Remove paperpile hyperlinks from PDF

clean_paperpile.py

# Basically seems to work to strip all paperpile links from the text
# and references section, while leaving rest of links intact.

import pdfrw  # https://github.com/pmaupin/pdfrw/tree/master/pdfrw

pdf = pdfrw.PdfReader('input_path.pdf')
for page in pdf.pages:
  if not page.Annots:
    continue
  nopaperpile = pdfrw.objects.pdfarray.PdfArray()
  for annot in page.Annots:
    if not (annot.A.URI.startswith('(https://paperpile.com/') or
            annot.A.URI.startswith('(http://paperpile.com/')):
      nopaperpile.append(annot)        
  page.Annots = nopaperpile
    
output = pdfrw.PdfWriter('output_path.pdf')
for page in pdf.pages:    
  output.addPage(page)
output.write()