61 lines
3.1 KiB
Python
61 lines
3.1 KiB
Python
import json
|
||
|
||
from flask_app.货物标.货物标截取pdf import truncate_pdf_main
|
||
from flask_app.main.format_change import docx2pdf, pdf2docx
|
||
from flask_app.main.多线程提问 import multi_threading
|
||
from flask_app.main.通义千问long import upload_file,qianwen_long
|
||
from flask_app.main.json_utils import clean_json_string,combine_json_results
|
||
|
||
def generate_key_paths(data, parent_key=''):
|
||
key_paths = []
|
||
for key, value in data.items():
|
||
current_key = f"{parent_key}.{key}" if parent_key else key
|
||
if isinstance(value, dict):
|
||
if value: # 字典非空时，递归处理
|
||
key_paths.extend(generate_key_paths(value, current_key))
|
||
else: # 字典为空时，直接添加键路径
|
||
key_paths.append(current_key)
|
||
else:
|
||
# 如果到达了末端，添加当前键路径
|
||
key_paths.append(current_key)
|
||
return key_paths
|
||
|
||
#获取采购清单
|
||
def fetch_purchasing_list(file_path,output_folder,file_type):
|
||
global pdf_path,docx_path
|
||
if file_type==1:
|
||
docx_path=file_path
|
||
pdf_path = docx2pdf(file_path)
|
||
elif file_type==2:
|
||
pdf_path=file_path
|
||
docx_path=pdf2docx(file_path)
|
||
technical_requirements=[]
|
||
truncate_path=truncate_pdf_main(pdf_path,output_folder,1)
|
||
user_query1="这是一份货物标中采购要求部分的内容，你需要摘取出需要采购的系统（货物），一个大系统（大项）中可能包含多个小系统（小项），你需要保留这种层次关系，给出货物名称，请以json格式返回，外层键名为\"采购需求\"，嵌套键名为对应的系统名称或货物名称，无需给出采购数量和单位，如有未知内容，在对应键值处填\"未知\"。"
|
||
file_id=upload_file(truncate_path[0])
|
||
res=qianwen_long(file_id,user_query1)
|
||
cleaned_res=clean_json_string(res)
|
||
keys_list=generate_key_paths(cleaned_res['采购需求']) #提取需要采购的货物清单
|
||
user_query_template = "这是一份货物标中采购要求部分的内容，请你给出\"{}\"的具体型号参数要求，请以json格式返回结果，外层键名为\"{}\", 键值对中的键是你对该要求的总结，而值需要完全与原文保持一致，不可擅自总结删减。"
|
||
queries=[]
|
||
for key in keys_list:
|
||
# 替换 user_query2 中的 "网络硬盘录像机" 为当前 key
|
||
new_query = user_query_template.format(key, key)
|
||
print(new_query)
|
||
queries.append(new_query)
|
||
results=multi_threading(queries,"",file_id,2)
|
||
if not results:
|
||
print("errror!")
|
||
else:
|
||
# 打印结果
|
||
for question, response in results:
|
||
technical_requirements.append(response)
|
||
technical_requirements_combined_res=combine_json_results(technical_requirements)
|
||
json_string = json.dumps(technical_requirements_combined_res, ensure_ascii=False, indent=4)
|
||
print(json_string)
|
||
if __name__ == "__main__":
|
||
output_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles"
|
||
file_path="C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\磋商文件.doc"
|
||
fetch_purchasing_list(file_path,output_folder,1)
|
||
|