Office文档在线预览

谁践踏了优雅 2022-04-24 01:02 738阅读 0赞

文章目录

    • 方案一：word转html
          1. 添加依赖
          1. 编写工具类Word2HtmlUtil.java
          1. 测试
    • 方案二：使用第三方服务
    • 方案三：使用微软 Office Online 服务
    • 永中文档预览服务详解
          1. 试一试在线预览！
          1. Web调用
          1. Java调用

方案一：word转html

使用Apache POI将word转为html，生成静态html，预览功能直接链接到html。

1. 添加依赖

  1. <!-- word转html -->
  2. <dependency>
  3.     <groupId>fr.opensagres.xdocreport</groupId>
  4.     <artifactId>fr.opensagres.xdocreport.document</artifactId>
  5.     <version>1.0.5</version>
  6. </dependency>
  7. <dependency>
  8.     <groupId>fr.opensagres.xdocreport</groupId>
  9.     <artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId>
  10.     <version>1.0.5</version>
  11. </dependency>
  12. <dependency>
  13.     <groupId>org.apache.poi</groupId>
  14.     <artifactId>poi</artifactId>
  15.     <version>3.12</version>
  16. </dependency>
  17. <dependency>
  18.     <groupId>org.apache.poi</groupId>
  19.     <artifactId>poi-scratchpad</artifactId>
  20.     <version>3.12</version>
  21. </dependency>

2. 编写工具类Word2HtmlUtil.java

  1. import java.io.BufferedWriter;
  2. import java.io.ByteArrayOutputStream;
  3. import java.io.File;
  4. import java.io.FileInputStream;
  5. import java.io.FileNotFoundException;
  6. import java.io.FileOutputStream;
  7. import java.io.IOException;
  8. import java.io.InputStream;
  9. import java.io.OutputStream;
  10. import java.io.OutputStreamWriter;
  11. import java.util.List;
  13. import javax.xml.parsers.DocumentBuilderFactory;
  14. import javax.xml.transform.OutputKeys;
  15. import javax.xml.transform.Transformer;
  16. import javax.xml.transform.TransformerFactory;
  17. import javax.xml.transform.dom.DOMSource;
  18. import javax.xml.transform.stream.StreamResult;
  20. import org.apache.poi.hwpf.HWPFDocument;
  21. import org.apache.poi.hwpf.converter.PicturesManager;
  22. import org.apache.poi.hwpf.converter.WordToHtmlConverter;
  23. import org.apache.poi.hwpf.usermodel.Picture;
  24. import org.apache.poi.hwpf.usermodel.PictureType;
  25. import org.apache.poi.xwpf.converter.core.BasicURIResolver;
  26. import org.apache.poi.xwpf.converter.core.FileImageExtractor;
  27. import org.apache.poi.xwpf.converter.core.FileURIResolver;
  28. import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
  29. import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
  30. import org.apache.poi.xwpf.usermodel.XWPFDocument;
  31. import org.w3c.dom.Document;
  33. public class Word2HtmlUtil { 
  34.     /** * 兼容doc和docx的word转html方法 * @param inFile 需要转换的word文件 * @param outPath 输出文件路径 * @param outName 输出文件名 */
  35.     public static void word2Html(String inFile, String outPath, String outName) throws Exception{ 
  36.         FileInputStream fis=new FileInputStream(inFile);
  37.         String suffix=inFile.substring(inFile.lastIndexOf("."));
  38.         if (suffix.equalsIgnoreCase(".docx")) { 
  39.             docx2Html(fis, outPath, outName);
  40.         } else { 
  41.             doc2Html(fis, outPath, outName);
  42.         }
  43.     }
  45.     public static void docx2Html(InputStream fis, String outPath ,String outName) throws Exception{ 
  46.         // 加载word文档生成 XWPFDocument对象
  47.         XWPFDocument document = new XWPFDocument(fis);
  48.         // 解析 XHTML配置
  49.         String imageFolder = outPath + "images"+File.separator+"docx"+File.separator;//图片存放路径
  50.         File imageFolderFile = new File(imageFolder);
  51.         XHTMLOptions options = XHTMLOptions.create().URIResolver(new FileURIResolver(imageFolderFile));
  52.         options.setExtractor(new FileImageExtractor(imageFolderFile));
  53.         options.setIgnoreStylesIfUnused(false);
  54.         options.setFragment(true);
  55.         options.URIResolver(new BasicURIResolver("images/docx/"));//html中img的src前缀
  56.         // 将 XWPFDocument转换成XHTML
  57.         OutputStream out = new FileOutputStream(new File(outPath + outName));
  58.         XHTMLConverter.getInstance().convert(document, out, options);
  59.     }
  61.     public static void doc2Html(InputStream fis, String outPath, String outName) throws Exception { 
  62.         HWPFDocument wordDocument = new HWPFDocument(fis);
  63.         WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
  64.         wordToHtmlConverter.setPicturesManager(new PicturesManager() { 
  65.             public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) { 
  66.                 return "images/doc/" + suggestedName;// html中img的src值
  67.             }
  68.         });
  69.         wordToHtmlConverter.processDocument(wordDocument);
  70.         //保存图片
  71.         List <Picture> pics = wordDocument.getPicturesTable().getAllPictures();
  72.         if (pics != null) { 
  73.             for (int i = 0; i < pics.size(); i++) { 
  74.                 Picture pic = (Picture) pics.get(i);
  75.                 try { 
  76.                     String imageFolder = outPath + "images" + File.separator + "doc" + File.separator;
  77.                     File dir=new File(imageFolder);//图片保存路径
  78.                     if(!dir.exists()) { 
  79.                         dir.mkdirs();
  80.                     }
  81.                     pic.writeImageContent(new FileOutputStream(imageFolder + pic.suggestFullFileName()));
  82.                 } catch (FileNotFoundException e) { 
  83.                     e.printStackTrace();
  84.                 }
  85.             }
  86.         }
  87.         Document htmlDocument = wordToHtmlConverter.getDocument();
  88.         ByteArrayOutputStream out = new ByteArrayOutputStream();
  89.         DOMSource domSource = new DOMSource(htmlDocument);
  90.         StreamResult streamResult = new StreamResult(out);
  91.         TransformerFactory tf = TransformerFactory.newInstance();
  92.         Transformer serializer = tf.newTransformer();
  93.         serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
  94.         serializer.setOutputProperty(OutputKeys.INDENT, "yes");
  95.         serializer.setOutputProperty(OutputKeys.METHOD, "html");
  96.         serializer.transform(domSource, streamResult);
  97.         out.close();
  98.         writeFile(new String(out.toByteArray()), outPath + outName);
  99.     }
  101.     public static void writeFile(String content, String path) { 
  102.         FileOutputStream fos = null;
  103.         BufferedWriter bw = null;
  104.         try { 
  105.             File file = new File(path);
  106.             fos = new FileOutputStream(file);
  107.             bw = new BufferedWriter(new OutputStreamWriter(fos, "utf-8"));
  108.             bw.write(content);
  109.         } catch (FileNotFoundException fnfe) { 
  110.             fnfe.printStackTrace();
  111.         } catch (IOException ioe) { 
  112.             ioe.printStackTrace();
  113.         } finally { 
  114.             try { 
  115.                 if (bw != null)
  116.                     bw.close();
  117.                 if (fos != null)
  118.                     fos.close();
  119.             } catch (IOException ie) { }
  120.         }
  121.     }
  122. }

