Develop Reference

Extract Only Images from PDF File in java using Apache Tika or PDFBox? [duplicate]

I m trying to extract images from a pdf using pdfbox. The example pdf here
But i m getting blank images only.
The code i m trying:-
public static void main(String[] args) {
PDFImageExtract obj = new PDFImageExtract();
try {
obj.read_pdf();
} catch (IOException ex) {
System.out.println("" + ex);
}
}
void read_pdf() throws IOException {
PDDocument document = null;
try {
document = PDDocument.load("C:\\Users\\Pradyut\\Documents\\MCS-034.pdf");
} catch (IOException ex) {
System.out.println("" + ex);
}
List pages = document.getDocumentCatalog().getAllPages();
Iterator iter = pages.iterator();
int i =1;
String name = null;
while (iter.hasNext()) {
PDPage page = (PDPage) iter.next();
PDResources resources = page.getResources();
Map pageImages = resources.getImages();
if (pageImages != null) {
Iterator imageIter = pageImages.keySet().iterator();
while (imageIter.hasNext()) {
String key = (String) imageIter.next();
PDXObjectImage image = (PDXObjectImage) pageImages.get(key);
image.write2file("C:\\Users\\Pradyut\\Documents\\image" + i);
i ++;
}
}
}
}
Thanks

Here is code using PDFBox 2.0.1 that will get a list of all images from the PDF. This is different than the other code in that it will recurse through the document instead of trying to get the images from the top level.
public List<RenderedImage> getImagesFromPDF(PDDocument document) throws IOException {
List<RenderedImage> images = new ArrayList<>();
for (PDPage page : document.getPages()) {
images.addAll(getImagesFromResources(page.getResources()));
}
return images;
}
private List<RenderedImage> getImagesFromResources(PDResources resources) throws IOException {
List<RenderedImage> images = new ArrayList<>();
for (COSName xObjectName : resources.getXObjectNames()) {
PDXObject xObject = resources.getXObject(xObjectName);
if (xObject instanceof PDFormXObject) {
images.addAll(getImagesFromResources(((PDFormXObject) xObject).getResources()));
} else if (xObject instanceof PDImageXObject) {
images.add(((PDImageXObject) xObject).getImage());
}
}
return images;
}

The below GetImagesFromPDF java class get all images in 04-Request-Headers.pdf file and save those files into destination folder PDFCopy.
import java.io.File;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDResources;
import org.apache.pdfbox.pdmodel.graphics.xobject.PDXObjectImage;
#SuppressWarnings({ "unchecked", "rawtypes", "deprecation" })
public class GetImagesFromPDF {
public static void main(String[] args) {
try {
String sourceDir = "C:/PDFCopy/04-Request-Headers.pdf";// Paste pdf files in PDFCopy folder to read
String destinationDir = "C:/PDFCopy/";
File oldFile = new File(sourceDir);
if (oldFile.exists()) {
PDDocument document = PDDocument.load(sourceDir);
List<PDPage> list = document.getDocumentCatalog().getAllPages();
String fileName = oldFile.getName().replace(".pdf", "_cover");
int totalImages = 1;
for (PDPage page : list) {
PDResources pdResources = page.getResources();
Map pageImages = pdResources.getImages();
if (pageImages != null) {
Iterator imageIter = pageImages.keySet().iterator();
while (imageIter.hasNext()) {
String key = (String) imageIter.next();
PDXObjectImage pdxObjectImage = (PDXObjectImage) pageImages.get(key);
pdxObjectImage.write2file(destinationDir + fileName+ "_" + totalImages);
totalImages++;
}
}
}
} else {
System.err.println("File not exists");
}
} catch (Exception e) {
e.printStackTrace();
}
}
}

For PDFBox 2.0.1, pudaykiran's answer must be slightly modified since some APIs have been changed.
public static void testPDFBoxExtractImages() throws Exception {
PDDocument document = PDDocument.load(new File("D:/Temp/Test.pdf"));
PDPageTree list = document.getPages();
for (PDPage page : list) {
PDResources pdResources = page.getResources();
for (COSName c : pdResources.getXObjectNames()) {
PDXObject o = pdResources.getXObject(c);
if (o instanceof org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject) {
File file = new File("D:/Temp/" + System.nanoTime() + ".png");
ImageIO.write(((org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject)o).getImage(), "png", file);
}
}
}
}

Just add the .jpeg to the end of your path:
image.write2file("C:\\Users\\Pradyut\\Documents\\image" + i + ".jpeg");
That works for me.

