从互联网获取股票数据（历史数据，Python + MySQL）

weapon 发布于2019-07-30 15:42 / 1379人阅读

摘要：目标从互联网网易数据接口获取股票历史数据，包括开盘价最高价最低价收盘价等等环境记录数条，以该表为基础，制作清单。

目标

从互联网（网易数据接口）获取股票历史数据，包括开盘价、最高价、最低价、收盘价等等

环境

Python 3.6
MySQL 5.6.34

table: stock_list

记录数：3592 条，以该表为基础，制作 mission 清单。

table: stock_list_20190209（ mission list ）

从这个表里，每次读取一定数量的记录，依次从互联网上获取。

code: getStockData.py

"""
《获取股票历史市值》
Created on 2018年2月12日
@author: Livon

# 读取 股票列表，含代码及 上市日期、终止上市日期

（1）列表
        每次执行前，手工新建一个当前日期的表，如果存在就删除重建（可能是执行一个存储过程）
        表名：stock_list_20180212 // 股票列表
        表字段：id, 股票代码， 是否顺利完成，获取记录数量
        每次取一条记录，依次执行，中断了，下次可以从中断处继续。
        
（2）
每条记录，按指定日期范围进行获取

再建

# 从网易数据接口拉取市值数据

# 存入表 stock_his_marketCap 中

"""

import util
import urllib
import csv
import time
import datetimeUtil

from urllib import request

jobListTable = "stock_list_20180209"

def p( msg ):
    print( "%s - %s" % ( datetimeUtil.getDatetime(), msg ))

def startJob():

    # 从数据池中读取 n 记录
    missionList = util.getMissionList( jobListTable )
    
    # 循环处理上述的 n 条记录
    for mission in missionList:
#         for value in row:
#             print( value )
        # 根据记录生成一条 url，一个 url 可以获取几千条日记录
        url = util.genUrl( mission )
    #     url = "http://quotes.money.163.com/service/chddata.html?code=1000001&start=19910401&end=19910409"
    #     url += "&fields=LCLOSE;TOPEN;HIGH;LOW;TCLOSE;CHG;PCHG;TURNOVER;VOTURNOVER;VATURNOVER;TCAP;MCAP"  
                
#         print( dt(), " - ", url )
        p( "url: %s" % url )
        
        # 从互联网上获取股票数据
        dataList = util.getStockDataList( url )
        
        if( dataList != None ):
            # 将数据保存在目标表：股票历史数据表中
            insertedRows = util.insertTable( dataList )        
            # 更新 mission List 状态标志列
            util.updateJobList( jobListTable, mission, insertedRows )    
        else :
            p( "csv 文件无数据。" )
        
        p("standby a moment for next mission（ you can terminal the program at this time）.")
        time.sleep(3)
        
# main
for i in range( 0, 2 ):
    p( "startJob: %s" % str(i)  )
    startJob()
    
# done
print( "= = = = = = = = = = = = = = = = = = = = = = " )
p( "all done !")
print( "= = = = = = = = = = = = = = = = = = = = = = " )

code: util.py

"""
Created on 2018年2月11日

@author: Livon
"""
   
import urllib.request

import re
import pymysql

from urllib import request

# from stock.获取股票历史市值 import datetimeUtil
import datetimeUtil



def p( msg ):
    print( "%s - %s" % ( datetimeUtil.getDatetime(), msg ))



# 任务清单，每一次任务会领一份任务清单，清单中的第一项，是一个股票
# 任务：job - 大循环
# 目标：mission - 小目标
# missionList - 目标清单
# getMissionList
# 参数：tableName 表名
def getMissionList( tableName ):
    
    rowsCount = "5" ;    
    
    conn = pymysql.connect(host="127.0.0.1", port=3306, user="root", passwd="root", db="stock", charset="utf8")
    # 创建游标
#     cursor = conn.cursor()

    cursor = conn.cursor()
    
#     sql="select * from "+ tableName +" where doneTime is NULL limit " + rowsCount
    sql = "select * from %s where doneTime is NULL limit %s" % ( tableName, rowsCount )
    cout = cursor.execute(sql)
#     print("数量： "+str(cout))
    rows = cursor.fetchall();
    
