Read & Extract Text from PowerPoint Presentation PPTX Files

				
//**************************************
// Name: Read & Extract Text from PowerPoint Presentation PPTX Files
// Description:<p><font face="Arial, Helvetica, sans-serif">TIn this technical tip, we will learn to <a href="http://www.aspose.com/docs/display/slidesjava/Extracting+Text+from+the+Presentation+%28PPTX%29"><strong>extract text from different slide shapes inside PowerPoint 2007 presentations </strong></a>by using Aspose.Slides for Java. We will extract text from slide shapes like Placeholders, Auto Shapes, Group Shapes and tables etc.<br />
Below is code example that can traverse through each shape belonging to every slide inside a PPTX presentation and extract text from that on portion level. Since, text is extracted on portion level, so its font related properties will be preserved.</font></p>
<p><font face="Arial, Helvetica, sans-serif"><strong>Extracting text from a slide</strong></font></p>
// By: aspose_seo
//
//This code is copyrighted and has// limited warranties.Please see http://www.Planet-Source-Code.com/vb/scripts/ShowCode.asp?txtCodeId=7028&lngWId=2//for details.//**************************************

import com.aspose.slides.pptx.*;
public class TextExtract{
 public static void ReadText(TextFrameEx TxtFrame)
 {
String prText="";
for(int pgCount=0;pgCount<TxtFrame.getParagraphs().size();pgCount++)
{
	ParagraphEx Paragraph=TxtFrame.getParagraphs().get(pgCount);
	for(int prCount=0;prCount<Paragraph.getPortions().size();prCount++)
{
	prText=Paragraph.getPortions().get(prCount).getText();
 System.out.println(prText+"\n");
	 }//End Portion Loop
}//End Paragraphs Loop
 }
	
 public static void main(String[] args) 
 {
try{
	 //Opening presentation
PresentationEx presentation=new PresentationEx("D:\\ppt\\TestPresentation.pptx");
	//Traversing through all slides
	SlideEx slide;
	ShapesEx shps;
		
	for (int index=0;index<presentation.getSlides().size();index++)
	{
	//Accessing Slides
	slide = presentation.getSlides().get(index);
	//Accessing all shapes in slide
	shps=slide.getShapes();
	ShapeEx shape;	
	//Traversing through all shapes
	for (int shpCount = 0; shpCount < shps.size(); shpCount++) 
 {
	 shape= shps.get(shpCount);
 if(shape.getPlaceholder() != null)
 {
		//Getting AutoShape from group shapes set
AutoShapeEx aShape = (AutoShapeEx)shape;
		if (aShape.getTextFrame() != null)
		{
		//Accessing the text frame of shape
		TextFrameEx tfText=aShape.getTextFrame();
		ReadText(tfText);
		}//End Text Frame IF
 }//End AutoShape Check
	 else if(shape instanceof AutoShapeEx )
 {
		//Getting AutoShape from group shapes set
AutoShapeEx aShp = (AutoShapeEx)shape;
 		if (aShp.getTextFrame() != null)
		{
		//Accessing the text frame of shape
 TextFrameEx tfText=aShp.getTextFrame();
		ReadText(tfText);
}//End Text Frame IF
 }//End AutoShape Check
	 //If shape is a group shape
	 else if(shape instanceof GroupShapeEx)
	 {
		//Type casting shape to group shape
		GroupShapeEx gShape = (GroupShapeEx)shape;
		//Traversing through all shapes in group shape
		for (int iCount=0;iCount< gShape.getShapes().size();iCount++)
		{
		if(gShape.getShapes().get(iCount) instanceof AutoShapeEx)
		{
		 //Getting AutoShape from group shapes set
		 AutoShapeEx aShp = (AutoShapeEx)gShape.getShapes().get(iCount);
 		 if (aShp.getTextFrame() != null)
		 {
			TextFrameEx tfText=aShp.getTextFrame();
			ReadText(tfText);
}//End Text Frame IF
		}
		}
	 }
	 //If shape is instance of Table
	 else if(shape instanceof TableEx)
	 { 
		 TableEx tTable=(TableEx)shape;
		 for(int iCol=0;iCol<tTable.getColumns().size();iCol++)
		 {
		for(int iRow=0;iRow<tTable.getRows().size();iRow++)
		{
		 TextFrameEx tfText=tTable.get(iCol,iRow).getTextFrame();
		 if(tfText!=null)
			ReadText(tfText);
		}//End Row Loop
		 }//End Col Loop
	}//End Group Shape IF
					
}//End Shape Loop
 }//End Slide Traversal
	}
	catch(Exception e)
	{
		e.printStackTrace();
	}
	
 }
}