Java自动化实现提取PDF表格数据

<repositories>
    <repository>
        <id>com.e-iceblue</id>
        <name>e-iceblue</name>
        <url>https://repo.e-iceblue.cn/repository/maven-public/</url>
    </repository>
</repositories>
<dependencies>
    <dependency>
        <groupId>e-iceblue</groupId>
        <artifactId>spire.pdf</artifactId>
        <version>11.8.3</version>
    </dependency>
</dependencies>

import com.spire.pdf.PdfDocument;
import com.spire.pdf.utilities.PdfTableExtractor;
import com.spire.pdf.utilities.PdfTable;
import java.io.FileWriter;
import java.io.IOException;

public class PdfTableExtractionDemo {
    public static void main(String[] args) {
        PdfDocument doc = new PdfDocument();
        doc.loadFromFile("sample_invoice.pdf");

        PdfTableExtractor extractor = new PdfTableExtractor(doc);

        try (FileWriter csvWriter = new FileWriter("extracted_data.csv")) {
            for (int pageIndex = 0; pageIndex < doc.getPages().getCount(); pageIndex++) {
                PdfTable[] tables = extractor.extractTable(pageIndex);

                if (tables != null) {
                    for (PdfTable table : tables) {
                        for (int i = 0; i < table.getRowCount(); i++) {
                            StringBuilder rowData = new StringBuilder();
                            for (int j = 0; j < table.getColumnCount(); j++) {
                                String cellText = table.getText(i, j).trim();
                                rowData.append(""").append(cellText.replace(""", """")).append(""");
                                if (j < table.getColumnCount() - 1) rowData.append(",");
                            }
                            csvWriter.append(rowData.toString()).append("\n");
                        }
                        csvWriter.append("\n");
                    }
                }
            }
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            doc.close();
        }
    }
}