beamer-pdf-merge-slides.py

#!/usr/bin/env python3

import argparse
import collections

import PyPDF2


def main():
    argp = argparse.ArgumentParser(description="Merge PDF presentation slide overlay foo")
    argp.add_argument('infile', type=str, metavar="infile.pdf", help="source pdf")
    argp.add_argument('outfile', type=str, metavar="outfile.pdf", help="target pdf")
    args = argp.parse_args()

    reader = PyPDF2.PdfFileReader(open(args.infile, "rb"))
    print("Document Title: %s" % reader.getDocumentInfo().title)
    print("Input file has %d slides" % reader.getNumPages())

    # Build dictionary of page number labels
    nums = reader.trailer["/Root"]["/PageLabels"]["/Nums"]
    numdict = dict(list((nums[i], int(nums[i+1]['/P'])) for i in range(0, len(nums), 2)))

    # Find last page for each page-number-change
    pages = collections.OrderedDict()
    for i in range(0, reader.getNumPages()):
        j = i
        while not j in numdict:
            j-=1
        pages[j] = i

    # Write new pdf
    writer = PyPDF2.PdfFileWriter()
    writer.addMetadata(reader.getDocumentInfo())
    for page in pages.values():
        writer.addPage(reader.getPage(page))

    print("Output file has %d slides" % writer.getNumPages())

    oneoutputfiletorulethemall = open(args.outfile, "wb")
    writer.write(oneoutputfiletorulethemall)
    oneoutputfiletorulethemall.close()

    print("All done :)")

if __name__ == '__main__':
    main()