Last active
August 13, 2025 01:59
-
-
Save phoenixthrush/627473e66dc2bf27117fc6a59dd8f0c8 to your computer and use it in GitHub Desktop.
Python mass downloader for baka.ms (images only) #baka.ms #Python #Scraper
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| MIT License | |
| Copyright (c) 2025 phoenixthrush | |
| Permission is hereby granted, free of charge, to any person obtaining a copy | |
| of this software and associated documentation files (the "Software"), to deal | |
| in the Software without restriction, including without limitation the rights | |
| to use, copy, modify, merge, publish, distribute, sublicense, and/or sell | |
| copies of the Software, and to permit persons to whom the Software is | |
| furnished to do so, subject to the following conditions: | |
| The above copyright notice and this permission notice shall be included in all | |
| copies or substantial portions of the Software. | |
| THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR | |
| IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, | |
| FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE | |
| AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER | |
| LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, | |
| OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE | |
| SOFTWARE. | |
| """ | |
| import re | |
| import mimetypes | |
| import pathlib | |
| import requests | |
| def fetch_gallery_links(gallery_url): | |
| response = requests.get(gallery_url) | |
| galleries = [] | |
| for href, name in re.findall(r'<a href="([^"]+)">([^<]+)</a>', response.text): | |
| if href == name and name != ".." and not name.endswith('.html'): | |
| galleries.append((name, f"https://baka.ms/galleries/{name}")) | |
| return galleries | |
| def fetch_subgallery_links(gallery_url): | |
| response = requests.get(gallery_url) | |
| subgalleries = [] | |
| for href, name in re.findall(r'<a href="([^"]+\.html)">([^<]+)</a>', response.text): | |
| subgalleries.append((name, f"{gallery_url}/{href}")) | |
| return subgalleries | |
| def fetch_subfolders(gallery_url): | |
| response = requests.get(gallery_url) | |
| subfolders = [] | |
| for href, name in re.findall(r'<a href="([^"]+)">([^<]+)</a>', response.text): | |
| if href == name and name != ".." and not name.endswith('.html') and '.' not in name: | |
| subfolders.append((name, f"{gallery_url}/{name}")) | |
| return subfolders | |
| def process_gallery_recursive(base_path, gallery_url, path_components): | |
| subgalleries = fetch_subgallery_links(gallery_url) | |
| for subgallery_name, subgallery_url in subgalleries: | |
| urls = fetch_photoservice_urls(subgallery_url) | |
| if urls: | |
| full_name = "_".join(path_components + [subgallery_name[:-5]]) | |
| links_file = pathlib.Path("links") / f"{full_name}.txt" | |
| if not links_file.exists(): | |
| links_file.write_text('\n'.join(urls), encoding='utf-8') | |
| download_images(full_name, urls) | |
| subfolders = fetch_subfolders(gallery_url) | |
| for subfolder_name, subfolder_url in subfolders: | |
| print( | |
| f" Exploring subfolder: {'/'.join(path_components + [subfolder_name])}") | |
| process_gallery_recursive( | |
| base_path, subfolder_url, path_components + [subfolder_name]) | |
| def fetch_photoservice_urls(gallery_url): | |
| # URL construction: data-idimg="abc123" -> token[::-1] = "321cba" -> https://photos.baka.ms/photoservice/uwu/pull/321cba?abc123 | |
| response = requests.get(gallery_url) | |
| return [f"https://photos.baka.ms/photoservice/uwu/pull/{token[::-1]}?{token}" | |
| for token in re.findall(r'data-idimg="([^"]+)"', response.text)] | |
| def download_images(gallery_name, urls): | |
| path_parts = gallery_name.split('_') | |
| gallery_dir = pathlib.Path("images") | |
| for part in path_parts: | |
| gallery_dir = gallery_dir / part | |
| gallery_dir.mkdir(parents=True, exist_ok=True) | |
| downloaded = 0 | |
| skipped = 0 | |
| for i, url in enumerate(urls, 1): | |
| try: | |
| # Check if file already exists first | |
| response = requests.get(url) | |
| if response.status_code == 200: | |
| content_type = response.headers.get( | |
| 'content-type', '').split(';')[0].strip() | |
| ext = mimetypes.guess_extension(content_type) or '.jpg' | |
| image_path = gallery_dir / f"{i:03d}{ext}" | |
| if image_path.exists(): | |
| print( | |
| f"\tSkipping {gallery_name}/{i:03d}{ext} (already exists)") | |
| skipped += 1 | |
| continue | |
| print(f"\tDownloading {gallery_name}/{i:03d}{ext}...") | |
| image_path.write_bytes(response.content) | |
| downloaded += 1 | |
| except: | |
| pass | |
| print(f" {gallery_name}: {downloaded} downloaded, {skipped} skipped") | |
| def main(): | |
| pathlib.Path("links").mkdir(exist_ok=True) | |
| pathlib.Path("images").mkdir(exist_ok=True) | |
| galleries = fetch_gallery_links("https://baka.ms/galleries/") | |
| # already downloaded :) | |
| galleries = [(name, url) | |
| for name, url in galleries if name != "belle_delphine"] | |
| print(f"Found {len(galleries)} galleries to process") | |
| for gallery_idx, (gallery_name, gallery_url) in enumerate(galleries, 1): | |
| print(f"[{gallery_idx}/{len(galleries)}] Processing {gallery_name}...") | |
| process_gallery_recursive(gallery_name, gallery_url, [gallery_name]) | |
| if __name__ == "__main__": | |
| main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment