正则提取数字，并返回列表以.csv保存本地

 

 

import re
import pandas as pd

def squeeze(value: str, replace=" ") -> str:
    re1 = re.sub(r"[\x00-\x20]+", replace, value).strip()     #将所有空格字符序列替换为单个空格.
    date = re.findall(r'\d{4}-\d{2}-\d{2}',re1)[:10]
    order = re.findall(r'(\d{2})万',re1)
    list1 = zip(date,order)
    return list(list1)


if __name__ == '__main__':
    s = str = "2020-07-15  37万  2020-07-16  30万   2020-07-17   31万 2020-07-18   32万    2020-07-19   33万     2020-07-20   34万 2020-07-21   33万    2020-07-22   32万     2020-07-23   38万 2020-07-24   39万     2020-07-25   40万        2020-07-26   41万 2020-07-27   42万     2020-07-28   41万         2020-07-29   40万 2020-07-30  43万"
    ret = squeeze(s)
    print(ret)
    #保存路径
    name = ['date','order_cnt']
    test =pd.DataFrame(columns=name,data = ret)
    test.to_csv('D:/applied data/test.csv',encoding='gbk')