app.py

import gradio as gr
from googlesearch import search
from bs4 import BeautifulSoup
import requests


def google_search(query, num_results=5):
    search_results = search(query, num_results=num_results)
    return search_results

def scrape_text_from_url(url):
    try:
        response = requests.get(url)
        soup = BeautifulSoup(response.text, 'html.parser')

        # Remove specific elements (customize as needed)
        unwanted_elements = ['footer', 'script', 'style', 'noscript']
        for tag in unwanted_elements:
            for el in soup.find_all(tag):
                el.extract()

        # Extract text from remaining paragraphs
        text = ' '.join([p.text for p in soup.find_all('p')])

        return text.strip()  # Strip leading and trailing whitespaces
    except Exception as e:
        print(f"Error scraping {url}: {e}")
        return None
    
def get_google_data(search_term):
    whole_result = ''
    search_results = google_search(search_term)
    for i, result in enumerate(search_results, start=1):
        text = scrape_text_from_url(result)
        if text:
            whole_result += text
    
    return whole_result


iface = gr.Interface(fn=get_google_data, inputs="text", outputs="text")

iface.launch(share=True)