Amazon Textract로 문서 텍스트 분석

문서의 텍스트를 분석하려면(API)

1. 아직 설정하지 않았다면 다음과 같이 하세요.

   1. 사용자에게 AmazonTextractFullAccess 및 AmazonS3ReadOnlyAccess 권한을 부여합니다. 자세한 내용은 1단계: AWS 계정 설정 및 사용자 만들기 단원을 참조하십시오.

   2. AWS CLI 및 AWS SDKs를 설치하고 구성합니다. 자세한 내용은 2단계: AWS CLI 및 AWS SDKs 설정 단원을 참조하십시오.

2. 문서가 포함된 이미지를 S3 버킷에 업로드합니다.

   이에 관한 지침은 Amazon Simple Storage Service 사용 설명서에서 Amazon S3에 객체 업로드를 참조하세요.

3. 다음 예제를 사용하여 AnalyzeDocument 작업을 호출합니다.

   Java

   다음 예제 코드는 감지된 항목 주위에 문서와 상자를 표시합니다.

   함수에서 bucket 및의 값을 2단계에서 사용한 Amazon S3 버킷 및 문서 이미지의 document 이름으로 main바꿉니다. credentialsProvider의 값을 개발자 프로필 이름으로 바꿉니다.

   
   //Loads document from S3 bucket. Displays the document and polygon around detected lines of text.
   import java.awt.*;
   import java.awt.image.BufferedImage;
   import java.util.List;
   import javax.imageio.ImageIO;
   import javax.swing.*;
   import com.amazonaws.services.s3.AmazonS3;
   import com.amazonaws.services.s3.AmazonS3ClientBuilder;
   import com.amazonaws.services.s3.model.S3ObjectInputStream;
   import com.amazonaws.auth.profile.ProfileCredentialsProvider;
   import com.amazonaws.services.textract.AmazonTextract;
   import com.amazonaws.services.textract.AmazonTextractClientBuilder;
   import com.amazonaws.services.textract.model.AnalyzeDocumentRequest;
   import com.amazonaws.services.textract.model.AnalyzeDocumentResult;
   import com.amazonaws.services.textract.model.Block;
   import com.amazonaws.services.textract.model.BoundingBox;
   import com.amazonaws.services.textract.model.Document;
   import com.amazonaws.services.textract.model.S3Object;
   import com.amazonaws.services.textract.model.Point;
   import com.amazonaws.services.textract.model.Relationship;
   import com.amazonaws.client.builder.AwsClientBuilder.EndpointConfiguration;
   
   public class AnalyzeDocument extends JPanel {
   
       private static final long serialVersionUID = 1L;
   
       BufferedImage image;
   
       AnalyzeDocumentResult result;
   
       public AnalyzeDocument(AnalyzeDocumentResult documentResult, BufferedImage bufImage) throws Exception {
           super();
   
           result = documentResult; // Results of text detection.
           image = bufImage; // The image containing the document.
   
       }
   
       // Draws the image and text bounding box.
       public void paintComponent(Graphics g) {
   
           int height = image.getHeight(this);
           int width = image.getWidth(this);
   
           Graphics2D g2d = (Graphics2D) g; // Create a Java2D version of g.
   
           // Draw the image.
           g2d.drawImage(image, 0, 0, image.getWidth(this), image.getHeight(this), this);
   
           // Iterate through blocks and display bounding boxes around everything.
   
           List<Block> blocks = result.getBlocks();
           for (Block block : blocks) {
               DisplayBlockInfo(block);
               switch(block.getBlockType()) {
               
