电子文档解析

调用方式

电子文档解析接口为同步接口，调用SubmitDigitalDocStructureJob或者SubmitDigitalDocStructureJobAdvance接口均可进行同步任务提交，等待超时时间可设置为5分钟。

调用电子文档解析提交服务SubmitDigitalDocStructureJob接口

同步提交服务支持上传本地文件和url文件两种方式：

• 本地文件上传的同步提交服务接口为：SubmitDigitalDocStructureJobAdvance接口。

• url上传的同步提交服务接口为：SubmitDigitalDocStructureJob接口。

请求参数

返回参数

使用示例

本接口支持本地文档上传和传入文档url这两种调用方式。

• 以Java SDK为例，本地文档上传调用方式的请求示例代码如下，调用电子文档解析提交服务SubmitDigitalDocStructureJobAdvance接口，通过fileUrlObject参数实现本地文档上传。

  说明

  获取并使用AccessKey信息的方式，可参考SDK概述中不同语言的SDK使用指南。

  Java

  import com.aliyun.docmind_api20220711.models.*;
  import com.aliyun.teaopenapi.models.Config;
  import com.aliyun.docmind_api20220711.Client;
  import com.aliyun.teautil.models.RuntimeOptions;
  import java.io.File;
  import java.io.FileInputStream;
  
  public static void main(String[] args) throws Exception {
          submit();
      }
  public static void submit() throws Exception {
      // 使用默认凭证初始化Credentials Client。
      com.aliyun.credentials.Client credentialClient = new com.aliyun.credentials.Client();
      Config config = new Config()
          // 通过credentials获取配置中的AccessKey ID
          .setAccessKeyId(credentialClient.getAccessKeyId())
          // 通过credentials获取配置中的AccessKey Secret
          .setAccessKeySecret(credentialClient.getAccessKeySecret());
      // 访问的域名，支持ipv4和ipv6两种方式，ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
      config.endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
      Client client = new Client(config);
      // 创建RuntimeObject实例并设置运行参数
      RuntimeOptions runtime = new RuntimeOptions();
      SubmitDigitalDocStructureJobAdvanceRequest request = new SubmitDigitalDocStructureJobAdvanceRequest();
      File file = new File("D:\\example.xlsx");
      request.fileUrlObject = new FileInputStream(file);
      request.fileName = "example.xlsx";
      request.revealMarkdown=true;
      // 发起请求并处理应答或异常。                                    
      SubmitDigitalDocStructureJobResponse response = client.submitDigitalDocStructureJobAdvance(request, runtimeOptions);
      System.out.println(JSON.toJSON(response.getBody()));
  }

  Node.js

  const Client = require('@alicloud/docmind-api20220711');
  const Credential = require('@alicloud/credentials');
  const Util = require('@alicloud/tea-util');
  const fs = require('fs');
  
  const getResult = async () => {
  	// 使用默认凭证初始化Credentials Client
    const cred = new Credential.default();
    const client = new Client.default({
      // 访问的域名，支持ipv4和ipv6两种方式，ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
      endpoint: 'docmind-api.cn-hangzhou.aliyuncs.com',
      // 通过credentials获取配置中的AccessKey ID
      accessKeyId: cred.credential.accessKeyId,
      // 通过credentials获取配置中的AccessKey Secret
      accessKeySecret: cred.credential.accessKeySecret,
      type: 'access_key',
      regionId: 'cn-hangzhou'
    });
    
    const advanceRequest = new Client.SubmitDigitalDocStructureJobAdvanceRequest();
    const file = fs.createReadStream('./example.pdf');
    advanceRequest.fileUrlObject = file;
    advanceRequest.fileName = 'example.pdf';
    const runtimeObject = new Util.RuntimeOptions({});
    const response = await client.submitDigitalDocStructureJobAdvance(advanceRequest, runtimeObject);
  	return response.body;
  };

  Python

  from alibabacloud_docmind_api20220711.client import Client as docmind_api20220711Client
  from alibabacloud_tea_openapi import models as open_api_models
  from alibabacloud_docmind_api20220711 import models as docmind_api20220711_models
  from alibabacloud_tea_util.client import Client as UtilClient
  from alibabacloud_tea_util import models as util_models
  from alibabacloud_credentials.client import Client as CredClient
  
