Add news fetcher for today's headlines via RSS

.gitignore

@@ -0,0 +1,2 @@
+__pycache__/
+*.pyc

news_fetcher.py

@@ -0,0 +1,116 @@
+"""Fetch today's news headlines from public RSS feeds."""
+
+import urllib.request
+import xml.etree.ElementTree as ET
+from datetime import datetime, timezone
+
+
+# Public RSS feed sources
+RSS_FEEDS = {
+    "BBC News": "https://feeds.bbci.co.uk/news/rss.xml",
+    "CNN": "http://rss.cnn.com/rss/edition.rss",
+    "Reuters": "https://feeds.reuters.com/reuters/topNews",
+}
+
+DEFAULT_TIMEOUT = 10  # seconds
+
+
+def fetch_rss(url, timeout=DEFAULT_TIMEOUT):
+    """Fetch and parse an RSS feed from the given URL.
+
+    Args:
+        url: The RSS feed URL.
+        timeout: Request timeout in seconds.
+
+    Returns:
+        A list of dicts with keys 'title', 'link', and 'published'.
+    """
+    req = urllib.request.Request(
+        url,
+        headers={"User-Agent": "NewsFetcher/1.0"},
+    )
+    with urllib.request.urlopen(req, timeout=timeout) as response:
+        data = response.read()
+
+    return parse_rss_xml(data)
+
+
+def parse_rss_xml(xml_bytes):
+    """Parse RSS XML bytes into a list of article dicts.
+
+    Args:
+        xml_bytes: Raw XML content as bytes.
+
+    Returns:
+        A list of dicts with keys 'title', 'link', and 'published'.
+    """
+    root = ET.fromstring(xml_bytes)
+    items = root.findall(".//item")
+
+    articles = []
+    for item in items:
+        title_el = item.find("title")
+        link_el = item.find("link")
+        pub_date_el = item.find("pubDate")
+
+        articles.append({
+            "title": title_el.text.strip() if title_el is not None and title_el.text else "",
+            "link": link_el.text.strip() if link_el is not None and link_el.text else "",
+            "published": pub_date_el.text.strip() if pub_date_el is not None and pub_date_el.text else "",
+        })
+
+    return articles
+
+
+def fetch_news(sources=None, max_items=5):
+    """Fetch top news headlines from multiple RSS sources.
+
+    Args:
+        sources: A dict mapping source names to RSS URLs.
+                 Defaults to RSS_FEEDS.
+        max_items: Maximum number of headlines per source.
+
+    Returns:
+        A dict mapping source names to lists of article dicts.
+    """
+    if sources is None:
+        sources = RSS_FEEDS
+
+    all_news = {}
+    for name, url in sources.items():
+        try:
+            articles = fetch_rss(url)
+            all_news[name] = articles[:max_items]
+        except Exception as exc:
+            all_news[name] = [{"title": f"Error fetching feed: {exc}", "link": "", "published": ""}]
+
+    return all_news
+
+
+def display_news(news):
+    """Print news headlines to the console.
+
+    Args:
+        news: A dict mapping source names to lists of article dicts.
+    """
+    today = datetime.now(timezone.utc).strftime("%Y-%m-%d")
+    print(f"\n{'='*60}")
+    print(f"  Today's News Headlines — {today}")
+    print(f"{'='*60}\n")
+
+    for source, articles in news.items():
+        print(f"📰 {source}")
+        print(f"{'-'*40}")
+        for i, article in enumerate(articles, 1):
+            print(f"  {i}. {article['title']}")
+            if article["link"]:
+                print(f"     🔗 {article['link']}")
+            if article["published"]:
+                print(f"     📅 {article['published']}")
+        print()
+
+
+if __name__ == "__main__":
+    print("Fetching today's news...")
+    news = fetch_news()
+    display_news(news)

test_news_fetcher.py

@@ -0,0 +1,82 @@
+"""Tests for news_fetcher module."""
+
+import unittest
+from news_fetcher import parse_rss_xml, display_news
+
+
+SAMPLE_RSS = b"""\
+<?xml version="1.0" encoding="UTF-8"?>
+<rss version="2.0">
+  <channel>
+    <title>Sample News</title>
+    <item>
+      <title>First headline</title>
+      <link>https://example.com/1</link>
+      <pubDate>Mon, 10 Feb 2026 00:00:00 GMT</pubDate>
+    </item>
+    <item>
+      <title>Second headline</title>
+      <link>https://example.com/2</link>
+      <pubDate>Mon, 10 Feb 2026 01:00:00 GMT</pubDate>
+    </item>
+  </channel>
+</rss>
+"""
+
+
+class TestParseRssXml(unittest.TestCase):
+    """Tests for the parse_rss_xml helper."""
+
+    def test_parses_titles(self):
+        articles = parse_rss_xml(SAMPLE_RSS)
+        self.assertEqual(len(articles), 2)
+        self.assertEqual(articles[0]["title"], "First headline")
+        self.assertEqual(articles[1]["title"], "Second headline")
+
+    def test_parses_links(self):
+        articles = parse_rss_xml(SAMPLE_RSS)
+        self.assertEqual(articles[0]["link"], "https://example.com/1")
+
+    def test_parses_pub_date(self):
+        articles = parse_rss_xml(SAMPLE_RSS)
+        self.assertEqual(articles[0]["published"], "Mon, 10 Feb 2026 00:00:00 GMT")
+
+    def test_empty_feed(self):
+        empty_rss = b"""\
+<?xml version="1.0" encoding="UTF-8"?>
+<rss version="2.0"><channel><title>Empty</title></channel></rss>
+"""
+        articles = parse_rss_xml(empty_rss)
+        self.assertEqual(articles, [])
+
+    def test_missing_optional_elements(self):
+        rss_no_link = b"""\
+<?xml version="1.0" encoding="UTF-8"?>
+<rss version="2.0">
+  <channel>
+    <item><title>Only title</title></item>
+  </channel>
+</rss>
+"""
+        articles = parse_rss_xml(rss_no_link)
+        self.assertEqual(len(articles), 1)
+        self.assertEqual(articles[0]["title"], "Only title")
+        self.assertEqual(articles[0]["link"], "")
+        self.assertEqual(articles[0]["published"], "")
+
+
+class TestDisplayNews(unittest.TestCase):
+    """Tests for the display_news function (smoke test)."""
+
+    def test_display_does_not_raise(self):
+        news = {
+            "Test Source": [
+                {"title": "Headline", "link": "https://example.com", "published": "today"},
+            ]
+        }
+        # Should not raise
+        display_news(news)
+
+
+if __name__ == "__main__":
+    unittest.main()