cli_pdf_to_ppt.py 文件源码

def pdf_splitter(self):
        self.log.info('Called pdf_splitter')
        input_pdf = PdfFileReader(file(self.pdf_file, 'rb'))
        self.total_pages = input_pdf.numPages

        for page_number in range(self.total_pages):
            output = PdfFileWriter()
            output.addPage(input_pdf.getPage(page_number))
            # new filename
            new_pdf = '_%s%s' % (str(page_number+1), '.pdf')
            new_pdf = self.pdf_file.replace('.pdf', new_pdf)
            file_stream = file(new_pdf, 'wb')
            output.write(file_stream)
            file_stream.close()

            # calling pdf to image conversion
            self.pdf_to_image(new_pdf)