python-删除PDF空白页

from PyPDF4 import PdfFileReader, PdfFileWriter,PdfFileMerger 
def delPdfPage(self,pdf_file_path):
        '''
        删除pdf 空白页
        '''
        pdf_file_path = os.path.join(self.pdf_dir, pdf_file_path)
        logger.info("path = {},pdf删除空白页开始时刻:{}".format(pdf_file_path, 
        str(datetime.now())))
        pdf_name = random_name(12) + "_" + 
        datetime.now().strftime("%Y%m%d%H%M%S%f")+".pdf"
        path_output = get_pdf_file_path(pdf_name)
        reader = PdfFileReader(open(pdf_file_path, 'rb'))
        writer = PdfFileWriter()
        pages = reader.getNumPages()
        for i in range(pages):
            page = reader.getPage(i)
            text = page.extractText()
            if text:
                writer.addPage(page)
        writer.write(open(path_output, 'wb'))
        logger.info("path = {},pdf删除空白页结束时刻:{}".format(pdf_file_path,   
        str(datetime.now())))
        return pdf_name   

  

posted @ 2020-11-06 16:49  H......T!  阅读(877)  评论(0编辑  收藏  举报