JavaでGroupDocs.Parserを使用してPDFからテーブルを抽出する方法

<repositories>
   <repository>
      <id>repository.groupdocs.com</id>
      <name>GroupDocs Repository</name>
      <url>https://releases.groupdocs.com/parser/java/</url>
   </repository>
</repositories>

<dependencies>
   <dependency>
      <groupId>com.groupdocs</groupId>
      <artifactId>groupdocs-parser</artifactId>
      <version>25.5</version>
   </dependency>
</dependencies>

import com.groupdocs.parser.Parser;

public class DocumentParser {
    public static void main(String[] args) {
        final String filePath = "YOUR_DOCUMENT_DIRECTORY/SampleInvoicePagesPdf.pdf";
        try (Parser parser = new Parser(filePath)) {
            // Ready to perform operations on the document
        } catch (Exception e) {
            System.err.println("Error creating Parser instance: " + e.getMessage());
        }
    }
}

import com.groupdocs.parser.Parser;

public class CreateParserInstance {
    public static void main(String[] args) {
        final String filePath = "YOUR_DOCUMENT_DIRECTORY/SampleInvoicePagesPdf.pdf";
        try (Parser parser = new Parser(filePath)) {
            // Document is ready for operations
        } catch (Exception e) {
            System.err.println("Error creating Parser instance: " + e.getMessage());
        }
    }
}

import com.groupdocs.parser.Parser;

public class CheckTableSupport {
    public static void main(String[] args) {
        final String filePath = "YOUR_DOCUMENT_DIRECTORY/SampleInvoicePagesPdf.pdf";
        try (Parser parser = new Parser(filePath)) {
            boolean isTablesSupported = parser.getFeatures().isTables();
            
            if (!isTablesSupported) {
                System.out.println("Document doesn't support tables extraction.");
            }
        } catch (Exception e) {
            System.err.println("Error checking table extraction capability: " + e.getMessage());
        }
    }
}

import com.groupdocs.parser.templates.TemplateTableLayout;
import java.util.Arrays;

public class ConfigureTableLayout {
    public static void main(String[] args) {
        final double[] columnWidths = {50.0, 95.0, 275.0, 415.0, 485.0, 545.0};
        final double[] rowHeights = {325.0, 340.0, 365.0, 395.0};

        TemplateTableLayout layout = new TemplateTableLayout(
                Arrays.asList(columnWidths), 
                Arrays.asList(rowHeights));
    }
}

import com.groupdocs.parser.options.PageTableAreaOptions;
import com.groupdocs.parser.templates.TemplateTableLayout;

public class SetExtractionOptions {
    public static void main(String[] args) {
        TemplateTableLayout layout = new TemplateTableLayout(
                Arrays.asList(new Double[]{50.0, 95.0, 275.0, 415.0, 485.0, 545.0}), 
                Arrays.asList(new Double[]{325.0, 340.0, 365.0, 395.0}));

        PageTableAreaOptions options = new PageTableAreaOptions(layout);
    }
}

import com.groupdocs.parser.Parser;
import com.groupdocs.parser.options.PageTableAreaOptions;
import com.groupdocs.parser.data.PageTableArea;

public class ExtractTables {
    public static void main(String[] args) {
        final String filePath = "YOUR_DOCUMENT_DIRECTORY/SampleInvoicePagesPdf.pdf";
        PageTableAreaOptions options = new PageTableAreaOptions(/* layout from previous feature */);

        try (Parser parser = new Parser(filePath)) {
            Iterable<PageTableArea> tables = parser.getTables(options);
            
            for (PageTableArea table : tables) {
                // Process each table as needed
            }
        } catch (Exception e) {
            System.err.println("Error extracting tables: " + e.getMessage());
        }
    }
}

import com.groupdocs.parser.data.PageTableArea;
import com.groupdocs.parser.data.PageTableAreaCell;

public class IterateTables {
    public static void main(String[] args) {
        PageTableArea table = /* reference to a specific PageTableArea object */;

        for (int row = 0; row < table.getRowCount(); row++) {
            for (int column = 0; column < table.getColumnCount(); column++) {
                PageTableAreaCell cell = table.getCell(row, column);
                if (cell != null) {
                    // Process the cell text as needed
                }
            }
        }
    }
}