3. 测试

  1. @Test
  2. public void testWord2Html() throws Exception{ 
  3.     Word2HtmlUtil.word2Html("D:/test/doctest.doc", "D:/test/output/","doctest.html");
  4. }

在这里插入图片描述

方案二：使用第三方服务

一般是收费的，一般也会提供功能受限的免费版本。

  • 永中 http://www.yozodcs.com/index.html （有免费版）
  • Office Web 365 http://www.officeweb365.com/ （有免费版）
  • I Doc View http://www.officeweb365.com/

方案三：使用微软 Office Online 服务

地址：https://products.office.com/zh-CN/office-online/view-office-documents-online

使用：在https://view.officeapps.live.com/op/view.aspx?src=后连接在线文档URL（必须为 http:// 或 https:// 形式，文档必须是 Word、Excel 或 PowerPoint 文档）。
测试：https://view.officeapps.live.com/op/view.aspx?src=http%3A%2F%2Fwww.snpdp.com%2Ffile-download-1064.html

163邮箱附件预览（高清版）就是使用office apps实现的：
在这里插入图片描述

永中文档预览服务详解

163邮箱附件预览（极速版）就是使用永中的服务实现的：在这里插入图片描述

说明：
1.使用该方法，文档应该会被上传到永中的服务器，非公开文档不宜使用（购买的话应该也可以部署的自己的服务器上，不深究）。
2.下面测试方法中上传的文档不知道会不会被定时清理而不可用，不过如果有这个问题，只要申请免费受限账号应该就可以了。

1. 试一试在线预览！

地址：http://www.yozodcs.com/page/example.html
测试：http://www.yozodcs.com:8000/2019/04/11/MTkwNDExNTgxODc5MDUx.html
在这里插入图片描述

