Keynote text extractor

keynote_text_extractor.py

import pathlib
import os
import pipes
import subprocess
import sys
# Add env to prevent the Protobuf error
os.environ['PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION'] = 'python'

# I forgot what to install ...
import yaml
from keynote_parser.command_line import unpack_command


def main():
    if len(sys.argv) < 2:
        print(f'Usage: {sys.argv[0]} INFILE')
        sys.exit(1)

    for f in sys.argv[1:]:
        extract(f)


def extract(f: str):
    index = pathlib.Path(f.replace('.key', '') + f'/Index/')
    unpack_command(f)

    with open(index / 'Document.iwa.yaml', 'r') as raw:
        document = yaml.load(raw, yaml.Loader)

    slides = []
    for archive in document['chunks'][0]['archives']:
        objects = archive['objects'][0]
        if objects['_pbtype'] == 'KN.SlideNodeArchive' and not objects.get('isHidden', False):
            slides.append(objects['slide']['identifier'])

    exist_slides = []
    for slide in slides:
        try:
            p = index / f'Slide-{slide}.iwa.yaml'
            p.stat()
        except FileNotFoundError:
            continue

        exist_slides.append(slide)

    lines = []
    for slide in exist_slides:
        with open(index / f'Slide-{slide}.iwa.yaml') as raw:
            body = yaml.load(raw, yaml.Loader)

        for objs in body['chunks'][0]['archives']:
            obj = objs['objects'][0]
            if 'text' in obj:
                text = obj['text'][0].replace('\ufffc', '')
                if text:
                    lines.append(text.replace('\n', '\n\n'))

    input('Press f if you are ready')

    print(f'Copying all text from {f}')
    subprocess.Popen('pbcopy', stdin=subprocess.PIPE).communicate('\n\n'.join(lines).encode())

main()