python open gbk_【转】用python将GBK编码文件转为UTF-8编码文件

#!/usr/bin/env python

# -*- coding: utf-8 -*-

__author__ = ''

import logging, os, argparse, textwrap

import time

import chardet

# Default configuration will take effect when corresponding input args are missing.

# Feel free to change this for your convenience.

DEFAULT_CONF = {

# Only those files ending with extensions in this list will be scanned or converted.

'exts' : ['cfg'],

'overwrite' : False,

'add_BOM' : False,

'convert_UTF' : False,

'confi_thres' : 0.8,

}

# We have to set a minimum threshold. Only those target_encoding results returned by chartdet that are above that threshold level would be accepted.

logging.basicConfig(format='%(levelname)s:%(message)s', level=http://logging.INFO)

log = logging.getLogger(__name__)

class Convert2Utf8:

def __init__(self, args):

self.args = args

def walk_dir(self, dirname):

for root, dirs, files in os.walk(dirname):

for name in files:

extension = os.path.splitext(name)[1][1:].strip().lower()

# On linux there is a newline at the end which will cause the match to fail, so we just 'strip()' the '\n'

# Also, add 'lower()' to ensure matching

if (extension in self.args.exts):

fullname = os.path.join(root, name)

try:

self.convert_file(fullname)

except IOError:

log.error("Unable to read or write the file: %s. Please check the file's permission.", fullname)

except KeyboardInterrupt:

log.warning("Interrupted by keyboard (e.g. Ctrl+C)")

exit()

# else: