catalogue
Reading PDF files in the network and file type conversion
If this blog is helpful to you, remember to leave a message + like + collect.
Apache PDFBox is an open source Java library that supports the development and transformation of PDF documents.
It has the following functions -
-
Extract Text - With PDFBox, you can extract Unicode text from PDF files.
-
Split & Merge - With PDFBox, you can divide a single PDF file into multiple files and merge them into one file.
-
Fill Forms - With PDFBox, you can fill in the form data in the document.
-
Print - With PDFBox, you can print PDF files using the standard Java printing API.
-
Save as Image - With PDFBox, you can save PDF as an image file, such as PNG or JPEG.
-
Create PDFs - With PDFBox, you can create a new PDF file by creating a Java program, and you can also include images and fonts.
-
Signing - With PDFBox, you can add digital signatures to PDF files.
There is a tutorial that introduces PDFBox in detail. I won't say more here.
https://iowiki.com/pdfbox/pdfbox_quick_guide.htmlIntroduce dependency
<!--start:PDF Get the picture on the first page-->
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>2.0.20</version>
</dependency>
<!--end:PDF Get the picture on the first page-->Business code
/**
* Capture a page in the PDF as a thumbnail and upload (save)
* @param pdfFileName
* @return
*/
public String PDFFramer(String pdfFileName){
//Convert PDF files in the network to file
File file = URLToFile(pdfFileName);
//new File() can only access local files
//Convert local file to file
//File file = new File("C:\Users\Administrator\Downloads \ \ (important must see). pdf");
String pdfUrl="";
try
{
// Open source pdf
log.info("Start interception PDF:");
//The load() method of the PDDocument class is used to load an existing PDF document
PDDocument pdfDocument = PDDocument.load(file);
//The class of PDFRenderer renders PDF documents as AWT BufferedImage
PDFRenderer pdfRenderer = new PDFRenderer(pdfDocument);
// Extracted page number
int pageNumber = 0;
// The BufferedImage object is read and stored at 300 dpi
int dpi = 300;
//The renderImage() method of the Renderer class renders an image in a specific page
BufferedImage buffImage = pdfRenderer.renderImageWithDPI(pageNumber, dpi, ImageType.RGB);
// File type conversion
MultipartFile multipartFile = fileCase(buffImage);
log.info("PDF Start uploading:");
pdfUrl = fileLoad(multipartFile);
log.info("PDF Upload succeeded:{}",pdfUrl);
// close document
pdfDocument.close();
//Delete temporary file
String s = threadLocal.get();
log.info("Directory of temporary files:"+s);
File f=new File(s);
boolean delete = f.delete();
log.info("Delete file"+delete);
}
catch (InvalidPasswordException e)
{
e.printStackTrace();
}
catch (IOException e)
{
e.printStackTrace();
}
return pdfUrl;
}Reading PDF files in the network and file type conversion
/**
* Read PDF files from the network
* @param url
* @return
*/
public File URLToFile(String url){
log.info("read FastDFS Upper PDF");
//Save temporary file -- relative location of jar package
File file1 = new File("Temporary.pdf");
try {
URL url1 = new URL(url);
FileUtils.copyURLToFile(url1,file1);
} catch (IOException e) {
e.printStackTrace();
}
File absoluteFile = file1.getAbsoluteFile();
threadLocal.set(absoluteFile.toString());
log.info("ppt Already stored locally"+absoluteFile.toString());
return file1;
}
/**
* File conversion converts BufferedImage to MultipartFile: for file upload
* @param image
* @return
*/
public static MultipartFile fileCase(BufferedImage image){
//Get BufferedImage object
// BufferedImage bufferedImage = JoinTwoImage.testEncode(200, 200, url);
MultipartFile multipartFile= null;
try {
//Create a ByteArrayOutputStream
ByteArrayOutputStream os = new ByteArrayOutputStream();
//Write BufferedImage to ByteArrayOutputStream
ImageIO.write(image, "jpg", os);
//ByteArrayOutputStream to InputStream
InputStream input = new ByteArrayInputStream(os.toByteArray());
//Convert InputStream to MultipartFile
multipartFile =new MockMultipartFile("file", "file.jpg", "text/plain", input);
} catch (IOException e) {
e.printStackTrace();
}
return multipartFile;
}