Python之PyPDF2模块的使用

pip install PyPDF2

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2020/1/15 13:38
# @Author  : suk
# @File    : pyxl.py
# @Software: PyCharm
import PyPDF2

reader = PyPDF2.PdfFileReader(open(‘linux.pdf‘, ‘rb‘))
print(reader.getNumPages())  # 获取pdf总页数
print(reader.isEncrypted)  # 判断是否有加密
page = reader.getPage(4)  # 获取第四页
print(page.extractText())  # 获取第四页的内容
print(reader.getDocumentInfo())  # 获取PDF元信息，即创建时间，作者，标题等

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

import PyPDF2

reader = PyPDF2.PdfFileReader(open(‘linux.pdf‘, ‘rb‘))

output = PyPDF2.PdfFileWriter()

output.addPage(reader.getPage(1))
output.addPage(reader.getPage(4))
output.addPage(reader.getPage(5))
print(output.getNumPages())  # 获取写入页的总页数

output.encrypt(‘123456‘)
outputStream = open(‘PyPDF2-output.pdf‘, ‘wb‘)
output.write(outputStream)
outputStream.close()

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

import PyPDF2

reader = PyPDF2.PdfFileReader(open(‘linux.pdf‘, ‘rb‘))

page = reader.getPage(0)  # 获取第0页
page.rotateClockwise(180)  # 旋转180度

writer = PyPDF2.PdfFileWriter()  # 创建PDF写入的对象
writer.addPage(page)

outputStream = open(‘rotate-page-test.pdf‘, ‘wb‘)  # 创建一个PDF文件
writer.write(outputStream)  # 往文件写入PDF数据
outputStream.close()  # 写入流

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

import PyPDF2

reader = PyPDF2.PdfFileReader(open(‘linux.pdf‘, ‘rb‘))  # 增加水印的原文件

watermark = PyPDF2.PdfFileReader(open(‘水印模板.pdf‘, ‘rb‘))  # 水印的模板

writer = PyPDF2.PdfFileWriter()  # 写入PDF的对象

for i in range(reader.getNumPages()):
    page = reader.getPage(i)
    page.mergePage(watermark.getPage(0))  # 将原文件与水印模板合并
    writer.addPage(page)  # 增加到写入对象中

outputStream = open(‘watermark-test-linux.pdf‘, ‘wb‘)  # 打开一个写入硬盘的文件对象
writer.write(outputStream)  # 将合并好的数据，写入硬盘中
outputStream.close()  # 关闭文件句柄

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

from PyPDF2 import PdfFileMerger

merger = PdfFileMerger()  # 创建一个合并的对象

input1 = open(‘01PDF.pdf‘, ‘rb‘)
input2 = open(‘02PDF.pdf‘, ‘rb‘)
input3 = open(‘03PDF.pdf‘, ‘rb‘)

merger.append(fileobj=input1, pages=(0, 3))  # 合并文件1的0到3页
merger.merge(position=2, fileobj=input2, pages=(0, 1))  # 合并文件2的0到1页
merger.append(fileobj=input3)  # 合并文件的所有页

output = open(‘document-output.pdf‘, ‘wb‘)  # 保存硬盘上
merger.write(output)  # 写入到硬盘上
output.close()  # 关闭文件句柄

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

import PyPDF2
import os
import glob

def get_all_pdf_files(path):
    """获取指定目录的所有pdf文件名"""
    all_pdfs = glob.glob(‘{0}/*.pdf‘.format(path))
    all_pdfs.sort(key=str.lower)  # 排序
    return all_pdfs

def main():
    path = os.getcwd()
    all_pdfs = get_all_pdf_files(path)
    if not all_pdfs:
        raise SystemExit(‘没有可用的PDF类型文件‘)

    merger = PyPDF2.PdfFileMerger()

    first_obj = open(all_pdfs[0], ‘rb‘)  # 打开第一个PDF文件
    merger.append(first_obj)  # 增加到合并的对象中

    file_objs = []
    for pdf in all_pdfs[1:]:  # 读取所有的文件对象
        file_objs.append(open(pdf, ‘rb‘))

    for file_obj in file_objs:
        reader = PyPDF2.PdfFileReader(file_obj)
        merger.append(fileobj=file_obj, pages=(1, reader.getNumPages()))

    outputStream = open(‘merge-pdfs.pdf‘, ‘wb‘)
    merger.write(outputStream)
    outputStream.close()
    for file_obj in file_objs:  # 批量关闭文件句柄
        file_obj.close()

if __name__ == ‘__main__‘:
    main()