12.18 截取pdf

flask_app/general/insert_del_pagemark.py

@@ -85,6 +85,7 @@ def delete_mark(docx_path):
 
     # 保存修改后的文档
     docx.save(new_file_path)
+    return new_file_path
 
 if __name__ == '__main__':
     input=r'C:\Users\Administrator\Desktop\fsdownload\1073c74f-02b5-463e-a129-23c790a3c872\ztbfile_tobidders_notice_part2.pdf'

flask_app/general/截取pdf_main.py

@@ -109,15 +109,15 @@ if __name__ == "__main__":
     logger=get_global_logger("123")
     start_time = time.time()
     # input_path = r"C:\Users\Administrator\Desktop\new招标文件\工程标"
-    pdf_path=r"C:\Users\Administrator\Desktop\招标文件\招标test文件夹\zbtest5.pdf"
+    pdf_path=r"C:\Users\Administrator\Desktop\货物标\zbfiles\094定稿-湖北工业大学轻武器模拟射击设备采购项目招标文件.pdf"
 
     # pdf_path = r"C:\Users\Administrator\Desktop\招标文件\招标02.pdf"
     # input_path=r"C:\Users\Administrator\Desktop\招标文件\招标test文件夹\zbtest8.pdf"
     output_folder = r"C:\Users\Administrator\Desktop\fsdownload\91399aa4-1ee8-447d-a05b-03cd8d15ced5\tmp"
-    selections = [1, 4]  # 仅处理 selection 4、1
+    # selections = [1, 4]  # 仅处理 selection 4、1
     # selections=[5]
     #engineering
-    files=truncate_pdf_multiple(pdf_path,output_folder,logger,'engineering',selections)
+    files=truncate_pdf_multiple(pdf_path,output_folder,logger,'goods')
     print(files)
     # selection = 1  # 例如：1 - 招标公告, 2 - 评标办法, 3 -资格审查条件 4-投标人须知前附表+正文 5-无效标
     # generated_files = truncate_pdf_main_engineering(pdf_path, output_folder, selection,logger)

flask_app/general/清除file_id.py

@@ -112,5 +112,6 @@ def delete_file_by_ids(file_ids):
 
 if __name__ == '__main__':
     # delete_all_files()
-    file_ids=["file-fe-Lu6GKmTR1NjimC2tOebRAIYT"]
-    delete_file_by_ids(file_ids)
+    # file_ids=["file-fe-Lu6GKmTR1NjimC2tOebRAIYT"]
+    # delete_file_by_ids(file_ids)
+    delete_all_files()

flask_app/routes/货物标解析main.py

@@ -122,6 +122,7 @@ def fetch_evaluation_standards(invalid_deleted_docx, evaluation_method_path,logg
     start_time = time.time()
     if not evaluation_method_path:
         evaluation_method_path = invalid_deleted_docx
+        print(evaluation_method_path)
     evaluation_standards_res = combine_evaluation_standards(evaluation_method_path,invalid_deleted_docx,2)
     technical_standards = {"技术评分": evaluation_standards_res.get("技术评分", {})}
     commercial_standards = {"商务评分": evaluation_standards_res.get("商务评分", {})}