#     rows = conn.cursor().execute( sql ).fetchall()
    
#     for row in rows:
#         print("stockCode: "+str(row[0])+"  stockName： "+row[1]+"  startDate： "+ str(row[2]))
        
    cursor.close()
#     
#     try:
#         #获取一个游标
#         with conn.cursor() as cursor:
#             sql="select * from "+ tableName +" where doneTime is NULL limit 1"
#             cout=cursor.execute(sql)
#             print("数量： "+str(cout))
# 
#             for row in cursor.fetchall():
#                 #print("%s	%s	%s" %row)
#                 #注意int类型需要使用str函数转义
#                 print("stockCode: "+str(row[0])+"  stockName： "+row[1]+"  startDate： "+ str(row[2]))
# #         conn.commit()
# 
#     finally:
#         print( "done" )
        
    
    cursor.close()
    conn.close()
    
#     print( datetimeUtil.getDatetime(), " - 任务清单装载完毕！任务数量：", str( len( rows ))  )
#     print( "%s - %s missons loaded." % ( datetimeUtil.getDatetime(), str( len( rows )) ) )
    p( "%s missons loaded." % str( len( rows ) ))
    
    return rows




# 生成网址
def genUrl( row ):    
    
    stockCode = row[0]
    startDate = str( row[2] ).replace("-","")
#     endDate = ( row[3] == "None" )? "": row[3]
#     endDate = ( row[3] == None ) and "" or row[3]
    endDate = ( row[3] == None ) and row[3] or ""
    dataSource = row[4]
#     True and "Fire" or "Water"  
#     print( row[3] is "None")
#     print( row[3] is None )
#     print( row[3] is "" )
#     print( type( row[3] ) )
#     print( type( row[3] ) is None )
#     print( type( row[3] ) is "NoneType" )
    
    url = "http://quotes.money.163.com/service/chddata.html?code=%s%s&start=%s&end=%s"
    url = url % ( dataSource, stockCode, startDate, endDate )
    url += "&fields=LCLOSE;TOPEN;LOW;HIGH;TCLOSE;CHG;PCHG;TURNOVER;VOTURNOVER;VATURNOVER;TCAP;MCAP"    
    
    return url





def getCsv( url ):    
    
#     csv = csv.decode("gbk")
#     
#     csv_str = str(csv)
#     lines = csv_str.split("
")
#     
#     print( len( lines))
    
    return ""

# 从互联网上获取数据
def getStockDataList( url ):
    
    print( datetimeUtil.getDatetime(), " - ", "准备从互联网获取数据 ..." )
    
#     http = urllib3.PoolManager()
#     r = http.request("GET", url )
#     url="http://www.example.com/"
#     headers={"User-Agent":"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1"}

#     try:
#         req = urllib3.request(url, headers )
# #         req=urllib2.Request(url,headers=headers)
#         response = urllib3.request2.urlopen(req)
#     except urllib3.exceptions,e:
#         print e.reason
    dataList = None 
    try:
        response = request.urlopen( url )
        
        csv = response.read()     
        csv = csv.decode("gbk")  
    #     csv = csv.decode("iso-8859-1")        
        csv_str = str(csv)
        
#         print( type( csv ))
        
        if( len( csv_str ) < 1 ):
            print( "获取失败" )
        
#         print( csv_str )
    #     lines = csv_str.split("
")    
        lines = csv_str.splitlines()
#         print( "行数：" + str( len( lines )))   
        
        dataList = [] 
        
        for line in lines:
#             print( line )
            dataRow = line.split(",")
#             print( dataRow[0] )
            dataObj = {}
            dataObj["日期"]       = dataRow[0]
            dataObj["股票代码"]   = dataRow[1]
            dataObj["名称"]       = dataRow[2]
            dataObj["前收盘"]     = dataRow[3]
            dataObj["开盘价"]     = dataRow[4]
            dataObj["最高价"]     = dataRow[5]
            dataObj["最低价"]     = dataRow[6]
            dataObj["收盘价"]     = dataRow[7]
            dataObj["涨跌额"]     = dataRow[8]
            dataObj["涨跌幅"]     = dataRow[9]
            dataObj["换手率"]     = dataRow[10]
            dataObj["成交量"]     = dataRow[11]
            dataObj["成交金额"]   = dataRow[12]
            dataObj["总市值"]     = dataRow[13]
            dataObj["流通市值"]   = dataRow[14]
            dataList.append(dataObj)
        
    except Exception as e:
        print( e )
        
    
    return dataList


def netEaseUrl( stockCode, startDate, endDate ):
    
    url = "http://quotes.money.163.com/service/chddata.html?code=%s&start=%s&end=%s&fields="
    url = url % ( stockCode, startDate, endDate )
    
    print( url )
    
    return url

def receiveCsv( url ):
    
