12.2 清理bug修改

flask_app/general/file2markdown.py

@@ -72,6 +72,7 @@ def convert_pdf_to_markdown(file_path):
 
 
 if __name__ == "__main__":
-    file_path=r"C:\Users\Administrator\Desktop\fsdownload\e702f1e6-095d-443d-bb7d-ef2e42037cb1\ztbfile_procurement.pdf"
+    # file_path=r"C:\Users\Administrator\Desktop\fsdownload\e702f1e6-095d-443d-bb7d-ef2e42037cb1\ztbfile_procurement.pdf"
+    file_path=r"C:\Users\Administrator\Desktop\货物标\output1\招标文件（实高电子显示屏）_procurement.pdf"
     res=convert_pdf_to_markdown(file_path)
     print(res)

flask_app/old_version/文档理解大模型版知识库处理/文档理解main.py

@@ -111,9 +111,25 @@ def main():
     if status_info.status.lower() == 'success':
         print("Job completed successfully.")
         # Step 3: Retrieve the parsing result
-        result = docmind_client.get_result(job_id)
-        print("Parsing Result:")
-        print(result)
+        try:
+            result = docmind_client.get_result(job_id)
+        except Exception as e:
+            print(f"获取结果失败: {e}")
+            return
+
+            # 提取并连接每个布局的 'markdownContent'
+        try:
+            layouts = result.get('layouts', [])
+            markdown_contents = [layout.get('markdownContent', '') for layout in layouts]
+            concatenated_markdown = '\n'.join(markdown_contents)
+
+            # 将连接后的 markdown 写入 'extract.txt'
+            with open('extract.txt', 'w', encoding='utf-8') as extract_file:
+                extract_file.write(concatenated_markdown)
+
+            print("Markdown 内容已成功提取到 'extract.txt'。")
+        except Exception as e:
+            print(f"处理并写入 Markdown 内容失败: {e}")
     else:
         print("Job failed. Please check the error logs for more details.")