python 转换文件编码格式

Posted 2023-03-08 韩搏

开发中使用脚本分析日志，遇到编码不可解析问题，故做了转换

#coding: utf-8
import os 
import sys
import chardet
import codecs

def checkFileCharset(self, file_path):
	with open(file_path, "rb") as f:
		data = f.read(4)
		charset = chardet.detect(data)['encoding']
	return charset
		
def convertEncoding(self, filename):
	source_encoding = checkFileCharset(filename)
	print("convertEncoding file name:%s encode:%s" % (filename, source_encoding))
	if source_encoding.find("UTF-8") < 0:
		content = codecs.open(filename, 'r', encoding=source_encoding).read()
		# content = content.decode(source_encoding, 'ignore')# .encode(source_encoding)
		codecs.open(filename, 'w', encoding="UTF-8-SIG").write(content)

if __name__=="__main__":
	if len(sys.argv) >= 2:
		convertEncoding(sys.argv[1])