tushare 0.1.0

data/lib/tushare/internet/box_office.rb

@@ -0,0 +1,155 @@
+require 'tushare/util'
+
+module Tushare
+  module Internet
+    # 电影票房
+    module BoxOffice
+      extend Tushare::Util
+      extend self
+
+      # 获取实时电影票房数据
+      # 数据来源：EBOT艺恩票房智库
+      #  return
+      #  -------
+      #     DataFrame
+      #           BoxOffice     实时票房（万）
+      #           Irank         排名
+      #           MovieName     影片名
+      #           boxPer        票房占比 （%）
+      #           movieDay      上映天数
+      #           sumBoxOffice  累计票房（万）
+      #           time          数据获取时间
+      def realtime_boxoffice
+        url = format(MOVIE_BOX, P_TYPE['http'], DOMAINS['mbox'], BOX, _random)
+        resp = HTTParty.get url
+        return nil if resp.body.length < 15
+        json = JSON.parse resp
+        result = []
+        now = Time.now
+        json['data2'].each do |object|
+          object.delete 'MovieImg'
+          object.delete 'mId'
+          object['time'] = now
+          result << object
+        end
+        result
+      end
+
+      # 获取单日电影票房数据
+      # 数据来源：EBOT艺恩票房智库
+      # Parameters
+      # ------
+      #     date:日期，默认为上一日
+      #  return
+      #  -------
+      #     DataFrame
+      #           AvgPrice      平均票价
+      #           AvpPeoPle     场均人次
+      #           BoxOffice     单日票房（万）
+      #           BoxOffice_Up  环比变化 （%）
+      #           IRank         排名
+      #           MovieDay      上映天数
+      #           MovieName     影片名
+      #           SumBoxOffice  累计票房（万）
+      #           WomIndex      口碑指数
+      def day_boxoffice(date = nil)
+        date = if date.nil?
+                 0
+               else
+                 Date.today - Date.parse(date) + 1
+               end
+        url = format(BOXOFFICE_DAY, P_TYPE['http'], DOMAINS['mbox'], BOX, date,
+                     _random)
+        resp = HTTParty.get url
+        return nil if resp.body.length < 15
+        json = JSON.parse resp
+        result = []
+        json['data1'].each do |object|
+          %w(MovieImg BoxOffice1 MovieID Director IRank_pro).each do |key|
+            object.delete key
+          end
+          result << object
+        end
+        result
+      end
+
+      # 获取单月电影票房数据
+      # 数据来源：EBOT艺恩票房智库
+      # Parameters
+      # ------
+      #     date:日期，默认为上一月，格式YYYY-MM
+      #  return
+      #  -------
+      #     DataFrame
+      #           Irank         排名
+      #           MovieName     电影名称
+      #           WomIndex      口碑指数
+      #           avgboxoffice  平均票价
+      #           avgshowcount  场均人次
+      #           box_pro       月度占比
+      #           boxoffice     单月票房(万)
+      #           days          月内天数
+      #           releaseTime   上映日期
+      def month_boxoffice(date = nil)
+        date = Date.today.prev_month.strftime('%Y-%m') if date.nil?
+        raise BOX_INPUT_ERR_MSG if date.length > 8
+        date += '-01'
+        url = format(BOXOFFICE_MONTH, P_TYPE['http'], DOMAINS['mbox'], BOX,
+                     date)
+        resp = HTTParty.get url
+        return nil if resp.body.length < 15
+        json = JSON.parse resp
+        result = []
+        json['data1'].each do |object|
+          %w(defaultImage EnMovieID).each do |key|
+            object.delete key
+          end
+          result << object
+        end
+        result
+      end
+
+      # 获取影院单日票房排行数据
+      # 数据来源：EBOT艺恩票房智库
+      # Parameters
+      # ------
+      #     date:日期，默认为上一日
+      #  return
+      #  -------
+      #     DataFrame
+      #           Attendance         上座率
+      #           AvgPeople          场均人次
+      #           CinemaName         影院名称
+      #           RowNum             排名
+      #           TodayAudienceCount 当日观众人数
+      #           TodayBox           当日票房
+      #           TodayShowCount     当日场次
+      #           price              场均票价（元）
+      def day_cinema(date = nil)
+        date = Date.today.prev_day.strftime('%F') if date.nil?
