Update app.py

app.py

@@ -1,8 +1,14 @@
 import requests
 from bs4 import BeautifulSoup
 import streamlit as st
+import asyncio
+import concurrent.futures
 
-def scrape_wikipedia(url):
+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']
+
+async def scrape_wikipedia(url):
     response = requests.get(url)
     soup = BeautifulSoup(response.content, 'html.parser')
     div_element = soup.find('div', {'class': 'div-col columns column-width'})
@@ -12,12 +18,32 @@ def scrape_wikipedia(url):
         articles_list = []
     return articles_list
 
+async def scrape_urls(urls):
+    tasks = []
+    async with concurrent.futures.ThreadPoolExecutor(max_workers=len(urls)) as executor:
+        for url in urls:
+            tasks.append(asyncio.ensure_future(scrape_wikipedia(url)))
+        await asyncio.gather(*tasks)
+        return tasks
+
 def main():
-    url = 'https://en.wikipedia.org/wiki/Health_care'
-    articles_list = scrape_wikipedia(url)
-    st.write("List of articles on health care:")
-    for article in articles_list:
-        st.write(article.text)
+    st.title("List of Articles on Health Care")
+
+    loop = asyncio.get_event_loop()
+    tasks = loop.run_until_complete(scrape_urls(urls))
+
+    data = []
+    for task in tasks:
+        for article in task.result():
+            data.append({'url': task.result().index(article), '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()