学习笔记(32):Python 面试100讲（基于Python3.x）-提取HTML页面中的URL

立即学习:https://edu.csdn.net/course/play/26755/340150?utm_source=blogtoedu

import re

print(re.match('.*hello', 'hello'))

s = "Today is 2020-01-23"
m = re.match('\d{4}-\d{2}-\d{2}', s)
# print(m.group())


# match匹配，search搜索
m = re.match('python.*', 'python language')
print(m)
m = re.search('python', 'python language')
print(m)
m = re.search('1\d{10}', '手机号是1222222222333333')
print(m)

# 123-12345678-1234
m = re.search('(\d{3})-(\d{7,})-(\d{3,})','电话是024-12345678-1234')
print(m.group())
print(m.groups())
print(m.groups()[0])
print(m.groups()[1])
print(m.groups()[2])


# findall
m = re.findall("[0-9a-zA-Z]+@+[0-9a-zA-Z]+\." + 'net|' + "[0-9a-zA-Z]+@+[0-9a-zA-Z]+\." + 'com', "我的Email是[email protected],或者[email protected],或者[email protected]", re.I)
print(m)


def fun(matched):
    return "<" + matched.group() + ">"
res = re.subn("-?\d+(\.\d+)?", fun, "PI is 3.1415926, 1 + 1.1 = 2.1")
print(res)