import os

from icrawler.builtin import BingImageCrawler, BaiduImageCrawler

from bs4 import BeautifulSoup

import requests

import sys

def download_images(image_urls, folder_path):

print(f"Could not download {url}: {e}")

# Read command line arguments

if len(sys.argv) < 3:

print("Usage: python main.py <nb_of_images_per_source> <request>")

sys.exit(1)

count = int(sys.argv[1])

keyword = ' '.join(sys.argv[2:])

# Create directories to store the images

if not os.path.exists(keyword):

os.makedirs(keyword)

# Bing Image Crawler

bing_crawler = BingImageCrawler(downloader_threads=4, storage={'root_dir': f"{keyword}/bing"})

bing_crawler.crawl(keyword=keyword, max_num=count)

# Baidu Image Crawler with error handling

try:

baidu_crawler = BaiduImageCrawler(downloader_threads=4, storage={'root_dir': f"{keyword}/baidu"})

baidu_crawler.crawl(keyword=keyword, max_num=count)

except KeyError as e:

print(f"Error with Baidu Crawler: {e}")

# Google scraper

query = keyword

url = f"https://www.google.com/search?q={query}&tbm=isch"

response = requests.get(url)

soup = BeautifulSoup(response.text, "html.parser")

images = soup.find_all("img")

image_urls = []

for img in images:

try:

if img['src'].startswith('http'):

image_urls.append(img['src'])

except KeyError:

continue

# Download images from Google

max_images = count # Set max_images to count value from arguments

download_images(image_urls, f"{keyword}/google")

print("Image scraping completed.")