返回txt文档编码格式
- 安装
chardet
pip install chardet
- 获得文本文档编码类型
import chardet
from chardet.universaldetector import UniversalDetector
def GetEncoding(file_path):
with open(file_path, 'rb') as txt:
detector = UniversalDetector()
for line in txt.readlines():
detector.feed(line)
if detector.done:
break
detector.close()
return detector.result
my_path = '.\\my_test.txt'
with open(my_path, 'rb') as f:
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"]}')
print(f'附:{GetEncoding(my_path)}')
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)