Extract PDF from Dark Horse Digital

extract.py

from PIL import Image  # pip3 install pillow
import tarfile
import json

# Suppose the book is at `https://digital.darkhorse.com/read/{hex}`,
# then visit `https://digital.darkhorse.com/api/v6/book/{hex}` to get the tarball.
book = tarfile.open('book.tar', mode='r')
manifest = json.load(book.extractfile('manifest.json'))

pages = []
for page in manifest['pages']:
    pages.append(page['src_image'])
print(f'Resolved {len(pages)} pages')

jpg_images = []
for page in pages:
    jpg_images.append(Image.open(book.extractfile(page)))
print(f'Extracted {len(jpg_images)} pages')

print(f'Converting to PDF...')
if jpg_images:
    jpg_images[0].save('book.pdf', save_all=True, append_images=jpg_images[1:])