一.對西遊記文件的分詞

程式碼如下：

import jieba

import jieba


def takeSecond(elem):
    return elem[1]


def main():
    path = "西遊記.txt"
    file = open(path, "r", encoding="utf-8")
    text = file.read()
    file.close()

    words = jieba.lcut(text)
    counts = {}
    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[word] = counts.get(word, 0) + 1

    items = list(counts.items())
    items.sort(key=takeSecond, reverse=True)

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

main()

執行結果如下：

　　一部 35
　　三藏 30
　　行者 28
　　如來 20
　　唐僧 18
　　聖僧 18
　　八戒 15
　　師父 14
　　佛祖 14
　　大仙 12
　　沙僧 10
　　正是 9
　　金剛 9
　　四眾 8
　　山門 8
　　東土 8
　　菩薩 8　　
　　論經 8
　　傳經 7
　　長老 7