Regex-xpath-如何从字符串中提取子字符串？

import re
from lxml import etree

def extract_substring(text, pattern):
    # 使用正则表达式匹配模式
    matches = re.findall(pattern, text)
    
    # 将匹配结果转换为XML文档
    xml_text = "<root>{}</root>".format("".join(matches))
    xml_tree = etree.fromstring(xml_text)
    
    # 使用XPath选择子字符串
    substrings = xml_tree.xpath("//substring/text()")
    
    return substrings

# 示例用法
text = "Hello, my name is John. I live in New York. My email address is john@example.com."
pattern = r"\b\w+@\w+\.\w+\b"  # 匹配电子邮件地址

substrings = extract_substring(text, pattern)
print(substrings)