re.match详解 - Python正则表达式从头匹配方法使用指南

re.match(pattern, string, flags=0)

import re

# 基本示例：从开头匹配
result = re.match(r'Hello', 'Hello, World!')
print(result)        # <re.Match object; span=(0, 5), match='Hello'>
print(result.group())  # Hello

# 如果开头不匹配，返回 None
result = re.match(r'World', 'Hello, World!')
print(result)        # None

# 使用分组提取
result = re.match(r'(\w+)@(\w+)\.(\w+)', 'test@example.com')
if result:
    print(f'用户名: {result.group(1)}')    # test
    print(f'域名: {result.group(2)}')      # example
    print(f'后缀: {result.group(3)}')      # com

# 使用忽略大小写标志
result = re.match(r'python', 'PYTHON is great', re.IGNORECASE)
print(result.group())  # PYTHON

import re

text = '2024-06-07'
pattern = r'(\d{4})-(\d{2})-(\d{2})'
match = re.match(pattern, text)

if match:
    # group() 方法
    print(f'完整匹配: {match.group(0)}')     # 2024-06-07
    print(f'第一组: {match.group(1)}')       # 2024
    print(f'第二组: {match.group(2)}')       # 06
    print(f'第三组: {match.group(3)}')       # 07

    # groups() - 所有分组
    print(f'所有分组: {match.groups()}')     # ('2024', '06', '07')

    # 位置信息
    print(f'起始位置: {match.start()}')      # 0
    print(f'结束位置: {match.end()}')        # 10
    print(f'范围: {match.span()}')           # (0, 10)

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

import re

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

emails = [
    'user@example.com',      # True
    'test.name@domain.org',  # True
    'invalid-email',         # False
    '@missing.com',          # False
    'user@.com',             # False
]
for email in emails:
    print(f'{email}: {is_valid_email(email)}')

# ========== 示例2: 解析日志行 ==========
def parse_log_line(line):
    """解析标准格式的日志行"""
    pattern = r'^\[(?P<time>[\d:\- ]+)\] (?P<level>\w+): (?P<message>.+)$'
    match = re.match(pattern, line)
    if match:
        return match.groupdict()
    return None

log = '[2024-06-07 10:30:00] INFO: Server started successfully'
result = parse_log_line(log)
if result:
    print(f"时间: {result['time']}")     # 2024-06-07 10:30:00
    print(f"级别: {result['level']}")    # INFO
    print(f"消息: {result['message']}")  # Server started successfully

# ========== 示例3: 提取URL协议和域名 ==========
def parse_url(url):
    """解析URL的协议和域名"""
    pattern = r'^(?P<protocol>https?)://(?P<domain>[\w.-]+)(?P<path>/.*)?$'
    match = re.match(pattern, url)
    if match:
        return match.groupdict()
    return None

urls = [
    'https://www.example.com/page',
    'http://api.test.org/v1/users',
    'invalid-url',
]
for url in urls:
    result = parse_url(url)
    print(f'{url}: {result}')

# ========== 示例4: 验证身份证号 ==========
def validate_id_card(id_card):
    """验证18位身份证号格式"""
    pattern = r'^\d{17}[\dXx]$'
    match = re.match(pattern, id_card)
    return match is not None

print(validate_id_card('110105199001011234'))  # True
print(validate_id_card('11010519900101123X'))  # True
print(validate_id_card('11010519900101'))      # False

# ========== 示例5: 编译正则提高性能 ==========
# 频繁使用时，建议先编译正则
EMAIL_PATTERN = re.compile(r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$')

def batch_validate_emails(emails):
    """批量验证邮箱"""
    valid = []
    for email in emails:
        if EMAIL_PATTERN.match(email):
            valid.append(email)
    return valid

emails = ['user@test.com', 'invalid', 'admin@site.org']
print(batch_validate_emails(emails))  # ['user@test.com', 'admin@site.org']

import re

text = 'Email: user@example.com'

# re.match 从开头匹配，失败
print(re.match(r'user@\w+', text))   # None

# re.search 扫描全文，成功
print(re.search(r'user@\w+', text))  # <re.Match object; ... match='user@example'>