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")

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()

下面是针对我的特定用例的最常见答案的时间比较:合并5个大单页pdf文件的列表。每个测试我都运行了两次。

(免责声明:我在Flask中运行这个函数，您的里程可能会有所不同)

博士TL;

pdfrw是我测试的3个pdf文件组合库中最快的一个。

PyPDF2

start = time.time()
merger = PdfFileMerger()
for pdf in all_pdf_obj:
    merger.append(
        os.path.join(
            os.getcwd(), pdf.filename # full path
                )
            )
formatted_name = f'Summary_Invoice_{date.today()}.pdf'
merge_file = os.path.join(os.getcwd(), formatted_name)
merger.write(merge_file)
merger.close()
end = time.time()
print(end - start) #1 66.50084733963013 #2 68.2995400428772

PyMuPDF

start = time.time()
result = fitz.open()

for pdf in all_pdf_obj:
    with fitz.open(os.path.join(os.getcwd(), pdf.filename)) as mfile:
        result.insertPDF(mfile)
formatted_name = f'Summary_Invoice_{date.today()}.pdf'

result.save(formatted_name)
end = time.time()
print(end - start) #1 2.7166640758514404 #2 1.694727897644043

PDFrw

start = time.time()
result = fitz.open()

writer = PdfWriter()
for pdf in all_pdf_obj:
    writer.addpages(PdfReader(os.path.join(os.getcwd(), pdf.filename)).pages)

formatted_name = f'Summary_Invoice_{date.today()}.pdf'
writer.write(formatted_name)
end = time.time()
print(end - start) #1 0.6040127277374268 #2 0.9576816558837891

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。

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)

合并目录下的所有pdf文件

把pdf文件放到目录下。启动程序。你会得到一个合并了所有pdf文件的pdf。

import os
from PyPDF2 import PdfMerger

x = [a for a in os.listdir() if a.endswith(".pdf")]

merger = PdfMerger()

for pdf in x:
    merger.append(open(pdf, 'rb'))

with open("result.pdf", "wb") as fout:
    merger.write(fout)

今天我该如何编写上面相同的代码呢

from glob import glob
from PyPDF2 import PdfMerger



def pdf_merge():
    ''' Merges all the pdf files in current directory '''
    merger = PdfMerger()
    allpdfs = [a for a in glob("*.pdf")]
    [merger.append(pdf) for pdf in allpdfs]
    with open("Merged_pdfs.pdf", "wb") as new_file:
        merger.write(new_file)


if __name__ == "__main__":
    pdf_merge()