正则表达式基础语法详解 - Python re模块入门指南

import re

# . 匹配任意字符
print(re.findall('a.c', 'abc a1c a c aXc'))  # ['abc', 'a1c', 'a c', 'aXc']

# ^ 匹配开头
print(re.findall('^Hello', 'Hello world'))    # ['Hello']
print(re.findall('^Hello', 'Say Hello'))      # []

# $ 匹配结尾
print(re.findall('world$', 'Hello world'))    # ['world']
print(re.findall('world$', 'world Hello'))    # []

# * + ? 量词
print(re.findall('ab*', 'a ab abb abbb'))     # ['a', 'ab', 'abb', 'abbb']
print(re.findall('ab+', 'a ab abb abbb'))     # ['ab', 'abb', 'abbb']
print(re.findall('ab?', 'a ab abb'))          # ['a', 'ab', 'ab']

# | 逻辑或
print(re.findall('cat|dog', 'I have a cat and a dog'))  # ['cat', 'dog']

import re

# \d 匹配数字
print(re.findall(r'\d+', '电话号码: 138-1234-5678'))  # ['138', '1234', '5678']

# \w 匹配单词字符
print(re.findall(r'\w+', 'hello world! 你好'))  # ['hello', 'world', '你好']

# \s 匹配空白字符
print(re.findall(r'\s+', 'hello   world'))  # ['   ']

# 自定义字符类
print(re.findall(r'[aeiou]', 'hello world'))  # ['e', 'o', 'o']
print(re.findall(r'[0-9a-f]', 'abc123xyz'))   # ['a', 'b', 'c', '1', '2', '3']

# 取反字符类
print(re.findall(r'[^0-9]', 'abc123'))  # ['a', 'b', 'c']

import re

# {n} 精确匹配n次
print(re.findall(r'\d{4}', '年份: 2024, 月份: 06'))  # ['2024']

# {n,} 至少匹配n次
print(re.findall(r'\d{2,}', '1 22 333 4444'))  # ['22', '333', '4444']

# {n,m} 匹配n到m次
print(re.findall(r'\d{2,3}', '1 22 333 4444'))  # ['22', '333', '44', '44']

# 贪婪 vs 非贪婪
text = '<div>hello</div><div>world</div>'
print(re.findall(r'<.*>', text))      # 贪婪: ['<div>hello</div><div>world</div>']
print(re.findall(r'<.*?>', text))    # 非贪婪: ['<div>', '</div>', '<div>', '</div>']

import re

# \b 单词边界
print(re.findall(r'\bcat\b', 'cat scatter category cat'))  # ['cat', 'cat']
print(re.findall(r'\b\w{4}\b', 'I love Python and Java'))  # ['love', 'Java']

# \B 非单词边界
print(re.findall(r'\Bcat\B', 'cat scatter category'))  # ['cat']（仅在scatter中）

# ^ 和 $ 配合使用做精确匹配
print(re.findall(r'^\d{6}$', '123456'))    # ['123456']
print(re.findall(r'^\d{6}$', '12345'))     # []
print(re.findall(r'^\d{6}$', '1234567'))   # []

import re

# 匹配特殊字符本身
print(re.findall(r'\.', 'hello.world.test'))    # ['.', '.', '.']
print(re.findall(r'\+', '1+2=3'))               # ['+']
print(re.findall(r'\[', '[hello] [world]'))     # ['[', '[']
print(re.findall(r'\(', 'func(arg)'))           # ['(']

# 推荐使用原始字符串 r''
# 不使用 r'' 需要写成 \\\\
print(re.findall('\\.', 'hello.world'))         # 可以但不推荐
print(re.findall(r'\.', 'hello.world'))         # 推荐写法

import re

# 捕获分组
text = '2024-06-07'
pattern = r'(\d{4})-(\d{2})-(\d{2})'
match = re.search(pattern, text)
if match:
    print(f'完整匹配: {match.group(0)}')   # 2024-06-07
    print(f'年份: {match.group(1)}')       # 2024
    print(f'月份: {match.group(2)}')       # 06
    print(f'日期: {match.group(3)}')       # 07

# findall 返回分组内容
dates = '2024-01-15, 2024-06-07, 2025-12-25'
print(re.findall(r'(\d{4})-(\d{2})-(\d{2})', dates))
# [('2024', '01', '15'), ('2024', '06', '07'), ('2025', '12', '25')]

# 命名分组
pattern = r'(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2})'
match = re.search(pattern, '2024-06-07')
print(match.group('year'))    # 2024
print(match.group('month'))   # 06

# 非捕获分组
print(re.findall(r'(?:\d{3})-(\d{4})', '010-1234 021-5678'))  # ['1234', '5678']

import re

# ========== 示例1: 验证邮箱地址 ==========
def validate_email(email):
    """验证邮箱格式是否正确"""
    pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
    return bool(re.match(pattern, email))

print(validate_email('user@example.com'))     # True
print(validate_email('invalid-email'))        # False
print(validate_email('test@domain.org'))      # True

# ========== 示例2: 提取URL中的域名 ==========
def extract_domain(url):
    """从URL中提取域名"""
    pattern = r'https?://(?:www\.)?([^/]+)'
    match = re.search(pattern, url)
    return match.group(1) if match else None

print(extract_domain('https://www.example.com/page'))   # example.com
print(extract_domain('http://blog.test.org/post'))      # blog.test.org

# ========== 示例3: 提取文本中的所有电话号码 ==========
def extract_phones(text):
    """提取各种格式的电话号码"""
    # 匹配: 138-1234-5678, 13812345678, (010)12345678
    pattern = r'1[3-9]\d{9}|(?:\d{3,4}-)?\d{7,8}'
    return re.findall(pattern, text)

text = '联系电话: 13812345678, 010-12345678, 02112345678'
print(extract_phones(text))  # ['13812345678', '010-12345678', '02112345678']

# ========== 示例4: 替换文本中的敏感信息 ==========
def mask_info(text):
    """隐藏手机号中间4位"""
    return re.sub(r'(1[3-9]\d)\d{4}(\d{4})', r'\1****\2', text)

print(mask_info('张三电话: 13812345678'))  # 张三电话: 138****5678

# ========== 示例5: 分割复杂字符串 ==========
text = 'apple, banana; orange|grape, melon; pineapple'
fruits = re.split(r'[,;|]\s*', text)
print(fruits)  # ['apple', 'banana', 'orange', 'grape', 'melon', 'pineapple']