app.py

import requests
from bs4 import BeautifulSoup
import streamlit as st
import time

urls = ['https://en.wikipedia.org/wiki/Health_care',
        'https://en.wikipedia.org/wiki/Health_information_on_the_Internet',
        'https://www.who.int/health-topics/coronavirus#tab=tab_1']

def scrape_wikipedia(url):
    try:
        start_time = time.time()
        response = requests.get(url)
        end_time = time.time()
        soup = BeautifulSoup(response.content, 'html.parser')
        div_element = soup.find('div', {'class': 'div-col columns column-width'})
        if div_element is not None:
            articles_list = div_element.find_all('li')
        else:
            articles_list = []
        return {'url': url, 'response_time': end_time - start_time, 'articles': articles_list}
    except:
        return {'url': url, 'response_time': None, 'articles': []}

def main():
    st.title("List of Articles on Health Care")

    data = []
    for url in urls:
        st.write(f"Scraping {url}...")
        scraped_data = scrape_wikipedia(url)
        st.write(f"Response time: {scraped_data['response_time']}")
        for article in scraped_data['articles']:
            data.append({'url': scraped_data['url'], 'article': article.text})

    st.write('## Dataset')
    st.dataframe(data)

    st.write('## Grid')
    st.write('url', 'article')
    for d in data:
        st.write(d['url'], d['article'])

if __name__ == '__main__':
    main()