使用python读取文本中结构化数据

需求

read some .txt file in dir and find min and max num in file.
solution:

echo *.txt > file.name in linux shell
>>>execfile(“mytest.py”);       //equivalent to run mytest.m in matlab
import os
fileobj = open("./test2images/2d_xxx.name");
filestring = fileobj.readline();    //line is a list stored all .txt name
filestring = filestring.split();
dir = './test2images/'
x = [];
y = [];
for i in filestring:
dataname = open(dir + i);
for j in range(1,15):
data = dataname.readline();
if not data:
break;
data = data.strip('\r\n');
data = data.split();                //It will split the long string line as a list of strings
x.append(int(data[0]));
y.append(int(data[1]));
print min(x)
print min(y)
//normal structure of while circulation
#   while 1:
#       data = dataname.readline();
#       if not data:
#           break;

读写中英文参杂的文本

str.decode('utf8')    #str先使用utf8的方式解码，得到每个汉字为一个字符
str.encode('utf8')    #保存str到文件之前，先使用utf8的方式编码，再存储