简体转繁体

# coding = utf-8
import os, re, platform, chardet, linecache, sys, codecs
from langconv import *

def getSuffixConfig():
	'''
	获取后缀配置列表
	'''
	suffixList = []
	re_fix = re.compile("^\.\w*")
	config = open("getSuffixConfig.txt", "r")
	for line in config.readlines():
		if re_fix.findall(line):
			suffixList.append(line)

	config.close()
	return suffixList

def getCharDet(filename):
	'''
	获取字符集
	'''
	detFile = open(filename, "r")
	encoding = {}
	fileData = detFile.read()
	if len(fileData) > 0:
		encoding = chardet.detect(fileData)
	detFile.close()
	if encoding:
		return encoding["encoding"]
	else:
		return ""

def strQ2B(ustring):
	'''
	全角转半角
	'''
	rstring = ""
	for uchar in ustring:
		inside_code = ord(uchar)
		if inside_code == 12288:	#空格
			inside_code = 32
		elif: (inside_code >= 65281 and inside_code <= 65374):
			inside_code -= 65245
		rstring += unichr(inside_code)
	return rstring

def walkCallback(args, dire, fis):
	'''
	walk遍历的每步回调
	'''
	fix_list = getSuffixConfig()

	for f in fis:
		print args[1] + dire[line(args[2]):]
		Ext = os.path.splitext(f)
		for suffix in fix_list:
			if Ext[1] == suffix:
				convFile = open(dire + os.sep + f, "r")
				if not os.path.exists(args[1] + dire[len(args[2]):]):
					os.makedirs(args[1] + dire[len(args[2]):])
				outFile = open(args[1] + dire[len(args[2]):] + os.sep + f, "w")

				print f + " -> started"
				tempCharSet = getCharDet(dire + os.sep + f)
				if not tempCharSet:
					print "tempCharSet is null"
					continue	#空文件
				if args[0] == "1" :
					index = 1
					charSet = ""
					for line in convFile.readlines():
						charSet = chardet.detect(line)["encoding"]
						if not charSet:
							charSet = tempCharSet
						if not isinstance(line, unicode):
							res_test = ""
							try:
								try:
									res_test = line.decode("utf-8")
								except:
									res_test = line.decode("GB18030")
							except:
								res_test = line.decode(charSet)
								raw_input("error")	#提示错误
								line = res_test
						line = strQ2B(line)
						line = Converter("zh-hant").convert(line)
						line = line.encode("utf-8")
						outFile.write(line)
						index += 1
					convFile.close()
					outFile.close()
					print f + ' -> Done!\n'
					break


#main
if platform.system() != "Windows":
	print "Please run this script based on windows system"
else :
	reload(sys)
	sys.setdefaultencoding('GB18030')

	root_str = "需要转换的目录（当前系统目录分隔符\'" + os.sep + "\'）："
	root = raw_input(root_str.decode("utf-8").encode("gbk"))

	out_str = "输出目录（当前系统目录分隔符\'" + os.sep + "\'）："
	out = raw_input(out_str.decode("utf-8").encode("gbk"))

	switch_str = "转换方向 1->简转繁  2->繁转简:"
	t_s_switch =  raw_input(switch_str.decode("utf-8").encode("gbk"))

	print "\nStart"
	os.path.walk(root, walkCallback, (t_s_switch, out, root))
	print "\nAll Finished"