2021-08-27python读取ppt文本内容

huibif

已于 2022-01-28 22:22:15 修改

阅读量374

点赞数 1

分类专栏：学习笔记文章标签： python pycharm

于 2021-08-27 12:55:50 首次发布

本文链接：https://blog.csdn.net/xlionsky/article/details/119950699

版权

学习笔记专栏收录该内容

34 篇文章 0 订阅

订阅专栏

import win32com
from win32com.client import Dispatch, constants
path = "D:\\产品资料\\juicer blender catalogue榨汁机产品画册.pptx"
ppt = win32com.client.Dispatch('PowerPoint.Application')
ppt.Visible = 1
pptSel = ppt.Presentations.Open(path)
# win32com.client.gencache.EnsureDispatch('PowerPoint.Application')

#get the ppt's pages
slide_count = pptSel.Slides.Count
for i in range(1,slide_count + 1):
  shape_count = pptSel.Slides(i).Shapes.Count
  print(shape_count)
  for j in range(1,shape_count + 1):
    if pptSel.Slides(i).Shapes(j).HasTextFrame:
      s = pptSel.Slides(i).Shapes(j).TextFrame.TextRange.Text
      # print (str(s)+ "\n")
      new_path = 'read_ppt.txt'
      with open(new_path,'a',encoding='utf-8') as f:
          f.write(str(s))

ppt.Quit()