Java+ POI導(dǎo)出富文本的內(nèi)容到word文檔

依賴

<!-- jsoup依賴  主要是解析圖片標(biāo)簽,然后縮放圖片大小-->
<dependency>
  <groupId>org.jsoup</groupId>
  <artifactId>jsoup</artifactId>
  <version>1.12.1</version>
</dependency>
<!-- poi依賴-->
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>4.1.0</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>4.1.0</version>
</dependency>

ExportController


import cn.dev33.satoken.annotation.SaIgnore;
import cn.hutool.core.util.IdUtil;
import jakarta.servlet.http.HttpServletRequest;
import jakarta.servlet.http.HttpServletResponse;
import org.apache.commons.lang3.StringUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestBody;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;

import java.awt.image.BufferedImage;
import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.util.ArrayList;
import java.util.List;

 
@RestController
public class ExportController {

    @SaIgnore
    @PostMapping(value = "/fwbToWord")
    public void export(@RequestBody Fwb fwb,
            HttpServletRequest request, HttpServletResponse response) throws Exception {
        try {
            String tmpContent = fwb.getContent();

            // 獲取img圖片標(biāo)簽
            // 1.Jsoup解析html
            Document document = Jsoup.parse(tmpContent);
            // 獲取所有img圖片標(biāo)簽
            Elements img = document.getElementsByTag("img");
            int index = 0;
            List<String> imgBase64List = new ArrayList<>();
            for (Element element : img) {
                imgBase64List.add(element.attr("src"));
                // 處理特殊符號
                String attrData = element.attr("src");
                // base64編碼后可能包含 + 特殊字符,所以需要轉(zhuǎn)義
                attrData = attrData.replaceAll("\\+", "\\\\+");
                tmpContent = tmpContent.replaceAll(attrData, "{{image_src" + index + "}}");
                index++;
            }
            // 縮放圖片大小,然后重新base64編碼后替換到富文本內(nèi)容里面導(dǎo)出word
            index = 0;
            String prefix = "data:image/png;base64,"; // base64編碼前綴
            for (String base64 : imgBase64List) {
                if (StringUtils.isNotBlank(base64)) {
                    // 縮小圖片
                    base64 = base64.replaceAll(prefix, "");
                    BufferedImage bufferedImage = ImageUtils.bytesToBufferedImage(ImageUtils.base64ToByte(base64));
                    if (bufferedImage == null) {
                        tmpContent = tmpContent.replaceAll("\\{\\{image_src" + index + "}}", "");
                    } else {
                        int height = bufferedImage.getHeight();
                        int width = bufferedImage.getWidth();
                        // 如果圖片寬度大于650,圖片縮放
                        //System.out.println("----"+width+"-----"+height);
                        if (width > 650) {
                            //高度等比縮放
                            height = (int) (height * 650.0 / width);
                            BufferedImage imgZoom = ImageUtils.resizeImage(bufferedImage, 700, height);
                            String imageToBase64 = ImageUtils.imageToBase64(ImageUtils.imageToBytes(imgZoom));
                            tmpContent = tmpContent.replaceAll("\\{\\{image_src" + index + "}}", prefix + imageToBase64);
                        } else {
                            tmpContent = tmpContent.replaceAll("\\{\\{image_src" + index + "}}", prefix + base64);
                        }
                    }
                } else {
                    tmpContent = tmpContent.replaceAll("\\{\\{image_src" + index + "}}", "");
                }
                index++;
            }
            String uuid = IdUtil.fastSimpleUUID();
            // 執(zhí)行導(dǎo)出操作
            WordUtil.exportHtmlToWord(request, response, tmpContent, uuid);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }


    /**
     * 倒入本地測試
     *
     * @throws Exception
     */
    @RequestMapping(value = "/export")
    public void export() throws Exception {
        try {
            StringBuilder sb = new StringBuilder("<h1>如何將富文本內(nèi)容導(dǎo)出到word文檔</h1><p style=\"color:red;font-size:20px;\">采用poi將富文本內(nèi)容導(dǎo)出到word文檔</p><div style=\"background-color:green;\">這是有背景顏色的div內(nèi)容</div>\n" +
                    "<img src=\"").append("");
            //提前轉(zhuǎn)換過base64編碼的圖片,由于編碼文本太長,我提前存儲到txt中,再通過io流讀取出來
            File file = new File("/Users/lei/base.txt");
            FileInputStream fileInputStream = new FileInputStream(file);
            BufferedInputStream bis = new BufferedInputStream(fileInputStream);
            byte[] bytes = new byte[1024];
            int len = -1;
            while ((len = bis.read(bytes)) != -1) {
                sb.append(new String(bytes, 0, len));
            }


            sb.append("\">這是base64編碼后的圖片");
            String tmpContent = sb.toString();

