zbparse/flask_app/货物标/提取采购需求main.py

import concurrent.futures
import json
import time

from flask_app.货物标.技术要求提取 import get_technical_requirements
from flask_app.main.通义千问long import upload_file
from 商务服务其他要求提取 import get_business_requirements
from flask_app.main.json_utils import nest_json_under_key
#获取采购清单
def fetch_procurement_reqs(truncate_file):
    # 上传文件并获取 file_id
    file_id = upload_file(truncate_file)

    # 使用 ThreadPoolExecutor 并行处理 get_technical_requirements 和 get_business_requirements
    with concurrent.futures.ThreadPoolExecutor() as executor:
        # 提交任务给线程池
        future_technical = executor.submit(get_technical_requirements, file_id)
        time.sleep(1)
        future_business = executor.submit(get_business_requirements, truncate_file, file_id)

        # 获取并行任务的结果
        technical_requirements = future_technical.result()
        business_requirements = future_business.result()
    # 构建最终的嵌套结构，确保四个键平级
    procurement_reqs = {
            "技术要求": technical_requirements.get("技术要求", {}),
            "商务要求": business_requirements.get("商务要求", {}),
            "服务要求": business_requirements.get("服务要求", {}),
            "其他要求": business_requirements.get("其他要求", {})
    }

    return procurement_reqs

if __name__ == "__main__":
    output_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\货物标output"
    # file_path="C:\\Users\\Administrator\\Desktop\\货物标\\output1\\2-招标文件（2020年广水市中小学教师办公电脑系统及多媒体“班班通”设备采购安装项目）_procurement.pdf"
    file_path="C:\\Users\\Administrator\\Desktop\\货物标\\output1\\磋商文件_procurement.pdf"
    res=fetch_procurement_reqs(file_path)
    print(json.dumps(res, ensure_ascii=False, indent=4))