import java.io.File;
import java.io.FileOutputStream;
import java.io.OutputStream;
import com.itextpdf.text.Document;
import com.itextpdf.text.Paragraph;
import com.itextpdf.text.pdf.PdfWriter;
public class GeneratePDF {
public static void main(String[] args) {
try {
String k = "<html><body> This is my Project </body></html>";
OutputStream file = new FileOutputStream(new File("E:\\Test.pdf"));
Document document = new Document();
PdfWriter.getInstance(document, file);
document.open();
document.add(new Paragraph(k));
document.close();
file.close();
} catch (Exception e) {
e.printStackTrace();
}
}
}
This is my code to convert HTML to PDF. I am able to convert it but in PDF file it saves as whole HTML while I need to display only text. <html><body> This is my Project </body></html>
gets saved to PDF while it should save only This is my Project
.
You can do it with the HTMLWorker
class (deprecated) like this:
import com.itextpdf.text.html.simpleparser.HTMLWorker;
//...
try {
String k = "<html><body> This is my Project </body></html>";
OutputStream file = new FileOutputStream(new File("C:\\Test.pdf"));
Document document = new Document();
PdfWriter.getInstance(document, file);
document.open();
HTMLWorker htmlWorker = new HTMLWorker(document);
htmlWorker.parse(new StringReader(k));
document.close();
file.close();
} catch (Exception e) {
e.printStackTrace();
}
or using the XMLWorker
, (download from this jar) using this code:
import com.itextpdf.tool.xml.XMLWorkerHelper;
//...
try {
String k = "<html><body> This is my Project </body></html>";
OutputStream file = new FileOutputStream(new File("C:\\Test.pdf"));
Document document = new Document();
PdfWriter writer = PdfWriter.getInstance(document, file);
document.open();
InputStream is = new ByteArrayInputStream(k.getBytes());
XMLWorkerHelper.getInstance().parseXHtml(writer, document, is);
document.close();
file.close();
} catch (Exception e) {
e.printStackTrace();
}