            // 獲取img圖片標(biāo)簽
            // 1.Jsoup解析html
            Document document = Jsoup.parse(tmpContent);
            // 獲取所有img圖片標(biāo)簽
            Elements imgs = document.getElementsByTag("img");
            int index = 0;
            List<String> imgBase64List = new ArrayList<>();
            for (Element element : imgs) {
                imgBase64List.add(element.attr("src"));
                // 處理特殊符號
                String attrData = element.attr("src");
                // base64編碼后可能包含 + 特殊字符,所以需要轉(zhuǎn)義
                attrData = attrData.replaceAll("\\+", "\\\\+");
                tmpContent = tmpContent.replaceAll(attrData, "{{image_src" + index + "}}");
                index++;
            }
            // 縮放圖片大小,然后重新base64編碼后替換到富文本內(nèi)容里面導(dǎo)出word
            index = 0;
            String prefix = "data:image/png;base64,"; // base64編碼前綴
            for (String base64 : imgBase64List) {
                if (StringUtils.isNotBlank(base64)) {
                    // 縮小圖片
                    base64 = base64.replaceAll(prefix, "");
                    BufferedImage bufferedImage = ImageUtils.bytesToBufferedImage(ImageUtils.base64ToByte(base64));
                    if (bufferedImage == null) {
                        tmpContent = tmpContent.replaceAll("\\{\\{image_src" + index + "}}", "");
                    } else {
                        int height = bufferedImage.getHeight();
                        int width = bufferedImage.getWidth();
                        // 如果圖片寬度大于650,圖片縮放
                        System.out.println("----" + width + "-----" + height);
                        if (width > 650) {
                            //高度等比縮放
                            height = (int) (height * 650.0 / width);
                            BufferedImage imgZoom = ImageUtils.resizeImage(bufferedImage, 650, height);
                            String imageToBase64 = ImageUtils.imageToBase64(ImageUtils.imageToBytes(imgZoom));
                            tmpContent = tmpContent.replaceAll("\\{\\{image_src" + index + "}}", prefix + imageToBase64);
                        } else {
                            tmpContent = tmpContent.replaceAll("\\{\\{image_src" + index + "}}", prefix + base64);
                        }
                    }
                } else {
                    tmpContent = tmpContent.replaceAll("\\{\\{image_src" + index + "}}", "");
                }
                index++;
            }
            String uuid = IdUtil.fastSimpleUUID();
            // 執(zhí)行導(dǎo)出操作
            WordUtil.exportHtmlToWord("/data", tmpContent, uuid+".docx");
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

}

WordUtil

import jakarta.servlet.ServletOutputStream;
import jakarta.servlet.http.HttpServletRequest;
import jakarta.servlet.http.HttpServletResponse;
import org.apache.poi.poifs.filesystem.DirectoryEntry;
import org.apache.poi.poifs.filesystem.DocumentEntry;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;

import java.io.ByteArrayInputStream;
import java.io.File;
import java.io.FileOutputStream;

