Python 正则表达式从入门到实战(看完就能直接用在项目里)

import re

import re
def get_data(result):
    if result:
        return result.group()
    return "匹配失败"
# 正确匹配：开头符合规则
res1 = re.match('python', 'python正则')
print(get_data(res1))  # python
# 错误匹配：开头不符合
res2 = re.match('python', '学习python正则')
print(get_data(res2))  # 匹配失败

import re
def get_data(result):
    if result:
        return result.group()
    return "匹配失败"
# 在任意位置查找数字
res = re.search('\d+', 'python123java456')
print(get_data(res))  # 123

import re
# 提取所有数字
res = re.findall('\d+', '价格99元，折扣8折，库存100件')
print(res)  # ['99', '8', '100']

import re
# 匹配一个数字
print(re.findall('\d', 'a1b2c3'))  # ['1','2','3']
# 匹配a或b或c
print(re.findall('[abc]', 'a1b2c3'))  # ['a','b','c']

import re
# 匹配 python 或 java
res = re.findall('python|java', '我学python和java')
print(res)  # ['python', 'java']

import re
# +：至少1次
print(re.findall('\d+', 'abc123def45'))  # ['123','45']
# ?：0次或1次（匹配https中的s）
print(re.findall('https?', 'http://baidu.com'))  # ['http']

import re
# 验证手机号：必须以1开头，总共11位
def check_phone(phone):
    return re.match('^1[3-9]\d{9}$', phone) is not None
print(check_phone('13800138000'))  # True
print(check_phone('138001380'))    # False

import re
# 分组提取 姓名、年龄
text = "姓名：小明，年龄：18"
res = re.search('姓名：(\w+)，年龄：(\d+)', text)
print(res.group(1))  # 小明（第1个分组）
print(res.group(2))  # 18（第2个分组）

import re
# 匹配连续重复的单词：hello hello
text = "hello hello world world"
res = re.findall(r'(\w+)\s+\1', text)
print(res)  # ['hello', 'world']

import re
# 匹配 <div>正则</div> 这种成对标签
text = "<div>正则</div><p>python</p>"
res = re.findall(r'<(\w+)>.*?</\1>', text)
print(res)  # ['div', 'p']

import re
text = "<div>正则</div><div>Python</div>"
# 贪婪匹配：一口气匹配整个字符串
result = re.findall(r'<div>.*</div>', text)
print(result)
# ['<div>正则</div><div>Python</div>']

import re
text = "<div>正则</div><div>Python</div>"
# 非贪婪匹配：分别匹配两个标签
result = re.findall(r'<div>.*?</div>', text)
print(result)
# ['<div>正则</div>', '<div>Python</div>']

import re
res = re.findall(r'python', 'Python PYTHON python', re.I)
print(res)  # ['Python', 'PYTHON', 'python']

import re
text = "aa\nbb"
# 不加 re.S：. 不匹配\n，匹配失败
res1 = re.findall(r'aa.*bb', text)
print(res1)  # []
# 加 re.S：. 可以匹配\n，成功
res2 = re.findall(r'aa.*bb', text, re.S)
print(res2)  # ['aa\nbb']

import re
text = "hello\nworld\npython"
# 每行开头匹配
res = re.findall(r'^\w+', text, re.M)
print(res)  # ['hello', 'world', 'python']

# 验证邮箱
def check_email(email):
    return re.match('^\w+@\w+\.\w+$', email) is not None
# 提取链接
html = '<a href="https://www.baidu.com" rel="external nofollow" >百度</a>'
links = re.findall('https?://\S+', html)