"""使用 domscribe 解析 HTML"""
from typing import Optional, Tuple
def parse(html_content: str) -> Tuple[Optional[str], Optional[str]]:
"""使用 domscribe 解析 HTML"""
try:
from domscribe import html_to_markdown
except ImportError:
return None, "domscribe 库未安装"
try:
options = {
'extract_main_content': True,
}
markdown_content = html_to_markdown(html_content, options)
if not markdown_content.strip():
return None, "解析内容为空"
return markdown_content, None
except Exception as e:
return None, f"domscribe 解析失败: {str(e)}"