jieba分词-526互联

print("徐嘉俊32")
import jieba
txt = open("E:\\大学\\Python\\西游记.txt","r",encoding='gb18030').read()
words = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:      #排除单个字符的分词结果
        continue
    elif word == "行者" or word == "大圣" or word =="老孙":
        rword = "孙悟空"
    elif word == "师父" or word == "三藏" or word == "长老":
        rword = "唐僧"
    elif word == "呆子":
        rword = "八戒"
    else:
        rword = word
    counts[rword] = counts.get(rword,0) + 1
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))