Google Slides speaker notes => export as ODP => pdfpc JSON

odp2pdfpc.py

#!/usr/bin/env python3
import sys
import xml.etree.ElementTree as ET
import json
import os
import zipfile
import tempfile

ns = {
    'draw': 'urn:oasis:names:tc:opendocument:xmlns:drawing:1.0',
    'presentation': 'urn:oasis:names:tc:opendocument:xmlns:presentation:1.0',
    'text': 'urn:oasis:names:tc:opendocument:xmlns:text:1.0',
}

def extract_notes(content_xml_path):
    tree = ET.parse(content_xml_path)
    root = tree.getroot()
    pages = root.findall('.//draw:page', ns)
    notes = []

    for i, page in enumerate(pages):
        notes_elem = page.find('.//presentation:notes', ns)
        note_text = ''
        if notes_elem is not None:
            lines = []
            for tp in notes_elem.findall('.//text:p', ns):
                parts = []
                if tp.text:
                    parts.append(tp.text)
                for child in tp:
                    tag = child.tag.split('}')[-1] if '}' in child.tag else child.tag
                    if tag == 'line-break':
                        parts.append('\n')
                    elif tag == 'tab':
                        parts.append('\t')
                    elif tag == 's':
                        count = child.get('{urn:oasis:names:tc:opendocument:xmlns:text:1.0}c', '1')
                        parts.append(' ' * int(count))
                    if child.text:
                        parts.append(child.text)
                    if child.tail:
                        parts.append(child.tail)
                lines.append(''.join(parts))
            note_text = '\n'.join(lines)
        notes.append({'idx': i, 'note': note_text})

    return notes

def main():
    if len(sys.argv) != 2:
        print(f'Usage: {sys.argv[0]} <file.odp or extracted-dir>', file=sys.stderr)
        sys.exit(1)

    path = sys.argv[1]

    if os.path.isdir(path):
        content_xml = os.path.join(path, 'content.xml')
        base = path.rstrip('/')
    elif zipfile.is_zipfile(path):
        tmpdir = tempfile.mkdtemp()
        with zipfile.ZipFile(path) as zf:
            zf.extract('content.xml', tmpdir)
        content_xml = os.path.join(tmpdir, 'content.xml')
        base = path
    else:
        print(f'Error: {path} is not an ODP file or extracted directory', file=sys.stderr)
        sys.exit(1)

    notes = extract_notes(content_xml)
    pdfpc = {
        'pdfpcFormat': 2,
        'pages': notes,
    }

    outpath = base + '.pdfpc'
    with open(outpath, 'w', encoding='utf-8') as f:
        json.dump(pdfpc, f, indent=2, ensure_ascii=False)

    non_empty = sum(1 for n in notes if n['note'].strip())
    print(f'{outpath}: {len(notes)} slides, {non_empty} with notes')

if __name__ == '__main__':
    main()