Created
June 15, 2025 18:02
-
-
Save moorthi07/4ce80f34eacd3473570171543aa91672 to your computer and use it in GitHub Desktop.
plugsocket scrapper
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
import os | |
import requests | |
from bs4 import BeautifulSoup | |
def bing_image_scraper(query, download_path='outlet_images', num_images=50): | |
headers = {"User-Agent": "Mozilla/5.0"} | |
query = '+'.join(query.split()) | |
url = f"https://www.bing.com/images/search?q={query}&form=HDRSC2" | |
if not os.path.exists(download_path): | |
os.makedirs(download_path) | |
response = requests.get(url, headers=headers) | |
soup = BeautifulSoup(response.text, 'html.parser') | |
img_tags = soup.find_all("img") | |
count = 0 | |
for img in img_tags: | |
if count >= num_images: | |
break | |
img_url = img.get("src") or img.get("data-src") | |
if img_url and img_url.startswith("http"): | |
try: | |
img_data = requests.get(img_url).content | |
filename = os.path.join(download_path, f"{query}_{count}.jpg") | |
with open(filename, 'wb') as f: | |
f.write(img_data) | |
count += 1 | |
except Exception as e: | |
continue | |
print(f"Downloaded {count} images to {download_path}") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment