#!/usr/bin/env python3 import os import time import sys import requests import json from lxml import etree headers = { 'User-Agent': "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36", 'x-requested-with': 'XMLHttpRequest' } def usage(): print("lhtranslation.py command") print("commands:") print(" download") print(" list") exit(1) def usage_list(): print("lhtranslation.py list ") exit(1) def usage_download(): print("lhtranslation.py download ") print("examples:") print(" lhtranslation.py download \"https://lhtranslation.net/manga/kaifuku-jutsushi-no-yarinaoshi/\" /home/user/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, headers=headers, stream=True) as response: if not response.ok: return False with open(save_path, "wb") as file: for chunk in response.iter_content(chunk_size=8192): if chunk: file.write(chunk) return True def list_chapters(url, chapter_list_input): url = url.rstrip('/') response = requests.post(url + "/ajax/chapters/", headers=headers) response.raise_for_status() 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(" ", "").replace("/", "_")) seen_urls = set() for item in chapter_list_input: chapter_url = item.get("url") if chapter_url and len(chapter_url) > 0: seen_urls.add(chapter_url) tree = etree.HTML(response.text) chapters = [] for element in tree.xpath("//a[contains(@href, '/manga/')]"): title = element.text.strip().replace("/", "_") url = "https://lhtranslation.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, headers=headers) response.raise_for_status() in_progress_filepath = os.path.join(download_dir, ".in_progress") with open(in_progress_filepath, "w") as file: file.write(url) tree = etree.HTML(response.text) img_number = 1 for image_source in tree.xpath("//div[@class='reading-content']//img[contains(@data-src, '/uploads/')]/@data-src"): image_source = image_source.strip() ext = image_source[image_source.rfind("."):] image_name = str(img_number) + ext image_path = os.path.join(download_dir, image_name) print("Downloading {} to {}".format(image_source, image_path)) if not download_file(image_source, image_path): print("Failed to download image: %s" % image_source) os.remove(in_progress_filepath) exit(2) img_number += 1 if img_number == 1: print("Failed to find images for chapter") os.remove(in_progress_filepath) 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()