from PyPDF2 import PdfFileMerger
import webbrowser
import os
dir_path = os.path.dirname(os.path.realpath(__file__))

def list_files(directory, extension):
    return (f for f in os.listdir(directory) if f.endswith('.' + extension))

pdfs = list_files(dir_path, "pdf")

merger = PdfFileMerger()

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

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

webbrowser.open_new('file://'+ dir_path + '/result.pdf')

Go 回购：https://github.com/mahaguru24/Python_Merge_PDF.git

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。

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))

使用Pypdf或其后续版本PyPDF2:

作为PDF工具包构建的Pure-Python库。它能够: 逐页拆分文档， 逐页合并文件，

(以及更多)

下面是一个适用于这两个版本的示例程序。

#!/usr/bin/env python
import sys
try:
    from PyPDF2 import PdfFileReader, PdfFileWriter
except ImportError:
    from pyPdf import PdfFileReader, PdfFileWriter

def pdf_cat(input_files, output_stream):
    input_streams = []
    try:
        # First open all the files, then produce the output file, and
        # finally close the input files. This is necessary because
        # the data isn't read from the input files until the write
        # operation. Thanks to
        # https://stackoverflow.com/questions/6773631/problem-with-closing-python-pypdf-writing-getting-a-valueerror-i-o-operation/6773733#6773733
        for input_file in input_files:
            input_streams.append(open(input_file, 'rb'))
        writer = PdfFileWriter()
        for reader in map(PdfFileReader, input_streams):
            for n in range(reader.getNumPages()):
                writer.addPage(reader.getPage(n))
        writer.write(output_stream)
    finally:
        for f in input_streams:
            f.close()
        output_stream.close()

if __name__ == '__main__':
    if sys.platform == "win32":
        import os, msvcrt
        msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
    pdf_cat(sys.argv[1:], sys.stdout)

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()

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")