Python re模块的使用全过程

# 验证字符串是否以数字开头,调用这个方法等同于 r'^\d+'
# 如果匹配的字符串是c123abc，是匹配不到的
if re.match(r'\d+', '123abc'):
    print("Valid header")
else:
    print("Invalid header")

# 提取开头的版本号
version = re.match(r'v?(\d+\.\d+)', 'v3.8.1').group(1)  # '3.8'

# 查找第一个有效数字串,只匹配第一个
text = "Total: 1500 items, price $299"
match = re.search(r'\d+', text)
if match:
    print(f"价格：{match.group()}")  # 1500

# 带条件的搜索
pattern = r'(?<=ID:)\s*[A-Z0-9]{8}'  # 查找ID后的8位编码
id_code = re.search(pattern, "User ID: AB3XK9P2").group()  # AB3XK9P2

# 预编译邮箱验证正则
email_re = re.compile(
    r'''(
        [\w\.-]+          # 用户名
        @ 
        [\w\.-]+          # 域名
        \.
        [a-zA-Z]{2,4}     # 顶级域名
    )''', re.VERBOSE)

# 复用编译对象
valid = email_re.match('user@example.com') is not None  # True

# 提取所有数字
numbers = re.findall(r'\d+', 'A1B23C456')
print(numbers)  # ['1','23','456']

# 分组提取日期成分
dates = re.findall(r'(\d{4})-(\d{2})-(\d{2})', '2023-08-01, 2025-03-15')
print(dates)  # [('2023','08','01'), ('2025', '03', '15')]

# 处理100MB日志文件
with open('server.log') as f:
    for match in re.finditer(r'$$(ERROR|WARN)$$.*?(req_id=\w+)', f.read()):
        level = match.group(1)
        req_id = match.group(2)
        print(f"{level}报警：{req_id}")

# 复杂分隔符分割
text = "apple, banana;cherry|orange"
parts = re.split(r'[,;|]\s*', text)  # ['apple','banana','cherry','orange']

# 带保留分隔符的分割
re.split(r'([,;])', 'a,b;c')  # ['a', ',', 'b', ';', 'c']

# 控制分割次数
re.split(r'\d+', 'a1b22c333d', maxsplit=2)  # ['a','b','c333d']

log_pattern = re.compile(r'''
    (?P<time>\d{4}-\d{2}-\d{2}\s\d{2}:\d{2}:\d{2})  # 时间
    \s\|\s
    (?P<level>INFO|ERROR|WARN)                      # 日志级别
    \s\|\s
    (?P<module>\w+)\.py                             # 模块
    :(?P<line>\d+)                                  # 行号
    \s-\s
    (?P<msg>.+)                                     # 消息
''', re.VERBOSE)

for log in open('app.log'):
    if (match := log_pattern.search(log)):
        print(f"{match.group('time')} [{match.group('level')}]", 
              f"{match.group('module')}:{match.group('line')}",
              match.group('msg'))