+        _write_head
+        result = []
+        1.upto(11) do |page|
+          url = format(BOXOFFICE_CBD, P_TYPE['http'], DOMAINS['mbox'], BOX,
+                       page, date)
+          resp = HTTParty.get url
+          next if resp.body.length < 15
+          json = JSON.parse resp.body
+          json['data1'].each do |object|
+            object.delete 'CinemaID'
+            result << object
+          end
+        end
+        result
+      end
+
+      private
+
+      def _random(n = 13)
+        start_integer = 10**(n - 1)
+        end_integer = (10**n) - 1
+        rand(start_integer..end_integer)
+      end
+    end
+  end
+end

data/lib/tushare/stock/billboard.rb

@@ -0,0 +1,197 @@
+require 'tushare/util'
+
+module Tushare
+  module Stock
+    # 龙虎榜数据
+    module Billboard
+      extend Tushare::Util
+      extend self
+
+      # 获取每日龙虎榜列表
+      # Parameters
+      # --------
+      # date:string
+      #             明细数据日期 format：YYYY-MM-DD 如果为空，返回最近一个交易日的数据
+
+      # Return
+      # ------
+      # DataFrame
+      #     code：代码
+      #     name ：名称
+      #     pchange：涨跌幅
+      #     amount：龙虎榜成交额(万)
+      #     buy：买入额(万)
+      #     bratio：占总成交比例
+      #     sell：卖出额(万)
+      #     sratio ：占总成交比例
+      #     reason：上榜原因
+      #     date  ：日期
+      def top_list(date = Time.now.strftime('%F'))
+        # TODO: 判断日期是否合法
+        url = format(LHB_URL, P_TYPE['http'], DOMAINS['em'], date, date)
+        resp = HTTParty.get(url)
+        string = resp.body.encode('utf-8', 'gbk').split('_1=').last
+        json = JSON.parse(string)
+        result = []
+        json['data'].each do |datum|
+          object = {}
+          LHB_COLS.each_with_index do |key, index|
+            object[key] = datum[LHB_TMP_COLS[index]]
+            if %w(buy sell amount Turnover).include? key
+              object[key] = (object[key].to_f / 10000).round(2)
+            end
+          end
+          object['bration'] = (object['buy'] / object['Turnover']).round(2)
+          object['sratio'] = (object['sell'] /object['Turnover']).round(2)
+          object['date'] = date
+          object.delete('Turnover')
+          result << object
+        end
+        result
+      end
+
+      # 获取个股上榜统计数据
+      # Parameters
+      # --------
+      #     days:int
+      #               天数，统计n天以来上榜次数，默认为5天，其余是10、30、60
+      #     retry_count : int, 默认 3
+      #                  如遇网络等问题重复执行的次数
+      #     pause : int, 默认 0
+      #                 重复请求数据过程中暂停的秒数，防止请求间隔时间太短出现的问题
+      # Return
+      # ------
+      # DataFrame
+      #     code：代码
+      #     name：名称
+      #     count：上榜次数
+      #     bamount：累积购买额(万)
+      #     samount：累积卖出额(万)
+      #     net：净额(万)
+      #     bcount：买入席位数
+      #     scount：卖出席位数
+      def cap_tops(days = 5)
+        _check_lhb_input(days)
+        get_data(1, LHB_GGTJ_COLS, lambda do |p|
+          format(LHB_SINA_URL, P_TYPE['http'], DOMAINS['vsf'], LHB_KINDS[0],
+                 PAGES['fd'], days, p)
