pdf_title_image/celery_tasks/parser.py

# -*- coding: utf-8 -*-
# @Author: privacy
# @Date:   2024-06-11 13:43:14
# @Last Modified by:   privacy
# @Last Modified time: 2024-09-19 17:37:49
import os
import base64
import requests


def main(client_id, client_secret):
    url = "https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id={}&client_secret={}".format(client_id, client_secret)

    payload = ""
    headers = {
        'Content-Type': 'application/json',
        'Accept': 'application/json'
    }

    response = requests.request("POST", url, headers=headers, data=payload)

    print(response.text)
    return response.json()


def create_task(url, file_path, file_url):
    """
    Args:
        url: string, 服务请求链接
        file_path: 本地文件路径
        file_url: 文件链接
    Returns: 响应
    """
    file = open(file_path, 'rb').read()

    # 文件请求
    body = {
        "file": (os.path.basename(file_path), file, "multipart/form-data"),
    }

    # 文件链接请求
    # body = {
    #     "file_url": (file_url, "multipart/form-data")
    # }

    data = {
        "file_name": os.path.basename(file_path),
        "return_para_nodes": True
    }

    response = requests.post(url, data=data, files=body)
    return response.json()


def query_task(url, task_id):
    """
    Args:
        url: string, 请求链接
        task_id: string, task id
    Returns: 响应
    """
    data = {
        "task_id": task_id
    }

    response = requests.post(url, data=data, files=data)
    return response.json()


if __name__ == '__main__':
    import time
    import json

    # client_id = 'DFIQUMXb59oGUDkvGhTw15mE'
    # client_secret = 'F5LkFLo4TatiLcCcJgIXbJrv5Kw04Rf0'
    # token = main(client_id, client_secret)['access_token']
    token = "24.0ab90c2e2b750b61995052ab6b94f62c.2592000.1728805729.282335-86574608"
    # # print(token)
    request_host = f"https://aip.baidubce.com/file/2.0/brain/online/v1/parser/task?access_token={token}"
    file_path = "D:/desktop/三峡水利/celery.pdf"
    response = create_task(request_host, file_path, "")
    print(response)

    time.sleep(10)

    task_id = response['result']['task_id']

    request_host = f"https://aip.baidubce.com/file/2.0/brain/online/v1/parser/task/query?access_token={token}"
    resp = query_task(request_host, task_id)

    print(resp)

    url = resp['result']['parse_result_url']
    response = requests.get(url)
    response.encoding = 'utf-8'

    with open('浙江国迈建设集团有限公司技术文件.json', 'w', encoding='utf-8') as fp:
        json.dump(response.json(), fp, indent=4, ensure_ascii=False)