python09（文字字频统计）

#文本字频统计.py
#定义函数
def getFileText():
    filTxt=open(r'C:\Users\31850\Desktop\Python\Stu_Pack\Stu_pack9\file\See You Again.txt','r').read()
#将文本里所有的字母都转换成小写
    filTxt=filTxt.lower()
 
#将所有的标点符号都用空格替代
    for ch in '!"#$%&()*+-*/,.;;<=>?@[]\\^_{}|~':
        filTxt=filTxt.replace(ch," ")
    return filTxt
 
#将只有带空格的文本按空格分成每个单词
letterTxt=getFileText()
words=letterTxt.split()
 
#定义字典变量已备记录单词出现的次数和最后输入的内容
wdCountDict={}
excludes={"the","you","your","that","will"}
#excludes={"the","of","you","your","that","will","don't"}
 
#获取某单词的拼写和累加出现的次数
for word in words:
    wdCountDict[word]=wdCountDict.get(word,0)+1
 
#将exclude里出现的单词删除掉
for word in excludes:
    del(wdCountDict[word])
 
#将字典数据转化成列表类型
items=list(wdCountDict.items())
 
#将列表按第2列x[1]降序排列
items.sort(key=lambda x:x[1],reverse=True)
 
#将结果内容以对应的格式打印出来
print("{0:<10}{1:>5}".format("word","count"))
print("_"*21)
for key,val in items:
    if len(key)>3 and val>4:
        #‘<'表示左对齐'>’表示右对其
        print("{0:<10}{1:>5}".format(key,val))