+        end)
+      end
+
+      # 获取营业部上榜统计数据
+      # Parameters
+      # --------
+      # days:int
+      #           天数，统计n天以来上榜次数，默认为5天，其余是10、30、60
+      # retry_count : int, 默认 3
+      #              如遇网络等问题重复执行的次数
+      # pause : int, 默认 0
+      #             重复请求数据过程中暂停的秒数，防止请求间隔时间太短出现的问题
+      # Return
+      # ---------
+      # broker：营业部名称
+      # count：上榜次数
+      # bamount：累积购买额(万)
+      # bcount：买入席位数
+      # samount：累积卖出额(万)
+      # scount：卖出席位数
+      # top3：买入前三股票
+      def broker_tops(days = 5)
+        _check_lhb_input(days)
+        get_data(1, LHB_YYTJ_COLS, lambda do |p|
+          format(LHB_SINA_URL, P_TYPE['http'], DOMAINS['vsf'], LHB_KINDS[1],
+                 PAGES['fd'], days, p)
+        end)
+      end
+
+      # 获取机构席位追踪统计数据
+      # Parameters
+      # --------
+      # days:int
+      #           天数，统计n天以来上榜次数，默认为5天，其余是10、30、60
+      # retry_count : int, 默认 3
+      #              如遇网络等问题重复执行的次数
+      # pause : int, 默认 0
+      #             重复请求数据过程中暂停的秒数，防止请求间隔时间太短出现的问题
+
+      # Return
+      # --------
+      # code:代码
+      # name:名称
+      # bamount:累积买入额(万)
+      # bcount:买入次数
+      # samount:累积卖出额(万)
+      # scount:卖出次数
+      # net:净额(万)
+      def inst_tops(days = 5)
+        _check_lhb_input(days)
+        get_data(
+          1,
+          LHB_JGZZ_COLS,
+          lambda do |p|
+            format(LHB_SINA_URL, P_TYPE['http'], DOMAINS['vsf'], LHB_KINDS[2],
+                   PAGES['fd'], days, p)
+          end,
+          lambda do |tds|
+            tds = tds.to_a
+            tds[0..1].concat tds[4..8]
+          end)
+      end
+
+      # 获取最近一个交易日机构席位成交明细统计数据
+      # Parameters
+      # --------
+      # retry_count : int, 默认 3
+      #              如遇网络等问题重复执行的次数
+      # pause : int, 默认 0
+      #             重复请求数据过程中暂停的秒数，防止请求间隔时间太短出现的问题
+
+      # Return
+      # ----------
+      # code:股票代码
+      # name:股票名称
+      # date:交易日期
+      # bamount:机构席位买入额(万)
+      # samount:机构席位卖出额(万)
+      # type:类型
+      def inst_detail
+        get_data(
+          1,
+          LHB_JGMX_COLS,
+          lambda do |p|
+            format(LHB_SINA_URL, P_TYPE['http'], DOMAINS['vsf'], LHB_KINDS[3],
+                   PAGES['fd'], '', p)
+          end)
+      end
+
+      private
+
+      def get_data(page, headers, url_generator, td_preprocessor = nil)
+        _write_head
+        result = []
+        loop do
+          url = url_generator.call(page)
+          _write_console
+          doc = Nokogiri::HTML(open(url), nil, 'gbk')
+          doc.css('table#dataTable > tr').each do |tr|
+            item = {}
+            tds = tr.css('td')
+            tds = td_preprocessor.call(tds) if td_preprocessor
+            tds.each_with_index do |td, index|
+              item[headers[index]] = td.content if headers[index]
+            end
+            result << item
+          end
+          next_page = doc.css('div.pages > a:last').css('a.nolink')
+          break unless next_page.empty?
