Spaces:
Sleeping
Sleeping
Create news_sources.py
Browse files- news_sources.py +27 -0
news_sources.py
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import feedparser
|
| 2 |
+
import uuid
|
| 3 |
+
import json
|
| 4 |
+
|
| 5 |
+
RSS_FEEDS = [
|
| 6 |
+
"https://rss.nytimes.com/services/xml/rss/nyt/World.xml",
|
| 7 |
+
"https://www.reutersagency.com/feed/?best-topics=natural-disasters&post_type=best",
|
| 8 |
+
"https://www.aljazeera.com/xml/rss/all.xml"
|
| 9 |
+
]
|
| 10 |
+
|
| 11 |
+
def fetch_recent_articles():
|
| 12 |
+
articles = []
|
| 13 |
+
for url in RSS_FEEDS:
|
| 14 |
+
feed = feedparser.parse(url)
|
| 15 |
+
for entry in feed.entries[:5]:
|
| 16 |
+
articles.append({
|
| 17 |
+
"id": str(uuid.uuid4()),
|
| 18 |
+
"title": entry.title,
|
| 19 |
+
"content": entry.get("summary", "No summary available.")
|
| 20 |
+
})
|
| 21 |
+
return articles
|
| 22 |
+
|
| 23 |
+
# Save articles for embedding
|
| 24 |
+
if __name__ == "__main__":
|
| 25 |
+
data = fetch_recent_articles()
|
| 26 |
+
with open("sample_articles.json", "w") as f:
|
| 27 |
+
json.dump(data, f, indent=2)
|