Python RSS Reader

#!/usr/bin/env python3
import sys
import urllib.request
import xml.etree.ElementTree as ET
from html import escape
from datetime import datetime
from pathlib import Path


def fetch_rss(url: str) -> bytes:
    req = urllib.request.Request(
        url,
        headers={
            "User-Agent": (
                "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
                "AppleWebKit/537.36 (KHTML, like Gecko) "
                "Chrome/123.0.0.0 Safari/537.36"
            )
        }
    )
    with urllib.request.urlopen(req) as resp:
        return resp.read()

def parse_rss(data: bytes):
    root = ET.fromstring(data)

    # Try to handle both RSS 2.0 and Atom
    channel = root.find("channel")
    if channel is not None:  # RSS
        title = (channel.findtext("title") or "").strip()
        items = []
        for item in channel.findall("item"):
            items.append(
                {
                    "title": (item.findtext("title") or "").strip(),
                    "link": (item.findtext("link") or "").strip(),
                    "description": (item.findtext("description") or "").strip(),
                    "pubDate": (item.findtext("pubDate") or "").strip(),
                }
            )
        return title, items

    # Atom fallback
    title = (root.findtext("{http://www.w3.org/2005/Atom}title") or "").strip()
    items = []
    for entry in root.findall("{http://www.w3.org/2005/Atom}entry"):
        link_el = entry.find("{http://www.w3.org/2005/Atom}link")
        link = link_el.get("href") if link_el is not None else ""
        items.append(
            {
                "title": (entry.findtext("{http://www.w3.org/2005/Atom}title") or "").strip(),
                "link": link.strip(),
                "description": (entry.findtext("{http://www.w3.org/2005/Atom}summary") or "").strip(),
                "pubDate": (entry.findtext("{http://www.w3.org/2005/Atom}updated") or "").strip(),
            }
        )
    return title, items


def build_html(feed_title: str, items: list[dict]) -> str:
    now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
    rows = []

    for item in items:
        title = escape(item["title"]) or "(no title)"
        link = escape(item["link"])
        desc = escape(item["description"])
        pub = escape(item["pubDate"])

        row = f"""
        <article class="item">
            <h2 class="item-title">
                <a href="{link}" target="_blank" rel="noopener noreferrer">{title}</a>
            </h2>
            <p class="item-meta">{pub}</p>
            <p class="item-desc">{desc}</p>
        </article>
        """
        rows.append(row)

    items_html = "\n".join(rows)

    return f"""<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<title>{escape(feed_title or "RSS Feed")}</title>
<style>
body {{
    font-family: system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
    margin: 2rem auto;
    max-width: 800px;
    line-height: 1.5;
    color: #222;
    background: #f7f7f7;
}}
h1 {{
    margin-bottom: 0.25rem;
}}
.feed-meta {{
    color: #666;
    font-size: 0.9rem;
    margin-bottom: 1.5rem;
}}
.item {{
    background: #fff;
    padding: 1rem 1.25rem;
    margin-bottom: 1rem;
    border-radius: 6px;
    box-shadow: 0 1px 3px rgba(0,0,0,0.06);
}}
.item-title {{
    margin: 0 0 0.25rem 0;
    font-size: 1.1rem;
}}
.item-title a {{
    color: #0056b3;
    text-decoration: none;
}}
.item-title a:hover {{
    text-decoration: underline;
}}
.item-meta {{
    margin: 0 0 0.5rem 0;
    color: #777;
    font-size: 0.85rem;
}}
.item-desc {{
    margin: 0;
}}
</style>
</head>
<body>
<header>
    <h1>{escape(feed_title or "RSS Feed")}</h1>
    <p class="feed-meta">Generated at {escape(now)}</p>
</header>
<main>
{items_html}
</main>
</body>
</html>
"""


def main():
    if len(sys.argv) < 2:
        print(f"Usage: {Path(sys.argv[0]).name} <rss_or_atom_url> [output.html]", file=sys.stderr)
        sys.exit(1)

    url = sys.argv[1]
    output_path = Path(sys.argv[2]) if len(sys.argv) > 2 else Path("feed.html")

    try:
        data = fetch_rss(url)
        title, items = parse_rss(data)
        html = build_html(title, items)
        output_path.write_text(html, encoding="utf-8")
        print(f"Wrote {len(items)} items to {output_path}")
    except Exception as e:
        print(f"Error: {e}", file=sys.stderr)
        sys.exit(2)


if __name__ == "__main__":
    main()

Get Sonny Smith’s stories in your inbox

Join Medium for free to get updates from this writer.

Remember me for faster sign in

Usage:

python rss_reader.py "https://example.com/feed.xml"
# or with explicit output file
python rss_reader.py "https://example.com/feed.xml" myfeed.html