docx2txt TypeError: write() argument must be str, not bytes

来源：互联网发布：php 生成文本文件编辑：程序博客网时间：2024/05/21 22:58

最近在做一个从doc文件中提取图片的实验，可是报了一个错误TypeError: write() argument must be str, not bytes

python 3我的代码为

import osimport docx2txtclass fileUtil():    '''    删除其它格式的文件，保留图片格式的文件    '''    def deleteFiles(self,dirs):        for file in dirs:            # print dr            # print(file)            fileArray = file.split(".")            if fileArray[-1] == "pdf":  # 删除pdf文档                # print(file)                os.remove(os.path.join(path, file))                print(file)            elif fileArray[-1] == "docx":  # 删除pdf文档                # print(file)                os.remove(os.path.join(path, file))                print(file)            elif fileArray[-1] == "doc":  # 删除pdf文档                # print(file)                os.remove(os.path.join(path, file))                print(file)    def extractImageFromDoc(self,docPath,docOutputPath):        # text = docx2txt.process(docPath)        text = docx2txt.process(docPath, docOutputPath)        print(text)if __name__ == '__main__':    path='C:/Users/eric/Desktop\简谱图片'    dirs=os.listdir(path)    fileOperate=fileUtil();    # fileOperate.deleteFiles(dirs)    docPath="file/demo.docx"    docOutputPath="result"    fileOperate.extractImageFromDoc(docPath,docOutputPath)

需要修改docx2txt 源码中的 doc2txt.py中103行的

with open(dst_fname, "w") as dst_f:                    dst_f.write(zipf.read(fname))

改为

with open(dst_fname, "wb") as dst_f:                    dst_f.write(zipf.read(fname))

就可以通过运行

阅读全文

0 0