PyPDF3 拆分PDF - 技术栈

python 复制代码

from PyPDF3 import PdfFileWriter, PdfFileReader
path = "C://Users//Administrator//Desktop//拆分//"
input_pdf = PdfFileReader(path+"example.pdf")  # PdfFileReader读取原始文件
output = PdfFileWriter()  
# 获取PDF页数
num_pages = input_pdf.getNumPages()

for page_num in range(num_pages):
    output = PdfFileWriter()
    # PdfFileWriter().addPage()将PDF页面添加到新的PDF中并保存
    output.addPage(input_pdf.getPage(page_num))

    with open("{}page_{}.pdf".format(path,page_num + 1), 'wb') as output_pdf:
        output.write(output_pdf)

python 复制代码

from PyPDF3 import PdfFileReader, PdfFileWriter


def split_pdf(input_pdf_path, output_prefix, start_page, end_page):
    # 读取PDF
    reader = PdfFileReader(input_pdf_path)

    # 循环从start_page到end_page，每页创建新的PDF
    for page_number in range(start_page, end_page + 1):
        output = PdfFileWriter()
        # 将特定页面添加到输出PDF
        output.addPage(reader.pages[page_number - 1])
        # 写入PDF到文件
        with open(f"{output_prefix}-page_{page_number}.pdf", "wb") as output_pdf:
            output.write(output_pdf)


# 使用split_pdf函数拆分PDF
# 文件名，输出名，起始页，结束页
split_pdf("example.pdf", "output", 1, 3)  # 拆分从第1页到第3页的PDF

python 复制代码

import os
from PyPDF3 import PdfFileMerger
path = "C://Users//Administrator//Desktop//拆分//新建文件夹//"
pdf_lst = [f for f in os.listdir(path) if f.endswith('.pdf')]
pdf_lst = [os.path.join(path, filename) for filename in pdf_lst]

file_merger = PdfFileMerger()
for pdf in pdf_lst:
    file_merger.append(pdf)
file_merger.write(path + "合并文件.pdf")