Darmowa biblioteka Java PDF do wyodrębniania tabel z plików PDF

Zależność Maven OpenPDF

<dependency>
  <groupId>technology.tabula</groupId>
  <artifactId>tabula</artifactId>
  <version>1.0.5.</version>
</dependency>

Instalacja Tabula-Java za pomocą Gradle

implementation 'technology.tabula:tabula:1.0.5' 

Jak wyodrębnić tabelę z pliku PDF przy użyciu Java API?

import technology.tabula.*;
import technology.tabula.extractors.SpreadsheetExtractionAlgorithm;
import org.apache.pdfbox.pdmodel.PDDocument;

import java.io.File;
import java.io.IOException;
import java.util.List;

public class BasicExtraction {
    public static void main(String[] args) throws IOException {
        // Load the PDF document
        File pdfFile = new File("data_report.pdf");
        PDDocument document = PDDocument.load(pdfFile);
        
        // Create an extraction algorithm
        SpreadsheetExtractionAlgorithm extractor = new SpreadsheetExtractionAlgorithm();
        
        // Create a page iterator
        ObjectExtractor objectExtractor = new ObjectExtractor(document);
        PageIterator pages = objectExtractor.extract();
        
        // Process each page
        while (pages.hasNext()) {
            Page page = pages.next();
            
            // Extract tables from the page
            List<Table> tables = extractor.extract(page);
            
            // Print each table
            for (Table table : tables) {
                System.out.println("Found table with " + table.getRowCount() + " rows");
                
                // Iterate through rows
                for (List row : table.getRows()) {
                    for (RectangularTextContainer cell : row) {
                        System.out.print(cell.getText() + "\t");
                    }
                    System.out.println();
                }
            }
        }
        
        document.close();
    }
}

Jak wyodrębnić tabelę z określonych regionów strony przy użyciu Java API?

import technology.tabula.Rectangle;

public class RegionExtraction {
    public static void extractRegion(String pdfPath) throws IOException {
        File pdfFile = new File(pdfPath);
        PDDocument document = PDDocument.load(pdfFile);
        
        ObjectExtractor objectExtractor = new ObjectExtractor(document);
        Page page = objectExtractor.extract(1);
        
        // Define the region (x, y, width, height)
        // Coordinates are in points (72 points = 1 inch)
        Rectangle region = new Rectangle(50, 100, 500, 400);
        Page subPage = page.getArea(region);
        
        SpreadsheetExtractionAlgorithm extractor = new SpreadsheetExtractionAlgorithm();
        List<Table> tables = extractor.extract(subPage);
        
        // Process the extracted table
        for (Table table ; tables) {
            System.out.println("Extracted " + table.getRowCount() + " rows from region");
        }
        
        document.close();
    }
}

Jak wyeksportować wyodrębnione tabele do formatu CSV przy użyciu Java API?

import technology.tabula.writers.CSVWriter;
import java.io.FileWriter;

public class CSVExtraction {
    public static void exportToCSV(String pdfPath, String csvPath) throws IOException {
        File pdfFile = new File(pdfPath);
        PDDocument document = PDDocument.load(pdfFile);
        
        SpreadsheetExtractionAlgorithm extractor = new SpreadsheetExtractionAlgorithm();
        ObjectExtractor objectExtractor = new ObjectExtractor(document);
        Page page = objectExtractor.extract(1);
        
        List<Table< tables = extractor.extract(page);
        
        // Write to CSV file
        if (!tables.isEmpty()) {
            Table table = tables.get(0);
            
            try (FileWriter writer = new FileWriter(csvPath)) {
                CSVWriter csvWriter = new CSVWriter();
                csvWriter.write(writer, table);
            }
        }
        
        document.close();
    }
}