               case "KEY_VALUE_SET":
                   if (block.getEntityTypes().contains("KEY")){
                       ShowBoundingBox(height, width, block.getGeometry().getBoundingBox(), g2d, new Color(255,0,0));
                   }
                   else {  //VALUE
                       ShowBoundingBox(height, width, block.getGeometry().getBoundingBox(), g2d, new Color(0,255,0));
                   }
                   break;
               case "TABLE":
                   ShowBoundingBox(height, width, block.getGeometry().getBoundingBox(), g2d, new Color(0,0,255));
                   break;
               case "CELL":
                   ShowBoundingBox(height, width, block.getGeometry().getBoundingBox(), g2d, new Color(255,255,0));
                   break;
               case "SELECTION_ELEMENT":
                   if (block.getSelectionStatus().equals("SELECTED"))
                       ShowSelectedElement(height, width, block.getGeometry().getBoundingBox(), g2d, new Color(0,0,255));
                   break;    
               default:
                   //PAGE, LINE & WORD
                   //ShowBoundingBox(height, width, block.getGeometry().getBoundingBox(), g2d, new Color(200,200,0));
               }
           }
   
            // uncomment to show polygon around all blocks
            //ShowPolygon(height,width,block.getGeometry().getPolygon(),g2d);
         
         
       }
   
       // Show bounding box at supplied location.
       private void ShowBoundingBox(int imageHeight, int imageWidth, BoundingBox box, Graphics2D g2d, Color color) {
   
           float left = imageWidth * box.getLeft();
           float top = imageHeight * box.getTop();
   
           // Display bounding box.
           g2d.setColor(color);
           g2d.drawRect(Math.round(left), Math.round(top),
                   Math.round(imageWidth * box.getWidth()), Math.round(imageHeight * box.getHeight()));
   
       }
       private void ShowSelectedElement(int imageHeight, int imageWidth, BoundingBox box, Graphics2D g2d, Color color) {
   
           float left = imageWidth * box.getLeft();
           float top = imageHeight * box.getTop();
   
           // Display bounding box.
           g2d.setColor(color);
           g2d.fillRect(Math.round(left), Math.round(top),
                   Math.round(imageWidth * box.getWidth()), Math.round(imageHeight * box.getHeight()));
   
       }
   
       // Shows polygon at supplied location
       private void ShowPolygon(int imageHeight, int imageWidth, List<Point> points, Graphics2D g2d) {
   
           g2d.setColor(new Color(0, 0, 0));
           Polygon polygon = new Polygon();
   
           // Construct polygon and display
           for (Point point : points) {
               polygon.addPoint((Math.round(point.getX() * imageWidth)),
                       Math.round(point.getY() * imageHeight));
           }
           g2d.drawPolygon(polygon);
       }
       //Displays information from a block returned by text detection and text analysis
       private void DisplayBlockInfo(Block block) {
           System.out.println("Block Id : " + block.getId());
           if (block.getText()!=null)
               System.out.println("    Detected text: " + block.getText());
           System.out.println("    Type: " + block.getBlockType());
           
           if (block.getBlockType().equals("PAGE") !=true) {
               System.out.println("    Confidence: " + block.getConfidence().toString());
           }
           if(block.getBlockType().equals("CELL"))
           {
               System.out.println("    Cell information:");
               System.out.println("        Column: " + block.getColumnIndex());
               System.out.println("        Row: " + block.getRowIndex());
               System.out.println("        Column span: " + block.getColumnSpan());
               System.out.println("        Row span: " + block.getRowSpan());
   
           }
           
           System.out.println("    Relationships");
           List<Relationship> relationships=block.getRelationships();
           if(relationships!=null) {
               for (Relationship relationship : relationships) {
                   System.out.println("        Type: " + relationship.getType());
                   System.out.println("        IDs: " + relationship.getIds().toString());
               }
           } else {
               System.out.println("        No related Blocks");
           }
   
           System.out.println("    Geometry");
           System.out.println("        Bounding Box: " + block.getGeometry().getBoundingBox().toString());
           System.out.println("        Polygon: " + block.getGeometry().getPolygon().toString());
           
           List<String> entityTypes = block.getEntityTypes();
           
