chinacity 0.0.1

data/bin/chinacity

@@ -0,0 +1,6 @@
+#!/usr/bin/env ruby
+
+$: << File.expand_path('../../lib', __FILE__)
+
+require 'chinacity'
+

data/chinacity.gemspec

@@ -0,0 +1,27 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'chinacity/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "chinacity"
+  spec.version       = Chinacity::VERSION
+  spec.authors       = ["Ryan Wang"]
+  spec.email         = ["wongyouth@gmail.com"]
+  spec.summary       = %q{Get China cities data from China Official site}
+  spec.description   = %q{Get China cities data from China official site}
+  spec.homepage      = "http://github.com/wongyouth/chinacity"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "chinese_pinyin"
+  spec.add_dependency "json"
+  spec.add_dependency "nokogiri"
+  spec.add_dependency "httparty"
+  spec.add_development_dependency "bundler", "~> 1.5"
+  spec.add_development_dependency "rake"
+end

data/lib/chinacity/cli.rb

@@ -0,0 +1,107 @@
+# encoding: utf-8
+require 'nokogiri'
+require 'chinese_pinyin'
+require 'json'
+require 'httparty'
+
+module Chinacity
+  HOST = 'http://www.stats.gov.cn'
+  LIST_PATH = '/tjsj/tjbz/xzqhdm/'
+  LIST_URL = HOST + LIST_PATH
+
+  class Cli
+    def initialize options
+      @short = options[:short]
+      @foramt = options[:format]
+    end
+
+    def start
+      doc = Nokogiri::HTML(get_data)
+      get_cities(doc)
+
+      add_short_name if @short
+
+      output (@foramt == :json ? to_json : to_csv)
+    end
+
+    private
+      def get_data
+        # puts LIST_URL
+
+        # get newest city url
+        data = HTTParty.get(LIST_URL).body
+        doc = Nokogiri::HTML data
+        url = LIST_URL + doc.css('.center_list a')[0][:href]
+        # puts url
+
+        # get newest city data
+        HTTParty.get(url).body
+      end
+
+      def get_cities(doc)
+        @cities = doc.css('p.MsoNormal').map do |data|
+          id, text = data.text.gsub(/[[:space:]]+/, ' ').split
+
+          {id: id, text: text} if id
+        end.compact
+      end
+
+      def add_short_name
+        @cities.each do |city|
+          # puts city
+          city[:short] = Pinyin.t(city[:text]).split.map{|w|w[0]}.join.upcase
+        end
+
+        self
+      end
+
+      def nested_cities
+        pretty = {}
+
+        @cities.each do |city|
+          if city[:id].end_with? '0000'
+            pretty[:province] ||= []
+            pretty[:province] << city
+          elsif city[:id].end_with? '00'
+            pretty[:city] ||= []
+            pretty[:city] << city
+          else
+            pretty[:district] ||= []
+            pretty[:district] << city
+          end
+        end
+
+        pretty
+      end
+
+      def to_json
+        JSON.pretty_generate(nested_cities)
+      end
+
+      def to_csv
+        list = @short ? [ "id, 名称, 缩写, 层级" ] : ["id, 名称, 层级"]
+
+        list += @cities.map do |city|
+          level = if city[:id].end_with? '0000'
+            1
+          elsif city[:id].end_with? '00'
+            2
+          else
+            3
+          end
+
+          if @short
+            "#{city[:id]}, #{city[:text]}, #{city[:short]}, #{level}"
+          else
+            "#{city[:id]}, #{city[:text]}, #{level}"
+          end
+        end
+
+        list.join("\n")
+      end
+
+      def output data
+        STDOUT.write data.to_s
+      end
+  end
+end

data/lib/chinacity/version.rb

@@ -0,0 +1,3 @@
+module Chinacity
+  VERSION = "0.0.1"
+end

data/lib/chinacity.rb

@@ -0,0 +1,28 @@
+require 'optparse'
+require "chinacity/version"
+require "chinacity/cli"
+
+options = {
+  short: false,
+  format: :json
+}
+
+parser = OptionParser.new do |opts|
+  opts.banner = "Usage: chinacity [options]"
+  opts.separator ""
+  opts.separator "options:"
+
+  opts.on('-s', '--short', 'Short name, First charactor of every word in pinyin') do
+    options[:short] = true
+  end
+
+  opts.on('-c', '--csv', 'Output CSV format') do
+    options[:format] = :csv
+  end
+end
+
+parser.parse!
+
+cli = Chinacity::Cli.new options
+cli.start
+

metadata

@@ -0,0 +1,140 @@
+--- !ruby/object:Gem::Specification
+name: chinacity
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Ryan Wang
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-06-30 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: chinese_pinyin
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: json
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: httparty
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Get China cities data from China official site
+email:
+- wongyouth@gmail.com
+executables:
+- chinacity
+extensions: []
+extra_rdoc_files: []
+files:
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- areas.csv
+- areas.json
+- bin/chinacity
+- chinacity.gemspec
+- lib/chinacity.rb
+- lib/chinacity/cli.rb
+- lib/chinacity/version.rb
+homepage: http://github.com/wongyouth/chinacity
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.0
+signing_key: 
+specification_version: 4
+summary: Get China cities data from China Official site
+test_files: []