jieba分词

jieba分词，聊斋29

代码:

import jieba

txt = open("D:\python-learning\liaozhai.txt", "r", encoding='utf-8').read()
words = jieba.lcut(txt) 
counts = {}

for word in words:
    if len(word) == 1:
        continue
    elif word == "小倩" or word == "鬼妻":
        rword = "聂小倩"
    elif word == "采臣":
        rword = "唐僧"
    elif word == "黑山" or word == "万妖群魔之首":
        rword = "黑山老妖"
    elif word == "十四娘":
        rword = "辛十四娘"
    elif word == "子楚":
        rword = "孙子楚"
    elif word == "赵阿宝":
        rword = "阿宝"
    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))