返回txt文档编码格式

1. 安装chardet

pip install chardet

2. 获得文本文档编码类型

import chardet
from chardet.universaldetector import UniversalDetector
def GetEncoding(file):
    """
    :param file:
    :return: {'encoding': '', 'confidence': 0.99, 'language': ''}
    """
    txt = open(file, "rb")
    detector = UniversalDetector()
    for line in txt.readlines():
        detector.feed(line)
        if detector.done:
            break
    detector.close()
    txt.close()
    return detector.result

my_path = 'C:\\Users\\xiaocuncun\\Desktop\\my1200_web\\my_test.txt'
f = open(my_path, 'rb')
str1 = f.read()
char_encoding= chardet.detect(str1)
print(f'字符串为：{str1}')
print(f'字符串编码信息为：{char_encoding}' ) 
print(f'字符串编码为： {char_encoding["encoding"]}')

3. 把txt变成csv

import csv
import chardet

my_path = '.\\AuditTrail0.txt'
with open(my_path, 'rb') as f:
    str1 = f.read()
char_encoding= chardet.detect(str1)
encoding_format = char_encoding["encoding"]

csv_file = '.\\AuditTrail0.csv'

with open(my_path,'r',encoding=encoding_format) as file:
    lines = file.readlines()

with open(csv_file,'w',newline='',encoding=encoding_format) as file:
    writer = csv.writer(file)
    for line in lines:
        row = line.strip().split('\t')
        writer.writerow(row)