java html转excel，保留原有框架

如果您需要将 HTML 文件中的表格以及表格外的其他内容都转换为 Excel 文件，并保留原有的框架，可以使用 Apache POI 和 Apache Pdfbox 库来实现。以下是一个简单的示例代码：

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.ss.usermodel.CellStyle;
import org.apache.poi.ss.usermodel.Font;
import org.apache.poi.ss.usermodel.IndexedColors;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.Workbook;
import org.apache.poi.ss.usermodel.WorkbookFactory;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class HtmlToExcelConverter {

    public static void main(String[] args) throws Exception {
        // 读取 HTML 文件
        String htmlFilePath = "example.html";
        Document document = Jsoup.parse(new FileInputStream(htmlFilePath), "UTF-8", "");

        // 创建 Excel 工作簿
        Workbook workbook = new HSSFWorkbook();

        // 创建单元格样式
        CellStyle style = workbook.createCellStyle();
        Font font = workbook.createFont();
        font.setColor(IndexedColors.BLACK.getIndex());
        style.setFont(font);

        // 创建 Excel 工作表
        Sheet sheet = workbook.createSheet("Sheet1");

        // 读取 HTML 内容并写入 Excel 工作表
        Elements elements = document.body().children();
        int rowIndex = 0;
        for (Element element : elements) {
            if ("table".equals(element.tagName())) {
                Elements rows = element.getElementsByTag("tr");
                for (int i = 0; i < rows.size(); i++) {
                    Row row = sheet.createRow(rowIndex++);
                    Elements cells = rows.get(i).getElementsByTag("td");
                    for (int j = 0; j < cells.size(); j++) {
                        String cellText = cells.get(j).text();
                        row.createCell(j).setCellValue(cellText);
                        row.getCell(j).setCellStyle(style);
                    }
                }
            } else {
                String tempPdfFilePath = "temp.pdf";
                HtmlToPdfConverter.convertHtmlToPdf(element.outerHtml(), tempPdfFilePath);
                PdfToImageConverter.convertPdfToImage(tempPdfFilePath);
                insertImageIntoExcel(sheet, rowIndex++, tempPdfFilePath.replace(".pdf", ".png"));
                new File(tempPdfFilePath).delete();
                new File(tempPdfFilePath.replace(".pdf", ".png")).delete();
            }
        }

        // 写入 Excel 文件
        String excelFilePath = "example.xls";
        FileOutputStream outputStream = new FileOutputStream(excelFilePath);
        workbook.write(outputStream);
        workbook.close();
        outputStream.close();

        System.out.println("Excel 文件已生成！");
    }

    private static void insertImageIntoExcel(Sheet sheet, int rowIndex, String imagePath) throws Exception {
        FileInputStream inputStream = new FileInputStream(imagePath);
        byte[] imageBytes = new byte[inputStream.available()];
        inputStream.read(imageBytes);
        int pictureId = sheet.getWorkbook().addPicture(imageBytes, Workbook.PICTURE_TYPE_PNG);
        inputStream.close();
        CreationHelper helper = sheet.getWorkbook().getCreationHelper();
        Drawing drawing = sheet.createDrawingPatriarch();
        ClientAnchor anchor = helper.createClientAnchor();
        anchor.setCol1(0);
        anchor.setRow1(rowIndex);
        anchor.setCol2(1);
        anchor.setRow2(rowIndex + 1);
        drawing.createPicture(anchor, pictureId);
        sheet.getRow(rowIndex).setHeightInPoints(200);
    }

}

class HtmlToPdfConverter {

    public static void convertHtmlToPdf(String html, String pdfFilePath) throws Exception {
        PDDocument document = new PDDocument();
        PDPage page = new PDPage();
        document.addPage(page);
        PDPageContentStream contentStream = new PDPageContentStream(document, page);
        InputStream inputStream = new ByteArrayInputStream(html.getBytes("UTF-8"));
        XMLWorkerHelper.getInstance().parseXHtml(contentStream, document, inputStream);
        contentStream.close();
        document.save(pdfFilePath);
        document.close();
    }

}

class PdfToImageConverter {

    public static void convertPdfToImage(String pdfFilePath) throws Exception {
        PDDocument document = PDDocument.load(new File(pdfFilePath));
        PDFRenderer pdfRenderer = new PDFRenderer(document);
        BufferedImage image = pdfRenderer.renderImage(0);
        ImageIO.write(image, "png", new File(pdfFilePath.replace(".pdf", ".png")));
        document.close();
    }

}

上述代码中，我们先读取 HTML 文件中的内容，并遍历每个元素。如果元素是表格，则将表格内容写入 Excel 工作表；如果元素不是表格，则将元素转换为 PDF 文件，再将 PDF 文件转换为 PNG 图像，并将图像插入到 Excel 工作表中。需要注意的是，插入 PNG 图像时，我们需要根据行高进行调整。另外，我们还需要使用 Apache Pdfbox 和 iText 库来实现将 HTML 转换为 PDF 的功能。

需要将上述代码中的 `example.html` 替换为您要转换的 HTML 文件的路径，将 `example.xls` 替换为您要生成的 Excel 文件的路径。另外，您还需要在项目中添加以下依赖项：

<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>3.17</version>
</dependency>
<dependency>
    <groupId>org.apache.pdfbox</groupId>
    <artifactId>pdfbox</artifactId>
    <version>2.0.24</version>
</dependency>
<dependency>
    <groupId>org.apache.pdfbox</groupId>
    <artifactId>pdfbox-tools</artifactId>
    <version>2.0.24</version>
</dependency>
<dependency>
    <groupId>com.itextpdf</groupId>
    <artifactId>itextpdf</artifactId>
    <version>5.5.13.2</version>
</dependency>
<dependency>
    <groupId>com.itextpdf.tool</groupId>
    <artifactId>xmlworker</artifactId>
    <version>5.5.13</version>
</dependency>