awacke1's picture
Update app.py
4508b3b
raw
history blame
1.25 kB
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()
return {'url': url, 'response_time': end_time - start_time, 'content': response.content}
except:
return {'url': url, 'response_time': None, 'content': ""}
def main():
st.title("List of Articles on Health Care")
for url in urls:
st.write(f"Scraping {url}...")
scraped_data = scrape_wikipedia(url)
st.write(f"Response time: {scraped_data['response_time']}")
content = scraped_data['content']
if b'\r\n' not in content:
soup = BeautifulSoup(content, 'html.parser')
content = soup.prettify().encode()
st.write(f"Content: ")
st.text_area("", content.decode(), height=200, max_chars=None, key=None, help=None, return_streamlit=False, value=None, on_change=None, args=None, kwargs=None)
if __name__ == '__main__':
main()