lanyuanxiaoyao
15b63800a8
- 创建 scripts/ 目录作为核心代码根目录 - 移动 core/, readers/, utils/ 到 scripts/ 下 - 移动 config.py, lyxy_document_reader.py 到 scripts/ - 移动 encoding_detection.py 到 scripts/utils/ - 更新 pyproject.toml 中的入口点路径和 pytest 配置 - 更新所有内部导入语句为 scripts.* 模块 - 更新 README.md 目录结构说明 - 更新 openspec/config.yaml 添加目录结构说明 - 删除无用的 main.py 此变更使项目结构更清晰，便于区分核心代码与测试、文档等支撑文件。
42 lines
1.2 KiB
Python
42 lines
1.2 KiB
Python
"""使用 MarkItDown 解析 HTML"""
|
|
|
|
import os
|
|
import tempfile
|
|
from typing import Optional, Tuple
|
|
|
|
|
|
def parse(html_content: str, temp_file_path: Optional[str] = None) -> Tuple[Optional[str], Optional[str]]:
|
|
"""使用 MarkItDown 解析 HTML"""
|
|
try:
|
|
from markitdown import MarkItDown
|
|
except ImportError:
|
|
return None, "MarkItDown 库未安装"
|
|
|
|
try:
|
|
input_path = temp_file_path
|
|
if not input_path or not os.path.exists(input_path):
|
|
# 创建临时文件
|
|
fd, input_path = tempfile.mkstemp(suffix='.html')
|
|
with os.fdopen(fd, 'w', encoding='utf-8') as f:
|
|
f.write(html_content)
|
|
|
|
md = MarkItDown()
|
|
result = md.convert(
|
|
input_path,
|
|
heading_style="ATX",
|
|
strip=["img", "script", "style", "noscript"],
|
|
)
|
|
markdown_content = result.text_content
|
|
|
|
if not temp_file_path:
|
|
try:
|
|
os.unlink(input_path)
|
|
except Exception:
|
|
pass
|
|
|
|
if not markdown_content.strip():
|
|
return None, "解析内容为空"
|
|
return markdown_content, None
|
|
except Exception as e:
|
|
return None, f"MarkItDown 解析失败: {str(e)}"
|