正則表達式就是定義一個字符串的匹配模式。
與正則表達式相關(guān)的文檔如下:

例子1：假如我們想要得到6-20位字符串并且該字符串由數(shù)字字母下劃線構(gòu)成。
在沒有使用正則表達式需要寫如下的代碼：

def is_true(num):
    if 6 <= len(num) <= 20:
        for x in num:
            if not ('0' <= x <= '9' or 'A' <= x <= 'Z'
                    or 'a' <= x <= 'z' or x == '_'):
                return False
        return True
    return False

在使用正則表達式之后：

    username = input('username = ')
    pattern1 = re.compile(r'^[0-9a-zA-Z_]{6,20}$')
    m1 = pattern1.match(username)

下面就是一個完整使用正則表達式的例子：

import re


def main():
    username = input('username = ')
    qqnum = input('qqnum = ')
    pattern1 = re.compile(r'^[0-9a-zA-Z_]{6,20}$')
    m1 = pattern1.match(username)
    if not m1:
        print('用戶格式錯誤')
    m2 = re.match(r'^[1-9]\d{4,11}$', qqnum)  # 在使用r的時候表示字符串為原始的字符串，如果不使用r那么在這里的正則表達式就該寫成:'^[1-9]\\d{4,11}$'
    if not m2:
        print('QQ號格式錯誤')
    if m1 and m2:
        print('匹配成功')

if __name__ == '__main__':
    main()

map函數(shù)的使用：

from re import findall


def main():
    content = 'dsada4564sa4ds6a4d6sa'
    mylist = findall(r'\d+', content)
    mylist = list(map(int, mylist))
    print(sum(mylist) / len(mylist))  # 916.8


if __name__ == '__main__':
    main()

例子

1.手機號的驗證

import re


def main():
    pattern = re.compile(r'(?<=\D)1([38][0-9]|[5][0-35-9]|[4][57]|[7][678])\d{8}(?=\D)')
    sentence = '大1558454564564架上15502344653讀看18883362572灑金18883362572ljl13402311456ll'
    for temp in pattern.finditer(sentence):
        print(temp)  # <_sre.SRE_Match object; span=(16, 27), match='15502344653'>
        print(temp.group())  # 15502344653
        print(temp.span())  # (16, 27)


if __name__ == '__main__':
    main()

2.替換字符串中的不良文件：

import re


def main():
    sentence = '我操你大爺?shù)娜漳愣敻赡闳死褷擣uck你姑父'
    pure = re.sub('[操艸草日干頂媽]|fuck|shit', '*',
                  sentence, flags=re.IGNORECASE)
    print(pure)
    sentence = 'Your go your way, I will go mine!'  # 會將 , !.改成空格字符串
    mylist = re.split(r'[\s,!.]', sentence)
    print(mylist)

    # 貪婪匹配
    sentence = 'aabahdhsjb'
    m = re.match(r'a.*b', sentence)
    print(m)
    # 懶惰匹配
    sentence = 'aabahdhsjb'
    m = re.match(r'a.*?b', sentence)
    print(m)


if __name__ == '__main__':
    main()

3.得到字符串中的數(shù)字求平均值：

import re


def avage(num):
    pattern = re.compile(r'\d+')
    m = pattern.findall(num)
    totle = 0
    i = 0
    for x in m:
        totle += int(x)
        i += 1
    return totle / i


def main():
    n = input('n = ')
    print(avage(n))


if __name__ == '__main__':
    main()