  if __name__ == '__main__':
    	# 使用默认凭证初始化Credentials Client。
      cred=CredClient()
      config = open_api_models.Config(
          # 通过credentials获取配置中的AccessKey ID
          access_key_id=cred.get_credential().get_access_key_id(),
          # 通过credentials获取配置中的AccessKey Secret
          access_key_secret=cred.get_credential().get_access_key_secret()
      )
      # 访问的域名
      config.endpoint = f'docmind-api.cn-hangzhou.aliyuncs.com'
      client = docmind_api20220711Client(config)
      request = docmind_api20220711_models.SubmitDigitalDocStructureJobAdvanceRequest(
          # file_url_object : 本地文件流
          file_url_object=open("./example.xlsx", "rb"),
          # file_name ：文件名称。名称必须包含文件类型
          file_name='123.xlsx',
          reveal_markdown=True,
          # file_name_extension : 文件后缀格式。与文件名二选一
          # file_name_extension='xlsx'
      )
      runtime = util_models.RuntimeOptions()
      try:
          # 复制代码运行请自行打印 API 的返回值
          response = client.submit_digital_doc_structure_job_advance(request, runtime)
          # API返回值格式层级为 body -> data -> 具体属性。
          print(response.body)
      except Exception as error:
          # 如有需要，请打印 error
          UtilClient.assert_as_string(error.message)  

  Go

  import (
  	"fmt"
  	"os"
    
  	openClient "github.com/alibabacloud-go/darabonba-openapi/v2/client"
  	"github.com/alibabacloud-go/docmind-api-20220711/client"
  	"github.com/alibabacloud-go/tea-utils/v2/service"
    "github.com/aliyun/credentials-go/credentials"
  )
  
  func submit(){
   // 使用默认凭证初始化Credentials Client。
  	credential, err := credentials.NewCredential(nil)
  	// 通过credentials获取配置中的AccessKey ID
  	accessKeyId, err := credential.GetAccessKeyId()
  	// 通过credentials获取配置中的AccessKey Secret
  	accessKeySecret, err := credential.GetAccessKeySecret()
    // 访问的域名，支持ipv4和ipv6两种方式，ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
    var endpoint string = "docmind-api.cn-hangzhou.aliyuncs.com"
  	config := openClient.Config{AccessKeyId: accessKeyId, AccessKeySecret: accessKeySecret, Endpoint: &endpoint}
  	// 初始化client
    cli, err := client.NewClient(&config)
  	if err != nil {
  		panic(err)
  	}
    // 上传本地文档调用接口
    filename := "D:\\example.pdf"    
    f, err := os.Open(filename)
  	if err != nil {
      panic(err)
  	}
    // 初始化接口request
    request := client.SubmitDigitalDocStructureJobAdvanceRequest{
  		FileName:      &filename,
  		FileUrlObject: f,
  	}
    // 创建RuntimeObject实例并设置运行参数
    options := service.RuntimeOptions{}
    response, err := cli.SubmitDigitalDocStructureJobAdvance(&request, &options)
    if err != nil {
  		panic(err)
  	}
    // 打印结果
  	fmt.Println(response.Body.String())
  }

  C#

  using Newtonsoft.Json;
  using System;
  using System.Collections;
  using System.Collections.Generic;
  using System.IO;
  using System.Threading.Tasks;
  
  using Tea;
  using Tea.Utils;
  
    public static void SubmitFile()
          {
              // 使用默认凭证初始化Credentials Client。
            	var akCredential = new Aliyun.Credentials.Client(null);
              AlibabaCloud.OpenApiClient.Models.Config config = new AlibabaCloud.OpenApiClient.Models.Config
              {
                  // 通过credentials获取配置中的AccessKey Secret
                  AccessKeyId = akCredential.GetAccessKeyId(),
                  // 通过credentials获取配置中的AccessKey Secret
                  AccessKeySecret = akCredential.GetAccessKeySecret(),
              };
              // 访问的域名
              config.Endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
              AlibabaCloud.SDK.Docmind_api20220711.Client client = new AlibabaCloud.SDK.Docmind_api20220711.Client(config);
                 //需要安装额外的依赖库--> AlibabaCloud.DarabonbaStream        
      				Stream bodySyream = AlibabaCloud.DarabonbaStream.StreamUtil.ReadFromFilePath("<YOUR-FILE-PATH>");
              AlibabaCloud.SDK.Docmind_api20220711.Models.SubmitDigitalDocStructureJobAdvanceRequest request = new AlibabaCloud.SDK.Docmind_api20220711.Models.SubmitDigitalDocStructureJobAdvanceRequest
              {
                  FileUrlObject = bodySyream,
                  FileNameExtension = "pdf"
              };
              AlibabaCloud.TeaUtil.Models.RuntimeOptions runtime = new AlibabaCloud.TeaUtil.Models.RuntimeOptions();
              try
              {
                  // 复制代码运行请自行打印 API 的返回值
                  client.SubmitDigitalDocStructureJobAdvance(request, runtime);
              }
              catch (TeaException error)
              {
                  // 如有需要，请打印 error
                  AlibabaCloud.TeaUtil.Common.AssertAsString(error.Message);
              }
              catch (Exception _error)
              {
                  TeaException error = new TeaException(new Dictionary<string, object>
                  {
                      { "message", _error.Message }
                  });
                  // 如有需要，请打印 error
                  AlibabaCloud.TeaUtil.Common.AssertAsString(error.Message);
              }
          }

