#!/usr/bin/python 
# -*- coding:utf-8 -*- 
 
import sys 
reload(sys) 
 
sys.setdefaultencoding('utf-8') 
 
import jieba 
import jieba.analyse 
import xlwt #寫入Excel表的庫 
 
if __name__=="__main__": 
 
 wbk = xlwt.Workbook(encoding = 'ascii') 
 sheet = wbk.add_sheet("wordCount")#Excel單元格名字 
 word_lst = [] 
 key_list=[] 
 for line in open('1.txt'):#1.txt是需要分詞統(tǒng)計的文檔 
 
  item = line.strip('\n\r').split('\t') #制表格切分 
  # print item 
  tags = jieba.analyse.extract_tags(item[0]) #jieba分詞 
  for t in tags: 
   word_lst.append(t) 
 
 word_dict= {} 
 with open("wordCount.txt",'w') as wf2: #打開文件 
 
  for item in word_lst: 
   if item not in word_dict: #統(tǒng)計數(shù)量 
    word_dict[item] = 1 
   else: 
    word_dict[item] += 1 
 
  orderList=list(word_dict.values()) 
  orderList.sort(reverse=True) 
  # print orderList 
  for i in range(len(orderList)): 
   for key in word_dict: 
    if word_dict[key]==orderList[i]: 
     wf2.write(key+' '+str(word_dict[key])+'\n') #寫入txt文檔 
     key_list.append(key) 
     word_dict[key]=0 
  
  
 for i in range(len(key_list)): 
  sheet.write(i, 1, label = orderList[i]) 
  sheet.write(i, 0, label = key_list[i]) 
 wbk.save('wordCount.xls') #保存為 wordCount.xls文件