遇到的问题:
原先是 txtfile = open(r".\%s"%txt")
报错 'gbk' codec can't decode byte 0xaf in position 23: illegal multibyte sequence
修改为 txtfile = open(r".\%s"%txt,encoding="utf-8")
import os
import re
txtlist=[]
for file in os.listdir(r".\\"):
if file[-4:]==".txt":
txtlist.append(file)
for txt in txtlist:
#没加 encoding="utf-8" 直接报错 'gbk' codec can't decode byte 0xaf in position 23: illegal multibyte sequence
txtfile = open(r".\%s"%txt,encoding="utf-8")
text = txtfile.readline()
regex = re.compile(r'^\d.*')
prlist = regex.findall(text)
for i in prlist:
print(i)