python - 使用 Python 将 DOCX 文件转换为文本文件

Question

我编写了以下代码将我的 docx 文件转换为文本文件。我在文本文件中打印的输出是整个文件的最后一段/部分，而不是完整的内容。代码如下:

from docx import Document
import io
import shutil

def convertDocxToText(path):
    for d in os.listdir(path):
        fileExtension=d.split(".")[-1]
        if fileExtension =="docx":
            docxFilename = path + d
            print(docxFilename)
            document = Document(docxFilename)


# for printing the complete document
            print('\nThe whole content of the document:->>>\n')
            for para in document.paragraphs:
                textFilename = path + d.split(".")[0] + ".txt"
                with io.open(textFilename,"w", encoding="utf-8") as textFile:
                    #textFile.write(unicode(para.text))
                    x=unicode(para.text)
                    print(x) //the complete content gets printed by this line
                    textFile.write((x)) #after writing the content to text file only last paragraph is copied.
                #textFile.write(para.text)

path= "/home/python/resumes/"
convertDocxToText(path)

Answer 1

针对上述问题的解决方案如下:

from docx import Document
import io
import shutil
import os

def convertDocxToText(path):
    for d in os.listdir(path):
        fileExtension=d.split(".")[-1]
        if fileExtension =="docx":
            docxFilename = path + d
            print(docxFilename)
            document = Document(docxFilename)
            textFilename = path + d.split(".")[0] + ".txt"
            with io.open(textFilename,"w", encoding="utf-8") as textFile:
                for para in document.paragraphs: 
                    textFile.write(unicode(para.text))

path= "/home/python/resumes/"
convertDocxToText(path)