scripts/downloaders/comic-valkyrie.py

#!/usr/bin/env python3
from PIL import Image
from bs4 import BeautifulSoup
from tqdm import tqdm
import re
import requests
import sys


def parse_filename(filename):
    split = re.split(":|,|\+|>", filename)
    return map(int, split[1:])


def get_image_urls():
    url = sys.argv[1]
    soup = BeautifulSoup(requests.get(url).text, "html.parser")
    for div in soup.find(id="content").find_all("div"):
        yield url + div.get("data-ptimg")


pages = list(get_image_urls())

for metadata_url in tqdm(pages):
    image_url = re.sub("\.ptimg\.json$", ".jpg", metadata_url)

    ptimg_data = requests.get(metadata_url).json()
    image_data = requests.get(image_url, stream=True).raw

    scrambled_image = Image.open(image_data)
    combined_image = Image.new(
        "RGB", (ptimg_data["views"][0]["width"], ptimg_data["views"][0]["height"])
    )

    for from_x, from_y, width, height, to_x, to_y in map(
        parse_filename, ptimg_data["views"][0]["coords"]
    ):
        chunk_data = scrambled_image.crop(
            (from_x, from_y, from_x + width, from_y + height)
        )
        combined_image.paste(chunk_data, (to_x, to_y))

    combined_image.save(image_url.split("/")[-1])