使用Python从PPT文档中提取图片和图片信息(如坐标、宽度和高度等)

pip install spire.presentation

from spire.presentation import *
import os
 
def extract_background_images_from_slides(ppt_path, output_folder):
    """从幻灯片中提取背景图片"""
    presentation = Presentation()
    presentation.LoadFromFile(ppt_path)
    os.makedirs(output_folder, exist_ok=True)
 
    for i, slide in enumerate(presentation.Slides):
        bgd = slide.SlideBackground
        if bgd.Fill.FillType == FillFormatType.Picture:
            image_data = bgd.Fill.PictureFill.Picture.EmbedImage
            output_path = os.path.join(output_folder, f"幻灯片背景_{i}.png")
            image_data.Image.Save(output_path)
 
    presentation.Dispose()
 
# 使用示例
extract_background_images_from_slides("测试.pptx", "图片")

from spire.presentation import *
import os
 
def extract_background_images_from_slide_masters(ppt_path, output_folder):
    """从幻灯片母版中提取背景图片"""
    presentation = Presentation()
    presentation.LoadFromFile(ppt_path)
    os.makedirs(output_folder, exist_ok=True)
 
    for i, slide_master in enumerate(presentation.Masters):
        bgd = slide_master.SlideBackground
        if bgd.Fill.FillType == FillFormatType.Picture:
            image_data = bgd.Fill.PictureFill.Picture.EmbedImage
            output_path = os.path.join(output_folder, f"幻灯片母版背景_{i}.png")
            image_data.Image.Save(output_path)
 
    presentation.Dispose()
 
# 使用示例
extract_background_images_from_slide_masters("测试.pptx", "图片")

from spire.presentation import *
import os
 
def extract_images_from_shapes(ppt_path, output_folder):
    """从幻灯片形状中提取图片"""
    presentation = Presentation()
    presentation.LoadFromFile(ppt_path)
    os.makedirs(output_folder, exist_ok=True)
 
    img_count = 0
 
    for slide_index, slide in enumerate(presentation.Slides):
        for shape_index, shape in enumerate(slide.Shapes):
            if isinstance(shape, PictureShape):
                image_data = shape.EmbedImage
            elif isinstance(shape, SlidePicture):
                image_data = shape.PictureFill.Picture.EmbedImage
            else:
                continue
 
            img_count += 1
            output_path = os.path.join(output_folder, f"图片_{img_count}.png")
            image_data.Image.Save(output_path)
 
    presentation.Dispose()

from spire.presentation import *
 
def extract_image_metadata(ppt_path):
    """获取 PPT 中图片的信息（所在幻灯片、坐标位置、宽度与高度等）"""
    presentation = Presentation()
    presentation.LoadFromFile(ppt_path)
 
    for slide_index, slide in enumerate(presentation.Slides):
        for shape_index, shape in enumerate(slide.Shapes):
            if isinstance(shape, PictureShape) or isinstance(shape, SlidePicture):
                x = shape.Frame.Rectangle.X
                y = shape.Frame.Rectangle.Y
                width = shape.Frame.Rectangle.Width
                height = shape.Frame.Rectangle.Height
                print(f"幻灯片 {slide_index + 1}，形状 {shape_index + 1}：X={x}, Y={y}, 宽度={width}, 高度={height}")
 
    presentation.Dispose()
 
# 使用示例
extract_image_metadata("测试.pptx")

from spire.presentation import *
import os
 
def extract_images_from_presentation(ppt_path, output_folder):
    """提取整个PPT文档中的图片"""
    presentation = Presentation()
    presentation.LoadFromFile(ppt_path)
    os.makedirs(output_folder, exist_ok=True)
 
    for i, image in enumerate(presentation.Images):
        output_path = os.path.join(output_folder, f"图片_{i}.png")
        image.Image.Save(output_path)
 
    presentation.Dispose()
 
# 使用示例
extract_images_from_presentation("测试.pptx", "图片")