    # http://www.cnblogs.com/sysu-blackbear/p/3629420.html
    stockDataResponse = urllib.request.urlopen( url )
    stockData = stockDataResponse.read()
    # stockData = stockDataResponse.decode("utf8")
    stockData = stockData.decode("gb2312")
    # stockData = stockData.decode("gb2312")

#     print( stockData )
    
    return stockData


"""

"""
def getStockList():
    
    
    conn = pymysql.connect(host="127.0.0.1", port=3306, user="root", passwd="root", db="stock", charset="utf8")
    # 创建游标
#     cursor = conn.cursor()
    
    try:
        #获取一个游标
        with conn.cursor() as cursor:
            sql="select * from stock_list"
            cout=cursor.execute(sql)
            print("数量： "+str(cout))

            for row in cursor.fetchall():
                #print("%s	%s	%s" %row)
                #注意int类型需要使用str函数转义
                print("stockCode: "+str(row[0])+"  stockName： "+row[1]+"  startDate： "+ str(row[2]))
#         conn.commit()

    finally:
        cursor.close()
        conn.close()


  
def dbStore( str_stocks ):
    
    
    print( type( str_stocks ))
        
    stocks = re.findall("[(.*?)]",str_stocks )
    stocks = re.findall("{(.*?)}",stocks[0])    
    
    # 创建连接
    conn = pymysql.connect(host="127.0.0.1", port=3306, user="root", passwd="root", db="stock", charset="utf8")
    # 创建游标
    cursor = conn.cursor()
        
    for i in range( 0, len( stocks ) ):
        print( "No." + str(i))
        properties = stocks[i].split(",")            
#         print( properties )         
#         print( type( properties ))
#         effect_rows = insertDb( properties, cursor )
#         time.sleep(1)
        
    # 提交，不然无法保存新建或者修改的数据
    conn.commit()
  
    # 关闭游标
    cursor.close()
    # 关闭连接
    conn.close()    
    
    return ""


def updateJobList( jobListTable, row, insertedRows ):
    
    
    # 创建连接
    conn = pymysql.connect(host="127.0.0.1", port=3306, user="root", passwd="root", db="stock", charset="utf8")
    # 创建游标
    cursor = conn.cursor()
#     otherStyletime == "2013-10-10 23:40:00"
    
#     sql ="update " + jobListTable + " set doneTime = "" + otherStyleTime + "" where stockCode = "" + row[0] + """
    
    sql = "update %s set doneTime = "%s" , receivedRows = %s where stockCode = "%s"" % ( jobListTable, datetimeUtil.getDatetime(), insertedRows, row[0] )
    
    print( datetimeUtil.getDatetime(), " - 更新任务清单：", sql )
    
    effect_row = cursor.execute( sql )
    
    conn.commit()  
    # 关闭游标
    cursor.close()
    # 关闭连接
    conn.close()    
    
    
    
def insertTable( dataList ):
    
    # 创建连接
    conn = pymysql.connect(host="127.0.0.1", port=3306, user="root", passwd="root", db="stock", charset="utf8")
    # 创建游标
    cursor = conn.cursor()
        
    insertedRows = 0
    
    for i in range( 1, len( dataList )):
        
        for (k,v) in  dataList[i].items(): 
#             print( "dataList[i][%s]=" % k,v )
#             print( v )
            if( v == "None" ):
#                 print("Change to NULL")
                dataList[i][k] = "NULL"
        
#         for data in dataList[i]:
#             print( data. )
#             data = ( data == None ) and data or "NULL"        
        
        sql = "INSERT INTO stock_his_data ( "
        sql += "日期,"
        sql += "股票代码,"
        sql += "名称,"
        sql += "前收盘,"
        sql += "开盘价,"
        sql += "最低价,"
        sql += "最高价,"
        sql += "收盘价,"
        sql += "涨跌额,"
        sql += "涨跌幅,"
        sql += "换手率,"
        sql += "成交量,"
        sql += "成交金额,"
        sql += "总市值,"
        sql += "流通市值"   
        sql += " ) "    
        sql += "VALUES"  
        sql += " ( "  
        
