scripts/downloaders/mangarock.py

#!/usr/bin/env python3
from io import BytesIO
from tqdm import tqdm
import os
import requests
import sys

# Decoding thanks to https://github.com/bake/mri/blob/master/mri.go#L34

XOR_KEY = 101


def get_pages(chapter):
    api_response = requests.get(
        "https://api.mangarockhd.com/query/web401/pagesv2",
        params={"oid": "mrs-chapter-" + chapter},
    ).json()
    for item in api_response["data"]:
        yield item["url"]


def decode_ciphertext(byte):
    return byte ^ XOR_KEY


def get_image(url):
    ciphertext = requests.get(url).content
    size = len(ciphertext) + 7
    cleartext = BytesIO()
    cleartext.write("RIFF".encode("ascii"))
    cleartext.write(
        bytes([size >> 0 & 255, size >> 8 & 255, size >> 16 & 255, size >> 24 & 255])
    )
    cleartext.write("WEBPVP8".encode("ascii"))
    cleartext.write(bytes(list(map(decode_ciphertext, ciphertext))))
    cleartext.seek(0)
    return cleartext


requested_chapters = sys.argv[1:]

for chapter_idx, chapter in tqdm(list(enumerate(requested_chapters))):
    chapter_dir = str(chapter_idx + 1)
    os.makedirs(chapter_dir, exist_ok=True)
    pages = get_pages(chapter)
    for idx, page in tqdm(list(enumerate(pages))):
        filename = os.path.join(chapter_dir, f"{idx+1:04}.webp")
        if os.path.isfile(filename):
            continue

        image = get_image(page)
        with open(filename, "wb") as f:
            f.write(image.read())