You can use PDPage.convertToImage() function which can convert the PDF page into a BufferedImage. Next you can use the BufferedImage to create an Image.
Use the following reference for further detail:
All PDF realated classes in PDFBox you can get in
Apache PDFBox 1.8.3 API
Here you can see PDPage related documentation.
And do not forget to look for PDPage.convertToImage() function in PDPage class.

This is a kotlin version of #Matt's answer.
fun <R> PDResources.onImageResources(block: (RenderedImage) -> (R)): List<R> =
this.xObjectNames.flatMap {
when (val xObject = this.getXObject(it)) {
is PDFormXObject -> xObject.resources.onImageResources(block)
is PDImageXObject -> listOf(block(xObject.image))
else -> emptyList()
}
}
You can use it on PDPage Resources like this:
page.resources.onImageResources { image ->
Files.createTempFile("image", "xxx").also { path->
if(!ImageIO.write(it, "xxx", file.toFile()))
IllegalStateException("Couldn't write image to file")
}
}
Where "xxx" is the format you need (like "jpeg")

For someone who want just copy and paste this ready to use code
import org.apache.pdfbox.contentstream.PDFStreamEngine;
import org.apache.pdfbox.contentstream.operator.Operator;
import org.apache.pdfbox.cos.COSBase;
import org.apache.pdfbox.cos.COSName;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.graphics.PDXObject;
import org.apache.pdfbox.pdmodel.graphics.form.PDFormXObject;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;
import java.util.List;
import java.util.UUID;
public class ExtractImagesUseCase extends PDFStreamEngine{
private final String filePath;
private final String outputDir;
// Constructor
public ExtractImagesUseCase(String filePath,
String outputDir){
this.filePath = filePath;
this.outputDir = outputDir;
}
// Execute
public void execute(){
try{
File file = new File(filePath);
PDDocument document = PDDocument.load(file);
for(PDPage page : document.getPages()){
processPage(page);
}
}catch(IOException e){
e.printStackTrace();
}
}
#Override
protected void processOperator(Operator operator, List<COSBase> operands) throws IOException{
String operation = operator.getName();
if("Do".equals(operation)){
COSName objectName = (COSName) operands.get(0);
PDXObject pdxObject = getResources().getXObject(objectName);
if(pdxObject instanceof PDImageXObject){
// Image
PDImageXObject image = (PDImageXObject) pdxObject;
BufferedImage bImage = image.getImage();
// File
String randomName = UUID.randomUUID().toString();
File outputFile = new File(outputDir,randomName + ".png");
// Write image to file
ImageIO.write(bImage, "PNG", outputFile);
}else if(pdxObject instanceof PDFormXObject){
PDFormXObject form = (PDFormXObject) pdxObject;
showForm(form);
}
}
else super.processOperator(operator, operands);
}
}
Demo
public class ExtractImageDemo{
public static void main(String[] args){
String filePath = "C:\\Users\\John\\Downloads\\Documents\\sample-file.pdf";
String outputDir = "C:\\Users\\John\\Downloads\\Documents\\Output";
ExtractImagesUseCase useCase = new ExtractImagesUseCase(
filePath,
outputDir
);
useCase.execute();
}
}

Instead of calling
image.write2file("C:\\Users\\Pradyut\\Documents\\image" + i);
You can use the ImageIO.write() static method to write the RGB image out in whatever format you need. Here I've used PNG:
File outputFile = new File( "C:\\Users\\Pradyut\\Documents\\image" + i + ".png");
ImageIO.write( image.getRGBImage(), "png", outputFile);

How change pdf file in image (jpeg, jpg ) format and crop

How to convert pdf file to image(jpg ,jpeg..) format and how to crop the image as well. Any pointers(any existing API maybe)?
import java.io.File;
public class PDFtoJPGConverter {
public static void main(String[] args)
{
try
{
PDFDocument doc = new PDFDocument();
doc.loadPDF("Sample.pdf");
int pageCount = doc.getPageCount();
for(int i = 0; i < pageCount; i++)
{
BufferedImage image = doc.toImage(i);
ImageIO.write(image,"jpg", new File("output"+ i +".jpg"));
}
}
catch (Exception e) {
e.printStackTrace();
}
}
}

