Recently, my family has a pdf document that needs to be converted into word. I find it easy to search for tools on the Internet, but I didn’t find any useful tools. How many decent ones need money? ?
Is pdf conversion so difficult? Why do we need to spend money to solve it? Can't the powerful java and the easy-to-use apache tool series solve it? So I decided to look into it.
First, I found the dependency package for apache pdf parsing:
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>2.0.4</version>
</dependency>
<dependency>
<groupId>net.coobird</groupId>
<artifactId>thumbnailator</artifactId>
<version>0.4.8</version>
</dependency>The other is a package for image processing.
Since the pdf contains pictures and text, I extract the pictures and text and add them to the word, adding the POI dependency.
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi</artifactId>
<version>3.9</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
<version>3.9</version>
</dependency>Then post the code:
public class Pdf2word {
public static void main(String[] args) throws InvalidFormatException {
try {
String pdfFileName = "H:\\xuweichao.pdf";
PDDocument pdf = PDDocument.load(new File(pdfFileName));
int pageNumber = pdf.getNumberOfPages();
String docFileName = pdfFileName.substring(0, pdfFileName.lastIndexOf(".")) + ".doc";
File file = new File(docFileName);
if (!file.exists()) {
file.createNewFile();
}
CustomXWPFDocument document = new CustomXWPFDocument();
FileOutputStream fos = new FileOutputStream(docFileName);
//提取每一页的图片和文字，添加到 word 中
for (int i = 0; i < pageNumber; i++) {
PDPage page = pdf.getPage(i);
PDResources resources = page.getResources();
Iterable<COSName> names = resources.getXObjectNames();
Iterator<COSName> iterator = names.iterator();
while (iterator.hasNext()) {
COSName cosName = iterator.next();
if (resources.isImageXObject(cosName)) {
PDImageXObject imageXObject = (PDImageXObject) resources.getXObject(cosName);
File outImgFile = new File("H:\\img\\" + System.currentTimeMillis() + ".jpg");
Thumbnails.of(imageXObject.getImage()).scale(0.9).rotate(0).toFile(outImgFile);
BufferedImage bufferedImage = ImageIO.read(outImgFile);
int width = bufferedImage.getWidth();
int height = bufferedImage.getHeight();
if (width > 600) {
double ratio = Math.round((double) width / 550.0);
System.out.println("缩放比ratio："+ratio);
width = (int) (width / ratio);
height = (int) (height / ratio);
}
System.out.println("width: " + width + ", height: " + height);
FileInputStream in = new FileInputStream(outImgFile);
byte[] ba = new byte[in.available()];
in.read(ba);
ByteArrayInputStream byteInputStream = new ByteArrayInputStream(ba);
XWPFParagraph picture = document.createParagraph();
//添加图片
document.addPictureData(byteInputStream, CustomXWPFDocument.PICTURE_TYPE_JPEG);
//图片大小、位置
document.createPicture(document.getAllPictures().size() - 1, width, height, picture);
}
}
PDFTextStripper stripper = new PDFTextStripper();
stripper.setSortByPosition(true);
stripper.setStartPage(i);
stripper.setEndPage(i);
//当前页中的文字
String text = stripper.getText(pdf);
XWPFParagraph textParagraph = document.createParagraph();
XWPFRun textRun = textParagraph.createRun();
textRun.setText(text);
textRun.setFontFamily("仿宋");
textRun.setFontSize(11);
//换行
textParagraph.setWordWrap(true);
}
document.write(fos);
fos.close();
pdf.close();
System.out.println("pdf转换解析结束！！----");
} catch (IOException e) {
e.printStackTrace();
}
}
}Custom document class:
public class CustomXWPFDocument extends XWPFDocument {
public CustomXWPFDocument(InputStream in) throws IOException {
super(in);
}
public CustomXWPFDocument() {
super();
}
public CustomXWPFDocument(OPCPackage pkg) throws IOException {
super(pkg);
}
/**
* @param id
* @param width
* 宽
* @param height
* 高
* @param paragraph
* 段落
*/
public void createPicture(int id, int width, int height,
XWPFParagraph paragraph) {
final int EMU = 9525;
width *= EMU;
height *= EMU;
String blipId = getAllPictures().get(id).getPackageRelationship()
.getId();
CTInline inline = paragraph.createRun().getCTR().addNewDrawing()
.addNewInline();
String picXml = ""
+ "<a:graphic xmlns:a=\"http://schemas.openxmlformats.org/drawingml/2006/main\">"
+ " <a:graphicData uri=\"http://schemas.openxmlformats.org/drawingml/2006/picture\">"
+ " <pic:pic xmlns:pic=\"http://schemas.openxmlformats.org/drawingml/2006/picture\">"
+ " <pic:nvPicPr>" + " <pic:cNvPr id=\""
+ id
+ "\" name=\"Generated\"/>"
+ " <pic:cNvPicPr/>"
+ " </pic:nvPicPr>"
+ " <pic:blipFill>"
+ " <a:blip r:embed=\""
+ blipId
+ "\" xmlns:r=\"http://schemas.openxmlformats.org/officeDocument/2006/relationships\"/>"
+ " <a:stretch>"
+ " <a:fillRect/>"
+ " </a:stretch>"
+ " </pic:blipFill>"
+ " <pic:spPr>"
+ " <a:xfrm>"
+ " <a:off x=\"0\" y=\"0\"/>"
+ " <a:ext cx=\""
+ width
+ "\" cy=\""
+ height
+ "\"/>"
+ " </a:xfrm>"
+ " <a:prstGeom prst=\"rect\">"
+ " <a:avLst/>"
+ " </a:prstGeom>"
+ " </pic:spPr>"
+ " </pic:pic>"
+ " </a:graphicData>" + "</a:graphic>";
inline.addNewGraphic().addNewGraphicData();
XmlToken xmlToken = null;
try {
xmlToken = XmlToken.Factory.parse(picXml);
} catch (XmlException xe) {
xe.printStackTrace();
}
inline.set(xmlToken);
inline.setDistT(0);
inline.setDistB(0);
inline.setDistL(0);
inline.setDistR(0);
CTPositiveSize2D extent = inline.addNewExtent();
extent.setCx(width);
extent.setCy(height);
CTNonVisualDrawingProps docPr = inline.addNewDocPr();
docPr.setId(id);
docPr.setName("图片名称");
docPr.setDescr("描述信息");
}
}The program is as simple as that. It traverses each page of the file and extracts the pictures and texts in the pdf. The text style problem has not been solved yet, but the generated word file is scaled down for large pictures, and the effect is good for simple pdf files with simple layout.