Python实现提取Word文档中的文本和图片

pip install Spire.Doc

from turtle import st
from spire.doc import *
from spire.doc.common import *

def WriteAllText(fname:str,text:List[str]):
        fp = open(fname,"w")
        for s in text:
            fp.write(s)
        fp.close()

inputFile = "示例.docx"
outputFile =  "获取的文本.txt"
     
#创建Document的对象
document = Document()

#载入Word文档
document.LoadFromFile(inputFile)

#获取文档中的文本
text = document.GetText()

#将文本写入文本文件
WriteAllText(outputFile, text)
document.Close()

import queue
from spire.doc import *
from spire.doc.common import *
import os

outputPath = "Images/"
inputFile = "示例.docx"

if not os.path.exists(outputPath):
    os.makedirs(outputPath)

#创建Document的对象
document = Document()

#载入Word文档
document.LoadFromFile(inputFile)

#创建一个队列并将文档元素放入其中
nodes = queue.Queue()
nodes.put(document)

#创建一个列表
images = []

#循环遍历文档元素
while nodes.qsize() > 0:
    node = nodes.get()
    for i in range(node.ChildObjects.Count):
        #获取文档元素的子对象
        child = node.ChildObjects.get_Item(i)
        #判断子对象是否为图片
        if child.DocumentObjectType == DocumentObjectType.Picture:
            picture = child if isinstance(child, DocPicture) else None
            dataBytes = picture.ImageBytes
            #添加到列表中
            images.append(dataBytes)
        #判断子对象是否为复合对象
        elif isinstance(child, ICompositeObject):
            #添加到队列中
            nodes.put(child if isinstance(child, ICompositeObject) else None)

#保存图片
for i, item in enumerate(images):
    fileName = "Image-{}.png".format(i)
    with open(outputPath+fileName,'wb') as imageFile:
        imageFile.write(item)
document.Close()