Python处理MLDonkey 下载中文文件乱码问题 (2)

# -*- coding: cp936 -*-

############################################################

# convert mldonkey's chinese

# Version:    0.1

# Author: kongxx

# Email: kongxxcn@yahoo.com.cn

############################################################

import os ,sys ,string ,urllib ,telnetlib ,operator

# define the mldonkey incoming dir

sdir='/usr/local/mldonkey/incoming/'

#flag the num

sNum='0123456789'

#length

len8 = 8

len12 = 12

lengths = [len8 ,len12]

def convert():

     filenames=os.listdir(sdir)

     for filename in filenames :

         for length in lengths :

              s1 = filename

              s2 = convertName(filename ,length)

              try :

                   if s1 != s2 :              

                       print '############################################################'

                       print 'The source name is:' + s1

                       print 'The target name is:' + s2

                       print ''

                       confirm = raw_input('Do you confirm rename the file[yes or no]? ')

                       if confirm == 'yes' :

                            os.rename(sdir + s1 ,sdir + s2)

                            break

              except UnicodeDecodeError:

                   print ''

# convert ths file name

# param s the filename

# param length

def convertName(s ,length) :

     location = 0

     ret = ''

     if length not in lengths:

         return s

     while True :

         if location + length <= len(s) :

              subStr = s[location:location + length]

              if check(subStr) :

                   if length == len8 :

                       ret += "%" + hex((int)(subStr[1:4]))[2:4] + "%" + hex((int)(subStr[5:8]))[2:4]

                   if length == len12 :

                       ret += "%" + hex((int)(subStr[1:4]))[2:4] + "%" + hex((int)(subStr[5:8]))[2:4] + "%" + hex((int)(subStr[9:12]))[2:4]

                   location = location + length

              else :

                   ret += s[location :location + 1]

                   location = location + 1

         else :

              ret += s[location:]

              break

     ret = urllib.unquote(ret)

     if ret == s : return s

     try :

         if length == len8 :

              return ret.decode('GBK')

         if length == len12 :

              return ret.decode('UTF-8')

     except UnicodeDecodeError:

         return ret

def check(s):

     if len(s) != len8 and len(s) != len12:

         return False

     if s[0] != '_' or s[4] != '_' :

         return False

     if len(s) == len12 and s[8] != '_':

         return False

     s = s.replace('_','')

     for c in s :

         if (c not in sNum) :return False

     return True

convert()