使用PDFBox處理PDF文件
阿新 • • 發佈:2019-01-10
專案需要在原有的PDF檔案中插入圖片、文字,並將最終的PDF檔案轉換為圖片,在網上找了很多Demo,現在開源可以解析處理PDF檔案的第三方外掛比較多,eg:IText、PDFBox等,現在就PDFBox解析處理PDF檔案總結如下:
【PDFBox簡介】
自從Adobe公司1993年第一次釋出公共PDF參考以來,支援各種語言和平臺的PDF工具和類庫就如雨後春筍般湧現。然而,Java應用開發中Adobe技術的支援相對滯後了。這是個奇怪的現象,因為PDF文件是企業資訊系統儲存和交換資訊的大勢所趨,而Java技術特別適合這種應用。然而,Java開發人員似乎直到最近才獲得成熟可用的PDF支援。 PDFBox(一個BSD許可下的原始碼開放專案)是一個為開發人員讀取和建立PDF文件而準備的純Java類庫。它提供如下特性: 提取文字,包括Unicode字元。和Jakarta Lucene等文字搜尋引擎的整合過程十分簡單。加密/解密PDF文件。從PDF和XFDF格式中匯入或匯出表單資料。向已有PDF文件中追加內容。將一個PDF文件切分為多個文件。覆蓋PDF文件。 PS:http://baike.baidu.com/link?url=TsYWHJtTPMhlf0UvKzPOk-j3f9KzF7morIa4CqoZ0s4yIDCLB3z8nLVgLHVz-AO4dE6S7ls_3_yuvXP03nLSiq【PDFBox下載】
最常見的一種PDF文字抽取工具就是PDFBox了,訪問網址http://pdfbox.apache.org/download.cgi,進入如下圖所示的下載介面。讀者可以在該網頁下載其最新的版本。本書採用的是pdfbox-1.8.8版本。PDFBox是一個開源的Java PDF庫,這個庫允許你訪問PDF檔案的各項資訊。在接下來的例子中,將演示如何使用PDFBox提供的API操作PDF檔案。
【將剛下載的7個jar包引入到工程當中】
pdfbox-1.8.8-src.zip為pdfbox原始碼,裡面有很對的例子,在pdfbox-1.8.8\examples目錄下存在
【以下為Demo正式開始】
1、建立PDF檔案
1 public void createHelloPDF() { 2 PDDocument doc = null; 3 PDPage page = null; 4 5 try { 6 doc = new PDDocument(); 7 page = new PDPage(); 8 doc.addPage(page); 9 PDFont font = PDType1Font.HELVETICA_BOLD;10 PDPageContentStream content = new PDPageContentStream(doc, page); 11 content.beginText(); 12 content.setFont(font, 12); 13 content.moveTextPositionByAmount(100, 700); 14 content.drawString("hello"); 15 16 content.endText(); 17 content.close(); 18 doc.save("F:\\java56班\\eclipse-SDK-4.2-win32\\pdfwithText.pdf"); 19 doc.close(); 20 } catch (Exception e) { 21 System.out.println(e); 22 } 23 }
2、讀取PDF檔案:
1 public void readPDF() { 2 PDDocument helloDocument = null; 3 try { 4 helloDocument = PDDocument.load(new File( 5 "F:\\java56班\\eclipse-SDK-4.2-win32\\pdfwithText.pdf")); 6 PDFTextStripper textStripper = new PDFTextStripper("GBK"); 7 System.out.println(textStripper.getText(helloDocument)); 8 9 helloDocument.close(); 10 } catch (IOException e) { 11 // TODO Auto-generated catch block 12 e.printStackTrace(); 13 } 14 }
3、修改PDF檔案(處理中文亂碼,我可以搞定的):
1 /** 2 * Locate a string in a PDF and replace it with a new string. 3 * 4 * @param inputFile The PDF to open. 5 * @param outputFile The PDF to write to. 6 * @param strToFind The string to find in the PDF document. 7 * @param message The message to write in the file. 8 * 9 * @throws IOException If there is an error writing the data. 10 * @throws COSVisitorException If there is an error writing the PDF. 11 */ 12 public void doIt( String inputFile, String outputFile, String strToFind, String message) 13 throws IOException, COSVisitorException 14 { 15 // the document 16 PDDocument doc = null; 17 try 18 { 19 doc = PDDocument.load( inputFile ); 20 // PDFTextStripper stripper=new PDFTextStripper("ISO-8859-1"); 21 List pages = doc.getDocumentCatalog().getAllPages(); 22 for( int i=0; i<pages.size(); i++ ) 23 { 24 PDPage page = (PDPage)pages.get( i ); 25 PDStream contents = page.getContents(); 26 PDFStreamParser parser = new PDFStreamParser(contents.getStream() ); 27 parser.parse(); 28 List tokens = parser.getTokens(); 29 for( int j=0; j<tokens.size(); j++ ) 30 { 31 Object next = tokens.get( j ); 32 if( next instanceof PDFOperator ) 33 { 34 PDFOperator op = (PDFOperator)next; 35 //Tj and TJ are the two operators that display 36 //strings in a PDF 37 if( op.getOperation().equals( "Tj" ) ) 38 { 39 //Tj takes one operator and that is the string 40 //to display so lets update that operator 41 COSString previous = (COSString)tokens.get( j-1 ); 42 String string = previous.getString(); 43 string = string.replaceFirst( strToFind, message ); 44 System.out.println(string); 45 System.out.println(string.getBytes("GBK")); 46 previous.reset(); 47 previous.append( string.getBytes("GBK") ); 48 } 49 else if( op.getOperation().equals( "TJ" ) ) 50 { 51 COSArray previous = (COSArray)tokens.get( j-1 ); 52 for( int k=0; k<previous.size(); k++ ) 53 { 54 Object arrElement = previous.getObject( k ); 55 if( arrElement instanceof COSString ) 56 { 57 COSString cosString = (COSString)arrElement; 58 String string = cosString.getString(); 59 string = string.replaceFirst( strToFind, message ); 60 cosString.reset(); 61 cosString.append( string.getBytes("GBK") ); 62 } 63 } 64 } 65 } 66 } 67 //now that the tokens are updated we will replace the 68 //page content stream. 