统计文本单词数目--Python

统计单词数目–Python

def tihuan():  # 文本Python之禅
    txt = "The Zen of Python, by Tim Peters\
Beautiful is better than ugly.\
Explicit is better than implicit.\
Simple is better than complex.\
Complex is better than complicated.\
Flat is better than nested.\
Sparse is better than dense.\
Readability counts.\
Special cases aren't special enough to break the rules.\
Although practicality beats purity.\
Errors should never pass silently.\
Unless explicitly silenced.\
In the face of ambiguity, refuse the temptation to guess.\
There should be one-- and preferably only one --obvious way to do it.\
Although that way may not be obvious at first unless you're Dutch.\
Now is better than never.\
Although never is often better than *right* now.\
If the implementation is hard to explain, it's a bad idea.\
If the implementation is easy to explain, it may be a good idea.\
Namespaces are one honking great idea -- let's do more of those!"
    txt = txt.lower()  # 全部字符小写
    for i in "!@#$%^&*(){:'}?/|\_,.<>;`~-=+":
        txt = txt.replace(i, ' ')  # 将特殊字符转换为空格
    return txt


paichu = {'is', 'than', 'the', 'to', 'of', 'be', 'it'}  # 语法型词汇
tihuantxt = tihuan()
words = tihuantxt.split()  # 将字符串转换为列表，分隔符为空格
a = {}  # 定义空字典a
for word in words:
    a[word] = a.get(word, 0)+1  # 向字典a中赋值（键为单词，值为单词数目）
for word in paichu:
    del(a[word])  # 排除语法型词汇
items = list(a.items())  # 字典a转换为列表items[(单词,单词数目),(...),...]
items.sort(key=lambda x: x[1], reverse=True)  # 列表items按照单词数目从大到小排列
# key=lambda x:x[1]--<函数名>=lambda <参数列表>:<表达式>（lambda函数，将函数名作为结果返回）
for b in range(10):  # 单词数目前十
    word, count = items[b]  # word赋值列表items[b][0],count赋值列表items[b][1]
    print("{:<3}{:>2}个".format(word, count), end="， ")