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

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

Giovanni G. PY以一种简单易用的方式(至少对我来说)给出了答案:

import os
from PyPDF2 import PdfFileMerger

def merge_pdfs(export_dir, input_dir, folder):
    current_dir = os.path.join(input_dir, folder)
    pdfs = os.listdir(current_dir)
    
    merger = PdfFileMerger()
    for pdf in pdfs:
        merger.append(open(os.path.join(current_dir, pdf), 'rb'))

    with open(os.path.join(export_dir, folder + ".pdf"), "wb") as fout:
        merger.write(fout)

export_dir = r"E:\Output"
input_dir = r"E:\Input"
folders = os.listdir(input_dir)
[merge_pdfs(export_dir, input_dir, folder) for folder in folders];

您可以从PyPDF2模块使用pdffilemerge。

例如，要从路径列表中合并多个PDF文件，可以使用以下函数:

from PyPDF2 import PdfFileMerger

# pass the path of the output final file.pdf and the list of paths
def merge_pdf(out_path: str, extracted_files: list [str]):
    merger   = PdfFileMerger()
    
    for pdf in extracted_files:
        merger.append(pdf)

    merger.write(out_path)
    merger.close()

merge_pdf('./final.pdf', extracted_files)

这个函数从父文件夹中递归地获取所有文件:

import os

# pass the path of the parent_folder
def fetch_all_files(parent_folder: str):
    target_files = []
    for path, subdirs, files in os.walk(parent_folder):
        for name in files:
            target_files.append(os.path.join(path, name))
    return target_files 

# get a list of all the paths of the pdf
extracted_files = fetch_all_files('./parent_folder')

最后，使用这两个函数进行声明。可以包含多个文档的parent_folder_path，以及用于合并PDF的目的地的output_pdf_path:

# get a list of all the paths of the pdf
parent_folder_path = './parent_folder'
outup_pdf_path     = './final.pdf'

extracted_files = fetch_all_files(parent_folder_path)
merge_pdf(outup_pdf_path, extracted_files)

你可以从这里获得完整的代码(来源):如何使用Python合并PDF文档

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")