getter.py 文件源码

def download_data(quote,day=0):
    days = day+1
    url1='http://www.google.com/finance/getprices?q='
    url2='&x=NSE&i=60&p='
    url3='d&f=d,c,o,h,l,v&df=cpct&auto=1&ts=1266701290218' 
    #Not using the ts=1266701290218 parameter, if something goes wrong, do try it
    df = pd.read_csv(url1+quote+url2+str(days)+url3,header=4,parse_dates=True,
        skiprows=[5,6,7])
    # print df
    pd.set_option('display.max_rows', 100)
    if(days>1):
        i=0
        for i in range(2,len(df)):
            # print df.iat[i,0]
            if(str(df.iat[i,0]).startswith('a')): 
                # print "the next day readings start form " + str(df.iat[i,0])
                df.iat[i,0] = df.iat[i,0][1:]
            try:
                if(int(df.iat[i,0])-int(df.iat[i-2,0])<0): 
                    break
            except:
                print df
                continue
        #i=df.index.get_loc('a',method='ffill')
        df=df.ix[0:i-2]
    # print df
    df.columns = ['DATE', 'CLOSE','HIGH','LOW','OPEN','VOLUME']
    df=df.set_index('DATE')
    #print df
    return df