pptx2pdf-annotate

pptx2pdf-annotate.py

"""
Adds PPTX Presenter Notes as PDF Text Annotations.
This can then be used with `pdfpc` (https://github.com/pdfpc/pdfpc) for presentations.

NOTE:
<input.pptx> and <input.pdf> must contain the same number of pages.
"""
import sys

from pptx import Presentation
from pdf_annotate import PdfAnnotator, Location, Appearance

if len(sys.argv) <= 3:
    print('Usage: pptx2pdf-annot.py <input.pptx> <input.pdf> <output.pdf>')
    sys.exit(1)

prs = Presentation(sys.argv[1])
pdf = PdfAnnotator(sys.argv[2])
output = sys.argv[3]

for page, slide in enumerate(prs.slides):
    if slide.has_notes_slide:
        notes_slide = slide.notes_slide
        note_text = notes_slide.notes_text_frame.text
        
        # NOTE: pdf_annotate library currently doesn't support UTF-8
        encoded_text = note_text.encode('latin-1', 'ignore').decode()

        pdf.add_annotation('text', Location(x1=0, y1=0, x2=0, y2=0, page=page),
        Appearance(
                fill=[0, 0, 1, 0.5],
                wrap_text=True,
                content=str(encoded_text)
            ))

pdf.write(output)