自动化将 word 转为 pdf，再将pdf转为图片！

参考：

https://blog.csdn.net/ynyn2013/article/details/49120731

https://www.jianshu.com/p/f57cc64b9f5e

 

一、将 doc 转为 pdf

1、install 依赖

pip install pywin32

 

2、直接调用win32com接口打开文件，另存为pdf。SaveAs中的参数17代表村委pdf格式，完了关闭文件，关闭word。

    def doc2pdf(self):
        try:
            w = Dispatch("Word.Application")
            doc = w.Documents.Open(self.docPath, ReadOnly=1)
            doc.SaveAs(self.pdfPath, 17)
        except:
            traceback.print_exc()
        finally:
            doc.Close()
            w.Quit()
        self.checkFile(self.pdfPath, 'pdf')

以下为文件格式对应表

wdFormatDocument = 0
wdFormatDocument97 = 0
wdFormatDocumentDefault = 16
wdFormatDOSText = 4
wdFormatDOSTextLineBreaks = 5
wdFormatEncodedText = 7
wdFormatFilteredHTML = 10
wdFormatFlatXML = 19
wdFormatFlatXMLMacroEnabled = 20
wdFormatFlatXMLTemplate = 21
wdFormatFlatXMLTemplateMacroEnabled = 22
wdFormatHTML = 8
wdFormatPDF = 17
wdFormatRTF = 6
wdFormatTemplate = 1
wdFormatTemplate97 = 1
wdFormatText = 2
wdFormatTextLineBreaks = 3
wdFormatUnicodeText = 7
wdFormatWebArchive = 9
wdFormatXML = 11
wdFormatXMLDocument = 12
wdFormatXMLDocumentMacroEnabled = 13
wdFormatXMLTemplate = 14
wdFormatXMLTemplateMacroEnabled = 15
wdFormatXPS = 18

　　

 

二、将pdf转为图片

1、install 依赖

1.1、pip isntall PyMuPDF

 

1.2、Windows安装配置poppler

Windows用户必须为Windows安装poppler (http://blog.alivate.com.au/poppler-windows/)，然后将bin/文件夹添加到PATH（开始>输入env>编辑系统环境变量>环境变量...>系统变量>Path）

安装完poppler需重启系统后生效。

 

2、将pdf转为图片

    def pdf2image(self):
        # 建立图片文件夹
        if not os.path.exists(self.imgFold):
            os.mkdir(self.imgFold)

        # 转存图片
        pages = fitz.open(self.pdfPath)
        for page in pages:
            imgPath = os.path.join(self.imgFold, str(page.number)+'.jpg')
            pix = page.getPixmap()
            pix.writeImage(imgPath)
        self.checkFile(imgPath, 'last img')

 

三、直接将word转为图片

方法：结合1,2

代码如下：

'''
@Author: haikuoxin
@Date: 2019-11-11 11:21:12
@Last Modified by:   haikuoxin
@Last Modified time: 2019-11-11 11:21:12
'''
import os
import time
import traceback
import fitz
from win32com.client import Dispatch
import comtypes.client


class Word2Pdf2Img():
    def __init__(self, docPath):
        # 初始化路径
        self.docPath = docPath
        self.fileName = os.path.basename(self.docPath).split('.')[0]
        self.fileFold = os.path.dirname(self.docPath)
        self.pdfPath = os.path.join(self.fileFold, self.fileName + '.pdf')
        self.imgFold = os.path.join(self.fileFold, self.fileName)

    @staticmethod
    def checkFile(filePath, fileType=''):
        if os.path.isfile(filePath):
            print ('file {} existed!'.format(fileType))
        else:
            print ('file {} not existed!'.format(fileType))

    def doc2pdf(self):
        # try:
        #     doc = w.Documents.Open(self.docPath, ReadOnly=1)
        #     doc.SaveAs(self.pdfPath, 17)
        #     doc.Close()
        # except:
        #     traceback.print_exc()
        # finally:
        #     w.Quit()

        # w = Dispatch("Word.Application")
        # doc = w.Documents.Open(self.docPath, ReadOnly=1)
        # doc.SaveAs(self.pdfPath, 17)
        # doc.Close()
        # w.Quit()

        w = comtypes.client.CreateObject('Word.Application')
        w.Visible = True
        time.sleep(3)
        doc = w.Documents.Open(self.docPath)
        doc.SaveAs(self.pdfPath, FileFormat=17)
        doc.Close()
        w.Quit()
        # os.system('taskkill /f /im WINWORD.EXE')
        self.checkFile(self.pdfPath, 'pdf')

    def pdf2image(self):
        # 建立图片文件夹
        if not os.path.exists(self.imgFold):
            os.mkdir(self.imgFold)

        # 转存图片
        pages = fitz.open(self.pdfPath)
        for page in pages:
            imgPath = os.path.join(self.imgFold, str(page.number)+'.jpg')
            pix = page.getPixmap()
            pix.writeImage(imgPath)
        self.checkFile(imgPath, 'last img')
        
    def doc2image(self):
        self.doc2pdf()
        self.pdf2image()

def run():
    dataFold = r'C:\Users\Administrator\Desktop\chatuClass\data\online'
    docPaths = [os.path.join(dataFold, name) for name in os.listdir(dataFold)]
    docCnt = len(docPaths)
    errorCnt = 0
    for i, docPath in enumerate(docPaths[:]):
        if docPath=='':
            continue
    
        try:
            cvter = Word2Pdf2Img(docPath)
            print (docCnt, i, errorCnt, cvter.fileName)
            cvter.doc2image()
        except:
            errorCnt += 1
            traceback.print_exc()

if __name__ == "__main__":
    run()
    # docPath = r'C:\Users\Administrator\Desktop\chatuClass\data\test\b.docx'
    # cvter = Word2Pdf2Img(docPath)
    # cvter.doc2pdf()