lyxy-document/readers/html/html2text.py

"""使用 html2text 解析 HTML（兜底方案）"""

from typing import Optional, Tuple


def parse(html_content: str) -> Tuple[Optional[str], Optional[str]]:
    """使用 html2text 解析 HTML（兜底方案）"""
    try:
        import html2text
    except ImportError:
        return None, "html2text 库未安装"

    try:
        converter = html2text.HTML2Text()
        converter.ignore_emphasis = False
        converter.ignore_links = False
        converter.ignore_images = True
        converter.body_width = 0
        converter.skip_internal_links = True
        markdown_content = converter.handle(html_content)
        if not markdown_content.strip():
            return None, "解析内容为空"
        return markdown_content, None
    except Exception as e:
        return None, f"html2text 解析失败: {str(e)}"