[python]沪深龙虎榜数据进一步处理，计算日后5日的涨跌幅

沪深龙虎榜数据进一步处理，计算日后5日的涨跌幅

事前数据：

前面处理得到的csv文件

文件名前加入“[wait]”等待程序处理

python代码从雅虎股票历史数据api获取数据，计算后面5日的涨跌幅

雅虎数据api格式：

priceUrl = 'http://table.finance.yahoo.com/table.csv?s={%1}&d={%2}&e={%3}&f={%4}&g=d&a={%5}&b={%6}&c={%7}&ignore=.csv'
# %1:000001.sz
# END: %2:月-1 %3：日 %4:年
# STRAT: %5:月-1 %6：日 %7:年

事前数据截图：

计算后，再用excel的条件格式并另存为excel文件后截图：

代码：

#coding=utf-8

#读取'[wait]'开头的csv文件
#copyright @ WangXinsheng
#http://www.cnblogs.com/wangxinsheng/
import os
import gzip
import re
import http.cookiejar
import urllib.request
import urllib.parse
import time
import datetime

def getOpener(head):
    # deal with the Cookies
    cj = http.cookiejar.CookieJar()
    pro = urllib.request.HTTPCookieProcessor(cj)
    opener = urllib.request.build_opener(pro)
    header = []
    for key, value in head.items():
        elem = (key, value)
        header.append(elem)
    opener.addheaders = header
    return opener

def ungzip(data):
    try:        # 尝试解压
        print('正在解压.....')
        data = gzip.decompress(data)
        print('解压完毕!')
    except:
        print('未经压缩, 无需解压')
    return data
 
#常量
header = {
    #'Connection': 'Keep-Alive',
    'Accept': '*/*',
    'Accept-Language': 'zh-CN,zh;q=0.8',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.111 Safari/537.36',
    'Accept-Encoding': 'gzip, deflate',
    'Host': 'yahoo.com',
    'Referer' : 'http://www.yahoo.com'
}
priceUrl = 'http://table.finance.yahoo.com/table.csv?\
s={%1}&d={%2}&e={%3}\
&f={%4}&g=d&a={%5}&b={%6}&c={%7}&ignore=.csv'
# %1:000001.sz
# END:   %2:月-1 %3：日-1 %4:年
# STRAT: %5:月-1 %6：日 %7:年


path=r'.'
files = os.listdir(path)
files.sort()
out=[]

for f in files:
    if(f.startswith('[wait]') and
       f.endswith('.csv')):
        #读取文件
        print('读取文件：'+path+'/'+f)
        
        f=open(path+'/'+f,'rt')
        infos = f.readlines()
        f.close()

        i = 0
        add = False
        for info in infos:
            if(i==0):
                i=i+1
                info = info.replace('\n','')+',"一天后","二天后","三天后","四天后","五天后"\n'
                out.append(info)
                continue
            elif(len(info.split(','))>9):
                out.append(info)
                continue
            else:
                #确认需要取的数据范围
                tmp = info.split(',')
                try:
                    timeArray = time.strptime(tmp[0], "%Y-%m-%d")
                except:
                    timeArray = time.strptime(tmp[0], "%Y/%m/%d")
                timeStamp = int(time.mktime(timeArray))
                fromDay = datetime.datetime.utcfromtimestamp(timeStamp)
                fromDay = fromDay + datetime.timedelta(days = 1)
                endDay = fromDay + datetime.timedelta(days = 15)
                code = tmp[1].replace('"','').replace("'","")
                if(code.startswith('6')):
                    code = code +'.ss'
                else:
                    code = code +'.sz'
                url = priceUrl.replace('{%1}',code).replace('{%2}',str(endDay.month-1))
                url = url.replace('{%3}',str(endDay.day)).replace('{%4}',str(endDay.year))
                url = url.replace('{%5}',str(fromDay.month-1)).replace('{%6}',str(fromDay.day))
                url = url.replace('{%7}',str(fromDay.year))
                print('抓取URL: '+url)
                
                #通过雅虎获取价格
                dd = ''
                try:
                    opener = getOpener(header)
                    op = opener.open(url)
                    data = op.read()
                    data = ungzip(data)
                    dd = data.decode()
                except:
                    print('网络抓取失败')
                    out.append(info)
                    continue
                #计算涨跌幅百分比    
                if(dd!=''):
                    dataInfo = dd.split('\n')
                    j=0
                    dayCount = 0
                    startPrice = 0
                    for x in range(len(dataInfo)-1,0,-1):
                        #处理数据
                        if(dataInfo[x]==''):
                            continue
                        #print(dataInfo[x])
                        if(dayCount>5):
                            break
                        di = dataInfo[x]
                        if(dayCount==0):
                            startPrice = float(di.split(',')[4])
                        elif(int(di.split(',')[5])!=0):
                            add = True
                            closeP = float(di.split(',')[4])
                            info = info.replace('\n','')+',"'+str(round((closeP-startPrice)/startPrice*100,2))+'%['+str(closeP)+']"'
                            #print(info)
                        if(dayCount==0 or int(di.split(',')[5])!=0):
                            dayCount=dayCount+1
                            
                if(add):
                    out.append(info+'\n')
                #print(out)
                continue
        #输出
        ff = open(path+'/'+f.name.replace('[wait]','[处理完了]'),'w')
        for o in out:
            ff.write(o)
        ff.close()
        print('处理完了\n文件地址：'+path+'/'+f.name.replace('[wait]','[处理完了]'))
    else:
        continue