用Java写一个PDF,Word文件转换工具 |
您所在的位置:网站首页 › swf转exe不要控件 › 用Java写一个PDF,Word文件转换工具 |
前言
前段时间一直使用到word文档转pdf或者pdf转word,寻思着用Java应该是可以实现的,于是花了点时间写了个文件转换工具 源码weloe/FileConversion (github.com) 主要功能就是word和pdf的文件转换,如下 pdf 转 wordpdf 转 图片word 转 图片word 转 htmlword 转 pdf 实现方法主要使用了pdfbox Apache PDFBox | A Java PDF Library以及spire.doc Free Spire.Doc for Java | 100% 免费 Java Word 组件 (e-iceblue.cn)两个工具包 pom.xml com.e-iceblue http://repo.e-iceblue.cn/repository/maven-public/ 8 8 org.apache.pdfbox pdfbox 2.0.4 junit junit 4.13.2 test e-iceblue spire.doc.free 3.9.0策略接口 public interface FileConversion { boolean isSupport(String s); String convert(String pathName,String dirAndFileName) throws Exception; }PDF转图片实现 public class PDF2Image implements FileConversion{ private String suffix = ".jpg"; public static final int DEFAULT_DPI = 150; @Override public boolean isSupport(String s) { return "pdf2image".equals(s); } @Override public String convert(String pathName,String dirAndFileName) throws Exception { String outPath = dirAndFileName + suffix; if(Files.exists(Paths.get(outPath))){ throw new RuntimeException(outPath+" 文件已存在"); } pdf2multiImage(pathName,outPath,DEFAULT_DPI); return outPath; } /** * pdf转图片 * 多页PDF会每页转换为一张图片,下面会有多页组合成一页的方法 * * @param pdfFile pdf文件路径 * @param outPath 图片输出路径 * @param dpi 相当于图片的分辨率,值越大越清晰,但是转换时间变长 */ public void pdf2multiImage(String pdfFile, String outPath, int dpi) { if (dpi return "pdf2word".equals(s); } /** * * @param pathName * @throws IOException */ @Override public String convert(String pathName,String dirAndFileName) throws Exception { String outPath = dirAndFileName + suffix; if(Files.exists(Paths.get(outPath))){ throw new RuntimeException(outPath+" 文件已存在"); } pdf2word(pathName, outPath); return outPath; } private void pdf2word(String pathName, String outPath) throws IOException { PDDocument doc = PDDocument.load(new File(pathName)); int pagenumber = doc.getNumberOfPages(); // 创建文件 createFile(Paths.get(outPath)); FileOutputStream fos = new FileOutputStream(outPath); Writer writer = new OutputStreamWriter(fos, "UTF-8"); PDFTextStripper stripper = new PDFTextStripper(); stripper.setSortByPosition(true);//排序 stripper.setStartPage(1);//设置转换的开始页 stripper.setEndPage(pagenumber);//设置转换的结束页 stripper.writeText(doc, writer); writer.close(); doc.close(); } }word转html public class Word2HTML implements FileConversion{ private String suffix = ".html"; @Override public boolean isSupport(String s) { return "word2html".equals(s); } @Override public String convert(String pathName, String dirAndFileName) { String outPath = dirAndFileName + suffix; if(Files.exists(Paths.get(outPath))){ throw new RuntimeException(outPath+" 文件已存在"); } Document doc = new Document(); doc.loadFromFile(pathName); doc.saveToFile(outPath, FileFormat.Html); doc.dispose(); return outPath; } }word转图片 public class Word2Image implements FileConversion{ private String suffix = ".jpg"; @Override public boolean isSupport(String s) { return "word2image".equals(s); } @Override public String convert(String pathName, String dirAndFileName) throws Exception { String outPath = dirAndFileName + suffix; if(Files.exists(Paths.get(outPath))){ throw new RuntimeException(outPath+" 文件已存在"); } Document doc = new Document(); //加载文件 doc.loadFromFile(pathName); //上传文档页数,也是最后要生成的图片数 Integer pageCount = doc.getPageCount(); // 参数第一个和第三个都写死 第二个参数就是生成图片数 BufferedImage[] image = doc.saveToImages(0, pageCount, ImageType.Bitmap); // 组合图片 List imageList = Arrays.asList(image); ImageUtil.yPic(imageList, outPath); return outPath; } }word转pdf public class Word2PDF implements FileConversion{ private String suffix = ".pdf"; @Override public boolean isSupport(String s) { return "word2pdf".equals(s); } @Override public String convert(String pathName, String dirAndFileName) throws Exception { String outPath = dirAndFileName + suffix; if(Files.exists(Paths.get(outPath))){ throw new RuntimeException(outPath+" 文件已存在"); } //加载word Document document = new Document(); document.loadFromFile(pathName, FileFormat.Docx); //保存结果文件 document.saveToFile(outPath, FileFormat.PDF); document.close(); return outPath; } } 使用输入转换方法,文件路径,输出路径(输出路径如果输入’null’则为文件同目录下同名不同后缀文件) 转换方法可选项: pdf2wordpdf2imageword2htmlword2imageword2pdf例如输入: pdf2word D:\test\testpdf.pdf null控制台输出: 转换方法: pdf2word 文件: D:\test\testFile.pdf 转换成功!文件路径: D:\test\testFile.doc |
CopyRight 2018-2019 办公设备维修网 版权所有 豫ICP备15022753号-3 |