           System.out.println("    Entity Types");
           if(entityTypes!=null) {
               for (String entityType : entityTypes) {
                   System.out.println("        Entity Type: " + entityType);
               }
           } else {
               System.out.println("        No entity type");
           }
           
           if(block.getBlockType().equals("SELECTION_ELEMENT")) {
               System.out.print("    Selection element detected: ");
               if (block.getSelectionStatus().equals("SELECTED")){
                   System.out.println("Selected");
               }else {
                   System.out.println(" Not selected");
               }
           }
          
           if(block.getPage()!=null)
               System.out.println("    Page: " + block.getPage());            
           System.out.println();
       }
   
       public static void main(String arg[]) throws Exception {
   
           // The S3 bucket and document
           String document = "";
           String bucket = "";
           
           // set provider credentials
           AWSCredentialsProvider credentialsProvider = new ProfileCredentialsProvider("default");
   
           AmazonS3 s3client = AmazonS3ClientBuilder.standard().withCredentials(credentialsProvider)
                   .withEndpointConfiguration( 
                           new EndpointConfiguration("https://s3.amazonaws.com","us-east-1"))
                   .build();
           
                  
           // Get the document from S3
           com.amazonaws.services.s3.model.S3Object s3object = s3client.getObject(bucket, document);
           S3ObjectInputStream inputStream = s3object.getObjectContent();
           BufferedImage image = ImageIO.read(inputStream);
   
           // Call AnalyzeDocument 
           EndpointConfiguration endpoint = new EndpointConfiguration(
                   "https://textract.us-east-1.amazonaws.com", "us-east-1");
           AmazonTextract client = AmazonTextractClientBuilder.standard().withCredentials(credentialsProvider)
                   .withEndpointConfiguration(endpoint).build();
   
                   
           AnalyzeDocumentRequest request = new AnalyzeDocumentRequest()
                   .withFeatureTypes("TABLES","FORMS","SIGNATURES")
                    .withDocument(new Document().
                           withS3Object(new S3Object().withName(document).withBucket(bucket)));
   
   
           AnalyzeDocumentResult result = client.analyzeDocument(request);
   
           // Create frame and panel.
           JFrame frame = new JFrame("RotateImage");
           frame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
           AnalyzeDocument panel = new AnalyzeDocument(result, image);
           panel.setPreferredSize(new Dimension(image.getWidth(), image.getHeight()));
           frame.setContentPane(panel);
           frame.pack();
           frame.setVisible(true); 
   
       }
   }

   Java V2

   다음 예제 코드는 감지된 텍스트 줄 주위에 문서와 상자를 표시합니다.

   함수에서 bucket 및의 값을 2단계에서 사용한 Amazon S3 버킷 및 문서의 document 이름으로 main바꿉니다. 를 생성하는 줄profile-name의 TextractClient를 개발자 프로필의 이름으로 바꿉니다.

   import software.amazon.awssdk.auth.credentials.ProfileCredentialsProvider;
   import software.amazon.awssdk.core.SdkBytes;
   import software.amazon.awssdk.regions.Region;
   import software.amazon.awssdk.services.textract.TextractClient;
   import software.amazon.awssdk.services.textract.model.AnalyzeDocumentRequest;
   import software.amazon.awssdk.services.textract.model.Document;
   import software.amazon.awssdk.services.textract.model.FeatureType;
   import software.amazon.awssdk.services.textract.model.S3Object;
   import software.amazon.awssdk.services.textract.model.AnalyzeDocumentResponse;
   import software.amazon.awssdk.services.textract.model.Block;
   import software.amazon.awssdk.services.textract.model.TextractException;
   import java.io.File;
   import java.io.FileInputStream;
   import java.io.FileNotFoundException;
   import java.io.InputStream;
   import java.util.ArrayList;
   import java.util.Iterator;
   import java.util.List;
   // snippet-end:[textract.java2._analyze_doc.import]
   
   /**
    * Before running this Java V2 code example, set up your development environment, including your credentials.
    *
    * For more information, see the following documentation topic:
    *
    * https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
    */
   public class AnalyzeDocument {
   
       public static void main(String[] args) {
   
           final String usage = "\n" +
                    "Usage:\n" +
                    "    <bucketName> <docName> \n\n" +
                    "Where:\n" +
                    "    bucketName - The name of the Amazon S3 bucket that contains the document. \n\n" +
                    "    docName - The document name (must be an image, i.e., book.png). \n";
   
           if (args.length != 2) {
                    System.out.println(usage);
                    System.exit(1);
           }
   
