通过Python拉取PowerPoint文本属性

pip install python-pptx

from pptx import Presentation

def get_text_properties(presentation_path):
    prs = Presentation(presentation_path)
    text_properties = []

    for slide in prs.slides:
        for shape in slide.shapes:
            if shape.has_text_frame:
                text_frame = shape.text_frame
                for paragraph in text_frame.paragraphs:
                    for run in paragraph.runs:
                        text_properties.append({
                            'text': run.text,
                            'font_name': run.font.name,
                            'font_size': run.font.size.pt,
                            'bold': run.font.bold,
                            'italic': run.font.italic,
                            'underline': run.font.underline,
                            'color': run.font.color.rgb,
                            'alignment': paragraph.alignment,
                            'bullet': paragraph.level,
                            'slide_number': slide.slide_number
                        })

    return text_properties

# 调用函数并传入PowerPoint文件路径
text_properties = get_text_properties('presentation.pptx')

# 打印文本属性
for property in text_properties:
    print(property)