Java代码实现pdf文件中的表格以及内容转成excel文件输出

可以使用Apache PDFBox和Apache POI这两个Java库来实现将PDF文件中的表格以及内容转成Excel文件输出的功能。具体实现步骤如下：

1. 引入依赖

在项目的pom.xml文件中添加以下依赖：

<dependency>
    <groupId>org.apache.pdfbox</groupId>
    <artifactId>pdfbox</artifactId>
    <version>2.0.23</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>5.0.0</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>5.0.0</version>
</dependency>

2. 加载PDF文件

使用PDFBox库中的PDFTextStripper类将PDF文件中的文本内容提取出来，然后再使用PDFBox库中的PDFTableStripper类将PDF文件中的表格内容提取出来。具体代码如下：

PDDocument document = PDDocument.load(new File("test.pdf"));
PDFTextStripper textStripper = new PDFTextStripper();
String text = textStripper.getText(document);

PDFTableStripper tableStripper = new PDFTableStripper();
tableStripper.setSortByPosition(true);
tableStripper.setStartPage(0);
tableStripper.setEndPage(document.getNumberOfPages());
List<List<Rectangle>> rows = tableStripper.getRows(document.getPage(0));

3. 将表格内容转成二维数组

根据表格的行列信息，将表格内容转成二维数组。具体代码如下：

List<List<String>> table = new ArrayList<>();
for (List<Rectangle> row : rows) {
    List<String> rowData = new ArrayList<>();
    for (Rectangle cell : row) {
        int x = (int) cell.getX();
        int y = (int) cell.getY();
        int width = (int) cell.getWidth();
        int height = (int) cell.getHeight();
        String cellText = text.substring(text.indexOf("(" + x + "," + y + ")"), text.indexOf("(" + (x + width) + "," + (y + height) + ")"));
        rowData.add(cellText.trim());
    }
    table.add(rowData);
}

4. 将表格内容写入Excel文件

使用POI库中的Workbook和Sheet类创建Excel文件和工作表，然后将表格内容写入工作表中。具体代码如下：

Workbook workbook = new XSSFWorkbook();
Sheet sheet = workbook.createSheet();

for (int i = 0; i < table.size(); i++) {
    Row row = sheet.createRow(i);
    List<String> rowData = table.get(i);
    for (int j = 0; j < rowData.size(); j++) {
        Cell cell = row.createCell(j);
        cell.setCellValue(rowData.get(j));
    }
}

FileOutputStream outputStream = new FileOutputStream("test.xlsx");
workbook.write(outputStream);
workbook.close();
outputStream.close();

完整代码如下：

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.util.Rectangle;
import org.apache.pdfbox.util.Splitter;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.common.PDRectangle;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.font.PDType1Font;
import org.apache.pdfbox.pdmodel.font.PDFont;
import org.apache.pdfbox.pdmodel.interactive.form.*;
import org.apache.poi.ss.usermodel.*;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;

import java.io.File;
import java.io.FileOutputStream;
import java.util.ArrayList;
import java.util.List;

public class PdfToExcel {
    public static void main(String[] args) throws Exception {
        PDDocument document = PDDocument.load(new File("test.pdf"));
        PDFTextStripper textStripper = new PDFTextStripper();
        String text = textStripper.getText(document);

        PDFTableStripper tableStripper = new PDFTableStripper();
        tableStripper.setSortByPosition(true);
        tableStripper.setStartPage(0);
        tableStripper.setEndPage(document.getNumberOfPages());
        List<List<Rectangle>> rows = tableStripper.getRows(document.getPage(0));

        List<List<String>> table = new ArrayList<>();
        for (List<Rectangle> row : rows) {
            List<String> rowData = new ArrayList<>();
            for (Rectangle cell : row) {
                int x = (int) cell.getX();
                int y = (int) cell.getY();
                int width = (int) cell.getWidth();
                int height = (int) cell.getHeight();
                String cellText = text.substring(text.indexOf("(" + x + "," + y + ")"), text.indexOf("(" + (x + width) + "," + (y + height) + ")"));
                rowData.add(cellText.trim());
            }
            table.add(rowData);
        }

        Workbook workbook = new XSSFWorkbook();
        Sheet sheet = workbook.createSheet();

        for (int i = 0; i < table.size(); i++) {
            Row row = sheet.createRow(i);
            List<String> rowData = table.get(i);
            for (int j = 0; j < rowData.size(); j++) {
                Cell cell = row.createCell(j);
                cell.setCellValue(rowData.get(j));
            }
        }

        FileOutputStream outputStream = new FileOutputStream("test.xlsx");
        workbook.write(outputStream);
        workbook.close();
        outputStream.close();
    }
}