2. Web调用

（1）URL文档

  1. $.ajax({ 
  2.     url: "http://dcs.yozosoft.com:80/onlinefile", //服务地址
  3.     data: { 
  4.         downloadUrl: "http://www.snpdp.com/file-download-1064.html", //要预览的文档地址
  5.         convertType: "0"
  6.     },
  7.     dataType: "json",
  8.     type: "post",
  9.     success: function(data) { 
  10.         console.log(data);
  11.         //window.location=data.data[0];
  12.     },
  13.     error: function(data) { 
  14.         console.error(data)
  15.     }
  16. });

接口说明、convertType参数取值说明、返回参数说明：http://www.yozodcs.com/help.html#link14

（2）上传文档
引入ajaxfileupload.js（jQuery-File-Upload）

  1. <input id="fileupload" type="file" name="file"><!-- name值需为file，与永中接口参数名对应 -->
  3. <script src="https://cdn.bootcss.com/jquery/3.3.1/jquery.min.js"></script>
  4. <script src="js/jquery.ui.widget.js"></script>
  5. <script src="js/jquery.fileupload.js"></script>
  7. <script> $(function() { $('#fileupload').fileupload({ url: 'http://dcs.yozosoft.com:80/upload', dataType: 'json', formData: { convertType: "0" }, done: function(e, data) { console.log(data.result); } }); }); </script>

测试：http://dcs.yozosoft.com:8000/2019/04/12/MTkwNDEyNDAyNDM2MzMx.html
在这里插入图片描述

3. Java调用

（1）添加依赖

  1. <!-- https://mvnrepository.com/artifact/commons-logging/commons-logging -->
  2. <dependency>
  3.     <groupId>commons-logging</groupId>
  4.     <artifactId>commons-logging</artifactId>
  5.     <version>1.2</version>
  6. </dependency>
  7. <!-- https://mvnrepository.com/artifact/org.apache.httpcomponents/httpclient -->
  8. <dependency>
  9.     <groupId>org.apache.httpcomponents</groupId>
  10.     <artifactId>httpclient</artifactId>
  11.     <version>4.5.8</version>
  12. </dependency>
  13. <!-- https://mvnrepository.com/artifact/org.apache.httpcomponents/httpcore -->
  14. <dependency>
  15.     <groupId>org.apache.httpcomponents</groupId>
  16.     <artifactId>httpcore</artifactId>
  17.     <version>4.4.11</version>
  18. </dependency>
  19. <!-- https://mvnrepository.com/artifact/org.apache.httpcomponents/httpmime -->
  20. <dependency>
  21.     <groupId>org.apache.httpcomponents</groupId>
  22.     <artifactId>httpmime</artifactId>
  23.     <version>4.5.8</version>
  24. </dependency>
  25. <!-- https://mvnrepository.com/artifact/com.alibaba/fastjson -->
  26. <dependency>
  27.     <groupId>com.alibaba</groupId>
  28.     <artifactId>fastjson</artifactId>
  29.     <version>1.2.55</version>
  30. </dependency>