+          page += 1
+        end
+        result
+      end
+
+      def _check_lhb_input(last)
+        raise LHB_MSG unless [5, 10, 30, 60].include? last
+      end
+    end
+  end
+end

data/lib/tushare/stock/classifying.rb

@@ -0,0 +1,288 @@
+require 'tushare/util'
+
+module Tushare
+  module Stock
+    # 获取股票分类数据接口
+    module Classifying
+      extend Tushare::Util
+      extend self
+
+      # 获取行业分类数据
+      # Parameters
+      # ----------
+      # standard
+      # sina:新浪行业 sw：申万 行业
+
+      # Returns
+      # -------
+      # DataFrame
+      #     code :股票代码
+      #     name :股票名称
+      #     c_name :行业名称
+      def industry_classified(standard = 'sina')
+        _write_head
+        url = format(SINA_INDUSTRY_INDEX_URL, P_TYPE['http'], DOMAINS['vsf'],
+                     standard == 'sw' ? PAGES['ids_sw'] : PAGES['ids'])
+        type_data = fetch_type_data(url)
+        result = []
+        type_data.keys.each do |type|
+          result.concat fetch_detail(type, type_data[type])
+        end
+        result
+      end
+
+      # 获取概念分类数据
+      # Return
+      # --------
+      # DataFrame
+      #     code :股票代码
+      #     name :股票名称
+      #     c_name :概念名称
+      def concept_classified
+        _write_head
+        url = format(SINA_CONCEPTS_INDEX_URL, P_TYPE['http'], DOMAINS['sf'],
+                     PAGES['cpt'])
+        type_data = fetch_type_data(url)
+        result = []
+        type_data.keys.each do |type|
+          result.concat fetch_detail(type, type_data[type])
+        end
+        result
+      end
+
+      # 获取地域分类数据
+      # Return
+      # --------
+      # DataFrame
+      #     code :股票代码
+      #     name :股票名称
+      #     area :地域名称
+      def area_classified
+        basics = Tushare::Stock::Fundamental.get_stock_basics
+        result = []
+        basics.each do |basic|
+          result << { 'code' => basic['code'],
+                      'name' => basic['name'],
+                      'area' => basic['area'] }
+        end
+        result.sort_by { |object| object['area'] || '' }
+      end
+
+      # 获取创业板股票
+      # Return
+      # --------
+      # DataFrame
+      #     code :股票代码
+      #     name :股票名称
+      def gem_classified
+        basics = Tushare::Stock::Fundamental.get_stock_basics
+        basics.select! { |basic| basic['code'][0] == '3' }
+        result = []
+        basics.each do |basic|
+          result << { 'code' => basic['code'], 'name' => basic['name'] }
+        end
+        result.sort_by { |object| object['code'] || '' }
+      end
+
+      # 获取中小板股票
+      # Return
+      # --------
+      # DataFrame
+      #     code :股票代码
+      #     name :股票名称
+      def sme_classified
+        basics = Tushare::Stock::Fundamental.get_stock_basics
+        basics.select! { |basic| basic['code'][0..2] == '002' }
+        result = []
+        basics.each do |basic|
+          result << { 'code' => basic['code'], 'name' => basic['name'] }
+        end
+        result.sort_by { |object| object['code'] || '' }
+      end
+
+      # 获取风险警示板股票
+      # Return
+      # --------
+      # DataFrame
+      #     code :股票代码
+      #     name :股票名称
+      def st_classified
+        basics = Tushare::Stock::Fundamental.get_stock_basics
+        basics.select! { |basic| basic['name'].include? 'ST' }
+        result = []
+        basics.each do |basic|
+          result << { 'code' => basic['code'], 'name' => basic['name'] }
+        end
+        result.sort_by { |object| object['code'] || '' }
+      end
+
+      # 获取沪深300当前成份股及所占权重
+      # Return
+      # --------
+      # DataFrame
+      #     code :股票代码
+      #     name :股票名称
+      #     date :日期
+      #     weight:权重
+      def hs300s
+        url = format(HS300_CLASSIFY_URL_FTP, P_TYPE['ftp'], DOMAINS['idxip'],
+                     PAGES['hs300w'])
+        fetch_ftp_file url do |file|
+          xls = ::Roo::Spreadsheet.open(file, extension: 'xls')
+          result = []
+          xls.sheet(0).drop(1).each do |row|
+            result << { 'date' => row[0],
+                        'code' => row[3],
+                        'weight' => row[6] }
+          end
+          basics = Tushare::Stock::Fundamental.get_stock_basics
+          result.each do |object|
+            find_result = basics.find { |basic| basic['code'] == object['code'] }
+            object[name] = find_result['name']
+          end