          String bucketName = args[0];
          String docName = args[1];
           Region region = Region.US_EAST_1;
           TextractClient textractClient = TextractClient.builder()
                   .region(region)
                   .credentialsProvider(ProfileCredentialsProvider.create("profile-name"))
                   .build();
   
           analyzeDoc(textractClient, bucketName, docName);
           textractClient.close();
       }
   
       // snippet-start:[textract.java2._analyze_doc.main]
       public static void analyzeDoc(TextractClient textractClient, String bucketName, String docName) {
   
           try {
               S3Object s3Object = S3Object.builder()
                       .bucket(bucketName)
                       .name(docName)
                       .build();
   
                   // Create a Document object and reference the s3Object instance
                   Document myDoc = Document.builder()
                       .s3Object(s3Object)
                       .build();
   
               List<FeatureType> featureTypes = new ArrayList<FeatureType>();
               featureTypes.add(FeatureType.FORMS);
               featureTypes.add(FeatureType.TABLES);
   
               AnalyzeDocumentRequest analyzeDocumentRequest = AnalyzeDocumentRequest.builder()
                       .featureTypes(featureTypes)
                       .document(myDoc)
                       .build();
   
               AnalyzeDocumentResponse analyzeDocument = textractClient.analyzeDocument(analyzeDocumentRequest);
               List<Block> docInfo = analyzeDocument.blocks();
               Iterator<Block> blockIterator = docInfo.iterator();
   
               while(blockIterator.hasNext()) {
                   Block block = blockIterator.next();
                   System.out.println("The block type is " +block.blockType().toString());
               }
   
           } catch (TextractException e) {
   
               System.err.println(e.getMessage());
               System.exit(1);
           }
       }
       // snippet-end:[textract.java2._analyze_doc.main]
   }

   AWS CLI

   이 AWS CLI 명령은 analyze-document CLI 작업에 대한 JSON 출력을 표시합니다.

   Bucket 및의 값을 2단계에서 사용한 Amazon S3 버킷 및 문서의 Name 이름으로 바꿉니다. profile-name를 역할을 수임할 수 있는 프로파일의 이름으로 바꾸고를 코드를 실행하려는 리전region으로 바꿉니다.

   aws textract analyze-document \
       --document '{"S3Object":{"Bucket":"bucket","Name":"document"}}' \
       --feature-types '["TABLES","FORMS","SIGNATURES"]' \
       --profile profile-name \
       --region region

   쿼리 기능을 사용하려면 'QUERIES' 파라미터에 'feature-types' 값을 포함시킨 다음 'queries-config' 파라미터에 Queries 객체를 제공합니다. 어댑터를 사용하려면 AdapterConfig 파라미터Version에 Adapters 제공된 목록에 AdapterId및를 포함합니다.

   aws textract analyze-document \
   --document '{"S3Object":{"Bucket":"bucket","Name":"document"}}'\
    --feature-types '["QUERIES"]' \
   --queries-config '{"Queries":[{"Text":"Question"}]}' \
   --profile profile-name \
   --region region
   --adapters-config '{"Adapters": [{"AdapterId": "AdapterId", "Version": "1"]}' 

   Python

   다음 예제 코드는 감지된 항목 주위에 문서와 상자를 표시합니다.

   함수에서 bucket 및의 값을 2단계에서 사용한 Amazon S3 버킷 및 문서의 document 이름으로 main바꿉니다. profile-name를 역할을 수임할 수 있는 프로파일의 이름으로 바꾸고를 코드를 실행하려는 리전region으로 바꿉니다. 어댑터를 사용하려면 AdapterConfig 파라미터Version에 Adapters 제공된 목록에 AdapterId및를 포함합니다.