（2）编写工具类DCSUtil.java

  1. import java.io.BufferedReader;
  2. import java.io.File;
  3. import java.io.IOException;
  4. import java.io.InputStreamReader;
  5. import java.io.PrintWriter;
  6. import java.net.URL;
  7. import java.net.URLConnection;
  8. import java.nio.charset.Charset;
  9. import org.apache.http.HttpEntity;
  10. import org.apache.http.HttpResponse;
  11. import org.apache.http.HttpStatus;
  12. import org.apache.http.ParseException;
  13. import org.apache.http.client.HttpClient;
  14. import org.apache.http.client.methods.HttpPost;
  15. import org.apache.http.entity.mime.HttpMultipartMode;
  16. import org.apache.http.entity.mime.MultipartEntity;
  17. import org.apache.http.entity.mime.content.FileBody;
  18. import org.apache.http.entity.mime.content.StringBody;
  19. import org.apache.http.impl.client.DefaultHttpClient;
  20. import org.apache.http.util.EntityUtils;
  22. /** * @Description: DCS文档转换服务Java调用代码示例 */
  23. public class DCSUtil { 
  24.     /** * 向指定 URL 发送POST方法的请求 * @param url 发送请求的 URL * @param param 请求参数，请求参数应该是 name1=value1&name2=value2 的形式。 * @return 所代表远程资源的响应结果 */
  25.     public static String sendPost(String url, String param) { 
  26.         PrintWriter out = null;
  27.         BufferedReader in = null;
  28.         String result = "";
  29.         try { 
  30.             URL realUrl = new URL(url);
  31.             // 打开和URL之间的连接
  32.             URLConnection conn = realUrl.openConnection();
  33.             conn.setRequestProperty("Accept-Charset", "UTF-8");
  34.             // 设置通用的请求属性
  35.             conn.setRequestProperty("accept", "*/*");
  36.             conn.setRequestProperty("connection", "Keep-Alive");
  37.             conn.setRequestProperty("user-agent", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1;SV1)");
  38.             // 发送POST请求必须设置如下两行
  39.             conn.setDoOutput(true);
  40.             conn.setDoInput(true);
  41.             // 获取URLConnection对象对应的输出流
  42.             out = new PrintWriter(conn.getOutputStream());
  43.             // 发送请求参数
  44.             out.print(param);
  45.             // flush输出流的缓冲
  46.             out.flush();
  47.             // 定义BufferedReader输入流来读取URL的响应
  48.             in = new BufferedReader(new InputStreamReader(conn.getInputStream()));
  49.             String line;
  50.             while ((line = in.readLine()) != null) { 
  51.                 result += line;
  52.             }
  53.         } catch (Exception e) { 
  54.             System.out.println("发送 POST 请求出现异常！" + e);
  55.             e.printStackTrace();
  56.         }
  57.         // 使用finally块来关闭输出流、输入流
  58.         finally { 
  59.             try { 
  60.                 if (out != null) { 
  61.                     out.close();
  62.                 }
  63.                 if (in != null) { 
  64.                     in.close();
  65.                 }
  66.             } catch (IOException ex) { 
  67.                 ex.printStackTrace();
  68.             }
  69.         }
  70.         return result;
  71.     }
  73.     /** * 向指定 URL 上传文件POST方法的请求 * * @param url 发送请求的 URL * @param filepath 文件路径 * @param type 转换类型 * @return 所代表远程资源的响应结果, json数据 */
  74.     public static String SubmitPost(String url, String filepath, String type) { 
  75.         String requestJson = "";
  76.         HttpClient httpclient = new DefaultHttpClient();
  77.         try { 
  78.             HttpPost httppost = new HttpPost(url);
  79.             FileBody file = new FileBody(new File(filepath));
  80.             MultipartEntity reqEntity = new MultipartEntity(HttpMultipartMode.BROWSER_COMPATIBLE, null,
  81.             Charset.forName("UTF-8"));
  82.             reqEntity.addPart("file", file); // file为请求后台的File upload;属性
  83.             reqEntity.addPart("convertType", new StringBody(type, Charset.forName("UTF-8")));
  84.             httppost.setEntity(reqEntity);
  85.             HttpResponse response = httpclient.execute(httppost);
  86.             int statusCode = response.getStatusLine().getStatusCode();
  87.             if (statusCode == HttpStatus.SC_OK) { 
  88.                 HttpEntity resEntity = response.getEntity();
  89.                 requestJson = EntityUtils.toString(resEntity);
  90.                 EntityUtils.consume(resEntity);
  91.             }
  92.         } catch (ParseException e) { 
  93.             // TODO Auto-generated catch block
  94.             e.printStackTrace();
  95.             // requestJson = e.toString();
  96.         } catch (IOException e) { 
  97.             // TODO Auto-generated catch block
  98.             e.printStackTrace();
  99.             // requestJson = e.toString();
  100.         } finally { 
  101.             try { 
  102.                 httpclient.getConnectionManager().shutdown();
  103.             } catch (Exception ignore) { 
  104.             }
  105.         }
  106.         return requestJson;
  107.     }
  108. }

（3）测试

  1. @Test
  2. public void testDCS() { 
  3.     // 文件上传转换
  4.     String convertByFile = DCSUtil.SubmitPost("http://dcs.yozosoft.com:80/upload", "D:/test/doctest.doc", "0");
  5.     System.out.println(convertByFile);
  6.     // 输出：{"result":0,"data":["http://dcs.yozosoft.com:8000/2019/04/12/MTkwNDEyNTM5NTE2Njk5.html"],"message":"转换成功","type":0}
  8.     // 网络地址转换
  9.     String convertByUrl = DCSUtil.sendPost("http://dcs.yozosoft.com:80/onlinefile",
  10.             "downloadUrl=http://www.snpdp.com/file-download-1064.html&convertType=1");
  11.     System.out.println(convertByUrl);
  12.     // 输出：{"result":0,"data":["http://dcs.yozosoft.com:8000/2019/04/12/MTkwNDEyNTQ0NjcyMDI3.html"],"message":"转换成功","type":1}
  13. }

发表评论

表情：
评论列表 （有 0 条评论，738人围观）

还没有评论，来说两句吧...

相关阅读