python《红楼梦》人物统计

《红楼梦》人物统计

import jieba
						
txt = open("D:\红楼梦.txt", "r", \
           encoding='utf-8').read()			#打开文件

#排除不是人名的词语
excludes = {"什么", "一个", "我们", "那里", "你们", "如今", "说道", "知道", # 去掉无用的词
 "起来", "姑娘", "这里", "出来", "他们", "众人","自己","一面","太太","只见","怎么","奶奶","两个","没有","不是","不知",
            "这个","听见","这样","进来","咱们","告诉","就是","东西","回来","只是","大家","老爷","只得","丫头",
            "这些","不敢","出去","所以","不过","的话","不好","姐姐","不能","一时","鸳鸯","过来",
            "心里","二爷","如此","今日","银子","两人","还有","几个","却说","二人","二人","只管","不能","如此","这么","说话",
            "一回", "那边", "这话","外头","今儿","罢了","屋里","那些","听说","小丫头","打发","自然","如何","问道","看见","人家","不用","媳妇"
            }  
            

words = jieba.lcut(txt)				#精确模式
counts = {}
for word in words:         			#合并指代同一人的不同词语出现次数
    if len(word) == 1:
        continue
    elif word == "老太太"or word =="老祖宗":
        rword = "贾母"
    elif word == "林妹妹" or word =="林姑娘"or word =="黛玉":
        reord = "林黛玉"
    elif word =="宝钗" or word =="宝姑娘":
        rword = "薛宝钗"
    elif word =="怡红公子" or word =="宝玉":
        rword = "贾宝玉"
    elif word =="凤丫头" or word =="凤姐" or word =="凤哥儿"or word =="凤辣子":
        rword = "王熙凤"
    elif word =="蓉大奶奶" or word =="可卿":
        rword = "秦可卿"
    elif word == "湘云" or word =="史湘云":
        reord = "史湘云"
    elif word =="四姑娘" or word =="惜春":
        rword = "贾惜春"
    elif word =="凤丫头" or word =="凤姐":
        rword = "王熙凤"
    elif word =="探春" or word =="三姑娘":
        rword = "贾探春"
    else:
        rword = word
    counts[rword] = counts.get(rword,0)+1			#计数

   

for word in excludes:
    del counts[word]
    
items = list(counts.items())
items.sort(key=lambda x: x[1], reverse=True)	#排序

for i in range(20):              			#使用字典表达词频
    word, count = items[i]
print("{0:<10}{1:>5}".format(word, count))