Last active
June 18, 2024 20:20
-
-
Save phoenixthrush/24236b6be758bd41474d2184615f1271 to your computer and use it in GitHub Desktop.
Python nHentai Downloader
This file contains 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
import os | |
import requests | |
from concurrent.futures import ThreadPoolExecutor, as_completed | |
from bs4 import BeautifulSoup | |
import re | |
COLORS = { | |
'pink': '\033[38;5;219m', | |
'cyan': '\033[38;5;51m', | |
'green': '\033[38;5;156m', | |
'red': '\033[38;5;196m', | |
'reset': '\033[0m', | |
'clear': '\033[H\033[2J' | |
} | |
def get_input(prompt): | |
return input(f"{prompt}{COLORS['cyan']}> {COLORS['reset']}") | |
def create_output_folder(folder_name): | |
output_path = os.path.join(os.path.expanduser("~/Downloads"), folder_name) | |
os.makedirs(output_path, exist_ok=True) | |
return output_path | |
def download_image(image_url, output_path, i): | |
try: | |
response = requests.get(image_url) | |
if response.status_code == 200 and response.content.startswith(b'\xff\xd8'): | |
image_path = os.path.join(output_path, f'{i}.jpg') | |
with open(image_path, 'wb') as image_file: | |
image_file.write(response.content) | |
return f"Image {i} downloaded." | |
except requests.RequestException as e: | |
return f"Error downloading image {i}: {e}" | |
return None | |
def download_images_concurrently(base_url, output_path): | |
with ThreadPoolExecutor(os.cpu_count() * 2) as executor: | |
futures = { | |
executor.submit(download_image, f"{base_url}/{i}.jpg", output_path, i): i | |
for i in range(1, 1000) | |
} | |
for future in as_completed(futures): | |
result = future.result() | |
if result: | |
print(f"{COLORS['green']}{result}{COLORS['reset']}", end='\r') | |
else: | |
break | |
def fetch_image_base_url(gallery_id): | |
page_url = f"https://nhentai.net/g/{gallery_id}/1" | |
try: | |
response = requests.get(page_url) | |
if response.status_code == 200: | |
soup = BeautifulSoup(response.content, 'html.parser') | |
img_tag = soup.select_one('#image-container a img') | |
if img_tag: | |
img_url = img_tag['src'] | |
match = re.match(r'https://(\w+)\.nhentai\.net/galleries/(\d+)/\d+\.jpg', img_url) | |
if match: | |
subdomain, gallery_id = match.groups() | |
return f"https://{subdomain}.nhentai.net/galleries/{gallery_id}" | |
except requests.RequestException: | |
return None | |
def main(): | |
print(COLORS['clear'], end='') | |
source = get_input(f"{COLORS['pink']}Please provide the image source for any doujin image.") | |
folder = get_input(f"{COLORS['pink']}\nWhat should the output folder be called?") | |
output_path = create_output_folder(folder) | |
base_url = fetch_image_base_url(source) | |
if base_url: | |
download_images_concurrently(base_url, output_path) | |
else: | |
print(f"{COLORS['red']}Error: Unable to fetch the base URL for images.{COLORS['reset']}") | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment