（六）文本挖掘——名词提取

# @Time : 2021/3/16 19:54
# @Author : chao

#名词提取
from collections import Counter

f1 = open(r'C:\Users\代码\去除停用词并分词\去除停用词并分词结果\zong_fengci_tingyongci2.txt',
          'r', encoding='utf-8')
#构建一个空列表，用以保存提取出的每个词
words = []
#构建一个空列表，用于保存提取出的名词
ming_words = []
for i in f1.readlines():
    #print(i.replace('x','').split(" "))
    line = i.split(" ")
    for j in line:
        if(j!='' and j!='\n' and j!='x'):
            words.append(j)
#提取名词
for i in words:
    #if('n' in i):
        ming_words.append(i)

#统计词频
counter = Counter(ming_words)
dictionary=dict(counter)
# get to k most frequently occuring words
k=100
res=counter.most_common(k)
print(res)