前提條件

已開通AI搜索開放平臺服務，具體操作請參見開通服務。

已通過API-KEY完成身份鑒權，獲取鑒權信息請參見獲取API-KEY。

參數說明

• 請求體body最大不能超過8MB。

• 更多參數說明請參見文檔內容解析。

import base64
import os
import time
from alibabacloud_tea_openapi.models import Config
from alibabacloud_searchplat20240529.client import Client
from alibabacloud_searchplat20240529.models import (
    CreateDocumentAnalyzeTaskRequestDocument,
    CreateDocumentAnalyzeTaskRequestOutput,
    CreateDocumentAnalyzeTaskRequest,
    CreateDocumentAnalyzeTaskResponse,
    GetDocumentAnalyzeTaskStatusRequest,
    GetDocumentAnalyzeTaskStatusResponse
)

if __name__ == '__main__':
    config = Config(bearer_token="替換為您的API-KEY",
                    # endpoint: 配置統一的請求入口 需要去掉http://
                    endpoint="替換API訪問地址",
                    # 支持 protocol 配置 HTTPS/HTTP
                    protocol="http")
    client = Client(config=config)
    # URL模式
    document = CreateDocumentAnalyzeTaskRequestDocument(
        url="http://test.pdf",
        file_type="pdf"
    )

    # 本地模式，需要額外指定file_name
    # file_path = "path/to/xxx.pdf"
    # document = CreateDocumentAnalyzeTaskRequestDocument(
    #     content=base64.b64encode(open(file_path,'rb').read()).decode(),
    #     file_name=os.path.basename(file_path)
    # )

    output = CreateDocumentAnalyzeTaskRequestOutput(image_storage="url")
    request = CreateDocumentAnalyzeTaskRequest(document=document, output=output)
    # default：替換工作空間名稱, ops-document-analyze-001: 服務id
    response: CreateDocumentAnalyzeTaskResponse = client.create_document_analyze_task(
        "default", "ops-document-analyze-001", request)
    task_id = response.body.result.task_id
    print("task_id: " + task_id)
    request = GetDocumentAnalyzeTaskStatusRequest(task_id=task_id)
    while True:
        response: GetDocumentAnalyzeTaskStatusResponse = client.get_document_analyze_task_status(
            "default", "ops-document-analyze-001", request)
        status = response.body.result.status
        print("status: " + status)
        if status == "PENDING":
            time.sleep(5)
        elif status == "SUCCESS":
            data = response.body.result.data
            usage = response.body.usage
            print("content:\n" + data.content[:1000] + "\n")
            print("page count: " + str(data.page_num))
            print("usage: " + str(usage))
            break
        else:
            print(response.body.result)
            break