• 以Java SDK为例，传入文档url调用方式的请求示例代码如下，调用SubmitDigitalDocStructureJob接口，通过fileUrl参数实现传入文档url。请注意，您传入的文档url必须为公网可访问下载的url地址，无跨域限制，url不带特殊转义字符。

  说明

  获取并使用AccessKey信息的方式，可参考SDK概述中不同语言的SDK使用指南。

  Java

  import com.aliyun.docmind_api20220711.models.*;
  import com.aliyun.teaopenapi.models.Config;
  import com.aliyun.docmind_api20220711.Client;
  
  public static void main(String[] args) throws Exception {
          submit();
      }
  public static void submit() throws Exception {
      // 使用默认凭证初始化Credentials Client。
      com.aliyun.credentials.Client credentialClient = new com.aliyun.credentials.Client();
      Config config = new Config()
          // 通过credentials获取配置中的AccessKey ID
          .setAccessKeyId(credentialClient.getAccessKeyId())
          // 通过credentials获取配置中的AccessKey Secret
          .setAccessKeySecret(credentialClient.getAccessKeySecret());
      // 访问的域名，支持ipv4和ipv6两种方式，ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
      config.endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
      Client client = new Client(config);
      SubmitDigitalDocStructureJobRequest request = new SubmitDigitalDocStructureJobRequest();
      request.fileName = "example.xlsx";
      request.fileUrl = "https://example.com/example.xlsx";
      request.revealMarkdown=true;
      SubmitDigitalDocStructureJobResponse response = client.submitDigitalDocStructureJob(request);
      System.out.println(JSON.toJSON(response.getBody()));
  }

  Node.js

  const Client = require('@alicloud/docmind-api20220711');
  const Credential = require('@alicloud/credentials');
  
  const getResult = async () => {
  	// 使用默认凭证初始化Credentials Client
    const cred = new Credential.default();
    const client = new Client.default({
      // 访问的域名，支持ipv4和ipv6两种方式，ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
      endpoint: 'docmind-api.cn-hangzhou.aliyuncs.com',
      // 通过credentials获取配置中的AccessKey ID
      accessKeyId: cred.credential.accessKeyId,
      // 通过credentials获取配置中的AccessKey Secret
      accessKeySecret: cred.credential.accessKeySecret,
      type: 'access_key',
      regionId: 'cn-hangzhou'
    });
    
    const request = new Client.SubmitDigitalDocStructureJobRequest();
    request.fileName = 'example.pdf';
    request.fileUrl = 'https://example.com/example.pdf';
    const response = await client.submitDocStructureJob(request);
    
    return response.body;
  }

  Python

  from alibabacloud_docmind_api20220711.client import Client as docmind_api20220711Client
  from alibabacloud_tea_openapi import models as open_api_models
  from alibabacloud_docmind_api20220711 import models as docmind_api20220711_models
  from alibabacloud_tea_util.client import Client as UtilClient
  from alibabacloud_credentials.client import Client as CredClient
  
  if __name__ == '__main__':
    	# 使用默认凭证初始化Credentials Client。
      cred=CredClient()
      config = open_api_models.Config(
          # 通过credentials获取配置中的AccessKey ID
          access_key_id=cred.get_credential().get_access_key_id(),
          # 通过credentials获取配置中的AccessKey Secret
          access_key_secret=cred.get_credential().get_access_key_secret()
      )
      # 访问的域名
      config.endpoint = f'docmind-api.cn-hangzhou.aliyuncs.com'
      client = docmind_api20220711Client(config)
      request = docmind_api20220711_models.SubmitDigitalDocStructureJobRequest(
          # file_url : 文件url地址
          file_url='https://example.com/example.xlsx',
          # file_name ：文件名称。名称必须包含文件类型
          file_name='123.xlsx',
          reveal_markdown=True,
          # file_name_extension : 文件后缀格式。与文件名二选一
          # file_name_extension='xlsx'
      )
      try:
          # 复制代码运行请自行打印 API 的返回值
          response = client.submit_digital_doc_structure_job(request)
          # API返回值格式层级为 body -> data -> 具体属性。
          print(response.body)   
      except Exception as error:
          # 如有需要，请打印 error
          UtilClient.assert_as_string(error.message) 

