Created
May 19, 2020 14:01
-
-
Save fidelthomet/17c7cc587bd9db3e77a8bfb5c7308738 to your computer and use it in GitHub Desktop.
python3 script to merge pdf files with option to skip first or last page, based on https://stackoverflow.com/a/3444735
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from argparse import ArgumentParser | |
from glob import glob | |
from PyPDF2 import PdfFileReader, PdfFileWriter | |
def PDF_cat(files, output_filename, skipfirstpage, skiplastpage): | |
# 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 | |
writer = PdfFileWriter() | |
skipfirst = 1 if skipfirstpage else 0 | |
skiplast = 1 if skiplastpage else 0 | |
# collect and open input files | |
inp = [open(f,'rb') for f in sorted(glob(files)) if f != output_filename] | |
n = len(inp) | |
print ('merging %d files' % n) | |
for i, fh in enumerate(inp, 1): | |
reader = PdfFileReader(fh) | |
for pg in range(skipfirst, reader.getNumPages() - skiplast): | |
writer.addPage(reader.getPage(pg)) | |
print('writing output file...') | |
with open(output_filename, 'wb') as fout: | |
writer.write(fout) | |
# finallly... | |
for fh in inp: | |
fh.close() | |
if __name__ == '__main__': | |
parser = ArgumentParser() | |
# add more options if you like | |
parser.add_argument('-o', '--output', | |
dest='output_filename', | |
help='write merged PDF files to FILE', | |
metavar='FILE') | |
parser.add_argument(dest='files', | |
help='PDF files to merge') | |
parser.add_argument('-f', '--skipfirstpage', | |
dest='skipfirstpage', | |
action='store_true', | |
help='skip first page of each merged PDF') | |
parser.add_argument('-l', '--skiplastpage', | |
dest='skiplastpage', | |
action='store_true', | |
help='skip last page of each merged PDF') | |
parser.set_defaults(output_filename='mergedPDFs.pdf', files='.\*.pdf', | |
skipfirstpage=False, skiplastpage=False, verbose=False) | |
args = parser.parse_args() | |
PDF_cat(args.files, args.output_filename, args.skipfirstpage, args.skiplastpage) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment