使用 Python 从 PPT 演示文稿中提取文本和图像

import aspose.slides as slides

#Instatiate Presentation class that represents a PPT file
with slides.Presentation("pres.ppt") as pptxPresentation:
    # Get an Array of ITextFrame objects from all slides in the PPT
    textFramesPPTX = slides.util.SlideUtil.get_all_text_frames(pptxPresentation, True)
    
    # Loop through the Array of TextFrames
    for i in range(len(textFramesPPTX)):
	    # Loop through paragraphs in current ITextFrame
        for para in textFramesPPTX[i].paragraphs:
            # Loop through portions in the current IParagraph
            for port in para.portions:
			    # Display text in the current portion
                print(port.text)

    			# Display font height of the text
                print(port.portion_format.font_height)

			    # Display font name of the text
                if port.portion_format.latin_font != None:
                    print(port.portion_format.latin_font.font_name)