選取您的 Cookie 偏好設定

我們使用提供自身網站和服務所需的基本 Cookie 和類似工具。我們使用效能 Cookie 收集匿名統計資料，以便了解客戶如何使用我們的網站並進行改進。基本 Cookie 無法停用，但可以按一下「自訂」或「拒絕」以拒絕效能 Cookie。

如果您同意，AWS 與經核准的第三方也會使用 Cookie 提供實用的網站功能、記住您的偏好設定，並顯示相關內容，包括相關廣告。若要接受或拒絕所有非必要 Cookie，請按一下「接受」或「拒絕」。若要進行更詳細的選擇，請按一下「自訂」。

偏好設定
聯絡我們
意見回饋
AWS Documentation
建立 AWS 帳戶

使用 Amazon Textract 分析文檔文本

PDF
RSS
焦點模式
使用 Amazon Textract 分析文檔文本 - Amazon Textract

本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。

本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。

若要分析文檔中的文本，請使用AnalyzeDocument操作，並將文檔文件作為輸入傳遞。AnalyzeDocument會傳回含有分析文字的 JSON 結構。如需詳細資訊，請參閱 分析文檔。

您提供的輸入文檔可以是影像位元組陣列 (base64 編碼影像位元組)，或者 Amazon S3 物件。在此步驟中，您會將影像檔案上傳至您的 S3 儲存貯體，並指定檔案名稱。

分析文檔中的文本 (API)

  1. 如果您尚未：

    1. 使用創建或更新 IAM 用户AmazonTextractFullAccess和AmazonS3ReadOnlyAccess許可。如需詳細資訊，請參閱 步驟 1：設定 AWS 帳户並建立 IAM 使用者。

    2. 安裝並設定 AWS CLI 和 AWS SDK。如需詳細資訊，請參閱 步驟 2：設定AWS CLI和AWS開發套件。

  2. 將含有文檔的影像上傳至您的 S3 儲存貯體。

    如需說明，請參閱「」將物件上傳至 Amazon S3中的Amazon Simple Storage Service 用户指南。

  3. 使用下列範例來呼叫 AnalyzeDocument 操作。

    Java

    以下範例程式碼會顯示檢測到的項目周圍的文件和框。

    在函數中main中，替換bucket和document以您在步驟 2 中所使用的 Amazon S3 儲存貯體名稱與文件影像名稱來取代和。

    
//Loads document from S3 bucket. Displays the document and polygon around detected lines of text.
package com.amazonaws.samples;

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.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 = "";

        AmazonS3 s3client = AmazonS3ClientBuilder.standard()
                .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()
                .withEndpointConfiguration(endpoint).build();

                
        AnalyzeDocumentRequest request = new AnalyzeDocumentRequest()
                .withFeatureTypes("TABLES","FORMS")
                 .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); 

    }
}
    AWS CLI

    此 AWS CLI 命令顯示 detect-document-text CLI 操作的 JSON 輸出。

    替換Bucket和Name以您在步驟 2 中所使用的 Amazon S3 儲存貯體名稱與文件名稱來取代和。

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

    以下範例程式碼會顯示檢測到的項目周圍的文件和框。

    在函數中main中，替換bucket和document以您在步驟 2 中所使用的 Amazon S3 儲存貯體名稱與文件名稱來取代和。

    
#Analyzes text in a document stored in an S3 bucket. Display polygon box around text and angled text 
import boto3
import io
from io import BytesIO
import sys

import math
from PIL import Image, ImageDraw, ImageFont

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(bucket, document):

    #Get the document from S3
    s3_connection = boto3.resource('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
    client = boto3.client('textract')
    
    image_binary = stream.getvalue()
    response = client.analyze_document(Document={'Bytes': image_binary},
        FeatureTypes=["TABLES", "FORMS"])

    ### Alternatively, process using S3 object ###
    #response = client.analyze_document(
    #    Document={'S3Object': {'Bucket': bucket, 'Name': document}},
    #    FeatureTypes=["TABLES", "FORMS"])

    ### To use 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"])

    
    #Get the text blocks
    blocks=response['Blocks']
    width, height =image.size  
    draw = ImageDraw.Draw(image)  
    print ('Detected Document Text')
   
    # Create image showing bounding box/polygon the detected lines/text
    for block in blocks:

        DisplayBlockInformation(block)
             
        draw=ImageDraw.Draw(image)
        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')    
   
            #uncomment to draw polygon for all Blocks
            #points=[]
            #for polygon in block['Geometry']['Polygon']:
            #    points.append((width * polygon['X'], height * polygon['Y']))
            #draw.polygon((points), outline='blue')
            
    # Display the image
    image.show()
    return len(blocks)


def main():

    bucket = ''
    document = ''
    block_count=process_text_analysis(bucket,document)
    print("Blocks detected: " + str(block_count))
    
if __name__ == "__main__":
    main()
    Node.js

    以下範例程式碼會顯示檢測到的項目周圍的文件和框。

    在下面的代碼中，替換bucket和photo以您在步驟 2 中所使用的 Amazon S3 儲存貯體名稱與文件名稱來取代和。替換region以及與帳户相關聯的地區。

    // Import required AWS SDK clients and commands for Node.js
import { AnalyzeDocumentCommand } from  "@aws-sdk/client-textract";
import  { TextractClient } from "@aws-sdk/client-textract";

// Set the AWS Region.
const REGION = "region"; //e.g. "us-east-1"
// Create SNS service object.
const textractClient = new TextractClient({ region: REGION });

const bucket = 'buckets'
const photo = 'photo'

// Set params
const params = {
    Document: {
      S3Object: {
        Bucket: bucket,
        Name: photo
      },
    },
    FeatureTypes: ['TABLES', 'FORMS'],
  }

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()
    anchoranchoranchoranchor

    以下範例程式碼會顯示檢測到的項目周圍的文件和框。

    在函數中main中，替換bucket和document以您在步驟 2 中所使用的 Amazon S3 儲存貯體名稱與文件影像名稱來取代和。

    
//Loads document from S3 bucket. Displays the document and polygon around detected lines of text.
package com.amazonaws.samples;

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.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 = "";

        AmazonS3 s3client = AmazonS3ClientBuilder.standard()
                .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()
                .withEndpointConfiguration(endpoint).build();

                
        AnalyzeDocumentRequest request = new AnalyzeDocumentRequest()
                .withFeatureTypes("TABLES","FORMS")
                 .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); 

    }
}

  4. 執行範例。Python 和 Java 示例顯示帶有以下彩色邊界框的文檔圖像：

    • 紅色 — 密鑰塊對象

    • 綠色 — 值塊對象

    • 藍色 — 表格塊對象

    • 黃色 — 單元格塊對象

    選取的選擇元素將用藍色填充。

    所以此AWS CLI示例僅顯示AnalyzeDocumentoperation.

隱私權網站條款Cookie 偏好設定
© 2025, Amazon Web Services, Inc.或其附屬公司。保留所有權利。