69 PDStream updatedStream = new PDStream(doc); 70 OutputStream out = updatedStream.createOutputStream(); 71 ContentStreamWriter tokenWriter = new ContentStreamWriter(out); 72 tokenWriter.writeTokens( tokens ); 73 page.setContents( updatedStream ); 74 } 75 doc.save( outputFile ); 76 } 77 finally 78 { 79 if( doc != null ) 80 { 81 doc.close(); 82 } 83 } 84 }
4、在PDF中加入圖片:
1 /** 2 * Add an image to an existing PDF document. 3 * 4 * @param inputFile The input PDF to add the image to. 5 * @param image The filename of the image to put in the PDF. 6 * @param outputFile The file to write to the pdf to. 7 * 8 * @throws IOException If there is an error writing the data. 9 * @throws COSVisitorException If there is an error writing the PDF. 10 */ 11 public void createPDFFromImage( String inputFile, String image, String outputFile ) 12 throws IOException, COSVisitorException 13 { 14 // the document 15 PDDocument doc = null; 16 try 17 { 18 doc = PDDocument.load( inputFile ); 19 20 //we will add the image to the first page. 21 PDPage page = (PDPage)doc.getDocumentCatalog().getAllPages().get( 0 ); 22 23 PDXObjectImage ximage = null; 24 if( image.toLowerCase().endsWith( ".jpg" ) ) 25 { 26 ximage = new PDJpeg(doc, new FileInputStream( image ) ); 27 } 28 else if (image.toLowerCase().endsWith(".tif") || image.toLowerCase().endsWith(".tiff")) 29 { 30 ximage = new PDCcitt(doc, new RandomAccessFile(new File(image),"r")); 31 } 32 else 33 { 34 BufferedImage awtImage = ImageIO.read( new File( image ) ); 35 ximage = new PDPixelMap(doc, awtImage); 36 } 37 PDPageContentStream contentStream = new PDPageContentStream(doc, page, true, true); 38 39 //contentStream.drawImage(ximage, 20, 20 ); 40 // better method inspired by http://stackoverflow.com/a/22318681/535646 41 float scale = 0.5f; // reduce this value if the image is too large 42 System.out.println(ximage.getHeight()); 43 System.out.println(ximage.getWidth()); 44 // ximage.setHeight(ximage.getHeight()/5); 45 // ximage.setWidth(ximage.getWidth()/5); 46 contentStream.drawXObject(ximage, 20, 200, ximage.getWidth()*scale, ximage.getHeight()*scale); 47 48 contentStream.close(); 49 doc.save( outputFile ); 50 } 51 finally 52 { 53 if( doc != null ) 54 { 55 doc.close(); 56 } 57 } 58 }
5、PDF檔案轉換為圖片:
1 public void toImage() { 2 try { 3 PDDocument doc = PDDocument 4 .load("F:\\java56班\\eclipse-SDK-4.2-win32\\pdfwithText.pdf"); 5 int pageCount = doc.getPageCount(); 6 System.out.println(pageCount); 7 List pages = doc.getDocumentCatalog().getAllPages(); 8 for (int i = 0; i < pages.size(); i++) { 9 PDPage page = (PDPage) pages.get(i); 10 BufferedImage image = page.convertToImage(); 11 Iterator iter = ImageIO.getImageWritersBySuffix("jpg"); 12 ImageWriter writer = (ImageWriter) iter.next(); 13 File outFile = new File("F:\\java56班\\eclipse-SDK-4.2-win32\\" 14 + i + ".jpg"); 15 FileOutputStream out = new FileOutputStream(outFile); 16 ImageOutputStream outImage = ImageIO 17 .createImageOutputStream(out); 18 writer.setOutput(outImage); 19 writer.write(new IIOImage(image, null, null)); 20 } 21 doc.close(); 22 System.out.println("over"); 23 } catch (FileNotFoundException e) { 24 // TODO Auto-generated catch block 25 e.printStackTrace(); 26 } catch (IOException e) { 27 // TODO Auto-generated catch block 28 e.printStackTrace(); 29 } 30 }
6、圖片轉換為PDF檔案(支援多張圖片轉換為PDF檔案):
