|
+  config.cassette_library_dir = 'spec/fixures/vcr_cassettes'
+  config.hook_into :webmock
+end
+
+VCR.use_cassette('collections') do
+  USER_ID.each do |user_id|
+    collections_found = Taaze::TaazeCollections.new(user_id).collections
+
+    describe "Get all the collections with specific user's id" do
+      it 'has the right number of collections' do
+        collections_found.size.must_equal collections_from_file[user_id].size
+      end
+
+      collections_found.map do |book|
+        it 'finds book in the test collection' do
+          exist = collections_from_file[user_id].include? book
+          [book, exist].must_equal [book, true]
+        end
+      end
+    end
+  end
+end

data/spec/comments_spec.rb

@@ -0,0 +1,32 @@
+require 'yaml'
+require 'minitest/autorun'
+require 'vcr'
+require 'webmock/minitest'
+require_relative '../lib/taaze.rb'
+
+USER_ID = %w(12522728 13193872)
+comments_from_file = YAML.load(File.read('./spec/fixures/comments.yml'))
+
+VCR.configure do |config|
+  config.cassette_library_dir = 'spec/fixures/vcr_cassettes'
+  config.hook_into :webmock
+end
+
+VCR.use_cassette('comments') do
+  USER_ID.each do |user_id|
+    comments_found = Taaze::TaazeComments.new(user_id).comments
+
+    describe "Get all the comments with specific user's id" do
+      it 'has the right number of comments' do
+        comments_found.size.must_equal comments_from_file[user_id].size
+      end
+
+      comments_found.map do |comment|
+        it 'finds comments in the test comments' do
+          exist = comments_from_file[user_id].include? comment
+          [comment, exist].must_equal [comment, true]
+        end
+      end
+    end
+  end
+end

data/spec/fixures/collections.yml

@@ -0,0 +1,95 @@
+---
+'12522728':
+- title: '村上收音機'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100635522'
+- title: '尋找漩渦貓的方法'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100210251'
+- title: '張愛玲的世界'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100030671'
+- title: '拜訪糖果阿姨'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100653796'
+- title: 'A夢'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100732992'
+- title: '河流'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100683568'
+- title: '紅樓夢校注彩畫本（1－3冊合售）'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100161589'
+- title: '傾城之戀【張愛玲典藏新版】'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100228548'
+- title: '金烏'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100677389'
+- title: '臺灣成長小說選（增訂版）'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100649825'
+- title: '靈魂的領地：國民散文讀本 '
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100653909'
+- title: '懸崖上的花園：太平洋戰爭時期上海文學場域（1942-1945）'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100672028'
+- title: '九重葛與美少年'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100657709'
+- title: '春雪：豐饒之海四部曲（1）'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100034168'
+- title: '魯迅小說集'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100067679'
+- title: '波赫士（1－4冊合售合售）'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100125593'
+- title: '奇萊前書'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100067730'
+- title: '半生緣【張愛玲典藏新版】'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100192438'
+- title: '瓊美卡隨想錄（散文）'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100616297'
+- title: '犄角'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100617464'
+- title: '疾病的隱喻 '
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100625913'
+- title: '古都'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100268249'
+- title: '觀看的方式'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100238376'
+- title: '臺灣成長小說選'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100035125'
+- title: '晨讀10分鐘：青春無敵早點詩：中學生新詩選'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100631660'
+- title: '屏息的文明'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100034203'
+- title: '雲和'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100034334'
+- title: '海風野火花'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100249859'
+- title: '你的聲音充滿時間'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100276696'
+- title: '離與苦：戰爭的延續'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100254818'
+- title: '少女維特'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100241234'
+- title: '搜索者'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100067568'
+- title: '浮生草'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100591888'
+- title: '溫莎墓園日記（小說）'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100617237'
+- title: '漫長的告別'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100210749'
+- title: '雙月記'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100236244'
+- title: '愛情的盡頭'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100210189'
+- title: '我們在此相遇'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100154779'
+- title: '月球姓氏（聯合文學經典版）'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100220368'
+- title: '小團圓'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100192439'
+- title: '瑪德蓮'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100596747'
+'13193872':
+- title: '大賣場裡的人類學家：用人文科學搞懂消費者，解決最棘手的商業問題'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100707843'
+- title: '看不見的城市'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100175133'
+- title: '演算法統治世界'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100710575'
+- title: '從0到1：打開世界運作的未知祕密，在意想不到之處發現價值'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100720260'
+- title: '為社會而設計'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100713612'

