Python实现从PPT提取图片和文本

pip install Spire.Presentation

from spire.presentation.common import *
from spire.presentation import *

# 创建 Presentation 实例
ppt = Presentation()

# 加载 PowerPoint 文档
ppt.LoadFromFile("sample.pptx")

# 遍历文档中的所有图片
for i, image in enumerate(ppt.Images):
    # 提取并保存图片
    ImageName = "ExtractImage/Images_" + str(i) + ".png"
    image.Image.Save(ImageName)

ppt.Dispose()

from spire.presentation import *
from spire.presentation.common import *

# 创建 Presentation 对象
pres = Presentation()

# 加载 PowerPoint 演示文稿
pres.LoadFromFile("Sample.pptx")

text = []
# 遍历每一张幻灯片
for slide in pres.Slides:
    # 遍历每个形状
    for shape in slide.Shapes:
        # 判断形状是否为 IAutoShape 类型（可包含文本）
        if isinstance(shape, IAutoShape):
            # 提取形状中的文本
            for paragraph in shape.TextFrame.Paragraphs:
                text.append(paragraph.Text)

# 将提取的文本写入文件
with open("output/SlideText.txt", "w", encoding='utf-8') as f:
    for s in text:
        f.write(s + "\n")

pres.Dispose()

pip install python-pptx pillow

import os
from pptx import Presentation
from pptx.enum.shapes import MSO_SHAPE_TYPE
from PIL import Image
import io
def extract_text_and_images(pptx_path, output_dir="extracted"):
    """
    从 PPTX 文件中提取所有文本和图片
    :param pptx_path: PPTX 文件路径
    :param output_dir: 输出目录（文本文件和图片文件夹）
    """
    # 创建输出目录
    os.makedirs(output_dir, exist_ok=True)
    img_dir = os.path.join(output_dir, "images")
    os.makedirs(img_dir, exist_ok=True)
    # 加载 PPT
    prs = Presentation(pptx_path)
    # 用于保存所有文本的列表
    all_text = []
    # 遍历每一张幻灯片
    for slide_idx, slide in enumerate(prs.slides, start=1):
        slide_text = []
        slide_text.append(f"--- 幻灯片 {slide_idx} ---")
        # 遍历幻灯片中的所有形状
        for shape in slide.shapes:
            # --- 提取文本 ---
            # 1. 文本框或自选图形中的文本
            if shape.has_text_frame:
                for paragraph in shape.text_frame.paragraphs:
                    for run in paragraph.runs:
                        if run.text.strip():
                            slide_text.append(run.text)
            # 2. 表格中的文本
            if shape.has_table:
                table = shape.table
                for row in table.rows:
                    row_text = []
                    for cell in row.cells:
                        if cell.text.strip():
                            row_text.append(cell.text.strip())
                    if row_text:
                        slide_text.append(" | ".join(row_text))
            # 3. 图表中的文本（简单提取标题）
            if shape.has_chart:
                chart = shape.chart
                if chart.has_title:
                    title = chart.chart_title.text_frame.text
                    if title.strip():
                        slide_text.append(f"图表标题: {title}")
            # --- 提取图片 ---
            if shape.shape_type == MSO_SHAPE_TYPE.PICTURE:
                # 获取图片的二进制数据
                image_stream = shape.image.blob
                # 生成图片文件名
                img_filename = f"slide_{slide_idx}_img_{shape.shape_id}.png"
                img_path = os.path.join(img_dir, img_filename)
                # 使用 Pillow 保存图片
                img = Image.open(io.BytesIO(image_stream))
                img.save(img_path)
                slide_text.append(f"[图片已保存: {img_path}]")
        # 将当前幻灯片的文本加入总文本
        all_text.extend(slide_text)
        all_text.append("")  # 空行分隔
    # 保存所有文本到文件
    txt_path = os.path.join(output_dir, "extracted_text.txt")
    with open(txt_path, "w", encoding="utf-8") as f:
        f.write("\n".join(all_text))
    print(f"提取完成！")
    print(f"文本保存至: {txt_path}")
    print(f"图片保存至: {img_dir}")
# 使用示例
if __name__ == "__main__":
    extract_text_and_images("example.pptx", output_dir="my_extraction")