把word导出成图片的流程 word中的图片如何保存为jpg格式

由于工作中需要从大量docx文档中提出图片，于是到网上搜索，找了一大堆都是分析xml文件并提取的，太过于复杂，实际上有更简单的方法，我们需要用到python-docx这个第三方库，但该库并未开发提取图片功能，不过可以通过其他方法出得到图片数据并保存为图片。

本文为原创，如需转载请注明出处（仅处理docx文档，不能处理doc文档，如果需要可执行文件的，可将代码文件通过pyinstaller进行编译）。

软件界面

下面这段代码是核心：

    for file in os.listdir(filePath):
        try:
            #跳过非docx文件
            if ".docx" not in file:
                continue
            # 创建imgPath
            subImgPath = imgPath + re.sub(".docx",",file)
            if not os.path.exists(subImgPath):
                os.makedirs(subImgPath)

            doc = docx.Document(filePath + file)        #打开文件
            for rel in doc.part._rels:
                rel = doc.part._rels[rel]               #获得资源
                if "image" not in rel.target_ref:
                    continue
                imgName = re.findall("/(.*)",rel.target_ref)[0]
                with open(subImgPath + "/" + imgName,"wb") as f:
                    f.write(rel.target_part.blob)
            UI.currentFile.setText("当前文件：" + imgName)
        except:
            continue

后来经过改进，使用PyQt5制作了界面，下面为源代码：

import docx,re,os,sys,ui_imgExtract
from PyQt5.QtWidgets import QApplication,QMainWindow,QWidget,QMessageBox
from PyQt5.Qt import QFileDialog

def run():
    filePath = UI.filePath.text()
    imgPath = UI.imgPath.text()
    if not os.path.exists(filePath):
        QMessageBox.about(main, "错误", "请选择docx文件目录！")
        return
    if not os.path.exists(imgPath):
        os.makedirs(imgPath)

    for file in os.listdir(filePath):
        try:
            #跳过非docx文件
            if ".docx" not in file:
                continue
            # 创建imgPath
            subImgPath = imgPath + re.sub(".docx",",file)
            if not os.path.exists(subImgPath):
                os.makedirs(subImgPath)

            doc = docx.Document(filePath + file)        #打开文件
            for rel in doc.part._rels:
                rel = doc.part._rels[rel]               #获得资源
                if "image" not in rel.target_ref:
                    continue
                imgName = re.findall("/(.*)",rel.target_ref)[0]
                with open(subImgPath + "/" + imgName,"wb") as f:
                    f.write(rel.target_part.blob)
            UI.currentFile.setText("当前文件：" + imgName)
        except:
            continue
    QMessageBox.about(main, "完成", "图片提取已完成！")

def init():
    UI.btnRun.clicked.connect(run)      #绑定开始提取按钮
    UI.btnFilePath.clicked.connect(choiceFileDir)  # 绑定选择docx文件目录
    UI.btnImgPath.clicked.connect(choiceImgOutPutDir)    #绑定选择图片保存目录

    # docx文件默认目录
    UI.filePath.setText(os.getcwd())
    #默认输出目录
    if not os.path.exists(os.getcwd() + "img\"):
        os.makedirs(os.getcwd() + "img\")
    UI.imgPath.setText(os.getcwd() + "img\")


#选择docx文件目录
def choiceFileDir():
    dir = QFileDialog.getExistingDirectory(main, "选择docx文件目录", os.getcwd())
    UI.filePath.setText(dir + "/")

#选择图片保存目录
def choiceImgOutPutDir():
    dir = QFileDialog.getExistingDirectory(main, "选择输出目录", os.getcwd())
    UI.imgPath.setText(dir + "/")

if __name__ == "__main__":
    app = QApplication(sys.argv)
    main = QWidget()
    UI = ui_imgExtract.Ui_Form()
    UI.setupUi(main)
    main.show()
    init()

    sys.exit(app.exec_())

下面是界面文件ui_imgExtract.py：

# -*- coding: utf-8 -*-

# Form implementation generated from reading ui file 'ui_iask.ui'
#
# Created by: PyQt5 UI code generator 5.11.3
#
# WARNING! All changes made in this file will be lost!

from PyQt5 import QtCore, QtGui, QtWidgets

class Ui_Form(object):
    def setupUi(self, Form):
        Form.setObjectName("Form")
        Form.resize(604, 100)
        self.layoutWidget = QtWidgets.QWidget(Form)
        self.layoutWidget.setGeometry(QtCore.QRect(10, 10, 581, 83))
        self.layoutWidget.setObjectName("layoutWidget")
        self.gridLayout_4 = QtWidgets.QGridLayout(self.layoutWidget)
        self.gridLayout_4.setContentsMargins(0, 0, 0, 0)
        self.gridLayout_4.setObjectName("gridLayout_4")
        self.label_8 = QtWidgets.QLabel(self.layoutWidget)
        self.label_8.setObjectName("label_8")
        self.gridLayout_4.addWidget(self.label_8, 0, 0, 1, 1)
        self.filePath = QtWidgets.QLineEdit(self.layoutWidget)
        self.filePath.setObjectName("filePath")
        self.gridLayout_4.addWidget(self.filePath, 0, 1, 1, 1)
        self.btnFilePath = QtWidgets.QPushButton(self.layoutWidget)
        self.btnFilePath.setObjectName("btnFilePath")
        self.gridLayout_4.addWidget(self.btnFilePath, 0, 2, 1, 1)
        self.label_9 = QtWidgets.QLabel(self.layoutWidget)
        self.label_9.setObjectName("label_9")
        self.gridLayout_4.addWidget(self.label_9, 1, 0, 1, 1)
        self.imgPath = QtWidgets.QLineEdit(self.layoutWidget)
        self.imgPath.setObjectName("imgPath")
        self.gridLayout_4.addWidget(self.imgPath, 1, 1, 1, 1)
        self.btnImgPath = QtWidgets.QPushButton(self.layoutWidget)
        self.btnImgPath.setObjectName("btnImgPath")
        self.gridLayout_4.addWidget(self.btnImgPath, 1, 2, 1, 1)
        self.btnRun = QtWidgets.QPushButton(self.layoutWidget)
        self.btnRun.setObjectName("btnRun")
        self.gridLayout_4.addWidget(self.btnRun, 2, 2, 1, 1)
        self.currentFile = QtWidgets.QLabel(self.layoutWidget)
        self.currentFile.setObjectName("currentFile")
        self.gridLayout_4.addWidget(self.currentFile, 2, 0, 1, 2)

        self.retranslateUi(Form)
        QtCore.QMetaObject.connectSlotsByName(Form)

    def retranslateUi(self, Form):
        _translate = QtCore.QCoreApplication.translate
        Form.setWindowTitle(_translate("Form", "docx图片批量提取"))
        self.label_8.setText(_translate("Form", "docx文件目录："))
        self.btnFilePath.setText(_translate("Form", "选择"))
        self.label_9.setText(_translate("Form", "图片保存目录："))
        self.btnImgPath.setText(_translate("Form", "选择"))
        self.btnRun.setText(_translate("Form", "开始提取"))
        self.currentFile.setText(_translate("Form", "当前文件："))