python unicode字符编解码问题参见【Python笔记2.1】
python中用zipfile解压zip包网上资料一堆,这里就不多说了。
下面使用【Python笔记2.1】中总结出来的字符编解码函数来解决zipfile解压zip包的问题。时间仓促,直接上代码。
完整示例代码(含【Python笔记2.1】中的代码)
# -*- coding: utf-8 -*-
#!/usr/bin/env python2
"""
Created on Mon Jul 23 15:40:00 2018
@author:
"""
import os
import zipfile
# UTF_8_BOM = b'\xef\xbb\xbf'
def un_zip(filepath, dst_dir):
try:
encoding = 'utf-8'
dst_dir = try_encode(dst_dir, encoding)
zip_file = zipfile.ZipFile(filepath)
for names in zip_file.namelist():
unzip_file = zip_file.extract(names, dst_dir)
rename_file = os.path.join(dst_dir, try_encode(str_decode(names), encoding))
os.rename(unzip_file, rename_file)
zip_file.close()
return 0, 'unzip Success'
except Exception as err:
print('[un_zip]: Exception.ERROR: ', err)
return -1, 'ERROR, unzip error! please upload the zip package named in utf-8 format.'
def try_encode(s, encoding="utf-8"):
if s is None:
print('[tryEncode]: input param None!')
return s
try:
return s.encode(encoding)
except UnicodeEncodeError as err:
print(err)
def try_decode(s, decoding="utf-8"):
try:
return s.decode(decoding)
except UnicodeDecodeError as err:
print(err)
def str_decode(string):
while True:
dec = try_decode(string, "utf-8")
if dec is not None:
break
dec = try_decode(string, "ascii")
if dec is not None:
break
dec = try_decode(string, "GB2312")
if dec is not None:
break
dec = try_decode(string, "GBK")
if dec is not None:
break
dec = try_decode(string, "Big5")
if dec is not None:
break
print('[str_decode]: unknown encoding')
dec = None
break
return dec