Python re.compile()预编译正则详解 - 性能优化与Pattern对象使用

re.compile(pattern, flags=0)

import re

# 编译正则表达式
pattern = re.compile(r'\d+')

# 使用编译后的对象进行匹配
result = pattern.findall('我有3个苹果和5个橘子')
print(result)
# ['3', '5']

import re

# 编译时指定忽略大小写
pattern = re.compile(r'python', re.IGNORECASE)

# 后续调用无需再传 flags
matches = pattern.findall('Python PYTHON python')
print(matches)
# ['Python', 'PYTHON', 'python']

import re

# 预编译正则表达式
error_pattern = re.compile(r'ERROR\s+(.+)$')
ip_pattern = re.compile(r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}')

log_lines = [
    "2024-01-15 ERROR Connection timeout from 192.168.1.1",
    "2024-01-15 INFO Request processed",
    "2024-01-15 ERROR Database error from 10.0.0.5",
    "2024-01-15 WARNING Disk space low",
]

for line in log_lines:
    errors = error_pattern.findall(line)
    if errors:
        ip = ip_pattern.search(line)
        if ip:
            print(f"错误：{errors[0]}，来源：{ip.group()}")

import re

class Validator:
    def __init__(self):
        # 在初始化时编译所有正则表达式
        self.email_re = re.compile(r'^[\w\.-]+@[\w\.-]+\.\w+$')
        self.phone_re = re.compile(r'^1[3-9]\d{9}$')
        self.ip_re = re.compile(r'^(\d{1,3}\.){3}\d{1,3}$')

    def validate_email(self, email):
        return bool(self.email_re.match(email))

    def validate_phone(self, phone):
        return bool(self.phone_re.match(phone))

    def validate_ip(self, ip):
        return bool(self.ip_re.match(ip))

validator = Validator()
print(validator.validate_email('user@example.com'))  # True
print(validator.validate_phone('13800138000'))       # True
print(validator.validate_ip('192.168.1.1'))          # True

import re

# 预编译替换模式
html_tag_pattern = re.compile(r'<[^>]+>')
whitespace_pattern = re.compile(r'\s+')

html_text = "<div>  Hello   World  </div>   <span>  Test  </span>"

# 移除 HTML 标签
plain_text = html_tag_pattern.sub('', html_text)
print(repr(plain_text))
# '  Hello   World     Test  '

# 规范化空白字符
clean_text = whitespace_pattern.sub(' ', plain_text).strip()
print(repr(clean_text))
# 'Hello World Test'

import re

# 预编译带分组的正则表达式
contact_pattern = re.compile(r'(?P<name>\w+):(?P<phone>\d+)-(?P<email>[\w\.-]+@[\w\.-]+\.\w+)')

text = """
联系人列表：
张三:13800138000-zhangsan@example.com
李四:13900139000-lisi@test.org
"""

for match in contact_pattern.finditer(text):
    print(f"姓名：{match.group('name')}")
    print(f"电话：{match.group('phone')}")
    print(f"邮箱：{match.group('email')}")
    print("---")

import re
import time

# 测试数据
text = "apple123 banana456 cherry789 date012 elderberry345" * 1000

# 直接使用字符串模式（不编译）
start = time.time()
for _ in range(1000):
    re.findall(r'\w+\d+', text)
direct_time = time.time() - start

# 预编译后使用
pattern = re.compile(r'\w+\d+')
start = time.time()
for _ in range(1000):
    pattern.findall(text)
compiled_time = time.time() - start

print(f"直接使用：{direct_time:.4f} 秒")
print(f"预编译后：{compiled_time:.4f} 秒")
print(f"速度提升：{direct_time/compiled_time:.2f}x")