hitomi.la gallery download code

download_gallery_from_hitomi.py

import requests
import struct
import json
import re
import ast
import os


def get_subdomain_from_gallery_id(gallery_id):
    return chr(97 + gallery_id % 3)


def hash_to_url(image_hash):
    if len(image_hash) < 3:
        return image_hash

    return '{}/{}/{}'.format(image_hash[-1], image_hash[-3:-1], image_hash)


def convert_gallery_info_to_image_url(gallery_id, gallery_info):
    if gallery_info['haswebp'] == 1:
        return 'https://{}a.hitomi.la/webp/{}/{}.webp'.format(get_subdomain_from_gallery_id(int(str(gallery_id)[-1])), gallery_id, gallery_info['name'])
    else:
        return 'https://{}a.hitomi.la/images/{}.{}'.format(get_subdomain_from_gallery_id(int(gallery_info['hash'][-3:-1], 16)), hash_to_url(gallery_info['hash']), gallery_info['name'].split('.', maxsplit=1)[1])


def get_gallery_info(gallery_id):
    js_gallery_info_list = requests.get('https://ltn.hitomi.la/galleries/{}.js'.format(gallery_id)).text
    python_gallery_info_list = re.search(r'\[[\s\S]+]', js_gallery_info_list).group(0)
    return ast.literal_eval(python_gallery_info_list)


def get_image_url_list(gallery_id, gallery_info):
    return list([convert_gallery_info_to_image_url(gallery_id, gallery_info) for gallery_info in gallery_info])


def download_image_all(gallery_id, gallery_info, image_url_list):
    if not os.path.exists(str(gallery_id)):
        os.mkdir(str(gallery_id))

    for index in range(len(gallery_info)):
        with open('{}/{}'.format(gallery_id, gallery_info[index]['name']), 'wb') as file:
            file.write(requests.get(image_url_list[index], headers={
                'authority': image_url_list[index],
                'accept': 'image/webp,image/apng,image/*,*/*;q=0.8',
                'accept-encoding': 'gzip, deflate, br',
                'accept-language': 'ko-KR,ko;q=0.9,en-US;q=0.8,en;q=0.7,und;q=0.6,ja;q=0.5',
                'referer': 'https://hitomi.la/reader/{}.html'.format(gallery_id)
            }).content)


# Below codes demonstrates how to fetch all available gallery ids.

# binary = requests.get('https://ltn.hitomi.la/index-all.nozomi').content
# gallery_count = len(binary) // 4
# print(gallery_count)
# gallery_id_list = struct.unpack('>{}I'.format(gallery_count), binary)
# print(gallery_id_list)

gallery_id = GALLERY_ID_HERE

gallery_info = get_gallery_info(gallery_id)
image_url_list = get_image_url_list(gallery_id, gallery_info)
download_image_all(gallery_id, gallery_info, image_url_list)