红楼梦分词

学号15

需要把是同一个人不同说法，要合并成一个。比如 孙猴子和孙悟空，要算成一个。‪‬‪‬‪‬‪‬‪‬‮‬‪‬‫‬‪‬‪‬‪‬‪‬‪‬‮‬‫‬‪‬‪‬‪‬‪‬‪‬‪‬‮‬‭‬‫‬‪‬‪‬‪‬‪‬‪‬‮‬‫‬‫‬‪‬‪‬‪‬‪‬‪‬‮‬‫‬‭‬‪‬‪‬‪‬‪‬‪‬‮‬‫‬‪‬‪‬‪‬‪‬‪‬‪‬‮‬‪‬‮‬

import jieba
excludes = {"什么","一个","我们","那里","你们","如今","说道","知道","起来","姑娘","这里","出来","他们","众人","自己",
            "一面","只见","怎么","两个","没有","不是","不知","这个","听见","这样","进来","咱们","告诉","就是","妹妹",
            "东西","回来","只是","大家","只得","老爷","丫头","这些","不敢","出去","所以","不过","的话","不好",
            "姐姐","一时","不能","过来","心里","如此","今日","银子","几个","答应","二人","还有","只管","太太",
            "这么","说话","一回","那边","这话","外头","打发","自然","今儿","罢了","屋里","那些","听说","小丫头","不用","如何"}

txt = open("D:\PythonWork\红楼梦.txt","r",encoding='gb18030').read()

words = jieba.lcut(txt)

counts = {}

for word in words:
    if len(word) == 1:      #如果长度是一，可能是语气词之类的，应该删除掉
        continue
    elif word == "林黛玉" or word == "林妹妹":
        rword = "黛玉"
    elif word == "贾宝玉":
        rword = "宝玉"
    elif word == "奶奶" or word == "老太太":
        rword = "贾母"
    elif word == "凤姐儿":
        rword = "凤姐"
    else:
        counts[word] = counts.get(word,0) + 1

for word in excludes:
    del(counts[word])

items = list(counts.items())

items.sort(key=lambda x:x[1],reverse = True)

for i in range(20):
    word,count = items[i]
    print("{0:<10}{1:>5}".format(word,count))