Python3.12 Version
import requests
from bs4 import BeautifulSoup
import os
from urllib.parse import urljoin, urlparse
import asyncio
import aiohttp
import aiofiles
async def download_image(session, url, folder):
"""Download a single image asynchronously"""
# Create a valid filename from the URL
filename = os.path.join(folder, os.path.basename(urlparse(url).path))
# Skip if file exists
if os.path.exists(filename):
print(f"Skipping existing file: {filename}")
return
try:
async with session.get(url) as response:
if response.status == 200:
# Ensure the filename has an extension
if not os.path.splitext(filename)[1]:
content_type = response.headers.get('Content-Type', '')
if 'jpeg' in content_type or 'jpg' in content_type:
filename += '.jpg'
elif 'png' in content_type:
filename += '.png'
elif 'gif' in content_type:
filename += '.gif'
elif 'webp' in content_type:
filename += '.webp'
else:
filename += '.jpg' # Default extension
# Save the image
async with aiofiles.open(filename, 'wb') as f:
await f.write(await response.read())
print(f"Downloaded: {filename}")
else:
print(f"Failed to download {url}, status code: {response.status}")
except Exception as e:
print(f"Error downloading {url}: {e}")
async def download_images_from_website(url, folder="downloaded_images"):
"""Download all images from a website"""
# Create the download folder if it doesn't exist
os.makedirs(folder, exist_ok=True)
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
}
# Get the webpage content
response = requests.get(url, headers=headers)
if response.status_code != 200:
print(f"Failed to access {url}")
return
# Parse HTML content
soup = BeautifulSoup(response.text, 'html.parser')
# Find all image tags
img_tags = soup.find_all('img')
img_urls = []
# Extract image URLs
for img in img_tags:
img_url = img.get('src')
if img_url:
# Convert relative URLs to absolute URLs
img_url = urljoin(url, img_url)
img_urls.append(img_url)
print(f"Found {len(img_urls)} images")
# Download images concurrently
async with aiohttp.ClientSession(headers=headers) as session:
tasks = [download_image(session, img_url, folder) for img_url in img_urls]
await asyncio.gather(*tasks)
if __name__ == "__main__":
website_url = input("Enter the website URL: ")
output_folder = input("Enter output folder (default: downloaded_images): ") or "downloaded_images"
# Run the async function
asyncio.run(download_images_from_website(website_url, output_folder))
print("Download complete!")
This Script Notes:
- Uses
requestsandBeautifulSoupto fetch and parse the webpage - Finds all
<img>tags and extracts their URLs - Uses
aiohttpandasynciofor concurrent downloads (much faster than sequential) - Creates filenames based on the image URL paths
- Adds appropriate file extensions based on Content-Type
- Skips already downloaded files
