根据某篇文章，从中随机抽取6句话，然后再生成 随机的词组

#-*- coding:utf-8 -*-
import sys
reload(sys)
sys.setdefaultencoding("gbk")



def autotxt(fname1,times):
 import random
 import jieba

 file = open(fname1)
 string=file.read()
 listzk=[]
 listzk=string.split()
 
 dataset_file = []
 for i in range(times):
  dataset_file.append(listzk[random.randint(0,len(listzk)-1)])
  dataset_file.append(listzk[random.randint(0,len(listzk)-1)])
 #dataset_file = ["",""]
 print("\n分词前：", dataset_file)
 for i, each_sentence in enumerate(dataset_file):
  dataset_file[i] = " ".join(jieba.cut(each_sentence))
  print("\n分词后：", dataset_file)
 model = {}

 for line in dataset_file:
    line = line.lower().split()
    for i, word in enumerate(line):
        if i == len(line)-1:   
            model['END'] = model.get('END', []) + [word]
        else:    
            if i == 0:
                model['START'] = model.get('START', []) + [word]
            model[word] = model.get(word, []) + [line[i+1]]
 print("\n模型：", model)
 generated = []
 while True:
    if not generated:
        words = model['START']
    elif generated[-1] in model['END']:
        break
    else:
        words = model[generated[-1]]
    generated.append(random.choice(words))
 print("\n生成的一个结果：" + "".join(generated))
 #file.close()


#########################
autotxt('readme.txt',6)  # 在文件中，随机抽取6句话，并根据这6句话，随机生成一个新的词组