  Go

  import (
  	"fmt"
  
  	openClient "github.com/alibabacloud-go/darabonba-openapi/v2/client"
    "github.com/alibabacloud-go/docmind-api-20220711/client"
    "github.com/aliyun/credentials-go/credentials"
  )
  
  func submit(){
    // 使用默认凭证初始化Credentials Client。
  	credential, err := credentials.NewCredential(nil)
  	// 通过credentials获取配置中的AccessKey ID
  	accessKeyId, err := credential.GetAccessKeyId()
  	// 通过credentials获取配置中的AccessKey Secret
  	accessKeySecret, err := credential.GetAccessKeySecret()
    // 访问的域名，支持ipv4和ipv6两种方式，ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
    var endpoint string = "docmind-api.cn-hangzhou.aliyuncs.com"
  	config := openClient.Config{AccessKeyId: accessKeyId, AccessKeySecret: accessKeySecret, Endpoint: &endpoint}
  	// 初始化client
    cli, err := client.NewClient(&config)
  	if err != nil {
  		panic(err)
  	}
    // 文件URL
    fileURL := "https://example.com/example.pdf"
    // 文件名
    fileName := "example.pdf"
    // 初始化接口request
    request := client.SubmitDigitalDocStructureJobRequest{
  		FileUrl:  &fileURL,
  		FileName: &fileName,
  	}
    response, err := cli.SubmitDigitalDocStructureJob(&request)
    if err != nil {
  		panic(err)
  	}
    // 打印结果
  	fmt.Println(response.Body.String())
  }

  C#

  using Newtonsoft.Json;
  using System;
  using System.Collections;
  using System.Collections.Generic;
  using System.IO;
  using System.Threading.Tasks;
  
  using Tea;
  using Tea.Utils;
  
  public static void SubmitUrl()
          {
              // 使用默认凭证初始化Credentials Client。
            	var akCredential = new Aliyun.Credentials.Client(null);
              AlibabaCloud.OpenApiClient.Models.Config config = new AlibabaCloud.OpenApiClient.Models.Config
              {
                  // 通过credentials获取配置中的AccessKey Secret
                  AccessKeyId = akCredential.GetAccessKeyId(),
                  // 通过credentials获取配置中的AccessKey Secret
                  AccessKeySecret = akCredential.GetAccessKeySecret(),
              };
              // 访问的域名
              config.Endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
              AlibabaCloud.SDK.Docmind_api20220711.Client client = new AlibabaCloud.SDK.Docmind_api20220711.Client(config);
              AlibabaCloud.SDK.Docmind_api20220711.Models.SubmitDigitalDocStructureJobRequest request = new AlibabaCloud.SDK.Docmind_api20220711.Models.SubmitDigitalDocStructureJobRequest
              {
                  FileUrl = "https://example.pdf",
                  FileNameExtension = "pdf"
              };
              try
              {
                  // 复制代码运行请自行打印 API 的返回值
                  client.SubmitDigitalDocStructureJob(request);
              }
              catch (TeaException error)
              {
                  // 如有需要，请打印 error
                  AlibabaCloud.TeaUtil.Common.AssertAsString(error.Message);
              }
              catch (Exception _error)
              {
                  TeaException error = new TeaException(new Dictionary<string, object>
                  {
                      { "message", _error.Message }
                  });
                  // 如有需要，请打印 error
                  AlibabaCloud.TeaUtil.Common.AssertAsString(error.Message);
              }
          }

  PHP

  use AlibabaCloud\SDK\Docmindapi\V20220711\Docmindapi;
  use AlibabaCloud\SDK\Docmindapi\V20220711\Models\SubmitDocStructureJobRequest;
  use Darabonba\OpenApi\Models\Config;
  use AlibabaCloud\Tea\Utils\Utils\RuntimeOptions;
  use AlibabaCloud\Tea\Exception\TeaUnableRetryError;
  use AlibabaCloud\Credentials\Credential;
  