data/spec/fixures/comments.yml

@@ -0,0 +1,47 @@
+---
+'12522728':
+- title: '張愛玲的世界'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100030671'
+  comment: '書中所收，尤其是王禎和〈張愛玲在台灣〉一文，珍貴且真摯。'
+  comment_url: 'http://www.taaze.tw/container_zekeaclt_view.html?co=1000238964&ci=12522728&cp=3'
+- title: '小團圓'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100192439'
+  comment: '祖奶奶晚期風格，誠實、枯寂又暴烈。'
+  comment_url: 'http://www.taaze.tw/container_zekeaclt_view.html?co=1000238963&ci=12522728&cp=3'
+- title: '村上收音機（3）：喜歡吃沙拉的獅子'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100644311'
+  comment: '第一集到第三集都很好看，雋永且富於生趣的小品，有如爽口的下酒菜！'
+  comment_url: 'http://www.taaze.tw/container_zekeaclt_view.html?co=1000238962&ci=12522728&cp=3'
+- title: '村上收音機（2）：大蕪菁、難挑的酪梨'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100635526'
+  comment: '第一集到第三集都很好看，雋永且富於生趣的小品，有如爽口的下酒菜！'
+  comment_url: 'http://www.taaze.tw/container_zekeaclt_view.html?co=1000238961&ci=12522728&cp=3'
+- title: '村上收音機'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100635522'
+  comment: '第一集到第三集都很好看，雋永且富於生趣的小品，有如爽口的下酒菜！'
+  comment_url: 'http://www.taaze.tw/container_zekeaclt_view.html?co=1000238960&ci=12522728&cp=3'
+- title: '尋找漩渦貓的方法'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100210251'
+  comment: '貓控大叔的異國生活誌，充滿了自以為是的趣味感，十分適合自認為有點怪怪的人（咦）。'
+  comment_url: 'http://www.taaze.tw/container_zekeaclt_view.html?co=1000238959&ci=12522728&cp=3'
+- title: '拜訪糖果阿姨'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100653796'
+  comment: '那些終於灰心或終於原諒的情感角落，發出被記憶篩過的，淡而暖的光。'
+  comment_url: 'http://www.taaze.tw/container_zekeaclt_view.html?co=1000224332&ci=12522728&cp=3'
+- title: 'A夢'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100732992'
+  comment: '鮮活聯繫新詩小傳統與當代文化，夭矯複雜如深情的孫悟空。'
+  comment_url: 'http://www.taaze.tw/container_zekeaclt_view.html?co=1000224330&ci=12522728&cp=3'
+- title: '河流'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100683568'
+  comment: '城市的女漫遊者，寫邊緣，寫冷淡，寫不被看見或被拋擲的。'
+  comment_url: 'http://www.taaze.tw/container_zekeaclt_view.html?co=1000224331&ci=12522728&cp=3'
+- title: '紅樓夢校注彩畫本（1－3冊合售）'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100161589'
+  comment: '此書要什麼有什麼，纏綿悱惻有之，狗皮倒灶有之，詩情畫意有之，醜態怪狀有之，不可能有厭煩的時候。'
+  comment_url: 'http://www.taaze.tw/container_zekeaclt_view.html?co=1000213998&ci=12522728&cp=3'
+- title: '傾城之戀【張愛玲典藏新版】'
+  book_url: 'http://www.taaze.tw/sing.html?pid=11100228548'
+  comment: "張愛玲《傾城之戀》（應是舊版《第一爐香》，現已絕版）。最感官化的小說家，最斑斕的視覺，蒙太奇的敘事，張愛玲的「色彩狂」令人在閱讀時總會想像那電影般的畫面。\n"
+  comment_url: 'http://www.taaze.tw/container_zekeaclt_view.html?co=1000211000&ci=12522728&cp=3'
+'13193872': ''

