Python正则表达式分组与捕获 - 命名分组和非捕获分组详解

import re

# 示例：提取日期中的年、月、日
text = "今天是2024-12-25"
pattern = r"(\d{4})-(\d{2})-(\d{2})"
match = re.search(pattern, text)

if match:
    print(f"完整匹配: {match.group()}")    # 2024-12-25
    print(f"第1组(年): {match.group(1)}")  # 2024
    print(f"第2组(月): {match.group(2)}")  # 12
    print(f"第3组(日): {match.group(3)}")  # 25

import re

text = "订单号: ORD-2024-A12345"
pattern = r"ORD-(\d{4})-([A-Z]\d{5})"
match = re.search(pattern, text)

if match:
    print(match.groups())       # ('2024', 'A12345')
    print(match.group(0))       # ORD-2024-A12345
    print(match.group(1))       # 2024
    print(match.group(2))       # A12345

import re

# 使用命名分组解析邮箱
email = "zhangsan@example.com"
pattern = r"(?P<username>[a-zA-Z0-9_.+-]+)@(?P<domain>[a-zA-Z0-9-]+\.[a-zA-Z]{2,})"
match = re.search(pattern, email)

if match:
    print(f"用户名: {match.group('username')}")    # zhangsan
    print(f"域名: {match.group('domain')}")         # example.com
    
    # groupdict() 返回所有命名分组的字典
    print(match.groupdict())
    # {'username': 'zhangsan', 'domain': 'example.com'}

import re

text = "2024-06-07"
pattern = r"(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2})"
match = re.search(pattern, text)

# 通过组号访问
print(match.group(1))       # 2024
print(match.group(2))       # 06

# 通过名称访问
print(match.group('year'))  # 2024
print(match.group('month')) # 06

import re

# 捕获分组 vs 非捕获分组对比
text = "Python 3.12"

# 使用捕获分组
p1 = r"(Python) (\d+\.\d+)"
m1 = re.search(p1, text)
print(m1.groups())   # ('Python', '3.12')

# 使用非捕获分组（版本号部分不捕获）
p2 = r"(Python) (?:\d+\.\d+)"
m2 = re.search(p2, text)
print(m2.groups())   # ('Python',)

import re

# 查找连续重复的单词
text = "hello hello world world"
pattern = r"\b(\w+)\s+\1\b"
matches = re.findall(pattern, text)
print(matches)  # ['hello', 'world']

# 查找HTML标签的匹配
html = "<div>content</div><span>more</span>"
pattern = r"<(\w+)>(.*?)</\1>"
matches = re.findall(pattern, html)
print(matches)  # [('div', 'content'), ('span', 'more')]

import re

# 使用命名分组的反向引用
text = "<title>网页标题</title>"
pattern = r"<(?P<tag>\w+)>(?P<content>.*)</(?P=tag)>"
match = re.search(pattern, text)

if match:
    print(f"标签名: {match.group('tag')}")      # title
    print(f"标签内容: {match.group('content')}") # 网页标题

import re

# 解析URL中的协议、域名和路径
urls = [
    "https://www.example.com/path/to/page",
    "http://api.test.com/v1/users",
    "ftp://files.server.com/docs/report.pdf"
]

pattern = r"(?P<protocol>https?|ftp)://(?P<domain>[^/]+)/(?P<path>.*)"

for url in urls:
    match = re.search(pattern, url)
    if match:
        d = match.groupdict()
        print(f"协议: {d['protocol']}, 域名: {d['domain']}, 路径: {d['path']}")

import re

# 解析服务器日志格式: [时间] 级别: 消息
logs = [
    "[2024-12-25 10:30:00] INFO: Server started on port 8080",
    "[2024-12-25 10:30:05] ERROR: Database connection failed",
    "[2024-12-25 10:31:00] WARNING: High memory usage detected"
]

pattern = r"\[(?P<time>[^\]]+)\] (?P<level>\w+): (?P<message>.*)"

for log in logs:
    match = re.search(pattern, log)
    if match:
        d = match.groupdict()
        print(f"[{d['time']}] {d['level']} -> {d['message']}")