使用python批量修改文本文件编码格式
把文本文件的编码格式进行批量幻化，比如ascii， gb2312， utf8等，相互转化，字符集的大小来看，utf8>gb2312>ascii,因此最好把gb2312转为utf8，否则容易出现乱码。
gb2312和utf-8的主要区别：
关于字库规模： UTF-8 > gb2312（utf8字全而gb2312只有汉字）
关于保存大小： UTF-8> gb2312 （utf8更臃肿、加载更慢，gb2312更小巧，加载更快）
关于适用范围：gb2312主要在中国大陆地区使用，是一个本地化的字符集，UTF-8包含全世界所有国家需要用到的字符，是国际编码，通用性强。UTF-8编码的文字可以在各国支持UTF8字符集的浏览器上显示。
立即学习“Python免费学习笔记（深入）”；
import sys
import chardet
import codecs
def get_encoding_type(fileName):
'''print the encoding format of a txt file '''
with open(fileName, 'rb') as f:
data = f.read()
encoding_type = chardet.detect(data)
#print(encoding_type)
return encoding_type
# such as {'encoding': 'GB2312', 'confidence': 0.99, 'language': 'Chinese'}
def convert_encoding_type(filename_in, filename_out, encode_in="gb2312", encode_out="utf-8"):
'''convert encoding format of txt file '''
#filename_in = 'flash.c'
#filename_out = 'flash_gb2312.c'
#encode_in = 'utf-8' # 输入文件的编码类型
#encode_out = 'gb2312'# 输出文件的编码类型
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))
if __name__=="__main__":
# fileName = argv[1]
# get_encoding_type(fileName)
# convert_encoding_type(fileName, fileName)
filename_of_files = sys.argv[1] #the file contain full file path at each line
with open(filename_of_files, 'rb') as f:
lines = f.readlines()
for line in lines:
fileName = line[:-1]
encoding_type = get_encoding_type(fileName)
if encoding_type['encoding']=='GB2312':
print(encoding_type)
convert_encoding_type(fileName, fileName)
print(fileName)补充：python实现文件批量转为utf-8格式
python实现文件批量转为utf-8格式
xml_path = './'
with open(xml_path , 'rb+') as f:
content = f.read()
codeType = detect(content)['encoding']
content = content.decode(codeType, "ignore").encode("utf8")
fp.seek(0)
fp.write(content) 