  // 使用默认凭证初始化Credentials Client。
  $bearerToken = new Credential();    
  $config = new Config();
  // 访问的域名，支持ipv4和ipv6两种方式，ipv6请使用docmind-api-dualstack.cn-hangzhou.aliyuncs.com
  $config->endpoint = "docmind-api.cn-hangzhou.aliyuncs.com";
  // 通过credentials获取配置中的AccessKey ID
  $config->accessKeyId = $bearerToken->getCredential()->getAccessKeyId();
  // 通过credentials获取配置中的AccessKey Secret
  $config->accessKeySecret = $bearerToken->getCredential()->getAccessKeySecret();
  $config->type = "access_key";
  $config->regionId = "cn-hangzhou";
  $client = new Docmindapi($config);
  $request = new SubmitDigitalDocStructureJobRequest();
  
  $runtime = new RuntimeOptions();
  $runtime->maxIdleConns = 3;
  $runtime->connectTimeout = 10000;
  $runtime->readTimeout = 10000;
  
  $request->fileName = "example.pdf";
  $request->fileUrl = "https://example.com/example.pdf";
  
  try {
    $response = $client->submitDigitalDocStructureJob($request, $runtime);
    var_dump($response->toMap());
  } catch (TeaUnableRetryError $e) {
    var_dump($e->getMessage());
    var_dump($e->getErrorInfo());
    var_dump($e->getLastException());
    var_dump($e->getLastRequest());
  }

处理成功后Status返回值为Success，表示处理成功。处理成功返回结果示例如下：

{
  "data":{
    "docInfo":{
      "pageCountEstimate":3,
      "docType":"pdf"
    },
    "styles":[ ],
    "layouts":[
      {
        "pos":[
          {
            "x":0,
            "y":0
          },
          {
            "x":1113,
            "y":0
          },
          {
            "x":1113,
            "y":1440
          },
          {
            "x":0,
            "y":1440
          }
        ],
        "index":0,
        "subType":"none",
        "text":"",
        "type":"image",
        "pageNum":[
          0
        ],
        "uniqueId":"31128703ac73c52f05717b3b654de020"
      },
      {
        "pos":[
          {
            "x":0,
            "y":0
          },
          {
            "x":1113,
            "y":0
          },
          {
            "x":1113,
            "y":1440
          },
          {
            "x":0,
            "y":1440
          }
        ],
        "index":0,
        "subType":"none",
        "text":"",
        "type":"image",
        "pageNum":[
          1
        ],
        "uniqueId":"25b2a6f63bdf57f0d7a4f3da67c8616a"
      },
      {
        "pos":[
          {
            "x":0,
            "y":0
          },
          {
            "x":1113,
            "y":0
          },
          {
            "x":1113,
            "y":1440
          },
          {
            "x":0,
            "y":1440
          }
        ],
        "index":0,
        "subType":"none",
        "text":"",
        "type":"image",
        "pageNum":[
          2
        ],
        "uniqueId":"8c651c04c72a029b4be4ed80aa57fbbd"
      }
    ],
    "version":"1.2.0",
    "requestId":"docmind-20240820-6bf3e1bc1f164f0c99b8a12cfbcbeXXX"
  },
  "requestId":"1556A10B-E31C-5B21-8A5E-2179069D2XXX",
  "id":"docmind-20240820-6bf3e1bc1f164f0c99b8a12cfbcbeXXX",
  "status":"Success"
}

具体的处理结果在Data节点中，如下为Data节点的具体格式：

场景示例

本内容阐述获取JSON后，场景处理使用上建议和方案。

获取markdown信息

GetDocStructureResult设置RevealMarkdown为true，ImageStrategy为url。

import json
response = json.load(open("demo.json", "r"))
doc_json = response["Data"]

markdown_str = ""
for layout in doc_json["layouts"]:
  markdown_str += layout["markdownContent"] + "\n"
print(markdown_str)

获取指定层级内容

SubmitDocStructureJob/SubmitDocStructureJobAdvance接口中，设置doc_tree或default，用于获取文档的结构信息。

import json
response = json.load(open("demo.json", "r"))
doc_json = response["Data"]
doc_tree = doc_json["logics"]["docTree"]
layout_cache: {} = {}
for layout in doc_json["layouts"]:
    layout_cache[layout["uniqueId"]] = layout
    layout["children"] = list()

for node in doc_tree:
    father = node["backlink"]["上级"][0]
    child = node["uniqueId"]
    if father in layout_cache:
        # 设置 子layout
        layout_cache[father]["children"].append(layout_cache[child])
for layout in doc_json["layouts"]:
    # 当前layout下的子layout
    print(layout["children"])

附录

doc-json数据结构

VERSION（STRING: DOC-JSON版本信息）

版面类型

文档智能解析返回结果中，版面的类型type及子类型subType列表如下：