Python实现提取或替换PPT中文本与图片的示例代码

import os
import re,random
from pptx import Presentation

# coding=gbkimport osimport refrom pptx import Presentationimport random
class ExtractPPTXimg():
    def __init__(self,params): 
        self.errFlag = False 
        self.msg = "" 
        self.sourcePath = params["sourcePath"] 
        if not os.path.exists(self.sourcePath): 
            self.errFlag = True 
            self.msg = "源文件夹不存在！" 
        self.targetPath = params["targetPath"] 
        if not os.path.exists(self.targetPath): 
            os.makedirs(self.targetPath) 
            self.run()

    def run(self): 
        if self.errFlag: 
            print(self.msg) 
            return 
        for file in os.listdir(self.sourcePath): 
            if not file[-4:] == "pptx": 
                continue 
            if re.findall("^~",file): 
                continue 
            
            # 提取图片 
            self.extractImg(file)
    # 保存pptx中的图片 
    def extractImg(self,file): 
        fileName,expadName = os.path.splitext(file) 
        prs = Presentation(os.path.join(self.sourcePath,file)) 
        for slide in prs.slides: 
            for shape in slide.shapes: 
                try: 
                    if "image" in shape.image.content_type: 
                        imgName = shape.image.filename 
                        newPath = os.path.join(self.targetPath, fileName) 
                        if not os.path.exists(newPath):  os.makedirs(newPath)  newFile = os.path.join(newPath, imgName)  self.saveImage(newFile,shape.image.blob) 
                except: 
                    continue

    # 保存图片 
    def saveImage(self,newFile,blob): 
        if os.path.exists(newFile): 
            fileName, expadName = os.path.splitext(newFile) 
            newFile = "{}-{}{}".format(fileName,random.randint(1,1000),expadName) 
        with open(newFile, "wb") as f: 
            f.write(blob) 
            print("已保存{}".format(newFile))

    def __str__(self): 
        return self.msg

if __name__ == '__main__': 
    # 要进行提取的pptx的所在目录 "targetPath":r"K:\伍德春原创视频\自动化\2020-11-10\img", # 提取后的txt文件要保存到的目录 
    params = { "sourcePath":r"D:\自动化", "targetPath":r"D:\自动化\img",} 
    newobj = ExtractPPTXimg(params)

from pptx import Presentation
from pptx.enum.shapes import MSO_SHAPE_TYPE
 
def ppt_catch_format_text(filename):
    """
    抓取PPT的内容，按段落返回
    其中 filename 是PPT文件的路径
    """
    search_str = '性能探测器'
    repl_str = '性能探测器PPT啦qqqqqq'
    prs = Presentation(filename)
    for x in range(len(prs.slides)):
        # ---Only on text-boxes outside group elements---
        for shape in prs.slides[x].shapes:
            if hasattr(shape, "text"):
                if(shape.text.find(search_str))!=-1:
                    text_frame = shape.text_frame
                    cur_texts = text_frame.paragraphs[0].runs
                    for index in range(len(cur_texts)):
                        print(text_frame.paragraphs[0].runs[index].text)
                        if(cur_texts[index].text.find(search_str))!=-1: #print(5566) #print(cur_texts[index].text) cur_text = text_frame.paragraphs[0].runs[index].text new_text = cur_text.replace(str(search_str), str(repl_str)) text_frame.paragraphs[0].runs[index].text = new_text
 
        # ---Only operate on group shapes---
        group_shapes = [shp for shp in prs.slides[x].shapes
                        if shp.shape_type ==MSO_SHAPE_TYPE.GROUP]
        #print(group_shapes)
        for group_shape in group_shapes:
            for shape in group_shape.shapes:
                if shape.has_text_frame:
                    if(shape.text.find(search_str))!=-1:
                        text_frame = shape.text_frame
                       # cur_texts = text_frame.paragraphs[0].runs
 
                        for index in range(len(text_frame.paragraphs)): cur_text = text_frame.paragraphs[index].text #print(cur_texts[index].text.encode('utf-8').strip().decode()) if(cur_text.find(search_str))!=-1:     print(7788)     #print(cur_texts[index].text)     new_text = cur_text.replace(str(search_str), str(repl_str))     text_frame.paragraphs[index].text = new_text     #print(cur_text)
    prs.save('D:\自动化\ss.pptx')
 
 
 
ppt_catch_format_text(r"D:\自动化\课件.pptx")