整合代码

temp/scripts/pptx_parser.py

@@ -6,28 +6,12 @@ import xml.etree.ElementTree as ET
 import zipfile
 from typing import Any, List, Optional, Tuple
 
-from common import build_markdown_table, filter_markdown_content, flush_list_stack
+from common import build_markdown_table, flush_list_stack, parse_with_markitdown
 
 
 def parse_pptx_with_markitdown(file_path: str) -> Tuple[Optional[str], Optional[str]]:
     """使用 MarkItDown 库解析 PPTX 文件"""
-    try:
-        from markitdown import MarkItDown
-
-        md = MarkItDown()
-        result = md.convert(file_path)
-        if not result.text_content.strip():
-            return None, "文档为空"
-
-        filtered_content = filter_markdown_content(result.text_content)
-        if not filtered_content.strip():
-            return None, "过滤后文档为空"
-
-        return filtered_content, None
-    except ImportError:
-        return None, "MarkItDown 库未安装"
-    except Exception as e:
-        return None, f"MarkItDown 解析失败: {str(e)}"
+    return parse_with_markitdown(file_path)
 
 
 def extract_formatted_text_pptx(runs: List[Any]) -> str: