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)

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)

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

pdfrw库可以很容易地做到这一点，假设您不需要保存书签和注释，并且您的pdf文件没有加密。Cat.py是一个示例拼接脚本，而子集.py是一个示例页面子集脚本。

串联脚本的相关部分——假设input是一个输入文件名列表，outfn是一个输出文件名:

from pdfrw import PdfReader, PdfWriter

writer = PdfWriter()
for inpfn in inputs:
    writer.addpages(PdfReader(inpfn).pages)
writer.write(outfn)

正如你所看到的，省略最后一页是很容易的，例如:

    writer.addpages(PdfReader(inpfn).pages[:-1])

免责声明:我是pdfrw的主要作者。