pdf_title_image/celery_tasks/all_instance.py

#!/usr/bin/python
# -*- coding=utf-8 -*-
# @Create Time:		2024-12-23 15:22:39
# @Last Modified time: 2024-12-25 16:17:09
import uuid
import time
import json
import requests
from .get_tender_info import PdfExtractAttr_
from .document_ import DocumentPreReview
from .busi_instance import busi_loc
from .tech_instance import tech_loc
from .parse_textmind_result import get_ocr_new


def detail_task(zb_file: str, tb_file: str, tb_filename: str, projectId: str, project: str, supplier: str):
    host = '192.168.1.111:9999'

    detail_check_url = f'http://{host}/bm/alg/result_check_detail'

    agent = PdfExtractAttr_(file_path=zb_file)
    zb_table_path = f'./tmp/zb_table-{uuid.uuid4()}.json'
    agent.parse_table_pro(table_path=zb_table_path)

    dpr = DocumentPreReview(zb_table_path)
    scrutinize_dict = dpr.get_table()
    print(scrutinize_dict)

    with open(tb_file, 'r', encoding='utf-8') as fp:
        raw = json.load(fp)
    result = get_ocr_new(raw=raw, pretty=True)

    busi_score = busi_loc(
        scrutinize_dict=scrutinize_dict,
        outline_dict=result['outline'],
        title_list=result['title'],
        table_list=result['tables'],
        image_list=result['images'],
        supplier=supplier,
        project=project,
        file_name=tb_filename.split('.')[0] + 'pdf'
    )
    busi_score['name'] = '商务部分评分标准'

    tech_score = tech_loc(
        scrutinize_dict=scrutinize_dict,
        outline_dict=result['outline'],
        content_list=result['contents'],
        supplier=supplier,
        project=project,
        file_name=tb_filename.split('.')[0] + 'pdf'
    )
    tech_score['name'] = '技术部分评分标准'

    detail_data = {
        'projectId': projectId,
        'projectName': project,
        'bidderUnit': supplier,
        'list': [busi_score, tech_score]
    }

    print(detail_data)

    detail_check_response = requests.post(url=detail_check_url, json=detail_data)

    print("detail_check_response: ", detail_check_response.json())

    return