You could try pdf-renderer it is a pure java solution.
Code Solution:
package com.pdf.pdfbox.examples;
import java.awt.image.BufferedImage;
import java.io.File;
import java.util.List;
import javax.imageio.ImageIO;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
#SuppressWarnings("unchecked")
public class ConvertPDFPagesToImages {
public static void main(String[] args) {
try {
String sourceDir = "C:/Documents/04-Request-Headers.pdf"; // Pdf files are read from this folder
String destinationDir = "C:/Documents/Converted_PdfFiles_to_Image/"; // converted images from pdf document are saved here
File sourceFile = new File(sourceDir);
File destinationFile = new File(destinationDir);
if (!destinationFile.exists()) {
destinationFile.mkdir();
System.out.println("Folder Created -> "+ destinationFile.getAbsolutePath());
}
if (sourceFile.exists()) {
System.out.println("Images copied to Folder: "+ destinationFile.getName());
PDDocument document = PDDocument.load(sourceDir);
List<PDPage> list = document.getDocumentCatalog().getAllPages();
System.out.println("Total files to be converted -> "+ list.size());
String fileName = sourceFile.getName().replace(".pdf", "");
int pageNumber = 1;
for (PDPage page : list) {
BufferedImage image = page.convertToImage();
File outputfile = new File(destinationDir + fileName +"_"+ pageNumber +".png");
System.out.println("Image Created -> "+ outputfile.getName());
ImageIO.write(image, "png", outputfile);
pageNumber++;
}
document.close();
System.out.println("Converted Images are saved at -> "+ destinationFile.getAbsolutePath());
} else {
System.err.println(sourceFile.getName() +" File not exists");
}
} catch (Exception e) {
e.printStackTrace();
}
}
}

iText Java - Can't get the image show on pdf on html header

I am following this example HtmlHeaderFooter.java
for creating a pdf file that has the same header and footers on each page but for some reason i can't get the image to display on pdf. It's just blank where it needs to show the image.
I tried moving the image on every single folder in case it's a path issue but no luck on that either.
Here is an example of my code below.
package amt.view.PDF.section0;
import amt.Methods;
import com.itextpdf.text.*;
import com.itextpdf.text.pdf.*;
import com.itextpdf.tool.xml.*;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.sql.Connection;
import java.sql.ResultSet;
import java.sql.SQLException;
public class section0 {
static String Customer;
static String CustomerTitle;
static String RefNo;
static String Revision;
static String RefNoTitle;
public static String DEST;
public static final String UserDesktop = System.getProperty("user.home") + "/Desktop";
static String selectedID = "1";
public static void getVariables() throws SQLException {
Connection c = Methods.chooseConnection();
String SQL = "SELECT * FROM preset_values WHERE ID LIKE '" + selectedID + "'";
ResultSet rs = c.createStatement().executeQuery(SQL);
while (rs.next()) {
Customer = rs.getString("Customer");
RefNo = rs.getString("Reference_No");
CustomerTitle = rs.getString("Customer").replace(" ", "_");
RefNoTitle = rs.getString("Reference_No").replace(" ", "_");
Revision = rs.getString("Revision");
}
DEST = UserDesktop + "/" + CustomerTitle + "-" + RefNoTitle + "_Rev-" + Revision + ".pdf";
}
public static final String HEADER = "<table width=\"100%\" border=\"0\"><tr><td><img src=\"logo.png\" /></td><td align=\"right\">Some title</td></tr></table>";
public static final String FOOTER = "<table width=\"100%\" border=\"0\"><tr><td>Footer</td><td align=\"right\">Some title</td></tr></table>";
public class HeaderFooter extends PdfPageEventHelper {
protected ElementList header;
protected ElementList footer;
public HeaderFooter() throws IOException {
header = XMLWorkerHelper.parseToElementList(HEADER, "../headerfooter.css");
footer = XMLWorkerHelper.parseToElementList(FOOTER, null);
}
#
Override
public void onEndPage(PdfWriter writer, Document document) {
try {
ColumnText ct = new ColumnText(writer.getDirectContent());
ct.setSimpleColumn(new Rectangle(36, 832, 559, 810));
header.stream().forEach((e) - > {
ct.addElement(e);
});
ct.go();
ct.setSimpleColumn(new Rectangle(36, 10, 559, 32));
footer.stream().forEach((e) - > {
ct.addElement(e);
});
ct.go();
} catch (DocumentException de) {
throw new ExceptionConverter(de);
}
}
}
public static void main(String[] args) throws IOException, DocumentException, SQLException {
getVariables();
File file = new File(DEST);
file.getParentFile().mkdirs();
new section0().createPdf(DEST);
}
public void createPdf(String filename) throws IOException, DocumentException {
// step 1
Document document = new Document(PageSize.A4, 36, 36, 36, 72);
// step 2
PdfWriter writer = PdfWriter.getInstance(document, new FileOutputStream(filename));
writer.setPageEvent(new HeaderFooter());
// step 3
document.open();
// step 4
for (int i = 0; i < 50; i++)
document.add(new Paragraph(Customer + "\n" + RefNo));
// step 5
document.close();
}
}

