import jieba

txt = open("《西遊記》.txt", "r", encoding='utf-8').read()

words = jieba.lcut(txt) # 使用精確模式對文字進行分詞

counts = {} # 通過鍵值對的形式儲存詞語及其出現的次數

for word in words:

if len(word) == 1:

continue

elif word == "大聖" or word == "老孫" or word == "行者" or word == "孫大聖" or word == "孫行者" \
　　　　　　or word == "猴王" or word == "悟空" or word == "齊天大聖" or word == "猴子":

rword = "孫悟空"

elif word == "師父" or word == "三藏" or word == "聖僧":

rword = "唐僧"

elif word == "呆子" or word == "八戒" or word == "老豬":

rword = "豬八戒"

elif word == "沙和尚":

rword = "沙僧"

elif word == "妖精" or word == "妖魔" or word == "妖道":

rword = "妖怪"

elif word == "佛祖":

rword = "如來"

elif word == "三太子":

rword = "白馬"

else:

rword = word

counts[rword] = counts.get(rword, 0) + 1

items = list(counts.items()) # 將鍵值對轉換成列表

items.sort(key=lambda x: x[1], reverse=True) # 根據詞語出現的次數進行從大到小排序

for i in range(20):

word, count = items[i]

print("{0:<10}{1:>5}".format(word, count))