PyPDF2切割单页为两页

mysick 2021-12-16 原文

# -*- coding: UTF-8 -*-  
from PyPDF2 import PdfFileReader, PdfFileWriter
import os

def split_pdf(infile, out_path):
    """
    :param infile: 待拆分的pdf文件
    :param out_path: 拆分成单页的pdf文件的存储路径
    :return: 无
    """

    if not os.path.exists(out_path):
        os.makedirs(out_path)
    with open(infile, \'rb\') as infile:
    
        pdfReader = PdfFileReader(infile)
        number_of_pages = pdfReader.getNumPages()  #计算此PDF文件中的页数
        
        for i in range(number_of_pages):

            page = pdfReader.getPage(i)
            width = float(page.mediaBox.getWidth())
            height = float(page.mediaBox.getHeight())
            #print("width:"+str(width)+" Height"+str(height))

            #top page
            pdfReader=PdfFileReader(infile)   #一定要重新读取，要不会报错。
            pdfWriter = PdfFileWriter()    #循环创建空白的pdf 
            page_top = pdfReader.getPage(i)
            page_top.mediaBox.lowerLeft = (0,height/2)
            page_top.mediaBox.lowerRight = (width,height/2)
            page_top.mediaBox.upperLeft = (0,height)
            page_top.mediaBox.upperRight = (width,height)
            pdfWriter.addPage(page_top)
            out_file_name = out_path + str(i+1)+\'_top.pdf\'
            with open(out_file_name, \'wb\') as outfile:
                pdfWriter.write(outfile) 
   
            #bottom page
            pdfReader=PdfFileReader(infile)   #一定要重新读取，要不会报错。
            pdfWriter = PdfFileWriter()    #循环创建空白的pdf
            page_buttom = pdfReader.getPage(i)
            page_buttom.mediaBox.lowerLeft = (0,0)
            page_buttom.mediaBox.lowerRight = (width,0)
            page_buttom.mediaBox.upperLeft = (0,height/2)
            page_buttom.mediaBox.upperRight = (width,height/2)
    
            pdfWriter.addPage(page_buttom)   
            out_file_name = out_path + str(i+1)+\'_bottom.pdf\' 
            with open(out_file_name, \'wb\') as outfile:
                pdfWriter.write(outfile) 


if __name__ == \'__main__\':
    in_File = \'./1.pdf\'
    out_Path = \'./Single/\'  # 生成输出文件夹
    split_pdf(in_File, out_Path)