使用字典以获得更大的灵活性(例如sort, dedup):

import os
from PyPDF2 import PdfFileMerger
# use dict to sort by filepath or filename
file_dict = {}
for subdir, dirs, files in os.walk("<dir>"):
    for file in files:
        filepath = subdir + os.sep + file
        # you can have multiple endswith
        if filepath.endswith((".pdf", ".PDF")):
            file_dict[file] = filepath
# use strict = False to ignore PdfReadError: Illegal character error
merger = PdfFileMerger(strict=False)

for k, v in file_dict.items():
    print(k, v)
    merger.append(v)

merger.write("combined_result.pdf")

我在linux终端上通过利用subprocess(假设目录中存在one.pdf和two.pdf)使用pdf unite，目的是将它们合并为three.pdf

 import subprocess
 subprocess.call(['pdfunite one.pdf two.pdf three.pdf'],shell=True)

使用正确的python解释器:

conda activate py_envs

pip install PyPDF2

Python代码:

from PyPDF2 import PdfMerger

#set path files
import os
os.chdir('/ur/path/to/folder/')
cwd = os.path.abspath('')
files = os.listdir(cwd)

def merge_pdf_files():
    merger = PdfMerger()
    pdf_files = [x for x in files if x.endswith(".pdf")]
    [merger.append(pdf) for pdf in pdf_files]
    with open("merged_pdf_all.pdf", "wb") as new_file:
        merger.write(new_file)

if __name__ == "__main__":
    merge_pdf_files()

它是可能的，使用Python，合并单独的PDF文件?

Yes.

下面的例子将一个文件夹中的所有文件合并为一个新的PDF文件:

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

from argparse import ArgumentParser
from glob import glob
from pyPdf import PdfFileReader, PdfFileWriter
import os

def merge(path, output_filename):
    output = PdfFileWriter()

    for pdffile in glob(path + os.sep + '*.pdf'):
        if pdffile == output_filename:
            continue
        print("Parse '%s'" % pdffile)
        document = PdfFileReader(open(pdffile, 'rb'))
        for i in range(document.getNumPages()):
            output.addPage(document.getPage(i))

    print("Start writing '%s'" % output_filename)
    with open(output_filename, "wb") as f:
        output.write(f)

if __name__ == "__main__":
    parser = ArgumentParser()

    # Add more options if you like
    parser.add_argument("-o", "--output",
                        dest="output_filename",
                        default="merged.pdf",
                        help="write merged PDF to FILE",
                        metavar="FILE")
    parser.add_argument("-p", "--path",
                        dest="path",
                        default=".",
                        help="path of source PDF files")

    args = parser.parse_args()
    merge(args.path, args.output_filename)

def pdf_merger(路径): """将pdf文件合并为一个pdf""" "

import logging
logging.basicConfig(filename = 'output.log', level = logging.DEBUG, format = '%(asctime)s %(levelname)s %(message)s' )

try:
    import glob, os
    import PyPDF2
    
    os.chdir(path)
    
    pdfs = []
    
    for file in glob.glob("*.pdf"):
        pdfs.append(file)
        
    if len(pdfs) == 0:
        logging.info("No pdf in the given directory")
        
    else:
        merger = PyPDF2.PdfFileMerger()
        
        for pdf in pdfs:
            merger.append(pdf)
            
        merger.write('result.pdf')
        merger.close()
        
except Exception as e:
    logging.error('Error has happened')
    logging.exception('Exception occured' + str(e))

您也可以使用pikepdf(源代码文档)。

示例代码可以是(摘自文档):

from glob import glob

from pikepdf import Pdf

pdf = Pdf.new()

for file in glob('*.pdf'):  # you can change this to browse directories recursively
    with Pdf.open(file) as src:
        pdf.pages.extend(src.pages)

pdf.save('merged.pdf')
pdf.close()

如果想要排除页面，可以采用另一种方法，例如将页面复制到新的pdf中(然后，您可以选择不复制哪些页面。Pages对象的行为类似于一个列表)。

它仍然被积极维护，截至2022年2月，PyPDF2和pdfrw似乎都不是这种情况。

我还没有对它进行基准测试，所以我不知道它比其他解决方案更快还是更慢。

在我的例子中，与PyMuPDF相比的一个优点是有一个官方的Ubuntu包可用(python3-pikepdf)，可以根据它来打包我自己的软件。