From b8d310a0b0d378e80d08934bbd34125d9ddad52f Mon Sep 17 00:00:00 2001 From: zy123 <646228430@qq.com> Date: Wed, 18 Dec 2024 12:26:27 +0800 Subject: [PATCH] =?UTF-8?q?12.18=20=E6=88=AA=E5=8F=96pdf?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- flask_app/routes/货物标解析main.py | 2 +- flask_app/货物标/商务服务其他要求提取.py | 14 ++++++++------ flask_app/货物标/基础信息解析main.py | 4 ++-- flask_app/货物标/技术参数要求提取.py | 6 +++--- flask_app/货物标/提取采购需求main.py | 1 - 5 files changed, 14 insertions(+), 13 deletions(-) diff --git a/flask_app/routes/货物标解析main.py b/flask_app/routes/货物标解析main.py index 3c51d04..f443c57 100644 --- a/flask_app/routes/货物标解析main.py +++ b/flask_app/routes/货物标解析main.py @@ -90,6 +90,7 @@ def fetch_project_basic_info(invalid_deleted_docx, merged_baseinfo_path, procure if not procurement_path: procurement_path = invalid_deleted_docx basic_res = combine_basic_info(merged_baseinfo_path, procurement_path, clause_path, invalid_deleted_docx) + print(json.dumps(basic_res,ensure_ascii=False,indent=4)) base_info, good_list = post_process_baseinfo(basic_res, logger) result = base_info, good_list end_time = time.time() @@ -122,7 +123,6 @@ 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", {})} diff --git a/flask_app/货物标/商务服务其他要求提取.py b/flask_app/货物标/商务服务其他要求提取.py index 5a9abe9..c935778 100644 --- a/flask_app/货物标/商务服务其他要求提取.py +++ b/flask_app/货物标/商务服务其他要求提取.py @@ -258,8 +258,8 @@ def generate_template(required_keys,full_text, type=1): def get_business_requirements(procurement_path,processed_filepath): required_keys = ["技\s*术\s*要\s*求", "商\s*务\s*要\s*求", "服\s*务\s*要\s*求", "其\s*他\s*要\s*求","总\s*体\s*要\s*求","建\s*设\s*要\s*求","进\s*度\s*要\s*求","工\s*期\s*要\s*求","质\s*保\s*要\s*求","培\s*训\s*要\s*求","售\s*后\s*要\s*求"] procurement_pdf_path=procurement_path - if procurement_path.lower().endswith('.doc', '.docx'): - procurement_pdf_path=docx2pdf(procurement_path) + if procurement_path.lower().endswith(('.doc', '.docx')): + procurement_pdf_path = docx2pdf(procurement_path) contained_keys = find_exists(procurement_pdf_path, required_keys) print(contained_keys) if not contained_keys: @@ -289,10 +289,12 @@ def get_business_requirements(procurement_path,processed_filepath): # TODO:改为先判断，再摘取 if __name__ == "__main__": # truncate_file = "C:\\Users\\Administrator\\Desktop\\fsdownload\\e4be098d-b378-4126-9c32-a742b237b3b1\\ztbfile_procurement.docx" - truncate_file = r"C:\Users\Administrator\Desktop\货物标\output1\2-招标文件（广水市教育局封闭管理）_procurement.pdf" - docx_path=r'C:\Users\Administrator\Desktop\货物标\output1\2-招标文件（广水市教育局封闭管理）_procurement.docx' + # truncate_file = r"C:\Users\Administrator\Desktop\货物标\output1\2-招标文件（广水市教育局封闭管理）_procurement.pdf" + procurement_path=r'D:\flask_project\flask_app\static\output\output1\83ae3e35-9136-4402-a74f-01d7adfcbb73\invalid_added.docx' + docx_path=r'D:\flask_project\flask_app\static\output\output1\83ae3e35-9136-4402-a74f-01d7adfcbb73\invalid_added.docx' # truncate_file=r"C:\Users\Administrator\Desktop\new招标文件\output5\HBDL-2024-0519-001-招标文件_procurement.pdf" # file_id = upload_file(truncate_file) - processed_filepath = pdf2txt(truncate_file) - final_res= get_business_requirements(truncate_file, docx_path) + # processed_filepath = pdf2txt(procurement_path) + processed_filepath=r'D:\flask_project\flask_app\static\output\output1\83ae3e35-9136-4402-a74f-01d7adfcbb73\extract1.txt' + final_res= get_business_requirements(procurement_path,processed_filepath) print(json.dumps(final_res, ensure_ascii=False, indent=4)) diff --git a/flask_app/货物标/基础信息解析main.py b/flask_app/货物标/基础信息解析main.py index 7e9df11..a2bc09d 100644 --- a/flask_app/货物标/基础信息解析main.py +++ b/flask_app/货物标/基础信息解析main.py @@ -209,9 +209,9 @@ def combine_basic_info(merged_baseinfo_path, procurement_path,clause_path,invali if __name__ == "__main__": start_time=time.time() # baseinfo_file_path = "C:\\Users\\Administrator\\Desktop\\货物标\\truncate_all\\ztbfile_merged_baseinfo\\ztbfile_merged_baseinfo_3-31.pdf" - merged_baseinfo_path="D:\\flask_project\\flask_app\\static\\output\\output1\\bf225a5e-16d0-45c8-8c19-54a1a94cf3e2\\ztbfile_merged_baseinfo.pdf" + merged_baseinfo_path=r"D:\flask_project\flask_app\static\output\output1\83ae3e35-9136-4402-a74f-01d7adfcbb73\invalid_added.docx" # procurement_file_path = "C:\\Users\\Administrator\\Desktop\\fsdownload\\b4601ea1-f087-4fa2-88ae-336ad4d8e1e9\\tmp\\ztbfile_procurement.pdf" - procurement_file_path = "D:\\flask_project\\flask_app\\static\\output\\output1\\bf225a5e-16d0-45c8-8c19-54a1a94cf3e2\\ztbfile_procurement.docx" + procurement_file_path = r"D:\flask_project\flask_app\static\output\output1\83ae3e35-9136-4402-a74f-01d7adfcbb73\invalid_added.docx" clause_path='D:\\flask_project\\flask_app\\static\\output\\output1\\bf225a5e-16d0-45c8-8c19-54a1a94cf3e2\\clause1.json' res = combine_basic_info(merged_baseinfo_path, procurement_file_path,clause_path) print("------------------------------------") diff --git a/flask_app/货物标/技术参数要求提取.py b/flask_app/货物标/技术参数要求提取.py index f6c0c49..9500c6c 100644 --- a/flask_app/货物标/技术参数要求提取.py +++ b/flask_app/货物标/技术参数要求提取.py @@ -387,7 +387,7 @@ def get_technical_requirements(invalid_path,processed_filepath): processed_data=truncate_system_keys(cleaned_res['采购需求']) key_paths, grouped_paths, good_list, data_copy= generate_key_paths(processed_data) # 提取需要采购的货物清单 key_list：交通监控视频子系统.高清视频抓拍像机 ... grouped_paths是同一系统下同时有'交换机-1'和'交换机-2'，提取'交换机' ，输出eg:{'交通标志.标志牌铝板', '交通信号灯.交换机'} modified_data=rename_keys(data_copy) - print(json.dumps(modified_data,ensure_ascii=False,indent=4)) + # print(json.dumps(modified_data,ensure_ascii=False,indent=4)) user_query_template = """请根据货物标中采购要求部分的内容，告诉我\"{}\"的技术参数或采购要求是什么。请以 JSON 格式返回结果，键名为\"{}\"，键值为一个列表，列表中包含若干描述\"{}\"的技术参数或采购要求或功能说明的字符串，请按原文内容回答，保留三角▲、五角★和序号，不可擅自增删内容，尤其是不可擅自添加序号。 要求与指南： @@ -538,10 +538,10 @@ if __name__ == "__main__": # truncate_file="D:\\flask_project\\flask_app\\static\\output\\output1\\e7dda5cb-10ba-47a8-b989-d2993d34bb89\\ztbfile_procurement.docx" # output_folder="C:\\Users\\Administrator\\Desktop\\货物标\\output1\\tmp" # file_id = upload_file(truncate_file) - invalid_path=r"C:\Users\Administrator\Desktop\fsdownload\8c63f0c9-d642-4f0c-918c-33db5efd6cd0\extract1.txt" + invalid_path=r"D:\flask_project\flask_app\static\output\output1\9f63f6f1-6e91-44d6-83ca-189461bf151f\invalid_del.docx" # file_id=upload_file(truncate_file) # processed_filepath = pdf2txt(truncate_file) - processed_filepath=r"C:\Users\Administrator\Desktop\fsdownload\8c63f0c9-d642-4f0c-918c-33db5efd6cd0\extract1.txt" + processed_filepath=r"D:\flask_project\flask_app\static\output\output1\9f63f6f1-6e91-44d6-83ca-189461bf151f\extract1.txt" res=get_technical_requirements(invalid_path,processed_filepath) json_string = json.dumps(res, ensure_ascii=False, indent=4) print(json_string) diff --git a/flask_app/货物标/提取采购需求main.py b/flask_app/货物标/提取采购需求main.py index ad024a2..4f0f4a3 100644 --- a/flask_app/货物标/提取采购需求main.py +++ b/flask_app/货物标/提取采购需求main.py @@ -39,7 +39,6 @@ def fetch_procurement_reqs(procurement_path, invalid_path): # 获取并行任务的结果 technical_requirements = future_technical.result() business_requirements = future_business.result() - # 构建最终的采购需求字典 procurement_reqs = { "采购需求": technical_requirements.get("采购需求", {})