Python re 库从入门到高阶用法详解

import re
# 示例1：匹配成功
result = re.match(r'hello', 'hello world')
print(result.group())  # 输出: hello
# 示例2：匹配失败（不是从开头匹配）
result = re.match(r'world', 'hello world')
print(result)  # 输出: None

def starts_with_letter(s):
    return bool(re.match(r'^[a-zA-Z]', s))
print(starts_with_letter("hello"))  # True
print(starts_with_letter("123hello"))  # False

import re
# 示例：在整个字符串中查找
result = re.search(r'world', 'hello world')
print(result.group())  # 输出: world

def has_number(s):
    return bool(re.search(r'\d', s))
print(has_number("hello123"))  # True
print(has_number("helloworld"))  # False

import re
# 示例：找到所有数字
result = re.findall(r'\d+', 'age: 25, score: 98, weight: 65')
print(result)  # 输出: ['25', '98', '65']

def extract_emails(s):
    return re.findall(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', s)
text = "联系我们: info@example.com, 销售: sales@company.org"
print(extract_emails(text))  # ['info@example.com', 'sales@company.org']

import re
# 示例：替换所有数字为*
result = re.sub(r'\d+', '*', 'age: 25, score: 98')
print(result)  # 输出: age: *, score: *

def mask_phone(s):
    return re.sub(r'1[3-9]\d{9}', '1xxxxxxxxx', s)
text = "我的电话是13812345678，他的电话是13987654321"
print(mask_phone(text))  # 我的电话是1xxxxxxxxx，他的电话是1xxxxxxxxx

import re
def is_valid_ip(ip):
    pattern = r'^((25[0-5]|2[0-4]\d|[01]?\d\d?)\.){3}(25[0-5]|2[0-4]\d|[01]?\d\d?)$'
    return bool(re.match(pattern, ip))
print(is_valid_ip("192.168.1.1"))  # True
print(is_valid_ip("256.0.0.1"))    # False

import re
def extract_tag_content(html, tag):
    pattern = rf'<{tag}>(.*?)</{tag}>'
    return re.findall(pattern, html, re.DOTALL)
html = '''
<div>第一部分</div>
<div>第二部分</div>
<p>这是段落</p>
'''
print(extract_tag_content(html, 'div'))  # ['第一部分', '第二部分']

import re
# 编译正则表达式
pattern = re.compile(r'\d+')
# 使用编译后的模式
print(pattern.findall('age: 25, score: 98'))  # ['25', '98']
print(pattern.sub('*', 'age: 25, score: 98'))  # age: *, score: *

import re
result = re.search(r'(\d+)-(\d+)-(\d+)', '今天是2023-10-05')
print(result.group())   # 2023-10-05
print(result.group(1))  # 2023
print(result.group(2))  # 10
print(result.group(3))  # 05
print(result.span())    # (3, 13)

import re
# 贪婪匹配
text = '<div>内容1</div><div>内容2</div>'
print(re.findall(r'<div>(.*)</div>', text))  # ['内容1</div><div>内容2']
# 非贪婪匹配
print(re.findall(r'<div>(.*?)</div>', text))  # ['内容1', '内容2']

import re
# 忽略大小写
print(re.findall(r'hello', 'Hello HELLO hello', re.IGNORECASE))
# ['Hello', 'HELLO', 'hello']
# 多行模式
text = 'line1\nline2\nline3'
print(re.findall(r'^line', text, re.MULTILINE))  # ['line', 'line', 'line']

import re
def parse_url_params(url):
    params = {}
    # 提取参数部分
    match = re.search(r'\?(.*)$', url)
    if match:
        param_str = match.group(1)
        # 分割参数
        param_list = re.split(r'&', param_str)
        for param in param_list:
            # 分割键值对
            key_value = re.split(r'=', param, 1)
            if len(key_value) == 2:
                params[key_value[0]] = key_value[1]
    return params
url = "https://example.com/search?query=python&page=2&sort=desc"
print(parse_url_params(url))
# {'query': 'python', 'page': '2', 'sort': 'desc'}

import re
def check_password_strength(password):
    # 至少8个字符，包含大小写字母、数字和特殊字符
    if len(password) < 8:
        return "弱：密码长度不足8位"
    strength = 0
    if re.search(r'[A-Z]', password):
        strength += 1
    if re.search(r'[a-z]', password):
        strength += 1
    if re.search(r'\d', password):
        strength += 1
    if re.search(r'[!@#$%^&*(),.?":{}|<>]', password):
        strength += 1
    if strength == 4:
        return "强：密码强度良好"
    elif strength >= 2:
        return "中：密码强度一般"
    else:
        return "弱：密码组成太简单"
print(check_password_strength("123456"))       # 弱：密码长度不足8位
print(check_password_strength("abcdefgh"))     # 弱：密码组成太简单
print(check_password_strength("Abcdefgh"))     # 中：密码强度一般
print(check_password_strength("Abcdefgh123"))  # 中：密码强度一般
print(check_password_strength("Abc@12345"))    # 强：密码强度良好