python正則表現は中国語の数字処理をフィルタします。

def numberChange():
    f = open('C:\Users\Administrator\Desktop\mytest.txt','r')
    s = f.read()
    #              20202           1212    10.12             1244525.000            0.01             0001                        123,450,000.000                      11 2200           

    for i in ["utf8","gb2312"]:
        try:
            data = s.decode(i)
            break
        except:
            pass
    #      ‘u’   
    number = re.compile(ur'([               ]+|[0-9]+[,]*[0-9]+.[0-9]+)')
    pattern = re.compile(number)
    all = pattern.findall(data)
    for i in all:
        print i

    #      
    # 20202
    # 1212
    # 10.12
    # 1244525.000
    # 0001
    # 123, 450, 000
    #           
    # 11
    #  2200
    #      
    f.close()