Python修改文件编码格式
#修改文件编码格式
import chardet
#查看当前文件编码格式
filename_in = '2017.2-2022.9.csv'
with open(filename_in, 'rb') as f:
data = f.read()
encoding_type = chardet.detect(data)
print(encoding_type)
import chardet
import codecs
filename_out = '2017.2_2022.9_new.csv'
# 输入文件的编码类型
encode_in = 'GB2312'
# 输出文件的编码类型
encode_out = 'UTF-8'
with codecs.open(filename=filename_in, mode='r', encoding=encode_in) as fi:
data = fi.read()
with open(filename_out, mode='w', encoding=encode_out) as fo:
fo.write(data)
fo.close()
with open(filename_out, 'rb') as f:
data = f.read()
print(chardet.detect(data))