使用PDFbox将HTML 转为PDF

你可以使用 Apache PDFBox 库将 HTML 转换为 PDF。下面是一个使用 PDFBox 的示例代码：

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.PDPageTree;
import org.apache.pdfbox.pdmodel.common.PDRectangle;
import org.apache.pdfbox.pdmodel.common.PDStream;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.apache.pdfbox.tools.imageio.ImageIOUtil;

public class HTMLtoPDFConverter {
    public static void main(String[] args) {
        String htmlFilePath = "path/to/input.html";
        String pdfFilePath = "path/to/output.pdf";

        // Load HTML file
        File htmlFile = new File(htmlFilePath);

        try {
            // Create a new PDF document
            PDDocument document = new PDDocument();
            PDPage page = new PDPage(PDRectangle.A4);
            document.addPage(page);

            // Create a PDPageContentStream object
            PDPageContentStream contentStream = new PDPageContentStream(document, page);

            // Load the HTML file into a PDStream
            FileInputStream inputStream = new FileInputStream(htmlFile);
            PDStream pdStream = new PDStream(document, inputStream);

            // Set the media box of the page
            PDRectangle mediaBox = page.getMediaBox();
            contentStream.addRect(mediaBox.getLowerLeftX(), mediaBox.getLowerLeftY(),
                    mediaBox.getWidth(), mediaBox.getHeight());
            contentStream.clip();

            // Create a PDF renderer
            PDFRenderer renderer = new PDFRenderer(document);
            renderer.setDocument(document);

            // Render the HTML file to PDF
            renderer.renderPageToStream(renderer.getCurrentPageNo(), pdStream);

            // Close the content stream and the document
            contentStream.close();
            document.save(new FileOutputStream(pdfFilePath));
            document.close();

            System.out.println("HTML converted to PDF successfully.");
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

请确保将 `path/to/input.html` 替换为要转换的 HTML 文件的路径，将 `path/to/output.pdf` 替换为保存生成的 PDF 文件的路径。运行此代码将生成一个包含 HTML 内容的 PDF 文件。