西游记用字统计

#!/usr/bin/env python

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

import re

import sys

reload(sys)

sys.setdefaultencoding("utf8")

def translate(str):

line = str.strip().decode('utf-8', 'ignore') # 处理前进行相关的处理，包括转换成Unicode等

p2 = re.compile(ur'[^\u4e00-\u9fa5]') # 中文的编码范围是：\u4e00到\u9fa5

zh = " ".join(p2.split(line)).strip()

sh = "".join(zh.split())

return sh

 

def txtToDic(f):

g = open(f,'r')

txt = g.readline()

txt = unicode(txt, "utf-8")

d = {}

for i in txt:

d[i] = txt.count(i)

return d

 

def sortDic(d):

d = sorted(d.items(), key=lambda x: x[1], reverse=False)

return d

 

if __name__ == '__main__':

 

f = open('test.txt', 'r')

g = open('get.txt', 'w')

for line in f.readlines():

if line == '\n':

continue

line = line.strip()

line = translate(line)

g.write(line)

f.close()

g.close()

 

g = 'get.txt'

dic = txtToDic(g)

 

dic = sortDic(dic)

g = open('get.txt', 'w')

for item in dic:

s = item[0] + ":" + str(item[1])

g.write(s + '\n')

g.close()