Copy a PDF without any extra data.

py

# Simple python script that will copy content from 1 pdf to a new pdf.
# FYI I just copied from https://github.com/pmaupin/pdfrw/blob/master/examples/cat.py while I was playing around.

import sys
import os
from pdfrw import PdfReader, PdfWriter

reader = PdfReader(sys.argv[1])
pages = reader.pages

writer = PdfWriter()
writer.addpages(pages)
writer.write("trim" + os.path.basename(sys.argv[1]))

'''
These PDFs differ by one piece of metadata:
$ diff --text 1-s2.0-S0166864121003783-main.pdf 2-s2.0-S0166864121003783-main.pdf
2765c2765
<          <tprDsz.uSntuRm9iGoguJnLNNz.qQlt6Jm.iGn9j-mPz-z.eSndb_o9ePndmLmtmNmMmTma/>
---
>          <ZtV1wzduMmPuLnweGogqNy8NNnwyOlwf8m.eGm9z8zdyRoweKnMuLo9ePndmLmtmQmMmTma/>

$ python .\cleanpdf.py .\1-s2.0-S0166864121003783-main.pdf
$ python .\cleanpdf.py .\2-s2.0-S0166864121003783-main.pdf

$ diff --text trim1-s2.0-S0166864121003783-main.pdf trim2-s2.0-S0166864121003783-main.pdf
Look mom! No diff!
'''