Python脚本通过正则表达式处理文本文件：1.如何找出以z为结尾的所有单词（去重） 2. 如何找出4个字母单词及其频率

1.如何找出以z为结尾的所有单词

from mpmath.function_docs import re
import re  # 引入正则表达式模块

def main():
    # 以uft-8模式读取 metadata.txt文件
    with open('metadata.txt',encoding='utf-8') as f:
        passage = f.read()
    # 通过正则表达式记录所有以z为结尾的单词
    word = re.findall(r'\b\w*z\b', passage)

    # 去重
    words = set(word)
    print(words)
if __name__ == '__main__':main()

2. 如何找出4个字母单词及其频率

from mpmath.function_docs import re
import re  # 引入正则表达式模块

def main():
    with open('metadata.txt',encoding='utf-8') as f:
        passage = f.read()
    # 通过正则表达式记录所有4字单词
    word = re.findall(r'[:alpha:]{4}', passage)

    # 去重
    words = set(word)
    # 记频
    count_list = list()
    for i in words:
        count_list.append((i, word.count(i)))
    print(count_list)
if __name__ == '__main__':main()