Read PDF file contents and images with PDFBox

Recently read the contents and pictures of the PDF file with PDFBox, you can get the content and pictures of each page, but there is a problem is unable to get the picture in the location of the page. The source code is as follows:

Package com.util;


Import Java.awt.image.BufferedImage;
Import Java.io.BufferedInputStream;
Import Java.io.File;
Import Java.io.FileInputStream;
Import Java.io.InputStream;
Import Java.io.StringWriter;
Import Java.text.SimpleDateFormat;
Import Java.util.Calendar;
Import Java.util.Iterator;
Import java.util.List;
Import Java.util.Map;
Import Java.util.Set;


Import Javax.imageio.ImageIO;


Import Org.apache.pdfbox.pdfparser.PDFParser;
Import org.apache.pdfbox.pdmodel.PDDocument;
Import Org.apache.pdfbox.pdmodel.PDDocumentCatalog;
Import Org.apache.pdfbox.pdmodel.PDPage;
Import org.apache.pdfbox.pdmodel.PDResources;
Import Org.apache.pdfbox.pdmodel.graphics.xobject.PDXObjectImage;
Import Org.apache.pdfbox.util.PDFTextStripper;

public class Pdfboxutil {

try {

InputStream InputStream = new Bufferedinputstream (new FileInputStream (New File ("D:/android/a.pdf"));
Pdfparser parser = new Pdfparser (InputStream);
Parser.parse ();
PDDocument pdfdocument = Pddocument.load (InputStream);
PDDocument pdfdocument = Parser.getpddocument ();
StringWriter writer = new StringWriter ();
Pdftextstripper stripper = new Pdftextstripper ();
Stripper.writetext (pdfdocument, writer);
String contents = Writer.getbuffer (). toString ();

/*
Pddocumentinformation documentinformation = Pdfdocument.getdocumentinformation ();
System.out.println ("title:" + Documentinformation.gettitle ());
Pddocumentinformation info = pdfdocument.getdocumentinformation ();
System.out.println ("title:" + Info.gettitle ());
System.out.println ("Subject:" + info.getsubject ());
System.out.println ("Author:" + Info.getauthor ());
System.out.println ("Keyword:" + info.getkeywords ());
System.out.println ("Application:" + info.getcreator ());
System.out.println ("PDF Production Program:" + Info.getproducer ());
System.out.println ("Author:" + info.gettrapped ());
SYSTEM.OUT.PRINTLN ("Creation time:" + DateFormat (Info.getcreationdate ()));
SYSTEM.OUT.PRINTLN ("Modification Time:" + DateFormat (Info.getmodificationdate ()));
*/


/** Document page Information **/
Pddocumentcatalog cata = Pdfdocument.getdocumentcatalog ();


List pages = Cata.getallpages ();
int count = 1;
for (int i = 0; i < pages.size (); i++) {
Pdpage page = (pdpage) pages.get (i);

if (null! = page) {

Text content on this page
StringWriter SW = new StringWriter ();
Pdftextstripper PST = new Pdftextstripper ();
Pst.setstartpage (i+1);
Pst.setendpage (i+1);
Pst.writetext (Pdfdocument, SW);
String content = Sw.getbuffer (). toString ();
SYSTEM.OUT.PRINTLN (content);

pdresources res = page.findresources ();
Get page picture information
Map IMGs = Res.getimages ();
if (null! = IMGs) {
Set KeySet = Imgs.keyset ();
Iterator it = Keyset.iterator ();
while (It.hasnext ()) {
Object obj = It.next ();
Pdxobjectimage img = (pdxobjectimage) imgs.get (obj);
Img.write2file ("d:/" + count);
count++;
}
}
}
}
} catch (Exception e) {
TODO automatically generates catch blocks
E.printstacktrace ();
}
}


public static String DateFormat (Calendar calendar) throws Exception {
if (null = = Calendar)
return null;
String date = null;
try {
String pattern = "YYYY-MM-DD";
SimpleDateFormat format = new SimpleDateFormat (pattern);
Date = Format.format (Calendar.gettime ());
} catch (Exception e) {
Throw e;
}
return date = = null? "": Date;
}
}

In the end there was no way to convert the contents of each page into pictures. Replace the code with the red part to print each page as a picture.

if (null! = page) {

bufferedimage img1 = Page.converttoimage ();

File File = new file ("d:/" +i+ ". PNG ");
Imageio.write (IMG1, "PNG", file);

}

Environmental net