【Day3】2.re模块使用案例

课程目标

1、提取

2、匹配

3、替换

1、提取

import re
ret = re.findall([正则表达式])
#  返回的类型是列表

2、匹配

import re
ret = re.match([正则表达式],[被匹配的字符串])
if(ret):
    return '匹配成功'
else:
    return '匹配失败'
#  如果匹配成功,返回<class 're.Match'>对象
#  如果匹配不成功,返回None

3、替换

import re
ret = re.sub([正则表达式],[替换成的字符串],[被替换的字符串])
import re
with open('index.html','r',encoding='utf-8') as f:
        html = f.read()
        # print(html)
        html = re.sub('\n','',html)
        pattern_1 = '<div class="email">(.*?)</div>'
        ret_1 = re.findall(pattern_1,html)
        print(ret_1[0].strip())

pwd_pattern = r'^[a-zA-Z][a-zA-Z0-9_]{5,15}$'
pwd1 = '123'
pwd2 = 'a123123'
pwd3 = 'aaa'
print(re.match(pwd_pattern,pwd1))
print(re.match(pwd_pattern,pwd2))
print(re.match(pwd_pattern,pwd3))

index.html

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>Title</title>
</head>
<body>
<div>
    <div class="email">
        Email:[email protected]
    </div>
    <div class="mobile">
        Mobile:18688888888
    </div>
</div>
</body>
</html>

猜你喜欢

转载自www.cnblogs.com/zsczsc/p/11888864.html
今日推荐