python日常应用——pdf拆分和合并 python PyPDF2

#! /usr/bin/env python# -*- coding: utf-8 -*-from PyPDF2 import PdfFileWriter, PdfFileReader,PdfFileMergerdef pdf_split(pdf_in):"""拆分PDF成单页"""# 读取pdfwith open(pdf_in,'rb') as in_pdf:pdf_file = PdfFile

西木九

238人浏览 · 2021-10-04 09:42:27

西木九 · 2021-10-04 09:42:27 发布

#! /usr/bin/env python
# -*- coding: utf-8 -*-

from PyPDF2 import PdfFileWriter, PdfFileReader,PdfFileMerger

def pdf_split(pdf_in):
    """拆分PDF成单页"""
    # 读取pdf
    with open(pdf_in,'rb') as in_pdf:
        pdf_file = PdfFileReader(in_pdf)
        if pdf_file.isEncrypted:
            pdf_file.decrypt('')
        page_num = pdf_file.getNumPages()
        # 从pdf中逐页存储
        for i in range(page_num):
            # 建立一个pdf
            pdf_out = 'after_split_b_' + str(i) +'.pdf'
            output = PdfFileWriter()
            output.addPage(pdf_file.getPage(i))
            # 写出pdf
            with open(pdf_out,'ab') as out_pdf:
                output.write(out_pdf)

if __name__ == '__main__':
	"""拆分PDF"""
	pdf_split("pdf_in") 
    """合并PDF"""
    # 初始化
    merger = PdfFileMerger()
    # 循环，a,b 交叉合并
    for i in range(72):
        with open('after_split_b_' + str(i) + '.pdf' , 'rb') as pdf:
            merger.append(PdfFileReader(pdf))
        with open('after_split_a_' + str(i+1) + '.pdf' , 'rb') as pdf:
            merger.append(PdfFileReader(pdf))
    # 合并单页
    merger.append(PdfFileReader('after_split_a_73.pdf'))
    merger.append(PdfFileReader('after_split_a_74.pdf'))
    merger.write('merged.pdf')