Finding text in a PDF document with the same font properties in PDFBox

I am new to Java and PDFBox. I am trying to find words in a PDF document, store its font properties (font family, XScale, font size etc.) in variables and then find other words with the same font properties using the previously stored values. What should I do with processTextPosition() to show font properties of String "References"?
Here is my code:
package pdfinjava;
import java.io.*;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.common.PDStream;
import org.apache.pdfbox.util.PDFTextStripper;
import org.apache.pdfbox.util.TextPosition;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
class reference extends PDFTextStripper {
static ArrayList<String> boldWordList=new ArrayList<String>();
String boldWord="";
String c="";
public reference() throws IOException {
super.setSortByPosition(true);
}
public static void main(String[] args) throws Exception {
PDDocument document = null;
try {
File input = new File("C:\\abc.pdf");
document = PDDocument.load(input);
// File output=new File("D:/acadmic/7/research/pdf/2.txt");
PDFTextStripper s=new PDFTextStripper();
String content = s.getText(document);
int n= content.indexOf("References");
String c = content.substring(n, n+10);
System.out.println(c);
reference printer = new reference();
List allPages = document.getDocumentCatalog().getAllPages();
for (int i = 0; i < allPages.size(); i++) {
PDPage page = (PDPage) allPages.get(i);
//System.out.println("Processing page: " + i);
PDStream contents = page.getContents();
if (contents != null) {
printer.processStream(page, page.findResources(), page.getContents().getStream());
}
}
} finally {
if (document != null) {
document.close();
}
}
}
/**
* #param text The text to be processed
*/
#Override
protected void processTextPosition(TextPosition text) {
if(text.getFont().getFontDescriptor().isForceBold()){
boldWord+=text;
//System.out.println(text);
System.out.println("String["+ text.getXDirAdj() + ","
+ text.getYDirAdj() + " Font Size=" + text.getFontSize()
+ " Font Family=" + text.getFont().getFontDescriptor().getFontName()
+ " xscale=" + text.getXScale() + " height=" + text.getHeightDir()
+ " space=" + text.getWidthOfSpace() + " width="+ text.getWidthDirAdj()
+ "]" + text.getCharacter());
}
}
}

itext Converting PDF to csv

I am trying to use itext framework to convert a pdf file into a csv for import into excel.
The output is garbled and I pressume I am missing a step in regards to format conversion however I can't seem to find the information in the itext site and am looking for assistance.
Current is as below.
package com.pdf.convert;
import java.io.FileOutputStream;
import java.io.IOException;
import com.itextpdf.text.Document;
import com.itextpdf.text.DocumentException;
import com.itextpdf.text.Image;
import com.itextpdf.text.pdf.PdfImportedPage;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.PdfWriter;
public class ThirdPDF {
private static String INPUTFILE = "/location/test.pdf";
private static String OUTPUTFILE = "/location/test.csv";
public static void main(String[] args) throws DocumentException,
IOException {
Document document = new Document();
PdfWriter writer = PdfWriter.getInstance(document,
new FileOutputStream(OUTPUTFILE));
document.open();
PdfReader reader = new PdfReader(INPUTFILE);
int n = reader.getNumberOfPages();
PdfImportedPage page;
// Go through all pages
for (int i = 1; i <= n; i++) {
// Only page number 2 will be included
if (i == 2) {
page = writer.getImportedPage(reader, i);
Image instance = Image.getInstance(page);
document.add(instance);
}
}
document.close();
}
}

Converting PDF file to CSV file.
Present Directory and File creation is based on Android Framework.
Change your path and Directory as per your Framework Accordingly.
private void convertPDFToCSV(String pdfFilePath) {
String myfolder = Environment.getExternalStorageDirectory() + "/Mycsv";
if (createFolder(myfolder)) {
try {
Document document = new Document();
document.open();
FileOutputStream fos=new FileOutputStream(myfolder + "/MyCSVFile.csv");
StringBuilder parsedText=new StringBuilder();
PdfReader reader1 = new PdfReader(pdfFilePath);
int n = reader1.getNumberOfPages();
for (int i = 0; i <n ; i++) {
parsedText.append(parsedText+PdfTextExtractor.getTextFromPage(reader1, i+1).trim()+"\n") ;
//Extracting the content fromx the different pages
}
StringReader stReader = new StringReader(parsedText.toString());
int t;
while((t=stReader.read())>0)
fos.write(t);
document.close();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}
private boolean createFolder(String myfolder) {
File f = new File(myfolder);
if (!f.exists()) {
if (!f.mkdir()) {
return false;
} else {
return true;
}
}else{
return true;
}
}