Extract Text from PowerPoint Presentations in Java

readme.md

Read the complete article on how to extract text from PowerPoint presentations using Java: https://blog.aspose.com/2021/07/28/extract-text-from-powerpoint-files-using-java/

extract-text-from-presentation.java

//Instatiate PresentationEx class that represents a PPTX file
Presentation pptxPresentation = new Presentation("presentation.pptx");

//Get an Array of ITextFrame objects from the first slide
ITextFrame[] textFrames = SlideUtil.getAllTextFrames(pptxPresentation, true);

//Loop through the Array of TextFrames
for (int i = 0; i < textFrames.length; i++)
{
    //Loop through paragraphs in current TextFrame
    for (IParagraph para : textFrames[i].getParagraphs())
    {
        //Loop through portions in the current Paragraph
        for (IPortion port : para.getPortions())
        {
            //Display text in the current portion
            System.out.println(port.getText());
        }
    }
}

extract-text-from-slide.java

//Instatiate PresentationEx class that represents a PPTX file
Presentation pptxPresentation = new Presentation("presentation.pptx");

//Get an Array of ITextFrame objects from the first slide
ITextFrame[] textFramesSlideOne = SlideUtil.getAllTextBoxes(pptxPresentation.getSlides().get_Item(1));

//Loop through the Array of TextFrames
for (int i = 0; i < textFramesSlideOne.length; i++)
{
    //Loop through paragraphs in current TextFrame
    for (IParagraph para : textFramesSlideOne[i].getParagraphs())
    {
        //Loop through portions in the current Paragraph
        for (IPortion port : para.getPortions())
        {
            //Display text in the current portion
            System.out.println(port.getText());

            //Display font height of the text
            System.out.println(port.getPortionFormat().getFontHeight());

            //Display font name of the text
            System.out.println(port.getPortionFormat().getLatinFont().getFontName());
        }
    }
}