data/spec/fixures/tags.yml

@@ -0,0 +1,16 @@
+---
+'11100763435':
+- '文化研究'
+- '社會科學'
+- '台灣史地'
+- '中文書'
+- '人文史地'
+'11100714084':
+- '建議國家高層讀一下'
+'11303096752': ''
+'11100745134':
+- '旅遊'
+- '單車'
+- '台灣歷史'
+- '打狗'
+- '高雄'

data/spec/tags_spec.rb

@@ -0,0 +1,31 @@
+require 'yaml'
+require 'minitest/autorun'
+require 'vcr'
+require 'webmock/minitest'
+require_relative '../lib/taaze.rb'
+
+BOOK_ID = %w(11100763435 11100745134 11100714084 11303096752)
+tags_from_file = YAML.load(File.read('./spec/fixures/tags.yml'))
+
+VCR.configure do |config|
+  config.cassette_library_dir = 'spec/fixures/vcr_cassettes'
+  config.hook_into :webmock
+end
+
+VCR.use_cassette('tags') do
+  BOOK_ID.each do |book_id|
+    tags_found = Taaze::TaazeBooktags.new(book_id).tags
+    describe "Get all the tags with specific book's id" do
+      it 'has the right number of tags' do
+        tags_found.size.must_equal tags_from_file[book_id].size
+      end
+
+      tags_found.map do |tag|
+        it 'finds tags in the test tags' do
+          exist = tags_from_file[book_id].include? tag
+          [tag, exist].must_equal [tag, true]
+        end
+      end
+    end
+  end
+end

data/taaze.gemspec

@@ -0,0 +1,18 @@
+$LOAD_PATH.push File.expand_path('../lib', __FILE__)
+require 'taaze/version'
+
+Gem::Specification.new do |s|
+  s.name        =  'taaze'
+  s.version     =  Taaze::VERSION
+  s.executables << 'taaze'
+  s.add_runtime_dependency 'nokogiri'
+  s.date        =  Taaze::DATE
+  s.summary     =  'Data extractor of Taaze'
+  s.description =  'Get the book comments or collections of specific user.'
+  s.authors     =  ['Bueze']
+  s.email       =  ''
+  s.files       =  `git ls-files`.split("\n")
+  s.test_files  =  `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.homepage    =  'https://github.com/BUEZE/taaze'
+  s.license     =  'MIT'
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: taaze
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
 platform: ruby
 authors:
 - Bueze
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-10-24 00:00:00.000000000 Z
+date: 2015-10-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -31,7 +31,26 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
+- ".gitignore"
+- ".travis.yml"
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
 - bin/taaze
+- example.jpg
+- lib/taaze.rb
+- lib/taaze/collections.rb
+- lib/taaze/comments.rb
+- lib/taaze/tags.rb
+- lib/taaze/version.rb
+- spec/collections_spec.rb
+- spec/comments_spec.rb
+- spec/fixures/collections.yml
+- spec/fixures/comments.yml
+- spec/fixures/tags.yml
+- spec/tags_spec.rb
+- taaze.gemspec
 homepage: https://github.com/BUEZE/taaze
 licenses:
 - MIT
@@ -56,4 +75,10 @@ rubygems_version: 2.5.0
 signing_key: 
 specification_version: 4
 summary: Data extractor of Taaze
-test_files: []
+test_files:
+- spec/collections_spec.rb
+- spec/comments_spec.rb
+- spec/fixures/collections.yml
+- spec/fixures/comments.yml
+- spec/fixures/tags.yml
+- spec/tags_spec.rb