加入pandoc解析docx

temp/scripts/docx_parser.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""DOCX 文件解析模块，提供三种解析方法。"""
+"""DOCX 文件解析模块，提供多种解析方法。"""
 
 import xml.etree.ElementTree as ET
 import zipfile
@@ -8,6 +8,32 @@ from typing import Any, List, Optional, Tuple
 from common import build_markdown_table, parse_with_markitdown, safe_open_zip
 
 
+def parse_docx_with_pypandoc(file_path: str) -> Tuple[Optional[str], Optional[str]]:
+    """使用 pypandoc-binary 库解析 DOCX 文件。"""
+    try:
+        import pypandoc
+    except ImportError:
+        return None, "pypandoc-binary 库未安装"
+
+    try:
+        content = pypandoc.convert_file(
+            source_file=file_path,
+            to="md",
+            format="docx",
+            outputfile=None,
+            extra_args=["--wrap=none"],
+        )
+    except OSError as exc:
+        return None, f"pypandoc-binary 缺少 Pandoc 可执行文件: {exc}"
+    except RuntimeError as exc:
+        return None, f"pypandoc-binary 解析失败: {exc}"
+
+    content = content.strip()
+    if not content:
+        return None, "文档为空"
+    return content, None
+
+
 def parse_docx_with_markitdown(file_path: str) -> Tuple[Optional[str], Optional[str]]:
     """使用 MarkItDown 库解析 DOCX 文件"""
     return parse_with_markitdown(file_path)