1import requests
2import os
3import base64
4
5
6def create_task(url, file_path, file_url):
7    """
8    Args:
9        url: string, 服务请求链接
10        file_path: 本地文件路径
11        file_url: 文件链接
12    Returns: 响应
13    """
14    # 文件请求
15    with open(file_path, "rb") as f:
16        file_data = base64.b64encode(f.read())
17    data = {
18        "file_data": file_data, #与file_url二选一，只传 URL 时不要带 file_data
19        "file_url": file_url,
20        "file_name": os.path.basename(file_path)
21    }
22  
23    # 文档切分参数，非必传
24    # return_doc_chunks = json.dumps({"switch": True, "chunk_size": -1})
25    # data["return_doc_chunks"] = return_doc_chunks
26  
27    headers = {'Content-Type': 'application/x-www-form-urlencoded'}
28
29    response = requests.post(url, headers=headers, data=data)
30    return response
31
32if __name__ == '__main__':
33    request_host = "https://aip.baidubce.com/rest/2.0/brain/online/v2/parser/task?" \
34                   "access_token={token}"
35    file_path = "./test.pdf"
36    response = create_task(request_host, file_path, "")
37    print(response.json())

1{
2    "error_code": 0,
3    "error_msg": "",
4    "log_id": "10138598131137362685273505665433",
5    "result": {
6        "task_id": "task-3zy9Bg8CHt1M4pPOcX2q5bg28j26801S"
7    }
8}

1{
2    "error_code": 282003,
3    "error_msg": "missing parameters",
4    "log_id": "37507631033585544507983253924141",
5    "result": "null"
6}

1import requests
2
3def query_task(url, task_id):
4    """
5    Args:
6        url: string, 请求链接
7        task_id: string, task id
8    Returns: 响应
9    """
10    data = {
11        "task_id": task_id
12    }
13    headers = {'Content-Type': 'application/x-www-form-urlencoded'}
14    print(url)
15    response = requests.post(url, headers=headers, data=data)
16    return response
17
18
19if __name__ == '__main__':
20    # 需要替换为实际的任务id
21    task_id = "task_id"
22    # {access_token} 需要替换为实际调用鉴权接口获取的access_token
23    request_host = "https://aip.baidubce.com/rest/2.0/brain/online/v2/parser/task/query?access_token={access_token}"
24    resp = query_task(request_host, task_id)
25    print(resp.json())

1{
2  "error_code": 0,
3  "error_msg": "success",
4  "log_id": "23082741357017441497115454226056",
5  "result": {
6    "task_id": "task-example",
7    "status": "success",
8    "task_error": null,
9    "parse_result_url": "https://example.invalid/result.json",
10    "markdown_url": "https://example.invalid/result.md",
11    "cost_page_num": 5
12  }
13}

1{
2  "cells": [
3    {"text": "合并表头"},
4    {"text": "备注"},
5    {"text": "A"},
6    {"text": "B"},
7    {"text": "C"}
8  ],
9  "matrix": [[0, 0, 1], [2, 3, 4]]
10}

1{
2  "file_name": "standard-layout-synthetic-fixture.pdf",
3  "file_id": "file-example",
4  "pages": [
5    {
6      "page_id": "page-example",
7      "page_num": 0,
8      "page_angle": 0,
9      "layouts": [
10        {
11          "layout_id": "header-example",
12          "text": "文档页眉",
13          "position": [62, 31, 112, 8],
14          "type": "head_tail",
15          "sub_type": "header"
16        },
17        {
18          "layout_id": "title-example",
19          "text": "文档标题",
20          "position": [110, 78, 375, 22],
21          "type": "title",
22          "sub_type": "title_1"
23        }
24      ],
25      "meta": {
26        "page_width": 595,
27        "page_height": 841,
28        "is_scan": false,
29        "page_type": "doc"
30      }
31    }
32  ]
33}