news-reader-actions-test/services/rssService.ts

import { v4 as uuidv4 } from 'uuid';
import { RSSFeed, RSSArticle } from '../types';
import { saveRSSFeed, updateRSSFeedLastFetched } from './storageService';

// CORS proxy for RSS feeds
const RSS_PROXY = (url: string) => `https://api.allorigins.win/raw?url=${encodeURIComponent(url)}`;

/**
 * Parse RSS/Atom feed XML into articles
 */
const parseRSSFeed = (xml: string, feedId: string): RSSArticle[] => {
  const parser = new DOMParser();
  const doc = parser.parseFromString(xml, 'text/xml');

  const articles: RSSArticle[] = [];

  // Try RSS 2.0 format
  const items = doc.querySelectorAll('item');
  if (items.length > 0) {
    items.forEach(item => {
      const title = item.querySelector('title')?.textContent || '';
      const link = item.querySelector('link')?.textContent || '';
      const description = item.querySelector('description')?.textContent || '';
      const pubDate = item.querySelector('pubDate')?.textContent || '';

      if (title && link) {
        articles.push({
          title: title.trim(),
          url: link.trim(),
          description: description.replace(/<[^>]*>/g, '').substring(0, 200),
          pubDate,
          feedId
        });
      }
    });
    return articles;
  }

  // Try Atom format
  const entries = doc.querySelectorAll('entry');
  entries.forEach(entry => {
    const title = entry.querySelector('title')?.textContent || '';
    const link = entry.querySelector('link')?.getAttribute('href') || '';
    const summary = entry.querySelector('summary')?.textContent || '';
    const published = entry.querySelector('published')?.textContent || '';

    if (title && link) {
      articles.push({
        title: title.trim(),
        url: link.trim(),
        description: summary.replace(/<[^>]*>/g, '').substring(0, 200),
        pubDate: published,
        feedId
      });
    }
  });

  return articles;
};

/**
 * Get feed title from XML
 */
const getFeedTitle = (xml: string): string => {
  const parser = new DOMParser();
  const doc = parser.parseFromString(xml, 'text/xml');

  // RSS 2.0
  const channelTitle = doc.querySelector('channel > title')?.textContent;
  if (channelTitle) return channelTitle.trim();

  // Atom
  const feedTitle = doc.querySelector('feed > title')?.textContent;
  if (feedTitle) return feedTitle.trim();

  return 'Unknown Feed';
};

/**
 * Fetch and parse RSS feed
 */
export const fetchRSSFeed = async (feedUrl: string): Promise<{
  feed: RSSFeed;
  articles: RSSArticle[];
}> => {
  const response = await fetch(RSS_PROXY(feedUrl));
  if (!response.ok) {
    throw new Error(`Failed to fetch feed: ${response.status}`);
  }

  const xml = await response.text();
  const feedId = uuidv4();
  const title = getFeedTitle(xml);
  const articles = parseRSSFeed(xml, feedId);

  const feed: RSSFeed = {
    id: feedId,
    url: feedUrl,
    title,
    articleCount: articles.length,
    lastFetched: Date.now(),
    isActive: true,
    addedAt: Date.now()
  };

  return { feed, articles };
};

/**
 * Refresh articles from an existing feed
 */
export const refreshFeed = async (feed: RSSFeed): Promise<RSSArticle[]> => {
  const response = await fetch(RSS_PROXY(feed.url));
  if (!response.ok) {
    throw new Error(`Failed to refresh feed: ${response.status}`);
  }

  const xml = await response.text();
  const articles = parseRSSFeed(xml, feed.id);

  updateRSSFeedLastFetched(feed.id);

  return articles;
};

/**
 * Validate RSS feed URL
 */
export const validateRSSUrl = async (url: string): Promise<boolean> => {
  try {
    const response = await fetch(RSS_PROXY(url));
    if (!response.ok) return false;

    const text = await response.text();
    // Check if it looks like RSS/Atom
    return text.includes('<rss') || text.includes('<feed') || text.includes('<channel');
  } catch {
    return false;
  }
};

// Popular RSS feed suggestions organized by category
export const SUGGESTED_FEEDS = [
  // General News
  { name: 'BBC News', url: 'https://feeds.bbci.co.uk/news/rss.xml', category: 'news' },
  { name: 'NPR News', url: 'https://feeds.npr.org/1001/rss.xml', category: 'news' },
  { name: 'Reuters', url: 'https://www.reutersagency.com/feed/', category: 'news' },
  { name: 'The Guardian', url: 'https://www.theguardian.com/world/rss', category: 'news' },
  { name: 'Associated Press', url: 'https://feeds.apnews.com/rss/topnews', category: 'news' },
  { name: 'CNN World', url: 'http://rss.cnn.com/rss/cnn_world.rss', category: 'news' },
  { name: 'Al Jazeera', url: 'https://www.aljazeera.com/xml/rss/all.xml', category: 'news' },
  { name: 'The New York Times', url: 'https://rss.nytimes.com/services/xml/rss/nyt/HomePage.xml', category: 'news' },
  { name: 'Washington Post', url: 'https://feeds.washingtonpost.com/rss/world', category: 'news' },

  // Technology
  { name: 'TechCrunch', url: 'https://techcrunch.com/feed/', category: 'tech' },
  { name: 'Hacker News', url: 'https://hnrss.org/frontpage', category: 'tech' },
  { name: 'Ars Technica', url: 'https://feeds.arstechnica.com/arstechnica/index', category: 'tech' },
  { name: 'The Verge', url: 'https://www.theverge.com/rss/index.xml', category: 'tech' },
  { name: 'Wired', url: 'https://www.wired.com/feed/rss', category: 'tech' },
  { name: 'MIT Technology Review', url: 'https://www.technologyreview.com/feed/', category: 'tech' },
  { name: 'Engadget', url: 'https://www.engadget.com/rss.xml', category: 'tech' },
  { name: 'ZDNet', url: 'https://www.zdnet.com/news/rss.xml', category: 'tech' },

  // Business & Finance
  { name: 'Financial Times', url: 'https://www.ft.com/?format=rss', category: 'business' },
  { name: 'Bloomberg', url: 'https://feeds.bloomberg.com/markets/news.rss', category: 'business' },
  { name: 'The Economist', url: 'https://www.economist.com/finance-and-economics/rss.xml', category: 'business' },
  { name: 'Forbes', url: 'https://www.forbes.com/real-time/feed2/', category: 'business' },
  { name: 'MarketWatch', url: 'https://feeds.marketwatch.com/marketwatch/topstories/', category: 'business' },

  // Science
  { name: 'Nature News', url: 'https://www.nature.com/nature.rss', category: 'science' },
  { name: 'Scientific American', url: 'https://www.scientificamerican.com/feed/', category: 'science' },
  { name: 'ScienceDaily', url: 'https://www.sciencedaily.com/rss/all.xml', category: 'science' },
  { name: 'Phys.org', url: 'https://phys.org/rss-feed/', category: 'science' },
  { name: 'Space.com', url: 'https://www.space.com/feeds/all', category: 'science' },

  // International
  { name: 'The Japan Times', url: 'https://www.japantimes.co.jp/feed/', category: 'international' },
  { name: 'South China Morning Post', url: 'https://www.scmp.com/rss/91/feed', category: 'international' },
  { name: 'Deutsche Welle', url: 'https://rss.dw.com/rdf/rss-en-all', category: 'international' },
  { name: 'France 24', url: 'https://www.france24.com/en/rss', category: 'international' }
];