import sys

 reload(sys)

 sys.setdefaultencoding('utf-8')

 from datetime import datetime

 from elasticsearch import Elasticsearch

 from os import path

 import jieba

 import random

 es = Elasticsearch()

 filePath = path.dirname(__file__)

 # index1:wordcount

 # stopwords

 stopWordFile = u'stopwords.txt'

 stopWordList = []

 for L in open(path.join(filePath , stopWordFile)).readlines():

     stopWordList.append(L.strip().decode('utf-8'))

 stopWordList.extend([u'腾讯',u'视频' , u'。'])

 stopWordList = set(stopWordList)

 # information words

 new = 'words.txt'

 text = open(path.join( filePath , new )).read().strip('\r')

 wordDict = {}

 for w in jieba.cut(text):

     if w not in stopWordList:

         wordDict.setdefault(w , 0)

         wordDict[w] += 1

 for key in wordDict.keys():

     data = {'word':key , 'count':wordDict[key]}

     es.index(index = 'wordcount' , doc_type = 'test' , body = data)