10.24

flask_app/general/format_change.py

@@ -66,7 +66,6 @@ def docx2pdf(local_path_in):
     downloaded_filepath,file_type = download_file(receive_download_url, local_filename)
     print(f"format_change d2p:have downloaded file to: {downloaded_filepath}")
     return downloaded_filepath
-
 # def docx2pdf(file_path):
 #     """
 #     将本地的 .docx 或 .doc 文件转换为 .pdf 文件。

flask_app/main/start_up.py

@@ -176,7 +176,7 @@ def get_procurement_reqs():
             return jsonify({
                 'message': 'procurement_reqs processed successfully',
                 'filename': "filename",
-                'data': response
+                'data': json.dumps(response, ensure_ascii=False)
             })
     except Exception as e:
         logger.error('Exception occurred: ' + str(e))  # 使用全局 logger 记录
@@ -386,7 +386,7 @@ def process_and_stream(file_url, zb_type):
         procurement_reqs_response={
             'message': 'procurement_reqs',
             'filename': os.path.basename(downloaded_filepath),
-            'data': procurement_reqs
+            'data': json.dumps(procurement_reqs, ensure_ascii=False)
         }
         yield f"data: {json.dumps(procurement_reqs_response, ensure_ascii=False)}\n\n"
 

flask_app/testdir/截取文件格式.py

@@ -178,7 +178,6 @@ def process_input(input_path, output_folder, begin_pattern, begin_page, end_patt
         generated_files.append(result)
     else:
         print("提供的路径既不是文件夹也不是PDF/Word文件。")
-
     return [f for f in generated_files if f]  # 过滤空字符串
 
 
@@ -191,7 +190,6 @@ def truncate_pdf_main(input_path, output_folder, selection):
             begin_page = 10
             begin_pattern = re.compile(
                 r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:响应|投标).*?格式.*',
-                re.MULTILINE
             )
             end_pattern = re.compile(
                 r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+',
@@ -211,9 +209,10 @@ def truncate_pdf_main(input_path, output_folder, selection):
 
 if __name__ == "__main__":
     # 定义输入和输出路径
-    input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\包头市公安支队机动车查验监管系统招标文201907.pdf"
+    # input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles"
+    input_path="C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹"
     output_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\新建文件夹"
     selection = 1  # 1 - 投标文件格式
     # 执行截取
     generated_files = truncate_pdf_main(input_path, output_folder, selection)
-    print("生成的文件:", generated_files)
+    # print("生成的文件:", generated_files)