   #Analyzes text in a document stored in an S3 bucket. Display polygon box around text and angled text 
   import boto3
   import io
   from PIL import Image, ImageDraw
   
   def ShowBoundingBox(draw,box,width,height,boxColor):
                
       left = width * box['Left']
       top = height * box['Top'] 
       draw.rectangle([left,top, left + (width * box['Width']), top +(height * box['Height'])],outline=boxColor)   
   
   def ShowSelectedElement(draw,box,width,height,boxColor):
                
       left = width * box['Left']
       top = height * box['Top'] 
       draw.rectangle([left,top, left + (width * box['Width']), top +(height * box['Height'])],fill=boxColor)  
   
   # Displays information about a block returned by text detection and text analysis
   def DisplayBlockInformation(block):
       print('Id: {}'.format(block['Id']))
       if 'Text' in block:
           print('    Detected: ' + block['Text'])
       print('    Type: ' + block['BlockType'])
      
       if 'Confidence' in block:
           print('    Confidence: ' + "{:.2f}".format(block['Confidence']) + "%")
   
       if block['BlockType'] == 'CELL':
           print("    Cell information")
           print("        Column:" + str(block['ColumnIndex']))
           print("        Row:" + str(block['RowIndex']))
           print("        Column Span:" + str(block['ColumnSpan']))
           print("        RowSpan:" + str(block['ColumnSpan']))    
       
       if 'Relationships' in block:
           print('    Relationships: {}'.format(block['Relationships']))
       print('    Geometry: ')
       print('        Bounding Box: {}'.format(block['Geometry']['BoundingBox']))
       print('        Polygon: {}'.format(block['Geometry']['Polygon']))
       
       if block['BlockType'] == "KEY_VALUE_SET":
           print ('    Entity Type: ' + block['EntityTypes'][0])
       
       if block['BlockType'] == 'SELECTION_ELEMENT':
           print('    Selection element detected: ', end='')
   
           if block['SelectionStatus'] =='SELECTED':
               print('Selected')
           else:
               print('Not selected')    
       
       if 'Page' in block:
           print('Page: ' + block['Page'])
       print()
   
   def process_text_analysis(s3_connection, client, bucket, document):
   
       # Get the document from S3                          
       s3_object = s3_connection.Object(bucket,document)
       s3_response = s3_object.get()
   
       stream = io.BytesIO(s3_response['Body'].read())
       image=Image.open(stream)
   
       # Analyze the document
       image_binary = stream.getvalue()
       response = client.analyze_document(Document={'Bytes': image_binary},
           FeatureTypes=["TABLES", "FORMS", "SIGNATURES"])
   
       ### Uncomment to process using S3 object ###
       #response = client.analyze_document(
       #    Document={'S3Object': {'Bucket': bucket, 'Name': document}},
       #    FeatureTypes=["TABLES", "FORMS", "SIGNATURES"])
   
       ### Uncomment to analyze a local file ###
       # with open("pathToFile", 'rb') as img_file:
           ### To display image using PIL ###
       #    image = Image.open()
           ### Read bytes ###
       #    img_bytes = img_file.read()
       #    response = client.analyze_document(Document={'Bytes': img_bytes}, FeatureTypes=["TABLES", "FORMS", "SIGNATURES"])
       
       #Get the text blocks
       blocks=response['Blocks']
       width, height =image.size    
       print ('Detected Document Text')
      
       # Create image showing bounding box/polygon the detected lines/text
       for block in blocks:
           DisplayBlockInformation(block)    
           draw=ImageDraw.Draw(image)
   
           # Draw bounding boxes for different detected response objects
           if block['BlockType'] == "KEY_VALUE_SET":
               if block['EntityTypes'][0] == "KEY":
                   ShowBoundingBox(draw, block['Geometry']['BoundingBox'],width,height,'red')
               else:
                   ShowBoundingBox(draw, block['Geometry']['BoundingBox'],width,height,'green')             
           if block['BlockType'] == 'TABLE':
               ShowBoundingBox(draw, block['Geometry']['BoundingBox'],width,height, 'blue')
           if block['BlockType'] == 'CELL':
               ShowBoundingBox(draw, block['Geometry']['BoundingBox'],width,height, 'yellow')
           if block['BlockType'] == 'SELECTION_ELEMENT':
               if block['SelectionStatus'] =='SELECTED':
                   ShowSelectedElement(draw, block['Geometry']['BoundingBox'],width,height, 'blue')    
               
