import requests
import os
import base64

API_KEY = "bce-v3/ALTAK-xxxxxxxx/xxxxxxxxxxxxxxxx"
CREATE_URL = "https://aip.baidubce.com/rest/2.0/brain/online/v2/paddle-vl-parser/task"


def create_task(file_path, file_url=""):
    """
    Args:
        file_path: 本地文件路径
        file_url: 文件链接
    Returns: 响应
    """
    with open(file_path, "rb") as f:
        file_data = base64.b64encode(f.read()).decode("utf-8")

    data = {
        "file_data": file_data,
        "file_url": file_url,     # file_path 和 file_url 只能传入其中一个，不可同时传入
        "file_name": os.path.basename(file_path)
    }

    # 文档切分参数，非必传
    # return_doc_chunks = json.dumps({"switch": True, "chunk_size": -1})
    # data["return_doc_chunks"] = return_doc_chunks

    headers = {
        "Content-Type": "application/x-www-form-urlencoded",
        "Authorization": f"Bearer {API_KEY}",
    }

    response = requests.post(CREATE_URL, headers=headers, data=data, timeout=120)
    return response


if __name__ == '__main__':
    file_path = "./test.pdf"
    print(create_task(file_path).json())