Python从PPT文件中提取所有文字到Word

需求

将PPT文件或PPTX文件里面的所有文字提取到一个新的以​​docx​​结尾的Word文件中。

安装Python库

（1）基于Python 3

（2） 运行下方代码安装需要用到的库

pip install python-pptx
pip install python-docx

执行下方Python代码

import collections
import collections.abc
import sys
import os
from pptx import Presentation
import docx

def extract_text(input_file, output_file):
    prs = Presentation(input_file)
    doc = docx.Document()
    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:
                    doc.add_paragraph(run.text)
    doc.save(output_file)

if __name__ == "__main__":
    if len(sys.argv) != 3:
        print("Usage: python main.py <input_file> <output_file>")
        sys.exit()
    input_file = sys.argv[1]
    output_file = sys.argv[2]
    if not input_file.endswith(".pptx") or not output_file.endswith(".docx"):
        print("Error: input file must be .ppt and output file must be .docx")
        sys.exit()
    if not os.path.exists(input_file):
        print("Error: input file does not exist")
        sys.exit()
    extract_text(input_file, output_file)
    print("Text extracted successfully!")