       # Display the image
       image.show()
       return len(blocks)
   
   def main():
   
       session = boto3.Session(profile_name='profile-name')
       s3_connection = session.resource('s3')
       client = session.client('textract', region_name='region')
       bucket = ""
       document = ""
       block_count=process_text_analysis(s3_connection, client, bucket, document)
       print("Blocks detected: " + str(block_count))
       
   if __name__ == "__main__":
       main()
   

   AnalyzeDocument 작업의 다양한 기능을 사용하려면 features-type 파라미터에 적절한 기능 유형을 제공합니다. 예를 들어 쿼리 기능을 사용하려면 feature-types 파라미터에 QUERIES 값을 포함시킨 다음 queries-config 파라미터에 Queries 객체를 제공합니다. 문서를 쿼리하려면 다음 코드의 query_document 함수를 이전 코드 예제에 추가합니다. 그런 다음 함수를 호출하는 question 변수와 줄을 이전 main 함수query_document에 포함합니다.

   def query_document(client, bucket, document, question):
       # Analyze the document
       response = client.analyze_document(Document={'S3Object': {'Bucket': bucket, 'Name': document}},
                                          FeatureTypes=["TABLES", "FORMS", "QUERIES"],
                                          QueriesConfig={'Queries':[
                                              {'Text':'{}'.format(question)}
                                          ]})
       
       for block in response['Blocks']:
           if block["BlockType"] == "QUERY":
               print("Query info:")
               print(block["Query"])
           if block["BlockType"] == "QUERY_RESULT":
               print("Query answer:")
               print(block["Text"])
   
   question = "query here"
   query_document(client, bucket, document, question)

   Node.js

   다음 예제 코드는 감지된 항목 주위에 문서와 상자를 표시합니다.

   다음 코드에서 bucket 및의 값을 2단계에서 사용한 Amazon S3 버킷 및 문서의 photo 이름으로 바꿉니다. 의 값을 계정과 연결된 region 리전으로 바꿉니다. credentials의 값을 개발자 프로필 이름으로 바꿉니다.

   // Import required AWS SDK clients and commands for Node.js
   import { AnalyzeDocumentCommand } from  "@aws-sdk/client-textract";
   import  { TextractClient } from "@aws-sdk/client-textract";
   import {fromIni} from '@aws-sdk/credential-providers';
   
   // Set the AWS Region.
   const REGION = "region"; //e.g. "us-east-1"
   const profileName = "default";
   
   // Create SNS service object.
   const textractClient = new TextractClient({region: REGION, 
     credentials: fromIni({profile: profileName,}), 
   });
   
   const bucket = 'buckets'
   const photo = 'photo'
   
   // Set params
   const params = {
       Document: {
         S3Object: {
           Bucket: bucket,
           Name: photo
         },
       },
       FeatureTypes: ['TABLES', 'FORMS', 'SIGNATURES'],
     }
   
   const displayBlockInfo = async (response) => {
       try {
           response.Blocks.forEach(block => {
               console.log(`ID: ${block.Id}`)
               console.log(`Block Type: ${block.BlockType}`)
               if ("Text" in block && block.Text !== undefined){
                   console.log(`Text: ${block.Text}`)
               }
               else{}
               if ("Confidence" in block && block.Confidence !== undefined){
                   console.log(`Confidence: ${block.Confidence}`)
               }
               else{}
               if (block.BlockType == 'CELL'){
                   console.log("Cell info:")
                   console.log(`   Column Index - ${block.ColumnIndex}`)
                   console.log(`   Row - ${block.RowIndex}`)
                   console.log(`   Column Span - ${block.ColumnSpan}`)
                   console.log(`   Row Span - ${block.RowSpan}`)
               }
               if ("Relationships" in block && block.Relationships !== undefined){
                   console.log(block.Relationships)
                   console.log("Geometry:")
                   console.log(`   Bounding Box - ${JSON.stringify(block.Geometry.BoundingBox)}`)
                   console.log(`   Polygon - ${JSON.stringify(block.Geometry.Polygon)}`)
               }
               console.log("-----")
           });
         } catch (err) {
           console.log("Error", err);
         }
   }
   
