Python正则表达式中非捕获分组的用法详解

import re
pattern = r'(ISO|IEEE)\s\d+'  # 捕获分组
text = 'ISO 12345'
match = re.match(pattern, text)
print(match.group(1))  # 输出: ISO

import re
pattern = r'(?:ISO|IEEE)\s\d+'  # 非捕获分组
text = 'ISO 12345'
match = re.match(pattern, text)
print(match.groups())  # 输出: ()（无捕获组）

import re
pattern = r'^(?:ISO|IEEE|IEC/IEEE|CISPR)\s\d+$'
texts = [
    'ISO 12345',
    'IEEE 67890',
    'IEC/IEEE 54321',
    'CISPR 98765',
    'INVALID 123'  # 不匹配
]

for text in texts:
    if re.match(pattern, text):
        print(f"匹配成功: {text}")
    else:
        print(f"匹配失败: {text}")

# 匹配多个标准编号（如 "ISO 123, IEEE 456"）
pattern = r'^(?:ISO|IEEE|IEC/IEEE|CISPR)\s\d+(?:,\s*(?:ISO|IEEE|IEC/IEEE|CISPR)\s\d+)*$'
text = 'ISO 123, IEEE 456, CISPR 789'
print(re.match(pattern, text) is not None)  # 输出: True

# 提取标准组织名称和编号
pattern = r'^(?P<org>ISO|IEEE|IEC/IEEE|CISPR)\s(?P<num>\d+)$'
text = 'IEC/IEEE 54321'
match = re.match(pattern, text)
if match:
    print(match.groupdict())  # 输出: {'org': 'IEC/IEEE', 'num': '54321'}

import re
text = """
    项目1: ISO 9001
    项目2: IEEE 802.3
    无效项: ABC 123
"""
pattern = r'(?:ISO|IEEE|IEC/IEEE|CISPR)\s\d+'
matches = re.findall(pattern, text)
print(matches)  # 输出: ['ISO 9001', 'IEEE 802']

def validate_standard_number(input_str):
    pattern = r'^(?:ISO|IEEE|IEC/IEEE|CISPR)\s\d+$'
    return bool(re.match(pattern, input_str))

print(validate_standard_number('CISPR 32'))  # 输出: True
print(validate_standard_number('XYZ 456'))   # 输出: False

log = """
    2026-04-20: Processing ISO 14001...
    2026-04-20: Error in IEEE 802.11
    2026-04-20: Skipping UNKNOWN 999
"""
pattern = r'(?:ISO|IEEE|IEC/IEEE|CISPR)\s\d+'
for line in log.split('\n'):
    if re.search(pattern, line):
        print(f"相关日志: {line.strip()}")