python 实现提取PPT中所有的文字

# 导入pptx包
from pptx import Presentation
prs = Presentation(path_to_presentation)
text_runs = []
for slide in prs.slides:
 for shape in slide.shapes:
  if not shape.has_text_frame:
   continue
  for paragraph in shape.text_frame.paragraphs:
   for run in paragraph.runs:
    text_runs.append(run.text)

pip install python-pptx

Python 2.6, 2.7, 3.3, 3.4, or 3.6
lxml
Pillow
XlsxWriter (to use charting features)

from pptx     import Presentation
prs = Presentation()
title_slide_layout = prs.slide_layouts[0]
slide = prs.slides.add_slide(title_slide_layout)
title = slide.shapes.title
subtitle = slide.placeholders[1]
title.text = 'Hello world!'
subtitle.text = 'python-pptx was here.'
prs.save(r'd:\temp\test.pptx')
printf("\a")

from pptx import Presentation
from pptx.util import Inches, Pt
prs = Presentation()
blank_slide_layout = prs.slide_layouts[6]
slide = prs.slides.add_slide(blank_slide_layout)
left = top = width = height = Inches(1)
txBox = slide.shapes.add_textbox(left, top, width, height)
tf = txBox.text_frame
tf.text = "This is text inside a textbox"
p = tf.add_paragraph()
p.text = "This is a second paragraph that's bold"
p.font.bold = True
p = tf.add_paragraph()
p.text = "This is a third paragraph that's big"
p.font.size = Pt(40)
prs.save(r'd:\temp\test1.pptx')

pip install python-pptx-interface

from pptx_tools import utils
pptfile = r'D:\Temp\如何搭建自己的电子实验室_20210102R10.pptx'
png_folder = r'd:\temp\pptimage'
utils.save_pptx_as_png(png_folder, pptfile, overwrite_folder=True)