   const analyze_document_text = async () => {
       try {
           const analyzeDoc = new AnalyzeDocumentCommand(params);
           const response = await textractClient.send(analyzeDoc);
           //console.log(response)
           displayBlockInfo(response)
           return response; // For unit tests.
         } catch (err) {
           console.log("Error", err);
         }
   }
   
   analyze_document_text()

   .NET

   다음 예제에서는 감지된 텍스트와 해당 관계를 목록에 표시합니다.

   bucket 및의 값을 2단계에서 사용한 Amazon S3 버킷 및 문서 이미지의 이름으로 document 바꿉니다.

   
   using System;
   using System.Linq;
   using System.Reflection.Emit;
   using Amazon.Runtime;
   using Amazon.Textract;
   using Amazon.Textract.Model;
   
   namespace TextractAnalyzeExpense
   {
       class Program 
       {
           static async Task Main()
           {
               String document = "document";
               String bucket = "bucket";
   
               AmazonTextractClient textractClient = new AmazonTextractClient();
   
               AnalyzeExpenseRequest analyzeExpenseRequest = new AnalyzeExpenseRequest()
               {
                   Document = new Document()
                   {
                       S3Object = new S3Object()
                       {
                           Name = document,
                           Bucket = bucket
                       }
                   }
               };
   
               try
               {
                   var ExpenseAnalysis = await textractClient.AnalyzeExpenseAsync(analyzeExpenseRequest);
                   Console.WriteLine("Line Items:");
                   foreach (ExpenseDocument expenseDocument in ExpenseAnalysis.ExpenseDocuments)
                   {
                       Console.WriteLine("Line Items:");
                      foreach(LineItemGroup linegroup in expenseDocument.LineItemGroups)
                      {
                       PrintLineItems.LineItemPrinter.LineItemParse(linegroup);
                      }
                      
                      Console.WriteLine("Summary:\n");
                      foreach(ExpenseField summary in expenseDocument.SummaryFields)
                      {
                       if (summary.LabelDetection is not null) 
                       {
                           Console.WriteLine(summary.LabelDetection.Text);
                       }
                      if (summary.ValueDetection is not null) 
                       {
                           Console.WriteLine(summary.ValueDetection.Text);
                       }
   
                      }
                   }
   
                   
               }
               catch (Exception e)
               {
                   Console.WriteLine(e.Message);
               }
           }
       
       }
   }
   
   namespace PrintLineItems 
   {
       class LineItemPrinter
       {
           public static void LineItemParse(LineItemGroup lineitemgroup) 
           {
               foreach(LineItemFields lineitem in lineitemgroup.LineItems) {
                   foreach(ExpenseField expense in lineitem.LineItemExpenseFields){
                      if (expense.LabelDetection is not null) 
                      {
                       Console.WriteLine(expense.LabelDetection.Text);
                      }
                      if (expense.ValueDetection is not null) 
                      {
                       Console.WriteLine(expense.ValueDetection.Text);
                      }
   
                   }    
   
               }
   
           }
       }
   }
                           

4. 예제를 실행합니다. Python 및 Java 예제에서는 다음과 같은 색상이 지정된 경계 상자가 있는 문서 이미지를 표시합니다.

   • 빨간색 - KEY 객체 차단

   • 녹색 - 값 블록 객체

   • 파란색 - 테이블 객체 차단

   • 노란색 - CELL Block 객체

   선택한 선택 요소는 파란색으로 채워집니다.

   이 AWS CLI 예제에서는 AnalyzeDocument 작업에 대한 JSON 출력만 표시합니다.