文档内容解析

前提条件

已开通AI搜索开放平台服务，具体操作请参见开通服务。

已通过API-KEY完成身份鉴权，获取鉴权信息请参见获取API-KEY。

参数说明

• 请求体body最大不能超过8MB。

• 更多参数说明请参见文档内容解析。

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="替换为您的API-KEY",
                    # endpoint: 配置统一的请求入口 需要去掉http://
                    endpoint="替换API访问地址",
                    # 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，需要额外指定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：替换工作空间名称, ops-document-analyze-001: 服务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