Python使用PyPDF2轻松实现pdf的拆分与合并

pip install PyPDF2

from PyPDF2 import PdfReader, PdfWriter
import os
#  逐页拆分pdf，将pdf中的每一页拆分为单独的pdf
def split_pdf(input_pdf_path, output_dir):
    # 创建 PdfReader 对象
    reader = PdfReader(input_pdf_path)
    # 遍历原 PDF d的每一页，逐页拆分
    for page_number in range(len(reader.pages)):
        output_path = os.path.join(output_dir, f"page_{page_number}.pdf")
        writer = PdfWriter()
        writer.add_page(reader.pages[page_number])
        with open(output_path, "wb") as output_file:
            writer.write(output_file)
        print(f"Page {page_number + 1} saved to {output_path}")
if __name__=="__main__":
    # 需要拆分的PDF完整路径
    input_pdf = 'data/test.pdf'
    # 逐页拆分后每个单独PDF保存的文件夹路径，注意是文件夹的路径
    output_file = 'data/'
    split_pdf(input_pdf,output_file)

from PyPDF2 import PdfReader, PdfWriter
import os
# 指定连续页拆分pdf
def split_page_pdf(input_pdf_path, output_pdf_path,start_num,end_num):
    # 创建 PdfReader 对象
    reader = PdfReader(input_pdf_path)
    # 创建 PdfWriter 对象
    writer = PdfWriter()
    # 指定连续的页码
    for page_number in range(start_num,end_num):
        writer.add_page(reader.pages[page_number])
    # 保存到新pdf
    with open(output_pdf_path, "wb") as output_file:
        writer.write(output_file)
if __name__=="__main__":
    # 需要拆分的PDF完整路径
    input_pdf = 'data/test.pdf'
    # 拆分PDF保存的完整路径
    output_pdf = 'data/test1.pdf'
    split_page_pdf(input_pdf,output_pdf,1,3)

from PyPDF2 import PdfReader, PdfWriter
# 指定页拆分pdf
def split_page_pdf(input_pdf_path, output_pdf_path,page_list):
    # 创建 PdfReader 对象
    reader = PdfReader(input_pdf_path)
    # 创建 PdfWriter 对象
    writer = PdfWriter()
    for page_number in page_list:
        writer.add_page(reader.pages[page_number])
    # 保存到新pdf
    with open(output_pdf_path, "wb") as output_file:
        writer.write(output_file)
if __name__=="__main__":
    # 需要拆分的PDF完整路径
    input_pdf = 'data/test.pdf'
    # 拆分PDF保存的完整路径
    output_pdf = 'data/test2.pdf'
    # 指定需要的pdf页码列表
    page_list = [0, 2, 4]
    split_page_pdf(input_pdf,output_pdf,page_list)

from PyPDF2 import PdfMerger
# 合并pdf
def merger_pdf(input_pdf,output_filename):
    merger = PdfMerger()
    for pdf_info in input_pdf:
        merger.append(pdf_info)
    with open(output_filename, "wb") as f_out:
        merger.write(f_out)
    print('合并完成！')
if __name__=="__main__":
    # 需要合并的pdf文件完整路径列表
    pdf_list = ['data/page_0.pdf','data/page_4.pdf']
    # 传入需要合并的pdf文件完整路径列表，和合并后的文件路径及名称
    merger_pdf(pdf_list,'data/page_test.pdf')

# 示例：在添加页面前将其顺时针旋转90度
page = reader.pages[0]
page.rotate(90)  # 顺时针旋转90度
writer.add_page(page)

# 示例：提取第一页的所有文本
reader = PdfReader('source.pdf')
first_page = reader.pages[0]
text = first_page.extract_text()
print(text)