Pdfmerger updated for python3 usage

README.md

This was originally taken from https://superuser.com/a/1012669/894282 and then updated to be compatible with python 3.X

Requires pypdf2 to be installed.

pdfmerger.py

#! /usr/bin/env python
# Original author Nicholas Kim, modified by Yan Pashkovsky
# New license - GPL v3
import sys
import time
from pathlib import Path
# from PyPDF2 import PdfReader, PdfWriter
# try:
#     from PyPDF2.utils import PdfReadError
# except ImportError:
#     from PyPDF2._reader import PdfReadError

from pypdf import PdfReader, PdfWriter
try:
    from pypdf.utils import PdfReadError
except ImportError:
    from pypdf._reader import PdfReadError

def eprint(*args, **kwargs):
    """Print to stderr

    Taken from https://stackoverflow.com/a/14981125/7564988
    """
    print(*args, file=sys.stderr, **kwargs)

def get_cmdline_arguments():
    """Retrieve command line arguments."""

    from optparse import OptionParser

    usage_string = "%prog [-v] [-o output_name] [-b bookmarks_file] file1, file2 [, ...]"

    parser = OptionParser(usage_string)
    parser.add_option(
        "-o", "--output",
        dest="output_filename",
        default=time.strftime("output_%Y%m%d_%H%M%S"),
        help="Specify output filename (exclude .pdf extension); default is current date/time stamp"
    )
    parser.add_option(
        "-b", "--bookmarks",
        dest="bookmark_file",
        default=None,
        help="Specify the bookmark names for each file. The file should be new-line delimited and the number of lies must match the number of input files. If not given, the name of each file will be used as the bookmark name."
    )
    parser.add_option("-v", "--verbose",
                  action="store_true", dest="verbose", default=True,
                  help="Print detailed output (undoes quiet)")
    parser.add_option("-q", "--quiet",
                  action="store_false", dest="verbose", default=True,
                  help="Do not print detailed output (undoes verbose)")

    options, args = parser.parse_args()
    if len(args) < 2:
        parser.print_help()
        sys.exit(1)
    return options, args

def main():
    options, filenames = get_cmdline_arguments()
    verboseprint = print if options.verbose else lambda *a, **k: None
    output_pdf_name = options.output_filename + ".pdf"
    files_to_merge = []
    bookmarks = []

    verboseprint(f"Output filename: {output_pdf_name}")
    verboseprint(f"Input filenames:")
    for f in filenames:
        verboseprint(f"\t{f}")

    # gather bookmark names
    if options.bookmark_file:
        bookmark_path = Path(options.bookmark_file)
        assert bookmark_path.exists(), f"Bookmark file '{options.bookmark_file}' does not exist."
        with bookmark_path.open() as file:
            bookmarks = file.read().splitlines()

        assert len(bookmarks) == len(filenames), f"Number of bookmarks in '{bookmark_path}' ({len(bookmarks)}) does not match the number of files ({len(filenames)})"

        verboseprint(f"Bookmark Names:")
        for b in bookmarks:
            verboseprint(f"\t{b}")
    else:
        bookmarks = [filename for filename in filenames]
        verboseprint(f"Bookmark Names: Same as filenames")

    # get PDF files
    for f in filenames:
        try:
            next_pdf_file = PdfReader(open(f, "rb"))
        except(PdfReadError):
            eprint("%s is not a valid PDF file." % f)
            sys.exit(1)
        except(IOError):
            eprint("%s could not be found." % f)
            sys.exit(1)
        else:
            files_to_merge.append(next_pdf_file)

    # merge page by page
    output_pdf_stream = PdfWriter()
    j=0
    k=0
    for f in files_to_merge:
        verboseprint(f"Adding {filenames[k]} to output")
        for i in range(len(f.pages)):
            output_pdf_stream.add_page(f.pages[i])
            if i==0:
                output_pdf_stream.add_outline_item(str(bookmarks[k]),j)
            j = j + 1
        k += 1

    # create output pdf file
    verboseprint(f"Writing output file...")
    try:
        output_pdf_file = open(output_pdf_name, "wb")
        output_pdf_stream.write(output_pdf_file)
    finally:
        output_pdf_file.close()

    print("%s successfully created." % output_pdf_name)


if __name__ == "__main__":
    main()

Latest revision works with PyPDF2 version 3.0.1.

NOTE PyPDF2 is deprecated in favor of pypdf, which actually gets regular updates. This still works for now, so I'm not going to fix what isn't broken.

Compatibility with mainline pypdf is as simple as replacing PyPDF2 with pypdf in the import statements; everything else should work.

Latest update adds the ability to customize what the bookmark labels to be added are and also adds more verbose output (with the option of disabling).