匹配url的主域名

import re

def extract_domain(url):
    # 正则表达式匹配主域名
    match = re.search(r'https?://([^/]+)', url)
    if match:
        return match.group(1)
    return None

# 测试
urls = [
    'https://www.example.com/path/to/file.html',
    'http://subdomain.example.co.uk',
    'https://example.com?query=param'
]

for url in urls:
    print(f'URL: {url} -> Domain: {extract_domain(url)}')

import idna

def extract_domain(url):
    # 先对URL进行标准化处理
    url = url.split('//')[1].split('/')[0]
    # 处理国际化域名
    try:
        domain = idna.decode(url)
    except UnicodeError:
        domain = url
    # 正则表达式匹配主域名
    match = re.search(r'([^/]+)', domain)
    if match:
        return match.group(1)
    return None