zbparse/flask_app/general/纯技术参数要求提取.py

import json
import logging

from flask_app.general.format_change import pdf2docx, docx2pdf
from flask_app.general.通义千问long import upload_file
from flask_app.货物标.截取pdf货物标版 import truncate_pdf_main
from flask_app.货物标.技术参数要求提取 import get_technical_requirements

def get_global_logger(unique_id):
    if unique_id is None:
        return logging.getLogger()  # 获取默认的日志器
    logger = logging.getLogger(unique_id)
    return logger


logger = None

def extract_matching_keys(data_dict, good_list):
    """
    递归遍历data_dict，查找good_list中存在的键，并将匹配的键及其值添加到结果字典中。

    参数:
    - data_dict (dict): 要遍历的嵌套字典。
    - good_list (list): 包含要查找的键的列表。

    返回:
    - dict: 包含所有匹配键及其值的字典。
    """
    result = {}

    def recurse(current_dict):
        if isinstance(current_dict, dict):
            for key, value in current_dict.items():
                if key in good_list:
                    result[key] = value
                # 递归遍历子字典
                recurse(value)
        elif isinstance(current_dict, list):
            for item in current_dict:
                recurse(item)
        # 如果current_dict不是dict或list，则无需进一步处理
    recurse(data_dict)
    return result

def get_technical_requirements_main(file_path,file_type,unique_id,output_folder):
    global logger
    logger = get_global_logger(unique_id)
    if file_type == 1:  # docx
        docx_path = file_path
        pdf_path = docx2pdf(docx_path)  # 将docx转换为pdf以供后续处理
    elif file_type == 2:  # pdf
        pdf_path = file_path
    elif file_type == 3:  # doc
        pdf_path = docx2pdf(file_path)
    else:
        logger.error("Unsupported file type provided. Preprocessing halted.")
        return None
    truncate_file=truncate_pdf_main(pdf_path,output_folder,5)[0]
    if not truncate_file:
        truncate_file=pdf_path    #直接传整份文件
    truncate_file_docx=pdf2docx(truncate_file)
    file_id=upload_file(truncate_file_docx)
    # file_id=upload_file(truncate_file)
    final_res=get_technical_requirements(file_id,pdf_path)
    # 安全地提取 "技术要求" 内部的字典内容
    if isinstance(final_res, dict) and '技术要求' in final_res and isinstance(final_res['技术要求'], dict):
        technical_requirements = final_res['技术要求']
        good_list = technical_requirements.pop('货物列表', [])  # 如果 '货物列表' 不存在，返回 []
        print(good_list)
        logger.info("Collected good_list from the processing function: %s", good_list)
        return extract_matching_keys(technical_requirements,good_list)
    else:
        return final_res
if __name__ == "__main__":
    file_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"
    file_type=2
    output_folder = "C:\\Users\\Administrator\\Desktop\\fsdownload\\45f650ce-e519-457b-9ad6-5840e2ede539\\tmp"
    res=get_technical_requirements_main(file_path,file_type,"123",output_folder)
    print(json.dumps(res,ensure_ascii=False,indent=4))