Dmitry Sergeev
139 lines
4.4 KiB
Python
139 lines
4.4 KiB
Python
from bs4 import BeautifulSoup
|
|
import os
|
|
import requests
|
|
from time import sleep
|
|
from urllib.parse import urlparse, urljoin
|
|
import sys
|
|
|
|
def download_comic(url, download_dir):
|
|
"""Download a comic and return the previous comic URL"""
|
|
if not url:
|
|
return None
|
|
|
|
try:
|
|
# Fetch the page
|
|
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
|
|
response = requests.get(url, headers=headers, timeout=15)
|
|
response.raise_for_status()
|
|
html_text = response.text
|
|
except requests.RequestException as e:
|
|
print(f"❌ Error fetching {url}: {e}")
|
|
return None
|
|
|
|
soup = BeautifulSoup(html_text, "html.parser")
|
|
|
|
# Get previous comic URL
|
|
prev_link = soup.find("a", class_="previous-comic", href=True)
|
|
if prev_link is None:
|
|
print("⚠️ No previous comic link found (might be the first comic)")
|
|
return None
|
|
|
|
prev_url = prev_link["href"]
|
|
# Make absolute URL if needed
|
|
if not prev_url.startswith('http'):
|
|
prev_url = urljoin(url, prev_url)
|
|
print(f"🔗 Previous: {prev_url}")
|
|
|
|
# Find comic image in spliced-comic div
|
|
comic_div = soup.find("div", {"id": "spliced-comic"})
|
|
if comic_div is None:
|
|
print("❌ Can't find div#spliced-comic")
|
|
return prev_url
|
|
|
|
img_tag = comic_div.find("img")
|
|
if img_tag is None:
|
|
print("❌ No img tag found in div#spliced-comic")
|
|
return prev_url
|
|
|
|
img_url = img_tag.get("src") or img_tag.get("data-src")
|
|
if not img_url:
|
|
print("❌ No src or data-src attribute found")
|
|
return prev_url
|
|
|
|
# Make absolute URL
|
|
if not img_url.startswith('http'):
|
|
img_url = urljoin(url, img_url)
|
|
|
|
print(f"🖼️ Image: {img_url}")
|
|
|
|
# Download the image
|
|
try:
|
|
img_data = requests.get(img_url, headers=headers, timeout=30)
|
|
img_data.raise_for_status()
|
|
except requests.RequestException as e:
|
|
print(f"❌ Failed to download image: {e}")
|
|
return prev_url
|
|
|
|
# Create download directory if it doesn't exist
|
|
os.makedirs(download_dir, exist_ok=True)
|
|
|
|
# Get filename from URL
|
|
parsed_url = urlparse(img_url)
|
|
filename = os.path.basename(parsed_url.path)
|
|
|
|
# If filename is empty or has no extension, create one
|
|
if not filename or '.' not in filename:
|
|
filename = f"comic_{len(os.listdir(download_dir)) + 1:03d}.jpg"
|
|
|
|
# Save the file
|
|
filepath = os.path.join(download_dir, filename)
|
|
|
|
# Check if file already exists
|
|
if os.path.exists(filepath):
|
|
print(f"⏭️ {filename} already exists, skipping")
|
|
return prev_url
|
|
|
|
try:
|
|
with open(filepath, "wb") as handler:
|
|
handler.write(img_data.content)
|
|
print(f"✅ {filename} downloaded ({len(img_data.content)} bytes)")
|
|
except IOError as e:
|
|
print(f"❌ Failed to save {filename}: {e}")
|
|
return prev_url
|
|
|
|
return prev_url
|
|
|
|
def main():
|
|
print("╔═══════════════════════════════════╗")
|
|
print("║ StoneToss Comic Downloader ║")
|
|
print("╚═══════════════════════════════════╝")
|
|
print()
|
|
|
|
url = "https://stonetoss.com/"
|
|
download_dir = "comic"
|
|
max_comics = 50
|
|
downloaded = 0
|
|
|
|
print(f"📚 Downloading up to {max_comics} comics...")
|
|
print()
|
|
|
|
for i in range(max_comics):
|
|
print(f"[{i+1}/{max_comics}] Processing...")
|
|
|
|
# Download the comic and get the previous URL
|
|
prev_url = download_comic(url, download_dir)
|
|
|
|
if prev_url is None:
|
|
print("🏁 Reached the first comic or encountered an error")
|
|
break
|
|
|
|
downloaded += 1
|
|
url = prev_url
|
|
sleep(1) # Be nice to the server
|
|
|
|
print()
|
|
print("╔═══════════════════════════════════╗")
|
|
print(f"║ ✅ Downloaded {downloaded} comics ║")
|
|
print(f"║ 📁 Saved to: ./{download_dir}/ ║")
|
|
print("╚═══════════════════════════════════╝")
|
|
|
|
if __name__ == "__main__":
|
|
try:
|
|
main()
|
|
except KeyboardInterrupt:
|
|
print("\n⏹️ Interrupted by user")
|
|
sys.exit(0)
|
|
except Exception as e:
|
|
print(f"\n❌ Unexpected error: {e}")
|
|
sys.exit(1)
|