1 /** 2 * create the second sample document from the PDF file format specification. 3 * 4 * @param file 5 * The file to write the PDF to. 6 * @param image 7 * The filename of the image to put in the PDF. 8 * 9 * @throws IOException 10 * If there is an error writing the data. 11 * @throws COSVisitorException 12 * If there is an error writing the PDF. 13 */ 14 public void createPDFFromImage(String file, String image)throws IOException, COSVisitorException { 15 // 多張圖片轉換為PDF檔案 16 PDDocument doc = null; 17 doc = new PDDocument(); 18 PDPage page = null; 19 PDXObjectImage ximage = null; 20 PDPageContentStream contentStream = null; 21 22 File files = new File(image); 23 String[] a = files.list(); 24 for (String string : a) { 25 if (string.toLowerCase().endsWith(".jpg")) { 26 String temp = image + "\\" + string; 27 ximage = new PDJpeg(doc, new FileInputStream(temp)); 28 page = new PDPage(); 29 doc.addPage(page); 30 contentStream = new PDPageContentStream(doc, page); 31 float scale = 0.5f; 32 contentStream.drawXObject(ximage, 20, 400, ximage.getWidth() 33 * scale, ximage.getHeight() * scale); 34 35 PDFont font = PDType1Font.HELVETICA_BOLD; 36 contentStream.beginText(); 37 contentStream.setFont(font, 12); 38 contentStream.moveTextPositionByAmount(100, 700); 39 contentStream.drawString("Hello"); 40 contentStream.endText(); 41 42 contentStream.close(); 43 } 44 } 45 doc.save(file); 46 doc.close(); 47 }
7、替換PDF檔案中的某個字串:
1 /** 2 * Locate a string in a PDF and replace it with a new string. 3 * 4 * @param inputFile The PDF to open. 5 * @param outputFile The PDF to write to. 6 * @param strToFind The string to find in the PDF document. 7 * @param message The message to write in the file. 8 * 9 * @throws IOException If there is an error writing the data. 10 * @throws COSVisitorException If there is an error writing the PDF. 11 */ 12 public void doIt( String inputFile, String outputFile, String strToFind, String message) 13 throws IOException, COSVisitorException 14 { 15 // the document 16 PDDocument doc = null; 17 try 18 { 19 doc = PDDocument.load( inputFile ); 20 // PDFTextStripper stripper=new PDFTextStripper("ISO-8859-1"); 21 List pages = doc.getDocumentCatalog().getAllPages(); 22 for( int i=0; i<pages.size(); i++ ) 23 { 24 PDPage page = (PDPage)pages.get( i ); 25 PDStream contents = page.getContents(); 26 PDFStreamParser parser = new PDFStreamParser(contents.getStream() ); 27 parser.parse(); 28 List tokens = parser.getTokens(); 29 for( int j=0; j<tokens.size(); j++ ) 30 { 31 Object next = tokens.get( j ); 32 if( next instanceof PDFOperator ) 33 { 34 PDFOperator op = (PDFOperator)next; 35 //Tj and TJ are the two operators that display 36 //strings in a PDF 37 if( op.getOperation().equals( "Tj" ) ) 38 { 39 //Tj takes one operator and that is the string 40 //to display so lets update that operator 41 COSString previous = (COSString)tokens.get( j-1 ); 42 String string = previous.getString(); 43 string = string.replaceFirst( strToFind, message ); 44 System.out.println(string); 45 System.out.println(string.getBytes("GBK")); 46 previous.reset(); 47 previous.append( string.getBytes("GBK") ); 48 } 49 else if( op.getOperation().equals( "TJ" ) ) 50 { 51 COSArray previous = (COSArray)tokens.get( j-1 ); 52 for( int k=0; k<previous.size(); k++ ) 53 { 54 Object arrElement = previous.getObject( k ); 55 if( arrElement instanceof COSString ) 56 { 57 COSString cosString = (COSString)arrElement; 58 String string = cosString.getString(); 59 string = string.replaceFirst( strToFind, message ); 60 cosString.reset(); 61 cosString.append( string.getBytes("GBK") ); 62 } 63 } 64 } 65 } 66 } 67 //now that the tokens are updated we will replace the 68 //page content stream. 69 PDStream updatedStream = new PDStream(doc); 70 OutputStream out = updatedStream.createOutputStream(); 71 ContentStreamWriter tokenWriter = new ContentStreamWriter(out); 72 tokenWriter.writeTokens( tokens ); 73 page.setContents( updatedStream ); 74 } 75 doc.save( outputFile ); 76 } 77 finally 78 { 79 if( doc != null ) 80 { 81 doc.close(); 82 } 83 } 84 }
上述描述的只是PDFBox的部分功能,在原始資源包中有很對例子,大家可以學習,PDFBox API路徑:http://pdfbox.apache.org/docs/1.8.8/javadocs/
轉載自:愛程式設計w2bc.com 如果本部落格無法幫助你,請看這裡,效果也很好:http://blog.csdn.net/w20228396/article/details/68065552