public class WordUtil {

    /**
     * 導(dǎo)出富文本內(nèi)容到word
     * @param request
     * @param response
     * @param content 輸出內(nèi)容
     * @param fileName 導(dǎo)出文件名稱
     * @throws Exception
     */
    public static void exportHtmlToWord(HttpServletRequest request, HttpServletResponse response, String content, String fileName) throws Exception {
        // 拼接html格式內(nèi)容
        StringBuffer sbf = new StringBuffer();
        // 這里拼接一下html標(biāo)簽,便于word文檔能夠識別
        sbf.append("<html " +
                "xmlns:v=\"urn:schemas-microsoft-com:vml\" xmlns:o=\"urn:schemas-microsoft-com:office:office\" xmlns:w=\"urn:schemas-microsoft-com:office:word\" xmlns:m=\"http://schemas.microsoft.com/office/2004/12/omml\" xmlns=\"http://www.w3.org/TR/REC-html40\"" + //將版式從web版式改成頁面試圖
                ">");
        sbf.append("<head>" +
                "<!--[if gte mso 9]><xml><w:WordDocument><w:View>Print</w:View><w:TrackMoves>false</w:TrackMoves><w:TrackFormatting/><w:ValidateAgainstSchemas/><w:SaveIfXMLInvalid>false</w:SaveIfXMLInvalid><w:IgnoreMixedContent>false</w:IgnoreMixedContent><w:AlwaysShowPlaceholderText>false</w:AlwaysShowPlaceholderText><w:DoNotPromoteQF/><w:LidThemeOther>EN-US</w:LidThemeOther><w:LidThemeAsian>ZH-CN</w:LidThemeAsian><w:LidThemeComplexScript>X-NONE</w:LidThemeComplexScript><w:Compatibility><w:BreakWrappedTables/><w:SnapToGridInCell/><w:WrapTextWithPunct/><w:UseAsianBreakRules/><w:DontGrowAutofit/><w:SplitPgBreakAndParaMark/><w:DontVertAlignCellWithSp/><w:DontBreakConstrainedForcedTables/><w:DontVertAlignInTxbx/><w:Word11KerningPairs/><w:CachedColBalance/><w:UseFELayout/></w:Compatibility><w:BrowserLevel>MicrosoftInternetExplorer4</w:BrowserLevel><m:mathPr><m:mathFont m:val=\"Cambria Math\"/><m:brkBin m:val=\"before\"/><m:brkBinSub m:val=\"--\"/><m:smallFrac m:val=\"off\"/><m:dispDef/><m:lMargin m:val=\"0\"/> <m:rMargin m:val=\"0\"/><m:defJc m:val=\"centerGroup\"/><m:wrapIndent m:val=\"1440\"/><m:intLim m:val=\"subSup\"/><m:naryLim m:val=\"undOvr\"/></m:mathPr></w:WordDocument></xml><![endif]-->" +
                "</head>");
        sbf.append("<body>");
        // 富文本內(nèi)容
        sbf.append(content);
        sbf.append("</body></html>");

        // 必須要設(shè)置編碼,避免中文就會亂碼
        byte[] b = sbf.toString().getBytes("GBK");
        // 將字節(jié)數(shù)組包裝到流中
        ByteArrayInputStream bais = new ByteArrayInputStream(b);
        POIFSFileSystem poifs = new POIFSFileSystem();
        DirectoryEntry directory = poifs.getRoot();
        // 這代碼不能省略,否則導(dǎo)出亂碼。
        DocumentEntry documentEntry = directory.createDocument("WordDocument", bais);
        //輸出文件
        request.setCharacterEncoding("utf-8");
        // 導(dǎo)出word格式
        response.setContentType("application/msword");
        response.addHeader("Content-Disposition", "attachment;filename=" +
                new String(fileName.getBytes("GB2312"),"iso8859-1") + ".doc");
        ServletOutputStream ostream = response.getOutputStream();
        poifs.writeFilesystem(ostream);
        bais.close();
        ostream.close();
    }

    /**
     * 富文本內(nèi)容到word(本地)
     * @param content 輸出內(nèi)容
     * @param fileName 導(dǎo)出文件名稱
     * @throws Exception
     */
    public static void exportHtmlToWord(String filepath, String content, String fileName) throws Exception {
        // 拼接html格式內(nèi)容
        StringBuffer sbf = new StringBuffer();
        // 這里拼接一下html標(biāo)簽,便于word文檔能夠識別
        sbf.append("<html " +
                "xmlns:v=\"urn:schemas-microsoft-com:vml\" xmlns:o=\"urn:schemas-microsoft-com:office:office\" xmlns:w=\"urn:schemas-microsoft-com:office:word\" xmlns:m=\"http://schemas.microsoft.com/office/2004/12/omml\" xmlns=\"http://www.w3.org/TR/REC-html40\"" + //將版式從web版式改成頁面試圖
                ">");
        sbf.append("<head>" +
                "<!--[if gte mso 9]><xml><w:WordDocument><w:View>Print</w:View><w:TrackMoves>false</w:TrackMoves><w:TrackFormatting/><w:ValidateAgainstSchemas/><w:SaveIfXMLInvalid>false</w:SaveIfXMLInvalid><w:IgnoreMixedContent>false</w:IgnoreMixedContent><w:AlwaysShowPlaceholderText>false</w:AlwaysShowPlaceholderText><w:DoNotPromoteQF/><w:LidThemeOther>EN-US</w:LidThemeOther><w:LidThemeAsian>ZH-CN</w:LidThemeAsian><w:LidThemeComplexScript>X-NONE</w:LidThemeComplexScript><w:Compatibility><w:BreakWrappedTables/><w:SnapToGridInCell/><w:WrapTextWithPunct/><w:UseAsianBreakRules/><w:DontGrowAutofit/><w:SplitPgBreakAndParaMark/><w:DontVertAlignCellWithSp/><w:DontBreakConstrainedForcedTables/><w:DontVertAlignInTxbx/><w:Word11KerningPairs/><w:CachedColBalance/><w:UseFELayout/></w:Compatibility><w:BrowserLevel>MicrosoftInternetExplorer4</w:BrowserLevel><m:mathPr><m:mathFont m:val=\"Cambria Math\"/><m:brkBin m:val=\"before\"/><m:brkBinSub m:val=\"--\"/><m:smallFrac m:val=\"off\"/><m:dispDef/><m:lMargin m:val=\"0\"/> <m:rMargin m:val=\"0\"/><m:defJc m:val=\"centerGroup\"/><m:wrapIndent m:val=\"1440\"/><m:intLim m:val=\"subSup\"/><m:naryLim m:val=\"undOvr\"/></m:mathPr></w:WordDocument></xml><![endif]-->" +
                "</head>");
        sbf.append("<body>");
        // 富文本內(nèi)容
        sbf.append(content);
        sbf.append("</body></html>");

