利用PyPDF2模块快速拆分PDF文档

ken-yu 2021-12-16 原文

利用PyPDF2模块快速拆分PDF文档，

自动查找py文件所在的目录里的pdf文件，并将拆分后的文件放到当前目录中。

from PyPDF2 import PdfFileReader, PdfFileWriter
import os

pdf_dir=[]

def get_filepath():
    docunames = os.listdir()
    for docuname in docunames:
        if os.path.splitext(docuname)[1] == \'.pdf\':
            pdf_dir.append(docuname)


def current_path():
   current_path = os.path.abspath(__file__)
   return os.path.abspath(os.path.dirname(current_path) + os.path.sep + ".")


# 将PDF文件每页分割为一个单独pdf的文件，并pdf保存至当前目录中
def pdf_split_1(pdf_input, path_output):
    fname = os.path.splitext(os.path.basename(pdf_input))[0] # 获取pdf文件名，去掉后缀名
    pdf = PdfFileReader(pdf_input)
    
    for page in range(pdf.getNumPages()):
        pdf_writer = PdfFileWriter()
        pdf_writer.addPage(pdf.getPage(page))
        output_filename = path_output + r\'\{}-{}.pdf\'.format(fname, page+1)

        with open(output_filename, \'wb\') as out:
            pdf_writer.write(out)
            # print(\'生成文件:{}\'.format(output_filename))


if __name__ == "__main__":
    get_filepath()
    pdffile = os.path.join(current_path(),"".join(pdf_dir))
    pdf_split_1(pdffile, current_path())