java将html富文本带图片转为.docx、 .pdf、 .image的工具类

可以使用Apache POI和iText库来实现将带有图片的富文本转换为.docx和.pdf文件。

1. 将富文本转换为.docx文件

使用Apache POI库可以将富文本转换为.docx文件，具体代码如下：

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;

public class HtmlToDocxConverter {
    public static void convert(String htmlFilePath, String docxFilePath) throws IOException {
        XWPFDocument doc = new XWPFDocument();
        XWPFParagraph paragraph = doc.createParagraph();
        XWPFRun run = paragraph.createRun();
        InputStream in = new FileInputStream(htmlFilePath);
        run.setText(org.apache.commons.io.IOUtils.toString(in, "UTF-8"));
        OutputStream out = new FileOutputStream(docxFilePath);
        doc.write(out);
        out.close();
        doc.close();
    }
}

2. 将富文本转换为.pdf文件

使用iText库可以将富文本转换为.pdf文件，具体代码如下：

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import com.itextpdf.kernel.pdf.PdfDocument;
import com.itextpdf.kernel.pdf.PdfWriter;
import com.itextpdf.layout.Document;
import com.itextpdf.layout.element.Paragraph;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document.OutputSettings;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class HtmlToPdfConverter {
    public static void convert(String htmlFilePath, String pdfFilePath) throws IOException {
        PdfWriter writer = new PdfWriter(new FileOutputStream(pdfFilePath));
        PdfDocument pdf = new PdfDocument(writer);
        Document document = new Document(pdf);
        org.jsoup.nodes.Document htmlDoc = Jsoup.parse(new File(htmlFilePath), "UTF-8");
        OutputSettings settings = new OutputSettings();
        settings.prettyPrint(false);
        for (Element element : htmlDoc.body().children()) {
            if ("img".equals(element.tagName())) {
                byte[] imageBytes = getImageBytes(element.attr("src"));
                if (imageBytes != null) {
                    com.itextpdf.layout.element.Image image = new com.itextpdf.layout.element.Image(
                            com.itextpdf.io.image.ImageDataFactory.create(imageBytes));
                    document.add(image);
                }
            } else {
                Elements pElements = element.getElementsByTag("p");
                for (Element pElement : pElements) {
                    Paragraph p = new Paragraph(pElement.html());
                    document.add(p);
                }
            }
        }
        document.close();
    }

    private static byte[] getImageBytes(String imageUrl) {
        // 将图片url转换为字节数组
    }
}

3. 将富文本转换为图片

将富文本转换为图片可以使用第三方工具，如wkhtmltoimage或phantomjs。这里以wkhtmltoimage为例，具体代码如下：

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

public class HtmlToImageConverter {
    public static void convert(String htmlFilePath, String imageFilePath) throws IOException {
        List<String> cmd = new ArrayList<>();
        cmd.add("wkhtmltoimage");
        cmd.add("--quality");
        cmd.add("100");
        cmd.add(htmlFilePath);
        cmd.add(imageFilePath);
        ProcessBuilder pb = new ProcessBuilder(cmd);
        pb.redirectErrorStream(true);
        Process process = pb.start();
        try {
            process.waitFor();
        } catch (InterruptedException e) {
            e.printStackTrace();
        }
    }
}