python实例：利用jieba库，分析统计金庸名著《倚天屠龙记》中人

txt=open("C:UsersBeckhamDesktoppython倚天屠龙记.txt","r",encoding=‘utf-8‘).read()    #打开倚天屠龙记文本
words=jieba.lcut(txt)   #jieba库分析文本

for word in words:    #筛选分析后的词组
    if len(word)==1:   #因为词组中的汉字数大于1个即认为是一个词组，所以通过continue结束点读取的汉字书为1的内容
        continue
    elif word=="教主":  #书中教主也指张无忌，即循环读取到教主也认为是张无忌这个名字出现一次，后面类似
        rword="张无忌"
    elif word=="无忌":
        rword="张无忌"
    elif word=="义父":
        rword="谢逊"
    else:
        rword=word
    counts[rword]=counts.get(rword,0)+1  #对rword出现的频率进行统计，当rword不在words时，返回值是0，当rword在words中时，返回+1，以此进行累计计数

for word in exculdes:#如果循环读取到的词组与exculdes字典内的内容匹配，那么过滤掉（不显示）这个词组
    del(counts[word])

items=list(counts.items())#字典到列表
items.sort(key=lambda x:x[1],reverse=True)#lambda是一个隐函数，是固定写法，以下命令的意思就是按照记录的第2列排序  

    
for i in range(15):#显示前15位数据
    word,count=items[i]
    print("{0:<10}{1:>10}".format(word,count)) #0:<10左对齐，宽度10，”>10"右对齐

# -*-coding:utf8-*-
# encoding:utf-8

import jieba   #倒入jieba库

txt=open("C:UsersBeckhamDesktoppython倚天屠龙记.txt",encoding=‘utf-8‘).read()    #打开倚天屠龙记文本

exculdes={"说道","甚么","自己","武功","咱们","一声","心中","少林","一个","弟子","明教","便是","之中","如何","师父","只见","怎么","两个","没有","不是","不知","这个","不能","只是","他们","突然","出来","如此","今日","知道","我们","心想","二人","两人","不敢","虽然","姑娘","这时","众人","可是","原来","之下","当下","身子","你们","脸上","左手","手中","倘若","之后","起来","喝道","武当派","跟着","武当","却是","登时","身上","说话","长剑","峨嵋派","性命","难道","丐帮","兄弟","见到","魔教","不可","心下","之间","少林寺","伸手","高手","一招","这里","正是"}   #创建字典，主要用于存储非人物名词，供后面剔除使用

words=jieba.lcut(txt)   #jieba库分析文本
counts={}

for word in words:    #筛选分析后的名词
    if len(word)==1:   #因为词组中的汉字数大于1个即认为是一个词组，所以通过continue结束掉读取的汉字书为1的内容
        continue
    elif word=="教主":  #书中教主也指张无忌，即循环读取到教主也认为是张无忌这个名字出现一次，后面类似
        rword="张无忌"
    elif word=="无忌":
        rword="张无忌"
    elif word=="义父":
        rword="谢逊"
    else:
        rword=word
    counts[rword]=counts.get(rword,0)+1  #对rword出现的频率进行统计，当rword不在words时，返回值是0，当rword在words中时，返回+1，以此进行累计计数

for word in exculdes:#如果循环读取到的词组与exculdes字典内的内容匹配，那么过滤掉（不显示）这个词组
    del(counts[word])

items=list(counts.items())#字典到列表
items.sort(key=lambda x:x[1],count)) #0:<10左对齐，宽度10，”>10"右对齐