+          result
+        end
+      end
+
+      # 获取上证50成份股
+      # Return
+      # --------
+      # DataFrame
+      #     code :股票代码
+      #     name :股票名称
+      def sz50s
+        url = format(HS300_CLASSIFY_URL_FTP, P_TYPE['ftp'], DOMAINS['idxip'],
+                     PAGES['sz50b'])
+        fetch_ftp_file url do |file|
+          xls = ::Roo::Spreadsheet.open(file, extension: 'xls')
+          result = []
+          xls.sheet(0).drop(1).each do |row|
+            result << { 'code' => row[0],
+                        'name' => row[1] }
+          end
+          result
+        end
+      end
+
+      # 获取中证500成份股
+      # Return
+      # --------
+      # DataFrame
+      #     code :股票代码
+      #     name :股票名称
+      def zz500s
+        url = format(HS300_CLASSIFY_URL_FTP, P_TYPE['ftp'], DOMAINS['idxip'],
+                     PAGES['zz500wt'])
+        fetch_ftp_file url do |file|
+          xls = ::Roo::Spreadsheet.open(file, extension: 'xls')
+          result = []
+          xls.sheet(0).drop(1).each do |row|
+            result << { 'date' => row[0],
+                        'code' => row[3],
+                        'weight' => row[6] }
+          end
+          basics = Tushare::Stock::Fundamental.get_stock_basics
+          result.each do |object|
+            find_result = basics.find { |basic| basic['code'] == object['code'] }
+            object[name] = find_result['name']
+          end
+        end
+      end
+
+      # 获取终止上市股票列表
+      # Return
+      # --------
+      # DataFrame
+      #     code :股票代码
+      #     name :股票名称
+      #     oDate:上市日期
+      #     tDate:终止上市日期
+      def terminated
+        ref = format(SSEQ_CQ_REF_URL, P_TYPE['http'], DOMAINS['sse'])
+        url = format(TERMINATED_URL, P_TYPE['http'], DOMAINS['sseq'],
+                     PAGES['ssecq'], _random(5), _random)
+        resp = HTTParty.get(
+          url,
+          headers: { 'Referer' => ref },
+          cookies: MAR_SH_COOKIES
+        )
+        json = JSON.parse(resp.body.sub(/jsonpCallback\d+\(/, '')[0..-2])['pageHelp']
+        result = []
+        json['data'].each do |datum|
+          object = {}
+          TERMINATED_T_COLS.each_with_index do |key, index|
+            object[TERMINATED_COLS[index]] = datum[key]
+          end
+          result << object
+        end
+        result
+      end
+
+      # 获取暂停上市股票列表
+      # Return
+      # --------
+      # DataFrame
+      #     code :股票代码
+      #     name :股票名称
+      #     oDate:上市日期
+      #     tDate:终止上市日期
+      def suspended
+        ref = format(SSEQ_CQ_REF_URL, P_TYPE['http'], DOMAINS['sse'])
+        url = format(SUSPENDED_URL, P_TYPE['http'], DOMAINS['sseq'],
+                     PAGES['ssecq'], _random(5), _random)
+        resp = HTTParty.get(
+          url,
+          headers: { 'Referer' => ref },
+          cookies: MAR_SH_COOKIES
+        )
+        json = JSON.parse(resp.body.sub(/jsonpCallback\d+\(/, '')[0..-2])['pageHelp']
+        result = []
+        json['data'].each do |datum|
+          object = {}
+          TERMINATED_T_COLS.each_with_index do |key, index|
+            object[TERMINATED_COLS[index]] = datum[key]
+          end
+          result << object
+        end
+        result
+      end
+
+      private
+
+      def fetch_detail(type, type_name)
+        _write_console
+        url = format(SINA_DATA_DETAIL_URL, P_TYPE['http'], DOMAINS['vsf'],
+                     PAGES['jv'], type)
+        resp = HTTParty.get(url)
+        json = JSON.parse(resp.body.encode('utf-8', 'gbk').gsub(/,(.*?):/) { |s| ",\"#{s[1..-2]}\":" }.gsub('"{symbol', '{"symbol').gsub('{symbol', '{"symbol"'))
+        result = []
+        json.each do |row|
+          object = {}
+          FOR_CLASSIFY_B_COLS.each do |field|
+            object[field] = row[field]
+          end
+          object['c_name'] = type_name
+          result << object
+        end
+        result
+      end
+
+      def fetch_type_data(url)
+        resp = HTTParty.get(url)
+        json = JSON.parse(resp.body.encode('utf-8', 'gbk').split('=').last)
+        result = {}
+        json.values.each do |row|
+          arr = row.split(',')
+          result[arr[0]] = arr[1]
+        end
+        result
+      end
+
+      def _random(n = 13)
+        start_int = 10**(n-1)
+        end_int = (10**n) - 1
+        rand(start_int..end_int).to_s
+      end
+    end
+  end
+end