import jieba
txt=open('D:/紅樓夢/紅樓夢.txt',"r",encoding='utf-8').read()
excludes = {"什麼","一個","我們","你們","如今","說道","知道","姑娘",\
"起來","這裡","出來","眾人","那裡","自己",\
"太太","一面","只見","兩個","沒有","怎麼","不是","不知","這個","聽見",\
"這樣","進來","咱們","就是","東西","告訴","回來","回來","只是","大家",\
"老爺","只得","這些","他們","丫頭","不敢","出去","所以","薛姨媽","不過",\
"不好","姐姐","的話","一時","鴛鴦","過來","不能","心裡","二爺","過來",\
"如此","銀子","今日","二人","答應","她們","那麼","幾個","還有","只管","說話",\
"那邊","一回","這麼"}
words =jieba.lcut(txt)
counts = {}
for word in words:
if len(word) == 1:
continue
elif word == "鳳姐" or word == "王夫人" or word =="鳳姐兒":
rword = "王熙鳳"
elif word == "老太太" or word =="賈母" or word =="奶奶":
rword = "賈母"
else:
rword = word
counts[rword] = counts.get(rword,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))

print("曾俊諶，學號：2020310143026")