        sql += """ + dataList[i]["日期"]    +  "","
        sql += """ + dataList[i]["股票代码"]+  "","
        sql += """ + dataList[i]["名称"]    +  "","
        sql +=       dataList[i]["前收盘"]  +  " ,"
        sql +=       dataList[i]["开盘价"]  +  " ,"
        sql +=       dataList[i]["最低价"]  +  " ,"
        sql +=       dataList[i]["最高价"]  +  " ,"
        sql +=       dataList[i]["收盘价"]  +  " ,"
        sql +=       dataList[i]["涨跌额"]  +  " ,"
        sql +=       dataList[i]["涨跌幅"]  +  " ,"
        sql +=       dataList[i]["换手率"]  +  " ,"
        sql +=       dataList[i]["成交量"]  +  " ,"
        sql +=       dataList[i]["成交金额"]+  " ,"
        sql +=       dataList[i]["总市值"]  +  " ,"
        sql +=       dataList[i]["流通市值"]
        sql += " ) "
        
#         print( sql )
        
        effect_row = cursor.execute( sql )
        
        if( effect_row > 0 ):
            insertedRows += 1
            
    print( datetimeUtil.getDatetime(), " - 数据数量：", insertedRows )
#     
    # 提交，不然无法保存新建或者修改的数据
    conn.commit()  
    # 关闭游标
    cursor.close()
    # 关闭连接
    conn.close()    
    
    
    
#     arr_values = []
#     arr_columns = []
#     
#     for j in range( 0, len( properties) ):
#         
# #         print( "propertie["+ str(j)+"]: " + properties[j] )
# #         key_value = properties[j].split(":")
# #         print( key_value[0] + " -> " + key_value[1] )
#         key = properties[j][:properties[j].find(":")]
#         value = properties[j][properties[j].find(":")+1:]
#         value = value.replace(""", "")
# #         print( key + " -> " + value )
# #         sql += """ + value + """
#         arr_columns.append( "`" + key + "`" )
# #         arr_columns.append( key )
#         arr_values.append( """ + value + """ )
#         
#     sql = "insert into stock_sina "
#     sql = sql + " ( " + ",".join( arr_columns ) + " ) VALUES ( " + ",".join( arr_values ) + " ) "
    
#     print( sql )
       
#     effect_row = cursor.execute( sql )
    
    return insertedRows

code: datetimeUtil.py

"""
Created on 2018年2月14日

@author: Livon
"""

import time

def getDatetime():
    
    timeArray = time.localtime( time.time() )
    otherStyleTime = time.strftime("%Y-%m-%d %H:%M:%S", timeArray)
    
    return otherStyleTime

最终得到的数据：table: stock_his_data

记录总数：9045612（九百万）

文章版权归作者所有，未经允许请勿转载,若此文章存在违规行为，您可以联系管理员删除。

转载请注明本文地址：https://www.ucloud.cn/yun/41411.html

Python财经数据接口包TuShare的使用

摘要：本例以数据库为代表，展示将获取到的股票数据存入数据库的方法其他类型数据库请参考官网文档的部分。存入数据库追加数据到现有表财经数据接口包的使用存入财经数据接口包的使用安装TuShare 方式1：pip install tushare 方式2：访问https://pypi.python.org/pypi/tushare/下载安装方式3：将源代码下载到本地python setup.py ...

20171112 2019-07-31 11:00 评论0 收藏0
磨刀霍霍：爬爬爬爬爬爬虫爬起来~

摘要：目标很简单，因为我想要爬一下证券化率，然后可视化输出结果。证券化率的基础就是上市公司的总市值，对于证券化率其实还蛮多说法的，比如雪球的这篇文。我们可以利用这个回调函数来显示当前的下载进度。写在前面的叨叨折腾了这么久，我终于在喝完一听快乐肥宅水后下定决心来学习写爬虫了。目标很简单，因为我想要爬一下证券化率，然后可视化输出结果。证券化率的基础就是上市公司的总市值，对于证券化率其实还蛮多...

Allen 2019-07-31 10:07 评论0 收藏0
python爬虫实战二——股票数据定向爬虫

摘要：选取方法打开网页，查看源代码，搜索网页的股票价格数据是否存在于源代码中。将上述的代码封装成一个函数，对东方财富网页面解析的完整代码如下所示接下来是获得百度股票网链接描述单只股票的信息。功能简介目标：获取上交所和深交所所有股票的名称和交易信息。输出：保存到文件中。技术路线： requests---bs4--re语言：python3.5 说明网站选择原则：股票信息静态存在于ht...

icattlecoder 2019-07-30 14:27 评论0 收藏0