takecomic_download.py

# pip install requests beautifulsoup4 pillow

import argparse
import json
import os
import time
import shutil
import requests
from urllib.parse import urlparse
from bs4 import BeautifulSoup

try:
	from PIL import Image
except Exception:
	Image = None


# ========== viewer-id ==========
def get_viewer_id(episode_id=None):
	if episode_id is None:
		episode_id = input("episodes ID: ").strip()

	url = f"https://takecomic.jp/episodes/{episode_id}"
	headers = {
		"User-Agent": "Mozilla/5.0",
		"Accept": "text/html",
	}

	resp = requests.get(url, headers=headers, timeout=15)
	resp.raise_for_status()

	soup = BeautifulSoup(resp.text, "html.parser")
	el = soup.find(attrs={"data-comici-viewer-id": True})
	if not el:
		raise RuntimeError("data-comici-viewer-id not found")

	return el["data-comici-viewer-id"]


# ========== JSON helpers ==========
def find_total_pages(obj):
	if isinstance(obj, dict):
		if "totalPages" in obj:
			return obj["totalPages"]
		for v in obj.values():
			r = find_total_pages(v)
			if r is not None:
				return r
	elif isinstance(obj, list):
		for i in obj:
			r = find_total_pages(i)
			if r is not None:
				return r
	return None


def fetch_json(url):
	resp = requests.get(url, headers={"User-Agent": "Mozilla/5.0"}, timeout=20)
	resp.raise_for_status()
	return resp.json()


# ========== descramble ==========
def _parse_scramble(scramble_str):
	if not scramble_str:
		return None
	s = ''.join(scramble_str.split())
	if s.startswith('[') and s.endswith(']'):
		s = s[1:-1]
	return [int(x) for x in s.split(',')] if s else []


def descramble_image(src_path, scramble_str, br=4, pr=4):
	if Image is None:
		raise RuntimeError("pip install pillow")

	scramble = _parse_scramble(scramble_str)

	with Image.open(src_path) as im:
		w, h = im.size
		tw = w // br
		th = h // pr

		xr = [[c, r] for c in range(br) for r in range(pr)]
		v = [xr[i] for i in scramble]

		out = Image.new(im.mode, (w, h))
		f = 0
		for p in range(br):
			for q in range(pr):
				sc, sr = v[f]
				box = (sc * tw, sr * th, sc * tw + tw, sr * th + th)
				crop = im.crop(box)
				out.paste(crop, (p * tw, q * th))
				f += 1

		base, ext = os.path.splitext(src_path)
		out_path = base + "_descrambled" + ext
		out.save(out_path)

		# move original
		orig_dir = os.path.join(os.path.dirname(src_path), "original")
		os.makedirs(orig_dir, exist_ok=True)
		shutil.move(src_path, os.path.join(orig_dir, os.path.basename(src_path)))

		return out_path


# ========== main ==========
def main():
	p = argparse.ArgumentParser()
	p.add_argument("viewer_id", nargs="?", help="viewer-id")
	p.add_argument("--json", help="local contentsInfo.json path")
	p.add_argument("-e", "--episode", help="episode id")
	args = p.parse_args()
	viewer_id = args.viewer_id
	full = None
	out_dir = None
	base_api = "https://takecomic.jp/api/book/contentsInfo"

	# If user provided a local JSON, use it directly
	if args.json:
		local_json = args.json
		if not os.path.isfile(local_json):
			raise FileNotFoundError(f"Local JSON file not found: {local_json}")
		with open(local_json, "r", encoding="utf-8") as f:
			full = json.load(f)
		# create out dir and copy JSON there
		ts = str(int(time.time()))
		out_dir = os.path.join(os.getcwd(), ts)
		os.makedirs(out_dir, exist_ok=True)
		shutil.copy(local_json, os.path.join(out_dir, "data.json"))
		results = full.get("result", [])
		print(f"Using local JSON, processing {len(results)} images")

	else:
		viewer_id = args.viewer_id
		if not viewer_id:
			# try to obtain viewer id from episode page; if that fails, fall back to prompt for local JSON
			try:
				viewer_id = get_viewer_id(args.episode)
			except RuntimeError as e:
				if "data-comici-viewer-id not found" in str(e):
					local_json = input("viewer requires auth — local contentsInfo.json path: ").strip()
					if not os.path.isfile(local_json):
						raise FileNotFoundError(f"Local JSON file not found: {local_json}")
					with open(local_json, "r", encoding="utf-8") as f:
						full = json.load(f)
					# create out dir and copy JSON there
					ts = str(int(time.time()))
					out_dir = os.path.join(os.getcwd(), ts)
					os.makedirs(out_dir, exist_ok=True)
					shutil.copy(local_json, os.path.join(out_dir, "data.json"))
					results = full.get("result", [])
					print(f"Using local JSON, processing {len(results)} images")
				else:
					raise
		if viewer_id and full is None:
			# normal online flow: fetch pages from API
			first = fetch_json(f"{base_api}?comici-viewer-id={viewer_id}&page-from=0&page-to=0")
			total = int(find_total_pages(first)) - 1

			full = fetch_json(
				f"{base_api}?comici-viewer-id={viewer_id}&page-from=0&page-to={total}"
			)

			# create out dir and save fetched JSON
			ts = str(int(time.time()))
			out_dir = os.path.join(os.getcwd(), ts)
			os.makedirs(out_dir, exist_ok=True)

			with open(os.path.join(out_dir, "data.json"), "w", encoding="utf-8") as f:
				json.dump(full, f, ensure_ascii=False, indent=2)

			results = full.get("result", [])
			print(f"Downloaded and processing {len(results)} images")

	img_headers = {
	    "accept": "image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8",
	    "accept-language": "en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7",
	    "dnt": "1",
	    "origin": "https://takecomic.jp",
	    "referer": "https://takecomic.jp/",
	    "sec-fetch-dest": "image",
	    "sec-fetch-mode": "cors",
	    "sec-fetch-site": "same-site",
	    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/143.0.0.0 Safari/537.36",
	}

	for idx, item in enumerate(results):
		url = item.get("imageUrl")
		scramble = item.get("scramble")

		if not url:
			continue

		name = os.path.basename(urlparse(url).path)
		dst = os.path.join(out_dir, name)

		with requests.get(url, headers=img_headers, stream=True) as r:
			r.raise_for_status()
			with open(dst, "wb") as f:
				for c in r.iter_content(8192):
					f.write(c)

		print(f"DOWNLOADED: {name}")

		if scramble:
			try:
				outp = descramble_image(dst, scramble)
				print(f"DESCRAMBLED: {outp}")
			except Exception as e:
				print(f"SCRAMBLE ERROR {name}: {e}")


if __name__ == "__main__":
	main()