Content_Creation / tools /web_search_tools1.py
SwatGarg's picture
Rename tools/web_search_tools.py to tools/web_search_tools1.py
05de743 verified
import requests
from bs4 import BeautifulSoup
import json
import os
class WebSearchTools:
@staticmethod
def search_images(query):
search_url = f"https://www.google.com/search?q={query}&tbm=isch"
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"
}
response = requests.get(search_url, headers=headers)
soup = BeautifulSoup(response.text, "html.parser")
images = []
for item in soup.find_all('img'):
img_url = item.get('src')
if img_url and img_url.startswith('http'):
images.append(img_url)
return images[:5] # Limit to first 5 images for brevity
@staticmethod
def download_image(img_url, save_path):
img_data = requests.get(img_url).content
with open(save_path, 'wb') as handler:
handler.write(img_data)
@staticmethod
def scrape_and_summarize_website(url):
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
paragraphs = soup.find_all('p')
text = ' '.join([para.get_text() for para in paragraphs])
return text
# Example usage
if __name__ == "__main__":
image_urls = WebSearchTools.search_images("random forest")
for idx, img_url in enumerate(image_urls):
WebSearchTools.download_image(img_url, f'image_{idx}.png')