pdf基本操作（分拆，合并，修改）

原创已于 2023-02-14 14:55:24 修改 · 253 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#pdf

于 2023-02-14 11:40:00 首次发布

python 专栏收录该内容

27 篇文章

订阅专栏

该代码示例展示了如何利用pyPDF2Python库对PDF文件进行拆分和合并操作。split_pdf函数接收输入PDF文件的起始和结束页码，创建新的PDF输出。hebing_pdf函数则将两个PDF文件在指定页码范围内的页面合并到一起，生成合并后的PDF文件。

基于pyPDF2

from PyPDF2 import PdfReader, PdfWriter
from pathlib import Path

TESTS_ROOT = Path(__file__).parent.resolve()
PROJECT_ROOT = TESTS_ROOT.parent
RESOURCE_ROOT = PROJECT_ROOT / "resources"

def split_pdf(file_name, start_page, end_page, output_pdf):
    #拆分pdf
    input_file = PdfReader(file_name)
    page = input_file.pages[0]
    print(page.extract_text())
    output_file = PdfWriter()
    for i in range(start_page, end_page):
        output_file.add_page(input_file.pages[i])
    with open(output_pdf, 'wb') as f:
        output_file.write(f)

    #writer.clone_document_from_reader(reader.getPage(7))
def hebing_pdf(file_name1, start_page1, end_page1,file_name2,start_page2,end_page2,output_pdf):
    #合并pdf
    input_file1 = PdfReader(file_name1)
    input_file2 = PdfReader(file_name2)
    page = input_file1.pages[0]
    print(page.extract_text())
    output_file = PdfWriter()
    print(file_name1+" 文件1的页数:"+str(len(input_file1.pages))+" \n"+file_name2+" 文件2的页数:"+str(len(input_file2.pages)) )
    for i in range(start_page1, end_page1):
        output_file.add_page(input_file1.pages[i])
        print("文件1取:"+str(i+1))
    for i in range(start_page2, end_page2):
        output_file.add_page(input_file2.pages[i])
        print("文件2取:"+str(i+1))
    with open(output_pdf, 'wb') as f:
        output_file.write(f)
        print("输入文件:"+output_pdf)

    #writer.clone_document_from_reader(reader.getPage(7))

'''
test_writer_clone() 
reader = PdfReader("期权营销表-新版.pdf")
number_of_pages = len(reader.pages)
page = reader.pages[0]
text = page.extract_text()
print(page)
print(text)
'''
if __name__ == '__main__':
 #split_pdf("测试通知.pdf", 0, 1, "1.pdf")
 hebing_pdf("测试通知.pdf", 0, 1,"新版.pdf",3,5,"1.pdf")