如何读取pdf文件并将其写入outputStream

Question

我需要读取带有filepath“C：\ file.pdf”的pdf文件并将其写入outputStream。什么是最简单的方法来做到这一点？

@Controller 
public class ExportTlocrt { 

@Autowired 
private PhoneBookService phoneBookSer; 

private void setResponseHeaderTlocrtPDF(HttpServletResponse response) { 
    response.setContentType("application/pdf"); 
    response.setHeader("content-disposition", "attachment; filename=Tlocrt.pdf"); 
} 

@RequestMapping(value = "/exportTlocrt.html", method = RequestMethod.POST) 
public void exportTlocrt(Model model, HttpServletResponse response, HttpServletRequest request){ 

    setResponseHeaderTlocrtPDF(response); 
    File f = new File("C:\\Tlocrt.pdf"); 

    try { 
     OutputStream os = response.getOutputStream(); 
     byte[] buf = new byte[8192]; 
     InputStream is = new FileInputStream(f); 
     int c = 0; 
     while ((c = is.read(buf, 0, buf.length)) > 0) { 
      os.write(buf, 0, c); 
      os.flush(); 
     } 
     os.close(); 
     is.close(); 
    } catch (IOException e) { 
     e.printStackTrace(); 
    } 

} 
} 

............................................ ................................................

Answer 1

import java.io.*; 


public class FileRead { 


    public static void main(String[] args) throws IOException { 


     File f=new File("C:\\Documents and Settings\\abc\\Desktop\\abc.pdf"); 

     OutputStream oos = new FileOutputStream("test.pdf"); 

     byte[] buf = new byte[8192]; 

     InputStream is = new FileInputStream(f); 

     int c = 0; 

     while ((c = is.read(buf, 0, buf.length)) > 0) { 
      oos.write(buf, 0, c); 
      oos.flush(); 
     } 

     oos.close(); 
     System.out.println("stop"); 
     is.close(); 

    } 

} 

The到目前为止最简单的方法。希望这可以帮助。

Answer 2

您可以使用Apache的PdfBox，它易于使用且性能良好。

下面是一个PDF文件中提取文本的例子（你可以阅读更多here）：

import java.io.*; 
import org.apache.pdfbox.pdmodel.*; 
import org.apache.pdfbox.util.*; 

public class PDFTest { 

public static void main(String[] args){ 
PDDocument pd; 
BufferedWriter wr; 
try { 
     File input = new File("C:\\Invoice.pdf"); // The PDF file from where you would like to extract 
     File output = new File("C:\\SampleText.txt"); // The text file where you are going to store the extracted data 
     pd = PDDocument.load(input); 
     System.out.println(pd.getNumberOfPages()); 
     System.out.println(pd.isEncrypted()); 
     pd.save("CopyOfInvoice.pdf"); // Creates a copy called "CopyOfInvoice.pdf" 
     PDFTextStripper stripper = new PDFTextStripper(); 
     wr = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(output))); 
     stripper.writeText(pd, wr); 
     if (pd != null) { 
      pd.close(); 
     } 
     // I use close() to flush the stream. 
     wr.close(); 
} catch (Exception e){ 
     e.printStackTrace(); 
     } 
    } 
} 

UPDATE：

可以使用PDFTextStripper获取文本：

PDFTextStripper reader = new PDFTextStripper(); 
String pageText = reader.getText(pd); // PDDocument object created