#CalHamletV1.py
#hamlet文本下载链接：https://python123.io/resources/pye/hamlet.txt
def getText():     #对文本归一化处理（变为小写，特殊字符替换为空格）
    txt = open("hamlet.txt","r").read()
    txt = txt.lower()   #所有字母变为小写
    for ch in ‘!"#$%&(）*+,-./:;<=>?@[\\]^_{|}`~‘:
        txt= txt.replace(ch," ")  #用空格代替各种特殊字符
    return txt
hamletTxt=getText()
words =hamletTxt.split()  #根据空格分隔每一个字母
counts ={}
for word in words:
    counts[word] = counts.get(word,0) + 1  #如果键不存在字典中，给出默认值
items = list(counts.items())   #变为列表类型，便于排序操作
items.sort(key=lambda x:x[1], reverse=True)   #对第二个元素，从大到小倒排
#sort方法小知识：参数lambda用来指定列表中使用哪一个多元选项的列作为排序列，默认的排序是从小到大；reverse设为True，则排序从大到小
for i in range(10):   #输出最多的10个单词
    word, count = items[i]
    print("{0:<10}{1:>5}".format(word, count))

#CalThreeKingdomsV1.py
import jieba
txt = open("threekingdoms.txt","r",encoding="utf-8").read()
words = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
          continue
    else:
        counts[word]=counts.get(word,0)+ 1
items = list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)
for i in range(15):
    word,count = items[i]
    print("{0:<10}{1:>5}".format(word,count))

#CalThreeKingdomsv2.py
import jieba
txt = open("threekingdoms.txt","r",encoding="utf-8").read()
excludes = {"将军","却说","荆州","二人","不可","不能","如此"}
words = jieba.lcut(txt)
counts={}
for word in words:
    if len(word) == 1:
        continue
    elif word =="诸葛亮" or word == "孔明曰":
        rword = "孔明"
    elif word =="关公"or word =="云长":
        rword ="关羽"
    elif word =="玄德" or word =="玄德曰":
        rword ="刘备"
    elif word == "孟德"or word =="丞相":
        rword = "曹操"
    else:
        rword = word
    counts[rword]= counts.get(rword,0)+ 1
for word in excludes:
    del counts[word]
items = list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)
for i in range(10):
    word,count = items[i]
    print("{0:<10}{1:>5}".format(word,count))