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

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()

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()

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))

http://pieceofpy.com/2009/03/05/concatenating-pdf-with-python/提供了一个解决方案。

类似的:

from pyPdf import PdfFileWriter, PdfFileReader

def append_pdf(input,output):
    [output.addPage(input.getPage(page_num)) for page_num in range(input.numPages)]

output = PdfFileWriter()

append_pdf(PdfFileReader(file("C:\\sample.pdf","rb")),output)
append_pdf(PdfFileReader(file("c:\\sample1.pdf","rb")),output)
append_pdf(PdfFileReader(file("c:\\sample2.pdf","rb")),output)
append_pdf(PdfFileReader(file("c:\\sample3.pdf","rb")),output)

output.write(file("c:\\combined.pdf","wb"))

------ 11月25日更新------

------似乎以上代码不再工作------

------请使用以下:------

from PyPDF2 import PdfFileMerger, PdfFileReader
import os

merger = PdfFileMerger()

file_folder = "C:\\My Ducoments\\"

root, dirs, files = next(os.walk(file_folder))

for path, subdirs, files in os.walk(root):
    for f in files:
        if f.endswith(".pdf"):
            merger.append(file_folder + f)

merger.write(file_folder + "Economists-1.pdf")

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)