Spaces:
Paused
Paused
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,11 +1,19 @@
|
|
| 1 |
import streamlit as st
|
| 2 |
import feedparser
|
|
|
|
| 3 |
|
| 4 |
# Function to fetch and parse RSS feed
|
| 5 |
def fetch_rss_feed(url):
|
| 6 |
feed = feedparser.parse(url)
|
| 7 |
return feed.entries
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
# RSS feed URL
|
| 10 |
rss_url = "https://feeds.feedburner.com/ndtvnews-top-stories"
|
| 11 |
|
|
@@ -17,5 +25,23 @@ st.title("NDTV Top Stories")
|
|
| 17 |
|
| 18 |
for entry in entries:
|
| 19 |
st.subheader(entry.title)
|
| 20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
st.write(f"[Read more]({entry.link})")
|
|
|
|
| 1 |
import streamlit as st
|
| 2 |
import feedparser
|
| 3 |
+
from bs4 import BeautifulSoup
|
| 4 |
|
| 5 |
# Function to fetch and parse RSS feed
|
| 6 |
def fetch_rss_feed(url):
|
| 7 |
feed = feedparser.parse(url)
|
| 8 |
return feed.entries
|
| 9 |
|
| 10 |
+
# Function to extract images and text from HTML content
|
| 11 |
+
def extract_images_and_text(html_content):
|
| 12 |
+
soup = BeautifulSoup(html_content, 'html.parser')
|
| 13 |
+
images = [img['src'] for img in soup.find_all('img')]
|
| 14 |
+
text = soup.get_text()
|
| 15 |
+
return images, text
|
| 16 |
+
|
| 17 |
# RSS feed URL
|
| 18 |
rss_url = "https://feeds.feedburner.com/ndtvnews-top-stories"
|
| 19 |
|
|
|
|
| 25 |
|
| 26 |
for entry in entries:
|
| 27 |
st.subheader(entry.title)
|
| 28 |
+
|
| 29 |
+
# Display publication date
|
| 30 |
+
st.write(f"Published on: {entry.published}")
|
| 31 |
+
|
| 32 |
+
# Check for media content
|
| 33 |
+
media_content = entry.get('media_content', [])
|
| 34 |
+
if media_content:
|
| 35 |
+
for media in media_content:
|
| 36 |
+
if media.get('url'):
|
| 37 |
+
st.image(media['url'], width=600) # Display image
|
| 38 |
+
|
| 39 |
+
# Use BeautifulSoup to parse HTML content
|
| 40 |
+
content_encoded = entry.get('content_encoded', entry.description)
|
| 41 |
+
images, text = extract_images_and_text(content_encoded)
|
| 42 |
+
st.write(text) # Display plain text
|
| 43 |
+
|
| 44 |
+
for img_url in images:
|
| 45 |
+
st.image(img_url, width=600) # Display images if any
|
| 46 |
+
|
| 47 |
st.write(f"[Read more]({entry.link})")
|