#!/usr/bin/env python3 import os import time import sys import requests import json import re from lxml import etree def usage(): print("mangawindow.py command") print("commands:") print(" download") print(" list") exit(1) def usage_list(): print("mangawindow.py list ") exit(1) def usage_download(): print("mangawindow.py download ") print("examples:") print(" mangawindow.py download \"https://mangawindow.net/chapter/1430298\" /home/adam/Manga/MangaName") print("") print("Note: The manga directory has to exist.") exit(1) if len(sys.argv) < 2: usage() def download_file(url, save_path): with requests.get(url, stream=True) as response: response.raise_for_status() with open(save_path, "wb") as file: for chunk in response.iter_content(chunk_size=8192): if chunk: file.write(chunk) def list_chapters(url, chapter_list_input): response = requests.get(url) if response.status_code != 200: print("Failed to list chapters, server responded with status code %d" % response.status_code) exit(2) seen_titles = set() for item in chapter_list_input: title = item.get("title") if title and len(title) > 0: seen_titles.add(title.lower().replace(" ", "")) seen_urls = set() for item in chapter_list_input: url = item.get("url") if url and len(url) > 0: seen_urls.add(url) tree = etree.HTML(response.text) chapters = [] for element in tree.xpath("//a[@class='chapt']"): title = element.findtext('b') if title is None: print("Failed to get title for chapter") exit(2) title = title.strip() url = "https://mangawindow.net" + element.attrib.get("href").strip() if title.lower().replace(" ", "") in seen_titles or url in seen_urls: break chapters.append({ "name": title, "url": url }) print(json.dumps(chapters)) def download_chapter(url, download_dir): response = requests.get(url) if response.status_code != 200: print("Failed to list chapter images, server responded with status code %d" % response.status_code) exit(2) in_progress_filepath = os.path.join(download_dir, ".in_progress") with open(in_progress_filepath, "w") as file: file.write(url) img_number = 1 image_urls = re.findall(r'mangawindow\.net/images[^"]+', response.text) for image_url in image_urls: image_url = "https://z-img-04." + image_url ext = image_url[image_url.rfind("."):] image_name = str(img_number) + ext image_path = os.path.join(download_dir, image_name) print("Downloading {} to {}".format(image_url, image_path)) download_file(image_url, image_path) img_number += 1 if img_number == 1: print("Failed to find images for chapter") exit(2) with open(os.path.join(download_dir, ".finished"), "w") as file: file.write("1") os.remove(in_progress_filepath) command = sys.argv[1] if command == "list": if len(sys.argv) < 3: usage_list() url = sys.argv[2] chapter_list_input = sys.stdin.read() if len(chapter_list_input) == 0: chapter_list_input = [] else: chapter_list_input = json.loads(chapter_list_input) list_chapters(url, chapter_list_input) elif command == "download": if len(sys.argv) < 4: usage_download() url = sys.argv[2] download_dir = sys.argv[3] download_chapter(url, download_dir) else: usage()