        // 必須要設(shè)置編碼,避免中文就會亂碼
        byte[] b = sbf.toString().getBytes("GBK");
        // 將字節(jié)數(shù)組包裝到流中
        ByteArrayInputStream bais = new ByteArrayInputStream(b);
        POIFSFileSystem poifs = new POIFSFileSystem();
        DirectoryEntry directory = poifs.getRoot();
        // 這代碼不能省略,否則導(dǎo)出亂碼。
        DocumentEntry documentEntry = directory.createDocument("WordDocument", bais);

        FileOutputStream out = new FileOutputStream(new File(filepath+fileName));
        poifs.writeFilesystem(out);
        bais.close();
        out.close();
    }
}

ImageUtils

import cn.hutool.core.codec.Base64Decoder;
import cn.hutool.core.codec.Base64Encoder;

import javax.imageio.ImageIO;
import java.awt.*;
import java.awt.image.BufferedImage;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;

public class ImageUtils {
    /**
     * 通過BufferedImage圖片流調(diào)整圖片大小
     */
    public static BufferedImage resizeImage(BufferedImage originalImage, int targetWidth, int targetHeight) throws IOException {
        Image resultingImage = originalImage.getScaledInstance(targetWidth, targetHeight, Image.SCALE_AREA_AVERAGING);
        BufferedImage outputImage = new BufferedImage(targetWidth, targetHeight, BufferedImage.TYPE_INT_RGB);
        outputImage.getGraphics().drawImage(resultingImage, 0, 0, null);
        return outputImage;
    }

    /**
     * 返回base64圖片
     * @param data
     * @return
     */
    public static String imageToBase64(byte[] data) {
        // 返回Base64編碼過的字節(jié)數(shù)組字符串
        return Base64Encoder.encode(data);
    }

    /**
     * base64轉(zhuǎn)換成byte數(shù)組
     * @param base64
     * @return
     * @throws IOException
     */
    public static byte[] base64ToByte(String base64) throws IOException {
        // 返回Base64編碼過的字節(jié)數(shù)組字符串
        return Base64Decoder.decode(base64);
    }

    /**
     * BufferedImage圖片流轉(zhuǎn)byte[]數(shù)組
     */
    public static byte[] imageToBytes(BufferedImage bImage) {
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        try {
            ImageIO.write(bImage, "png", out);
        } catch (IOException e) {
            e.printStackTrace();
        }
        return out.toByteArray();
    }

    /**
     * byte[]數(shù)組轉(zhuǎn)BufferedImage圖片流
     */
    public static BufferedImage bytesToBufferedImage(byte[] ImageByte) {
        ByteArrayInputStream in = new ByteArrayInputStream(ImageByte);
        BufferedImage image = null;
        try {
            image = ImageIO.read(in);
        } catch (IOException e) {
            e.printStackTrace();
        }
        return image;
    }
}

?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請聯(lián)系作者
【社區(qū)內(nèi)容提示】社區(qū)部分內(nèi)容疑似由AI輔助生成,瀏覽時(shí)請結(jié)合常識與多方信息審慎甄別。
平臺聲明:文章內(nèi)容(如有圖片或視頻亦包括在內(nèi))由作者上傳并發(fā)布,文章內(nèi)容僅代表作者本人觀點(diǎn),簡書系信息發(fā)布平臺,僅提供信息存儲服務(wù)。

相關(guān)閱讀更多精彩內(nèi)容

友情鏈接更多精彩內(nèi)容